diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 7befba8fceb2510728d52d70edf9318243bfc641..b55bb30817659eded19426d294b47a84b934ebfe 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -9185,25 +9185,6 @@ static int do_quick_linkup(struct hfi1_devdata *dd)
 	return 0; /* success */
 }
 
-/*
- * Set the SerDes to internal loopback mode.
- * Returns 0 on success, -errno on error.
- */
-static int set_serdes_loopback_mode(struct hfi1_devdata *dd)
-{
-	int ret;
-
-	ret = set_physical_link_state(dd, PLS_INTERNAL_SERDES_LOOPBACK);
-	if (ret == HCMD_SUCCESS)
-		return 0;
-	dd_dev_err(dd,
-		   "Set physical link state to SerDes Loopback failed with return %d\n",
-		   ret);
-	if (ret >= 0)
-		ret = -EINVAL;
-	return ret;
-}
-
 /*
  * Do all special steps to set up loopback.
  */
@@ -9229,13 +9210,11 @@ static int init_loopback(struct hfi1_devdata *dd)
 		return 0;
 	}
 
-	/* handle serdes loopback */
-	if (loopback == LOOPBACK_SERDES) {
-		/* internal serdes loopack needs quick linkup on RTL */
-		if (dd->icode == ICODE_RTL_SILICON)
-			quick_linkup = 1;
-		return set_serdes_loopback_mode(dd);
-	}
+	/*
+	 * SerDes loopback init sequence is handled in set_local_link_attributes
+	 */
+	if (loopback == LOOPBACK_SERDES)
+		return 0;
 
 	/* LCB loopback - handled at poll time */
 	if (loopback == LOOPBACK_LCB) {
@@ -9294,7 +9273,7 @@ static int set_local_link_attributes(struct hfi1_pportdata *ppd)
 	u8 tx_polarity_inversion;
 	u8 rx_polarity_inversion;
 	int ret;
-
+	u32 misc_bits = 0;
 	/* reset our fabric serdes to clear any lingering problems */
 	fabric_serdes_reset(dd);
 
@@ -9340,7 +9319,14 @@ static int set_local_link_attributes(struct hfi1_pportdata *ppd)
 	if (ret != HCMD_SUCCESS)
 		goto set_local_link_attributes_fail;
 
-	ret = write_vc_local_link_width(dd, 0, 0,
+	/*
+	 * SerDes loopback init sequence requires
+	 * setting bit 0 of MISC_CONFIG_BITS
+	 */
+	if (loopback == LOOPBACK_SERDES)
+		misc_bits |= 1 << LOOPBACK_SERDES_CONFIG_BIT_MASK_SHIFT;
+
+	ret = write_vc_local_link_width(dd, misc_bits, 0,
 					opa_to_vc_link_widths(
 						ppd->link_width_enabled));
 	if (ret != HCMD_SUCCESS)
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 579a6c70b93eb96bc73bf77098830398410e9b2c..9dd5c5c29bf6b837bf6f9e060e699be6cf636555 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -582,6 +582,9 @@ enum {
 #define LOOPBACK_LCB	2
 #define LOOPBACK_CABLE	3	/* external cable */
 
+/* set up serdes bit in MISC_CONFIG_BITS */
+#define LOOPBACK_SERDES_CONFIG_BIT_MASK_SHIFT 0
+
 /* read and write hardware registers */
 u64 read_csr(const struct hfi1_devdata *dd, u32 offset);
 void write_csr(const struct hfi1_devdata *dd, u32 offset, u64 value);
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index 3e27794ec750c33cfab3c386535e8e6c64137681..7108d4d9225920c25443806a93654d2709fadd6b 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -328,6 +328,7 @@ struct diag_pkt {
 #define SC15_PACKET 0xF
 #define SIZE_OF_CRC 1
 #define SIZE_OF_LT 1
+#define MAX_16B_PADDING 12 /* CRC = 4, LT = 1, Pad = 0 to 7 bytes */
 
 #define LIM_MGMT_P_KEY       0x7FFF
 #define FULL_MGMT_P_KEY      0xFFFF
diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index dee3c674f33deb48f5591a2ad36cd14b68c33753..148a2c7bddaca000ec0d6ec33316b21caa10f348 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -1424,7 +1424,14 @@ int acquire_hw_mutex(struct hfi1_devdata *dd)
 	unsigned long timeout;
 	int try = 0;
 	u8 mask = 1 << dd->hfi1_id;
-	u8 user;
+	u8 user = (u8)read_csr(dd, ASIC_CFG_MUTEX);
+
+	if (user == mask) {
+		dd_dev_info(dd,
+			    "Hardware mutex already acquired, mutex mask %u\n",
+			    (u32)mask);
+		return 0;
+	}
 
 retry:
 	timeout = msecs_to_jiffies(HM_TIMEOUT) + jiffies;
@@ -1455,7 +1462,15 @@ int acquire_hw_mutex(struct hfi1_devdata *dd)
 
 void release_hw_mutex(struct hfi1_devdata *dd)
 {
-	write_csr(dd, ASIC_CFG_MUTEX, 0);
+	u8 mask = 1 << dd->hfi1_id;
+	u8 user = (u8)read_csr(dd, ASIC_CFG_MUTEX);
+
+	if (user != mask)
+		dd_dev_warn(dd,
+			    "Unable to release hardware mutex, mutex mask %u, my mask %u\n",
+			    (u32)user, (u32)mask);
+	else
+		write_csr(dd, ASIC_CFG_MUTEX, 0);
 }
 
 /* return the given resource bit(s) as a mask for the given HFI */
@@ -1770,7 +1785,7 @@ static int check_meta_version(struct hfi1_devdata *dd, u32 *system_table)
 	ver_start /= 8;
 	meta_ver = *((u8 *)system_table + ver_start) & ((1 << ver_len) - 1);
 
-	if (meta_ver < 5) {
+	if (meta_ver < 4) {
 		dd_dev_info(
 			dd, "%s:Please update platform config\n", __func__);
 		return -EINVAL;
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 8ca26e67a096492f582e8fac43b97566087b0e6f..32d7bbe9738c8df76c3c71edfef94fbd09702abf 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -276,7 +276,6 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	if (IS_ERR(ps->s_txreq))
 		goto bail_no_tx;
 
-	ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type;
 	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
 		/* header size in 32-bit words LRH+BTH = (8+12)/4. */
 		hwords = 5;
diff --git a/drivers/infiniband/hw/hfi1/trace.c b/drivers/infiniband/hw/hfi1/trace.c
index ce5a43f1da77b886666442f8b7ee793e20a7db93..959a80429ee95f04a0551302c175dc056da7d8d9 100644
--- a/drivers/infiniband/hw/hfi1/trace.c
+++ b/drivers/infiniband/hw/hfi1/trace.c
@@ -151,7 +151,7 @@ void hfi1_trace_parse_9b_bth(struct ib_other_headers *ohdr,
 	*opcode = ib_bth_get_opcode(ohdr);
 	*tver = ib_bth_get_tver(ohdr);
 	*pkey = ib_bth_get_pkey(ohdr);
-	*psn = ib_bth_get_psn(ohdr);
+	*psn = mask_psn(ib_bth_get_psn(ohdr));
 	*qpn = ib_bth_get_qpn(ohdr);
 }
 
@@ -166,7 +166,7 @@ void hfi1_trace_parse_16b_bth(struct ib_other_headers *ohdr,
 	*pad = ib_bth_get_pad(ohdr);
 	*se = ib_bth_get_se(ohdr);
 	*tver = ib_bth_get_tver(ohdr);
-	*psn = ib_bth_get_psn(ohdr);
+	*psn = mask_psn(ib_bth_get_psn(ohdr));
 	*qpn = ib_bth_get_qpn(ohdr);
 }
 
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index 0b646173ca22272fc5a5cca17b231f4675462a1d..fcd81866e33248fb05808fb7a15e0b1ad6046bb2 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -93,7 +93,6 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 		goto done_free_tx;
 	}
 
-	ps->s_txreq->phdr.hdr.hdr_type = priv->hdr_type;
 	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
 		/* header size in 32-bit words LRH+BTH = (8+12)/4. */
 		hwords = 5;
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 8acdb5dded24fd59c247495a47b8f0ebb875270b..a985a224cdf9f884c8a4253fa830f26c33701cad 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -146,6 +146,9 @@ static int pio_wait(struct rvt_qp *qp,
 /* Length of buffer to create verbs txreq cache name */
 #define TXREQ_NAME_LEN 24
 
+/* 16B trailing buffer */
+static const u8 trail_buf[MAX_16B_PADDING];
+
 static uint wss_threshold;
 module_param(wss_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
@@ -813,7 +816,6 @@ static int build_verbs_tx_desc(
 	struct hfi1_sdma_header *phdr = &tx->phdr;
 	u16 hdrbytes = tx->hdr_dwords << 2;
 	u8 extra_bytes = 0;
-	static char trail_buf[12]; /* CRC = 4, LT = 1, Pad = 0 to 7 bytes */
 
 	if (tx->phdr.hdr.hdr_type) {
 		/*
@@ -865,9 +867,9 @@ static int build_verbs_tx_desc(
 	}
 
 	/* add icrc, lt byte, and padding to flit */
-	if (extra_bytes != 0)
+	if (extra_bytes)
 		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
-					trail_buf, extra_bytes);
+					(void *)trail_buf, extra_bytes);
 
 bail_txadd:
 	return ret;
@@ -1118,18 +1120,10 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 				len -= slen;
 			}
 		}
-		/*
-		 * Bypass packet will need to copy additional
-		 * bytes to accommodate for CRC and LT bytes
-		 */
-		if (extra_bytes) {
-			u8 *empty_buf;
+		/* add icrc, lt byte, and padding to flit */
+		if (extra_bytes)
+			seg_pio_copy_mid(pbuf, trail_buf, extra_bytes);
 
-			empty_buf = kcalloc(extra_bytes, sizeof(u8),
-					    GFP_KERNEL);
-			seg_pio_copy_mid(pbuf, empty_buf, extra_bytes);
-			kfree(empty_buf);
-		}
 		seg_pio_copy_end(pbuf);
 	}
 
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 76216f2ef35a5159bbd6a47c8497a206ee7afc74..cec7a4b34d16f61f3352894f4a480655f8a885e1 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -92,6 +92,8 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 	tx->psc = priv->s_sendcontext;
 	/* so that we can test if the sdma decriptors are there */
 	tx->txreq.num_desc = 0;
+	/* Set the header type */
+	tx->phdr.hdr.hdr_type = priv->hdr_type;
 	return tx;
 }
 
diff --git a/drivers/infiniband/sw/rdmavt/mcast.c b/drivers/infiniband/sw/rdmavt/mcast.c
index 1f12b69a0d075c5e20ed78b49b1f50f5948f9fa2..b3a38c5e4cade8ea57b714bbbc79ff161b81a15a 100644
--- a/drivers/infiniband/sw/rdmavt/mcast.c
+++ b/drivers/infiniband/sw/rdmavt/mcast.c
@@ -351,7 +351,7 @@ int rvt_detach_mcast(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	int last = 0;
 	int ret = 0;
 
-	if (ibqp->qp_num <= 1 || qp->state == IB_QPS_RESET)
+	if (ibqp->qp_num <= 1)
 		return -EINVAL;
 
 	spin_lock_irq(&ibp->lock);
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index efcff70564964e155a98fe379f1a6b4c68cbf856..9b01b715895896d68607ff73c3957c9e9c67c5f4 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -717,7 +717,6 @@ static void rvt_reset_qp(struct rvt_dev_info *rdi, struct rvt_qp *qp,
 
 		/* take qp out the hash and wait for it to be unused */
 		rvt_remove_qp(rdi, qp);
-		wait_event(qp->wait, !atomic_read(&qp->refcount));
 
 		/* grab the lock b/c it was locked at call time */
 		spin_lock_irq(&qp->r_lock);
@@ -1444,6 +1443,7 @@ int rvt_destroy_qp(struct ib_qp *ibqp)
 	spin_unlock(&qp->s_hlock);
 	spin_unlock_irq(&qp->r_lock);
 
+	wait_event(qp->wait, !atomic_read(&qp->refcount));
 	/* qpn is now available for use again */
 	rvt_free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);