IB/hfi1,qib: Round 2 of hfi1/qib fixes for 4.9

index db63967..d32f0c8 100644
@@ -55,7 +55,7 @@
 #include "trace.h"
 
 /* cut down ridiculously long IB macro names */
-#define OP(x) IB_OPCODE_RC_##x
+#define OP(x) RC_OP(x)
 
 /**
  * hfi1_add_retry_timer - add/start a retry timer

@@ -184,18 +184,6 @@ void hfi1_del_timers_sync(struct rvt_qp *qp)
 	del_timer_sync(&priv->s_rnr_timer);
 }
 
-/* only opcode mask for adaptive pio */
-const u32 rc_only_opcode =
-	BIT(OP(SEND_ONLY) & 0x1f) |
-	BIT(OP(SEND_ONLY_WITH_IMMEDIATE & 0x1f)) |
-	BIT(OP(RDMA_WRITE_ONLY & 0x1f)) |
-	BIT(OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE & 0x1f)) |
-	BIT(OP(RDMA_READ_REQUEST & 0x1f)) |
-	BIT(OP(ACKNOWLEDGE & 0x1f)) |
-	BIT(OP(ATOMIC_ACKNOWLEDGE & 0x1f)) |
-	BIT(OP(COMPARE_SWAP & 0x1f)) |
-	BIT(OP(FETCH_ADD & 0x1f));
-
 static u32 restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe,
 		       u32 psn, u32 pmtu)
 {

index e7fa176..5e6d1ba 100644
@@ -50,14 +50,7 @@
 #include "qp.h"
 
 /* cut down ridiculously long IB macro names */
-#define OP(x) IB_OPCODE_UC_##x
-
-/* only opcode mask for adaptive pio */
-const u32 uc_only_opcode =
-	BIT(OP(SEND_ONLY) & 0x1f) |
-	BIT(OP(SEND_ONLY_WITH_IMMEDIATE & 0x1f)) |
-	BIT(OP(RDMA_WRITE_ONLY & 0x1f)) |
-	BIT(OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE & 0x1f));
+#define OP(x) UC_OP(x)
 
 /**
  * hfi1_make_uc_req - construct a request packet (SEND, RDMA write)

index d502ba0..0a0e93e 100644
@@ -403,6 +403,28 @@ static const opcode_handler opcode_handler_tbl[256] = {
 	[IB_OPCODE_CNP]				      = &hfi1_cnp_rcv
 };
 
+#define OPMASK 0x1f
+
+static const u32 pio_opmask[BIT(3)] = {
+	/* RC */
+	[IB_OPCODE_RC >> 5] =
+		BIT(RC_OP(SEND_ONLY) & OPMASK) |
+		BIT(RC_OP(SEND_ONLY_WITH_IMMEDIATE) & OPMASK) |
+		BIT(RC_OP(RDMA_WRITE_ONLY) & OPMASK) |
+		BIT(RC_OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE) & OPMASK) |
+		BIT(RC_OP(RDMA_READ_REQUEST) & OPMASK) |
+		BIT(RC_OP(ACKNOWLEDGE) & OPMASK) |
+		BIT(RC_OP(ATOMIC_ACKNOWLEDGE) & OPMASK) |
+		BIT(RC_OP(COMPARE_SWAP) & OPMASK) |
+		BIT(RC_OP(FETCH_ADD) & OPMASK),
+	/* UC */
+	[IB_OPCODE_UC >> 5] =
+		BIT(UC_OP(SEND_ONLY) & OPMASK) |
+		BIT(UC_OP(SEND_ONLY_WITH_IMMEDIATE) & OPMASK) |
+		BIT(UC_OP(RDMA_WRITE_ONLY) & OPMASK) |
+		BIT(UC_OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE) & OPMASK),
+};
+
 /*
  * System image GUID.
  */

@@ -1210,22 +1232,18 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 	case IB_QPT_GSI:
 	case IB_QPT_UD:
 		break;
-	case IB_QPT_RC:
-		if (piothreshold &&
-		    qp->s_cur_size <= min(piothreshold, qp->pmtu) &&
-		    (BIT(get_opcode(h) & 0x1f) & rc_only_opcode) &&
-		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
-		    !sdma_txreq_built(&tx->txreq))
-			return dd->process_pio_send;
-		break;
 	case IB_QPT_UC:
+	case IB_QPT_RC: {
+		u8 op = get_opcode(h);
+
 		if (piothreshold &&
 		    qp->s_cur_size <= min(piothreshold, qp->pmtu) &&
-		    (BIT(get_opcode(h) & 0x1f) & uc_only_opcode) &&
+		    (BIT(op & OPMASK) & pio_opmask[op >> 5]) &&
 		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
 		    !sdma_txreq_built(&tx->txreq))
 			return dd->process_pio_send;
 		break;
+	}
 	default:
 		break;
 	}

index 0dd65eb..1c3815d 100644
@@ -97,6 +97,9 @@ struct hfi1_packet;
 
 #define IB_DEFAULT_GID_PREFIX	cpu_to_be64(0xfe80000000000000ULL)
 
+#define RC_OP(x) IB_OPCODE_RC_##x
+#define UC_OP(x) IB_OPCODE_UC_##x
+
 /* flags passed by hfi1_ib_rcv() */
 enum {
 	HFI1_HAS_GRH = (1 << 0),

index bebc9a5..a3e21a2 100644
@@ -1132,7 +1132,6 @@ extern spinlock_t qib_devs_lock;
 extern struct qib_devdata *qib_lookup(int unit);
 extern u32 qib_cpulist_count;
 extern unsigned long *qib_cpulist;
-extern u16 qpt_mask;
 extern unsigned qib_cc_table_size;
 
 int qib_init(struct qib_devdata *, int);

index f9b8cd2..99d31ef 100644
@@ -41,14 +41,6 @@
 
 #include "qib.h"
 
-/*
- * mask field which was present in now deleted qib_qpn_table
- * is not present in rvt_qpn_table. Defining the same field
- * as qpt_mask here instead of adding the mask field to
- * rvt_qpn_table.
- */
-u16 qpt_mask;
-
 static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
 			      struct rvt_qpn_map *map, unsigned off)
 {

@@ -57,7 +49,7 @@ static inline unsigned mk_qpn(struct rvt_qpn_table *qpt,
 
 static inline unsigned find_next_offset(struct rvt_qpn_table *qpt,
 					struct rvt_qpn_map *map, unsigned off,
-					unsigned n)
+					unsigned n, u16 qpt_mask)
 {
 	if (qpt_mask) {
 		off++;

@@ -179,6 +171,7 @@ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 	struct qib_ibdev *verbs_dev = container_of(rdi, struct qib_ibdev, rdi);
 	struct qib_devdata *dd = container_of(verbs_dev, struct qib_devdata,
 					      verbs_dev);
+	u16 qpt_mask = dd->qpn_mask;
 
 	if (type == IB_QPT_SMI || type == IB_QPT_GSI) {
 		unsigned n;

@@ -215,7 +208,7 @@ int qib_alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 				goto bail;
 			}
 			offset = find_next_offset(qpt, map, offset,
-				dd->n_krcv_queues);
+				dd->n_krcv_queues, qpt_mask);
 			qpn = mk_qpn(qpt, map, offset);
 			/*
 			 * This test differs from alloc_pidmap().

index c12ec8f..876ebb4 100644
@@ -1606,8 +1606,6 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	/* Only need to initialize non-zero fields. */
 	setup_timer(&dev->mem_timer, mem_timer, (unsigned long)dev);
 
-	qpt_mask = dd->qpn_mask;
-
 	INIT_LIST_HEAD(&dev->piowait);
 	INIT_LIST_HEAD(&dev->dmawait);
 	INIT_LIST_HEAD(&dev->txwait);

index aecfc5b..9487c9b 100644
@@ -1406,12 +1406,6 @@ static int set_pkeys(struct hfi1_devdata *dd, u8 port, u16 *pkeys)
 		if (key == okey)
 			continue;
 		/*
-		 * Don't update pkeys[2], if an HFI port without MgmtAllowed
-		 * by neighbor is a switch.
-		 */
-		if (i == 2 && !ppd->mgmt_allowed && ppd->neighbor_type == 1)
-			continue;
-		/*
 		 * The SM gives us the complete PKey table. We have
 		 * to ensure that we put the PKeys in the matching
 		 * slots.

index 0a0e93e..1f19334 100644
@@ -76,7 +76,7 @@ static unsigned int hfi1_max_ahs = 0xFFFF;
 module_param_named(max_ahs, hfi1_max_ahs, uint, S_IRUGO);
 MODULE_PARM_DESC(max_ahs, "Maximum number of address handles to support");
 
-unsigned int hfi1_max_cqes = 0x2FFFF;
+unsigned int hfi1_max_cqes = 0x2FFFFF;
 module_param_named(max_cqes, hfi1_max_cqes, uint, S_IRUGO);
 MODULE_PARM_DESC(max_cqes,
 		 "Maximum number of completion queue entries to support");

@@ -89,7 +89,7 @@ unsigned int hfi1_max_qp_wrs = 0x3FFF;
 module_param_named(max_qp_wrs, hfi1_max_qp_wrs, uint, S_IRUGO);
 MODULE_PARM_DESC(max_qp_wrs, "Maximum number of QP WRs to support");
 
-unsigned int hfi1_max_qps = 16384;
+unsigned int hfi1_max_qps = 32768;
 module_param_named(max_qps, hfi1_max_qps, uint, S_IRUGO);
 MODULE_PARM_DESC(max_qps, "Maximum number of QPs to support");
 

index 4e95ad8..1869f63 100644
@@ -161,7 +161,7 @@ static struct hfi1_i2c_bus *init_i2c_bus(struct hfi1_devdata *dd,
 	bus->algo.getsda = hfi1_getsda;
 	bus->algo.getscl = hfi1_getscl;
 	bus->algo.udelay = 5;
-	bus->algo.timeout = usecs_to_jiffies(50);
+	bus->algo.timeout = usecs_to_jiffies(100000);
 	bus->algo.data = bus;
 
 	bus->adapter.owner = THIS_MODULE;

index 3a1ef30..7b0aa19 100644
@@ -254,30 +254,6 @@ static inline void read_extra_bytes(struct pio_buf *pbuf,
 }
 
 /*
- * Zero extra bytes from the end of pbuf->carry.
- *
- * NOTES:
- * o zbytes <= old_bytes
- */
-static inline void zero_extra_bytes(struct pio_buf *pbuf, unsigned int zbytes)
-{
-	unsigned int remaining;
-
-	if (zbytes == 0)	/* nothing to do */
-		return;
-
-	remaining = pbuf->carry_bytes - zbytes;	/* remaining bytes */
-
-	/* NOTE: zshift only guaranteed to work if remaining != 0 */
-	if (remaining)
-		pbuf->carry.val64 = (pbuf->carry.val64 << zshift(remaining))
-					>> zshift(remaining);
-	else
-		pbuf->carry.val64 = 0;
-	pbuf->carry_bytes = remaining;
-}
-
-/*
  * Write a quad word using parts of pbuf->carry and the next 8 bytes of src.
  * Put the unused part of the next 8 bytes of src into the LSB bytes of
  * pbuf->carry with the upper bytes zeroed..

@@ -385,20 +361,6 @@ static inline void read_extra_bytes(struct pio_buf *pbuf,
 }
 
 /*
- * Zero extra bytes from the end of pbuf->carry.
- *
- * We do not care about the value of unused bytes in carry, so just
- * reduce the byte count.
- *
- * NOTES:
- * o zbytes <= old_bytes
- */
-static inline void zero_extra_bytes(struct pio_buf *pbuf, unsigned int zbytes)
-{
-	pbuf->carry_bytes -= zbytes;
-}
-
-/*
  * Write a quad word using parts of pbuf->carry and the next 8 bytes of src.
  * Put the unused part of the next 8 bytes of src into the low bytes of
  * pbuf->carry.

@@ -550,8 +512,8 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes)
 {
 	void __iomem *dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
 	void __iomem *dend;			/* 8-byte data end */
-	unsigned long qw_to_write = (pbuf->carry_bytes + nbytes) >> 3;
-	unsigned long bytes_left = (pbuf->carry_bytes + nbytes) & 0x7;
+	unsigned long qw_to_write = nbytes >> 3;
+	unsigned long bytes_left = nbytes & 0x7;
 
 	/* calculate 8-byte data end */
 	dend = dest + (qw_to_write * sizeof(u64));

@@ -621,16 +583,46 @@ static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes)
 		dest += sizeof(u64);
 	}
 
-	/* adjust carry */
-	if (pbuf->carry_bytes < bytes_left) {
-		/* need to read more */
-		read_extra_bytes(pbuf, from, bytes_left - pbuf->carry_bytes);
+	pbuf->qw_written += qw_to_write;
+
+	/* handle carry and left-over bytes */
+	if (pbuf->carry_bytes + bytes_left >= 8) {
+		unsigned long nread;
+
+		/* there is enough to fill another qw - fill carry */
+		nread = 8 - pbuf->carry_bytes;
+		read_extra_bytes(pbuf, from, nread);
+
+		/*
+		 * One more write - but need to make sure dest is correct.
+		 * Check for wrap and the possibility the write
+		 * should be in SOP space.
+		 *
+		 * The two checks immediately below cannot both be true, hence
+		 * the else. If we have wrapped, we cannot still be within the
+		 * first block. Conversely, if we are still in the first block,
+		 * we cannot have wrapped. We do the wrap check first as that
+		 * is more likely.
+		 */
+		/* adjust if we have wrapped */
+		if (dest >= pbuf->end)
+			dest -= pbuf->size;
+		/* jump to the SOP range if within the first block */
+		else if (pbuf->qw_written < PIO_BLOCK_QWS)
+			dest += SOP_DISTANCE;
+
+		/* flush out full carry */
+		carry8_write8(pbuf->carry, dest);
+		pbuf->qw_written++;
+
+		/* now adjust and read the rest of the bytes into carry */
+		bytes_left -= nread;
+		from += nread; /* from is now not aligned */
+		read_low_bytes(pbuf, from, bytes_left);
 	} else {
-		/* remove invalid bytes */
-		zero_extra_bytes(pbuf, pbuf->carry_bytes - bytes_left);
+		/* not enough to fill another qw, append the rest to carry */
+		read_extra_bytes(pbuf, from, bytes_left);
 	}
-
-	pbuf->qw_written += qw_to_write;
 }
 
 /*

index 7b0aa19..aa77736 100644
@@ -165,9 +165,6 @@ void pio_copy(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc,
 	preempt_enable();
 }
 
-/* USE_SHIFTS is faster in user-space tests on a Xeon X5570 @ 2.93GHz */
-#define USE_SHIFTS 1
-#ifdef USE_SHIFTS
 /*
  * Handle carry bytes using shifts and masks.
  *

@@ -187,126 +184,6 @@ void pio_copy(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc,
 #define mshift(x) (8 * (x))
 
 /*
- * Read nbytes bytes from "from" and return them in the LSB bytes
- * of pbuf->carry.  Other bytes are zeroed.  Any previous value
- * pbuf->carry is lost.
- *
- * NOTES:
- * o do not read from from if nbytes is zero
- * o from may _not_ be u64 aligned
- * o nbytes must not span a QW boundary
- */
-static inline void read_low_bytes(struct pio_buf *pbuf, const void *from,
-				  unsigned int nbytes)
-{
-	unsigned long off;
-
-	if (nbytes == 0) {
-		pbuf->carry.val64 = 0;
-	} else {
-		/* align our pointer */
-		off = (unsigned long)from & 0x7;
-		from = (void *)((unsigned long)from & ~0x7l);
-		pbuf->carry.val64 = ((*(u64 *)from)
-				<< zshift(nbytes + off))/* zero upper bytes */
-				>> zshift(nbytes);	/* place at bottom */
-	}
-	pbuf->carry_bytes = nbytes;
-}
-
-/*
- * Read nbytes bytes from "from" and put them at the next significant bytes
- * of pbuf->carry.  Unused bytes are zeroed.  It is expected that the extra
- * read does not overfill carry.
- *
- * NOTES:
- * o from may _not_ be u64 aligned
- * o nbytes may span a QW boundary
- */
-static inline void read_extra_bytes(struct pio_buf *pbuf,
-				    const void *from, unsigned int nbytes)
-{
-	unsigned long off = (unsigned long)from & 0x7;
-	unsigned int room, xbytes;
-
-	/* align our pointer */
-	from = (void *)((unsigned long)from & ~0x7l);
-
-	/* check count first - don't read anything if count is zero */
-	while (nbytes) {
-		/* find the number of bytes in this u64 */
-		room = 8 - off;	/* this u64 has room for this many bytes */
-		xbytes = min(room, nbytes);
-
-		/*
-		 * shift down to zero lower bytes, shift up to zero upper
-		 * bytes, shift back down to move into place
-		 */
-		pbuf->carry.val64 |= (((*(u64 *)from)
-					>> mshift(off))
-					<< zshift(xbytes))
-					>> zshift(xbytes + pbuf->carry_bytes);
-		off = 0;
-		pbuf->carry_bytes += xbytes;
-		nbytes -= xbytes;
-		from += sizeof(u64);
-	}
-}
-
-/*
- * Write a quad word using parts of pbuf->carry and the next 8 bytes of src.
- * Put the unused part of the next 8 bytes of src into the LSB bytes of
- * pbuf->carry with the upper bytes zeroed..
- *
- * NOTES:
- * o result must keep unused bytes zeroed
- * o src must be u64 aligned
- */
-static inline void merge_write8(
-	struct pio_buf *pbuf,
-	void __iomem *dest,
-	const void *src)
-{
-	u64 new, temp;
-
-	new = *(u64 *)src;
-	temp = pbuf->carry.val64 | (new << mshift(pbuf->carry_bytes));
-	writeq(temp, dest);
-	pbuf->carry.val64 = new >> zshift(pbuf->carry_bytes);
-}
-
-/*
- * Write a quad word using all bytes of carry.
- */
-static inline void carry8_write8(union mix carry, void __iomem *dest)
-{
-	writeq(carry.val64, dest);
-}
-
-/*
- * Write a quad word using all the valid bytes of carry.  If carry
- * has zero valid bytes, nothing is written.
- * Returns 0 on nothing written, non-zero on quad word written.
- */
-static inline int carry_write8(struct pio_buf *pbuf, void __iomem *dest)
-{
-	if (pbuf->carry_bytes) {
-		/* unused bytes are always kept zeroed, so just write */
-		writeq(pbuf->carry.val64, dest);
-		return 1;
-	}
-
-	return 0;
-}
-
-#else /* USE_SHIFTS */
-/*
- * Handle carry bytes using byte copies.
- *
- * NOTE: the value the unused portion of carry is left uninitialized.
- */
-
-/*
  * Jump copy - no-loop copy for < 8 bytes.
  */
 static inline void jcopy(u8 *dest, const u8 *src, u32 n)

@@ -314,18 +191,25 @@ static inline void jcopy(u8 *dest, const u8 *src, u32 n)
 	switch (n) {
 	case 7:
 		*dest++ = *src++;
+		/* fall through */
 	case 6:
 		*dest++ = *src++;
+		/* fall through */
 	case 5:
 		*dest++ = *src++;
+		/* fall through */
 	case 4:
 		*dest++ = *src++;
+		/* fall through */
 	case 3:
 		*dest++ = *src++;
+		/* fall through */
 	case 2:
 		*dest++ = *src++;
+		/* fall through */
 	case 1:
 		*dest++ = *src++;
+		/* fall through */
 	}
 }
 

@@ -341,6 +225,7 @@ static inline void jcopy(u8 *dest, const u8 *src, u32 n)
 static inline void read_low_bytes(struct pio_buf *pbuf, const void *from,
 				  unsigned int nbytes)
 {
+	pbuf->carry.val64 = 0;
 	jcopy(&pbuf->carry.val8[0], from, nbytes);
 	pbuf->carry_bytes = nbytes;
 }

@@ -362,25 +247,30 @@ static inline void read_extra_bytes(struct pio_buf *pbuf,
 
 /*
  * Write a quad word using parts of pbuf->carry and the next 8 bytes of src.
- * Put the unused part of the next 8 bytes of src into the low bytes of
- * pbuf->carry.
+ * Put the unused part of the next 8 bytes of src into the LSB bytes of
+ * pbuf->carry with the upper bytes zeroed..
+ *
+ * NOTES:
+ * o result must keep unused bytes zeroed
+ * o src must be u64 aligned
  */
 static inline void merge_write8(
 	struct pio_buf *pbuf,
-	void *dest,
+	void __iomem *dest,
 	const void *src)
 {
-	u32 remainder = 8 - pbuf->carry_bytes;
+	u64 new, temp;
 
-	jcopy(&pbuf->carry.val8[pbuf->carry_bytes], src, remainder);
-	writeq(pbuf->carry.val64, dest);
-	jcopy(&pbuf->carry.val8[0], src + remainder, pbuf->carry_bytes);
+	new = *(u64 *)src;
+	temp = pbuf->carry.val64 | (new << mshift(pbuf->carry_bytes));
+	writeq(temp, dest);
+	pbuf->carry.val64 = new >> zshift(pbuf->carry_bytes);
 }
 
 /*
  * Write a quad word using all bytes of carry.
  */
-static inline void carry8_write8(union mix carry, void *dest)
+static inline void carry8_write8(union mix carry, void __iomem *dest)
 {
 	writeq(carry.val64, dest);
 }

@@ -390,20 +280,16 @@ static inline void carry8_write8(union mix carry, void *dest)
  * has zero valid bytes, nothing is written.
  * Returns 0 on nothing written, non-zero on quad word written.
  */
-static inline int carry_write8(struct pio_buf *pbuf, void *dest)
+static inline int carry_write8(struct pio_buf *pbuf, void __iomem *dest)
 {
 	if (pbuf->carry_bytes) {
-		u64 zero = 0;
-
-		jcopy(&pbuf->carry.val8[pbuf->carry_bytes], (u8 *)&zero,
-		      8 - pbuf->carry_bytes);
+		/* unused bytes are always kept zeroed, so just write */
 		writeq(pbuf->carry.val64, dest);
 		return 1;
 	}
 
 	return 0;
 }
-#endif /* USE_SHIFTS */
 
 /*
  * Segmented PIO Copy - start

index d32f0c8..e9623d0 100644
@@ -926,8 +926,10 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 	return;
 
 queue_ack:
-	this_cpu_inc(*ibp->rvp.rc_qacks);
 	spin_lock_irqsave(&qp->s_lock, flags);
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK))
+		goto unlock;
+	this_cpu_inc(*ibp->rvp.rc_qacks);
 	qp->s_flags |= RVT_S_ACK_PENDING | RVT_S_RESP_PENDING;
 	qp->s_nak_state = qp->r_nak_state;
 	qp->s_ack_psn = qp->r_ack_psn;

@@ -936,6 +938,7 @@ queue_ack:
 
 	/* Schedule the send tasklet. */
 	hfi1_schedule_send(qp);
+unlock:
 	spin_unlock_irqrestore(&qp->s_lock, flags);
 }
 

index eaa3a9f..26c5ee5 100644
@@ -971,7 +971,9 @@ static struct flag_table dc8051_info_err_flags[] = {
 	FLAG_ENTRY0("Failed LNI(VerifyCap_1)", FAILED_LNI_VERIFY_CAP1),
 	FLAG_ENTRY0("Failed LNI(VerifyCap_2)", FAILED_LNI_VERIFY_CAP2),
 	FLAG_ENTRY0("Failed LNI(ConfigLT)",    FAILED_LNI_CONFIGLT),
-	FLAG_ENTRY0("Host Handshake Timeout",  HOST_HANDSHAKE_TIMEOUT)
+	FLAG_ENTRY0("Host Handshake Timeout",  HOST_HANDSHAKE_TIMEOUT),
+	FLAG_ENTRY0("External Device Request Timeout",
+		    EXTERNAL_DEVICE_REQ_TIMEOUT),
 };
 
 /*

index 35a7855..92f2485 100644
@@ -254,12 +254,14 @@
 #define FAILED_LNI_VERIFY_CAP2		BIT(10)
 #define FAILED_LNI_CONFIGLT		BIT(11)
 #define HOST_HANDSHAKE_TIMEOUT		BIT(12)
+#define EXTERNAL_DEVICE_REQ_TIMEOUT	BIT(13)
 
 #define FAILED_LNI (FAILED_LNI_POLLING | FAILED_LNI_DEBOUNCE \
 			| FAILED_LNI_ESTBCOMM | FAILED_LNI_OPTEQ \
 			| FAILED_LNI_VERIFY_CAP1 \
 			| FAILED_LNI_VERIFY_CAP2 \
-			| FAILED_LNI_CONFIGLT | HOST_HANDSHAKE_TIMEOUT)
+			| FAILED_LNI_CONFIGLT | HOST_HANDSHAKE_TIMEOUT \
+			| EXTERNAL_DEVICE_REQ_TIMEOUT)
 
 /* DC_DC8051_DBG_ERR_INFO_SET_BY_8051.HOST_MSG - host message flags */
 #define HOST_REQ_DONE		BIT(0)

index 26c5ee5..88394cd 100644
@@ -13385,9 +13385,9 @@ static void init_rbufs(struct hfi1_devdata *dd)
 		/*
 		 * Give up after 1ms - maximum wait time.
 		 *
-		 * RBuf size is 148KiB.  Slowest possible is PCIe Gen1 x1 at
+		 * RBuf size is 136KiB.  Slowest possible is PCIe Gen1 x1 at
 		 * 250MB/s bandwidth.  Lower rate to 66% for overhead to get:
-		 *	148 KB / (66% * 250MB/s) = 920us
+		 *	136 KB / (66% * 250MB/s) = 844us
 		 */
 		if (count++ > 500) {
 			dd_dev_err(dd,

index 92f2485..9234525 100644
@@ -82,7 +82,7 @@
  */
 #define CM_VAU 3
 /* HFI link credit count, AKA receive buffer depth (RBUF_DEPTH) */
-#define CM_GLOBAL_CREDITS 0x940
+#define CM_GLOBAL_CREDITS 0x880
 /* Number of PKey entries in the HW */
 #define MAX_PKEY_VALUES 16
 

index e9623d0..8bc5013 100644
@@ -835,7 +835,7 @@ bail_no_tx:
  *
  * This is called from hfi1_rc_rcv() and handle_receive_interrupt().
  * Note that RDMA reads and atomics are handled in the
- * send side QP state and tasklet.
+ * send side QP state and send engine.
  */
 void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 		      int is_fecn)

@@ -911,7 +911,7 @@ void hfi1_send_rc_ack(struct hfi1_ctxtdata *rcd, struct rvt_qp *qp,
 	if (!pbuf) {
 		/*
 		 * We have no room to send at the moment.  Pass
-		 * responsibility for sending the ACK to the send tasklet
+		 * responsibility for sending the ACK to the send engine
 		 * so that when enough buffer space becomes available,
 		 * the ACK is sent ahead of other outgoing packets.
 		 */

@@ -936,7 +936,7 @@ queue_ack:
 	if (is_fecn)
 		qp->s_flags |= RVT_S_ECN;
 
-	/* Schedule the send tasklet. */
+	/* Schedule the send engine. */
 	hfi1_schedule_send(qp);
 unlock:
 	spin_unlock_irqrestore(&qp->s_lock, flags);

@@ -1025,7 +1025,7 @@ done:
 	qp->s_psn = psn;
 	/*
 	 * Set RVT_S_WAIT_PSN as rc_complete() may start the timer
-	 * asynchronously before the send tasklet can get scheduled.
+	 * asynchronously before the send engine can get scheduled.
 	 * Doing it in hfi1_make_rc_req() is too late.
 	 */
 	if ((cmp_psn(qp->s_psn, qp->s_sending_hpsn) <= 0) &&

@@ -1946,7 +1946,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data,
 	case OP(FETCH_ADD): {
 		/*
 		 * If we didn't find the atomic request in the ack queue
-		 * or the send tasklet is already backed up to send an
+		 * or the send engine is already backed up to send an
 		 * earlier entry, we can ignore this request.
 		 */
 		if (!e || e->opcode != (u8)opcode || old_req)

@@ -2433,7 +2433,7 @@ send_last:
 		qp->r_nak_state = 0;
 		qp->r_head_ack_queue = next;
 
-		/* Schedule the send tasklet. */
+		/* Schedule the send engine. */
 		qp->s_flags |= RVT_S_RESP_PENDING;
 		hfi1_schedule_send(qp);
 

@@ -2499,7 +2499,7 @@ send_last:
 		qp->r_nak_state = 0;
 		qp->r_head_ack_queue = next;
 
-		/* Schedule the send tasklet. */
+		/* Schedule the send engine. */
 		qp->s_flags |= RVT_S_RESP_PENDING;
 		hfi1_schedule_send(qp);
 

index 7ce2b3c..a1576ae 100644
@@ -352,7 +352,7 @@ err:
  *
  * This is called from hfi1_do_send() to
  * forward a WQE addressed to the same HFI.
- * Note that although we are single threaded due to the tasklet, we still
+ * Note that although we are single threaded due to the send engine, we still
  * have to protect against post_send().  We don't have to worry about
  * receive interrupts since this is a connected protocol and all packets
  * will pass through here.

@@ -846,7 +846,7 @@ void _hfi1_do_send(struct work_struct *work)
  * @work: contains a pointer to the QP
  *
  * Process entries in the send work queue until credit or queue is
- * exhausted.  Only allow one CPU to send a packet per QP (tasklet).
+ * 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)

@@ -909,7 +909,7 @@ void hfi1_do_send(struct rvt_qp *qp)
 			spin_unlock_irqrestore(&qp->s_lock, ps.flags);
 			/*
 			 * If the packet cannot be sent now, return and
-			 * the send tasklet will be woken up later.
+			 * the send engine will be woken up later.
 			 */
 			if (hfi1_verbs_send(qp, &ps))
 				return;

index 52ffd11..5711620 100644
@@ -1061,8 +1061,6 @@ struct hfi1_devdata {
 	u8 psxmitwait_supported;
 	/* cycle length of PS* counters in HW (in picoseconds) */
 	u16 psxmitwait_check_rate;
-	/* high volume overflow errors deferred to tasklet */
-	struct tasklet_struct error_tasklet;
 
 	/* MSI-X information */
 	struct hfi1_msix_entry *msix_entries;

index 335796f..13bb6a5 100644
@@ -978,14 +978,16 @@ static int allocate_ctxt(struct file *fp, struct hfi1_devdata *dd,
 	 */
 	uctxt->sc = sc_alloc(dd, SC_USER, uctxt->rcvhdrqentsize,
 			     uctxt->dd->node);
-	if (!uctxt->sc)
-		return -ENOMEM;
-
+	if (!uctxt->sc) {
+		ret = -ENOMEM;
+		goto ctxdata_free;
+	}
 	hfi1_cdbg(PROC, "allocated send context %u(%u)\n", uctxt->sc->sw_index,
 		  uctxt->sc->hw_context);
 	ret = sc_enable(uctxt->sc);
 	if (ret)
-		return ret;
+		goto ctxdata_free;
+
 	/*
 	 * Setup shared context resources if the user-level has requested
 	 * shared contexts and this is the 'master' process.

@@ -999,7 +1001,7 @@ static int allocate_ctxt(struct file *fp, struct hfi1_devdata *dd,
 		 * send context because it will be done during file close
 		 */
 		if (ret)
-			return ret;
+			goto ctxdata_free;
 	}
 	uctxt->userversion = uinfo->userversion;
 	uctxt->flags = hfi1_cap_mask; /* save current flag state */

@@ -1019,6 +1021,11 @@ static int allocate_ctxt(struct file *fp, struct hfi1_devdata *dd,
 	fd->uctxt = uctxt;
 
 	return 0;
+
+ctxdata_free:
+	dd->rcd[ctxt] = NULL;
+	hfi1_free_ctxtdata(dd, uctxt);
+	return ret;
 }
 
 static int init_subctxts(struct hfi1_ctxtdata *uctxt,

index ab2f221..60db615 100644
@@ -336,6 +336,7 @@ struct hfi1_ctxtdata *hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, u32 ctxt,
 	}
 	return rcd;
 bail:
+	dd->rcd[ctxt] = NULL;
 	kfree(rcd->egrbufs.rcvtids);
 	kfree(rcd->egrbufs.buffers);
 	kfree(rcd);