Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "This has been a fairly typical cycle, with the usual sorts of driver
  updates. Several series continue to come through which improve and
  modernize various parts of the core code, and we finally are starting
  to get the uAPI command interface cleaned up.

   - Various driver fixes for bnxt_re, cxgb3/4, hfi1, hns, i40iw, mlx4,
     mlx5, qib, rxe, usnic

   - Rework the entire syscall flow for uverbs to be able to run over
     ioctl(). Finally getting past the historic bad choice to use
     write() for command execution

   - More functional coverage with the mlx5 'devx' user API

   - Start of the HFI1 series for 'TID RDMA'

   - SRQ support in the hns driver

   - Support for new IBTA defined 2x lane widths

   - A big series to consolidate all the driver function pointers into a
     big struct and have drivers provide a 'static const' version of the
     struct instead of open coding initialization

   - New 'advise_mr' uAPI to control device caching/loading of page
     tables

   - Support for inline data in SRPT

   - Modernize how umad uses the driver core and creates cdev's and
     sysfs files

   - First steps toward removing 'uobject' from the view of the drivers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (193 commits)
  RDMA/srpt: Use kmem_cache_free() instead of kfree()
  RDMA/mlx5: Signedness bug in UVERBS_HANDLER()
  IB/uverbs: Signedness bug in UVERBS_HANDLER()
  IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
  IB/umad: Start using dev_groups of class
  IB/umad: Use class_groups and let core create class file
  IB/umad: Refactor code to use cdev_device_add()
  IB/umad: Avoid destroying device while it is accessed
  IB/umad: Simplify and avoid dynamic allocation of class
  IB/mlx5: Fix wrong error unwind
  IB/mlx4: Remove set but not used variable 'pd'
  RDMA/iwcm: Don't copy past the end of dev_name() string
  IB/mlx5: Fix long EEH recover time with NVMe offloads
  IB/mlx5: Simplify netdev unbinding
  IB/core: Move query port to ioctl
  RDMA/nldev: Expose port_cap_flags2
  IB/core: uverbs copy to struct or zero helper
  IB/rxe: Reuse code which sets port state
  IB/rxe: Make counters thread safe
  IB/mlx5: Use the correct commands for UMEM and UCTX allocation
  ...

1 files changed, 20 insertions, 13 deletions

diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 4baa8f4d49de..88242fe95eaa 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -51,6 +51,7 @@
 #include "hfi.h"
 #include "mad.h"
 #include "verbs_txreq.h"
+#include "trace_ibhdrs.h"
 #include "qp.h"
 
 /* We support only two types - 9B and 16B for now */
@@ -656,18 +657,19 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 	u32 bth0, plen, vl, hwords = 7;
 	u16 len;
 	u8 l4;
-	struct hfi1_16b_header hdr;
+	struct hfi1_opa_header hdr;
 	struct ib_other_headers *ohdr;
 	struct pio_buf *pbuf;
 	struct send_context *ctxt = qp_to_send_context(qp, sc5);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	u32 nwords;
 
+	hdr.hdr_type = HFI1_PKT_TYPE_16B;
 	/* Populate length */
 	nwords = ((hfi1_get_16b_padding(hwords << 2, 0) +
 		   SIZE_OF_LT) >> 2) + SIZE_OF_CRC;
 	if (old_grh) {
-		struct ib_grh *grh = &hdr.u.l.grh;
+		struct ib_grh *grh = &hdr.opah.u.l.grh;
 
 		grh->version_tclass_flow = old_grh->version_tclass_flow;
 		grh->paylen = cpu_to_be16(
@@ -675,11 +677,11 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 		grh->hop_limit = 0xff;
 		grh->sgid = old_grh->dgid;
 		grh->dgid = old_grh->sgid;
-		ohdr = &hdr.u.l.oth;
+		ohdr = &hdr.opah.u.l.oth;
 		l4 = OPA_16B_L4_IB_GLOBAL;
 		hwords += sizeof(struct ib_grh) / sizeof(u32);
 	} else {
-		ohdr = &hdr.u.oth;
+		ohdr = &hdr.opah.u.oth;
 		l4 = OPA_16B_L4_IB_LOCAL;
 	}
 
@@ -693,7 +695,7 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 
 	/* Convert dwords to flits */
 	len = (hwords + nwords) >> 1;
-	hfi1_make_16b_hdr(&hdr, slid, dlid, len, pkey, 1, 0, l4, sc5);
+	hfi1_make_16b_hdr(&hdr.opah, slid, dlid, len, pkey, 1, 0, l4, sc5);
 
 	plen = 2 /* PBC */ + hwords + nwords;
 	pbc_flags |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
@@ -701,9 +703,11 @@ void return_cnp_16B(struct hfi1_ibport *ibp, struct rvt_qp *qp,
 	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
 	if (ctxt) {
 		pbuf = sc_buffer_alloc(ctxt, plen, NULL, NULL);
-		if (pbuf)
+		if (pbuf) {
+			trace_pio_output_ibhdr(ppd->dd, &hdr, sc5);
 			ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
 						 &hdr, hwords);
+		}
 	}
 }
 
@@ -715,14 +719,15 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 	u32 bth0, plen, vl, hwords = 5;
 	u16 lrh0;
 	u8 sl = ibp->sc_to_sl[sc5];
-	struct ib_header hdr;
+	struct hfi1_opa_header hdr;
 	struct ib_other_headers *ohdr;
 	struct pio_buf *pbuf;
 	struct send_context *ctxt = qp_to_send_context(qp, sc5);
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 
+	hdr.hdr_type = HFI1_PKT_TYPE_9B;
 	if (old_grh) {
-		struct ib_grh *grh = &hdr.u.l.grh;
+		struct ib_grh *grh = &hdr.ibh.u.l.grh;
 
 		grh->version_tclass_flow = old_grh->version_tclass_flow;
 		grh->paylen = cpu_to_be16(
@@ -730,11 +735,11 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 		grh->hop_limit = 0xff;
 		grh->sgid = old_grh->dgid;
 		grh->dgid = old_grh->sgid;
-		ohdr = &hdr.u.l.oth;
+		ohdr = &hdr.ibh.u.l.oth;
 		lrh0 = HFI1_LRH_GRH;
 		hwords += sizeof(struct ib_grh) / sizeof(u32);
 	} else {
-		ohdr = &hdr.u.oth;
+		ohdr = &hdr.ibh.u.oth;
 		lrh0 = HFI1_LRH_BTH;
 	}
 
@@ -746,16 +751,18 @@ void return_cnp(struct hfi1_ibport *ibp, struct rvt_qp *qp, u32 remote_qpn,
 	ohdr->bth[1] = cpu_to_be32(remote_qpn | (1 << IB_BECN_SHIFT));
 	ohdr->bth[2] = 0; /* PSN 0 */
 
-	hfi1_make_ib_hdr(&hdr, lrh0, hwords + SIZE_OF_CRC, dlid, slid);
+	hfi1_make_ib_hdr(&hdr.ibh, lrh0, hwords + SIZE_OF_CRC, dlid, slid);
 	plen = 2 /* PBC */ + hwords;
 	pbc_flags |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
 	vl = sc_to_vlt(ppd->dd, sc5);
 	pbc = create_pbc(ppd, pbc_flags, qp->srate_mbps, vl, plen);
 	if (ctxt) {
 		pbuf = sc_buffer_alloc(ctxt, plen, NULL, NULL);
-		if (pbuf)
+		if (pbuf) {
+			trace_pio_output_ibhdr(ppd->dd, &hdr, sc5);
 			ppd->dd->pio_inline_send(ppd->dd, pbuf, pbc,
 						 &hdr, hwords);
+		}
 	}
 }
 
@@ -912,7 +919,7 @@ void hfi1_ud_rcv(struct hfi1_packet *packet)
 		src_qp = hfi1_16B_get_src_qpn(packet->mgmt);
 	}
 
-	process_ecn(qp, packet, (opcode != IB_OPCODE_CNP));
+	process_ecn(qp, packet);
 	/*
 	 * Get the number of bytes the message was padded by
 	 * and drop incomplete packets.