IB/hfi1: Fix output trace issues from 16B change (e08aa594) · Commits · 戴 / test

The 16B changes to the output side of the header trace introduced two issues: 1. An uninitialized field "l4" for 9B packets This field needs to be given a value of 0 for 9B packets to insure a correct 9B trace. The fix adds a new define to insure that there is a dummy default for 9B packets to insure the correct string is decoded. 2. Use of entry vs. __entry in field references Fixes: Commit ("IB/hfi1: Add 16B trace support") Reported-by:

Kaike Wan <kaike.wan@intel.com> Reviewed-by:

Don Hiatt <don.hiatt@intel.com> Signed-off-by:

Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:

Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:

Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/hfi1/hfi.h

+1 −0

Original line number	Diff line number	Diff line
		@@ -390,6 +390,7 @@ struct hfi1_packet {
		/*
		* OPA 16B L2/L4 Encodings
		*/
		#define OPA_16B_L4_9B 0x00
		#define OPA_16B_L2_TYPE 0x02
		#define OPA_16B_L4_IB_LOCAL 0x09
		#define OPA_16B_L4_IB_GLOBAL 0x0A

drivers/infiniband/hw/hfi1/trace_ibhdrs.h

+3 −2

Original line number	Diff line number	Diff line
		@@ -334,7 +334,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
		&__entry->dlid,
		&__entry->slid);

		if (entry->l4 == OPA_16B_L4_IB_LOCAL)
		if (__entry->l4 == OPA_16B_L4_IB_LOCAL)
		ohdr = &opah->opah.u.oth;
		else
		ohdr = &opah->opah.u.l.oth;
		@@ -348,6 +348,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
		&__entry->psn,
		&__entry->qpn);
		} else {
		__entry->l4 = OPA_16B_L4_9B;
		hfi1_trace_parse_9b_hdr(&opah->ibh, sc5,
		&__entry->lnh,
		&__entry->lver,
		@@ -356,7 +357,7 @@ DECLARE_EVENT_CLASS(hfi1_output_ibhdr_template,
		&__entry->len,
		&__entry->dlid,
		&__entry->slid);
		if (entry->lnh == HFI1_LRH_BTH)
		if (__entry->lnh == HFI1_LRH_BTH)
		ohdr = &opah->ibh.u.oth;
		else
		ohdr = &opah->ibh.u.l.oth;

Admin message