[PATCH v1 01/13] perf/core: add union to struct perf_branch_entry

[Stephane Eranian]

To make it simpler to reset all the info fields on the perf_branch_entry in
a single store, we use a union. This avoids missing some of the bitfields and
improves generated code by minimizing the number of stores.

Using an anonymous struct around the bitfields to guarantee field ordering.

A single perf_branch_entry.val = 0 guarantees all fields are all zeroes on any arch.

Signed-off-by: Stephane Eranian <eranian@xxxxxxxxxx>
---
 arch/x86/events/intel/lbr.c     | 13 +++----------
 include/uapi/linux/perf_event.h | 19 ++++++++++++-------
 2 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 9e6d6eaeb4cb..27aa48cce3c6 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -801,15 +801,9 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
+		cpuc->lbr_entries[i].val	= 0;
 		cpuc->lbr_entries[i].from	= msr_lastbranch.from;
 		cpuc->lbr_entries[i].to		= msr_lastbranch.to;
-		cpuc->lbr_entries[i].mispred	= 0;
-		cpuc->lbr_entries[i].predicted	= 0;
-		cpuc->lbr_entries[i].in_tx	= 0;
-		cpuc->lbr_entries[i].abort	= 0;
-		cpuc->lbr_entries[i].cycles	= 0;
-		cpuc->lbr_entries[i].type	= 0;
-		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
 	cpuc->lbr_stack.hw_idx = tos;
@@ -896,6 +890,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (abort && x86_pmu.lbr_double_abort && out > 0)
 			out--;
 
+		cpuc->lbr_entries[out].val	 = 0;
 		cpuc->lbr_entries[out].from	 = from;
 		cpuc->lbr_entries[out].to	 = to;
 		cpuc->lbr_entries[out].mispred	 = mis;
@@ -903,8 +898,6 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[out].in_tx	 = in_tx;
 		cpuc->lbr_entries[out].abort	 = abort;
 		cpuc->lbr_entries[out].cycles	 = cycles;
-		cpuc->lbr_entries[out].type	 = 0;
-		cpuc->lbr_entries[out].reserved	 = 0;
 		out++;
 	}
 	cpuc->lbr_stack.nr = out;
@@ -966,6 +959,7 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		to = rdlbr_to(i, lbr);
 		info = rdlbr_info(i, lbr);
 
+		e->val		= 0;
 		e->from		= from;
 		e->to		= to;
 		e->mispred	= get_lbr_mispred(info);
@@ -974,7 +968,6 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		e->abort	= !!(info & LBR_INFO_ABORT);
 		e->cycles	= get_lbr_cycles(info);
 		e->type		= get_lbr_br_type(info);
-		e->reserved	= 0;
 	}
 
 	cpuc->lbr_stack.nr = i;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f92880a15645..eb11f383f4be 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1329,13 +1329,18 @@ union perf_mem_data_src {
 struct perf_branch_entry {
 	__u64	from;
 	__u64	to;
-	__u64	mispred:1,  /* target mispredicted */
-		predicted:1,/* target predicted */
-		in_tx:1,    /* in transaction */
-		abort:1,    /* transaction abort */
-		cycles:16,  /* cycle count to last branch */
-		type:4,     /* branch type */
-		reserved:40;
+	union {
+		__u64	val;	    /* to make it easier to clear all fields */
+		struct {
+			__u64	mispred:1,  /* target mispredicted */
+				predicted:1,/* target predicted */
+				in_tx:1,    /* in transaction */
+				abort:1,    /* transaction abort */
+				cycles:16,  /* cycle count to last branch */
+				type:4,     /* branch type */
+				reserved:40;
+		};
+	};
 };
 
 union perf_sample_weight {
-- 
2.33.0.153.gba50c8fa24-goog