[PATCH v6 3/3] perf/core: Clear the whole branch entry in perf_clear_branch_entry()

[Puranjay Mohan]

perf_clear_branch_entry_bitfields() clears the bitfields of struct
perf_branch_entry one by one and leaves from/to alone, since callers
overwrite those straight away. The list has to be kept in sync with the
struct by hand and has already fallen behind: new_type and priv were
added to perf_branch_entry and never added here.

Only BRBE writes those two, and neither is written for every record.
brbe_set_perf_entry_type() leaves new_type alone for a branch type it
does not recognise, and priv is not set for source-only records.
arm_pmuv3.c allocates the per-CPU branch stack with kmalloc(), so such a
record carries whatever the slot held: uninitialised kmalloc() data on
the first pass over the buffer, the previous record's values after that.
Both reach userspace through the branch stack. Nothing under
arch/x86/events/ writes either field, so x86 is unaffected.

Clear the entry with a single struct assignment instead:

	*br = (struct perf_branch_entry){ };

The bitfields add up to exactly 64 bits, so there is no padding, and
every caller assigns from/to immediately afterwards, so zeroing those as
well changes nothing. PERF_BR_SPEC_NA is 0, so dropping the explicit
spec assignment leaves the behaviour unchanged. Nothing needs keeping in
sync when a field is added.

The helper no longer touches only bitfields, so rename it to
perf_clear_branch_entry().

Fixes: b190bc4ac9e6 ("perf: Extend branch type classification")
Fixes: 5402d25aa571 ("perf: Capture branch privilege information")
Suggested-by: James Clark <james.clark at linaro.org>
Reviewed-by: James Clark <james.clark at linaro.org>
Acked-by: Usama Arif <usama.arif at linux.dev>
Signed-off-by: Puranjay Mohan <puranjay at kernel.org>
---
 arch/x86/events/amd/brs.c   |  2 +-
 arch/x86/events/amd/lbr.c   |  2 +-
 arch/x86/events/intel/lbr.c |  6 +++---
 drivers/perf/arm_brbe.c     |  2 +-
 include/linux/perf_event.h  | 16 ++--------------
 5 files changed, 8 insertions(+), 20 deletions(-)

diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
index 06f35a6b58a5b..68c5f42965e91 100644
--- a/arch/x86/events/amd/brs.c
+++ b/arch/x86/events/amd/brs.c
@@ -343,7 +343,7 @@ void amd_brs_drain(void)
 
 		rdmsrq(brs_from(brs_idx), from);
 
-		perf_clear_branch_entry_bitfields(br+nr);
+		perf_clear_branch_entry(br + nr);
 
 		br[nr].from = from;
 		br[nr].to   = to;
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 5b437dc8e4ce2..3639817456119 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -183,7 +183,7 @@ void amd_pmu_lbr_read(void)
 		    entry.to.split.reserved)
 			continue;
 
-		perf_clear_branch_entry_bitfields(br + out);
+		perf_clear_branch_entry(br + out);
 
 		br[out].from	= sign_ext_branch_ip(entry.from.split.ip);
 		br[out].to	= sign_ext_branch_ip(entry.to.split.ip);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f8fadb0b16a45..6541c7046c2b3 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -756,7 +756,7 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 
 		rdmsrq(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
 
-		perf_clear_branch_entry_bitfields(br);
+		perf_clear_branch_entry(br);
 
 		br->from	= msr_lastbranch.from;
 		br->to		= msr_lastbranch.to;
@@ -847,7 +847,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		if (abort && x86_pmu.lbr_double_abort && out > 0)
 			out--;
 
-		perf_clear_branch_entry_bitfields(br+out);
+		perf_clear_branch_entry(br + out);
 		br[out].from	 = from;
 		br[out].to	 = to;
 		br[out].mispred	 = mis;
@@ -921,7 +921,7 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc,
 		to = rdlbr_to(i, lbr);
 		info = rdlbr_info(i, lbr);
 
-		perf_clear_branch_entry_bitfields(e);
+		perf_clear_branch_entry(e);
 
 		e->from		= from;
 		e->to		= to;
diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
index ba554e0c846c4..effbdeacfcbb3 100644
--- a/drivers/perf/arm_brbe.c
+++ b/drivers/perf/arm_brbe.c
@@ -604,7 +604,7 @@ static bool perf_entry_from_brbe_regset(int index, struct perf_branch_entry *ent
 		return false;
 
 	brbinf = bregs.brbinf;
-	perf_clear_branch_entry_bitfields(entry);
+	perf_clear_branch_entry(entry);
 	if (brbe_record_is_complete(brbinf)) {
 		entry->from = bregs.brbsrc;
 		entry->to = bregs.brbtgt;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 48d851fbd8ea5..e034be4a473a8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1467,21 +1467,9 @@ static inline u32 perf_sample_data_size(struct perf_sample_data *data,
 	return size;
 }
 
-/*
- * Clear all bitfields in the perf_branch_entry.
- * The to and from fields are not cleared because they are
- * systematically modified by caller.
- */
-static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
+static inline void perf_clear_branch_entry(struct perf_branch_entry *br)
 {
-	br->mispred	= 0;
-	br->predicted	= 0;
-	br->in_tx	= 0;
-	br->abort	= 0;
-	br->cycles	= 0;
-	br->type	= 0;
-	br->spec	= PERF_BR_SPEC_NA;
-	br->reserved	= 0;
+	*br = (struct perf_branch_entry){ };
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
-- 
2.53.0-Meta