From: dongsheng <dongsheng.x.zhang@intel.com>

For Intel Atom CPUs, the PMU events "Instruction Retired" or
"Branch Instruction Retired" may be overcounted for some certain
instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
and complex SGX/SMX/CSTATE instructions/flows.

The detailed information can be found in the errata (section SRF7):
https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/

For the Atom platforms before Sierra Forest (including Sierra Forest),
Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
be overcounted on these certain instructions, but for Clearwater Forest
only "Instruction Retired" event is overcounted on these instructions.

So add a helper detect_inst_overcount_flags() to detect whether the
platform has the overcount issue and the later patches would relax the
precise count check by leveraging the gotten overcount flags from this
helper.

Signed-off-by: dongsheng <dongsheng.x.zhang@intel.com>
[Rewrite comments and commit message - Dapeng]
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Yi Lai <yi1.lai@intel.com>
---
 lib/x86/processor.h | 27 ++++++++++++++++++++++++++
 x86/pmu.c           | 47 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

diff --git a/lib/x86/processor.h b/lib/x86/processor.h
index 62f3d578..937f75e4 100644
--- a/lib/x86/processor.h
+++ b/lib/x86/processor.h
@@ -1188,4 +1188,31 @@ static inline bool is_lam_u57_enabled(void)
 	return !!(read_cr3() & X86_CR3_LAM_U57);
 }
 
+/* Copy from kernel arch/x86/lib/cpu.c */
+static inline u32 x86_family(u32 sig)
+{
+	u32 x86;
+
+	x86 = (sig >> 8) & 0xf;
+
+	if (x86 == 0xf)
+		x86 += (sig >> 20) & 0xff;
+
+	return x86;
+}
+
+static inline u32 x86_model(u32 sig)
+{
+	u32 fam, model;
+
+	fam = x86_family(sig);
+
+	model = (sig >> 4) & 0xf;
+
+	if (fam >= 0x6)
+		model += ((sig >> 16) & 0xf) << 4;
+
+	return model;
+}
+
 #endif
diff --git a/x86/pmu.c b/x86/pmu.c
index a6b0cfcc..87365aff 100644
--- a/x86/pmu.c
+++ b/x86/pmu.c
@@ -159,6 +159,14 @@ static struct pmu_event *gp_events;
 static unsigned int gp_events_size;
 static unsigned int fixed_counters_num;
 
+/*
+ * Flags for Intel "Instruction Retired" and "Branch Instruction Retired"
+ * overcount flaws.
+ */
+#define INST_RETIRED_OVERCOUNT BIT(0)
+#define BR_RETIRED_OVERCOUNT   BIT(1)
+static u32 intel_inst_overcount_flags;
+
 static int has_ibpb(void)
 {
 	return this_cpu_has(X86_FEATURE_SPEC_CTRL) ||
@@ -959,6 +967,43 @@ static void check_invalid_rdpmc_gp(void)
 	       "Expected #GP on RDPMC(64)");
 }
 
+/*
+ * For Intel Atom CPUs, the PMU events "Instruction Retired" or
+ * "Branch Instruction Retired" may be overcounted for some certain
+ * instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
+ * and complex SGX/SMX/CSTATE instructions/flows.
+ *
+ * The detailed information can be found in the errata (section SRF7):
+ * https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/
+ *
+ * For the Atom platforms before Sierra Forest (including Sierra Forest),
+ * Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
+ * be overcounted on these certain instructions, but for Clearwater Forest
+ * only "Instruction Retired" event is overcounted on these instructions.
+ */
+static u32 detect_inst_overcount_flags(void)
+{
+	u32 flags = 0;
+	struct cpuid c = cpuid(1);
+
+	if (x86_family(c.a) == 0x6) {
+		switch (x86_model(c.a)) {
+		case 0xDD: /* Clearwater Forest */
+			flags = INST_RETIRED_OVERCOUNT;
+			break;
+
+		case 0xAF: /* Sierra Forest */
+		case 0x4D: /* Avaton, Rangely */
+		case 0x5F: /* Denverton */
+		case 0x86: /* Jacobsville */
+			flags = INST_RETIRED_OVERCOUNT | BR_RETIRED_OVERCOUNT;
+			break;
+		}
+	}
+
+	return flags;
+}
+
 int main(int ac, char **av)
 {
 	int instruction_idx;
@@ -985,6 +1030,8 @@ int main(int ac, char **av)
 		branch_idx = INTEL_BRANCHES_IDX;
 		branch_miss_idx = INTEL_BRANCH_MISS_IDX;
 
+		intel_inst_overcount_flags = detect_inst_overcount_flags();
+
 		/*
 		 * For legacy Intel CPUS without clflush/clflushopt support,
 		 * there is no way to force to trigger a LLC miss, thus set
-- 
2.34.1