[PATCH 05/12] perf_events: add LBR mappings for PERF_SAMPLE_BRANCH filters

[Stephane Eranian <eranian@google.com>]

This patch adds the mappings from the generic PERF_SAMPLE_BRANCH_*
filters to the actual Intel X86 LBR filters, whenever they exist.

The patch also adds a restriction on Intel Atom, whereby only
stepping 10 (PineView) and more recent are supported. Older models,
do not have a functional LBR (does not freeze on PMU interrupt).

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c     |    2 +-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  110 +++++++++++++++++++++++++++-
 2 files changed, 109 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index e2639f4..740857f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1612,7 +1612,7 @@ static __init int intel_pmu_init(void)
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
-		intel_pmu_lbr_init_nhm();
+		intel_pmu_lbr_init_snb();
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_events;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index e8a6851..abcabe3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -8,6 +8,47 @@ enum {
 };
 
 /*
+ * Intel LBR_SELECT bits
+ * Intel Vol3a, April 2011, Section 16.7 Table 16-10
+ *
+ * Hardware branch filter (not available on all CPUs)
+ */
+#define LBR_KERNEL_BIT		0 /* do not capture at ring0 */
+#define LBR_USER_BIT		1 /* do not capture at ring > 0 */
+#define LBR_JCC_BIT		2 /* do not capture conditional branches */
+#define LBR_REL_CALL_BIT	3 /* do not capture relative calls */
+#define LBR_IND_CALL_BIT	4 /* do not capture indirect calls */
+#define LBR_RETURN_BIT		5 /* do not capture near returns */
+#define LBR_IND_JMP_BIT		6 /* do not capture indirect jumps */
+#define LBR_REL_JMP_BIT		7 /* do not capture relative jumps */
+#define LBR_FAR_BIT		8 /* do not capture far branches */
+
+#define LBR_KERNEL	(1 << LBR_KERNEL_BIT)
+#define LBR_USER	(1 << LBR_USER_BIT)
+#define LBR_JCC		(1 << LBR_JCC_BIT)
+#define LBR_REL_CALL	(1 << LBR_REL_CALL_BIT)
+#define LBR_IND_CALL	(1 << LBR_IND_CALL_BIT)
+#define LBR_RETURN	(1 << LBR_RETURN_BIT)
+#define LBR_REL_JMP	(1 << LBR_REL_JMP_BIT)
+#define LBR_IND_JMP	(1 << LBR_IND_JMP_BIT)
+#define LBR_FAR		(1 << LBR_FAR_BIT)
+
+#define LBR_PLM (LBR_KERNEL | LBR_USER)
+
+#define LBR_SEL_MASK	0x1ff /* valid bits in LBR_SELECT */
+
+#define LBR_ANY		 \
+	(LBR_JCC	|\
+	 LBR_REL_CALL	|\
+	 LBR_IND_CALL	|\
+	 LBR_RETURN	|\
+	 LBR_REL_JMP	|\
+	 LBR_IND_JMP	|\
+	 LBR_FAR)
+
+#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
+
+/*
  * We only support LBR implementations that have FREEZE_LBRS_ON_PMI
  * otherwise it becomes near impossible to get a reliable stack.
  */
@@ -147,8 +188,6 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 	cpuc->lbr_stack.nr = i;
 }
 
-#define LBR_FROM_FLAG_MISPRED  (1ULL << 63)
-
 /*
  * Due to lack of segmentation in Linux the effective address (offset)
  * is the same as the linear address, allowing us to merge the LIP and EIP
@@ -196,28 +235,95 @@ static void intel_pmu_lbr_read(void)
 		intel_pmu_lbr_read_64(cpuc);
 }
 
+/*
+ * Map interface branch filters onto LBR filters
+ */
+static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX]=
+{
+	[PERF_SAMPLE_BRANCH_ANY]        = LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]       = LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]     = LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN] =
+		LBR_RETURN | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
+	 */
+	[PERF_SAMPLE_BRANCH_ANY_CALL] =
+		LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
+	/*
+	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
+	 */
+	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+};
+
+static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX]=
+{
+	[PERF_SAMPLE_BRANCH_ANY]        = LBR_ANY,
+	[PERF_SAMPLE_BRANCH_USER]       = LBR_USER,
+	[PERF_SAMPLE_BRANCH_KERNEL]     = LBR_KERNEL,
+	[PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_ANY_CALL]   = LBR_REL_CALL | LBR_IND_CALL | LBR_FAR,
+	[PERF_SAMPLE_BRANCH_IND_CALL]   = LBR_IND_CALL,
+};
+
+/* core */
 static void intel_pmu_lbr_init_core(void)
 {
 	x86_pmu.lbr_nr     = 4;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	pr_cont("4-deep LBR, ");
 }
 
+/* nehalem/westmere */
 static void intel_pmu_lbr_init_nhm(void)
 {
 	x86_pmu.lbr_nr     = 16;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_NHM_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = nhm_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
+}
+
+/* sandy bridge */
+static void intel_pmu_lbr_init_snb(void)
+{
+	x86_pmu.lbr_nr	 = 16;
+	x86_pmu.lbr_tos	 = MSR_LBR_TOS;
+	x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+	x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
+
+	x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+	x86_pmu.lbr_sel_map  = snb_lbr_sel_map;
+
+	pr_cont("16-deep LBR, ");
 }
 
+/* atom */
 static void intel_pmu_lbr_init_atom(void)
 {
+	/*
+	 * only models starting at stepping 10 seems
+	 * to have an operational LBR which can freeze
+	 * on PMU interrupt
+	 */
+	if (boot_cpu_data.x86_mask < 10) {
+		pr_cont("LBR disabled due to erratum");
+		return;
+	}
+
 	x86_pmu.lbr_nr	   = 8;
 	x86_pmu.lbr_tos    = MSR_LBR_TOS;
 	x86_pmu.lbr_from   = MSR_LBR_CORE_FROM;
 	x86_pmu.lbr_to     = MSR_LBR_CORE_TO;
+
+	pr_cont("8-deep LBR, ");
 }
 
 #endif /* CONFIG_CPU_SUP_INTEL */
-- 
1.7.4.1