powerpc: add 2 additional performance counters for e6500 core

There are 6 counters in e6500 core instead of 4 in e500 core.
Correct the typos in counter enumeration.
Some of the codes are based on Priyanka Jain's patch.
e6500 core performance monitors has the following features:
- 6 performance monitor counters
- none restricted access
- 512 events supported

Signed-off-by: Lijun Pan <Lijun.Pan@freescale.com>
Change-Id: Ia8a5f17087028752f2984e61c2c8abd823d27639
Reviewed-on: http://git.am.freescale.net:8181/1638
Reviewed-by: Wood Scott-B07421 <scottwood@freescale.com>
Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>

6 files changed, 195 insertions, 7 deletions

diff --git a/arch/powerpc/include/asm/reg_fsl_emb.h b/arch/powerpc/include/asm/reg_fsl_emb.h
index 77bb71c..0e3ddf5 100644
--- a/arch/powerpc/include/asm/reg_fsl_emb.h
+++ b/arch/powerpc/include/asm/reg_fsl_emb.h
@@ -17,12 +17,16 @@
 /* Freescale Book E Performance Monitor APU Registers */
 #define PMRN_PMC0	0x010	/* Performance Monitor Counter 0 */
 #define PMRN_PMC1	0x011	/* Performance Monitor Counter 1 */
-#define PMRN_PMC2	0x012	/* Performance Monitor Counter 1 */
-#define PMRN_PMC3	0x013	/* Performance Monitor Counter 1 */
+#define PMRN_PMC2	0x012	/* Performance Monitor Counter 2 */
+#define PMRN_PMC3	0x013	/* Performance Monitor Counter 3 */
+#define PMRN_PMC4	0x014	/* Performance Monitor Counter 4 */
+#define PMRN_PMC5	0x015	/* Performance Monitor Counter 5 */
 #define PMRN_PMLCA0	0x090	/* PM Local Control A0 */
 #define PMRN_PMLCA1	0x091	/* PM Local Control A1 */
 #define PMRN_PMLCA2	0x092	/* PM Local Control A2 */
 #define PMRN_PMLCA3	0x093	/* PM Local Control A3 */
+#define PMRN_PMLCA4	0x094	/* PM Local Control A4 */
+#define PMRN_PMLCA5	0x095	/* PM Local Control A5 */
 
 #define PMLCA_FC	0x80000000	/* Freeze Counter */
 #define PMLCA_FCS	0x40000000	/* Freeze in Supervisor */
@@ -30,14 +34,18 @@
 #define PMLCA_FCM1	0x10000000	/* Freeze when PMM==1 */
 #define PMLCA_FCM0	0x08000000	/* Freeze when PMM==0 */
 #define PMLCA_CE	0x04000000	/* Condition Enable */
+#define PMLCA_FGCS1	0x00000002	/* Freeze in guest state */
+#define PMLCA_FGCS0	0x00000001	/* Freeze in hypervisor state */
 
-#define PMLCA_EVENT_MASK 0x00ff0000	/* Event field */
+#define PMLCA_EVENT_MASK 0x01ff0000	/* Event field */
 #define PMLCA_EVENT_SHIFT	16
 
 #define PMRN_PMLCB0	0x110	/* PM Local Control B0 */
 #define PMRN_PMLCB1	0x111	/* PM Local Control B1 */
 #define PMRN_PMLCB2	0x112	/* PM Local Control B2 */
 #define PMRN_PMLCB3	0x113	/* PM Local Control B3 */
+#define PMRN_PMLCB4	0x114	/* PM Local Control B4 */
+#define PMRN_PMLCB5	0x115	/* PM Local Control B5 */
 
 #define PMLCB_THRESHMUL_MASK	0x0700	/* Threshold Multiple Field */
 #define PMLCB_THRESHMUL_SHIFT	8
@@ -55,16 +63,22 @@
 
 #define PMRN_UPMC0	0x000	/* User Performance Monitor Counter 0 */
 #define PMRN_UPMC1	0x001	/* User Performance Monitor Counter 1 */
-#define PMRN_UPMC2	0x002	/* User Performance Monitor Counter 1 */
-#define PMRN_UPMC3	0x003	/* User Performance Monitor Counter 1 */
+#define PMRN_UPMC2	0x002	/* User Performance Monitor Counter 2 */
+#define PMRN_UPMC3	0x003	/* User Performance Monitor Counter 3 */
+#define PMRN_UPMC4	0x004	/* User Performance Monitor Counter 4 */
+#define PMRN_UPMC5	0x005	/* User Performance Monitor Counter 5 */
 #define PMRN_UPMLCA0	0x080	/* User PM Local Control A0 */
 #define PMRN_UPMLCA1	0x081	/* User PM Local Control A1 */
 #define PMRN_UPMLCA2	0x082	/* User PM Local Control A2 */
 #define PMRN_UPMLCA3	0x083	/* User PM Local Control A3 */
+#define PMRN_UPMLCA4	0x084	/* User PM Local Control A4 */
+#define PMRN_UPMLCA5	0x085	/* User PM Local Control A5 */
 #define PMRN_UPMLCB0	0x100	/* User PM Local Control B0 */
 #define PMRN_UPMLCB1	0x101	/* User PM Local Control B1 */
 #define PMRN_UPMLCB2	0x102	/* User PM Local Control B2 */
 #define PMRN_UPMLCB3	0x103	/* User PM Local Control B3 */
+#define PMRN_UPMLCB4	0x104	/* User PM Local Control B4 */
+#define PMRN_UPMLCB5	0x105	/* User PM Local Control B5 */
 #define PMRN_UPMGC0	0x180	/* User PM Global Control 0 */
 
 
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 5d116d0..5f9ecfe 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2078,7 +2078,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 			MMU_FTR_USE_TLBILX,
 		.icache_bsize		= 64,
 		.dcache_bsize		= 64,
-		.num_pmcs		= 4,
+		.num_pmcs		= 6,
 		.oprofile_cpu_type	= "ppc/e6500",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
 		.cpu_setup		= __setup_cpu_e6500,
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index ccc1daa..2a82d3e 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -46,6 +46,12 @@ static inline u32 get_pmlca(int ctr)
 		case 3:
 			pmlca = mfpmr(PMRN_PMLCA3);
 			break;
+		case 4:
+			pmlca = mfpmr(PMRN_PMLCA4);
+			break;
+		case 5:
+			pmlca = mfpmr(PMRN_PMLCA5);
+			break;
 		default:
 			panic("Bad ctr number\n");
 	}
@@ -68,6 +74,12 @@ static inline void set_pmlca(int ctr, u32 pmlca)
 		case 3:
 			mtpmr(PMRN_PMLCA3, pmlca);
 			break;
+		case 4:
+			mtpmr(PMRN_PMLCA4, pmlca);
+			break;
+		case 5:
+			mtpmr(PMRN_PMLCA5, pmlca);
+			break;
 		default:
 			panic("Bad ctr number\n");
 	}
@@ -84,6 +96,10 @@ static inline unsigned int ctr_read(unsigned int i)
 			return mfpmr(PMRN_PMC2);
 		case 3:
 			return mfpmr(PMRN_PMC3);
+		case 4:
+			return mfpmr(PMRN_PMC4);
+		case 5:
+			return mfpmr(PMRN_PMC5);
 		default:
 			return 0;
 	}
@@ -104,6 +120,12 @@ static inline void ctr_write(unsigned int i, unsigned int val)
 		case 3:
 			mtpmr(PMRN_PMC3, val);
 			break;
+		case 4:
+			mtpmr(PMRN_PMC4, val);
+			break;
+		case 5:
+			mtpmr(PMRN_PMC5, val);
+			break;
 		default:
 			break;
 	}
@@ -133,6 +155,14 @@ static void init_pmc_stop(int ctr)
 			mtpmr(PMRN_PMLCA3, pmlca);
 			mtpmr(PMRN_PMLCB3, pmlcb);
 			break;
+		case 4:
+			mtpmr(PMRN_PMLCA4, pmlca);
+			mtpmr(PMRN_PMLCB4, pmlcb);
+			break;
+		case 5:
+			mtpmr(PMRN_PMLCA5, pmlca);
+			mtpmr(PMRN_PMLCB5, pmlcb);
+			break;
 		default:
 			panic("Bad ctr number!\n");
 	}
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index af3fac2..06dd8d5 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -8,7 +8,7 @@ obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
-obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
+obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 106c533..a81e666 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -70,6 +70,12 @@ static unsigned long read_pmc(int idx)
 	case 3:
 		val = mfpmr(PMRN_PMC3);
 		break;
+	case 4:
+		val = mfpmr(PMRN_PMC4);
+		break;
+	case 5:
+		val = mfpmr(PMRN_PMC5);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to read PMC%d\n", idx);
 		val = 0;
@@ -95,6 +101,12 @@ static void write_pmc(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMC3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMC4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMC5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
 	}
@@ -120,6 +132,12 @@ static void write_pmlca(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMLCA3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMLCA4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMLCA5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMLCA%d\n", idx);
 	}
@@ -145,6 +163,12 @@ static void write_pmlcb(int idx, unsigned long val)
 	case 3:
 		mtpmr(PMRN_PMLCB3, val);
 		break;
+	case 4:
+		mtpmr(PMRN_PMLCB4, val);
+		break;
+	case 5:
+		mtpmr(PMRN_PMLCB5, val);
+		break;
 	default:
 		printk(KERN_ERR "oops trying to write PMLCB%d\n", idx);
 	}
diff --git a/arch/powerpc/perf/e6500-pmu.c b/arch/powerpc/perf/e6500-pmu.c
new file mode 100644
index 0000000..795a565
--- /dev/null
+++ b/arch/powerpc/perf/e6500-pmu.c
@@ -0,0 +1,120 @@
+/*
+ * Performance counter support for e6500 family processors.
+ *
+ * Author: Lijun Pan
+ * Based on Priyanka Jain's code
+ * Based on e500-pmu.c
+ * Copyright 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/string.h>
+#include <linux/perf_event.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+/*
+ * Map of generic hardware event types to hardware events
+ * Zero if unsupported
+ */
+static int e6500_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES] = 1,
+	[PERF_COUNT_HW_INSTRUCTIONS] = 2,
+	[PERF_COUNT_HW_CACHE_MISSES] = 221,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
+	[PERF_COUNT_HW_BRANCH_MISSES] = 15,
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int e6500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	27,		222	},
+		[C(OP_WRITE)] = {	28,		223	},
+		[C(OP_PREFETCH)] = {	29,		0	},
+	},
+	[C(L1I)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	2,		254	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	37,		0	},
+	},
+	/*
+	 * Assuming LL means L2, it's not a good match for this model.
+	 * It does not have separate read/write events (but it does have
+	 * separate instruction/data events).
+	 */
+	[C(LL)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	/*
+	 * There are data/instruction MMU misses, but that's a miss on
+	 * the chip's internal level-one TLB which is probably not
+	 * what the user wants.  Instead, unified level-two TLB misses
+	 * are reported here.
+	 */
+	[C(DTLB)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	26,		66	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {
+				/*RESULT_ACCESS		RESULT_MISS */
+		[C(OP_READ)] = {	12,		15	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(NODE)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	-1,		-1 	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+static int num_events = 512;
+
+/* Upper half of event id is PMLCb, for threshold events */
+static u64 e6500_xlate_event(u64 event_id)
+{
+	u32 event_low = (u32)event_id;
+	if ((event_low >= num_events) ||
+		(event_id & (FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)))
+		return 0;
+
+	return FSL_EMB_EVENT_VALID;
+}
+
+static struct fsl_emb_pmu e6500_pmu = {
+	.name			= "e6500 family",
+	.n_counter		= 6,
+	.n_restricted		= 0,
+	.xlate_event		= e6500_xlate_event,
+	.n_generic		= ARRAY_SIZE(e6500_generic_events),
+	.generic_events		= e6500_generic_events,
+	.cache_events		= &e6500_cache_events,
+};
+
+static int init_e6500_pmu(void)
+{
+	if ((!cur_cpu_spec->oprofile_cpu_type) ||
+		(strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/e6500")))
+		return -ENODEV;
+
+	return register_fsl_emb_pmu(&e6500_pmu);
+}
+
+early_initcall(init_e6500_pmu);