Merge branches 'perf/powerpc' and 'perf/bench' into perf/core

Merge reason: Both 'perf bench' and the pending PowerPC changes are now ready for the next merge window. Signed-off-by: Ingo Molnar <[email protected]>
mrcsosa · Nov 15, 2009 · 0ffa798 · 0ffa798
3 parents 39dc78b + c86e2ea + c5659b7
commit 0ffa798
Show file tree

Hide file tree

Showing 37 changed files with 1,146 additions and 96 deletions.
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
@@ -46,7 +46,7 @@ config DEBUG_STACK_USAGE
 
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
-	depends on PPC_PSERIES && DEBUG_FS
+	depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS
 	help
 	  Adds code to keep track of the number of hypervisor calls made and
 	  the amount of time spent in hypervisor calls.  Wall time spent in

diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
@@ -1683,7 +1683,7 @@ CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 # CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_DEBUG_PAGEALLOC is not set
-CONFIG_HCALL_STATS=y
+# CONFIG_HCALL_STATS is not set
 # CONFIG_CODE_PATCHING_SELFTEST is not set
 # CONFIG_FTR_FIXUP_SELFTEST is not set
 # CONFIG_MSI_BITMAP_SELFTEST is not set

diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
@@ -19,6 +19,7 @@
 #define _ASM_POWERPC_EMULATED_OPS_H
 
 #include <asm/atomic.h>
+#include <linux/perf_event.h>
 
 
 #ifdef CONFIG_PPC_EMULATED_STATS
@@ -57,7 +58,7 @@ extern u32 ppc_warn_emulated;
 
 extern void ppc_warn_emulated_print(const char *type);
 
-#define PPC_WARN_EMULATED(type)						 \
+#define __PPC_WARN_EMULATED(type)					 \
 	do {								 \
 		atomic_inc(&ppc_emulated.type.val);			 \
 		if (ppc_warn_emulated)					 \
@@ -66,8 +67,22 @@ extern void ppc_warn_emulated_print(const char *type);
 
 #else /* !CONFIG_PPC_EMULATED_STATS */
 
-#define PPC_WARN_EMULATED(type)	do { } while (0)
+#define __PPC_WARN_EMULATED(type)	do { } while (0)
 
 #endif /* !CONFIG_PPC_EMULATED_STATS */
 
+#define PPC_WARN_EMULATED(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
+			1, 0, regs, 0);					\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#define PPC_WARN_ALIGNMENT(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
+			1, 0, regs, regs->dar);				\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
 #endif /* _ASM_POWERPC_EMULATED_OPS_H */
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
@@ -274,6 +274,8 @@ struct hcall_stats {
 	unsigned long	num_calls;	/* number of calls (on this CPU) */
 	unsigned long	tb_total;	/* total wall time (mftb) of calls. */
 	unsigned long	purr_total;	/* total cpu time (PURR) of calls. */
+	unsigned long	tb_start;
+	unsigned long	purr_start;
 };
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
@@ -489,6 +489,8 @@
 #define SPRN_MMCR1	798
 #define SPRN_MMCRA	0x312
 #define   MMCRA_SDSYNC	0x80000000UL /* SDAR synced with SIAR */
+#define   MMCRA_SDAR_DCACHE_MISS 0x40000000UL
+#define   MMCRA_SDAR_ERAT_MISS   0x20000000UL
 #define   MMCRA_SIHV	0x10000000UL /* state of MSR HV when SIAR set */
 #define   MMCRA_SIPR	0x08000000UL /* state of MSR PR when SIAR set */
 #define   MMCRA_SLOT	0x07000000UL /* SLOT bits (37-39) */

diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
@@ -0,0 +1,133 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM powerpc
+
+#if !defined(_TRACE_POWERPC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWERPC_H
+
+#include <linux/tracepoint.h>
+
+struct pt_regs;
+
+TRACE_EVENT(irq_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(irq_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_entry,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+TRACE_EVENT(timer_interrupt_exit,
+
+	TP_PROTO(struct pt_regs *regs),
+
+	TP_ARGS(regs),
+
+	TP_STRUCT__entry(
+		__field(struct pt_regs *, regs)
+	),
+
+	TP_fast_assign(
+		__entry->regs = regs;
+	),
+
+	TP_printk("pt_regs=%p", __entry->regs)
+);
+
+#ifdef CONFIG_PPC_PSERIES
+extern void hcall_tracepoint_regfunc(void);
+extern void hcall_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN(hcall_entry,
+
+	TP_PROTO(unsigned long opcode, unsigned long *args),
+
+	TP_ARGS(opcode, args),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+	),
+
+	TP_printk("opcode=%lu", __entry->opcode),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+
+TRACE_EVENT_FN(hcall_exit,
+
+	TP_PROTO(unsigned long opcode, unsigned long retval,
+		unsigned long *retbuf),
+
+	TP_ARGS(opcode, retval, retbuf),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, opcode)
+		__field(unsigned long, retval)
+	),
+
+	TP_fast_assign(
+		__entry->opcode = opcode;
+		__entry->retval = retval;
+	),
+
+	TP_printk("opcode=%lu retval=%lu", __entry->opcode, __entry->retval),
+
+	hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc
+);
+#endif
+
+#endif /* _TRACE_POWERPC_H */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+
+#define TRACE_INCLUDE_PATH asm
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
@@ -732,7 +732,7 @@ int fix_alignment(struct pt_regs *regs)
 
 #ifdef CONFIG_SPE
 	if ((instr >> 26) == 0x4) {
-		PPC_WARN_EMULATED(spe);
+		PPC_WARN_ALIGNMENT(spe, regs);
 		return emulate_spe(regs, reg, instr);
 	}
 #endif
@@ -786,15 +786,15 @@ int fix_alignment(struct pt_regs *regs)
 			flags |= SPLT;
 			nb = 8;
 		}
-		PPC_WARN_EMULATED(vsx);
+		PPC_WARN_ALIGNMENT(vsx, regs);
 		return emulate_vsx(addr, reg, areg, regs, flags, nb);
 	}
 #endif
 	/* A size of 0 indicates an instruction we don't support, with
 	 * the exception of DCBZ which is handled as a special case here
 	 */
 	if (instr == DCBZ) {
-		PPC_WARN_EMULATED(dcbz);
+		PPC_WARN_ALIGNMENT(dcbz, regs);
 		return emulate_dcbz(regs, addr);
 	}
 	if (unlikely(nb == 0))
@@ -804,7 +804,7 @@ int fix_alignment(struct pt_regs *regs)
 	 * function
 	 */
 	if (flags & M) {
-		PPC_WARN_EMULATED(multiple);
+		PPC_WARN_ALIGNMENT(multiple, regs);
 		return emulate_multiple(regs, addr, reg, nb,
 					flags, instr, swiz);
 	}
@@ -825,11 +825,11 @@ int fix_alignment(struct pt_regs *regs)
 
 	/* Special case for 16-byte FP loads and stores */
 	if (nb == 16) {
-		PPC_WARN_EMULATED(fp_pair);
+		PPC_WARN_ALIGNMENT(fp_pair, regs);
 		return emulate_fp_pair(addr, reg, flags);
 	}
 
-	PPC_WARN_EMULATED(unaligned);
+	PPC_WARN_ALIGNMENT(unaligned, regs);
 
 	/* If we are loading, get the data from user space, else
 	 * get it from register values

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
@@ -551,7 +551,7 @@ restore:
 BEGIN_FW_FTR_SECTION
 	ld	r5,SOFTE(r1)
 FW_FTR_SECTION_ELSE
-	b	iseries_check_pending_irqs
+	b	.Liseries_check_pending_irqs
 ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 2:
 	TRACE_AND_RESTORE_IRQ(r5);
@@ -623,7 +623,7 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 
 #endif /* CONFIG_PPC_BOOK3E */
 
-iseries_check_pending_irqs:
+.Liseries_check_pending_irqs:
 #ifdef CONFIG_PPC_ISERIES
 	ld	r5,SOFTE(r1)
 	cmpdi	0,r5,0

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
@@ -185,12 +185,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 * prolog code of the PerformanceMonitor one. A little
 	 * trickery is thus necessary
 	 */
+performance_monitor_pSeries_1:
 	. = 0xf00
 	b	performance_monitor_pSeries
 
+altivec_unavailable_pSeries_1:
 	. = 0xf20
 	b	altivec_unavailable_pSeries
 
+vsx_unavailable_pSeries_1:
 	. = 0xf40
 	b	vsx_unavailable_pSeries
 

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
@@ -70,6 +70,8 @@
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
 #endif
+#define CREATE_TRACE_POINTS
+#include <asm/trace.h>
 
 int __irq_offset_value;
 static int ppc_spurious_interrupts;
@@ -325,6 +327,8 @@ void do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned int irq;
 
+	trace_irq_entry(regs);
+
 	irq_enter();
 
 	check_stack_overflow();
@@ -348,6 +352,8 @@ void do_IRQ(struct pt_regs *regs)
 		timer_interrupt(regs);
 	}
 #endif
+
+	trace_irq_exit(regs);
 }
 
 void __init init_IRQ(void)

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
@@ -1165,7 +1165,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	 */
 	if (record) {
 		struct perf_sample_data data = {
-			.addr	= 0,
+			.addr	= ~0ULL,
 			.period	= event->hw.last_period,
 		};
 

diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
@@ -72,10 +72,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0x7f
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000

diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
@@ -72,10 +72,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0x7f
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
@@ -390,7 +386,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			       unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	unsigned int pmc, unit, byte, psel;
 	unsigned int ttm, grp;
 	int i, isbus, bit, grsel;

diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
@@ -178,7 +178,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
 			   unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	int i;
 	unsigned int pmc, ev, b, u, s, psel;
 	unsigned int ttmset = 0;

diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
@@ -50,10 +50,6 @@
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0xff
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000
@@ -230,7 +226,7 @@ static int power7_compute_mmcr(u64 event[], int n_ev,
 			       unsigned int hwc[], unsigned long mmcr[])
 {
 	unsigned long mmcr1 = 0;
-	unsigned long mmcra = 0;
+	unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS;
 	unsigned int pmc, unit, combine, l2sel, psel;
 	unsigned int pmc_inuse = 0;
 	int i;