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 <mingo@elte.hu>

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

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

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 */

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)
 

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) */

arch/powerpc/include/asm/trace.h

+#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>

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
@@ -786,7 +786,7 @@ 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
@@ -794,7 +794,7 @@ int fix_alignment(struct pt_regs *regs)
 	 * 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

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

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
 

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)

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,
 		};
 

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

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;

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;

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;

arch/powerpc/kernel/ppc970-pmu.c

@@ -83,10 +83,6 @@ static short mmcr1_adder_bits[8] = {
 	MMCR1_PMC8_ADDER_SEL_SH
 };
 
-/*
- * Bits in MMCRA
- */
-
 /*
  * Layout of constraint bits:
  * 6666555555555544444444443333333333222222222211111111110000000000

arch/powerpc/kernel/setup-common.c

@@ -660,6 +660,7 @@ late_initcall(check_cache_coherency);
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *powerpc_debugfs_root;
+EXPORT_SYMBOL(powerpc_debugfs_root);
 
 static int powerpc_debugfs_init(void)
 {

arch/powerpc/kernel/time.c

@@ -54,6 +54,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/perf_event.h>
+#include <asm/trace.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -571,6 +572,8 @@ void timer_interrupt(struct pt_regs * regs)
 	struct clock_event_device *evt = &decrementer->event;
 	u64 now;
 
+	trace_timer_interrupt_entry(regs);
+
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continuue to take decrementer exceptions */
 	set_dec(DECREMENTER_MAX);
@@ -590,6 +593,7 @@ void timer_interrupt(struct pt_regs * regs)
 		now = decrementer->next_tb - now;
 		if (now <= DECREMENTER_MAX)
 			set_dec((int)now);
+		trace_timer_interrupt_exit(regs);
 		return;
 	}
 	old_regs = set_irq_regs(regs);
@@ -620,6 +624,8 @@ void timer_interrupt(struct pt_regs * regs)
 
 	irq_exit();
 	set_irq_regs(old_regs);
+
+	trace_timer_interrupt_exit(regs);
 }
 
 void wakeup_decrementer(void)

arch/powerpc/kernel/traps.c

@@ -759,7 +759,7 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate the mfspr rD, PVR. */
 	if ((instword & PPC_INST_MFSPR_PVR_MASK) == PPC_INST_MFSPR_PVR) {
-		PPC_WARN_EMULATED(mfpvr);
+		PPC_WARN_EMULATED(mfpvr, regs);
 		rd = (instword >> 21) & 0x1f;
 		regs->gpr[rd] = mfspr(SPRN_PVR);
 		return 0;
@@ -767,7 +767,7 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulating the dcba insn is just a no-op.  */
 	if ((instword & PPC_INST_DCBA_MASK) == PPC_INST_DCBA) {
-		PPC_WARN_EMULATED(dcba);
+		PPC_WARN_EMULATED(dcba, regs);
 		return 0;
 	}
 
@@ -776,7 +776,7 @@ static int emulate_instruction(struct pt_regs *regs)
 		int shift = (instword >> 21) & 0x1c;
 		unsigned long msk = 0xf0000000UL >> shift;
 
-		PPC_WARN_EMULATED(mcrxr);
+		PPC_WARN_EMULATED(mcrxr, regs);
 		regs->ccr = (regs->ccr & ~msk) | ((regs->xer >> shift) & msk);
 		regs->xer &= ~0xf0000000UL;
 		return 0;
@@ -784,19 +784,19 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate load/store string insn. */
 	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
-		PPC_WARN_EMULATED(string);
+		PPC_WARN_EMULATED(string, regs);
 		return emulate_string_inst(regs, instword);
 	}
 
 	/* Emulate the popcntb (Population Count Bytes) instruction. */
 	if ((instword & PPC_INST_POPCNTB_MASK) == PPC_INST_POPCNTB) {
-		PPC_WARN_EMULATED(popcntb);
+		PPC_WARN_EMULATED(popcntb, regs);
 		return emulate_popcntb_inst(regs, instword);
 	}
 
 	/* Emulate isel (Integer Select) instruction */
 	if ((instword & PPC_INST_ISEL_MASK) == PPC_INST_ISEL) {
-		PPC_WARN_EMULATED(isel);
+		PPC_WARN_EMULATED(isel, regs);
 		return emulate_isel(regs, instword);
 	}
 
@@ -995,7 +995,7 @@ void SoftwareEmulation(struct pt_regs *regs)
 #ifdef CONFIG_MATH_EMULATION
 	errcode = do_mathemu(regs);
 	if (errcode >= 0)
-		PPC_WARN_EMULATED(math);
+		PPC_WARN_EMULATED(math, regs);
 
 	switch (errcode) {
 	case 0:
@@ -1018,7 +1018,7 @@ void SoftwareEmulation(struct pt_regs *regs)
 #elif defined(CONFIG_8XX_MINIMAL_FPEMU)
 	errcode = Soft_emulate_8xx(regs);
 	if (errcode >= 0)
-		PPC_WARN_EMULATED(8xx);
+		PPC_WARN_EMULATED(8xx, regs);
 
 	switch (errcode) {
 	case 0:
@@ -1129,7 +1129,7 @@ void altivec_assist_exception(struct pt_regs *regs)
 
 	flush_altivec_to_thread(current);
 
-	PPC_WARN_EMULATED(altivec);
+	PPC_WARN_EMULATED(altivec, regs);
 	err = emulate_altivec(regs);
 	if (err == 0) {
 		regs->nip += 4;		/* skip emulated instruction */

arch/powerpc/lib/copypage_64.S

@@ -26,11 +26,11 @@ BEGIN_FTR_SECTION
 	srd	r8,r5,r11
 
 	mtctr	r8
-setup:
+.Lsetup:
 	dcbt	r9,r4
 	dcbz	r9,r3
 	add	r9,r9,r12
-	bdnz	setup
+	bdnz	.Lsetup
 END_FTR_SECTION_IFSET(CPU_FTR_CP_USE_DCBTZ)
 	addi	r3,r3,-8
 	srdi    r8,r5,7		/* page is copied in 128 byte strides */

arch/powerpc/platforms/pseries/hvCall.S

@@ -14,68 +14,94 @@
 	
 #define STK_PARM(i)     (48 + ((i)-3)*8)
 
-#ifdef CONFIG_HCALL_STATS
+#ifdef CONFIG_TRACEPOINTS
+
+	.section	".toc","aw"
+
+	.globl hcall_tracepoint_refcount
+hcall_tracepoint_refcount:
+	.llong	0
+
+	.section	".text"
+
 /*
  * precall must preserve all registers.  use unused STK_PARM()
- * areas to save snapshots and opcode.
+ * areas to save snapshots and opcode. We branch around this
+ * in early init (eg when populating the MMU hashtable) by using an
+ * unconditional cpu feature.
  */
-#define HCALL_INST_PRECALL					\
-	std	r3,STK_PARM(r3)(r1);	/* save opcode */	\
-	mftb	r0;			/* get timebase and */	\
-	std     r0,STK_PARM(r5)(r1);	/* save for later */	\
+#define HCALL_INST_PRECALL(FIRST_REG)				\
 BEGIN_FTR_SECTION;						\
-	mfspr	r0,SPRN_PURR;		/* get PURR and */	\
-	std	r0,STK_PARM(r6)(r1);	/* save for later */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);
-	
+	b	1f;						\
+END_FTR_SECTION(0, 1);						\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	std	r3,STK_PARM(r3)(r1);				\
+	std	r4,STK_PARM(r4)(r1);				\
+	std	r5,STK_PARM(r5)(r1);				\
+	std	r6,STK_PARM(r6)(r1);				\
+	std	r7,STK_PARM(r7)(r1);				\
+	std	r8,STK_PARM(r8)(r1);				\
+	std	r9,STK_PARM(r9)(r1);				\
+	std	r10,STK_PARM(r10)(r1);				\
+	std	r0,16(r1);					\
+	addi	r4,r1,STK_PARM(FIRST_REG);			\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_entry;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	ld	r4,STK_PARM(r4)(r1);				\
+	ld	r5,STK_PARM(r5)(r1);				\
+	ld	r6,STK_PARM(r6)(r1);				\
+	ld	r7,STK_PARM(r7)(r1);				\
+	ld	r8,STK_PARM(r8)(r1);				\
+	ld	r9,STK_PARM(r9)(r1);				\
+	ld	r10,STK_PARM(r10)(r1);				\
+	mtlr	r0;						\
+1:
+
 /*
  * postcall is performed immediately before function return which
  * allows liberal use of volatile registers.  We branch around this
  * in early init (eg when populating the MMU hashtable) by using an
  * unconditional cpu feature.
  */
-#define HCALL_INST_POSTCALL					\
+#define __HCALL_INST_POSTCALL					\
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r4,STK_PARM(r3)(r1);	/* validate opcode */	\
-	cmpldi	cr7,r4,MAX_HCALL_OPCODE;			\
-	bgt-	cr7,1f;						\
-								\
-	/* get time and PURR snapshots after hcall */		\
-	mftb	r7;			/* timebase after */	\
-BEGIN_FTR_SECTION;						\
-	mfspr	r8,SPRN_PURR;		/* PURR after */	\
-	ld	r6,STK_PARM(r6)(r1);	/* PURR before */	\
-	subf	r6,r6,r8;		/* delta */		\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
-	ld	r5,STK_PARM(r5)(r1);	/* timebase before */	\
-	subf	r5,r5,r7;		/* time delta */	\
-								\
-	/* calculate address of stat structure r4 = opcode */	\
-	srdi	r4,r4,2;		/* index into array */	\
-	mulli	r4,r4,HCALL_STAT_SIZE;				\
-	LOAD_REG_ADDR(r7, per_cpu__hcall_stats);		\
-	add	r4,r4,r7;					\
-	ld	r7,PACA_DATA_OFFSET(r13); /* per cpu offset */	\
-	add	r4,r4,r7;					\
-								\
-	/* update stats	*/					\
-	ld	r7,HCALL_STAT_CALLS(r4); /* count */		\
-	addi	r7,r7,1;					\
-	std	r7,HCALL_STAT_CALLS(r4);			\
-	ld      r7,HCALL_STAT_TB(r4);	/* timebase */		\
-	add	r7,r7,r5;					\
-	std	r7,HCALL_STAT_TB(r4);				\
-BEGIN_FTR_SECTION;						\
-	ld	r7,HCALL_STAT_PURR(r4);	/* PURR */		\
-	add	r7,r7,r6;					\
-	std	r7,HCALL_STAT_PURR(r4);				\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
+	ld      r12,hcall_tracepoint_refcount@toc(r2);		\
+	cmpdi	r12,0;						\
+	beq+	1f;						\
+	mflr	r0;						\
+	ld	r6,STK_PARM(r3)(r1);				\
+	std	r3,STK_PARM(r3)(r1);				\
+	mr	r4,r3;						\
+	mr	r3,r6;						\
+	std	r0,16(r1);					\
+	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
+	bl	.__trace_hcall_exit;				\
+	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
+	ld	r0,16(r1);					\
+	ld	r3,STK_PARM(r3)(r1);				\
+	mtlr	r0;						\
 1:
+
+#define HCALL_INST_POSTCALL_NORETS				\
+	li	r5,0;						\
+	__HCALL_INST_POSTCALL
+
+#define HCALL_INST_POSTCALL(BUFREG)				\
+	mr	r5,BUFREG;					\
+	__HCALL_INST_POSTCALL
+
 #else
-#define HCALL_INST_PRECALL
-#define HCALL_INST_POSTCALL
+#define HCALL_INST_PRECALL(FIRST_ARG)
+#define HCALL_INST_POSTCALL_NORETS
+#define HCALL_INST_POSTCALL(BUFREG)
 #endif
 
 	.text
@@ -86,11 +112,11 @@ _GLOBAL(plpar_hcall_norets)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r4)
 
 	HVSC				/* invoke the hypervisor */
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL_NORETS
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -102,7 +128,7 @@ _GLOBAL(plpar_hcall)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -121,7 +147,7 @@ _GLOBAL(plpar_hcall)
 	std	r6, 16(r12)
 	std	r7, 24(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
@@ -168,7 +194,7 @@ _GLOBAL(plpar_hcall9)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL
+	HCALL_INST_PRECALL(r5)
 
 	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
 
@@ -196,7 +222,7 @@ _GLOBAL(plpar_hcall9)
 	std	r11,56(r12)
 	std	r0, 64(r12)
 
-	HCALL_INST_POSTCALL
+	HCALL_INST_POSTCALL(r12)
 
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0

arch/powerpc/platforms/pseries/hvCall_inst.c

@@ -26,6 +26,7 @@
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
 #include <asm/cputable.h>
+#include <asm/trace.h>
 
 DEFINE_PER_CPU(struct hcall_stats[HCALL_STAT_ARRAY_SIZE], hcall_stats);
 
@@ -100,6 +101,35 @@ static const struct file_operations hcall_inst_seq_fops = {
 #define	HCALL_ROOT_DIR		"hcall_inst"
 #define CPU_NAME_BUF_SIZE	32
 
+
+static void probe_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &get_cpu_var(hcall_stats)[opcode / 4];
+	h->tb_start = mftb();
+	h->purr_start = mfspr(SPRN_PURR);
+}
+
+static void probe_hcall_exit(unsigned long opcode, unsigned long retval,
+			     unsigned long *retbuf)
+{
+	struct hcall_stats *h;
+
+	if (opcode > MAX_HCALL_OPCODE)
+		return;
+
+	h = &__get_cpu_var(hcall_stats)[opcode / 4];
+	h->num_calls++;
+	h->tb_total = mftb() - h->tb_start;
+	h->purr_total = mfspr(SPRN_PURR) - h->purr_start;
+
+	put_cpu_var(hcall_stats);
+}
+
 static int __init hcall_inst_init(void)
 {
 	struct dentry *hcall_root;
@@ -110,6 +140,14 @@ static int __init hcall_inst_init(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR))
 		return 0;
 
+	if (register_trace_hcall_entry(probe_hcall_entry))
+		return -EINVAL;
+
+	if (register_trace_hcall_exit(probe_hcall_exit)) {
+		unregister_trace_hcall_entry(probe_hcall_entry);
+		return -EINVAL;
+	}
+
 	hcall_root = debugfs_create_dir(HCALL_ROOT_DIR, NULL);
 	if (!hcall_root)
 		return -ENOMEM;

arch/powerpc/platforms/pseries/lpar.c

@@ -39,6 +39,7 @@
 #include <asm/cputable.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/trace.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
@@ -661,3 +662,35 @@ void arch_free_page(struct page *page, int order)
 EXPORT_SYMBOL(arch_free_page);
 
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+/*
+ * We optimise our hcall path by placing hcall_tracepoint_refcount
+ * directly in the TOC so we can check if the hcall tracepoints are
+ * enabled via a single load.
+ */
+
+/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
+extern long hcall_tracepoint_refcount;
+
+void hcall_tracepoint_regfunc(void)
+{
+	hcall_tracepoint_refcount++;
+}
+
+void hcall_tracepoint_unregfunc(void)
+{
+	hcall_tracepoint_refcount--;
+}
+
+void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
+{
+	trace_hcall_entry(opcode, args);
+}
+
+void __trace_hcall_exit(long opcode, unsigned long retval,
+			unsigned long *retbuf)
+{
+	trace_hcall_exit(opcode, retval, retbuf);
+}
+#endif

include/linux/perf_counter.h

@@ -106,6 +106,8 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };

include/linux/perf_event.h

@@ -102,6 +102,8 @@ enum perf_sw_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS		= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN		= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ		= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS		= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS		= 8,
 
 	PERF_COUNT_SW_MAX,			/* non-ABI */
 };

kernel/perf_event.c

@@ -4274,6 +4274,8 @@ static const struct pmu *sw_perf_event_init(struct perf_event *event)
 	case PERF_COUNT_SW_PAGE_FAULTS_MAJ:
 	case PERF_COUNT_SW_CONTEXT_SWITCHES:
 	case PERF_COUNT_SW_CPU_MIGRATIONS:
+	case PERF_COUNT_SW_ALIGNMENT_FAULTS:
+	case PERF_COUNT_SW_EMULATION_FAULTS:
 		if (!event->parent) {
 			atomic_inc(&perf_swevent_enabled[event_id]);
 			event->destroy = sw_perf_event_destroy;

tools/perf/Documentation/perf-bench.txt

+perf-bench(1)
+============
+
+NAME
+----
+perf-bench - General framework for benchmark suites
+
+SYNOPSIS
+--------
+[verse]
+'perf bench' [<common options>] <subsystem> <suite> [<options>]
+
+DESCRIPTION
+-----------
+This 'perf bench' command is general framework for benchmark suites.
+
+COMMON OPTIONS
+--------------
+-f::
+--format=::
+Specify format style.
+Current available format styles are,
+
+'default'::
+Default style. This is mainly for human reading.
+---------------------
+% perf bench sched pipe                      # with no style specify
+(executing 1000000 pipe operations between two tasks)
+        Total time:5.855 sec
+                5.855061 usecs/op
+		170792 ops/sec
+---------------------
+
+'simple'::
+This simple style is friendly for automated
+processing by scripts.
+---------------------
+% perf bench --format=simple sched pipe      # specified simple
+5.988
+---------------------
+
+SUBSYSTEM
+---------
+
+'sched'::
+	Scheduler and IPC mechanisms.
+
+SUITES FOR 'sched'
+~~~~~~~~~~~~~~~~~~
+*messaging*::
+Suite for evaluating performance of scheduler and IPC mechanisms.
+Based on hackbench by Rusty Russell.
+
+Options of *pipe*
+^^^^^^^^^^^^^^^^^
+-p::
+--pipe::
+Use pipe() instead of socketpair()
+
+-t::
+--thread::
+Be multi thread instead of multi process
+
+-g::
+--group=::
+Specify number of groups
+
+-l::
+--loop=::
+Specify number of loops
+
+Example of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched messaging                 # run with default
+options (20 sender and receiver processes per group)
+(10 groups == 400 processes run)
+
+      Total time:0.308 sec
+
+% perf bench sched messaging -t -g 20        # be multi-thread,with 20 groups
+(20 sender and receiver threads per group)
+(20 groups == 800 threads run)
+
+      Total time:0.582 sec
+---------------------
+
+*pipe*::
+Suite for pipe() system call.
+Based on pipe-test-1m.c by Ingo Molnar.
+
+Options of *pipe*
+^^^^^^^^^^^^^^^^^
+-l::
+--loop=::
+Specify number of loops.
+
+Example of *pipe*
+^^^^^^^^^^^^^^^^^
+
+---------------------
+% perf bench sched pipe
+(executing 1000000 pipe operations between two tasks)
+
+        Total time:8.091 sec
+                8.091833 usecs/op
+                123581 ops/sec
+
+% perf bench sched pipe -l 1000              # loop 1000
+(executing 1000 pipe operations between two tasks)
+
+        Total time:0.016 sec
+                16.948000 usecs/op
+                59004 ops/sec
+---------------------
+
+SEE ALSO
+--------
+linkperf:perf[1]

tools/perf/Makefile

@@ -421,6 +421,13 @@ LIB_OBJS += util/hist.o
 LIB_OBJS += util/data_map.o
 
 BUILTIN_OBJS += builtin-annotate.o
+
+BUILTIN_OBJS += builtin-bench.o
+
+# Benchmark modules
+BUILTIN_OBJS += bench/sched-messaging.o
+BUILTIN_OBJS += bench/sched-pipe.o
+
 BUILTIN_OBJS += builtin-help.o
 BUILTIN_OBJS += builtin-sched.o
 BUILTIN_OBJS += builtin-list.o

tools/perf/bench/bench.h

+#ifndef BENCH_H
+#define BENCH_H
+
+extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
+extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
+
+#define BENCH_FORMAT_DEFAULT_STR	"default"
+#define BENCH_FORMAT_DEFAULT		0
+#define BENCH_FORMAT_SIMPLE_STR		"simple"
+#define BENCH_FORMAT_SIMPLE		1
+
+#define BENCH_FORMAT_UNKNOWN		-1
+
+extern int bench_format;
+
+#endif

tools/perf/bench/sched-messaging.c

+/*
+ *
+ * builtin-bench-messaging.c
+ *
+ * messaging: Benchmark for scheduler and IPC mechanisms
+ *
+ * Based on hackbench by Rusty Russell <rusty@rustcorp.com.au>
+ * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../builtin.h"
+#include "bench.h"
+
+/* Test groups of 20 processes spraying to 20 receivers */
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <sys/time.h>
+#include <sys/poll.h>
+#include <limits.h>
+
+#define DATASIZE 100
+
+static int use_pipes = 0;
+static unsigned int loops = 100;
+static unsigned int thread_mode = 0;
+static unsigned int num_groups = 10;
+
+struct sender_context {
+	unsigned int num_fds;
+	int ready_out;
+	int wakefd;
+	int out_fds[0];
+};
+
+struct receiver_context {
+	unsigned int num_packets;
+	int in_fds[2];
+	int ready_out;
+	int wakefd;
+};
+
+static void barf(const char *msg)
+{
+	fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
+	exit(1);
+}
+
+static void fdpair(int fds[2])
+{
+	if (use_pipes) {
+		if (pipe(fds) == 0)
+			return;
+	} else {
+		if (socketpair(AF_UNIX, SOCK_STREAM, 0, fds) == 0)
+			return;
+	}
+
+	barf(use_pipes ? "pipe()" : "socketpair()");
+}
+
+/* Block until we're ready to go */
+static void ready(int ready_out, int wakefd)
+{
+	char dummy;
+	struct pollfd pollfd = { .fd = wakefd, .events = POLLIN };
+
+	/* Tell them we're ready. */
+	if (write(ready_out, &dummy, 1) != 1)
+		barf("CLIENT: ready write");
+
+	/* Wait for "GO" signal */
+	if (poll(&pollfd, 1, -1) != 1)
+		barf("poll");
+}
+
+/* Sender sprays loops messages down each file descriptor */
+static void *sender(struct sender_context *ctx)
+{
+	char data[DATASIZE];
+	unsigned int i, j;
+
+	ready(ctx->ready_out, ctx->wakefd);
+
+	/* Now pump to every receiver. */
+	for (i = 0; i < loops; i++) {
+		for (j = 0; j < ctx->num_fds; j++) {
+			int ret, done = 0;
+
+again:
+			ret = write(ctx->out_fds[j], data + done,
+				    sizeof(data)-done);
+			if (ret < 0)
+				barf("SENDER: write");
+			done += ret;
+			if (done < DATASIZE)
+				goto again;
+		}
+	}
+
+	return NULL;
+}
+
+
+/* One receiver per fd */
+static void *receiver(struct receiver_context* ctx)
+{
+	unsigned int i;
+
+	if (!thread_mode)
+		close(ctx->in_fds[1]);
+
+	/* Wait for start... */
+	ready(ctx->ready_out, ctx->wakefd);
+
+	/* Receive them all */
+	for (i = 0; i < ctx->num_packets; i++) {
+		char data[DATASIZE];
+		int ret, done = 0;
+
+again:
+		ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
+		if (ret < 0)
+			barf("SERVER: read");
+		done += ret;
+		if (done < DATASIZE)
+			goto again;
+	}
+
+	return NULL;
+}
+
+static pthread_t create_worker(void *ctx, void *(*func)(void *))
+{
+	pthread_attr_t attr;
+	pthread_t childid;
+	int err;
+
+	if (!thread_mode) {
+		/* process mode */
+		/* Fork the receiver. */
+		switch (fork()) {
+		case -1:
+			barf("fork()");
+			break;
+		case 0:
+			(*func) (ctx);
+			exit(0);
+			break;
+		default:
+			break;
+		}
+
+		return (pthread_t)0;
+	}
+
+	if (pthread_attr_init(&attr) != 0)
+		barf("pthread_attr_init:");
+
+#ifndef __ia64__
+	if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
+		barf("pthread_attr_setstacksize");
+#endif
+
+	err = pthread_create(&childid, &attr, func, ctx);
+	if (err != 0) {
+		fprintf(stderr, "pthread_create failed: %s (%d)\n",
+			strerror(err), err);
+		exit(-1);
+	}
+	return childid;
+}
+
+static void reap_worker(pthread_t id)
+{
+	int proc_status;
+	void *thread_status;
+
+	if (!thread_mode) {
+		/* process mode */
+		wait(&proc_status);
+		if (!WIFEXITED(proc_status))
+			exit(1);
+	} else {
+		pthread_join(id, &thread_status);
+	}
+}
+
+/* One group of senders and receivers */
+static unsigned int group(pthread_t *pth,
+		unsigned int num_fds,
+		int ready_out,
+		int wakefd)
+{
+	unsigned int i;
+	struct sender_context *snd_ctx = malloc(sizeof(struct sender_context)
+			+ num_fds * sizeof(int));
+
+	if (!snd_ctx)
+		barf("malloc()");
+
+	for (i = 0; i < num_fds; i++) {
+		int fds[2];
+		struct receiver_context *ctx = malloc(sizeof(*ctx));
+
+		if (!ctx)
+			barf("malloc()");
+
+
+		/* Create the pipe between client and server */
+		fdpair(fds);
+
+		ctx->num_packets = num_fds * loops;
+		ctx->in_fds[0] = fds[0];
+		ctx->in_fds[1] = fds[1];
+		ctx->ready_out = ready_out;
+		ctx->wakefd = wakefd;
+
+		pth[i] = create_worker(ctx, (void *)receiver);
+
+		snd_ctx->out_fds[i] = fds[1];
+		if (!thread_mode)
+			close(fds[0]);
+	}
+
+	/* Now we have all the fds, fork the senders */
+	for (i = 0; i < num_fds; i++) {
+		snd_ctx->ready_out = ready_out;
+		snd_ctx->wakefd = wakefd;
+		snd_ctx->num_fds = num_fds;
+
+		pth[num_fds+i] = create_worker(snd_ctx, (void *)sender);
+	}
+
+	/* Close the fds we have left */
+	if (!thread_mode)
+		for (i = 0; i < num_fds; i++)
+			close(snd_ctx->out_fds[i]);
+
+	/* Return number of children to reap */
+	return num_fds * 2;
+}
+
+static const struct option options[] = {
+	OPT_BOOLEAN('p', "pipe", &use_pipes,
+		    "Use pipe() instead of socketpair()"),
+	OPT_BOOLEAN('t', "thread", &thread_mode,
+		    "Be multi thread instead of multi process"),
+	OPT_INTEGER('g', "group", &num_groups,
+		    "Specify number of groups"),
+	OPT_INTEGER('l', "loop", &loops,
+		    "Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_sched_message_usage[] = {
+	"perf bench sched messaging <options>",
+	NULL
+};
+
+int bench_sched_messaging(int argc, const char **argv,
+		    const char *prefix __used)
+{
+	unsigned int i, total_children;
+	struct timeval start, stop, diff;
+	unsigned int num_fds = 20;
+	int readyfds[2], wakefds[2];
+	char dummy;
+	pthread_t *pth_tab;
+
+	argc = parse_options(argc, argv, options,
+			     bench_sched_message_usage, 0);
+
+	pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
+	if (!pth_tab)
+		barf("main:malloc()");
+
+	fdpair(readyfds);
+	fdpair(wakefds);
+
+	total_children = 0;
+	for (i = 0; i < num_groups; i++)
+		total_children += group(pth_tab+total_children, num_fds,
+					readyfds[1], wakefds[0]);
+
+	/* Wait for everyone to be ready */
+	for (i = 0; i < total_children; i++)
+		if (read(readyfds[0], &dummy, 1) != 1)
+			barf("Reading for readyfds");
+
+	gettimeofday(&start, NULL);
+
+	/* Kick them off */
+	if (write(wakefds[1], &dummy, 1) != 1)
+		barf("Writing to start them");
+
+	/* Reap them all */
+	for (i = 0; i < total_children; i++)
+		reap_worker(pth_tab[i]);
+
+	gettimeofday(&stop, NULL);
+
+	timersub(&stop, &start, &diff);
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# %d sender and receiver %s per group\n",
+		       num_fds, thread_mode ? "threads" : "processes");
+		printf("# %d groups == %d %s run\n\n",
+		       num_groups, num_groups * 2 * num_fds,
+		       thread_mode ? "threads" : "processes");
+		printf(" %14s: %lu.%03lu [sec]\n", "Total time",
+		       diff.tv_sec, diff.tv_usec/1000);
+		break;
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n", diff.tv_sec, diff.tv_usec/1000);
+		break;
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}

tools/perf/bench/sched-pipe.c

+/*
+ *
+ * builtin-bench-pipe.c
+ *
+ * pipe: Benchmark for pipe()
+ *
+ * Based on pipe-test-1m.c by Ingo Molnar <mingo@redhat.com>
+ *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
+ * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+#include "../builtin.h"
+#include "bench.h"
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sys/wait.h>
+#include <linux/unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/time.h>
+#include <sys/types.h>
+
+#define LOOPS_DEFAULT 1000000
+static int loops = LOOPS_DEFAULT;
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop", &loops,
+		    "Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_sched_pipe_usage[] = {
+	"perf bench sched pipe <options>",
+	NULL
+};
+
+int bench_sched_pipe(int argc, const char **argv,
+		     const char *prefix __used)
+{
+	int pipe_1[2], pipe_2[2];
+	int m = 0, i;
+	struct timeval start, stop, diff;
+	unsigned long long result_usec = 0;
+
+	/*
+	 * why does "ret" exist?
+	 * discarding returned value of read(), write()
+	 * causes error in building environment for perf
+	 */
+	int ret, wait_stat;
+	pid_t pid, retpid;
+
+	argc = parse_options(argc, argv, options,
+			     bench_sched_pipe_usage, 0);
+
+	assert(!pipe(pipe_1));
+	assert(!pipe(pipe_2));
+
+	pid = fork();
+	assert(pid >= 0);
+
+	gettimeofday(&start, NULL);
+
+	if (!pid) {
+		for (i = 0; i < loops; i++) {
+			ret = read(pipe_1[0], &m, sizeof(int));
+			ret = write(pipe_2[1], &m, sizeof(int));
+		}
+	} else {
+		for (i = 0; i < loops; i++) {
+			ret = write(pipe_1[1], &m, sizeof(int));
+			ret = read(pipe_2[0], &m, sizeof(int));
+		}
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	if (pid) {
+		retpid = waitpid(pid, &wait_stat, 0);
+		assert((retpid == pid) && WIFEXITED(wait_stat));
+		return 0;
+	}
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		printf("# Extecuted %d pipe operations between two tasks\n\n",
+			loops);
+
+		result_usec = diff.tv_sec * 1000000;
+		result_usec += diff.tv_usec;
+
+		printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
+		       diff.tv_sec, diff.tv_usec/1000);
+
+		printf(" %14lf usecs/op\n",
+		       (double)result_usec / (double)loops);
+		printf(" %14d ops/sec\n",
+		       (int)((double)loops /
+			     ((double)result_usec / (double)1000000)));
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%lu.%03lu\n",
+		       diff.tv_sec, diff.tv_usec / 1000);
+		break;
+
+	default:
+		/* reaching here is something disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+		break;
+	}
+
+	return 0;
+}

tools/perf/builtin-bench.c

+/*
+ *
+ * builtin-bench.c
+ *
+ * General benchmarking subsystem provided by perf
+ *
+ * Copyright (C) 2009, Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
+ *
+ */
+
+/*
+ *
+ * Available subsystem list:
+ *  sched ... scheduler and IPC mechanism
+ *
+ */
+
+#include "perf.h"
+#include "util/util.h"
+#include "util/parse-options.h"
+#include "builtin.h"
+#include "bench/bench.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+struct bench_suite {
+	const char *name;
+	const char *summary;
+	int (*fn)(int, const char **, const char *);
+};
+
+static struct bench_suite sched_suites[] = {
+	{ "messaging",
+	  "Benchmark for scheduler and IPC mechanisms",
+	  bench_sched_messaging },
+	{ "pipe",
+	  "Flood of communication over pipe() between two processes",
+	  bench_sched_pipe      },
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+
+struct bench_subsys {
+	const char *name;
+	const char *summary;
+	struct bench_suite *suites;
+};
+
+static struct bench_subsys subsystems[] = {
+	{ "sched",
+	  "scheduler and IPC mechanism",
+	  sched_suites },
+	{ NULL,
+	  NULL,
+	  NULL         }
+};
+
+static void dump_suites(int subsys_index)
+{
+	int i;
+
+	printf("List of available suites for %s...\n\n",
+	       subsystems[subsys_index].name);
+
+	for (i = 0; subsystems[subsys_index].suites[i].name; i++)
+		printf("\t%s: %s\n",
+		       subsystems[subsys_index].suites[i].name,
+		       subsystems[subsys_index].suites[i].summary);
+
+	printf("\n");
+	return;
+}
+
+static char *bench_format_str;
+int bench_format = BENCH_FORMAT_DEFAULT;
+
+static const struct option bench_options[] = {
+	OPT_STRING('f', "format", &bench_format_str, "default",
+		    "Specify format style"),
+	OPT_END()
+};
+
+static const char * const bench_usage[] = {
+	"perf bench [<common options>] <subsystem> <suite> [<options>]",
+	NULL
+};
+
+static void print_usage(void)
+{
+	int i;
+
+	printf("Usage: \n");
+	for (i = 0; bench_usage[i]; i++)
+		printf("\t%s\n", bench_usage[i]);
+	printf("\n");
+
+	printf("List of available subsystems...\n\n");
+
+	for (i = 0; subsystems[i].name; i++)
+		printf("\t%s: %s\n",
+		       subsystems[i].name, subsystems[i].summary);
+	printf("\n");
+}
+
+static int bench_str2int(char *str)
+{
+	if (!str)
+		return BENCH_FORMAT_DEFAULT;
+
+	if (!strcmp(str, BENCH_FORMAT_DEFAULT_STR))
+		return BENCH_FORMAT_DEFAULT;
+	else if (!strcmp(str, BENCH_FORMAT_SIMPLE_STR))
+		return BENCH_FORMAT_SIMPLE;
+
+	return BENCH_FORMAT_UNKNOWN;
+}
+
+int cmd_bench(int argc, const char **argv, const char *prefix __used)
+{
+	int i, j, status = 0;
+
+	if (argc < 2) {
+		/* No subsystem specified. */
+		print_usage();
+		goto end;
+	}
+
+	argc = parse_options(argc, argv, bench_options, bench_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	bench_format = bench_str2int(bench_format_str);
+	if (bench_format == BENCH_FORMAT_UNKNOWN) {
+		printf("Unknown format descriptor:%s\n", bench_format_str);
+		goto end;
+	}
+
+	if (argc < 1) {
+		print_usage();
+		goto end;
+	}
+
+	for (i = 0; subsystems[i].name; i++) {
+		if (strcmp(subsystems[i].name, argv[0]))
+			continue;
+
+		if (argc < 2) {
+			/* No suite specified. */
+			dump_suites(i);
+			goto end;
+		}
+
+		for (j = 0; subsystems[i].suites[j].name; j++) {
+			if (strcmp(subsystems[i].suites[j].name, argv[1]))
+				continue;
+
+			if (bench_format == BENCH_FORMAT_DEFAULT)
+				printf("# Running %s/%s benchmark...\n",
+				       subsystems[i].name,
+				       subsystems[i].suites[j].name);
+			status = subsystems[i].suites[j].fn(argc - 1,
+							    argv + 1, prefix);
+			goto end;
+		}
+
+		if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help")) {
+			dump_suites(i);
+			goto end;
+		}
+
+		printf("Unknown suite:%s for %s\n", argv[1], argv[0]);
+		status = 1;
+		goto end;
+	}
+
+	printf("Unknown subsystem:%s\n", argv[0]);
+	status = 1;
+
+end:
+	return status;
+}

tools/perf/builtin.h

@@ -15,6 +15,7 @@ extern int read_line_with_nul(char *buf, int size, FILE *file);
 extern int check_pager_config(const char *cmd);
 
 extern int cmd_annotate(int argc, const char **argv, const char *prefix);
+extern int cmd_bench(int argc, const char **argv, const char *prefix);
 extern int cmd_help(int argc, const char **argv, const char *prefix);
 extern int cmd_sched(int argc, const char **argv, const char *prefix);
 extern int cmd_list(int argc, const char **argv, const char *prefix);

tools/perf/command-list.txt

@@ -3,6 +3,7 @@
 # command name			category [deprecated] [common]
 #
 perf-annotate			mainporcelain common
+perf-bench			mainporcelain common
 perf-list			mainporcelain common
 perf-sched			mainporcelain common
 perf-record			mainporcelain common

tools/perf/design.txt

@@ -137,6 +137,8 @@ enum sw_event_ids {
 	PERF_COUNT_SW_CPU_MIGRATIONS	= 4,
 	PERF_COUNT_SW_PAGE_FAULTS_MIN	= 5,
 	PERF_COUNT_SW_PAGE_FAULTS_MAJ	= 6,
+	PERF_COUNT_SW_ALIGNMENT_FAULTS	= 7,
+	PERF_COUNT_SW_EMULATION_FAULTS	= 8,
 };
 
 Counters of the type PERF_TYPE_TRACEPOINT are available when the ftrace event

tools/perf/perf.c

@@ -289,6 +289,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "list", cmd_list, 0 },
 		{ "record", cmd_record, 0 },
 		{ "report", cmd_report, 0 },
+		{ "bench", cmd_bench, 0 },
 		{ "stat", cmd_stat, 0 },
 		{ "timechart", cmd_timechart, 0 },
 		{ "top", cmd_top, 0 },

tools/perf/util/parse-events.c

@@ -48,6 +48,8 @@ static struct event_symbol event_symbols[] = {
   { CSW(PAGE_FAULTS_MAJ),	"major-faults",		""		},
   { CSW(CONTEXT_SWITCHES),	"context-switches",	"cs"		},
   { CSW(CPU_MIGRATIONS),	"cpu-migrations",	"migrations"	},
+  { CSW(ALIGNMENT_FAULTS),	"alignment-faults",	""		},
+  { CSW(EMULATION_FAULTS),	"emulation-faults",	""		},
 };
 
 #define __PERF_EVENT_FIELD(config, name) \
@@ -76,6 +78,8 @@ static const char *sw_event_names[] = {
 	"CPU-migrations",
 	"minor-faults",
 	"major-faults",
+	"alignment-faults",
+	"emulation-faults",
 };
 
 #define MAX_ALIASES 8