[OPROFILE] First cut at oprofile support for Alpha.

arch/alpha/Kconfig

@@ -942,6 +942,7 @@ source "drivers/usb/Kconfig"
 
 source "net/bluetooth/Kconfig"
 
+source "arch/alpha/oprofile/Kconfig"
 
 menu "Kernel hacking"
 

arch/alpha/Makefile

@@ -92,9 +92,10 @@ CFLAGS := $(CFLAGS) -Wa,-mev6
 
 HEAD := arch/alpha/kernel/head.o
 
-core-y			+= arch/alpha/kernel/ arch/alpha/mm/
-core-$(CONFIG_MATHEMU)  += arch/alpha/math-emu/
-libs-y			+= arch/alpha/lib/
+core-y				+= arch/alpha/kernel/ arch/alpha/mm/
+core-$(CONFIG_MATHEMU)		+= arch/alpha/math-emu/
+drivers-$(CONFIG_OPROFILE)	+= arch/alpha/oprofile/
+libs-y				+= arch/alpha/lib/
 
 export libs-y
 

arch/alpha/kernel/irq_alpha.c

@@ -74,7 +74,7 @@ do_entInt(unsigned long type, unsigned long vector,
 		alpha_mv.device_interrupt(vector, regs);
 		return;
 	case 4:
-		perf_irq(vector, regs);
+		perf_irq(la_ptr, regs);
 		return;
 	default:
 		printk(KERN_CRIT "Hardware intr %ld %lx? Huh?\n",

arch/alpha/oprofile/Kconfig

+
+menu "Profiling support"
+	depends on EXPERIMENTAL
+
+config PROFILING
+	bool "Profiling support (EXPERIMENTAL)"
+	help
+	  Say Y here to enable the extended profiling support mechanisms used
+	  by profilers such as OProfile.
+	  
+
+config OPROFILE
+	tristate "OProfile system profiling (EXPERIMENTAL)"
+	depends on PROFILING
+	help
+	  OProfile is a profiling system capable of profiling the
+	  whole system, include the kernel, kernel modules, libraries,
+	  and applications.
+
+	  If unsure, say N.
+
+endmenu
+

arch/alpha/oprofile/Makefile

+obj-$(CONFIG_OPROFILE) += oprofile.o
+
+DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
+		oprof.o cpu_buffer.o buffer_sync.o \
+		event_buffer.o oprofile_files.o \
+		oprofilefs.o oprofile_stats.o )
+
+oprofile-y				:= $(DRIVER_OBJS) common.o
+oprofile-$(CONFIG_ALPHA_GENERIC)	+= op_model_ev4.o \
+					   op_model_ev5.o \
+					   op_model_ev6.o
+oprofile-$(CONFIG_ALPHA_EV4)		+= op_model_ev4.o
+oprofile-$(CONFIG_ALPHA_EV5)		+= op_model_ev5.o
+oprofile-$(CONFIG_ALPHA_EV6)		+= op_model_ev6.o

arch/alpha/oprofile/common.c

+/**
+ * @file arch/alpha/oprofile/common.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author Richard Henderson <rth@twiddle.net>
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+
+#include "op_impl.h"
+
+extern struct op_axp_model op_model_ev4 __attribute__((weak));
+extern struct op_axp_model op_model_ev5 __attribute__((weak));
+extern struct op_axp_model op_model_pca56 __attribute__((weak));
+extern struct op_axp_model op_model_ev6 __attribute__((weak));
+
+static struct op_axp_model *model;
+
+extern void (*perf_irq)(unsigned long, struct pt_regs *);
+static void (*save_perf_irq)(unsigned long, struct pt_regs *);
+
+static struct op_counter_config ctr[3];
+static struct op_system_config sys;
+static struct op_register_config reg;
+
+/* Called from do_entInt to handle the performance monitor interrupt.  */
+
+static void
+op_handle_interrupt(unsigned long which, struct pt_regs *regs)
+{
+	/* EV4 can't properly disable counters individually.
+	   Discard "disabled" events now.  */
+	if (!ctr[which].enabled)
+		return;
+
+	/* Record the sample.  */
+	oprofile_add_sample(regs->pc, which, smp_processor_id());
+
+	/* If the user has selected an interrupt frequency that is
+	   not exactly the width of the counter, write a new value
+	   into the counter such that it'll overflow after N more
+	   events.  */
+	if ((reg.need_reset >> which) & 1)
+		model->reset_ctr(&reg, which);
+}
+ 
+static int
+op_axp_setup(void)
+{
+	unsigned long i, e;
+
+	/* Install our interrupt handler into the existing hook.  */
+	save_perf_irq = perf_irq;
+	perf_irq = op_handle_interrupt;
+
+	/* Compute the mask of enabled counters.  */
+	for (i = e = 0; i < model->num_counters; ++i)
+		if (ctr[0].enabled)
+			e |= 1 << i;
+	reg.enable = e;
+
+	/* Pre-compute the values to stuff in the hardware registers.  */
+	model->reg_setup(&reg, ctr, &sys);
+
+	/* Configure the registers on all cpus.  */
+	smp_call_function(model->cpu_setup, &reg, 0, 1);
+	model->cpu_setup(&reg);
+	return 0;
+}
+
+static void
+op_axp_shutdown(void)
+{
+	/* Remove our interrupt handler.  We may be removing this module.  */
+	perf_irq = save_perf_irq;
+}
+
+static void
+op_axp_cpu_start(void *dummy)
+{
+	wrperfmon(1, reg.enable);
+}
+
+static int
+op_axp_start(void)
+{
+	smp_call_function(op_axp_cpu_start, NULL, 0, 1);
+	op_axp_cpu_start(NULL);
+	return 0;
+}
+
+static inline void
+op_axp_cpu_stop(void *dummy)
+{
+	/* Disable performance monitoring for all counters.  */
+	wrperfmon(0, -1);
+}
+
+static void
+op_axp_stop(void)
+{
+	smp_call_function(op_axp_cpu_stop, NULL, 0, 1);
+	op_axp_cpu_stop(NULL);
+}
+
+static int
+op_axp_create_files(struct super_block * sb, struct dentry * root)
+{
+	int i;
+
+	for (i = 0; i < model->num_counters; ++i) {
+		struct dentry *dir;
+		char buf[2];
+
+		buf[0] = i + '0';
+		buf[1] = 0;
+		dir = oprofilefs_mkdir(sb, root, buf);
+
+		oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
+                oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
+		oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+	}
+
+	if (model->can_set_proc_mode) {
+		oprofilefs_create_ulong(sb, root, "enable_pal",
+					&sys.enable_pal);
+		oprofilefs_create_ulong(sb, root, "enable_kernel",
+					&sys.enable_kernel);
+		oprofilefs_create_ulong(sb, root, "enable_user",
+					&sys.enable_user);
+	}
+
+	return 0;
+}
+
+static struct oprofile_operations oprof_axp_ops = {
+	.create_files	= op_axp_create_files,
+	.setup		= op_axp_setup,
+	.shutdown	= op_axp_shutdown,
+	.start		= op_axp_start,
+	.stop		= op_axp_stop
+};
+
+int __init
+oprofile_arch_init(struct oprofile_operations **ops, enum oprofile_cpu *cpu)
+{
+	switch (implver()) {
+	case IMPLVER_EV4:
+		model = &op_model_ev4;
+		break;
+	case IMPLVER_EV5:
+		/* 21164PC has a slightly different set of events.
+		   Recognize the chip by the presence of the MAX insns.  */
+		if (!amask(AMASK_MAX))
+			model = &op_model_pca56;
+		else
+			model = &op_model_ev5;
+		break;
+	case IMPLVER_EV6:
+		model = &op_model_ev6;
+		break;
+	default:
+		model = NULL;
+	}
+
+	if (!model)
+		return ENODEV;
+
+	*ops = &oprof_axp_ops;
+	*cpu = model->cpu;
+	return 0;
+}

arch/alpha/oprofile/op_impl.h

+/**
+ * @file arch/alpha/oprofile/op_impl.h
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author Richard Henderson <rth@twiddle.net>
+ */
+
+#ifndef OP_IMPL_H
+#define OP_IMPL_H 1
+
+/* Per-counter configuration as set via oprofilefs.  */
+struct op_counter_config {
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long count;
+};
+
+/* System-wide configuration as set via oprofilefs.  */
+struct op_system_config {
+	unsigned long enable_pal;
+	unsigned long enable_kernel;
+	unsigned long enable_user;
+};
+
+/* Cached values for the various performance monitoring registers.  */
+struct op_register_config {
+	unsigned long enable;
+	unsigned long mux_select;
+	unsigned long proc_mode;
+	unsigned long freq;
+	unsigned long reset_values;
+	unsigned long need_reset;
+};
+
+/* Per-architecture configury and hooks.  */
+struct op_axp_model {
+	void (*reg_setup) (struct op_register_config *,
+			   struct op_counter_config *,
+			   struct op_system_config *);
+	void (*cpu_setup) (void *);
+	void (*reset_ctr) (struct op_register_config *, unsigned long);
+	enum oprofile_cpu cpu;
+	unsigned char num_counters;
+	unsigned char can_set_proc_mode;
+};
+
+#endif

arch/alpha/oprofile/op_model_ev4.c

+/**
+ * @file arch/alpha/oprofile/op_model_ev4.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author Richard Henderson <rth@twiddle.net>
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <asm/system.h>
+
+#include "op_impl.h"
+
+
+/* Compute all of the registers in preparation for enabling profiling.  */
+
+static void
+ev4_reg_setup(struct op_register_config *reg,
+	      struct op_counter_config *ctr,
+	      struct op_system_config *sys)
+{
+	unsigned long ctl = 0, count, hilo;
+
+	/* Select desired events.  We've mapped the event numbers
+	   such that they fit directly into the event selection fields.
+
+	   Note that there is no "off" setting.  In both cases we select
+	   the EXTERNAL event source, hoping that it'll be the lowest
+	   frequency, and set the frequency counter to LOW.  The interrupts
+	   for these "disabled" counter overflows are ignored by the
+	   interrupt handler.
+
+	   This is most irritating, becuase the hardware *can* enable and
+	   disable the interrupts for these counters independently, but the
+	   wrperfmon interface doesn't allow it.  */
+
+	ctl |= (ctr[0].enabled ? ctr[0].event << 8 : 14 << 8);
+	ctl |= (ctr[1].enabled ? (ctr[1].event - 16) << 32 : 7ul << 32);
+
+	/* EV4 can not read or write its counter registers.  The only
+	   thing one can do at all is see if you overflow and get an
+	   interrupt.  We can set the width of the counters, to some
+	   extent.  Take the interrupt count selected by the user,
+	   map it onto one of the possible values, and write it back.  */
+
+	count = ctr[0].count;
+	if (count <= 4096)
+		count = 4096, hilo = 1;
+	else
+		count = 65536, hilo = 0;
+	ctr[0].count = count;
+	ctl |= (ctr[0].enabled && hilo) << 3;
+
+	count = ctr[1].count;
+	if (count <= 256)
+		count = 256, hilo = 1;
+	else
+		count = 4096, hilo = 0;
+	ctr[1].count = count;
+	ctl |= (ctr[1].enabled && hilo);
+
+	reg->mux_select = ctl;
+
+	/* Select performance monitoring options.  */
+	/* ??? Need to come up with some mechanism to trace only
+	   selected processes.  EV4 does not have a mechanism to
+	   select kernel or user mode only.  For now, enable always.  */
+	reg->proc_mode = 0;
+
+	/* Frequency is folded into mux_select for EV4.  */
+	reg->freq = 0;
+
+	/* See above regarding no writes.  */
+	reg->reset_values = 0;
+	reg->need_reset = 0;
+
+}
+
+/* Program all of the registers in preparation for enabling profiling.  */
+
+static void
+ev4_cpu_setup(void *x)
+{
+	struct op_register_config *reg = x;
+
+	wrperfmon(2, reg->mux_select);
+	wrperfmon(3, reg->proc_mode);
+}
+
+struct op_axp_model op_model_ev4 = {
+	.reg_setup		= ev4_reg_setup,
+	.cpu_setup		= ev4_cpu_setup,
+	.reset_ctr		= NULL,
+	.cpu			= OPROFILE_CPU_AXP_EV4,
+	.num_counters		= 2,
+	.can_set_proc_mode	= 0,
+};

arch/alpha/oprofile/op_model_ev5.c

+/**
+ * @file arch/alpha/oprofile/op_model_ev5.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author Richard Henderson <rth@twiddle.net>
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <asm/system.h>
+
+#include "op_impl.h"
+
+
+/* Compute all of the registers in preparation for enabling profiling.
+
+   The 21164 (EV5) and 21164PC (PCA65) vary in the bit placement and
+   meaning of the "CBOX" events.  Given that we don't care about meaning
+   at this point, arrange for the difference in bit placement to be
+   handled by common code.  */
+
+static void
+common_reg_setup(struct op_register_config *reg,
+		 struct op_counter_config *ctr,
+		 struct op_system_config *sys,
+		 int cbox1_ofs, int cbox2_ofs)
+{
+	int i, ctl, reset, need_reset;
+
+	/* Select desired events.  The event numbers are selected such
+	   that they map directly into the event selection fields:
+
+		PCSEL0:	0, 1
+		PCSEL1:	24-39
+		 CBOX1: 40-47
+		PCSEL2: 48-63
+		 CBOX2: 64-71
+
+	   There are two special cases, in that CYCLES can be measured
+	   on PCSEL[02], and SCACHE_WRITE can be measured on CBOX[12].
+	   These event numbers are canonicalizes to their first appearance.  */
+
+	ctl = 0;
+	for (i = 0; i < 3; ++i) {
+		unsigned long event = ctr[i].event;
+		if (!ctr[i].enabled)
+			continue;
+
+		/* Remap the duplicate events, as described above.  */
+		if (i == 2) {
+			if (event == 0)
+				event = 12+48;
+			else if (event == 2+41)
+				event = 4+65;
+		}
+
+		/* Convert the event numbers onto mux_select bit mask.  */
+		if (event < 2)
+			ctl |= event << 31;
+		else if (event < 24)
+			/* error */;
+		else if (event < 40)
+			ctl |= (event - 24) << 4;
+		else if (event < 48)
+			ctl |= (event - 40) << cbox1_ofs | 15 << 4;
+		else if (event < 64)
+			ctl |= event - 48;
+		else if (event < 72)
+			ctl |= (event - 64) << cbox2_ofs | 15;
+	}
+	reg->mux_select = ctl;
+
+	/* Select processor mode.  */
+	/* ??? Need to come up with some mechanism to trace only selected
+	   processes.  For now select from pal, kernel and user mode.  */
+	ctl = 0;
+	ctl |= !sys->enable_pal << 9;
+	ctl |= !sys->enable_kernel << 8;
+	ctl |= !sys->enable_user << 30;
+	reg->proc_mode = ctl;
+
+	/* Select interrupt frequencies.  Take the interrupt count selected
+	   by the user, and map it onto one of the possible counter widths.
+	   If the user value is in between, compute a value to which the
+	   counter is reset at each interrupt.  */
+
+	ctl = reset = need_reset = 0;
+	for (i = 0; i < 3; ++i) {
+		unsigned long max, hilo, count = ctr[i].count;
+		if (!ctr[i].enabled)
+			continue;
+
+		if (count <= 256)
+			count = 256, hilo = 3, max = 256;
+		else {
+			max = (i == 2 ? 16384 : 65536);
+			hilo = 2;
+			if (count > max)
+				count = max;
+		}
+		ctr[i].count = count;
+
+		ctl |= hilo << (8 - i*2);
+		reset |= (max - count) << (48 - 16*i);
+		if (count != max)
+			need_reset |= 1 << i;
+	}
+	reg->freq = ctl;
+	reg->reset_values = reset;
+	reg->need_reset = need_reset;
+}
+
+static void
+ev5_reg_setup(struct op_register_config *reg,
+	      struct op_counter_config *ctr,
+	      struct op_system_config *sys)
+{
+	common_reg_setup(reg, ctr, sys, 19, 22);
+}
+
+static void
+pca56_reg_setup(struct op_register_config *reg,
+	        struct op_counter_config *ctr,
+	        struct op_system_config *sys)
+{
+	common_reg_setup(reg, ctr, sys, 8, 11);
+}
+
+/* Program all of the registers in preparation for enabling profiling.  */
+
+static void
+ev5_cpu_setup (void *x)
+{
+	struct op_register_config *reg = x;
+
+	wrperfmon(2, reg->mux_select);
+	wrperfmon(3, reg->proc_mode);
+	wrperfmon(4, reg->freq);
+	wrperfmon(6, reg->reset_values);
+}
+
+/* CTR is a counter for which the user has requested an interrupt count
+   in between one of the widths selectable in hardware.  Reset the count
+   for CTR to the value stored in REG->RESET_VALUES.
+
+   For EV5, this means disabling profiling, reading the current values,
+   masking in the value for the desired register, writing, then turning
+   profiling back on.
+
+   This can be streamlined if profiling is only enabled for user mode.
+   In that case we know that the counters are not currently incrementing
+   (due to being in kernel mode).  */
+
+static void
+ev5_reset_ctr(struct op_register_config *reg, unsigned long ctr)
+{
+	unsigned long values, mask, not_pk, reset_values;
+
+	mask = (ctr == 0 ? 0xfffful << 48
+	        : ctr == 1 ? 0xfffful << 32
+		: 0x3fff << 16);
+
+	not_pk = 1 << 9 | 1 << 8;
+
+	reset_values = reg->reset_values;
+
+	if ((reg->proc_mode & not_pk) == not_pk) {
+		values = wrperfmon(5, 0);
+		values = (reset_values & mask) | (values & ~mask & -2);
+		wrperfmon(6, values);
+	} else {
+		wrperfmon(0, -1);
+		values = wrperfmon(5, 0);
+		values = (reset_values & mask) | (values & ~mask & -2);
+		wrperfmon(6, values);
+		wrperfmon(1, reg->enable);
+	}
+}
+
+struct op_axp_model op_model_ev5 = {
+	.reg_setup		= ev5_reg_setup,
+	.cpu_setup		= ev5_cpu_setup,
+	.reset_ctr		= ev5_reset_ctr,
+	.cpu			= OPROFILE_CPU_AXP_EV5,
+	.num_counters		= 3,
+	.can_set_proc_mode	= 1,
+};
+
+struct op_axp_model op_model_pca56 = {
+	.reg_setup		= pca56_reg_setup,
+	.cpu_setup		= ev5_cpu_setup,
+	.reset_ctr		= ev5_reset_ctr,
+	.cpu			= OPROFILE_CPU_AXP_PCA56,
+	.num_counters		= 3,
+	.can_set_proc_mode	= 1,
+};

arch/alpha/oprofile/op_model_ev6.c

+/**
+ * @file arch/alpha/oprofile/op_model_ev6.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author Richard Henderson <rth@twiddle.net>
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <asm/system.h>
+
+#include "op_impl.h"
+
+
+/* Compute all of the registers in preparation for enabling profiling.  */
+
+static void
+ev6_reg_setup(struct op_register_config *reg,
+	      struct op_counter_config *ctr,
+	      struct op_system_config *sys)
+{
+	unsigned long ctl, reset, need_reset, i;
+
+	/* Select desired events.  We've mapped the event numbers
+	   such that they fit directly into the event selection fields.  */
+	ctl = 0;
+	if (ctr[0].enabled && ctr[0].event)
+		ctl |= (ctr[0].event & 1) << 4;
+	if (ctr[1].enabled)
+		ctl |= (ctr[1].event - 2) & 15;
+	reg->mux_select = ctl;
+
+	/* Select logging options.  */
+	/* ??? Need to come up with some mechanism to trace only
+	   selected processes.  EV6 does not have a mechanism to
+	   select kernel or user mode only.  For now, enable always.  */
+	reg->proc_mode = 1;
+
+	/* EV6 cannot change the width of the counters as with the
+	   other implementations.  But fortunately, we can write to
+	   the counters and set the value such that it will overflow
+	   at the right time.  */
+	reset = need_reset = 0;
+	for (i = 0; i < 2; ++i) {
+		unsigned long count = ctr[i].count;
+		if (!ctr[i].enabled)
+			continue;
+
+		if (count > 0x100000)
+			count = 0x100000;
+		ctr[i].count = count;
+		reset |= (0x100000 - count) << (i ? 6 : 28);
+		if (count != 0x100000)
+			need_reset |= 1 << i;
+	}
+	reg->reset_values = reset;
+	reg->need_reset = need_reset;
+}
+
+/* Program all of the registers in preparation for enabling profiling.  */
+
+static void
+ev6_cpu_setup (void *x)
+{
+	struct op_register_config *reg = x;
+
+	wrperfmon(2, reg->mux_select);
+	wrperfmon(3, reg->proc_mode);
+	wrperfmon(6, reg->reset_values | 3);
+}
+
+/* CTR is a counter for which the user has requested an interrupt count
+   in between one of the widths selectable in hardware.  Reset the count
+   for CTR to the value stored in REG->RESET_VALUES.  */
+
+static void
+ev6_reset_ctr(struct op_register_config *reg, unsigned long ctr)
+{
+	wrperfmon(6, reg->reset_values | (1 << ctr));
+}
+
+struct op_axp_model op_model_ev6 = {
+	.reg_setup		= ev6_reg_setup,
+	.cpu_setup		= ev6_cpu_setup,
+	.reset_ctr		= ev6_reset_ctr,
+	.cpu			= OPROFILE_CPU_AXP_EV6,
+	.num_counters		= 2,
+	.can_set_proc_mode	= 0,
+};

drivers/oprofile/oprofile_stats.c

@@ -9,6 +9,7 @@
 
 #include <linux/oprofile.h>
 #include <linux/smp.h>
+#include <linux/threads.h>
  
 #include "oprofile_stats.h"
 #include "cpu_buffer.h"

include/linux/oprofile.h

@@ -26,7 +26,17 @@ enum oprofile_cpu {
 	OPROFILE_CPU_PII,
 	OPROFILE_CPU_PIII,
 	OPROFILE_CPU_ATHLON,
-	OPROFILE_CPU_TIMER
+	OPROFILE_CPU_TIMER,
+	OPROFILE_CPU_RTC,
+	OPROFILE_CPU_P4,
+	OPROFILE_CPU_IA64,
+	OPROFILE_CPU_IA64_1,
+	OPROFILE_CPU_IA64_2,
+	OPROFILE_CPU_HAMMER,
+	OPROFILE_CPU_AXP_EV4,
+	OPROFILE_CPU_AXP_EV5,
+	OPROFILE_CPU_AXP_PCA56,
+	OPROFILE_CPU_AXP_EV6,
 };
 
 /* Operations structure to be filled in */