Merge branch 'oprofile-for-linus' of...

Merge branch 'oprofile-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'oprofile-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (55 commits)
  arch/x86/oprofile/op_model_amd.c: fix op_amd_handle_ibs() return type
  Revert "x86: oprofile/op_model_amd.c set return values for op_amd_handle_ibs()"
  x86/oprofile: Small coding style fixes
  x86/oprofile: Add counter reservation check for virtual counters
  x86/oprofile: Implement op_x86_virt_to_phys()
  oprofile: Adding switch counter to oprofile statistic variables
  x86/oprofile: Implement mux_clone()
  x86/oprofile: Enable multiplexing only if the model supports it
  x86/oprofile: Add function has_mux() to check multiplexing support
  x86/oprofile: Modify initialization of num_virt_counters
  x86/oprofile: Remove unused num_virt_controls from struct op_x86_model_spec
  x86/oprofile: Remove const qualifier from struct op_x86_model_spec
  x86/oprofile: Moving nmi_cpu_switch() in nmi_int.c
  x86/oprofile: Moving nmi_cpu_save/restore_mpx_registers() in nmi_int.c
  x86/oprofile: Moving nmi_setup_cpu_mux() in nmi_int.c
  x86/oprofile: Implement multiplexing setup/shutdown functions
  oprofile: Grouping multiplexing code in op_model_amd.c
  oprofile: Introduce op_x86_phys_to_virt()
  oprofile: Grouping multiplexing code in oprof.c
  oprofile: Remove oprofile_multiplexing_init()
  ...

arch/Kconfig

@@ -30,6 +30,18 @@ config OPROFILE_IBS
 
 	  If unsure, say N.
 
+config OPROFILE_EVENT_MULTIPLEX
+	bool "OProfile multiplexing support (EXPERIMENTAL)"
+	default n
+	depends on OPROFILE && X86
+	help
+	  The number of hardware counters is limited. The multiplexing
+	  feature enables OProfile to gather more events than counters
+	  are provided by the hardware. This is realized by switching
+	  between events at an user specified time interval.
+
+	  If unsure, say N.
+
 config HAVE_OPROFILE
 	bool
 

arch/x86/oprofile/op_counter.h

@@ -10,7 +10,7 @@
 #ifndef OP_COUNTER_H
 #define OP_COUNTER_H
 
-#define OP_MAX_COUNTER 8
+#define OP_MAX_COUNTER 32
 
 /* Per-perfctr configuration as set via
  * oprofilefs.

arch/x86/oprofile/op_model_p4.c

@@ -32,6 +32,8 @@
 #define NUM_CCCRS_HT2 9
 #define NUM_CONTROLS_HT2 (NUM_ESCRS_HT2 + NUM_CCCRS_HT2)
 
+#define OP_CTR_OVERFLOW			(1ULL<<31)
+
 static unsigned int num_counters = NUM_COUNTERS_NON_HT;
 static unsigned int num_controls = NUM_CONTROLS_NON_HT;
 
@@ -350,8 +352,6 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
 #define ESCR_SET_OS_1(escr, os) ((escr) |= (((os) & 1) << 1))
 #define ESCR_SET_EVENT_SELECT(escr, sel) ((escr) |= (((sel) & 0x3f) << 25))
 #define ESCR_SET_EVENT_MASK(escr, mask) ((escr) |= (((mask) & 0xffff) << 9))
-#define ESCR_READ(escr, high, ev, i) do {rdmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
-#define ESCR_WRITE(escr, high, ev, i) do {wrmsr(ev->bindings[(i)].escr_address, (escr), (high)); } while (0)
 
 #define CCCR_RESERVED_BITS 0x38030FFF
 #define CCCR_CLEAR(cccr) ((cccr) &= CCCR_RESERVED_BITS)
@@ -361,17 +361,9 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
 #define CCCR_SET_PMI_OVF_1(cccr) ((cccr) |= (1<<27))
 #define CCCR_SET_ENABLE(cccr) ((cccr) |= (1<<12))
 #define CCCR_SET_DISABLE(cccr) ((cccr) &= ~(1<<12))
-#define CCCR_READ(low, high, i) do {rdmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
-#define CCCR_WRITE(low, high, i) do {wrmsr(p4_counters[(i)].cccr_address, (low), (high)); } while (0)
 #define CCCR_OVF_P(cccr) ((cccr) & (1U<<31))
 #define CCCR_CLEAR_OVF(cccr) ((cccr) &= (~(1U<<31)))
 
-#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, i) do {rdmsr(p4_counters[(i)].counter_address, (l), (h)); } while (0)
-#define CTR_WRITE(l, i) do {wrmsr(p4_counters[(i)].counter_address, -(u32)(l), -1); } while (0)
-#define CTR_OVERFLOW_P(ctr) (!((ctr) & 0x80000000))
-
 
 /* this assigns a "stagger" to the current CPU, which is used throughout
    the code in this module as an extra array offset, to select the "even"
@@ -515,7 +507,7 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
 		if (ev->bindings[i].virt_counter & counter_bit) {
 
 			/* modify ESCR */
-			ESCR_READ(escr, high, ev, i);
+			rdmsr(ev->bindings[i].escr_address, escr, high);
 			ESCR_CLEAR(escr);
 			if (stag == 0) {
 				ESCR_SET_USR_0(escr, counter_config[ctr].user);
@@ -526,10 +518,11 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
 			}
 			ESCR_SET_EVENT_SELECT(escr, ev->event_select);
 			ESCR_SET_EVENT_MASK(escr, counter_config[ctr].unit_mask);
-			ESCR_WRITE(escr, high, ev, i);
+			wrmsr(ev->bindings[i].escr_address, escr, high);
 
 			/* modify CCCR */
-			CCCR_READ(cccr, high, VIRT_CTR(stag, ctr));
+			rdmsr(p4_counters[VIRT_CTR(stag, ctr)].cccr_address,
+			      cccr, high);
 			CCCR_CLEAR(cccr);
 			CCCR_SET_REQUIRED_BITS(cccr);
 			CCCR_SET_ESCR_SELECT(cccr, ev->escr_select);
@@ -537,7 +530,8 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
 				CCCR_SET_PMI_OVF_0(cccr);
 			else
 				CCCR_SET_PMI_OVF_1(cccr);
-			CCCR_WRITE(cccr, high, VIRT_CTR(stag, ctr));
+			wrmsr(p4_counters[VIRT_CTR(stag, ctr)].cccr_address,
+			      cccr, high);
 			return;
 		}
 	}
@@ -548,7 +542,8 @@ static void pmc_setup_one_p4_counter(unsigned int ctr)
 }
 
 
-static void p4_setup_ctrs(struct op_msrs const * const msrs)
+static void p4_setup_ctrs(struct op_x86_model_spec const *model,
+			  struct op_msrs const * const msrs)
 {
 	unsigned int i;
 	unsigned int low, high;
@@ -563,8 +558,8 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
 	}
 
 	/* clear the cccrs we will use */
-	for (i = 0 ; i < num_counters ; i++) {
-		if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
+	for (i = 0; i < num_counters; i++) {
+		if (unlikely(!msrs->controls[i].addr))
 			continue;
 		rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 		CCCR_CLEAR(low);
@@ -574,17 +569,18 @@ static void p4_setup_ctrs(struct op_msrs const * const msrs)
 
 	/* clear all escrs (including those outside our concern) */
 	for (i = num_counters; i < num_controls; i++) {
-		if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
+		if (unlikely(!msrs->controls[i].addr))
 			continue;
 		wrmsr(msrs->controls[i].addr, 0, 0);
 	}
 
 	/* setup all counters */
-	for (i = 0 ; i < num_counters ; ++i) {
-		if ((counter_config[i].enabled) && (CTRL_IS_RESERVED(msrs, i))) {
+	for (i = 0; i < num_counters; ++i) {
+		if (counter_config[i].enabled && msrs->controls[i].addr) {
 			reset_value[i] = counter_config[i].count;
 			pmc_setup_one_p4_counter(i);
-			CTR_WRITE(counter_config[i].count, VIRT_CTR(stag, i));
+			wrmsrl(p4_counters[VIRT_CTR(stag, i)].counter_address,
+			       -(u64)counter_config[i].count);
 		} else {
 			reset_value[i] = 0;
 		}
@@ -624,14 +620,16 @@ static int p4_check_ctrs(struct pt_regs * const regs,
 
 		real = VIRT_CTR(stag, i);
 
-		CCCR_READ(low, high, real);
-		CTR_READ(ctr, high, real);
-		if (CCCR_OVF_P(low) || CTR_OVERFLOW_P(ctr)) {
+		rdmsr(p4_counters[real].cccr_address, low, high);
+		rdmsr(p4_counters[real].counter_address, ctr, high);
+		if (CCCR_OVF_P(low) || !(ctr & OP_CTR_OVERFLOW)) {
 			oprofile_add_sample(regs, i);
-			CTR_WRITE(reset_value[i], real);
+			wrmsrl(p4_counters[real].counter_address,
+			       -(u64)reset_value[i]);
 			CCCR_CLEAR_OVF(low);
-			CCCR_WRITE(low, high, real);
-			CTR_WRITE(reset_value[i], real);
+			wrmsr(p4_counters[real].cccr_address, low, high);
+			wrmsrl(p4_counters[real].counter_address,
+			       -(u64)reset_value[i]);
 		}
 	}
 
@@ -653,9 +651,9 @@ static void p4_start(struct op_msrs const * const msrs)
 	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
-		CCCR_READ(low, high, VIRT_CTR(stag, i));
+		rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 		CCCR_SET_ENABLE(low);
-		CCCR_WRITE(low, high, VIRT_CTR(stag, i));
+		wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 	}
 }
 
@@ -670,9 +668,9 @@ static void p4_stop(struct op_msrs const * const msrs)
 	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
-		CCCR_READ(low, high, VIRT_CTR(stag, i));
+		rdmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 		CCCR_SET_DISABLE(low);
-		CCCR_WRITE(low, high, VIRT_CTR(stag, i));
+		wrmsr(p4_counters[VIRT_CTR(stag, i)].cccr_address, low, high);
 	}
 }
 
@@ -680,8 +678,8 @@ static void p4_shutdown(struct op_msrs const * const msrs)
 {
 	int i;
 
-	for (i = 0 ; i < num_counters ; ++i) {
-		if (CTR_IS_RESERVED(msrs, i))
+	for (i = 0; i < num_counters; ++i) {
+		if (msrs->counters[i].addr)
 			release_perfctr_nmi(msrs->counters[i].addr);
 	}
 	/*
@@ -689,15 +687,15 @@ static void p4_shutdown(struct op_msrs const * const msrs)
 	 * conjunction with the counter registers (hence the starting offset).
 	 * This saves a few bits.
 	 */
-	for (i = num_counters ; i < num_controls ; ++i) {
-		if (CTRL_IS_RESERVED(msrs, i))
+	for (i = num_counters; i < num_controls; ++i) {
+		if (msrs->controls[i].addr)
 			release_evntsel_nmi(msrs->controls[i].addr);
 	}
 }
 
 
 #ifdef CONFIG_SMP
-struct op_x86_model_spec const op_p4_ht2_spec = {
+struct op_x86_model_spec op_p4_ht2_spec = {
 	.num_counters		= NUM_COUNTERS_HT2,
 	.num_controls		= NUM_CONTROLS_HT2,
 	.fill_in_addresses	= &p4_fill_in_addresses,
@@ -709,7 +707,7 @@ struct op_x86_model_spec const op_p4_ht2_spec = {
 };
 #endif
 
-struct op_x86_model_spec const op_p4_spec = {
+struct op_x86_model_spec op_p4_spec = {
 	.num_counters		= NUM_COUNTERS_NON_HT,
 	.num_controls		= NUM_CONTROLS_NON_HT,
 	.fill_in_addresses	= &p4_fill_in_addresses,

arch/x86/oprofile/op_model_ppro.c

@@ -10,6 +10,7 @@
  * @author Philippe Elie
  * @author Graydon Hoare
  * @author Andi Kleen
+ * @author Robert Richter <robert.richter@amd.com>
  */
 
 #include <linux/oprofile.h>
@@ -18,7 +19,6 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <asm/nmi.h>
-#include <asm/perf_counter.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"
@@ -26,20 +26,7 @@
 static int num_counters = 2;
 static int counter_width = 32;
 
-#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_OVERFLOWED(n) (!((n) & (1ULL<<(counter_width-1))))
-
-#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
-#define CTRL_WRITE(l, h, msrs, c) do {wrmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
-#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
-#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22))
-#define CTRL_CLEAR(x) (x &= (1<<21))
-#define CTRL_SET_ENABLE(val) (val |= 1<<20)
-#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16))
-#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17))
-#define CTRL_SET_UM(val, m) (val |= (m << 8))
-#define CTRL_SET_EVENT(val, e) (val |= e)
+#define MSR_PPRO_EVENTSEL_RESERVED	((0xFFFFFFFFULL<<32)|(1ULL<<21))
 
 static u64 *reset_value;
 
@@ -63,9 +50,10 @@ static void ppro_fill_in_addresses(struct op_msrs * const msrs)
 }
 
 
-static void ppro_setup_ctrs(struct op_msrs const * const msrs)
+static void ppro_setup_ctrs(struct op_x86_model_spec const *model,
+			    struct op_msrs const * const msrs)
 {
-	unsigned int low, high;
+	u64 val;
 	int i;
 
 	if (!reset_value) {
@@ -93,36 +81,30 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 	}
 
 	/* clear all counters */
-	for (i = 0 ; i < num_counters; ++i) {
-		if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
+	for (i = 0; i < num_counters; ++i) {
+		if (unlikely(!msrs->controls[i].addr))
 			continue;
-		CTRL_READ(low, high, msrs, i);
-		CTRL_CLEAR(low);
-		CTRL_WRITE(low, high, msrs, i);
+		rdmsrl(msrs->controls[i].addr, val);
+		val &= model->reserved;
+		wrmsrl(msrs->controls[i].addr, val);
 	}
 
 	/* avoid a false detection of ctr overflows in NMI handler */
 	for (i = 0; i < num_counters; ++i) {
-		if (unlikely(!CTR_IS_RESERVED(msrs, i)))
+		if (unlikely(!msrs->counters[i].addr))
 			continue;
 		wrmsrl(msrs->counters[i].addr, -1LL);
 	}
 
 	/* enable active counters */
 	for (i = 0; i < num_counters; ++i) {
-		if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) {
+		if (counter_config[i].enabled && msrs->counters[i].addr) {
 			reset_value[i] = counter_config[i].count;
-
 			wrmsrl(msrs->counters[i].addr, -reset_value[i]);
-
-			CTRL_READ(low, high, msrs, i);
-			CTRL_CLEAR(low);
-			CTRL_SET_ENABLE(low);
-			CTRL_SET_USR(low, counter_config[i].user);
-			CTRL_SET_KERN(low, counter_config[i].kernel);
-			CTRL_SET_UM(low, counter_config[i].unit_mask);
-			CTRL_SET_EVENT(low, counter_config[i].event);
-			CTRL_WRITE(low, high, msrs, i);
+			rdmsrl(msrs->controls[i].addr, val);
+			val &= model->reserved;
+			val |= op_x86_get_ctrl(model, &counter_config[i]);
+			wrmsrl(msrs->controls[i].addr, val);
 		} else {
 			reset_value[i] = 0;
 		}
@@ -143,14 +125,14 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 	if (unlikely(!reset_value))
 		goto out;
 
-	for (i = 0 ; i < num_counters; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
 		rdmsrl(msrs->counters[i].addr, val);
-		if (CTR_OVERFLOWED(val)) {
-			oprofile_add_sample(regs, i);
-			wrmsrl(msrs->counters[i].addr, -reset_value[i]);
-		}
+		if (val & (1ULL << (counter_width - 1)))
+			continue;
+		oprofile_add_sample(regs, i);
+		wrmsrl(msrs->counters[i].addr, -reset_value[i]);
 	}
 
 out:
@@ -171,16 +153,16 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 
 static void ppro_start(struct op_msrs const * const msrs)
 {
-	unsigned int low, high;
+	u64 val;
 	int i;
 
 	if (!reset_value)
 		return;
 	for (i = 0; i < num_counters; ++i) {
 		if (reset_value[i]) {
-			CTRL_READ(low, high, msrs, i);
-			CTRL_SET_ACTIVE(low);
-			CTRL_WRITE(low, high, msrs, i);
+			rdmsrl(msrs->controls[i].addr, val);
+			val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+			wrmsrl(msrs->controls[i].addr, val);
 		}
 	}
 }
@@ -188,7 +170,7 @@ static void ppro_start(struct op_msrs const * const msrs)
 
 static void ppro_stop(struct op_msrs const * const msrs)
 {
-	unsigned int low, high;
+	u64 val;
 	int i;
 
 	if (!reset_value)
@@ -196,9 +178,9 @@ static void ppro_stop(struct op_msrs const * const msrs)
 	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
-		CTRL_READ(low, high, msrs, i);
-		CTRL_SET_INACTIVE(low);
-		CTRL_WRITE(low, high, msrs, i);
+		rdmsrl(msrs->controls[i].addr, val);
+		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		wrmsrl(msrs->controls[i].addr, val);
 	}
 }
 
@@ -206,12 +188,12 @@ static void ppro_shutdown(struct op_msrs const * const msrs)
 {
 	int i;
 
-	for (i = 0 ; i < num_counters ; ++i) {
-		if (CTR_IS_RESERVED(msrs, i))
+	for (i = 0; i < num_counters; ++i) {
+		if (msrs->counters[i].addr)
 			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
 	}
-	for (i = 0 ; i < num_counters ; ++i) {
-		if (CTRL_IS_RESERVED(msrs, i))
+	for (i = 0; i < num_counters; ++i) {
+		if (msrs->controls[i].addr)
 			release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
 	}
 	if (reset_value) {
@@ -222,8 +204,9 @@ static void ppro_shutdown(struct op_msrs const * const msrs)
 
 
 struct op_x86_model_spec op_ppro_spec = {
-	.num_counters		= 2,	/* can be overriden */
-	.num_controls		= 2,	/* dito */
+	.num_counters		= 2,
+	.num_controls		= 2,
+	.reserved		= MSR_PPRO_EVENTSEL_RESERVED,
 	.fill_in_addresses	= &ppro_fill_in_addresses,
 	.setup_ctrs		= &ppro_setup_ctrs,
 	.check_ctrs		= &ppro_check_ctrs,
@@ -241,7 +224,7 @@ struct op_x86_model_spec op_ppro_spec = {
  * the specific CPU.
  */
 
-void arch_perfmon_setup_counters(void)
+static void arch_perfmon_setup_counters(void)
 {
 	union cpuid10_eax eax;
 
@@ -259,11 +242,17 @@ void arch_perfmon_setup_counters(void)
 
 	op_arch_perfmon_spec.num_counters = num_counters;
 	op_arch_perfmon_spec.num_controls = num_counters;
-	op_ppro_spec.num_counters = num_counters;
-	op_ppro_spec.num_controls = num_counters;
+}
+
+static int arch_perfmon_init(struct oprofile_operations *ignore)
+{
+	arch_perfmon_setup_counters();
+	return 0;
 }
 
 struct op_x86_model_spec op_arch_perfmon_spec = {
+	.reserved		= MSR_PPRO_EVENTSEL_RESERVED,
+	.init			= &arch_perfmon_init,
 	/* num_counters/num_controls filled in at runtime */
 	.fill_in_addresses	= &ppro_fill_in_addresses,
 	/* user space does the cpuid check for available events */

arch/x86/oprofile/op_x86_model.h

@@ -6,51 +6,66 @@
  * @remark Read the file COPYING
  *
  * @author Graydon Hoare
+ * @author Robert Richter <robert.richter@amd.com>
  */
 
 #ifndef OP_X86_MODEL_H
 #define OP_X86_MODEL_H
 
-struct op_saved_msr {
-	unsigned int high;
-	unsigned int low;
-};
+#include <asm/types.h>
+#include <asm/perf_counter.h>
 
 struct op_msr {
-	unsigned long addr;
-	struct op_saved_msr saved;
+	unsigned long	addr;
+	u64		saved;
 };
 
 struct op_msrs {
 	struct op_msr *counters;
 	struct op_msr *controls;
+	struct op_msr *multiplex;
 };
 
 struct pt_regs;
 
+struct oprofile_operations;
+
 /* The model vtable abstracts the differences between
  * various x86 CPU models' perfctr support.
  */
 struct op_x86_model_spec {
-	int (*init)(struct oprofile_operations *ops);
-	void (*exit)(void);
-	unsigned int num_counters;
-	unsigned int num_controls;
-	void (*fill_in_addresses)(struct op_msrs * const msrs);
-	void (*setup_ctrs)(struct op_msrs const * const msrs);
-	int (*check_ctrs)(struct pt_regs * const regs,
-		struct op_msrs const * const msrs);
-	void (*start)(struct op_msrs const * const msrs);
-	void (*stop)(struct op_msrs const * const msrs);
-	void (*shutdown)(struct op_msrs const * const msrs);
+	unsigned int	num_counters;
+	unsigned int	num_controls;
+	unsigned int	num_virt_counters;
+	u64		reserved;
+	u16		event_mask;
+	int		(*init)(struct oprofile_operations *ops);
+	void		(*exit)(void);
+	void		(*fill_in_addresses)(struct op_msrs * const msrs);
+	void		(*setup_ctrs)(struct op_x86_model_spec const *model,
+				      struct op_msrs const * const msrs);
+	int		(*check_ctrs)(struct pt_regs * const regs,
+				      struct op_msrs const * const msrs);
+	void		(*start)(struct op_msrs const * const msrs);
+	void		(*stop)(struct op_msrs const * const msrs);
+	void		(*shutdown)(struct op_msrs const * const msrs);
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+	void		(*switch_ctrl)(struct op_x86_model_spec const *model,
+				       struct op_msrs const * const msrs);
+#endif
 };
 
+struct op_counter_config;
+
+extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
+			   struct op_counter_config *counter_config);
+extern int op_x86_phys_to_virt(int phys);
+extern int op_x86_virt_to_phys(int virt);
+
 extern struct op_x86_model_spec op_ppro_spec;
-extern struct op_x86_model_spec const op_p4_spec;
-extern struct op_x86_model_spec const op_p4_ht2_spec;
-extern struct op_x86_model_spec const op_amd_spec;
+extern struct op_x86_model_spec op_p4_spec;
+extern struct op_x86_model_spec op_p4_ht2_spec;
+extern struct op_x86_model_spec op_amd_spec;
 extern struct op_x86_model_spec op_arch_perfmon_spec;
 
-extern void arch_perfmon_setup_counters(void);
-
 #endif /* OP_X86_MODEL_H */

drivers/oprofile/cpu_buffer.c

@@ -21,7 +21,6 @@
 
 #include <linux/sched.h>
 #include <linux/oprofile.h>
-#include <linux/vmalloc.h>
 #include <linux/errno.h>
 
 #include "event_buffer.h"
@@ -407,6 +406,21 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val)
 	return op_cpu_buffer_add_data(entry, val);
 }
 
+int oprofile_add_data64(struct op_entry *entry, u64 val)
+{
+	if (!entry->event)
+		return 0;
+	if (op_cpu_buffer_get_size(entry) < 2)
+		/*
+		 * the function returns 0 to indicate a too small
+		 * buffer, even if there is some space left
+		 */
+		return 0;
+	if (!op_cpu_buffer_add_data(entry, (u32)val))
+		return 0;
+	return op_cpu_buffer_add_data(entry, (u32)(val >> 32));
+}
+
 int oprofile_write_commit(struct op_entry *entry)
 {
 	if (!entry->event)

drivers/oprofile/oprof.c

@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/oprofile.h>
 #include <linux/moduleparam.h>
+#include <linux/workqueue.h>
+#include <linux/time.h>
 #include <asm/mutex.h>
 
 #include "oprof.h"
@@ -87,6 +89,69 @@ int oprofile_setup(void)
 	return err;
 }
 
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+
+static void switch_worker(struct work_struct *work);
+static DECLARE_DELAYED_WORK(switch_work, switch_worker);
+
+static void start_switch_worker(void)
+{
+	if (oprofile_ops.switch_events)
+		schedule_delayed_work(&switch_work, oprofile_time_slice);
+}
+
+static void stop_switch_worker(void)
+{
+	cancel_delayed_work_sync(&switch_work);
+}
+
+static void switch_worker(struct work_struct *work)
+{
+	if (oprofile_ops.switch_events())
+		return;
+
+	atomic_inc(&oprofile_stats.multiplex_counter);
+	start_switch_worker();
+}
+
+/* User inputs in ms, converts to jiffies */
+int oprofile_set_timeout(unsigned long val_msec)
+{
+	int err = 0;
+	unsigned long time_slice;
+
+	mutex_lock(&start_mutex);
+
+	if (oprofile_started) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	if (!oprofile_ops.switch_events) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	time_slice = msecs_to_jiffies(val_msec);
+	if (time_slice == MAX_JIFFY_OFFSET) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	oprofile_time_slice = time_slice;
+
+out:
+	mutex_unlock(&start_mutex);
+	return err;
+
+}
+
+#else
+
+static inline void start_switch_worker(void) { }
+static inline void stop_switch_worker(void) { }
+
+#endif
 
 /* Actually start profiling (echo 1>/dev/oprofile/enable) */
 int oprofile_start(void)
@@ -108,6 +173,8 @@ int oprofile_start(void)
 	if ((err = oprofile_ops.start()))
 		goto out;
 
+	start_switch_worker();
+
 	oprofile_started = 1;
 out:
 	mutex_unlock(&start_mutex);
@@ -123,6 +190,9 @@ void oprofile_stop(void)
 		goto out;
 	oprofile_ops.stop();
 	oprofile_started = 0;
+
+	stop_switch_worker();
+
 	/* wake up the daemon to read what remains */
 	wake_up_buffer_waiter();
 out:
@@ -155,7 +225,6 @@ void oprofile_shutdown(void)
 	mutex_unlock(&start_mutex);
 }
 
-
 int oprofile_set_backtrace(unsigned long val)
 {
 	int err = 0;

drivers/oprofile/oprof.h

@@ -24,6 +24,8 @@ struct oprofile_operations;
 extern unsigned long oprofile_buffer_size;
 extern unsigned long oprofile_cpu_buffer_size;
 extern unsigned long oprofile_buffer_watershed;
+extern unsigned long oprofile_time_slice;
+
 extern struct oprofile_operations oprofile_ops;
 extern unsigned long oprofile_started;
 extern unsigned long oprofile_backtrace_depth;
@@ -35,5 +37,6 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root);
 void oprofile_timer_init(struct oprofile_operations *ops);
 
 int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_timeout(unsigned long time);
 
 #endif /* OPROF_H */

drivers/oprofile/oprofile_files.c

@@ -9,6 +9,7 @@
 
 #include <linux/fs.h>
 #include <linux/oprofile.h>
+#include <linux/jiffies.h>
 
 #include "event_buffer.h"
 #include "oprofile_stats.h"
@@ -17,10 +18,51 @@
 #define BUFFER_SIZE_DEFAULT		131072
 #define CPU_BUFFER_SIZE_DEFAULT		8192
 #define BUFFER_WATERSHED_DEFAULT	32768	/* FIXME: tune */
+#define TIME_SLICE_DEFAULT		1
 
 unsigned long oprofile_buffer_size;
 unsigned long oprofile_cpu_buffer_size;
 unsigned long oprofile_buffer_watershed;
+unsigned long oprofile_time_slice;
+
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+
+static ssize_t timeout_read(struct file *file, char __user *buf,
+		size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(jiffies_to_msecs(oprofile_time_slice),
+					buf, count, offset);
+}
+
+
+static ssize_t timeout_write(struct file *file, char const __user *buf,
+		size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval)
+		return retval;
+
+	retval = oprofile_set_timeout(val);
+
+	if (retval)
+		return retval;
+	return count;
+}
+
+
+static const struct file_operations timeout_fops = {
+	.read		= timeout_read,
+	.write		= timeout_write,
+};
+
+#endif
+
 
 static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
 {
@@ -129,6 +171,7 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root)
 	oprofile_buffer_size =		BUFFER_SIZE_DEFAULT;
 	oprofile_cpu_buffer_size =	CPU_BUFFER_SIZE_DEFAULT;
 	oprofile_buffer_watershed =	BUFFER_WATERSHED_DEFAULT;
+	oprofile_time_slice =		msecs_to_jiffies(TIME_SLICE_DEFAULT);
 
 	oprofilefs_create_file(sb, root, "enable", &enable_fops);
 	oprofilefs_create_file_perm(sb, root, "dump", &dump_fops, 0666);
@@ -139,6 +182,9 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root)
 	oprofilefs_create_file(sb, root, "cpu_type", &cpu_type_fops);
 	oprofilefs_create_file(sb, root, "backtrace_depth", &depth_fops);
 	oprofilefs_create_file(sb, root, "pointer_size", &pointer_size_fops);
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+	oprofilefs_create_file(sb, root, "time_slice", &timeout_fops);
+#endif
 	oprofile_create_stats_files(sb, root);
 	if (oprofile_ops.create_files)
 		oprofile_ops.create_files(sb, root);

drivers/oprofile/oprofile_stats.c

@@ -34,6 +34,7 @@ void oprofile_reset_stats(void)
 	atomic_set(&oprofile_stats.sample_lost_no_mapping, 0);
 	atomic_set(&oprofile_stats.event_lost_overflow, 0);
 	atomic_set(&oprofile_stats.bt_lost_no_mapping, 0);
+	atomic_set(&oprofile_stats.multiplex_counter, 0);
 }
 
 
@@ -76,4 +77,8 @@ void oprofile_create_stats_files(struct super_block *sb, struct dentry *root)
 		&oprofile_stats.event_lost_overflow);
 	oprofilefs_create_ro_atomic(sb, dir, "bt_lost_no_mapping",
 		&oprofile_stats.bt_lost_no_mapping);
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+	oprofilefs_create_ro_atomic(sb, dir, "multiplex_counter",
+		&oprofile_stats.multiplex_counter);
+#endif
 }

drivers/oprofile/oprofile_stats.h

@@ -17,6 +17,7 @@ struct oprofile_stat_struct {
 	atomic_t sample_lost_no_mapping;
 	atomic_t bt_lost_no_mapping;
 	atomic_t event_lost_overflow;
+	atomic_t multiplex_counter;
 };
 
 extern struct oprofile_stat_struct oprofile_stats;

include/linux/oprofile.h

@@ -67,6 +67,9 @@ struct oprofile_operations {
 
 	/* Initiate a stack backtrace. Optional. */
 	void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
+
+	/* Multiplex between different events. Optional. */
+	int (*switch_events)(void);
 	/* CPU identification string. */
 	char * cpu_type;
 };
@@ -171,7 +174,6 @@ struct op_sample;
 struct op_entry {
 	struct ring_buffer_event *event;
 	struct op_sample *sample;
-	unsigned long irq_flags;
 	unsigned long size;
 	unsigned long *data;
 };
@@ -180,6 +182,7 @@ void oprofile_write_reserve(struct op_entry *entry,
 			    struct pt_regs * const regs,
 			    unsigned long pc, int code, int size);
 int oprofile_add_data(struct op_entry *entry, unsigned long val);
+int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
 #endif /* OPROFILE_H */