1 files changed, 80 insertions, 102 deletions

diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 10131fbdaad..d90528ea541 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/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/intel_arch_perfmon.h>
 
 #include "op_x86_model.h"
 #include "op_counter.h"
@@ -26,55 +26,55 @@
 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 MSR_PPRO_EVENTSEL_RESERVED	((0xFFFFFFFFULL<<32)|(1ULL<<21))
 
-#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)
+static u64 reset_value[OP_MAX_COUNTER];
 
-static u64 *reset_value;
-
-static void ppro_fill_in_addresses(struct op_msrs * const msrs)
+static void ppro_shutdown(struct op_msrs const * const msrs)
 {
 	int i;
 
-	for (i = 0; i < num_counters; i++) {
-		if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
-			msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
-		else
-			msrs->counters[i].addr = 0;
+	for (i = 0; i < num_counters; ++i) {
+		if (!msrs->counters[i].addr)
+			continue;
+		release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
+		release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
 	}
+}
+
+static int ppro_fill_in_addresses(struct op_msrs * const msrs)
+{
+	int i;
 
 	for (i = 0; i < num_counters; i++) {
-		if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
-			msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
-		else
-			msrs->controls[i].addr = 0;
+		if (!reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
+			goto fail;
+		if (!reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) {
+			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
+			goto fail;
+		}
+		/* both registers must be reserved */
+		msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
+		msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
+		continue;
+	fail:
+		if (!counter_config[i].enabled)
+			continue;
+		op_x86_warn_reserved(i);
+		ppro_shutdown(msrs);
+		return -EBUSY;
 	}
+
+	return 0;
 }
 
 
-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) {
-		reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
-					GFP_ATOMIC);
-		if (!reset_value)
-			return;
-	}
-
 	if (cpu_has_arch_perfmon) {
 		union cpuid10_eax eax;
 		eax.full = cpuid_eax(0xa);
@@ -84,8 +84,8 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 		 * counter width:
 		 */
 		if (!(eax.split.version_id == 0 &&
-			current_cpu_data.x86 == 6 &&
-				current_cpu_data.x86_model == 15)) {
+			__this_cpu_read(cpu_info.x86) == 6 &&
+				__this_cpu_read(cpu_info.x86_model) == 15)) {
 
 			if (counter_width < eax.split.bit_width)
 				counter_width = eax.split.bit_width;
@@ -93,36 +93,30 @@ 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)))
-			continue;
-		CTRL_READ(low, high, msrs, i);
-		CTRL_CLEAR(low);
-		CTRL_WRITE(low, high, msrs, i);
-	}
-
-	/* 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 (!msrs->controls[i].addr)
 			continue;
+		rdmsrl(msrs->controls[i].addr, val);
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+			op_x86_warn_in_use(i);
+		val &= model->reserved;
+		wrmsrl(msrs->controls[i].addr, val);
+		/*
+		 * avoid a false detection of ctr overflows in NMI *
+		 * handler
+		 */
 		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;
 		}
@@ -136,14 +130,14 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 	u64 val;
 	int i;
 
-	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]);
 	}
 
 	/* Only P6 based Pentium M need to re-unmask the apic vector but it
@@ -163,16 +157,14 @@ 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_EVENTSEL_ENABLE;
+			wrmsrl(msrs->controls[i].addr, val);
 		}
 	}
 }
@@ -180,42 +172,22 @@ 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)
-		return;
 	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_EVENTSEL_ENABLE;
+		wrmsrl(msrs->controls[i].addr, val);
 	}
 }
 
-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))
-			release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
-	}
-	for (i = 0 ; i < num_counters ; ++i) {
-		if (CTRL_IS_RESERVED(msrs, i))
-			release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
-	}
-	if (reset_value) {
-		kfree(reset_value);
-		reset_value = NULL;
-	}
-}
-
-
 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,
@@ -233,29 +205,35 @@ 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;
 
 	eax.full = cpuid_eax(0xa);
 
 	/* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
-	if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
-		current_cpu_data.x86_model == 15) {
+	if (eax.split.version_id == 0 && __this_cpu_read(cpu_info.x86) == 6 &&
+		__this_cpu_read(cpu_info.x86_model) == 15) {
 		eax.split.version_id = 2;
 		eax.split.num_counters = 2;
 		eax.split.bit_width = 40;
 	}
 
-	num_counters = eax.split.num_counters;
+	num_counters = min((int)eax.split.num_counters, OP_MAX_COUNTER);
 
 	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 */