oprofile: Implement Intel architectural perfmon support

Newer Intel CPUs (Core1+) have support for architectural
events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details.

The advantage of this is that it can be done without knowing about
the specific CPU, because the CPU describes by itself what
performance events are supported. This is only a fallback
because only a limited set of 6 events are supported.
This allows to do profiling on Nehalem and on Atom systems
(later not tested)

This patch implements support for that in oprofile's Intel
Family 6 profiling module. It also has the advantage of supporting
an arbitary number of events now as reported by the CPU.
Also allow arbitary counter widths >32bit while we're at it.

Requires a patched oprofile userland to support the new
architecture.

v2: update for latest oprofile tree
    remove force_arch_perfmon

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Robert Richter <robert.richter@amd.com>

1 files changed, 17 insertions, 6 deletions

diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 1059f3fe6b1d..12d6f85084f1 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -429,6 +429,16 @@ static int __init ppro_init(char **cpu_type)
 	return 1;
 }
 
+static int __init arch_perfmon_init(char **cpu_type)
+{
+	if (!cpu_has_arch_perfmon)
+		return 0;
+	*cpu_type = "i386/arch_perfmon";
+	model = &op_arch_perfmon_spec;
+	arch_perfmon_setup_counters();
+	return 1;
+}
+
 /* in order to get sysfs right */
 static int using_nmi;
 
@@ -436,7 +446,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 {
 	__u8 vendor = boot_cpu_data.x86_vendor;
 	__u8 family = boot_cpu_data.x86;
-	char *cpu_type;
+	char *cpu_type = NULL;
 	int ret = 0;
 
 	if (!cpu_has_apic)
@@ -474,19 +484,20 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		switch (family) {
 			/* Pentium IV */
 		case 0xf:
-			if (!p4_init(&cpu_type))
-				return -ENODEV;
+			p4_init(&cpu_type);
 			break;
 
 			/* A P6-class processor */
 		case 6:
-			if (!ppro_init(&cpu_type))
-				return -ENODEV;
+			ppro_init(&cpu_type);
 			break;
 
 		default:
-			return -ENODEV;
+			break;
 		}
+
+		if (!cpu_type && !arch_perfmon_init(&cpu_type))
+			return -ENODEV;
 		break;
 
 	default: