[PATCH] x86: Add performance counter reservation framework for UP kernels

Adds basic infrastructure to allow subsystems to reserve performance
counters on the x86 chips.  Only UP kernels are supported in this patch to
make reviewing easier.  The SMP portion makes a lot more changes.

Think of this as a locking mechanism where each bit represents a different
counter.  In addition, each subsystem should also reserve an appropriate
event selection register that will correspond to the performance counter it
will be using (this is mainly neccessary for the Pentium 4 chips as they
break the 1:1 relationship to performance counters).

This will help prevent subsystems like oprofile from interfering with the
nmi watchdog.

Signed-off-by:  Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@suse.de>

1 files changed, 138 insertions, 40 deletions

diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 42c05d6..b7a7c99 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -27,6 +27,20 @@
 #include <asm/kdebug.h>
 #include <asm/mce.h>
 
+/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
+ * evtsel_nmi_owner tracks the ownership of the event selection
+ * - different performance counters/ event selection may be reserved for
+ *   different subsystems this reservation system just tries to coordinate
+ *   things a little
+ */
+static DEFINE_PER_CPU(unsigned, perfctr_nmi_owner);
+static DEFINE_PER_CPU(unsigned, evntsel_nmi_owner[2]);
+
+/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
+ * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
+ */
+#define NMI_MAX_COUNTER_BITS 66
+
 /*
  * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
  * - it may be reserved by some other driver, or not
@@ -90,6 +104,95 @@ static unsigned int nmi_p4_cccr_val;
 	(P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|	\
 	 P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
+/* converts an msr to an appropriate reservation bit */
+static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
+{
+	/* returns the bit offset of the performance counter register */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		return (msr - MSR_K7_PERFCTR0);
+	case X86_VENDOR_INTEL:
+		return (msr - MSR_P4_BPU_PERFCTR0);
+	}
+	return 0;
+}
+
+/* converts an msr to an appropriate reservation bit */
+static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
+{
+	/* returns the bit offset of the event selection register */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		return (msr - MSR_K7_EVNTSEL0);
+	case X86_VENDOR_INTEL:
+		return (msr - MSR_P4_BSU_ESCR0);
+	}
+	return 0;
+}
+
+/* checks for a bit availability (hack for oprofile) */
+int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
+{
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+}
+
+/* checks the an msr for availability */
+int avail_to_resrv_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+}
+
+int reserve_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner)))
+		return 1;
+	return 0;
+}
+
+void release_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner));
+}
+
+int reserve_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)))
+		return 1;
+	return 0;
+}
+
+void release_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner));
+}
+
 static __cpuinit inline int nmi_known_cpu(void)
 {
 	switch (boot_cpu_data.x86_vendor) {
@@ -325,34 +428,22 @@ late_initcall(init_lapic_nmi_sysfs);
 
 #endif	/* CONFIG_PM */
 
-/*
- * Activate the NMI watchdog via the local APIC.
- * Original code written by Keith Owens.
- */
-
-static void clear_msr_range(unsigned int base, unsigned int n)
+static int setup_k7_watchdog(void)
 {
-	unsigned int i;
-
-	for(i = 0; i < n; ++i)
-		wrmsr(base+i, 0, 0);
-}
-
-static void setup_k7_watchdog(void)
-{
-	int i;
 	unsigned int evntsel;
 
 	nmi_perfctr_msr = MSR_K7_PERFCTR0;
 
-	for(i = 0; i < 4; ++i) {
-		/* Simulator may not support it */
-		if (checking_wrmsrl(MSR_K7_EVNTSEL0+i, 0UL)) {
-			nmi_perfctr_msr = 0;
-			return;
-		}
-		wrmsrl(MSR_K7_PERFCTR0+i, 0UL);
-	}
+	if (!reserve_perfctr_nmi(nmi_perfctr_msr))
+		goto fail;
+
+	if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0))
+		goto fail1;
+
+	/* Simulator may not support it */
+	if (checking_wrmsrl(MSR_K7_EVNTSEL0, 0UL))
+		goto fail2;
+	wrmsrl(MSR_K7_PERFCTR0, 0UL);
 
 	evntsel = K7_EVNTSEL_INT
 		| K7_EVNTSEL_OS
@@ -364,6 +455,13 @@ static void setup_k7_watchdog(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= K7_EVNTSEL_ENABLE;
 	wrmsr(MSR_K7_EVNTSEL0, evntsel, 0);
+	return 1;
+fail2:
+	release_evntsel_nmi(MSR_K7_EVNTSEL0);
+fail1:
+	release_perfctr_nmi(nmi_perfctr_msr);
+fail:
+	return 0;
 }
 
 
@@ -382,22 +480,11 @@ static int setup_p4_watchdog(void)
 		nmi_p4_cccr_val |= P4_CCCR_OVF_PMI1;
 #endif
 
-	if (!(misc_enable & MSR_P4_MISC_ENABLE_PEBS_UNAVAIL))
-		clear_msr_range(0x3F1, 2);
-	/* MSR 0x3F0 seems to have a default value of 0xFC00, but current
-	   docs doesn't fully define it, so leave it alone for now. */
-	if (boot_cpu_data.x86_model >= 0x3) {
-		/* MSR_P4_IQ_ESCR0/1 (0x3ba/0x3bb) removed */
-		clear_msr_range(0x3A0, 26);
-		clear_msr_range(0x3BC, 3);
-	} else {
-		clear_msr_range(0x3A0, 31);
-	}
-	clear_msr_range(0x3C0, 6);
-	clear_msr_range(0x3C8, 6);
-	clear_msr_range(0x3E0, 2);
-	clear_msr_range(MSR_P4_CCCR0, 18);
-	clear_msr_range(MSR_P4_PERFCTR0, 18);
+	if (!reserve_perfctr_nmi(nmi_perfctr_msr))
+		goto fail;
+
+	if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
+		goto fail1;
 
 	wrmsr(MSR_P4_CRU_ESCR0, P4_NMI_CRU_ESCR0, 0);
 	wrmsr(MSR_P4_IQ_CCCR0, P4_NMI_IQ_CCCR0 & ~P4_CCCR_ENABLE, 0);
@@ -406,6 +493,10 @@ static int setup_p4_watchdog(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
 	return 1;
+fail1:
+	release_perfctr_nmi(nmi_perfctr_msr);
+fail:
+	return 0;
 }
 
 void setup_apic_nmi_watchdog(void)
@@ -416,7 +507,8 @@ void setup_apic_nmi_watchdog(void)
 			return;
 		if (strstr(boot_cpu_data.x86_model_id, "Screwdriver"))
 			return;
-		setup_k7_watchdog();
+		if (!setup_k7_watchdog())
+			return;
 		break;
 	case X86_VENDOR_INTEL:
 		if (boot_cpu_data.x86 != 15)
@@ -588,6 +680,12 @@ int proc_unknown_nmi_panic(struct ctl_table *table, int write, struct file *file
 
 EXPORT_SYMBOL(nmi_active);
 EXPORT_SYMBOL(nmi_watchdog);
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
+EXPORT_SYMBOL(reserve_perfctr_nmi);
+EXPORT_SYMBOL(release_perfctr_nmi);
+EXPORT_SYMBOL(reserve_evntsel_nmi);
+EXPORT_SYMBOL(release_evntsel_nmi);
 EXPORT_SYMBOL(reserve_lapic_nmi);
 EXPORT_SYMBOL(release_lapic_nmi);
 EXPORT_SYMBOL(disable_timer_nmi_watchdog);