3 files changed, 90 insertions, 14 deletions

diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index ca22b73aaa25..f961de9964c7 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -51,9 +51,13 @@
 #include <asm/e820.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
+#include <asm/pat.h>
 
 #include "mtrr.h"
 
+/* arch_phys_wc_add returns an MTRR register index plus this offset. */
+#define MTRR_TO_PHYS_WC_OFFSET 1000
+
 u32 num_var_ranges;
 
 unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
@@ -525,6 +529,73 @@ int mtrr_del(int reg, unsigned long base, unsigned long size)
 }
 EXPORT_SYMBOL(mtrr_del);
 
+/**
+ * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable
+ * @base: Physical base address
+ * @size: Size of region
+ *
+ * If PAT is available, this does nothing.  If PAT is unavailable, it
+ * attempts to add a WC MTRR covering size bytes starting at base and
+ * logs an error if this fails.
+ *
+ * Drivers must store the return value to pass to mtrr_del_wc_if_needed,
+ * but drivers should not try to interpret that return value.
+ */
+int arch_phys_wc_add(unsigned long base, unsigned long size)
+{
+	int ret;
+
+	if (pat_enabled)
+		return 0;  /* Success!  (We don't need to do anything.) */
+
+	ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true);
+	if (ret < 0) {
+		pr_warn("Failed to add WC MTRR for [%p-%p]; performance may suffer.",
+			(void *)base, (void *)(base + size - 1));
+		return ret;
+	}
+	return ret + MTRR_TO_PHYS_WC_OFFSET;
+}
+EXPORT_SYMBOL(arch_phys_wc_add);
+
+/*
+ * arch_phys_wc_del - undoes arch_phys_wc_add
+ * @handle: Return value from arch_phys_wc_add
+ *
+ * This cleans up after mtrr_add_wc_if_needed.
+ *
+ * The API guarantees that mtrr_del_wc_if_needed(error code) and
+ * mtrr_del_wc_if_needed(0) do nothing.
+ */
+void arch_phys_wc_del(int handle)
+{
+	if (handle >= 1) {
+		WARN_ON(handle < MTRR_TO_PHYS_WC_OFFSET);
+		mtrr_del(handle - MTRR_TO_PHYS_WC_OFFSET, 0, 0);
+	}
+}
+EXPORT_SYMBOL(arch_phys_wc_del);
+
+/*
+ * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value
+ * @handle: Return value from arch_phys_wc_add
+ *
+ * This will turn the return value from arch_phys_wc_add into an mtrr
+ * index suitable for debugging.
+ *
+ * Note: There is no legitimate use for this function, except possibly
+ * in printk line.  Alas there is an illegitimate use in some ancient
+ * drm ioctls.
+ */
+int phys_wc_to_mtrr_index(int handle)
+{
+	if (handle < MTRR_TO_PHYS_WC_OFFSET)
+		return -1;
+	else
+		return handle - MTRR_TO_PHYS_WC_OFFSET;
+}
+EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index);
+
 /*
  * HACK ALERT!
  * These should be called implicitly, but we can't yet until all the initcall
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
index 0db655ef3918..639d1289b1ba 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
@@ -491,10 +491,8 @@ static struct perf_amd_iommu __perf_iommu = {
 static __init int amd_iommu_pc_init(void)
 {
 	/* Make sure the IOMMU PC resource is available */
-	if (!amd_iommu_pc_supported()) {
-		pr_err("perf: amd_iommu PMU not installed. No support!\n");
+	if (!amd_iommu_pc_supported())
 		return -ENODEV;
-	}
 
 	_init_perf_amd_iommu(&__perf_iommu, "amd_iommu");
 
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index f4fe0b8879e0..cdaa347dfcad 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -265,23 +265,30 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 	 */
 }
 
-void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+static inline void smp_entering_irq(void)
 {
 	ack_APIC_irq();
+	irq_enter();
+}
+
+void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+{
+	/*
+	 * Need to call irq_enter() before calling the trace point.
+	 * __smp_reschedule_interrupt() calls irq_enter/exit() too (in
+	 * scheduler_ipi(). This is OK, since those functions are allowed
+	 * to nest.
+	 */
+	smp_entering_irq();
 	trace_reschedule_entry(RESCHEDULE_VECTOR);
 	__smp_reschedule_interrupt();
 	trace_reschedule_exit(RESCHEDULE_VECTOR);
+	exiting_irq();
 	/*
 	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */
 }
 
-static inline void call_function_entering_irq(void)
-{
-	ack_APIC_irq();
-	irq_enter();
-}
-
 static inline void __smp_call_function_interrupt(void)
 {
 	generic_smp_call_function_interrupt();
@@ -290,14 +297,14 @@ static inline void __smp_call_function_interrupt(void)
 
 void smp_call_function_interrupt(struct pt_regs *regs)
 {
-	call_function_entering_irq();
+	smp_entering_irq();
 	__smp_call_function_interrupt();
 	exiting_irq();
 }
 
 void smp_trace_call_function_interrupt(struct pt_regs *regs)
 {
-	call_function_entering_irq();
+	smp_entering_irq();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
 	__smp_call_function_interrupt();
 	trace_call_function_exit(CALL_FUNCTION_VECTOR);
@@ -312,14 +319,14 @@ static inline void __smp_call_function_single_interrupt(void)
 
 void smp_call_function_single_interrupt(struct pt_regs *regs)
 {
-	call_function_entering_irq();
+	smp_entering_irq();
 	__smp_call_function_single_interrupt();
 	exiting_irq();
 }
 
 void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
 {
-	call_function_entering_irq();
+	smp_entering_irq();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
 	__smp_call_function_single_interrupt();
 	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);