x86/amd: Cache debug register values in percpu variables

Reading DR[0-3]_ADDR_MASK MSRs takes about 250 cycles which is going to
be noticeable with the AMD KVM SEV-ES DebugSwap feature enabled.  KVM is
going to store host's DR[0-3] and DR[0-3]_ADDR_MASK before switching to
a guest; the hardware is going to swap these on VMRUN and VMEXIT.

Store MSR values passed to set_dr_addr_mask() in percpu variables
(when changed) and return them via new amd_get_dr_addr_mask().
The gain here is about 10x.

As set_dr_addr_mask() uses the array too, change the @dr type to
unsigned to avoid checking for <0. And give it the amd_ prefix to match
the new helper as the whole DR_ADDR_MASK feature is AMD-specific anyway.

While at it, replace deprecated boot_cpu_has() with cpu_feature_enabled()
in set_dr_addr_mask().
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20230120031047.628097-2-aik@amd.com

arch/x86/include/asm/debugreg.h

@@ -126,9 +126,14 @@ static __always_inline void local_db_restore(unsigned long dr7)
 }
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern void set_dr_addr_mask(unsigned long mask, int dr);
+extern void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr);
+extern unsigned long amd_get_dr_addr_mask(unsigned int dr);
 #else
-static inline void set_dr_addr_mask(unsigned long mask, int dr) { }
+static inline void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr) { }
+static inline unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+	return 0;
+}
 #endif
 
 #endif /* _ASM_X86_DEBUGREG_H */

arch/x86/kernel/cpu/amd.c

@@ -1158,24 +1158,43 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 	return false;
 }
 
-void set_dr_addr_mask(unsigned long mask, int dr)
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[4], amd_dr_addr_mask);
+
+static unsigned int amd_msr_dr_addr_masks[] = {
+	MSR_F16H_DR0_ADDR_MASK,
+	MSR_F16H_DR1_ADDR_MASK,
+	MSR_F16H_DR1_ADDR_MASK + 1,
+	MSR_F16H_DR1_ADDR_MASK + 2
+};
+
+void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
 {
-	if (!boot_cpu_has(X86_FEATURE_BPEXT))
+	int cpu = smp_processor_id();
+
+	if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
 		return;
 
-	switch (dr) {
-	case 0:
-		wrmsr(MSR_F16H_DR0_ADDR_MASK, mask, 0);
-		break;
-	case 1:
-	case 2:
-	case 3:
-		wrmsr(MSR_F16H_DR1_ADDR_MASK - 1 + dr, mask, 0);
-		break;
-	default:
-		break;
-	}
+	if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+		return;
+
+	if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
+		return;
+
+	wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+	per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
+}
+
+unsigned long amd_get_dr_addr_mask(unsigned int dr)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_BPEXT))
+		return 0;
+
+	if (WARN_ON_ONCE(dr >= ARRAY_SIZE(amd_msr_dr_addr_masks)))
+		return 0;
+
+	return per_cpu(amd_dr_addr_mask[dr], smp_processor_id());
 }
+EXPORT_SYMBOL_GPL(amd_get_dr_addr_mask);
 
 u32 amd_get_highest_perf(void)
 {

arch/x86/kernel/hw_breakpoint.c

@@ -127,7 +127,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 
 	set_debugreg(*dr7, 7);
 	if (info->mask)
-		set_dr_addr_mask(info->mask, i);
+		amd_set_dr_addr_mask(info->mask, i);
 
 	return 0;
 }
@@ -166,7 +166,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 
 	set_debugreg(dr7, 7);
 	if (info->mask)
-		set_dr_addr_mask(0, i);
+		amd_set_dr_addr_mask(0, i);
 
 	/*
 	 * Ensure the write to cpu_dr7 is after we've set the DR7 register.