[PATCH kernel v2 1/3] x86/amd: Cache values in percpu variables

[Alexey Kardashevskiy]

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

As amd_set_dr_addr_mask() uses the array too, change the @dr type to
unsigned to avoid checking for <0.

While at it, replace deprecated boot_cpu_has() with cpu_feature_enabled()
in set_dr_addr_mask().

Signed-off-by: Alexey Kardashevskiy <aik@xxxxxxx>
---
Changes:
v2:
* reworked to use arrays
* set() skips wrmsr() when the mask is not changed
* added stub for get_dr_addr_mask()
* changed @dr type to unsigned
* s/boot_cpu_has/cpu_feature_enabled/
* added amd_ prefix
---
 arch/x86/include/asm/debugreg.h |  9 +++-
 arch/x86/kernel/cpu/amd.c       | 45 ++++++++++++++------
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index cfdf307ddc01..59f97ba25d5f 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/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 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 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 */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c75d75b9f11a..9ac5a19f89b9 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1158,24 +1158,41 @@ 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)
+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 - 1 + 1,
+	MSR_F16H_DR1_ADDR_MASK - 1 + 2,
+	MSR_F16H_DR1_ADDR_MASK - 1 + 3
+};
+
+void set_dr_addr_mask(unsigned long mask, unsigned int dr)
 {
-	if (!boot_cpu_has(X86_FEATURE_BPEXT))
+	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, smp_processor_id())[dr] == mask)
+		return;
+
+	wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+	per_cpu(amd_dr_addr_mask, smp_processor_id())[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)
 {
-- 
2.38.1