x86/entry: Optimize local_db_save() for virt

Because DRn access is 'difficult' with virt; but the DR7 read is cheaper
than a cacheline miss on native, add a virt specific fast path to
local_db_save(), such that when breakpoints are not in use to avoid
touching DRn entirely.
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200529213321.187833200@infradead.org

arch/x86/include/asm/debugreg.h

@@ -85,7 +85,7 @@ static inline void hw_breakpoint_disable(void)
 	set_debugreg(0UL, 3);
 }
 
-static inline int hw_breakpoint_active(void)
+static inline bool hw_breakpoint_active(void)
 {
 	return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
 }
@@ -117,6 +117,9 @@ static __always_inline unsigned long local_db_save(void)
 {
 	unsigned long dr7;
 
+	if (static_cpu_has(X86_FEATURE_HYPERVISOR) && !hw_breakpoint_active())
+		return 0;
+
 	get_debugreg(dr7, 7);
 	dr7 &= ~0x400; /* architecturally set bit */
 	if (dr7)

arch/x86/kernel/hw_breakpoint.c

@@ -99,6 +99,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	unsigned long *dr7;
 	int i;
 
+	lockdep_assert_irqs_disabled();
+
 	for (i = 0; i < HBP_NUM; i++) {
 		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
@@ -117,6 +119,12 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	dr7 = this_cpu_ptr(&cpu_dr7);
 	*dr7 |= encode_dr7(i, info->len, info->type);
 
+	/*
+	 * Ensure we first write cpu_dr7 before we set the DR7 register.
+	 * This ensures an NMI never see cpu_dr7 0 when DR7 is not.
+	 */
+	barrier();
+
 	set_debugreg(*dr7, 7);
 	if (info->mask)
 		set_dr_addr_mask(info->mask, i);
@@ -136,9 +144,11 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 {
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-	unsigned long *dr7;
+	unsigned long dr7;
 	int i;
 
+	lockdep_assert_irqs_disabled();
+
 	for (i = 0; i < HBP_NUM; i++) {
 		struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
 
@@ -151,12 +161,20 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
 		return;
 
-	dr7 = this_cpu_ptr(&cpu_dr7);
-	*dr7 &= ~__encode_dr7(i, info->len, info->type);
+	dr7 = this_cpu_read(cpu_dr7);
+	dr7 &= ~__encode_dr7(i, info->len, info->type);
 
-	set_debugreg(*dr7, 7);
+	set_debugreg(dr7, 7);
 	if (info->mask)
 		set_dr_addr_mask(0, i);
+
+	/*
+	 * Ensure the write to cpu_dr7 is after we've set the DR7 register.
+	 * This ensures an NMI never see cpu_dr7 0 when DR7 is not.
+	 */
+	barrier();
+
+	this_cpu_write(cpu_dr7, dr7);
 }
 
 static int arch_bp_generic_len(int x86_len)

arch/x86/kvm/vmx/nested.c

@@ -3087,9 +3087,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	/*
 	 * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
 	 */
-	local_irq_enable();
 	if (hw_breakpoint_active())
 		set_debugreg(__this_cpu_read(cpu_dr7), 7);
+	local_irq_enable();
 	preempt_enable();
 
 	/*