perf/core: Rework guest callbacks to prepare for static_call support

To prepare for using static_calls to optimize perf's guest callbacks,
replace ->is_in_guest and ->is_user_mode with a new multiplexed hook
->state, tweak ->handle_intel_pt_intr to play nice with being called when
there is no active guest, and drop "guest" from ->get_guest_ip.

Return '0' from ->state and ->handle_intel_pt_intr to indicate "not in
guest" so that DEFINE_STATIC_CALL_RET0 can be used to define the static
calls, i.e. no callback == !guest.

[sean: extracted from static_call patch, fixed get_ip() bug, wrote changelog]
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-7-seanjc@google.com

arch/arm64/kernel/perf_callchain.c

@@ -104,7 +104,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 {
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->state()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -152,7 +152,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct stackframe frame;
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->state()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -165,8 +165,8 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 
-	if (guest_cbs && guest_cbs->is_in_guest())
-		return guest_cbs->get_guest_ip();
+	if (guest_cbs && guest_cbs->state())
+		return guest_cbs->get_ip();
 
 	return instruction_pointer(regs);
 }
@@ -174,10 +174,11 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+	unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0;
 	int misc = 0;
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
-		if (guest_cbs->is_user_mode())
+	if (guest_state) {
+		if (guest_state & PERF_GUEST_USER)
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;

arch/arm64/kvm/perf.c

@@ -13,39 +13,34 @@
 
 DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
 
-static int kvm_is_in_guest(void)
+static unsigned int kvm_guest_state(void)
 {
-        return kvm_get_running_vcpu() != NULL;
-}
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
+	unsigned int state;
 
-static int kvm_is_user_mode(void)
-{
-	struct kvm_vcpu *vcpu;
+	if (!vcpu)
+		return 0;
 
-	vcpu = kvm_get_running_vcpu();
+	state = PERF_GUEST_ACTIVE;
+	if (!vcpu_mode_priv(vcpu))
+		state |= PERF_GUEST_USER;
 
-	if (vcpu)
-		return !vcpu_mode_priv(vcpu);
-
-	return 0;
+	return state;
 }
 
 static unsigned long kvm_get_guest_ip(void)
 {
-	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
-	vcpu = kvm_get_running_vcpu();
+	if (WARN_ON_ONCE(!vcpu))
+		return 0;
 
-	if (vcpu)
-		return *vcpu_pc(vcpu);
-
-	return 0;
+	return *vcpu_pc(vcpu);
 }
 
 static struct perf_guest_info_callbacks kvm_guest_cbs = {
-	.is_in_guest	= kvm_is_in_guest,
-	.is_user_mode	= kvm_is_user_mode,
-	.get_guest_ip	= kvm_get_guest_ip,
+	.state		= kvm_guest_state,
+	.get_ip		= kvm_get_guest_ip,
 };
 
 void kvm_perf_init(void)

arch/x86/events/core.c

@@ -2772,7 +2772,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->state()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2876,7 +2876,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->state()) {
 		/* TODO: We don't support guest os callchain now */
 		return;
 	}
@@ -2955,8 +2955,8 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 
-	if (guest_cbs && guest_cbs->is_in_guest())
-		return guest_cbs->get_guest_ip();
+	if (guest_cbs && guest_cbs->state())
+		return guest_cbs->get_ip();
 
 	return regs->ip + code_segment_base(regs);
 }
@@ -2964,10 +2964,11 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs)
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
 	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+	unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0;
 	int misc = 0;
 
-	if (guest_cbs && guest_cbs->is_in_guest()) {
-		if (guest_cbs->is_user_mode())
+	if (guest_state) {
+		if (guest_state & PERF_GUEST_USER)
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;

arch/x86/events/intel/core.c

@@ -2906,10 +2906,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		handled++;
 
 		guest_cbs = perf_get_guest_cbs();
-		if (unlikely(guest_cbs && guest_cbs->is_in_guest() &&
-			     guest_cbs->handle_intel_pt_intr))
-			guest_cbs->handle_intel_pt_intr();
-		else
+		if (likely(!guest_cbs || !guest_cbs->handle_intel_pt_intr()))
 			intel_pt_interrupt();
 	}
 

arch/x86/include/asm/kvm_host.h

@@ -1895,7 +1895,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
-int kvm_is_in_guest(void);
+unsigned int kvm_guest_state(void);
 
 void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 				     u32 size);

arch/x86/kvm/pmu.c

@@ -87,7 +87,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 		 * woken up. So we should wake it, but this is impossible from
 		 * NMI context. Do it from irq work instead.
 		 */
-		if (!kvm_is_in_guest())
+		if (!kvm_guest_state())
 			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
 		else
 			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);

arch/x86/kvm/x86.c

@@ -8472,44 +8472,48 @@ static void kvm_timer_init(void)
 DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
 EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu);
 
-int kvm_is_in_guest(void)
-{
-	return __this_cpu_read(current_vcpu) != NULL;
-}
-
-static int kvm_is_user_mode(void)
-{
-	int user_mode = 3;
-
-	if (__this_cpu_read(current_vcpu))
-		user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu));
-
-	return user_mode != 0;
-}
-
-static unsigned long kvm_get_guest_ip(void)
-{
-	unsigned long ip = 0;
-
-	if (__this_cpu_read(current_vcpu))
-		ip = kvm_rip_read(__this_cpu_read(current_vcpu));
-
-	return ip;
-}
-
-static void kvm_handle_intel_pt_intr(void)
+unsigned int kvm_guest_state(void)
 {
 	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+	unsigned int state;
+
+	if (!vcpu)
+		return 0;
+
+	state = PERF_GUEST_ACTIVE;
+	if (static_call(kvm_x86_get_cpl)(vcpu))
+		state |= PERF_GUEST_USER;
+
+	return state;
+}
+
+static unsigned long kvm_guest_get_ip(void)
+{
+	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+
+	if (WARN_ON_ONCE(!vcpu))
+		return 0;
+
+	return kvm_rip_read(vcpu);
+}
+
+static unsigned int kvm_handle_intel_pt_intr(void)
+{
+	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+
+	/* '0' on failure so that the !PT case can use a RET0 static call. */
+	if (!vcpu)
+		return 0;
 
 	kvm_make_request(KVM_REQ_PMI, vcpu);
 	__set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT,
 			(unsigned long *)&vcpu->arch.pmu.global_status);
+	return 1;
 }
 
 static struct perf_guest_info_callbacks kvm_guest_cbs = {
-	.is_in_guest		= kvm_is_in_guest,
-	.is_user_mode		= kvm_is_user_mode,
-	.get_guest_ip		= kvm_get_guest_ip,
+	.state			= kvm_guest_state,
+	.get_ip			= kvm_guest_get_ip,
 	.handle_intel_pt_intr	= NULL,
 };
 

arch/x86/xen/pmu.c

@@ -413,34 +413,29 @@ int pmu_apic_update(uint32_t val)
 }
 
 /* perf callbacks */
-static int xen_is_in_guest(void)
+static unsigned int xen_guest_state(void)
 {
 	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
+	unsigned int state = 0;
 
 	if (!xenpmu_data) {
 		pr_warn_once("%s: pmudata not initialized\n", __func__);
-		return 0;
+		return state;
 	}
 
 	if (!xen_initial_domain() || (xenpmu_data->domain_id >= DOMID_SELF))
-		return 0;
+		return state;
 
-	return 1;
-}
+	state |= PERF_GUEST_ACTIVE;
 
-static int xen_is_user_mode(void)
-{
-	const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
-
-	if (!xenpmu_data) {
-		pr_warn_once("%s: pmudata not initialized\n", __func__);
-		return 0;
+	if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV) {
+		if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER)
+			state |= PERF_GUEST_USER;
+	} else if (xenpmu_data->pmu.r.regs.cpl & 3) {
+		state |= PERF_GUEST_USER;
 	}
 
-	if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV)
-		return (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER);
-	else
-		return !!(xenpmu_data->pmu.r.regs.cpl & 3);
+	return state;
 }
 
 static unsigned long xen_get_guest_ip(void)
@@ -456,9 +451,8 @@ static unsigned long xen_get_guest_ip(void)
 }
 
 static struct perf_guest_info_callbacks xen_guest_cbs = {
-	.is_in_guest            = xen_is_in_guest,
-	.is_user_mode           = xen_is_user_mode,
-	.get_guest_ip           = xen_get_guest_ip,
+	.state                  = xen_guest_state,
+	.get_ip			= xen_get_guest_ip,
 };
 
 /* Convert registers from Xen's format to Linux' */

include/linux/perf_event.h

@@ -26,11 +26,13 @@
 # include <asm/local64.h>
 #endif
 
+#define PERF_GUEST_ACTIVE	0x01
+#define PERF_GUEST_USER	0x02
+
 struct perf_guest_info_callbacks {
-	int				(*is_in_guest)(void);
-	int				(*is_user_mode)(void);
-	unsigned long			(*get_guest_ip)(void);
-	void				(*handle_intel_pt_intr)(void);
+	unsigned int			(*state)(void);
+	unsigned long			(*get_ip)(void);
+	unsigned int			(*handle_intel_pt_intr)(void);
 };
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT