cpuidle, xenpv: Make more PARAVIRT_XXL noinstr clean

objtool found a few cases where this code called out into instrumented
code:

  vmlinux.o: warning: objtool: acpi_idle_enter_s2idle+0xde: call to wbinvd() leaves .noinstr.text section
  vmlinux.o: warning: objtool: default_idle+0x4: call to arch_safe_halt() leaves .noinstr.text section
  vmlinux.o: warning: objtool: xen_safe_halt+0xa: call to HYPERVISOR_sched_op.constprop.0() leaves .noinstr.text section

Solve this by:

 - marking arch_safe_halt(), wbinvd(), native_wbinvd() and
   HYPERVISOR_sched_op() as __always_inline().

 - Explicitly uninlining xen_safe_halt() and pv_native_wbinvd() [they were
   already uninlined by the compiler on use as function pointers] and
   annotating them as 'noinstr'.

 - Annotating pv_native_safe_halt() as 'noinstr'.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Reviewed-by: Juergen Gross <jgross@suse.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195541.171918174@infradead.org

arch/x86/include/asm/paravirt.h

@@ -168,7 +168,7 @@ static inline void __write_cr4(unsigned long x)
 	PVOP_VCALL1(cpu.write_cr4, x);
 }
 
-static inline void arch_safe_halt(void)
+static __always_inline void arch_safe_halt(void)
 {
 	PVOP_VCALL0(irq.safe_halt);
 }
@@ -178,7 +178,9 @@ static inline void halt(void)
 	PVOP_VCALL0(irq.halt);
 }
 
-static inline void wbinvd(void)
+extern noinstr void pv_native_wbinvd(void);
+
+static __always_inline void wbinvd(void)
 {
 	PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
 }

arch/x86/include/asm/special_insns.h

@@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru)
 }
 #endif
 
-static inline void native_wbinvd(void)
+static __always_inline void native_wbinvd(void)
 {
 	asm volatile("wbinvd": : :"memory");
 }
@@ -179,7 +179,7 @@ static inline void __write_cr4(unsigned long x)
 	native_write_cr4(x);
 }
 
-static inline void wbinvd(void)
+static __always_inline void wbinvd(void)
 {
 	native_wbinvd();
 }

arch/x86/include/asm/xen/hypercall.h

@@ -382,7 +382,7 @@ MULTI_stack_switch(struct multicall_entry *mcl,
 }
 #endif
 
-static inline int
+static __always_inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
 	return _hypercall2(int, sched_op, cmd, arg);

arch/x86/kernel/paravirt.c

@@ -216,6 +216,11 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val)
 	native_set_debugreg(regno, val);
 }
 
+noinstr void pv_native_wbinvd(void)
+{
+	native_wbinvd();
+}
+
 static noinstr void pv_native_irq_enable(void)
 {
 	native_irq_enable();
@@ -225,6 +230,11 @@ static noinstr void pv_native_irq_disable(void)
 {
 	native_irq_disable();
 }
+
+static noinstr void pv_native_safe_halt(void)
+{
+	native_safe_halt();
+}
 #endif
 
 enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
@@ -256,7 +266,7 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.read_cr0		= native_read_cr0,
 	.cpu.write_cr0		= native_write_cr0,
 	.cpu.write_cr4		= native_write_cr4,
-	.cpu.wbinvd		= native_wbinvd,
+	.cpu.wbinvd		= pv_native_wbinvd,
 	.cpu.read_msr		= native_read_msr,
 	.cpu.write_msr		= native_write_msr,
 	.cpu.read_msr_safe	= native_read_msr_safe,
@@ -290,7 +300,7 @@ struct paravirt_patch_template pv_ops = {
 	.irq.save_fl		= __PV_IS_CALLEE_SAVE(native_save_fl),
 	.irq.irq_disable	= __PV_IS_CALLEE_SAVE(pv_native_irq_disable),
 	.irq.irq_enable		= __PV_IS_CALLEE_SAVE(pv_native_irq_enable),
-	.irq.safe_halt		= native_safe_halt,
+	.irq.safe_halt		= pv_native_safe_halt,
 	.irq.halt		= native_halt,
 #endif /* CONFIG_PARAVIRT_XXL */
 

arch/x86/xen/enlighten_pv.c

@@ -1068,7 +1068,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
 
 		.write_cr4 = xen_write_cr4,
 
-		.wbinvd = native_wbinvd,
+		.wbinvd = pv_native_wbinvd,
 
 		.read_msr = xen_read_msr,
 		.write_msr = xen_write_msr,

arch/x86/xen/irq.c

@@ -24,7 +24,7 @@ noinstr void xen_force_evtchn_callback(void)
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-static void xen_safe_halt(void)
+static noinstr void xen_safe_halt(void)
 {
 	/* Blocking includes an implicit local_irq_enable(). */
 	if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)