x86: retpolines: eliminate retpoline from msr event handlers

It's enough to check the value and issue the direct call.

After this commit is applied, here the most common retpolines executed
under a high resolution timer workload in the guest on a VMX host:

[..]
@[
    trace_retpoline+1
    __trace_retpoline+30
    __x86_indirect_thunk_rax+33
    do_syscall_64+89
    entry_SYSCALL_64_after_hwframe+68
]: 267
@[]: 2256
@[
    trace_retpoline+1
    __trace_retpoline+30
    __x86_indirect_thunk_rax+33
    __kvm_wait_lapic_expire+284
    vmx_vcpu_run.part.97+1091
    vcpu_enter_guest+377
    kvm_arch_vcpu_ioctl_run+261
    kvm_vcpu_ioctl+559
    do_vfs_ioctl+164
    ksys_ioctl+96
    __x64_sys_ioctl+22
    do_syscall_64+89
    entry_SYSCALL_64_after_hwframe+68
]: 2390
@[]: 33410

@total: 315707

Note the highest hit above is __delay so probably not worth optimizing
even if it would be more frequent than 2k hits per sec.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fcef678c342304ecea5bb9c29af16b9502f3cbc9..937363b803c19d3a1c90b84a22eeec2969d08be1 100644 (file)
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3323,8 +3323,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
        return 0;
 }
 
+#ifdef CONFIG_RETPOLINE
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr);
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr);
+#endif
+
 struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
+#ifdef CONFIG_RETPOLINE
+       if (x86_pmu.guest_get_msrs == intel_guest_get_msrs)
+               return intel_guest_get_msrs(nr);
+       else if (x86_pmu.guest_get_msrs == core_guest_get_msrs)
+               return core_guest_get_msrs(nr);
+#endif
        if (x86_pmu.guest_get_msrs)
                return x86_pmu.guest_get_msrs(nr);
        *nr = 0;