On 2021/5/17 16:32, Peter Zijlstra wrote:
On Tue, May 11, 2021 at 10:42:04AM +0800, Like Xu wrote:
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2f89fd599842..c791765f4761 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3898,31 +3898,49 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
+ u64 pebs_mask = (x86_pmu.flags & PMU_FL_PEBS_ALL) ?
+ cpuc->pebs_enabled : (cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+
+ *nr = 0;
+ arr[(*nr)++] = (struct perf_guest_switch_msr){
+ .msr = MSR_CORE_PERF_GLOBAL_CTRL,
+ .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask,
+ .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask),
+ };
+ if (!x86_pmu.pebs)
+ return arr;
+ /*
+ * If PMU counter has PEBS enabled it is not enough to
+ * disable counter on a guest entry since PEBS memory
+ * write can overshoot guest entry and corrupt guest
+ * memory. Disabling PEBS solves the problem.
+ *
+ * Don't do this if the CPU already enforces it.
+ */
+ if (x86_pmu.pebs_no_isolation) {
+ arr[(*nr)++] = (struct perf_guest_switch_msr){
+ .msr = MSR_IA32_PEBS_ENABLE,
+ .host = cpuc->pebs_enabled,
+ .guest = 0,
+ };
+ return arr;
}
+ if (!x86_pmu.pebs_vmx)
+ return arr;
+
+ arr[*nr] = (struct perf_guest_switch_msr){
+ .msr = MSR_IA32_PEBS_ENABLE,
+ .host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
+ .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+ };
+
+ /* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
+ arr[0].guest |= arr[*nr].guest;
+
+ ++(*nr);
return arr;
}
ISTR saying I was confused as heck by this function, I still don't see
clarifying comments :/
What's .host and .guest ?
Will adding the following comments help you ?
+/*
+ * Currently, the only caller of this function is the
atomic_switch_perf_msrs().
+ * The host perf conext helps to prepare the values of the real hardware for
+ * a set of msrs that need to be switched atomically in a vmx transaction.
+ *
+ * For example, the pseudocode needed to add a new msr should look like:
+ *
+ * arr[(*nr)++] = (struct perf_guest_switch_msr){
+ * .msr = the hardware msr address,
+ * .host = the value the hardware has when it doesn't run a guest,
+ * .guest = the value the hardware has when it runs a guest,
+ * };
+ *
+ * These values have nothing to do with the emulated values the guest sees
+ * when it uses {RD,WR}MSR, which should be handled in the KVM context.
+ */
static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void
*data)
