[PATCH v3 4/5] KVM: x86/pmu: Add counter reload registers to the MSR-load list

[Like Xu]

The guest counter reload registers need to be loaded to real HW
before VM-entry. Taking into account the existing guest PT
implementation, we add those counter reload registers to MSR-load list
when the corresponding PEBS counters are enabled and the optimization
from clear_atomic_switch_msr() can be reused.

To support that, it needs to expand the value of NR_LOADSTORE_MSRS
from 8 to 16 because when all counters are enabled, up to 7 or 8
counter reload registers need to be added into the MSR-load list.

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
---
 arch/x86/events/intel/core.c | 27 +++++++++++++++++++++++++++
 arch/x86/kvm/vmx/vmx.h       |  2 +-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 4404987bbc57..bd6d9e2a64d9 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3903,6 +3903,8 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	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);
+	u64 guest_pebs_enable, base, idx, host_reload_ctr;
+	unsigned long bit;
 
 	*nr = 0;
 	arr[(*nr)++] = (struct perf_guest_switch_msr){
@@ -3964,7 +3966,32 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		arr[0].guest |= arr[*nr].guest;
 	}
 
+	guest_pebs_enable = arr[*nr].guest;
 	++(*nr);
+
+	if (!x86_pmu.intel_cap.pebs_output_pt_available ||
+	    !(guest_pebs_enable & PEBS_OUTPUT_PT))
+		return arr;
+
+	for_each_set_bit(bit, (unsigned long *)&guest_pebs_enable,
+			 X86_PMC_IDX_MAX) {
+		base = (bit < INTEL_PMC_IDX_FIXED) ?
+			MSR_RELOAD_PMC0 : MSR_RELOAD_FIXED_CTR0;
+		idx = (bit < INTEL_PMC_IDX_FIXED) ?
+			bit : (bit - INTEL_PMC_IDX_FIXED);
+
+		/* It's good when the pebs counters are not cross-mapped. */
+		rdmsrl(base, host_reload_ctr);
+
+		arr[(*nr)++] = (struct perf_guest_switch_msr){
+			.msr = base,
+			.host = host_reload_ctr,
+			.guest = (bit < INTEL_PMC_IDX_FIXED) ?
+				pmu->gp_counters[bit].reload_counter :
+				pmu->fixed_counters[bit].reload_counter,
+		};
+	}
+
 	return arr;
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 3afdcebb0a11..25aa1cc3cc6a 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -28,7 +28,7 @@ extern const u32 vmx_msr_index[];
 #define MAX_NR_USER_RETURN_MSRS	4
 #endif
 
-#define MAX_NR_LOADSTORE_MSRS	8
+#define MAX_NR_LOADSTORE_MSRS	16
 
 struct vmx_msrs {
 	unsigned int		nr;
-- 
2.31.1