From: Wei Wang <wei.w.wang@intel.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
pbonzini@redhat.com, ak@linux.intel.com, peterz@infradead.org
Cc: kan.liang@intel.com, mingo@redhat.com, rkrcmar@redhat.com,
like.xu@intel.com, wei.w.wang@intel.com, jannh@google.com,
arei.gonglei@huawei.com, jmattson@google.com
Subject: [PATCH v7 04/12] KVM/x86: intel_pmu_lbr_enable
Date: Mon, 8 Jul 2019 09:23:11 +0800 [thread overview]
Message-ID: <1562548999-37095-5-git-send-email-wei.w.wang@intel.com> (raw)
In-Reply-To: <1562548999-37095-1-git-send-email-wei.w.wang@intel.com>
The lbr stack is architecturally specific, for example, SKX has 32 lbr
stack entries while HSW has 16 entries, so a HSW guest running on a SKX
machine may not get accurate perf results. Currently, we forbid the
guest lbr enabling when the guest and host see different lbr stack
entries or the host and guest see different lbr stack msr indices.
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
---
arch/x86/kvm/pmu.c | 8 +++
arch/x86/kvm/pmu.h | 2 +
arch/x86/kvm/vmx/pmu_intel.c | 136 +++++++++++++++++++++++++++++++++++++++++++
arch/x86/kvm/x86.c | 3 +-
4 files changed, 147 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 132d149..7d7ac18 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -296,6 +296,14 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
return 0;
}
+bool kvm_pmu_lbr_enable(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->pmu_ops->lbr_enable)
+ return kvm_x86_ops->pmu_ops->lbr_enable(vcpu);
+
+ return false;
+}
+
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
{
if (lapic_in_kernel(vcpu))
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 22dff66..c099b4b 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -29,6 +29,7 @@ struct kvm_pmu_ops {
u64 *mask);
int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx);
bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
+ bool (*lbr_enable)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
void (*refresh)(struct kvm_vcpu *vcpu);
@@ -107,6 +108,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel);
void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx);
void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
+bool kvm_pmu_lbr_enable(struct kvm_vcpu *vcpu);
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 68d231d..ef8ebd4 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -12,6 +12,7 @@
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
#include <asm/perf_event.h>
+#include <asm/intel-family.h>
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
@@ -162,6 +163,140 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
return ret;
}
+static bool intel_pmu_lbr_enable(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ u8 vcpu_model = guest_cpuid_model(vcpu);
+ unsigned int vcpu_lbr_from, vcpu_lbr_nr;
+
+ if (x86_perf_get_lbr_stack(&kvm->arch.lbr_stack))
+ return false;
+
+ if (guest_cpuid_family(vcpu) != boot_cpu_data.x86)
+ return false;
+
+ /*
+ * It could be possible that people have vcpus of old model run on
+ * physcal cpus of newer model, for example a BDW guest on a SKX
+ * machine (but not possible to be the other way around).
+ * The BDW guest may not get accurate results on a SKX machine as it
+ * only reads 16 entries of the lbr stack while there are 32 entries
+ * of recordings. We currently forbid the lbr enabling when the vcpu
+ * and physical cpu see different lbr stack entries or the guest lbr
+ * msr indices are not compatible with the host.
+ */
+ switch (vcpu_model) {
+ case INTEL_FAM6_CORE2_MEROM:
+ case INTEL_FAM6_CORE2_MEROM_L:
+ case INTEL_FAM6_CORE2_PENRYN:
+ case INTEL_FAM6_CORE2_DUNNINGTON:
+ /* intel_pmu_lbr_init_core() */
+ vcpu_lbr_nr = 4;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_NEHALEM:
+ case INTEL_FAM6_NEHALEM_EP:
+ case INTEL_FAM6_NEHALEM_EX:
+ /* intel_pmu_lbr_init_nhm() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_ATOM_BONNELL:
+ case INTEL_FAM6_ATOM_BONNELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL:
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+ /* intel_pmu_lbr_init_atom() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
+ case INTEL_FAM6_ATOM_AIRMONT:
+ case INTEL_FAM6_ATOM_AIRMONT_MID:
+ /* intel_pmu_lbr_init_slm() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_CORE_FROM;
+ break;
+ case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
+ /* intel_pmu_lbr_init_skl(); */
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+ /* intel_pmu_lbr_init_skl()*/
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_WESTMERE:
+ case INTEL_FAM6_WESTMERE_EP:
+ case INTEL_FAM6_WESTMERE_EX:
+ /* intel_pmu_lbr_init_nhm() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_SANDYBRIDGE:
+ case INTEL_FAM6_SANDYBRIDGE_X:
+ /* intel_pmu_lbr_init_snb() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_IVYBRIDGE:
+ case INTEL_FAM6_IVYBRIDGE_X:
+ /* intel_pmu_lbr_init_snb() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL_X:
+ case INTEL_FAM6_HASWELL_ULT:
+ case INTEL_FAM6_HASWELL_GT3E:
+ /* intel_pmu_lbr_init_hsw() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_BROADWELL_CORE:
+ case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL_X:
+ /* intel_pmu_lbr_init_hsw() */
+ vcpu_lbr_nr = 16;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
+ /* intel_pmu_lbr_init_knl() */
+ vcpu_lbr_nr = 8;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ case INTEL_FAM6_SKYLAKE_MOBILE:
+ case INTEL_FAM6_SKYLAKE_DESKTOP:
+ case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_KABYLAKE_MOBILE:
+ case INTEL_FAM6_KABYLAKE_DESKTOP:
+ /* intel_pmu_lbr_init_skl() */
+ vcpu_lbr_nr = 32;
+ vcpu_lbr_from = MSR_LBR_NHM_FROM;
+ break;
+ default:
+ vcpu_lbr_nr = 0;
+ vcpu_lbr_from = 0;
+ pr_warn("%s: vcpu model not supported %d\n", __func__,
+ vcpu_model);
+ }
+
+ if (vcpu_lbr_nr != kvm->arch.lbr_stack.nr ||
+ vcpu_lbr_from != kvm->arch.lbr_stack.from) {
+ pr_warn("%s: vcpu model %x incompatible to pcpu %x\n",
+ __func__, vcpu_model, boot_cpu_data.x86_model);
+ return false;
+ }
+
+ return true;
+}
+
static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -361,6 +496,7 @@ struct kvm_pmu_ops intel_pmu_ops = {
.msr_idx_to_pmc = intel_msr_idx_to_pmc,
.is_valid_msr_idx = intel_is_valid_msr_idx,
.is_valid_msr = intel_is_valid_msr,
+ .lbr_enable = intel_pmu_lbr_enable,
.get_msr = intel_pmu_get_msr,
.set_msr = intel_pmu_set_msr,
.refresh = intel_pmu_refresh,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b35a118..5ba4e3b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4625,8 +4625,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
break;
case KVM_CAP_X86_GUEST_LBR:
r = -EINVAL;
- if (cap->args[0] &&
- x86_perf_get_lbr_stack(&kvm->arch.lbr_stack))
+ if (cap->args[0] && !kvm_pmu_lbr_enable(kvm->vcpus[0]))
break;
if (copy_to_user((void __user *)cap->args[1],
--
2.7.4
next prev parent reply other threads:[~2019-07-08 2:07 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-08 1:23 [PATCH v7 00/12] Guest LBR Enabling Wei Wang
2019-07-08 1:23 ` [PATCH v7 01/12] perf/x86: fix the variable type of the LBR MSRs Wei Wang
2019-07-08 1:23 ` [PATCH v7 02/12] perf/x86: add a function to get the lbr stack Wei Wang
2019-07-08 1:23 ` [PATCH v7 03/12] KVM/x86: KVM_CAP_X86_GUEST_LBR Wei Wang
2019-07-08 1:23 ` Wei Wang [this message]
2019-07-08 1:23 ` [PATCH v7 05/12] KVM/x86/vPMU: tweak kvm_pmu_get_msr Wei Wang
2019-07-08 1:23 ` [PATCH v7 06/12] KVM/x86: expose MSR_IA32_PERF_CAPABILITIES to the guest Wei Wang
2019-07-08 1:23 ` [PATCH v7 07/12] perf/x86: no counter allocation support Wei Wang
2019-07-08 14:29 ` Peter Zijlstra
2019-07-09 2:58 ` Wei Wang
2019-07-09 9:43 ` Peter Zijlstra
2019-07-09 11:36 ` Wei Wang
2019-07-08 1:23 ` [PATCH v7 08/12] KVM/x86/vPMU: Add APIs to support host save/restore the guest lbr stack Wei Wang
2019-07-08 14:48 ` Peter Zijlstra
2019-07-09 3:04 ` Wei Wang
2019-07-09 9:39 ` Peter Zijlstra
2019-07-09 11:34 ` Wei Wang
2019-07-09 12:19 ` Peter Zijlstra
2019-07-10 8:19 ` Wei Wang
2019-07-09 11:45 ` Peter Zijlstra
2019-07-10 8:21 ` Wei Wang
2019-07-08 1:23 ` [PATCH v7 09/12] perf/x86: save/restore LBR_SELECT on vCPU switching Wei Wang
2019-07-08 1:23 ` [PATCH v7 10/12] KVM/x86/lbr: lazy save the guest lbr stack Wei Wang
2019-07-08 14:53 ` Peter Zijlstra
2019-07-08 15:11 ` Andi Kleen
2019-07-09 11:39 ` Peter Zijlstra
2019-07-09 3:14 ` Wei Wang
2019-07-08 1:23 ` [PATCH v7 11/12] KVM/x86: remove the common handling of the debugctl msr Wei Wang
2019-07-08 1:23 ` [PATCH v7 12/12] KVM/VMX/vPMU: support to report GLOBAL_STATUS_LBRS_FROZEN Wei Wang
2019-07-08 15:09 ` Peter Zijlstra
2019-07-09 3:24 ` Wei Wang
2019-07-09 11:35 ` Peter Zijlstra
2019-07-10 9:23 ` Wei Wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1562548999-37095-5-git-send-email-wei.w.wang@intel.com \
--to=wei.w.wang@intel.com \
--cc=ak@linux.intel.com \
--cc=arei.gonglei@huawei.com \
--cc=jannh@google.com \
--cc=jmattson@google.com \
--cc=kan.liang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=like.xu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rkrcmar@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox