From: Luwei Kang <luwei.kang@intel.com>
To: pbonzini@redhat.com, rkrcmar@redhat.com
Cc: sean.j.christopherson@intel.com, vkuznets@redhat.com,
wanpengli@tencent.com, jmattson@google.com, joro@8bytes.org,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
hpa@zytor.com, x86@kernel.org, ak@linux.intel.com,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Luwei Kang <luwei.kang@intel.com>
Subject: [RFC v1 6/9] KVM: x86: Add shadow value of PEBS status
Date: Thu, 29 Aug 2019 13:34:06 +0800 [thread overview]
Message-ID: <1567056849-14608-7-git-send-email-luwei.kang@intel.com> (raw)
In-Reply-To: <1567056849-14608-1-git-send-email-luwei.kang@intel.com>
The performance counter used by guest perspective may different
with the counter allocated from real hardware (e.g. Guest driver
get counter 0 for PEBS but the host PMU driver may alloc other
counters for this event).
Introduce a new parameter for the mapping of PEBS enable status from
guest to real hardware. Update the shadow value of PEBS before
VM-entry when PT is enabled in guest.
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/pmu.c | 34 ++++++++++++++++++++++++++++++++++
arch/x86/kvm/pmu.h | 1 +
arch/x86/kvm/vmx/vmx.c | 8 +++++++-
4 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9b930b5..07d3b21 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -473,6 +473,7 @@ struct kvm_pmu {
u64 global_ovf_ctrl_mask;
u64 reserved_bits;
u64 pebs_enable;
+ u64 pebs_enable_shadow;
u64 pebs_enable_mask;
u8 version;
bool pebs_pt; /* PEBS output to Intel PT */
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 6bdc282..89d3e4c 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -257,6 +257,40 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx)
}
EXPORT_SYMBOL_GPL(reprogram_counter);
+void kvm_pmu_pebs_shadow(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct perf_event *event;
+ int i;
+
+ if (!pmu->pebs_pt)
+ return;
+
+ pmu->pebs_enable_shadow = MSR_IA32_PEBS_OUTPUT_PT;
+
+ for (i = 0; i < pmu->nr_arch_gp_counters; i++) {
+ if (!test_bit(i, (unsigned long *)&pmu->pebs_enable))
+ continue;
+
+ event = pmu->gp_counters[i].perf_event;
+ if (event && (event->hw.idx != -1))
+ set_bit(event->hw.idx,
+ (unsigned long *)&pmu->pebs_enable_shadow);
+ }
+
+ for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+ if (!test_bit(i + INTEL_PMC_IDX_FIXED,
+ (unsigned long *)&pmu->pebs_enable))
+ continue;
+
+ event = pmu->fixed_counters[i].perf_event;
+ if (event && (event->hw.idx != -1))
+ set_bit(event->hw.idx,
+ (unsigned long *)&pmu->pebs_enable_shadow);
+ }
+}
+EXPORT_SYMBOL_GPL(kvm_pmu_pebs_shadow);
+
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 0c59a15..81c35c9 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -119,6 +119,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx,
void kvm_pmu_init(struct kvm_vcpu *vcpu);
void kvm_pmu_destroy(struct kvm_vcpu *vcpu);
int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp);
+void kvm_pmu_pebs_shadow(struct kvm_vcpu *vcpu);
bool is_vmware_backdoor_pmc(u32 pmc_idx);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c030c96..4090c08 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1019,6 +1019,7 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
wrmsrl(MSR_IA32_RTIT_CTL, 0);
pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+ kvm_pmu_pebs_shadow(&vmx->vcpu);
}
}
@@ -6365,12 +6366,17 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
if (!msrs)
return;
- for (i = 0; i < nr_msrs; i++)
+ for (i = 0; i < nr_msrs; i++) {
+ if (msrs[i].msr == MSR_IA32_PEBS_ENABLE)
+ msrs[i].guest =
+ vcpu_to_pmu(&vmx->vcpu)->pebs_enable_shadow;
+
if (msrs[i].host == msrs[i].guest)
clear_atomic_switch_msr(vmx, msrs[i].msr);
else
add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
msrs[i].host, false);
+ }
}
static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
--
1.8.3.1
next prev parent reply other threads:[~2019-08-29 5:39 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-29 5:34 [RFC v1 0/9] PEBS enabling in KVM guest Luwei Kang
2019-08-29 5:34 ` [RFC v1 1/9] KVM: x86: Add base address parameter for get_fixed_pmc function Luwei Kang
2019-08-29 19:01 ` Jim Mattson
2019-08-30 0:01 ` Kang, Luwei
2019-08-29 21:10 ` Andi Kleen
2019-08-30 0:15 ` Kang, Luwei
2019-08-29 5:34 ` [RFC v1 2/9] KVM: x86: PEBS via Intel PT HW feature detection Luwei Kang
2019-08-29 5:34 ` [RFC v1 3/9] KVM: x86: Implement MSR_IA32_PEBS_ENABLE read/write emulation Luwei Kang
2019-08-29 21:20 ` Andi Kleen
2019-08-30 0:22 ` Kang, Luwei
2019-08-29 5:34 ` [RFC v1 4/9] KVM: x86: Implement counter reload MSRs " Luwei Kang
2019-08-29 5:34 ` [RFC v1 5/9] KVM: x86: Allocate performance counter for PEBS event Luwei Kang
2019-08-29 5:34 ` Luwei Kang [this message]
2019-08-29 5:34 ` [RFC v1 7/9] KVM: X86: Expose PDCM cpuid to guest Luwei Kang
2019-08-29 5:34 ` [RFC v1 8/9] KVM: X86: MSR_IA32_PERF_CAPABILITIES MSR emulation Luwei Kang
2019-08-29 5:34 ` [RFC v1 9/9] KVM: x86: Expose PEBS feature to guest Luwei Kang
2019-08-29 7:28 ` [RFC v1 0/9] PEBS enabling in KVM guest Peter Zijlstra
2019-08-29 8:11 ` Kang, Luwei
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=1567056849-14608-7-git-send-email-luwei.kang@intel.com \
--to=luwei.kang@intel.com \
--cc=ak@linux.intel.com \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=tglx@linutronix.de \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=x86@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).