From: Like Xu <like.xu@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
Paolo Bonzini <pbonzini@redhat.com>,
kvm@vger.kernel.org
Cc: Sean Christopherson <sean.j.christopherson@intel.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Kan Liang <kan.liang@linux.intel.com>,
luwei.kang@intel.com, Thomas Gleixner <tglx@linutronix.de>,
wei.w.wang@intel.com, Tony Luck <tony.luck@intel.com>,
Stephane Eranian <eranian@google.com>,
Mark Gross <mgross@linux.intel.com>,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
linux-kernel@vger.kernel.org
Subject: [PATCH RFC v2 15/17] KVM: vmx/pmu: Rewrite applicable_counters field in the guest PEBS record
Date: Mon, 9 Nov 2020 10:12:52 +0800 [thread overview]
Message-ID: <20201109021254.79755-16-like.xu@linux.intel.com> (raw)
In-Reply-To: <20201109021254.79755-1-like.xu@linux.intel.com>
The PEBS event counters scheduled by host may different to the counters
required by guest. The host counter index will be leaked into the guest
PEBS record and the guest driver will be confused by the counter indexes
in the "Applicable Counters" field of the PEBS records and ignore them.
Before the guest PEBS overflow PMI is injected into the guest through
global status, KVM needs to rewrite the "Applicable Counters" field with
the right enabled guest pebs counter idx(s) in the guest PEBS records.
Co-developed-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/pmu.c | 1 +
arch/x86/kvm/vmx/pmu_intel.c | 85 +++++++++++++++++++++++++++++++--
3 files changed, 82 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 77b529b8c16a..cdc3c6efdd8e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -457,6 +457,7 @@ struct kvm_pmu {
bool counter_cross_mapped;
bool need_rewrite_ds_pebs_interrupt_threshold;
+ bool need_rewrite_pebs_records;
/*
* The gate to release perf_events not marked in
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 7c8e3ca5b7ad..64dce19644e3 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -77,6 +77,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
if (!test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) {
if (perf_event->attr.precise_ip) {
+ pmu->need_rewrite_pebs_records = pmu->counter_cross_mapped;
/* Indicate PEBS overflow PMI to guest. */
__set_bit(62, (unsigned long *)&pmu->global_status);
} else
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 346b1104e674..d58d04ee13a5 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -551,22 +551,97 @@ static int rewrite_ds_pebs_interrupt_threshold(struct kvm_vcpu *vcpu)
return ret;
}
+static int rewrite_ds_pebs_records(struct kvm_vcpu *vcpu)
+{
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+ struct kvm_pmc *pmc = NULL;
+ struct debug_store *ds = NULL;
+ gpa_t gpa;
+ u64 pebs_buffer_base, offset, status, new_status, format_size;
+ int srcu_idx, bit, ret = 0;
+
+ if (!pmu->counter_cross_mapped)
+ return ret;
+
+ ds = kmalloc(sizeof(struct debug_store), GFP_KERNEL);
+ if (!ds)
+ return -ENOMEM;
+
+ ret = -EFAULT;
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ gpa = kvm_mmu_gva_to_gpa_system(vcpu, pmu->ds_area, NULL);
+ if (gpa == UNMAPPED_GVA)
+ goto out;
+
+ if (kvm_read_guest(vcpu->kvm, gpa, ds, sizeof(struct debug_store)))
+ goto out;
+
+ if (ds->pebs_index <= ds->pebs_buffer_base)
+ goto out;
+
+ pebs_buffer_base = ds->pebs_buffer_base;
+ offset = offsetof(struct pebs_basic, applicable_counters);
+
+ do {
+ ret = -EFAULT;
+ gpa = kvm_mmu_gva_to_gpa_system(vcpu, pebs_buffer_base + offset, NULL);
+ if (gpa == UNMAPPED_GVA)
+ goto out;
+ if (kvm_read_guest(vcpu->kvm, gpa, &status, sizeof(u64)))
+ goto out;
+
+ new_status = 0ull;
+ for_each_set_bit(bit, (unsigned long *)&pmu->pebs_enable, X86_PMC_IDX_MAX) {
+ pmc = kvm_x86_ops.pmu_ops->pmc_idx_to_pmc(pmu, bit);
+
+ if (!pmc || !pmc->perf_event)
+ continue;
+
+ if (test_bit(pmc->perf_event->hw.idx, (unsigned long *)&status))
+ new_status |= BIT_ULL(pmc->idx);
+ }
+ if (kvm_write_guest(vcpu->kvm, gpa, &new_status, sizeof(u64)))
+ goto out;
+
+ gpa = kvm_mmu_gva_to_gpa_system(vcpu, pebs_buffer_base, NULL);
+ if (gpa == UNMAPPED_GVA)
+ goto out;
+ if (kvm_read_guest(vcpu->kvm, gpa, &format_size, sizeof(u64)))
+ goto out;
+ ret = 0;
+
+ pebs_buffer_base = pebs_buffer_base + (format_size >> 48);
+ } while (pebs_buffer_base < ds->pebs_index);
+
+out:
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+ kfree(ds);
+ return ret;
+}
+
void intel_pmu_handle_event(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- int ret;
+ int ret1, ret2;
+
+ if (pmu->need_rewrite_pebs_records) {
+ pmu->need_rewrite_pebs_records = false;
+ ret1 = rewrite_ds_pebs_records(vcpu);
+ }
if (!(pmu->global_ctrl & pmu->pebs_enable))
- return;
+ goto out;
if (pmu->counter_cross_mapped && pmu->need_rewrite_ds_pebs_interrupt_threshold) {
- ret = rewrite_ds_pebs_interrupt_threshold(vcpu);
pmu->need_rewrite_ds_pebs_interrupt_threshold = false;
+ ret2 = rewrite_ds_pebs_interrupt_threshold(vcpu);
}
- if (ret == -ENOMEM)
+out:
+
+ if (ret1 == -ENOMEM || ret2 == -ENOMEM)
pr_debug_ratelimited("%s: Fail to emulate guest PEBS due to OOM.", __func__);
- else if (ret == -EFAULT)
+ else if (ret1 == -EFAULT || ret2 == -EFAULT)
pr_debug_ratelimited("%s: Fail to emulate guest PEBS due to GPA fault.", __func__);
}
--
2.21.3
next prev parent reply other threads:[~2020-11-09 2:17 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-09 2:12 [PATCH RFC v2 00/17] KVM: x86/pmu: Add support to enable Guest PEBS via DS Like Xu
2020-11-09 2:12 ` [PATCH v2 01/17] KVM: x86/pmu: Set MSR_IA32_MISC_ENABLE_EMON bit when vPMU is enabled Like Xu
2020-11-09 2:12 ` [PATCH v2 02/17] KVM: vmx/pmu: Use IA32_PERF_CAPABILITIES to adjust features visibility Like Xu
2020-11-09 2:12 ` [PATCH v2 03/17] KVM: x86/pmu: Introduce the ctrl_mask value for fixed counter Like Xu
2020-11-09 2:12 ` [PATCH v2 04/17] perf: x86/ds: Handle guest PEBS overflow PMI and inject it to guest Like Xu
2020-11-17 14:35 ` Peter Zijlstra
2020-11-18 16:15 ` Like Xu
2020-11-18 18:07 ` Peter Zijlstra
2020-11-19 1:36 ` Xu, Like
2020-11-27 2:14 ` Xu, Like
2020-11-30 10:49 ` Peter Zijlstra
2020-12-01 1:25 ` Xu, Like
2020-11-09 2:12 ` [PATCH v2 05/17] KVM: x86/pmu: Reprogram guest PEBS event to emulate guest PEBS counter Like Xu
2020-11-17 14:41 ` Peter Zijlstra
2020-11-18 16:18 ` Like Xu
2020-11-09 2:12 ` [PATCH v2 06/17] KVM: x86/pmu: Add IA32_PEBS_ENABLE MSR emulation for extended PEBS Like Xu
2020-11-09 2:12 ` [PATCH v2 07/17] KVM: x86/pmu: Add IA32_DS_AREA MSR emulation to manage guest DS buffer Like Xu
2020-11-09 2:12 ` [PATCH v2 08/17] KVM: x86/pmu: Add PEBS_DATA_CFG MSR emulation to support adaptive PEBS Like Xu
2020-11-09 2:12 ` [PATCH v2 09/17] KVM: x86: Set PEBS_UNAVAIL in IA32_MISC_ENABLE when PEBS is enabled Like Xu
2020-11-09 2:12 ` [PATCH v2 10/17] KVM: x86/pmu: Expose CPUIDs feature bits PDCM, DS, DTES64 Like Xu
2020-11-09 2:12 ` [PATCH v2 11/17] KVM: x86/pmu: Adjust precise_ip to emulate Ice Lake guest PDIR counter Like Xu
2020-11-09 2:12 ` [PATCH v2 12/17] KVM: x86/pmu: Disable guest PEBS when counters are cross-mapped Like Xu
2020-11-09 2:12 ` [PATCH RFC v2 13/17] KVM: x86/pmu: Add hook to emulate pebs for cross-mapped counters Like Xu
2020-11-09 2:12 ` [PATCH RFC v2 14/17] KVM: vmx/pmu: Limit pebs_interrupt_threshold in the guest DS area Like Xu
2020-11-09 2:12 ` Like Xu [this message]
2020-11-09 2:12 ` [PATCH RFC v2 16/17] KVM: x86/pmu: Save guest pebs reset value when a pebs counter is configured Like Xu
2020-11-09 2:12 ` [PATCH RFC v2 17/17] KVM: x86/pmu: Adjust guest DS pebs reset counter values for mapped counter Like Xu
2020-11-10 15:12 ` [PATCH RFC v2 00/17] KVM: x86/pmu: Add support to enable Guest PEBS via DS Peter Zijlstra
2020-11-10 15:37 ` [PATCH] perf/intel: Remove Perfmon-v4 counter_freezing support Peter Zijlstra
2020-11-10 20:52 ` Stephane Eranian
2020-11-11 2:42 ` Xu, Like
2021-01-26 9:51 ` Paolo Bonzini
2021-01-26 10:36 ` Peter Zijlstra
2021-01-26 11:35 ` Xu, Like
2021-01-26 11:59 ` Paolo Bonzini
2020-11-11 8:38 ` Peter Zijlstra
2020-11-16 3:22 ` Like Xu
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=20201109021254.79755-16-like.xu@linux.intel.com \
--to=like.xu@linux.intel.com \
--cc=eranian@google.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kan.liang@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luwei.kang@intel.com \
--cc=mgross@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=sean.j.christopherson@intel.com \
--cc=srinivas.pandruvada@linux.intel.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.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;
as well as URLs for NNTP newsgroup(s).