From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Kan Liang <kan.liang@linux.intel.com>,
Dapeng Mi <dapeng1.mi@linux.intel.com>,
Jim Mattson <jmattson@google.com>,
Jinrong Liang <cloudliang@tencent.com>,
Aaron Lewis <aaronlewis@google.com>,
Like Xu <likexu@tencent.com>
Subject: [PATCH v8 07/26] KVM: x86/pmu: Apply "fast" RDPMC only to Intel PMUs
Date: Thu, 9 Nov 2023 18:12:47 -0800 [thread overview]
Message-ID: <20231110021306.1269082-8-seanjc@google.com> (raw)
In-Reply-To: <20231110021306.1269082-1-seanjc@google.com>
Move the handling of "fast" RDPMC instructions, which drop bits 63:31 of
the count, to Intel. The "fast" flag, and all flags for that matter, are
Intel-only and aren't supported by AMD.
Opportunistically replace open coded bit crud with proper #defines.
Fixes: ca724305a2b0 ("KVM: x86/vPMU: Implement AMD vPMU code for KVM")
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/pmu.c | 3 +--
arch/x86/kvm/vmx/pmu_intel.c | 20 ++++++++++++++++----
2 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 99ed72966528..e3ba5e12c2e7 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -499,10 +499,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
- bool fast_mode = idx & (1u << 31);
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
- u64 mask = fast_mode ? ~0u : ~0ull;
+ u64 mask = ~0ull;
if (!pmu->version)
return 1;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 3bac3b32b485..c6ea128ea7c8 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -20,6 +20,10 @@
#include "nested.h"
#include "pmu.h"
+/* Perf's "BASE" is wildly misleading, this is a single-bit flag, not a base. */
+#define INTEL_RDPMC_FIXED INTEL_PMC_FIXED_RDPMC_BASE
+#define INTEL_RDPMC_FAST BIT(31)
+
#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
@@ -55,12 +59,17 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
}
}
+static u32 intel_rdpmc_get_masked_idx(struct kvm_pmu *pmu, u32 idx)
+{
+ return idx & ~(INTEL_RDPMC_FIXED | INTEL_RDPMC_FAST);
+}
+
static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- bool fixed = idx & (1u << 30);
+ bool fixed = idx & INTEL_RDPMC_FIXED;
- idx &= ~(3u << 30);
+ idx = intel_rdpmc_get_masked_idx(pmu, idx);
return fixed ? idx < pmu->nr_arch_fixed_counters
: idx < pmu->nr_arch_gp_counters;
@@ -70,11 +79,14 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
unsigned int idx, u64 *mask)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
- bool fixed = idx & (1u << 30);
+ bool fixed = idx & INTEL_RDPMC_FIXED;
struct kvm_pmc *counters;
unsigned int num_counters;
- idx &= ~(3u << 30);
+ if (idx & INTEL_RDPMC_FAST)
+ *mask &= GENMASK_ULL(31, 0);
+
+ idx = intel_rdpmc_get_masked_idx(pmu, idx);
if (fixed) {
counters = pmu->fixed_counters;
num_counters = pmu->nr_arch_fixed_counters;
--
2.42.0.869.gea05f2083d-goog
next prev parent reply other threads:[~2023-11-10 2:13 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-10 2:12 [PATCH v8 00/26] KVM: x86/pmu: selftests: Fixes and new tests Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 01/26] KVM: x86/pmu: Always treat Fixed counters as available when supported Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 02/26] KVM: x86/pmu: Allow programming events that match unsupported arch events Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 03/26] KVM: x86/pmu: Remove KVM's enumeration of Intel's architectural encodings Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 04/26] KVM: x86/pmu: Setup fixed counters' eventsel during PMU initialization Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 05/26] KVM: x86/pmu: Get eventsel for fixed counters from perf Sean Christopherson
2023-11-10 13:48 ` Liang, Kan
2023-11-10 2:12 ` [PATCH v8 06/26] KVM: x86/pmu: Don't ignore bits 31:30 for RDPMC index on AMD Sean Christopherson
2023-11-10 2:12 ` Sean Christopherson [this message]
2023-11-10 3:22 ` [PATCH v8 07/26] KVM: x86/pmu: Apply "fast" RDPMC only to Intel PMUs Mi, Dapeng
2023-11-10 14:51 ` Sean Christopherson
2023-11-13 1:24 ` Mi, Dapeng
2023-11-10 2:12 ` [PATCH v8 08/26] KVM: x86/pmu: Disallow "fast" RDPMC for architectural " Sean Christopherson
2023-11-10 6:07 ` Mi, Dapeng
2023-11-10 23:32 ` Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 09/26] KVM: selftests: Add vcpu_set_cpuid_property() to set properties Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 10/26] KVM: selftests: Drop the "name" param from KVM_X86_PMU_FEATURE() Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 11/26] KVM: selftests: Extend {kvm,this}_pmu_has() to support fixed counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 12/26] KVM: selftests: Add pmu.h and lib/pmu.c for common PMU assets Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 13/26] KVM: selftests: Test Intel PMU architectural events on gp counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 14/26] KVM: selftests: Test Intel PMU architectural events on fixed counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 15/26] KVM: selftests: Test consistency of CPUID with num of gp counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 16/26] KVM: selftests: Test consistency of CPUID with num of fixed counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 17/26] KVM: selftests: Add functional test for Intel's fixed PMU counters Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 18/26] KVM: selftests: Expand PMU counters test to verify LLC events Sean Christopherson
2023-11-10 2:12 ` [PATCH v8 19/26] KVM: selftests: Add a helper to query if the PMU module param is enabled Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 20/26] KVM: selftests: Add helpers to read integer module params Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 21/26] KVM: selftests: Query module param to detect FEP in MSR filtering test Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 22/26] KVM: selftests: Move KVM_FEP macro into common library header Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 23/26] KVM: selftests: Test PMC virtualization with forced emulation Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 24/26] KVM: selftests: Add a forced emulation variation of KVM_ASM_SAFE() Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 25/26] KVM: selftests: Add helpers for safe and safe+forced RDMSR, RDPMC, and XGETBV Sean Christopherson
2023-11-10 2:13 ` [PATCH v8 26/26] KVM: selftests: Extend PMU counters test to validate RDPMC after WRMSR Sean Christopherson
2023-11-13 11:41 ` Jinrong Liang
2023-11-13 13:40 ` Sean Christopherson
2023-11-14 3:07 ` Jinrong Liang
2023-11-10 2:52 ` [PATCH v8 00/26] KVM: x86/pmu: selftests: Fixes and new tests Jinrong Liang
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=20231110021306.1269082-8-seanjc@google.com \
--to=seanjc@google.com \
--cc=aaronlewis@google.com \
--cc=cloudliang@tencent.com \
--cc=dapeng1.mi@linux.intel.com \
--cc=jmattson@google.com \
--cc=kan.liang@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=likexu@tencent.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@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