From: Like Xu <like.xu.linux@gmail.com>
To: Paolo Bonzini <pbonzini@redhat.com>, Jim Mattson <jmattson@google.com>
Cc: Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Joerg Roedel <joro@8bytes.org>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
Like Xu <likexu@tencent.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH 07/11] KVM: x86/pmu: Use PERF_TYPE_RAW to merge reprogram_{gp, fixed}counter()
Date: Mon, 21 Feb 2022 19:51:57 +0800 [thread overview]
Message-ID: <20220221115201.22208-8-likexu@tencent.com> (raw)
In-Reply-To: <20220221115201.22208-1-likexu@tencent.com>
From: Like Xu <likexu@tencent.com>
The code sketch for reprogram_{gp, fixed}_counter() is similar, while the
fixed counter using the PERF_TYPE_HARDWAR type and the gp being
able to use either PERF_TYPE_HARDWAR or PERF_TYPE_RAW type
depending on the pmc->eventsel value.
After 'commit 761875634a5e ("KVM: x86/pmu: Setup pmc->eventsel
for fixed PMCs")', the pmc->eventsel of the fixed counter will also have
been setup with the same semantic value and will not be changed during
the guest runtime. But essentially, "the HARDWARE is just a convenience
wrapper over RAW IIRC", quoated from Peterz. So it could be pretty safe
to use the PERF_TYPE_RAW type only to program both gp and fixed
counters naturally in the reprogram_counter().
To make the gp and fixed counters more semantically symmetrical,
the selection of EVENTSEL_{USER, OS, INT} bits is temporarily translated
via fixed_ctr_ctrl before the pmc_reprogram_counter() call.
Practically, this change drops the guest pmu support on the hosts without
X86_FEATURE_ARCH_PERFMON (the oldest Pentium 4), where the
PERF_TYPE_HARDWAR is intentionally introduced so that hosts can
map the architectural guest PMU events to their own.
Cc: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Like Xu <likexu@tencent.com>
---
arch/x86/kvm/pmu.c | 106 +++++++++++------------------------
arch/x86/kvm/vmx/pmu_intel.c | 2 +-
2 files changed, 35 insertions(+), 73 deletions(-)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 5816af6b6494..edd51ec7711d 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -213,35 +213,44 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc)
return allow_event;
}
-static void reprogram_gp_counter(struct kvm_pmc *pmc)
+static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
{
- u64 config;
- u32 type = PERF_TYPE_RAW;
- u64 eventsel = pmc->eventsel;
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
- printk_once("kvm pmu: pin control bit is ignored\n");
+ if (pmc_is_fixed(pmc))
+ return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+ pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
+
+ return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
+}
+
+void reprogram_counter(struct kvm_pmc *pmc)
+{
+ struct kvm_pmu *pmu = pmc_to_pmu(pmc);
+ u64 eventsel = pmc->eventsel;
+ u8 fixed_ctr_ctrl;
pmc_pause_counter(pmc);
- if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
+ if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc))
return;
if (!check_pmu_event_filter(pmc))
return;
- if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
- ARCH_PERFMON_EVENTSEL_INV |
- ARCH_PERFMON_EVENTSEL_CMASK |
- HSW_IN_TX |
- HSW_IN_TX_CHECKPOINTED))) {
- config = kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc);
- if (config != PERF_COUNT_HW_MAX)
- type = PERF_TYPE_HARDWARE;
- }
+ if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
+ printk_once("kvm pmu: pin control bit is ignored\n");
- if (type == PERF_TYPE_RAW)
- config = eventsel & AMD64_RAW_EVENT_MASK;
+ if (pmc_is_fixed(pmc)) {
+ fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl,
+ pmc->idx - INTEL_PMC_IDX_FIXED);
+ if (fixed_ctr_ctrl & 0x1)
+ eventsel |= ARCH_PERFMON_EVENTSEL_OS;
+ if (fixed_ctr_ctrl & 0x2)
+ eventsel |= ARCH_PERFMON_EVENTSEL_USR;
+ if (fixed_ctr_ctrl & 0x8)
+ eventsel |= ARCH_PERFMON_EVENTSEL_INT;
+ }
if (pmc->current_config == eventsel && pmc_resume_counter(pmc))
return;
@@ -249,49 +258,13 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc)
pmc_release_perf_event(pmc);
pmc->current_config = eventsel;
- pmc_reprogram_counter(pmc, type, config,
- !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
- !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT,
- (eventsel & HSW_IN_TX),
- (eventsel & HSW_IN_TX_CHECKPOINTED));
-}
-
-static void reprogram_fixed_counter(struct kvm_pmc *pmc)
-{
- struct kvm_pmu *pmu = pmc_to_pmu(pmc);
- int idx = pmc->idx - INTEL_PMC_IDX_FIXED;
- u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx);
- unsigned en_field = ctrl & 0x3;
- bool pmi = ctrl & 0x8;
-
- pmc_pause_counter(pmc);
-
- if (!en_field || !pmc_is_enabled(pmc))
- return;
-
- if (!check_pmu_event_filter(pmc))
- return;
-
- if (pmc->current_config == (u64)ctrl && pmc_resume_counter(pmc))
- return;
-
- pmc_release_perf_event(pmc);
-
- pmc->current_config = (u64)ctrl;
- pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE,
- kvm_x86_ops.pmu_ops->pmc_perf_hw_id(pmc),
- !(en_field & 0x2), /* exclude user */
- !(en_field & 0x1), /* exclude kernel */
- pmi, false, false);
-}
-
-void reprogram_counter(struct kvm_pmc *pmc)
-{
- if (pmc_is_gp(pmc))
- reprogram_gp_counter(pmc);
- else
- reprogram_fixed_counter(pmc);
+ pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
+ (eventsel & AMD64_RAW_EVENT_MASK),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+ eventsel & ARCH_PERFMON_EVENTSEL_INT,
+ (eventsel & HSW_IN_TX),
+ (eventsel & HSW_IN_TX_CHECKPOINTED));
}
EXPORT_SYMBOL_GPL(reprogram_counter);
@@ -449,17 +422,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
kvm_pmu_refresh(vcpu);
}
-static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc)
-{
- struct kvm_pmu *pmu = pmc_to_pmu(pmc);
-
- if (pmc_is_fixed(pmc))
- return fixed_ctrl_field(pmu->fixed_ctr_ctrl,
- pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3;
-
- return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE;
-}
-
/* Release perf_events for vPMCs that have been unused for a full time slice. */
void kvm_pmu_cleanup(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a69d2aeb7526..98a01f6a9d5d 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -492,7 +492,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
pmu->reserved_bits = 0xffffffff00200000ull;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
- if (!entry || !enable_pmu)
+ if (!entry || !enable_pmu || !boot_cpu_has(X86_FEATURE_ARCH_PERFMON))
return;
eax.full = entry->eax;
edx.full = entry->edx;
--
2.35.0
next prev parent reply other threads:[~2022-02-21 11:53 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-21 11:51 [PATCH 00/11] KVM: x86/pmu: Get rid of PERF_TYPE_HARDWAR and other minor fixes Like Xu
2022-02-21 11:51 ` [PATCH 01/11] KVM: x86/pmu: Update comments for AMD gp counters Like Xu
2022-02-23 19:50 ` Jim Mattson
2022-02-21 11:51 ` [PATCH 02/11] KVM: x86/pmu: Extract check_pmu_event_filter() from the same semantics Like Xu
2022-02-21 11:51 ` [PATCH 03/11] KVM: x86/pmu: Pass only "struct kvm_pmc *pmc" to reprogram_counter() Like Xu
2022-02-21 11:51 ` [PATCH 04/11] KVM: x86/pmu: Drop "u64 eventsel" for reprogram_gp_counter() Like Xu
2022-02-21 11:51 ` [PATCH 05/11] KVM: x86/pmu: Drop "u8 ctrl, int idx" for reprogram_fixed_counter() Like Xu
2022-02-21 11:51 ` [PATCH 06/11] KVM: x86/pmu: Use only the uniformly exported interface reprogram_counter() Like Xu
2022-02-21 11:51 ` Like Xu [this message]
2022-02-21 11:51 ` [PATCH 08/11] perf: x86/core: Add interface to query perfmon_event_map[] directly Like Xu
2022-02-21 11:51 ` [PATCH 09/11] KVM: x86/pmu: Replace pmc_perf_hw_id() with perf_get_hw_event_config() Like Xu
2022-02-21 20:57 ` kernel test robot
2022-02-21 11:52 ` [PATCH 10/11] KVM: x86/pmu: Drop amd_event_mapping[] in the KVM context Like Xu
2022-02-21 11:52 ` [PATCH 11/11] KVM: x86/pmu: Protect kvm->arch.pmu_event_filter with SRCU 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=20220221115201.22208-8-likexu@tencent.com \
--to=like.xu.linux@gmail.com \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=likexu@tencent.com \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.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).