| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sat, 23 Apr 2022 03:47:49 +0000
From: Sean Christopherson <seanjc@...gle.com>
To: Paolo Bonzini <pbonzini@...hat.com>
Cc: Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org, Ben Gardon <bgardon@...gle.com>,
David Matlack <dmatlack@...gle.com>,
Venkatesh Srinivas <venkateshs@...gle.com>,
Chao Peng <chao.p.peng@...ux.intel.com>
Subject: [PATCH 09/12] KVM: x86/mmu: Expand and clean up page fault stats
Expand and clean up the page fault stats. The current stats are at best
incomplete, and at worst misleading. Differentiate between faults that
are actually fixed vs those that result in an MMIO SPTE being created,
track faults that are spurious, faults that trigger emulation, faults
that that are fixed in the fast path, and last but not least, track the
number of faults that are taken.
Note, the number of faults that require emulation for write-protected
shadow pages can roughly be calculated by subtracting the number of MMIO
SPTEs created from the overall number of faults that trigger emulation.
Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
arch/x86/include/asm/kvm_host.h | 5 +++++
arch/x86/kvm/mmu/mmu.c | 7 +++++--
arch/x86/kvm/mmu/mmu_internal.h | 28 ++++++++++++++++++++++++++--
arch/x86/kvm/mmu/paging_tmpl.h | 1 -
arch/x86/kvm/mmu/tdp_mmu.c | 8 +-------
arch/x86/kvm/x86.c | 5 +++++
6 files changed, 42 insertions(+), 12 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f164c6c1514a..c5fb4115176d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1269,7 +1269,12 @@ struct kvm_vm_stat {
struct kvm_vcpu_stat {
struct kvm_vcpu_stat_generic generic;
+ u64 pf_taken;
u64 pf_fixed;
+ u64 pf_emulate;
+ u64 pf_spurious;
+ u64 pf_fast;
+ u64 pf_mmio_spte_created;
u64 pf_guest;
u64 tlb_flush;
u64 invlpg;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8b8b62d2a903..744c06bd7017 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2660,6 +2660,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
*sptep, write_fault, gfn);
if (unlikely(is_noslot_pfn(pfn))) {
+ vcpu->stat.pf_mmio_spte_created++;
mark_mmio_spte(vcpu, sptep, gfn, pte_access);
return RET_PF_EMULATE;
}
@@ -2943,7 +2944,6 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
return ret;
direct_pte_prefetch(vcpu, it.sptep);
- ++vcpu->stat.pf_fixed;
return ret;
}
@@ -3206,6 +3206,9 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
trace_fast_page_fault(vcpu, fault, sptep, spte, ret);
walk_shadow_page_lockless_end(vcpu);
+ if (ret != RET_PF_INVALID)
+ vcpu->stat.pf_fast++;
+
return ret;
}
@@ -5311,7 +5314,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
write_unlock(&vcpu->kvm->mmu_lock);
}
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
+int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
void *insn, int insn_len)
{
int r, emulation_type = EMULTYPE_PF;
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 9caa747ee033..bd2a26897b97 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -248,11 +248,35 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
.req_level = PG_LEVEL_4K,
.goal_level = PG_LEVEL_4K,
};
+ int r;
+
+ /*
+ * Async #PF "faults", a.k.a. prefetch faults, are not faults from the
+ * guest perspective and have already been counted at the time of the
+ * original fault.
+ */
+ if (!prefetch)
+ vcpu->stat.pf_taken++;
if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp)
- return kvm_tdp_page_fault(vcpu, &fault);
+ r = kvm_tdp_page_fault(vcpu, &fault);
+ else
+ r = vcpu->arch.mmu->page_fault(vcpu, &fault);
- return vcpu->arch.mmu->page_fault(vcpu, &fault);
+ /*
+ * Similar to above, prefetch faults aren't truly spurious, and the
+ * async #PF path doesn't do emulation. Do count faults that are fixed
+ * by the async #PF handler though, otherwise they'll never be counted.
+ */
+ if (r == RET_PF_FIXED)
+ vcpu->stat.pf_fixed++;
+ else if (prefetch)
+ ;
+ else if (r == RET_PF_EMULATE)
+ vcpu->stat.pf_emulate++;
+ else if (r == RET_PF_SPURIOUS)
+ vcpu->stat.pf_spurious++;
+ return r;
}
int kvm_mmu_max_mapping_level(struct kvm *kvm,
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 7f8f1c8dbed2..db80f7ccaa4e 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -723,7 +723,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
return ret;
FNAME(pte_prefetch)(vcpu, gw, it.sptep);
- ++vcpu->stat.pf_fixed;
return ret;
out_gpte_changed:
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index a2eda3e55697..8089beb312d1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1099,6 +1099,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
if (unlikely(is_mmio_spte(new_spte))) {
+ vcpu->stat.pf_mmio_spte_created++;
trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
new_spte);
ret = RET_PF_EMULATE;
@@ -1107,13 +1108,6 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
rcu_dereference(iter->sptep));
}
- /*
- * Increase pf_fixed in both RET_PF_EMULATE and RET_PF_FIXED to be
- * consistent with legacy MMU behavior.
- */
- if (ret != RET_PF_SPURIOUS)
- vcpu->stat.pf_fixed++;
-
return ret;
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7663c35a5c70..a6441b281fb3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -266,7 +266,12 @@ const struct kvm_stats_header kvm_vm_stats_header = {
const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
KVM_GENERIC_VCPU_STATS(),
+ STATS_DESC_COUNTER(VCPU, pf_taken),
STATS_DESC_COUNTER(VCPU, pf_fixed),
+ STATS_DESC_COUNTER(VCPU, pf_emulate),
+ STATS_DESC_COUNTER(VCPU, pf_spurious),
+ STATS_DESC_COUNTER(VCPU, pf_fast),
+ STATS_DESC_COUNTER(VCPU, pf_mmio_spte_created),
STATS_DESC_COUNTER(VCPU, pf_guest),
STATS_DESC_COUNTER(VCPU, tlb_flush),
STATS_DESC_COUNTER(VCPU, invlpg),
--
2.36.0.rc2.479.g8af0fa9b8e-goog
Powered by blists - more mailing lists