Move the checks related to the validity of an access to a memslot from the
inner __kvm_faultin_pfn() to its sole caller, kvm_faultin_pfn(). This
allows emulating accesses to the APIC access page, which don't need to
resolve a pfn, even if there is a relevant in-progress mmu_notifier
invalidation. Ditto for accesses to KVM internal memslots from L2, which
KVM also treats as emulated MMIO.
More importantly, this will allow for future cleanup by having the
"no memslot" case bail from kvm_faultin_pfn() very early on.
Go to rather extreme and gross lengths to make the change a glorified
nop, e.g. call into __kvm_faultin_pfn() even when there is no slot, as the
related code is very subtle. E.g. fault->slot can be nullified if it
points at the APIC access page, some flows in KVM x86 expect fault->pfn
to be KVM_PFN_NOSLOT, while others check only fault->slot, etc.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/mmu/mmu.c | 105 +++++++++++++++++++++--------------------
1 file changed, 53 insertions(+), 52 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ebdb3fcce3dc..8aa957f0a717 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4340,9 +4340,59 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
- struct kvm_memory_slot *slot = fault->slot;
bool async;
+ if (fault->is_private)
+ return kvm_faultin_pfn_private(vcpu, fault);
+
+ async = false;
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, false,
+ &async, fault->write,
+ &fault->map_writable, &fault->hva);
+ if (!async)
+ return RET_PF_CONTINUE; /* *pfn has correct page already */
+
+ if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
+ trace_kvm_try_async_get_page(fault->addr, fault->gfn);
+ if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) {
+ trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
+ kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+ return RET_PF_RETRY;
+ } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
+ return RET_PF_RETRY;
+ }
+ }
+
+ /*
+ * Allow gup to bail on pending non-fatal signals when it's also allowed
+ * to wait for IO. Note, gup always bails if it is unable to quickly
+ * get a page and a fatal signal, i.e. SIGKILL, is pending.
+ */
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
+ NULL, fault->write,
+ &fault->map_writable, &fault->hva);
+ return RET_PF_CONTINUE;
+}
+
+static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+ unsigned int access)
+{
+ struct kvm_memory_slot *slot = fault->slot;
+ int ret;
+
+ fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+ smp_rmb();
+
+ /*
+ * Check for a private vs. shared mismatch *after* taking a snapshot of
+ * mmu_invalidate_seq, as changes to gfn attributes are guarded by the
+ * invalidation notifier.
+ */
+ if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
+ kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
+ return -EFAULT;
+ }
+
/*
* Retry the page fault if the gfn hit a memslot that is being deleted
* or moved. This ensures any existing SPTEs for the old memslot will
@@ -4367,7 +4417,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
fault->slot = NULL;
fault->pfn = KVM_PFN_NOSLOT;
fault->map_writable = false;
- return RET_PF_CONTINUE;
+ goto faultin_done;
}
/*
* If the APIC access page exists but is disabled, go directly
@@ -4379,56 +4429,6 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
return RET_PF_EMULATE;
}
- if (fault->is_private)
- return kvm_faultin_pfn_private(vcpu, fault);
-
- async = false;
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
- fault->write, &fault->map_writable,
- &fault->hva);
- if (!async)
- return RET_PF_CONTINUE; /* *pfn has correct page already */
-
- if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
- trace_kvm_try_async_get_page(fault->addr, fault->gfn);
- if (kvm_find_async_pf_gfn(vcpu, fault->gfn)) {
- trace_kvm_async_pf_repeated_fault(fault->addr, fault->gfn);
- kvm_make_request(KVM_REQ_APF_HALT, vcpu);
- return RET_PF_RETRY;
- } else if (kvm_arch_setup_async_pf(vcpu, fault->addr, fault->gfn)) {
- return RET_PF_RETRY;
- }
- }
-
- /*
- * Allow gup to bail on pending non-fatal signals when it's also allowed
- * to wait for IO. Note, gup always bails if it is unable to quickly
- * get a page and a fatal signal, i.e. SIGKILL, is pending.
- */
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
- fault->write, &fault->map_writable,
- &fault->hva);
- return RET_PF_CONTINUE;
-}
-
-static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
- unsigned int access)
-{
- int ret;
-
- fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq;
- smp_rmb();
-
- /*
- * Check for a private vs. shared mismatch *after* taking a snapshot of
- * mmu_invalidate_seq, as changes to gfn attributes are guarded by the
- * invalidation notifier.
- */
- if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
- kvm_mmu_prepare_memory_fault_exit(vcpu, fault);
- return -EFAULT;
- }
-
/*
* Check for a relevant mmu_notifier invalidation event before getting
* the pfn from the primary MMU, and before acquiring mmu_lock.
@@ -4458,6 +4458,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
if (ret != RET_PF_CONTINUE)
return ret;
+faultin_done:
if (unlikely(is_error_pfn(fault->pfn)))
return kvm_handle_error_pfn(vcpu, fault);
--
2.44.0.278.ge034bb2e1d-goog