linux/arch/x86/kvm
Sean Christopherson 0e3223d8d0 KVM: x86/mmu: Use dummy root, backed by zero page, for !visible guest roots
When attempting to allocate a shadow root for a !visible guest root gfn,
e.g. that resides in MMIO space, load a dummy root that is backed by the
zero page instead of immediately synthesizing a triple fault shutdown
(using the zero page ensures any attempt to translate memory will generate
a !PRESENT fault and thus VM-Exit).

Unless the vCPU is racing with memslot activity, KVM will inject a page
fault due to not finding a visible slot in FNAME(walk_addr_generic), i.e.
the end result is mostly same, but critically KVM will inject a fault only
*after* KVM runs the vCPU with the bogus root.

Waiting to inject a fault until after running the vCPU fixes a bug where
KVM would bail from nested VM-Enter if L1 tried to run L2 with TDP enabled
and a !visible root.  Even though a bad root will *probably* lead to
shutdown, (a) it's not guaranteed and (b) the CPU won't read the
underlying memory until after VM-Enter succeeds.  E.g. if L1 runs L2 with
a VMX preemption timer value of '0', then architecturally the preemption
timer VM-Exit is guaranteed to occur before the CPU executes any
instruction, i.e. before the CPU needs to translate a GPA to a HPA (so
long as there are no injected events with higher priority than the
preemption timer).

If KVM manages to get to FNAME(fetch) with a dummy root, e.g. because
userspace created a memslot between installing the dummy root and handling
the page fault, simply unload the MMU to allocate a new root and retry the
instruction.  Use KVM_REQ_MMU_FREE_OBSOLETE_ROOTS to drop the root, as
invoking kvm_mmu_free_roots() while holding mmu_lock would deadlock, and
conceptually the dummy root has indeeed become obsolete.  The only
difference versus existing usage of KVM_REQ_MMU_FREE_OBSOLETE_ROOTS is
that the root has become obsolete due to memslot *creation*, not memslot
deletion or movement.

Reported-by: Reima Ishii <ishiir@g.ecc.u-tokyo.ac.jp>
Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Link: https://lore.kernel.org/r/20230729005200.1057358-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2023-08-31 14:08:24 -04:00
..
mmu KVM: x86/mmu: Use dummy root, backed by zero page, for !visible guest roots 2023-08-31 14:08:24 -04:00
svm KVM x86 changes for 6.6: 2023-08-31 13:36:33 -04:00
vmx KVM x86 changes for 6.6: 2023-08-31 13:36:33 -04:00
.gitignore KVM: x86: use a separate asm-offsets.c file 2022-11-09 12:10:17 -05:00
cpuid.c KVM x86 changes for 6.6: 2023-08-31 13:36:33 -04:00
cpuid.h KVM: x86: Add a framework for enabling KVM-governed x86 features 2023-08-17 11:38:27 -07:00
debugfs.c KVM: x86: Unify pr_fmt to use module name for all KVM modules 2022-12-29 15:47:35 -05:00
emulate.c KVM: x86: Remove break statements that will never be executed 2023-08-17 11:28:00 -07:00
fpu.h
governed_features.h KVM: nSVM: Use KVM-governed feature framework to track "vNMI enabled" 2023-08-17 11:43:31 -07:00
hyperv.c KVM: x86: Remove break statements that will never be executed 2023-08-17 11:28:00 -07:00
hyperv.h KVM: x86: Hyper-V invariant TSC control 2022-12-29 15:33:29 -05:00
i8254.c KVM: x86: Unify pr_fmt to use module name for all KVM modules 2022-12-29 15:47:35 -05:00
i8254.h KVM: x86: PIT: Preserve state of speaker port data bit 2022-06-08 13:06:20 -04:00
i8259.c KVM: x86: Fix poll command 2023-06-01 13:44:13 -07:00
ioapic.c KVM: x86/ioapic: Resample the pending state of an IRQ when unmasking 2023-03-27 10:13:28 -04:00
ioapic.h x86/kvm: remove unused ack_notifier callbacks 2021-11-18 07:05:57 -05:00
irq_comm.c KVM: x86: Unify pr_fmt to use module name for all KVM modules 2022-12-29 15:47:35 -05:00
irq.c KVM: x86: Unify pr_fmt to use module name for all KVM modules 2022-12-29 15:47:35 -05:00
irq.h x86/kvm: remove unused ack_notifier callbacks 2021-11-18 07:05:57 -05:00
Kconfig KVM: x86/mmu: Replace MMU_DEBUG with proper KVM_PROVE_MMU Kconfig 2023-08-31 13:48:47 -04:00
kvm_cache_regs.h KVM: x86: Add helpers to query individual CR0/CR4 bits 2023-03-22 10:10:53 -07:00
kvm_emulate.h KVM: x86: Remove x86_emulate_ops::guest_has_long_mode 2023-08-02 15:47:27 -07:00
kvm_onhyperv.c KVM: x86/mmu: Move filling of Hyper-V's TLB range struct into Hyper-V code 2023-04-10 15:17:29 -07:00
kvm_onhyperv.h s390: 2023-05-01 12:06:20 -07:00
kvm-asm-offsets.c KVM: SVM: move MSR_IA32_SPEC_CTRL save/restore to assembly 2022-11-09 12:25:53 -05:00
lapic.c KVM x86 changes for 6.6: 2023-08-31 13:36:33 -04:00
lapic.h KVM: x86: Split out logic to generate "readable" APIC regs mask to helper 2023-01-24 10:04:35 -08:00
Makefile KVM: x86: Introduce .hv_inject_synthetic_vmexit_post_tlb_flush() nested hook 2022-11-18 12:59:13 -05:00
mmu.h KVM: x86/mmu: Don't bounce through page-track mechanism for guest PTEs 2023-08-31 13:49:00 -04:00
mtrr.c KVM: x86: Make kvm_mtrr_valid() static now that there are no external users 2023-06-01 13:41:06 -07:00
pmu.c KVM: x86/pmu: Move .hw_event_available() check out of PMC filter helper 2023-08-02 16:44:36 -07:00
pmu.h KVM: x86/pmu: Disable vPMU if the minimum num of counters isn't met 2023-06-06 17:31:44 -07:00
reverse_cpuid.h KVM: x86: Advertise AMX-COMPLEX CPUID to userspace 2023-08-03 15:40:17 -07:00
smm.c KVM: x86: Use emulator callbacks instead of duplicating "host flags" 2023-01-31 17:29:09 -08:00
smm.h KVM: x86: smm: preserve interrupt shadow in SMRAM 2022-11-09 12:31:26 -05:00
trace.h KVM: x86/xen: Add CPL to Xen hypercall tracepoint 2022-11-28 13:31:01 -05:00
tss.h
x86.c KVM: x86/mmu: Move KVM-only page-track declarations to internal header 2023-08-31 14:08:13 -04:00
x86.h KVM: x86: Snapshot host's MSR_IA32_ARCH_CAPABILITIES 2023-08-02 16:37:26 -07:00
xen.c KVM: x86/xen: update Xen CPUID Leaf 4 (tsc info) sub-leaves, if present 2023-01-24 10:05:20 -08:00
xen.h KVM: x86/xen: update Xen CPUID Leaf 4 (tsc info) sub-leaves, if present 2023-01-24 10:05:20 -08:00