From: Omar Sandoval osandov@fb.com
[ Upstream commit 4da3768e1820cf15cced390242d8789aed34f54d ]
When re-injecting a soft interrupt from an INT3, INT0, or (select) INTn instruction, discard the exception and retry the instruction if the code stream is changed (e.g. by a different vCPU) between when the CPU executes the instruction and when KVM decodes the instruction to get the next RIP.
As effectively predicted by commit 6ef88d6e36c2 ("KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction"), failure to verify that the correct INTn instruction was decoded can effectively clobber guest state due to decoding the wrong instruction and thus specifying the wrong next RIP.
The bug most often manifests as "Oops: int3" panics on static branch checks in Linux guests. Enabling or disabling a static branch in Linux uses the kernel's "text poke" code patching mechanism. To modify code while other CPUs may be executing that code, Linux (temporarily) replaces the first byte of the original instruction with an int3 (opcode 0xcc), then patches in the new code stream except for the first byte, and finally replaces the int3 with the first byte of the new code stream. If a CPU hits the int3, i.e. executes the code while it's being modified, then the guest kernel must look up the RIP to determine how to handle the #BP, e.g. by emulating the new instruction. If the RIP is incorrect, then this lookup fails and the guest kernel panics.
The bug reproduces almost instantly by hacking the guest kernel to repeatedly check a static branch[1] while running a drgn script[2] on the host to constantly swap out the memory containing the guest's TSS.
[1]: https://gist.github.com/osandov/44d17c51c28c0ac998ea0334edf90b5a [2]: https://gist.github.com/osandov/10e45e45afa29b11e0c7209247afc00b
Fixes: 6ef88d6e36c2 ("KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction") Cc: stable@vger.kernel.org Co-developed-by: Sean Christopherson seanjc@google.com Signed-off-by: Omar Sandoval osandov@fb.com Link: https://patch.msgid.link/1cc6dcdf36e3add7ee7c8d90ad58414eeb6c3d34.1762278762... Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kvm_host.h | 9 +++++++++ arch/x86/kvm/svm/svm.c | 24 +++++++++++++----------- arch/x86/kvm/x86.c | 21 +++++++++++++++++++++ 3 files changed, 43 insertions(+), 11 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd7b4c5f5436c..fe5c0f86ae389 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1827,6 +1827,11 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); * the gfn, i.e. retrying the instruction will hit a * !PRESENT fault, which results in a new shadow page * and sends KVM back to square one. + * + * EMULTYPE_SKIP_SOFT_INT - Set in combination with EMULTYPE_SKIP to only skip + * an instruction if it could generate a given software + * interrupt, which must be encoded via + * EMULTYPE_SET_SOFT_INT_VECTOR(). */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -1837,6 +1842,10 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); #define EMULTYPE_PF (1 << 6) #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) +#define EMULTYPE_SKIP_SOFT_INT (1 << 9) + +#define EMULTYPE_SET_SOFT_INT_VECTOR(v) ((u32)((v) & 0xff) << 16) +#define EMULTYPE_GET_SOFT_INT_VECTOR(e) (((e) >> 16) & 0xff)
int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 00fb1c18e23a8..a2706b49ffa3d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -370,6 +370,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len);
static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, + int emul_type, bool commit_side_effects) { struct vcpu_svm *svm = to_svm(vcpu); @@ -399,7 +400,7 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags;
- if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + if (!kvm_emulate_instruction(vcpu, emul_type)) return 0;
if (unlikely(!commit_side_effects)) @@ -417,11 +418,13 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - return __svm_skip_emulated_instruction(vcpu, true); + return __svm_skip_emulated_instruction(vcpu, EMULTYPE_SKIP, true); }
-static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) +static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu, u8 vector) { + const int emul_type = EMULTYPE_SKIP | EMULTYPE_SKIP_SOFT_INT | + EMULTYPE_SET_SOFT_INT_VECTOR(vector); unsigned long rip, old_rip = kvm_rip_read(vcpu); struct vcpu_svm *svm = to_svm(vcpu);
@@ -437,7 +440,7 @@ static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) * in use, the skip must not commit any side effects such as clearing * the interrupt shadow or RFLAGS.RF. */ - if (!__svm_skip_emulated_instruction(vcpu, !nrips)) + if (!__svm_skip_emulated_instruction(vcpu, emul_type, !nrips)) return -EIO;
rip = kvm_rip_read(vcpu); @@ -473,7 +476,7 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu, ex);
if (kvm_exception_is_soft(ex->vector) && - svm_update_soft_interrupt_rip(vcpu)) + svm_update_soft_interrupt_rip(vcpu, ex->vector)) return;
svm->vmcb->control.event_inj = ex->vector @@ -3523,11 +3526,12 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu)
static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { + struct kvm_queued_interrupt *intr = &vcpu->arch.interrupt; struct vcpu_svm *svm = to_svm(vcpu); u32 type;
- if (vcpu->arch.interrupt.soft) { - if (svm_update_soft_interrupt_rip(vcpu)) + if (intr->soft) { + if (svm_update_soft_interrupt_rip(vcpu, intr->nr)) return;
type = SVM_EVTINJ_TYPE_SOFT; @@ -3535,12 +3539,10 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) type = SVM_EVTINJ_TYPE_INTR; }
- trace_kvm_inj_virq(vcpu->arch.interrupt.nr, - vcpu->arch.interrupt.soft, reinjected); + trace_kvm_inj_virq(intr->nr, intr->soft, reinjected); ++vcpu->stat.irq_injections;
- svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | - SVM_EVTINJ_VALID | type; + svm->vmcb->control.event_inj = intr->nr | SVM_EVTINJ_VALID | type; }
void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 562ca89ceb638..355c3e52f68cb 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8835,6 +8835,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; }
+static bool is_soft_int_instruction(struct x86_emulate_ctxt *ctxt, + int emulation_type) +{ + u8 vector = EMULTYPE_GET_SOFT_INT_VECTOR(emulation_type); + + switch (ctxt->b) { + case 0xcc: + return vector == BP_VECTOR; + case 0xcd: + return vector == ctxt->src.val; + case 0xce: + return vector == OF_VECTOR; + default: + return false; + } +} + /* * Decode an instruction for emulation. The caller is responsible for handling * code breakpoints. Note, manually detecting code breakpoints is unnecessary @@ -8925,6 +8942,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * injecting single-step #DBs. */ if (emulation_type & EMULTYPE_SKIP) { + if (emulation_type & EMULTYPE_SKIP_SOFT_INT && + !is_soft_int_instruction(ctxt, emulation_type)) + return 0; + if (ctxt->mode != X86EMUL_MODE_PROT64) ctxt->eip = (u32)ctxt->_eip; else