Lines Matching defs:instruction

507  * Handle a fault on a hardware virtualization (VMX or SVM) instruction.
511 * fault we just panic; during reboot instead the instruction is ignored.
725 that instruction re-execution will regenerate lost
2112 /* Treat an INVD instruction as a NOP and just skip it. */
2131 pr_warn_once("%s instruction emulated as NOP!\n", insn);
4872 * an instruction boundary and will not trigger guest emulation of any
4977 * instruction boundary and with no events half-injected.
5188 * The API doesn't provide the instruction length for software
7376 /* used for instruction fetching */
8379 * instruction. So, if the last instruction, be it emulated or
8381 * means that the last instruction is an sti. We should not
8600 * Do not retry the unhandleable instruction if it faults on the
8602 * retry instruction -> write #PF -> emulation fail -> retry
8603 * instruction -> ...
8608 * If the instruction failed on the error pfn, it can not be fixed,
8633 * guest to let CPU execute the instruction.
8656 * writing instruction, it means the VM-EXIT is caused by shadow
8658 * instruction directly.
8660 * Note: if the guest uses a non-page-table modifying instruction
8661 * on the PDE that points to the instruction, then we will unmap
8662 * the instruction and go to an infinite loop. So, we cache the
8742 * processor will not generate this exception after the instruction
8776 * the instruction has passed all exception checks, and all intercepted
8783 * the instruction being emulated. The intent of forced emulation is
8784 * to behave as if KVM intercepted the instruction without an exception
8858 * Decode an instruction for emulation. The caller is responsible for handling
9931 char instruction[3];
9945 static_call(kvm_x86_patch_hypercall)(vcpu, instruction);
9947 return emulator_write_emulated(ctxt, rip, instruction, 3,
10038 * Note, this is not guaranteed to be invoked on a guest instruction boundary,
10040 * be able to inject exceptions in the "middle" of an instruction, and so must
10041 * also be able to re-inject NMIs and IRQs in the middle of an instruction.
10042 * I.e. for exceptions and re-injected events, NOT invoking this on instruction
10047 * instruction boundaries for asynchronous events. However, because VM-Exits
10048 * that can occur during instruction execution typically result in KVM skipping
10049 * the instruction or injecting an exception, e.g. instruction and exception
10051 * interrupts, KVM still honors instruction boundaries in most scenarios.
10053 * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip
10054 * the instruction or inject an exception, then KVM can incorrecty inject a new
10056 * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation)
10058 * injected on the restarted instruction instead of being deferred until the
10059 * instruction completes.
10064 * phase of instruction execution, e.g. on the instruction fetch from memory.
10066 * ordering between that side effect, the instruction completing, _and_ the
10102 * priority, they're only generated (pended) during instruction
10103 * execution, and interrupts are recognized at instruction boundaries.
10105 * *previous* instruction and must be serviced prior to recognizing any
10106 * new events in order to fully complete the previous instruction.
10841 * An instruction is required after local_irq_enable() to fully unblock
10976 * of instruction emulation, the rest of the emulation could
10978 * this point can start executing an instruction.
11227 * instruction emulation. Registers state needs to be copied
13144 * another process. When the instruction that triggered a page
13372 * while handling a VMX instruction KVM could've handled the request