Home
last modified time | relevance | path

Searched refs:invlpg (Results 1 – 8 of 8) sorted by relevance

/Linux-v5.10/Documentation/x86/
Dtlb.rst14 2. Use the invlpg instruction to invalidate a single page at a
42 invlpg instruction (or instructions _near_ it) show up high in
57 You might see invlpg inside of flush_tlb_mm_range() show up in
61 Essentially, you are balancing the cycles you spend doing invlpg
/Linux-v5.10/Documentation/virt/kvm/
Dmmu.rst109 - invlpg/invlpga instruction execution
240 are synchronized when the guest executes invlpg or flushes its tlb by
274 and page invalidations (invlpg).
281 guest cr3. In this case, the guest is obliged to issue an invlpg instruction
284 We synchronize modified gptes when the guest invokes invlpg. This reduces
350 invlpg handling:
/Linux-v5.10/arch/x86/kvm/mmu/
Dmmu.c3800 context->invlpg = NULL; in nonpaging_init_context()
4382 context->invlpg = paging64_invlpg; in paging64_init_context_common()
4411 context->invlpg = paging32_invlpg; in paging32_init_context()
4493 context->invlpg = NULL; in init_kvm_tdp_mmu()
4665 context->invlpg = ept_invlpg; in kvm_init_shadow_ept_mmu()
4710 g_context->invlpg = NULL; in init_kvm_nested_mmu()
5116 if (!mmu->invlpg) in kvm_mmu_invalidate_gva()
5120 mmu->invlpg(vcpu, gva, mmu->root_hpa); in kvm_mmu_invalidate_gva()
5135 mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); in kvm_mmu_invalidate_gva()
5137 mmu->invlpg(vcpu, gva, root_hpa); in kvm_mmu_invalidate_gva()
[all …]
Dpaging_tmpl.h901 static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) in FNAME() argument
/Linux-v5.10/arch/x86/kvm/
Dkvm_emulate.h185 void (*invlpg)(struct x86_emulate_ctxt *ctxt, ulong addr); member
Demulate.c3811 ctxt->ops->invlpg(ctxt, linear); in em_invlpg()
4553 II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
Dx86.c208 VCPU_STAT("invlpg", invlpg),
6855 .invlpg = emulator_invlpg,
/Linux-v5.10/arch/x86/include/asm/
Dkvm_host.h360 void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); member
1034 u64 invlpg; member