summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-09-17 22:20:30 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2013-09-17 22:20:30 -0400
commit62d228b8c676232eca579f91cc0782b060a59097 (patch)
tree18acffcd94343a510dee6a8c14d7db2449359d86 /arch
parent84fca9f38c5d646e95cdeef70e41cf15db549b95 (diff)
parent0be9c7a89f75072e091cd079d76194aec8d1fb09 (diff)
downloadlinux-62d228b8c676232eca579f91cc0782b060a59097.tar.bz2
Merge branch 'fixes' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM fixes from Gleb Natapov. * 'fixes' of git://git.kernel.org/pub/scm/virt/kvm/kvm: KVM: VMX: set "blocked by NMI" flag if EPT violation happens during IRET from NMI kvm: free resources after canceling async_pf KVM: nEPT: reset PDPTR register cache on nested vmentry emulation KVM: mmu: allow page tables to be in read-only slots KVM: x86 emulator: emulate RETF imm
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kvm/emulate.c14
-rw-r--r--arch/x86/kvm/paging_tmpl.h20
-rw-r--r--arch/x86/kvm/vmx.c13
3 files changed, 45 insertions, 2 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2bc1e81045b0..ddc3f3d2afdb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2025,6 +2025,17 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
return rc;
}
+static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
+{
+ int rc;
+
+ rc = em_ret_far(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rsp_increment(ctxt, ctxt->src.val);
+ return X86EMUL_CONTINUE;
+}
+
static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
{
/* Save real source value, then compare EAX against destination. */
@@ -3763,7 +3774,8 @@ static const struct opcode opcode_table[256] = {
G(ByteOp, group11), G(0, group11),
/* 0xC8 - 0xCF */
I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave),
- N, I(ImplicitOps | Stack, em_ret_far),
+ I(ImplicitOps | Stack | SrcImmU16, em_ret_far_imm),
+ I(ImplicitOps | Stack, em_ret_far),
D(ImplicitOps), DI(SrcImmByte, intn),
D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
/* 0xD0 - 0xD7 */
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 043330159179..ad75d77999d0 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -99,6 +99,7 @@ struct guest_walker {
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -235,6 +236,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -309,7 +326,8 @@ retry_walk:
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1f1da43ff2a2..a1216de9ffda 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5339,6 +5339,15 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
return 0;
}
+ /*
+ * EPT violation happened while executing iret from NMI,
+ * "blocked by NMI" bit has to be set before next VM entry.
+ * There are errata that may cause this bit to not be set:
+ * AAK134, BY25.
+ */
+ if (exit_qualification & INTR_INFO_UNBLOCK_NMI)
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
+
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
@@ -7766,6 +7775,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ __clear_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_avail);
+ __clear_bit(VCPU_EXREG_PDPTR,
+ (unsigned long *)&vcpu->arch.regs_dirty);
}
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);