Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm into next

[uclinux-h8/linux.git] / arch / x86 / kvm / x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 20316c6..f32a025 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -704,25 +704,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
        }
 
        if (is_long_mode(vcpu)) {
-               if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) {
-                       if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS)
-                               return 1;
-               } else
-                       if (cr3 & CR3_L_MODE_RESERVED_BITS)
-                               return 1;
-       } else {
-               if (is_pae(vcpu)) {
-                       if (cr3 & CR3_PAE_RESERVED_BITS)
-                               return 1;
-                       if (is_paging(vcpu) &&
-                           !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
-                               return 1;
-               }
-               /*
-                * We don't check reserved bits in nonpae mode, because
-                * this isn't enforced, and VMware depends on this.
-                */
-       }
+               if (cr3 & CR3_L_MODE_RESERVED_BITS)
+                       return 1;
+       } else if (is_pae(vcpu) && is_paging(vcpu) &&
+                  !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
+               return 1;
 
        vcpu->arch.cr3 = cr3;
        __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
@@ -1935,6 +1921,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 
                if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
                        vcpu->arch.hv_vapic = data;
+                       if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+                               return 1;
                        break;
                }
                gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
@@ -1945,6 +1933,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
                        return 1;
                vcpu->arch.hv_vapic = data;
                mark_page_dirty(vcpu->kvm, gfn);
+               if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+                       return 1;
                break;
        }
        case HV_X64_MSR_EOI:
@@ -2647,6 +2637,7 @@ int kvm_dev_ioctl_check_extension(long ext)
        case KVM_CAP_IRQ_INJECT_STATUS:
        case KVM_CAP_IRQFD:
        case KVM_CAP_IOEVENTFD:
+       case KVM_CAP_IOEVENTFD_NO_LENGTH:
        case KVM_CAP_PIT2:
        case KVM_CAP_PIT_STATE2:
        case KVM_CAP_SET_IDENTITY_MAP_ADDR:
@@ -3649,11 +3640,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
                offset = i * BITS_PER_LONG;
                kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
        }
-       if (is_dirty)
-               kvm_flush_remote_tlbs(kvm);
 
        spin_unlock(&kvm->mmu_lock);
 
+       /* See the comments in kvm_mmu_slot_remove_write_access(). */
+       lockdep_assert_held(&kvm->slots_lock);
+
+       /*
+        * All the TLBs can be flushed out of mmu lock, see the comments in
+        * kvm_mmu_slot_remove_write_access().
+        */
+       if (is_dirty)
+               kvm_flush_remote_tlbs(kvm);
+
        r = -EFAULT;
        if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
                goto out;
@@ -4489,8 +4488,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
                               unsigned short port, void *val,
                               unsigned int count, bool in)
 {
-       trace_kvm_pio(!in, port, size, count);
-
        vcpu->arch.pio.port = port;
        vcpu->arch.pio.in = in;
        vcpu->arch.pio.count  = count;
@@ -4525,6 +4522,7 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
        if (ret) {
 data_avail:
                memcpy(val, vcpu->arch.pio_data, size * count);
+               trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
                vcpu->arch.pio.count = 0;
                return 1;
        }
@@ -4539,6 +4537,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
        struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 
        memcpy(vcpu->arch.pio_data, val, size * count);
+       trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
        return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
 }
 
@@ -4650,11 +4649,6 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
        return res;
 }
 
-static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
-{
-       kvm_set_rflags(emul_to_vcpu(ctxt), val);
-}
-
 static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
 {
        return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt));
@@ -4839,7 +4833,6 @@ static const struct x86_emulate_ops emulate_ops = {
        .set_idt             = emulator_set_idt,
        .get_cr              = emulator_get_cr,
        .set_cr              = emulator_set_cr,
-       .set_rflags          = emulator_set_rflags,
        .cpl                 = emulator_get_cpl,
        .get_dr              = emulator_get_dr,
        .set_dr              = emulator_set_dr,
@@ -4905,7 +4898,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
        ctxt->eip = kvm_rip_read(vcpu);
        ctxt->mode = (!is_protmode(vcpu))               ? X86EMUL_MODE_REAL :
                     (ctxt->eflags & X86_EFLAGS_VM)     ? X86EMUL_MODE_VM86 :
-                    cs_l                               ? X86EMUL_MODE_PROT64 :
+                    (cs_l && is_long_mode(vcpu))       ? X86EMUL_MODE_PROT64 :
                     cs_db                              ? X86EMUL_MODE_PROT32 :
                                                          X86EMUL_MODE_PROT16;
        ctxt->guest_mode = is_guest_mode(vcpu);
@@ -7333,8 +7326,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
                kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
        /*
         * Write protect all pages for dirty logging.
-        * Existing largepage mappings are destroyed here and new ones will
-        * not be created until the end of the logging.
+        *
+        * All the sptes including the large sptes which point to this
+        * slot are set to readonly. We can not create any new large
+        * spte on this slot until the end of the logging.
+        *
+        * See the comments in fast_page_fault().
         */
        if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
                kvm_mmu_slot_remove_write_access(kvm, mem->slot);