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

Pull KVM fixes from Paolo Bonzini:
 "Three x86 fixes and one for ARM/ARM64.

  In particular, nested virtualization on Intel is broken in 3.13 and
  fixed by this pull request"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm, vmx: Really fix lazy FPU on nested guest
  kvm: x86: fix emulator buffer overflow (CVE-2014-0049)
  arm/arm64: KVM: detect CPU reset on CPU_PM_EXIT
  KVM: MMU: drop read-only large sptes when creating lower level sptes

6 files changed, 40 insertions, 6 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248ea5669..bd18bb8b2770 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
                                     unsigned long cmd,
                                     void *v)
 {
-        if (cmd == CPU_PM_EXIT) {
+        if (cmd == CPU_PM_EXIT &&
+            __hyp_get_vectors() == hyp_default_vectors) {
                 cpu_init_hyp_mode(NULL);
                 return NOTIFY_OK;
         }
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc15539bad2..0d68d4073068 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@ hyp_hvc:
 host_switch_to_hyp:
         pop     {r0, r1, r2}
 
+        /* Check for __hyp_get_vectors */
+        cmp     r0, #-1
+        mrceq   p15, 4, r0, c12, c0, 0  @ get HVBAR
+        beq     1f
+
         push    {lr}
         mrs     lr, SPSR
         push    {lr}
@@ -378,7 +387,7 @@ THUMB(	orr	lr, #1)
         pop     {lr}
         msr     SPSR_csxf, lr
         pop     {lr}
-        eret
+1:      eret
 
 guest_trap:
         load_vcpu                       @ Load VCPU pointer to r0
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36e10ff..2c56012cb2d2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@ __hyp_panic_str:
 
         .align  2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
         hvc     #0
         ret
@@ -737,7 +755,12 @@ el1_sync:					// Guest trapped into EL2
         pop     x2, x3
         pop     x0, x1
 
-        push    lr, xzr
+        /* Check for __hyp_get_vectors */
+        cbnz    x0, 1f
+        mrs     x0, vbar_el2
+        b       2f
+
+1:      push    lr, xzr
 
         /*
          * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@ el1_sync:					// Guest trapped into EL2
         blr     lr
 
         pop     lr, xzr
-        eret
+2:      eret
 
 el1_trap:
         /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d0f5f7..9b531351a587 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
                         break;
                 }
 
+                drop_large_spte(vcpu, iterator.sptep);
                 if (!is_shadow_present_pte(*iterator.sptep)) {
                         u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101ef64b..392752834751 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
                 else if (is_page_fault(intr_info))
                         return enable_ept;
                 else if (is_no_device(intr_info) &&
-                         !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+                         !(vmcs12->guest_cr0 & X86_CR0_TS))
                         return 0;
                 return vmcs12->exception_bitmap &
                                 (1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09dfd5..2b8578432d5b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
                 frag->len -= len;
         }
 
-        if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+        if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
                 vcpu->mmio_needed = 0;
 
                 /* FIXME: return into emulator if single-stepping.  */