[PATCH 3.16 024/233] KVM: x86: Fix load damaged SSEx MXCSR register

[Ben Hutchings]

3.16.48-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>

commit a575813bfe4bc15aba511a5e91e61d242bff8b9d upstream.

Reported by syzkaller:

   BUG: unable to handle kernel paging request at ffffffffc07f6a2e
   IP: report_bug+0x94/0x120
   PGD 348e12067
   P4D 348e12067
   PUD 348e14067
   PMD 3cbd84067
   PTE 80000003f7e87161

   Oops: 0003 [#1] SMP
   CPU: 2 PID: 7091 Comm: kvm_load_guest_ Tainted: G           OE   4.11.0+ #8
   task: ffff92fdfb525400 task.stack: ffffbda6c3d04000
   RIP: 0010:report_bug+0x94/0x120
   RSP: 0018:ffffbda6c3d07b20 EFLAGS: 00010202
    do_trap+0x156/0x170
    do_error_trap+0xa3/0x170
    ? kvm_load_guest_fpu.part.175+0x12a/0x170 [kvm]
    ? mark_held_locks+0x79/0xa0
    ? retint_kernel+0x10/0x10
    ? trace_hardirqs_off_thunk+0x1a/0x1c
    do_invalid_op+0x20/0x30
    invalid_op+0x1e/0x30
   RIP: 0010:kvm_load_guest_fpu.part.175+0x12a/0x170 [kvm]
    ? kvm_load_guest_fpu.part.175+0x1c/0x170 [kvm]
    kvm_arch_vcpu_ioctl_run+0xed6/0x1b70 [kvm]
    kvm_vcpu_ioctl+0x384/0x780 [kvm]
    ? kvm_vcpu_ioctl+0x384/0x780 [kvm]
    ? sched_clock+0x13/0x20
    ? __do_page_fault+0x2a0/0x550
    do_vfs_ioctl+0xa4/0x700
    ? up_read+0x1f/0x40
    ? __do_page_fault+0x2a0/0x550
    SyS_ioctl+0x79/0x90
    entry_SYSCALL_64_fastpath+0x23/0xc2

SDM mentioned that "The MXCSR has several reserved bits, and attempting to write
a 1 to any of these bits will cause a general-protection exception(#GP) to be
generated". The syzkaller forks' testcase overrides xsave area w/ random values
and steps on the reserved bits of MXCSR register. The damaged MXCSR register
values of guest will be restored to SSEx MXCSR register before vmentry. This
patch fixes it by catching userspace override MXCSR register reserved bits w/
random values and bails out immediately.

Reported-by: Andrey Konovalov <andreyknvl@xxxxxxxxxx>
Reviewed-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
Signed-off-by: Radim KrÄmÃÅ <rkrcmar@xxxxxxxxxx>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/i387.c | 1 +
 arch/x86/kvm/x86.c     | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -115,6 +115,7 @@ void unlazy_fpu(struct task_struct *tsk)
 EXPORT_SYMBOL(unlazy_fpu);
 
 unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 static struct i387_fxsave_struct fx_scratch;
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3110,11 +3110,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave
 	}
 }
 
+#define XSAVE_MXCSR_OFFSET 24
+
 static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 					struct kvm_xsave *guest_xsave)
 {
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+	u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
 
 	if (cpu_has_xsave) {
 		/*
@@ -3122,12 +3125,14 @@ static int kvm_vcpu_ioctl_x86_set_xsave(
 		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
 		 * with old userspace.
 		 */
-		if (xstate_bv & ~kvm_supported_xcr0())
+		if (xstate_bv & ~kvm_supported_xcr0() ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
 			guest_xsave->region, vcpu->arch.guest_xstate_size);
 	} else {
-		if (xstate_bv & ~XSTATE_FPSSE)
+		if (xstate_bv & ~XSTATE_FPSSE ||
+			mxcsr & ~mxcsr_feature_mask)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
 			guest_xsave->region, sizeof(struct i387_fxsave_struct));