summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorQuentin Casasnovas <quentin.casasnovas@oracle.com>2016-06-18 11:01:05 +0200
committerPaolo Bonzini <pbonzini@redhat.com>2016-06-27 15:30:44 +0200
commitff30ef40deca4658e27b0c596e7baf39115e858f (patch)
tree8e3c6cfcdc039b450044584f99fa73e3de303a9c /arch
parentb606f189c7d5bf9b875bba168162fe05287880fe (diff)
KVM: nVMX: VMX instructions: fix segment checks when L1 is in long mode.
I couldn't get Xen to boot a L2 HVM when it was nested under KVM - it was getting a GP(0) on a rather unspecial vmread from Xen: (XEN) ----[ Xen-4.7.0-rc x86_64 debug=n Not tainted ]---- (XEN) CPU: 1 (XEN) RIP: e008:[<ffff82d0801e629e>] vmx_get_segment_register+0x14e/0x450 (XEN) RFLAGS: 0000000000010202 CONTEXT: hypervisor (d1v0) (XEN) rax: ffff82d0801e6288 rbx: ffff83003ffbfb7c rcx: fffffffffffab928 (XEN) rdx: 0000000000000000 rsi: 0000000000000000 rdi: ffff83000bdd0000 (XEN) rbp: ffff83000bdd0000 rsp: ffff83003ffbfab0 r8: ffff830038813910 (XEN) r9: ffff83003faf3958 r10: 0000000a3b9f7640 r11: ffff83003f82d418 (XEN) r12: 0000000000000000 r13: ffff83003ffbffff r14: 0000000000004802 (XEN) r15: 0000000000000008 cr0: 0000000080050033 cr4: 00000000001526e0 (XEN) cr3: 000000003fc79000 cr2: 0000000000000000 (XEN) ds: 0000 es: 0000 fs: 0000 gs: 0000 ss: 0000 cs: e008 (XEN) Xen code around <ffff82d0801e629e> (vmx_get_segment_register+0x14e/0x450): (XEN) 00 00 41 be 02 48 00 00 <44> 0f 78 74 24 08 0f 86 38 56 00 00 b8 08 68 00 (XEN) Xen stack trace from rsp=ffff83003ffbfab0: ... (XEN) Xen call trace: (XEN) [<ffff82d0801e629e>] vmx_get_segment_register+0x14e/0x450 (XEN) [<ffff82d0801f3695>] get_page_from_gfn_p2m+0x165/0x300 (XEN) [<ffff82d0801bfe32>] hvmemul_get_seg_reg+0x52/0x60 (XEN) [<ffff82d0801bfe93>] hvm_emulate_prepare+0x53/0x70 (XEN) [<ffff82d0801ccacb>] handle_mmio+0x2b/0xd0 (XEN) [<ffff82d0801be591>] emulate.c#_hvm_emulate_one+0x111/0x2c0 (XEN) [<ffff82d0801cd6a4>] handle_hvm_io_completion+0x274/0x2a0 (XEN) [<ffff82d0801f334a>] __get_gfn_type_access+0xfa/0x270 (XEN) [<ffff82d08012f3bb>] timer.c#add_entry+0x4b/0xb0 (XEN) [<ffff82d08012f80c>] timer.c#remove_entry+0x7c/0x90 (XEN) [<ffff82d0801c8433>] hvm_do_resume+0x23/0x140 (XEN) [<ffff82d0801e4fe7>] vmx_do_resume+0xa7/0x140 (XEN) [<ffff82d080164aeb>] context_switch+0x13b/0xe40 (XEN) [<ffff82d080128e6e>] schedule.c#schedule+0x22e/0x570 (XEN) [<ffff82d08012c0cc>] softirq.c#__do_softirq+0x5c/0x90 (XEN) [<ffff82d0801602c5>] domain.c#idle_loop+0x25/0x50 (XEN) (XEN) (XEN) **************************************** (XEN) Panic on CPU 1: (XEN) GENERAL PROTECTION FAULT (XEN) [error_code=0000] (XEN) **************************************** Tracing my host KVM showed it was the one injecting the GP(0) when emulating the VMREAD and checking the destination segment permissions in get_vmx_mem_address(): 3) | vmx_handle_exit() { 3) | handle_vmread() { 3) | nested_vmx_check_permission() { 3) | vmx_get_segment() { 3) 0.074 us | vmx_read_guest_seg_base(); 3) 0.065 us | vmx_read_guest_seg_selector(); 3) 0.066 us | vmx_read_guest_seg_ar(); 3) 1.636 us | } 3) 0.058 us | vmx_get_rflags(); 3) 0.062 us | vmx_read_guest_seg_ar(); 3) 3.469 us | } 3) | vmx_get_cs_db_l_bits() { 3) 0.058 us | vmx_read_guest_seg_ar(); 3) 0.662 us | } 3) | get_vmx_mem_address() { 3) 0.068 us | vmx_cache_reg(); 3) | vmx_get_segment() { 3) 0.074 us | vmx_read_guest_seg_base(); 3) 0.068 us | vmx_read_guest_seg_selector(); 3) 0.071 us | vmx_read_guest_seg_ar(); 3) 1.756 us | } 3) | kvm_queue_exception_e() { 3) 0.066 us | kvm_multiple_exception(); 3) 0.684 us | } 3) 4.085 us | } 3) 9.833 us | } 3) + 10.366 us | } Cross-checking the KVM/VMX VMREAD emulation code with the Intel Software Developper Manual Volume 3C - "VMREAD - Read Field from Virtual-Machine Control Structure", I found that we're enforcing that the destination operand is NOT located in a read-only data segment or any code segment when the L1 is in long mode - BUT that check should only happen when it is in protected mode. Shuffling the code a bit to make our emulation follow the specification allows me to boot a Xen dom0 in a nested KVM and start HVM L2 guests without problems. Fixes: f9eb4af67c9d ("KVM: nVMX: VMX instructions: add checks for #GP/#SS exceptions") Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Eugene Korenevsky <ekorenevsky@gmail.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: linux-stable <stable@vger.kernel.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kvm/vmx.c23
1 files changed, 11 insertions, 12 deletions
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 003618e324ce..64a79f271276 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6671,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
/* Checks for #GP/#SS exceptions. */
exn = false;
- if (is_protmode(vcpu)) {
+ if (is_long_mode(vcpu)) {
+ /* Long mode: #GP(0)/#SS(0) if the memory address is in a
+ * non-canonical form. This is the only check on the memory
+ * destination for long mode!
+ */
+ exn = is_noncanonical_address(*ret);
+ } else if (is_protmode(vcpu)) {
/* Protected mode: apply checks for segment validity in the
* following order:
* - segment type check (#GP(0) may be thrown)
@@ -6688,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
* execute-only code segment
*/
exn = ((s.type & 0xa) == 8);
- }
- if (exn) {
- kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
- return 1;
- }
- if (is_long_mode(vcpu)) {
- /* Long mode: #GP(0)/#SS(0) if the memory address is in a
- * non-canonical form. This is an only check for long mode.
- */
- exn = is_noncanonical_address(*ret);
- } else if (is_protmode(vcpu)) {
+ if (exn) {
+ kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+ return 1;
+ }
/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
*/
exn = (s.unusable != 0);