KVM: x86: Whitelist port 0x7e for pre-incrementing %rip

KVM's recent bug fix to update %rip after emulating I/O broke userspace
that relied on the previous behavior of incrementing %rip prior to
exiting to userspace.  When running a Windows XP guest on AMD hardware,
Qemu may patch "OUT 0x7E" instructions in reaction to the OUT itself.
Because KVM's old behavior was to increment %rip before exiting to
userspace to handle the I/O, Qemu manually adjusted %rip to account for
the OUT instruction.

Arguably this is a userspace bug as KVM requires userspace to re-enter
the kernel to complete instruction emulation before taking any other
actions.  That being said, this is a bit of a grey area and breaking
userspace that has worked for many years is bad.

Pre-increment %rip on OUT to port 0x7e before exiting to userspace to
hack around the issue.

Fixes: 45def77ebf79e ("KVM: x86: update %rip after emulating IO")
Reported-by: Simon Becherer <simon@becherer.de>
Reported-and-tested-by: Iakov Karpov <srid@rkmail.ru>
Reported-by: Gabriele Balducci <balducci@units.it>
Reported-by: Antti Antinoja <reader@fennosys.fi>
Cc: stable@vger.kernel.org
Cc: Takashi Iwai <tiwai@suse.com>
Cc: Jiri Slaby <jslaby@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index dabfcf7c3941aa90a92a91ee37f1164447c71655..7a0e64ccd6ff5d02108a4424fc72a36f49018987 100644 (file)
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -381,6 +381,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LINT0_REENABLED  (1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED    (1 << 1)
 #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE  (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP   (1 << 3)
 
 #define KVM_STATE_NESTED_GUEST_MODE    0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING   0x00000002

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9482cb36b92aca35b49df5d631ff35757cda0fa6..57621313deadc75800ad748f0add2fbfc93cce9c 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6539,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+       vcpu->arch.pio.count = 0;
+       return 1;
+}
+
 static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 {
        vcpu->arch.pio.count = 0;
@@ -6555,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
        unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
        int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
                                            size, port, &val, 1);
+       if (ret)
+               return ret;
 
-       if (!ret) {
+       /*
+        * Workaround userspace that relies on old KVM behavior of %rip being
+        * incremented prior to exiting to userspace to handle "OUT 0x7e".
+        */
+       if (port == 0x7e &&
+           kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+               vcpu->arch.complete_userspace_io =
+                       complete_fast_pio_out_port_0x7e;
+               kvm_skip_emulated_instruction(vcpu);
+       } else {
                vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
                vcpu->arch.complete_userspace_io = complete_fast_pio_out;
        }
-       return ret;
+       return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)