KVM: x86: Handle TIF_NEED_FPU_LOAD in kvm_{load,put}_guest_fpu()

Handle TIF_NEED_FPU_LOAD similar to how fpu__copy() handles the flag
when duplicating FPU state to a new task struct.  TIF_NEED_FPU_LOAD can
be set any time control is transferred out of KVM, be it voluntarily,
e.g. if I/O is triggered during a KVM call to get_user_pages, or
involuntarily, e.g. if softirq runs after an IRQ occurs.  Therefore,
KVM must account for TIF_NEED_FPU_LOAD whenever it is (potentially)
accessing CPU FPU state.

Fixes: 5f409e20 ("x86/fpu: Defer FPU state load until return to userspace")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/x86.c

@@ -8558,12 +8558,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void kvm_save_current_fpu(struct fpu *fpu)
+{
+	/*
+	 * If the target FPU state is not resident in the CPU registers, just
+	 * memcpy() from current, else save CPU state directly to the target.
+	 */
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&fpu->state, &current->thread.fpu.state,
+		       fpu_kernel_xstate_size);
+	else
+		copy_fpregs_to_fpstate(fpu);
+}
+
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
+	kvm_save_current_fpu(vcpu->arch.user_fpu);
+
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8579,7 +8593,8 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
+	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();