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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - A number of issues in the vgic discovered using SMATCH
   - A bit one-off calculation in out stage base address mask (32-bit
     and 64-bit)
   - Fixes to single-step debugging instructions that trap for other
     reasons such as MMMIO aborts
   - Printing unavailable hyp mode as error
   - Potential spinlock deadlock in the vgic
   - Avoid calling vgic vcpu free more than once
   - Broken bit calculation for big endian systems

 s390:
   - SPDX tags
   - Fence storage key accesses from problem state
   - Make sure that irq_state.flags is not used in the future

  x86:
   - Intercept port 0x80 accesses to prevent host instability (CVE)
   - Use userspace FPU context for guest FPU (mainly an optimization
     that fixes a double use of kernel FPU)
   - Do not leak one page per module load
   - Flush APIC page address cache from MMU invalidation notifiers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: x86: fix APIC page invalidation
  KVM: s390: Fix skey emulation permission check
  KVM: s390: mark irq_state.flags as non-usable
  KVM: s390: Remove redundant license text
  KVM: s390: add SPDX identifiers to the remaining files
  KVM: VMX: fix page leak in hardware_setup()
  KVM: VMX: remove I/O port 0x80 bypass on Intel hosts
  x86,kvm: remove KVM emulator get_fpu / put_fpu
  x86,kvm: move qemu/guest FPU switching out to vcpu_run
  KVM: arm/arm64: Fix broken GICH_ELRSR big endian conversion
  KVM: arm/arm64: kvm_arch_destroy_vm cleanups
  KVM: arm/arm64: Fix spinlock acquisition in vgic_set_owner
  kvm: arm: don't treat unavailable HYP mode as an error
  KVM: arm/arm64: Avoid attempting to load timer vgic state without a vgic
  kvm: arm64: handle single-step of hyp emulated mmio instructions
  kvm: arm64: handle single-step during SError exceptions
  kvm: arm64: handle single-step of userspace mmio instructions
  kvm: arm64: handle single-stepping trapped instructions
  KVM: arm/arm64: debug: Introduce helper for single-step
  arm: KVM: Fix VTTBR_BADDR_MASK BUG_ON off-by-one
  ...

5 files changed, 47 insertions, 64 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
-	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
-	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 977de5fb968b..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
+	/*
+	 * QEMU userspace and the guest each have their own FPU state.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
+	 *
+	 * Note that while the PKRU state lives inside the fpu registers,
+	 * it is switched out separately at VMENTER and VMEXIT time. The
+	 * "guest_fpu" state here contains the guest FPU context, with the
+	 * host PRKU bits.
+	 */
+	struct fpu user_fpu;
 	struct fpu guest_fpu;
+
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -1435,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e7d04d0c8008..abe74f779f9d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1046,7 +1046,6 @@ static void fetch_register_operand(struct operand *op)
 
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1068,13 +1067,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1096,12 +1093,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1113,12 +1108,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1130,7 +1123,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1138,9 +1130,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fninit");
-	ctxt->ops->put_fpu(ctxt);
 	return X86EMUL_CONTINUE;
 }
 
@@ -1151,9 +1141,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstcw %0": "+m"(fcw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fcw;
 
@@ -1167,9 +1155,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstsw %0": "+m"(fsw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fsw;
 
@@ -4001,12 +3987,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
-	ctxt->ops->put_fpu(ctxt);
-
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4049,8 +4031,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	if (size < __fxstate_size(16)) {
 		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
@@ -4066,8 +4046,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
-	ctxt->ops->put_fpu(ctxt);
-
 	return rc;
 }
 
@@ -5317,9 +5295,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
-	ctxt->ops->get_fpu(ctxt);
 	rc = asm_safe("fwait");
-	ctxt->ops->put_fpu(ctxt);
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4704aaf6d19e..8eba631c4dbd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6751,16 +6751,10 @@ static __init int hardware_setup(void)
 			goto out;
 	}
 
-	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
-	/*
-	 * Allow direct access to the PC debug port (it is often used for I/O
-	 * delays, but the vmexits simply slow things down).
-	 */
 	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-	clear_bit(0x80, vmx_io_bitmap_a);
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eee8e7faf1af..faf843c9b916 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2937,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	pagefault_enable();
 	kvm_x86_ops->vcpu_put(vcpu);
-	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
 }
 
@@ -5252,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt)
 	emul_to_vcpu(ctxt)->arch.halt_request = 1;
 }
 
-static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_disable();
-	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-}
-
-static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_enable();
-}
-
 static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 			      struct x86_instruction_info *info,
 			      enum x86_intercept_stage stage)
@@ -5340,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
 	.fix_hypercall       = emulator_fix_hypercall,
-	.get_fpu             = emulator_get_fpu,
-	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
@@ -6778,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->tlb_flush(vcpu);
 }
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end)
+{
+	unsigned long apic_address;
+
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (start <= apic_address && apic_address < end)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	struct page *page = NULL;
@@ -6952,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
 
 	/*
 	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
@@ -7297,12 +7296,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
+	kvm_load_guest_fpu(vcpu);
+
 	if (unlikely(vcpu->arch.complete_userspace_io)) {
 		int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
 		vcpu->arch.complete_userspace_io = NULL;
 		r = cui(vcpu);
 		if (r <= 0)
-			goto out;
+			goto out_fpu;
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
@@ -7311,6 +7312,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	else
 		r = vcpu_run(vcpu);
 
+out_fpu:
+	kvm_put_guest_fpu(vcpu);
 out:
 	post_kvm_run_save(vcpu);
 	kvm_sigset_deactivate(vcpu);
@@ -7704,32 +7707,25 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_fpu_loaded)
-		return;
-
-	/*
-	 * Restore all possible states in the guest,
-	 * and assume host would use all available bits.
-	 * Guest xcr0 would be loaded later.
-	 */
-	vcpu->guest_fpu_loaded = 1;
-	__kernel_fpu_begin();
+	preempt_disable();
+	copy_fpregs_to_fpstate(&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);
+	preempt_enable();
 	trace_kvm_fpu(1);
 }
 
+/* When vcpu_run ends, restore user space FPU context. */
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded)
-		return;
-
-	vcpu->guest_fpu_loaded = 0;
+	preempt_disable();
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	__kernel_fpu_end();
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	preempt_enable();
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -7846,7 +7842,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		 * To avoid have the INIT path from kvm_apic_has_events() that be
 		 * called with loaded FPU and does not let userspace fix the state.
 		 */
-		kvm_put_guest_fpu(vcpu);
+		if (init_event)
+			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
 					XFEATURE_MASK_BNDREGS);
 		if (mpx_state_buffer)
@@ -7855,6 +7852,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 					XFEATURE_MASK_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+		if (init_event)
+			kvm_load_guest_fpu(vcpu);
 	}
 
 	if (!init_event) {