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

Pull KVM fixes from Paolo Bonzini:
 "ARM fixes:
   - A bug in handling of SPE state for non-vhe systems
   - A fix for a crash on system shutdown
   - Three timer fixes, introduced by the timer optimizations for v4.15

  x86 fixes:
   - fix for a WARN that was introduced in 4.15
   - fix for SMM when guest uses PCID
   - fixes for several bugs found by syzkaller

  ... and a dozen papercut fixes for the kvm_stat tool"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (22 commits)
  tools/kvm_stat: sort '-f help' output
  kvm: x86: fix RSM when PCID is non-zero
  KVM: Fix stack-out-of-bounds read in write_mmio
  KVM: arm/arm64: Fix timer enable flow
  KVM: arm/arm64: Properly handle arch-timer IRQs after vtimer_save_state
  KVM: arm/arm64: timer: Don't set irq as forwarded if no usable GIC
  KVM: arm/arm64: Fix HYP unmapping going off limits
  arm64: kvm: Prevent restoring stale PMSCR_EL1 for vcpu
  KVM/x86: Check input paging mode when cs.l is set
  tools/kvm_stat: add line for totals
  tools/kvm_stat: stop ignoring unhandled arguments
  tools/kvm_stat: suppress usage information on command line errors
  tools/kvm_stat: handle invalid regular expressions
  tools/kvm_stat: add hint on '-f help' to man page
  tools/kvm_stat: fix child trace events accounting
  tools/kvm_stat: fix extra handling of 'help' with fields filter
  tools/kvm_stat: fix missing field update after filter change
  tools/kvm_stat: fix drilldown in events-by-guests mode
  tools/kvm_stat: fix command line option '-g'
  kvm: x86: fix WARN due to uninitialized guest FPU state
  ...

4 files changed, 67 insertions, 24 deletions

diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 321c9c05dd9e..f4363d40e2cd 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 {
 	u64 reg;
 
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
 	/* SPE present on this CPU? */
 	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
 						  ID_AA64DFR0_PMSVER_SHIFT))
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index abe74f779f9d..b514b2b2845a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2390,9 +2390,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 }
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
-				     u64 cr0, u64 cr4)
+				    u64 cr0, u64 cr3, u64 cr4)
 {
 	int bad;
+	u64 pcid;
+
+	/* In order to later set CR4.PCIDE, CR3[11:0] must be zero.  */
+	pcid = 0;
+	if (cr4 & X86_CR4_PCIDE) {
+		pcid = cr3 & 0xfff;
+		cr3 &= ~0xfff;
+	}
+
+	bad = ctxt->ops->set_cr(ctxt, 3, cr3);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
 
 	/*
 	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
@@ -2411,6 +2423,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
 		if (bad)
 			return X86EMUL_UNHANDLEABLE;
+		if (pcid) {
+			bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
+			if (bad)
+				return X86EMUL_UNHANDLEABLE;
+		}
+
 	}
 
 	return X86EMUL_CONTINUE;
@@ -2421,11 +2439,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	struct desc_struct desc;
 	struct desc_ptr dt;
 	u16 selector;
-	u32 val, cr0, cr4;
+	u32 val, cr0, cr3, cr4;
 	int i;
 
 	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
 	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
 	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
 
@@ -2467,14 +2485,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
 
-	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
 static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
-	u64 val, cr0, cr4;
+	u64 val, cr0, cr3, cr4;
 	u32 base3;
 	u16 selector;
 	int i, r;
@@ -2491,7 +2509,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
 	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
 	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
@@ -2519,7 +2537,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	r = rsm_enter_protected_mode(ctxt, cr0, cr4);
+	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 	if (r != X86EMUL_CONTINUE)
 		return r;
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e5e66e5c6640..c4deb1f34faa 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if(make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, 0, 0,
 				vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
@@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 			spin_lock(&vcpu->kvm->mmu_lock);
 			if (make_mmu_pages_available(vcpu) < 0) {
 				spin_unlock(&vcpu->kvm->mmu_lock);
-				return 1;
+				return -ENOSPC;
 			}
 			sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT),
 					i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL);
@@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if (make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
 				vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
@@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if (make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
-			return 1;
+			return -ENOSPC;
 		}
 		sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL,
 				      0, ACC_ALL);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index faf843c9b916..1cec2c62a0b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4384,7 +4384,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 					 addr, n, v))
 		    && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
 			break;
-		trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v);
+		trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v);
 		handled += n;
 		addr += n;
 		len -= n;
@@ -4643,7 +4643,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
 {
 	if (vcpu->mmio_read_completed) {
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
-			       vcpu->mmio_fragments[0].gpa, *(u64 *)val);
+			       vcpu->mmio_fragments[0].gpa, val);
 		vcpu->mmio_read_completed = 0;
 		return 1;
 	}
@@ -4665,14 +4665,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
 
 static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
 {
-	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+	trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val);
 	return vcpu_mmio_write(vcpu, gpa, bytes, val);
 }
 
 static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  void *val, int bytes)
 {
-	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
+	trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL);
 	return X86EMUL_IO_NEEDED;
 }
 
@@ -7264,13 +7264,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	struct fpu *fpu = &current->thread.fpu;
 	int r;
 
-	fpu__initialize(fpu);
-
 	kvm_sigset_activate(vcpu);
 
+	kvm_load_guest_fpu(vcpu);
+
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
 		if (kvm_run->immediate_exit) {
 			r = -EINTR;
@@ -7296,14 +7295,12 @@ 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_fpu;
+			goto out;
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
@@ -7312,9 +7309,8 @@ 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:
+	kvm_put_guest_fpu(vcpu);
 	post_kvm_run_save(vcpu);
 	kvm_sigset_deactivate(vcpu);
 
@@ -7384,7 +7380,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);
-	kvm_set_rflags(vcpu, regs->rflags);
+	kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
 
 	vcpu->arch.exception.pending = false;
 
@@ -7498,6 +7494,29 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
+int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) {
+		/*
+		 * When EFER.LME and CR0.PG are set, the processor is in
+		 * 64-bit mode (though maybe in a 32-bit code segment).
+		 * CR4.PAE and EFER.LMA must be set.
+		 */
+		if (!(sregs->cr4 & X86_CR4_PAE_BIT)
+		    || !(sregs->efer & EFER_LMA))
+			return -EINVAL;
+	} else {
+		/*
+		 * Not in 64-bit mode: EFER.LMA is clear and the code
+		 * segment cannot be 64-bit.
+		 */
+		if (sregs->efer & EFER_LMA || sregs->cs.l)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
@@ -7510,6 +7529,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 			(sregs->cr4 & X86_CR4_OSXSAVE))
 		return -EINVAL;
 
+	if (kvm_valid_sregs(vcpu, sregs))
+		return -EINVAL;
+
 	apic_base_msr.data = sregs->apic_base;
 	apic_base_msr.host_initiated = true;
 	if (kvm_set_apic_base(vcpu, &apic_base_msr))