* PPC: Fix bug leading to lost IPIs and smp_call_function_many()

lockups on POWER9.
 * ARM: locking fix, reset fix, GICv2 multi-source SGI injection fix,
 GICv2-on-v3 MMIO synchronization fix, make the console less verbose.
 * x86: fix device passthrough on AMD SME.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.22 (GNU/Linux)
 
 iQEcBAABAgAGBQJariCQAAoJEL/70l94x66D6j4H/iS51f1EFRjTXbM+/D0BxpOD
 hTz3tiV4JNezwXkxm9FMr7e5sfONTsqZodzCeXbz9XRmb6lwkEIbaPC4G2ALJeBH
 V1Gpy2NsoBNCaU6Ci7SGqs1PG7wmG1tGMkzgkUoi2mwJRbA7UfnPmL1bTRESc4/w
 oYN5xPj1/bLYWnok2cEJevND2VUTy+/dazpm+9gZzHqeoBnRRhhNluLW11A7yi2U
 mSxAZrCH8X9EejIEhU8jAah4PYZ9tP8TmvUcnAPYpNgDh2JH6tlkGAYSbpadiCvf
 FJNhtev67uDL1jPzqQJLNo5Z04cg06M+9cYqrLD1q287LXsKs+LHXJY/AI56oIM=
 =YHkv
 -----END PGP SIGNATURE-----

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

Pull KVM fixes from Paolo Bonzini:
 "PPC:
   - fix bug leading to lost IPIs and smp_call_function_many() lockups
     on POWER9

  ARM:
   - locking fix
   - reset fix
   - GICv2 multi-source SGI injection fix
   - GICv2-on-v3 MMIO synchronization fix
   - make the console less verbose.

  x86:
   - fix device passthrough on AMD SME"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Fix device passthrough when SME is active
  kvm: arm/arm64: vgic-v3: Tighten synchronization for guests using v2 on v3
  KVM: arm/arm64: vgic: Don't populate multiple LRs with the same vintid
  KVM: arm/arm64: Reduce verbosity of KVM init log
  KVM: arm/arm64: Reset mapped IRQs on VM reset
  KVM: arm/arm64: Avoid vcpu_load for other vcpu ioctls than KVM_RUN
  KVM: arm/arm64: vgic: Add missing irq_lock to vgic_mmio_read_pending
  KVM: PPC: Book3S HV: Fix trap number return from __kvmppc_vcore_entry

arch/arm64/kvm/guest.c

@@ -363,8 +363,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 {
 	int ret = 0;
 
-	vcpu_load(vcpu);
-
 	trace_kvm_set_guest_debug(vcpu, dbg->control);
 
 	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
@@ -386,7 +384,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	}
 
 out:
-	vcpu_put(vcpu);
 	return ret;
 }
 

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -320,7 +320,6 @@ kvm_novcpu_exit:
 	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -1220,6 +1219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 secondary_too_late:
 	li	r12, 0
+	stw	r12, STACK_SLOT_TRAP(r1)
 	cmpdi	r4, 0
 	beq	11f
 	stw	r12, VCPU_TRAP(r4)
@@ -1558,12 +1558,12 @@ mc_cont:
 3:	stw	r5,VCPU_SLB_MAX(r9)
 
 guest_bypass:
+	stw	r12, STACK_SLOT_TRAP(r1)
 	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop
 	ld	r9, HSTATE_KVM_VCPU(r13)
-	lwz	r12, VCPU_TRAP(r9)
 
 	/* Stop others sending VCPU interrupts to this physical CPU */
 	li	r0, -1
@@ -1898,6 +1898,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
 	 * have to coordinate the hardware threads.
+	 * Here STACK_SLOT_TRAP(r1) contains the trap number.
 	 */
 kvmhv_switch_to_host:
 	/* Secondary threads wait for primary to do partition switch */
@@ -1950,12 +1951,12 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* If HMI, call kvmppc_realmode_hmi_handler() */
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	cmpwi	r12, BOOK3S_INTERRUPT_HMI
 	bne	27f
 	bl	kvmppc_realmode_hmi_handler
 	nop
 	cmpdi	r3, 0
-	li	r12, BOOK3S_INTERRUPT_HMI
 	/*
 	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
 	 * the TB, and if it has, we must not subtract the guest timebase
@@ -2008,10 +2009,8 @@ BEGIN_FTR_SECTION
 	lwz	r8, KVM_SPLIT_DO_RESTORE(r3)
 	cmpwi	r8, 0
 	beq	47f
-	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_p9_restore_lpcr
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	48f
 47:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -2049,6 +2048,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
+	lwz	r12, STACK_SLOT_TRAP(r1)	/* return trap # in r12 */
 	ld	r0, SFS+PPC_LR_STKOFF(r1)
 	addi	r1, r1, SFS
 	mtlr	r0

arch/x86/kvm/mmu.c

@@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	else
 		pte_access &= ~ACC_WRITE_MASK;
 
+	if (!kvm_is_mmio_pfn(pfn))
+		spte |= shadow_me_mask;
+
 	spte |= (u64)pfn << PAGE_SHIFT;
-	spte |= shadow_me_mask;
 
 	if (pte_access & ACC_WRITE_MASK) {
 

include/kvm/arm_vgic.h

@@ -360,6 +360,7 @@ void kvm_vgic_put(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid);
 
 void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 

include/linux/irqchip/arm-gic-v3.h

@@ -503,6 +503,7 @@
 
 #define ICH_HCR_EN			(1 << 0)
 #define ICH_HCR_UIE			(1 << 1)
+#define ICH_HCR_NPIE			(1 << 3)
 #define ICH_HCR_TC			(1 << 10)
 #define ICH_HCR_TALL0			(1 << 11)
 #define ICH_HCR_TALL1			(1 << 12)

include/linux/irqchip/arm-gic.h

@@ -84,6 +84,7 @@
 
 #define GICH_HCR_EN			(1 << 0)
 #define GICH_HCR_UIE			(1 << 1)
+#define GICH_HCR_NPIE			(1 << 3)
 
 #define GICH_LR_VIRTUALID		(0x3ff << 0)
 #define GICH_LR_PHYSID_CPUID_SHIFT	(10)

virt/kvm/arm/arch_timer.c

@@ -581,6 +581,7 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 {
+	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
 
@@ -594,6 +595,9 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	ptimer->cnt_ctl = 0;
 	kvm_timer_update_state(vcpu);
 
+	if (timer->enabled && irqchip_in_kernel(vcpu->kvm))
+		kvm_vgic_reset_mapped_irq(vcpu, vtimer->irq.irq);
+
 	return 0;
 }
 
@@ -767,7 +771,7 @@ int kvm_timer_hyp_init(bool has_gic)
 		static_branch_enable(&has_gic_active_state);
 	}
 
-	kvm_info("virtual timer IRQ%d\n", host_vtimer_irq);
+	kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq);
 
 	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
 			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,

virt/kvm/arm/arm.c

@@ -384,14 +384,11 @@ static void vcpu_power_off(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	vcpu_load(vcpu);
-
 	if (vcpu->arch.power_off)
 		mp_state->mp_state = KVM_MP_STATE_STOPPED;
 	else
 		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
 
-	vcpu_put(vcpu);
 	return 0;
 }
 
@@ -400,8 +397,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 {
 	int ret = 0;
 
-	vcpu_load(vcpu);
-
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.power_off = false;
@@ -413,7 +408,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 		ret = -EINVAL;
 	}
 
-	vcpu_put(vcpu);
 	return ret;
 }
 
@@ -1036,8 +1030,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	struct kvm_device_attr attr;
 	long r;
 
-	vcpu_load(vcpu);
-
 	switch (ioctl) {
 	case KVM_ARM_VCPU_INIT: {
 		struct kvm_vcpu_init init;
@@ -1114,7 +1106,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 	}
 
-	vcpu_put(vcpu);
 	return r;
 }
 

virt/kvm/arm/hyp/vgic-v3-sr.c

@@ -215,7 +215,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 	 * are now visible to the system register interface.
 	 */
 	if (!cpu_if->vgic_sre) {
-		dsb(st);
+		dsb(sy);
+		isb();
 		cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2);
 	}
 

virt/kvm/arm/mmu.c

@@ -1810,9 +1810,9 @@ int kvm_mmu_init(void)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
-	kvm_info("IDMAP page: %lx\n", hyp_idmap_start);
+	kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
-	kvm_info("HYP VA range: %lx:%lx\n",
+	kvm_debug("HYP VA range: %lx:%lx\n",
-		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
+		  kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
 
 	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
 	    hyp_idmap_start <  kern_hyp_va(~0UL) &&

virt/kvm/arm/vgic/vgic-mmio.c

@@ -113,9 +113,12 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
 	/* Loop over all IRQs affected by this read */
 	for (i = 0; i < len * 8; i++) {
 		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+		unsigned long flags;
 
+		spin_lock_irqsave(&irq->irq_lock, flags);
 		if (irq_is_pending(irq))
 			value |= (1U << i);
+		spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 		vgic_put_irq(vcpu->kvm, irq);
 	}

virt/kvm/arm/vgic/vgic-v2.c

@@ -37,6 +37,13 @@ void vgic_v2_init_lrs(void)
 		vgic_v2_write_lr(i, 0);
 }
 
+void vgic_v2_set_npie(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
+
+	cpuif->vgic_hcr |= GICH_HCR_NPIE;
+}
+
 void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -64,7 +71,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
 	int lr;
 	unsigned long flags;
 
-	cpuif->vgic_hcr &= ~GICH_HCR_UIE;
+	cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE);
 
 	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u32 val = cpuif->vgic_lr[lr];
@@ -410,7 +417,7 @@ int vgic_v2_probe(const struct gic_kvm_info *info)
 	kvm_vgic_global_state.type = VGIC_V2;
 	kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS;
 
-	kvm_info("vgic-v2@%llx\n", info->vctrl.start);
+	kvm_debug("vgic-v2@%llx\n", info->vctrl.start);
 
 	return 0;
 out:

virt/kvm/arm/vgic/vgic-v3.c

@@ -26,6 +26,13 @@ static bool group1_trap;
 static bool common_trap;
 static bool gicv4_enable;
 
+void vgic_v3_set_npie(struct kvm_vcpu *vcpu)
+{
+	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
+
+	cpuif->vgic_hcr |= ICH_HCR_NPIE;
+}
+
 void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -47,7 +54,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
 	int lr;
 	unsigned long flags;
 
-	cpuif->vgic_hcr &= ~ICH_HCR_UIE;
+	cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE);
 
 	for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
 		u64 val = cpuif->vgic_lr[lr];

virt/kvm/arm/vgic/vgic.c

@@ -495,6 +495,32 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
 	return ret;
 }
 
+/**
+ * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ
+ * @vcpu: The VCPU pointer
+ * @vintid: The INTID of the interrupt
+ *
+ * Reset the active and pending states of a mapped interrupt.  Kernel
+ * subsystems injecting mapped interrupts should reset their interrupt lines
+ * when we are doing a reset of the VM.
+ */
+void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid)
+{
+	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
+	unsigned long flags;
+
+	if (!irq->hw)
+		goto out;
+
+	spin_lock_irqsave(&irq->irq_lock, flags);
+	irq->active = false;
+	irq->pending_latch = false;
+	irq->line_level = false;
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
+out:
+	vgic_put_irq(vcpu->kvm, irq);
+}
+
 int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid)
 {
 	struct vgic_irq *irq;
@@ -684,22 +710,37 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
 		vgic_v3_set_underflow(vcpu);
 }
 
+static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vgic_global_state.type == VGIC_V2)
+		vgic_v2_set_npie(vcpu);
+	else
+		vgic_v3_set_npie(vcpu);
+}
+
 /* Requires the ap_list_lock to be held. */
-static int compute_ap_list_depth(struct kvm_vcpu *vcpu)
+static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
+				 bool *multi_sgi)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_irq *irq;
 	int count = 0;
 
+	*multi_sgi = false;
+
 	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
 
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		spin_lock(&irq->irq_lock);
 		/* GICv2 SGIs can count for more than one... */
-		if (vgic_irq_is_sgi(irq->intid) && irq->source)
+		if (vgic_irq_is_sgi(irq->intid) && irq->source) {
-			count += hweight8(irq->source);
+			int w = hweight8(irq->source);
-		else
+
+			count += w;
+			*multi_sgi |= (w > 1);
+		} else {
 			count++;
+		}
 		spin_unlock(&irq->irq_lock);
 	}
 	return count;
@@ -710,28 +751,43 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_irq *irq;
-	int count = 0;
+	int count;
+	bool npie = false;
+	bool multi_sgi;
+	u8 prio = 0xff;
 
 	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
 
-	if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr)
+	count = compute_ap_list_depth(vcpu, &multi_sgi);
+	if (count > kvm_vgic_global_state.nr_lr || multi_sgi)
 		vgic_sort_ap_list(vcpu);
 
+	count = 0;
+
 	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
 		spin_lock(&irq->irq_lock);
 
-		if (unlikely(vgic_target_oracle(irq) != vcpu))
-			goto next;
-
 		/*
-		 * If we get an SGI with multiple sources, try to get
+		 * If we have multi-SGIs in the pipeline, we need to
-		 * them in all at once.
+		 * guarantee that they are all seen before any IRQ of
+		 * lower priority. In that case, we need to filter out
+		 * these interrupts by exiting early. This is easy as
+		 * the AP list has been sorted already.
 		 */
-		do {
+		if (multi_sgi && irq->priority > prio) {
-			vgic_populate_lr(vcpu, irq, count++);
+			spin_unlock(&irq->irq_lock);
-		} while (irq->source && count < kvm_vgic_global_state.nr_lr);
+			break;
+		}
+
+		if (likely(vgic_target_oracle(irq) == vcpu)) {
+			vgic_populate_lr(vcpu, irq, count++);
+
+			if (irq->source) {
+				npie = true;
+				prio = irq->priority;
+			}
+		}
 
-next:
 		spin_unlock(&irq->irq_lock);
 
 		if (count == kvm_vgic_global_state.nr_lr) {
@@ -742,6 +798,9 @@ next:
 		}
 	}
 
+	if (npie)
+		vgic_set_npie(vcpu);
+
 	vcpu->arch.vgic_cpu.used_lrs = count;
 
 	/* Nuke remaining LRs */

virt/kvm/arm/vgic/vgic.h

@@ -96,6 +96,7 @@
 /* we only support 64 kB translation table page size */
 #define KVM_ITS_L1E_ADDR_MASK		GENMASK_ULL(51, 16)
 
+/* Requires the irq_lock to be held by the caller. */
 static inline bool irq_is_pending(struct vgic_irq *irq)
 {
 	if (irq->config == VGIC_CONFIG_EDGE)
@@ -159,6 +160,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr);
 void vgic_v2_set_underflow(struct kvm_vcpu *vcpu);
+void vgic_v2_set_npie(struct kvm_vcpu *vcpu);
 int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
 int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
 			 int offset, u32 *val);
@@ -188,6 +190,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu);
 void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
 void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr);
 void vgic_v3_set_underflow(struct kvm_vcpu *vcpu);
+void vgic_v3_set_npie(struct kvm_vcpu *vcpu);
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
 void vgic_v3_enable(struct kvm_vcpu *vcpu);