Merge tag 'kvm-arm-fixes-for-v4.15-1' of...

Merge tag 'kvm-arm-fixes-for-v4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm

KVM/ARM Fixes for v4.15.

Fixes:
 - 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

arch/arm/include/asm/kvm_arm.h

@@ -161,8 +161,7 @@
 #else
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  _AC(48, ULL)
 #define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 

arch/arm/include/asm/kvm_host.h

@@ -285,6 +285,11 @@ static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
+					     struct kvm_run *run)
+{
+	return false;
+}
 
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);

arch/arm64/include/asm/kvm_arm.h

@@ -170,8 +170,7 @@
 #define VTCR_EL2_FLAGS			(VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
 #define VTTBR_X				(VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
 
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  (UL(48))
 #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 

arch/arm64/include/asm/kvm_host.h

@@ -370,6 +370,7 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,

arch/arm64/kvm/debug.c

@@ -221,3 +221,24 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 		}
 	}
 }
+
+
+/*
+ * After successfully emulating an instruction, we might want to
+ * return to user space with a KVM_EXIT_DEBUG. We can only do this
+ * once the emulation is complete, though, so for userspace emulations
+ * we have to wait until we have re-entered KVM before calling this
+ * helper.
+ *
+ * Return true (and set exit_reason) to return to userspace or false
+ * if no further action is required.
+ */
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
+		return true;
+	}
+	return false;
+}

arch/arm64/kvm/handle_exit.c

@@ -28,6 +28,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_psci.h>
+#include <asm/debug-monitors.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -186,6 +187,40 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	return arm_exit_handlers[hsr_ec];
 }
 
+/*
+ * We may be single-stepping an emulated instruction. If the emulation
+ * has been completed in the kernel, we can return to userspace with a
+ * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
+ * emulation first.
+ */
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int handled;
+
+	/*
+	 * See ARM ARM B1.14.1: "Hyp traps on instructions
+	 * that fail their condition code check"
+	 */
+	if (!kvm_condition_valid(vcpu)) {
+		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		handled = 1;
+	} else {
+		exit_handle_fn exit_handler;
+
+		exit_handler = kvm_get_exit_handler(vcpu);
+		handled = exit_handler(vcpu, run);
+	}
+
+	/*
+	 * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
+	 * structure if we need to return to userspace.
+	 */
+	if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
+		handled = 0;
+
+	return handled;
+}
+
 /*
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to userspace.
@@ -193,8 +228,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
-	exit_handle_fn exit_handler;
-
 	if (ARM_SERROR_PENDING(exception_index)) {
 		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
 
@@ -220,20 +253,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return 1;
 	case ARM_EXCEPTION_EL1_SERROR:
 		kvm_inject_vabt(vcpu);
+		/* We may still need to return for single-step */
+		if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+			&& kvm_arm_handle_step_debug(vcpu, run))
+			return 0;
+		else
 			return 1;
 	case ARM_EXCEPTION_TRAP:
-		/*
-		 * See ARM ARM B1.14.1: "Hyp traps on instructions
-		 * that fail their condition code check"
-		 */
-		if (!kvm_condition_valid(vcpu)) {
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
-			return 1;
-		}
-
-		exit_handler = kvm_get_exit_handler(vcpu);
-
-		return exit_handler(vcpu, run);
+		return handle_trap_exceptions(vcpu, run);
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest

arch/arm64/kvm/hyp/switch.c

@@ -22,6 +22,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
 
 static bool __hyp_text __fpsimd_enabled_nvhe(void)
 {
@@ -269,7 +270,11 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
+/* Skip an instruction which has been emulated. Returns true if
+ * execution can continue or false if we need to exit hyp mode because
+ * single-step was in effect.
+ */
+static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
 
@@ -282,6 +287,14 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg_el2(*vcpu_pc(vcpu), elr);
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		vcpu->arch.fault.esr_el2 =
+			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
+		return false;
+	} else {
+		return true;
+	}
 }
 
 int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
@@ -342,13 +355,21 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
 			if (ret == 1) {
-				__skip_instr(vcpu);
+				if (__skip_instr(vcpu))
 					goto again;
+				else
+					exit_code = ARM_EXCEPTION_TRAP;
 			}
 
 			if (ret == -1) {
-				/* Promote an illegal access to an SError */
-				__skip_instr(vcpu);
+				/* Promote an illegal access to an
+				 * SError. If we would be returning
+				 * due to single-step clear the SS
+				 * bit so handle_exit knows what to
+				 * do after dealing with the error.
+				 */
+				if (!__skip_instr(vcpu))
+					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 				exit_code = ARM_EXCEPTION_EL1_SERROR;
 			}
 
@@ -363,8 +384,10 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
 		if (ret == 1) {
-			__skip_instr(vcpu);
+			if (__skip_instr(vcpu))
 				goto again;
+			else
+				exit_code = ARM_EXCEPTION_TRAP;
 		}
 
 		/* 0 falls through to be handled out of EL2 */

include/kvm/arm_arch_timer.h

@@ -93,7 +93,4 @@ void kvm_timer_init_vhe(void);
 #define vcpu_vtimer(v)	(&(v)->arch.timer_cpu.vtimer)
 #define vcpu_ptimer(v)	(&(v)->arch.timer_cpu.ptimer)
 
-void enable_el1_phys_timer_access(void);
-void disable_el1_phys_timer_access(void);
-
 #endif

virt/kvm/arm/arch_timer.c

@@ -479,9 +479,6 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
 
 	vtimer_restore_state(vcpu);
 
-	if (has_vhe())
-		disable_el1_phys_timer_access();
-
 	/* Set the background timer for the physical timer emulation. */
 	phys_timer_emulate(vcpu);
 }
@@ -510,9 +507,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 	if (unlikely(!timer->enabled))
 		return;
 
-	if (has_vhe())
-		enable_el1_phys_timer_access();
-
 	vtimer_save_state(vcpu);
 
 	/*
@@ -841,6 +835,9 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
 no_vgic:
 	preempt_disable();
 	timer->enabled = 1;
+	if (!irqchip_in_kernel(vcpu->kvm))
+		kvm_timer_vcpu_load_user(vcpu);
+	else
 		kvm_timer_vcpu_load_vgic(vcpu);
 	preempt_enable();
 

virt/kvm/arm/arm.c

@@ -188,6 +188,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 			kvm->vcpus[i] = NULL;
 		}
 	}
+	atomic_set(&kvm->online_vcpus, 0);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -296,7 +297,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
-	kvm_vgic_vcpu_destroy(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
@@ -627,6 +627,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		ret = kvm_handle_mmio_return(vcpu, vcpu->run);
 		if (ret)
 			return ret;
+		if (kvm_arm_handle_step_debug(vcpu, vcpu->run))
+			return 0;
+
 	}
 
 	if (run->immediate_exit)
@@ -1502,7 +1505,7 @@ int kvm_arch_init(void *opaque)
 	bool in_hyp_mode;
 
 	if (!is_hyp_mode_available()) {
-		kvm_err("HYP mode not available\n");
+		kvm_info("HYP mode not available\n");
 		return -ENODEV;
 	}
 

virt/kvm/arm/hyp/timer-sr.c

@@ -27,18 +27,25 @@ void __hyp_text __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high)
 	write_sysreg(cntvoff, cntvoff_el2);
 }
 
-void __hyp_text enable_el1_phys_timer_access(void)
+void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We don't need to do this for VHE since the host kernel runs in EL2
+	 * with HCR_EL2.TGE ==1, which makes those bits have no impact.
+	 */
+	if (!has_vhe()) {
 		u64 val;
 
 		/* Allow physical timer/counter access for the host */
 		val = read_sysreg(cnthctl_el2);
 		val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
 		write_sysreg(val, cnthctl_el2);
+	}
 }
 
-void __hyp_text disable_el1_phys_timer_access(void)
+void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
 {
+	if (!has_vhe()) {
 		u64 val;
 
 		/*
@@ -49,20 +56,5 @@ void __hyp_text disable_el1_phys_timer_access(void)
 		val &= ~CNTHCTL_EL1PCEN;
 		val |= CNTHCTL_EL1PCTEN;
 		write_sysreg(val, cnthctl_el2);
-}
-
-void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu)
-{
-	/*
-	 * We don't need to do this for VHE since the host kernel runs in EL2
-	 * with HCR_EL2.TGE ==1, which makes those bits have no impact.
-	 */
-	if (!has_vhe())
-		enable_el1_phys_timer_access();
-}
-
-void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu)
-{
-	if (!has_vhe())
-		disable_el1_phys_timer_access();
+	}
 }

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

@@ -34,11 +34,7 @@ static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base)
 	else
 		elrsr1 = 0;
 
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1;
-#else
 	cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0;
-#endif
 }
 
 static void __hyp_text save_lrs(struct kvm_vcpu *vcpu, void __iomem *base)

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

@@ -112,8 +112,7 @@ int kvm_vgic_setup_default_irq_routing(struct kvm *kvm)
 	u32 nr = dist->nr_spis;
 	int i, ret;
 
-	entries = kcalloc(nr, sizeof(struct kvm_kernel_irq_routing_entry),
-			  GFP_KERNEL);
+	entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL);
 	if (!entries)
 		return -ENOMEM;
 

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

@@ -421,6 +421,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 	u32 *intids;
 	int nr_irqs, i;
 	unsigned long flags;
+	u8 pendmask;
 
 	nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
 	if (nr_irqs < 0)
@@ -428,7 +429,6 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < nr_irqs; i++) {
 		int byte_offset, bit_nr;
-		u8 pendmask;
 
 		byte_offset = intids[i] / BITS_PER_BYTE;
 		bit_nr = intids[i] % BITS_PER_BYTE;
@@ -821,6 +821,8 @@ static int vgic_its_alloc_collection(struct vgic_its *its,
 		return E_ITS_MAPC_COLLECTION_OOR;
 
 	collection = kzalloc(sizeof(*collection), GFP_KERNEL);
+	if (!collection)
+		return -ENOMEM;
 
 	collection->collection_id = coll_id;
 	collection->target_addr = COLLECTION_NOT_MAPPED;

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

@@ -327,13 +327,13 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 	int last_byte_offset = -1;
 	struct vgic_irq *irq;
 	int ret;
+	u8 val;
 
 	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
 		int byte_offset, bit_nr;
 		struct kvm_vcpu *vcpu;
 		gpa_t pendbase, ptr;
 		bool stored;
-		u8 val;
 
 		vcpu = irq->target_vcpu;
 		if (!vcpu)

virt/kvm/arm/vgic/vgic-v4.c

@@ -337,8 +337,10 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq,
 		goto out;
 
 	WARN_ON(!(irq->hw && irq->host_irq == virq));
+	if (irq->hw) {
 		irq->hw = false;
 		ret = its_unmap_vlpi(virq);
+	}
 
 out:
 	mutex_unlock(&its->its_lock);

virt/kvm/arm/vgic/vgic.c

@@ -492,6 +492,7 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid)
 int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner)
 {
 	struct vgic_irq *irq;
+	unsigned long flags;
 	int ret = 0;
 
 	if (!vgic_initialized(vcpu->kvm))
@@ -502,12 +503,12 @@ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner)
 		return -EINVAL;
 
 	irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
-	spin_lock(&irq->irq_lock);
+	spin_lock_irqsave(&irq->irq_lock, flags);
 	if (irq->owner && irq->owner != owner)
 		ret = -EEXIST;
 	else
 		irq->owner = owner;
-	spin_unlock(&irq->irq_lock);
+	spin_unlock_irqrestore(&irq->irq_lock, flags);
 
 	return ret;
 }
@@ -823,13 +824,14 @@ void vgic_kick_vcpus(struct kvm *kvm)
 
 bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid)
 {
-	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
+	struct vgic_irq *irq;
 	bool map_is_active;
 	unsigned long flags;
 
 	if (!vgic_initialized(vcpu->kvm))
 		return false;
 
+	irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
 	spin_lock_irqsave(&irq->irq_lock, flags);
 	map_is_active = irq->hw && irq->active;
 	spin_unlock_irqrestore(&irq->irq_lock, flags);