Merge tag 'kvm-arm-for-4.2' of...

Merge tag 'kvm-arm-for-4.2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/ARM changes for v4.2:

- Proper guest time accounting
- FP access fix for 32bit
- The usual pile of GIC fixes
- PSCI fixes
- Random cleanups

arch/arm/kvm/Kconfig

@@ -28,6 +28,7 @@ config KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
 	select MMU_NOTIFIER
+	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER

arch/arm/kvm/Makefile

@@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
 AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
 
 KVM := ../../../virt/kvm
-kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 
 obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o

arch/arm/kvm/arm.c

@@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	int r;
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_USER_MEMORY:
@@ -532,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		kvm_vgic_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 
+		preempt_disable();
 		local_irq_disable();
 
 		/*
@@ -544,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
 			local_irq_enable();
+			preempt_enable();
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			continue;
@@ -559,8 +560,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
-		__kvm_guest_exit();
-		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		/*
+		 * Back from guest
+		 *************************************************************/
+
 		/*
 		 * We may have taken a host interrupt in HYP mode (ie
 		 * while executing the guest). This interrupt is still
@@ -574,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();
 
 		/*
-		 * Back from guest
-		 *************************************************************/
+		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * that if a timer interrupt hits while running the guest we
+		 * account that tick as being spent in the guest.  We enable
+		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preempted we make sure ticks after that is not counted as
+		 * guest time.
+		 */
+		kvm_guest_exit();
+		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		preempt_enable();
+
 
 		kvm_timer_sync_hwstate(vcpu);
 		kvm_vgic_sync_hwstate(vcpu);

arch/arm/kvm/interrupts.S

@@ -170,13 +170,9 @@ __kvm_vcpu_return:
 	@ Don't trap coprocessor accesses for host kernel
 	set_hstr vmexit
 	set_hdcr vmexit
-	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore
 
 #ifdef CONFIG_VFPv3
-	@ Save floating point registers we if let guest use them.
-	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
-	bne	after_vfp_restore
-
 	@ Switch VFP/NEON hardware state to the host's
 	add	r7, vcpu, #VCPU_VFP_GUEST
 	store_vfp_state r7
@@ -188,6 +184,8 @@ after_vfp_restore:
 	@ Restore FPEXC_EN which we clobbered on entry
 	pop	{r2}
 	VFPFMXR FPEXC, r2
+#else
+after_vfp_restore:
 #endif
 
 	@ Reset Hyp-role
@@ -483,7 +481,7 @@ switch_to_guest_vfp:
 	push	{r3-r7}
 
 	@ NEON/VFP used.  Turn on VFP access.
-	set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11))
+	set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11))
 
 	@ Switch VFP/NEON hardware state to the guest's
 	add	r7, r0, #VCPU_VFP_HOST

arch/arm/kvm/interrupts_head.S

@@ -412,7 +412,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	add	r11, vcpu, #VCPU_VGIC_CPU
 
 	/* Save all interesting registers */
-	ldr	r3, [r2, #GICH_HCR]
 	ldr	r4, [r2, #GICH_VMCR]
 	ldr	r5, [r2, #GICH_MISR]
 	ldr	r6, [r2, #GICH_EISR0]
@@ -420,7 +419,6 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	ldr	r8, [r2, #GICH_ELRSR0]
 	ldr	r9, [r2, #GICH_ELRSR1]
 	ldr	r10, [r2, #GICH_APR]
-ARM_BE8(rev	r3, r3	)
 ARM_BE8(rev	r4, r4	)
 ARM_BE8(rev	r5, r5	)
 ARM_BE8(rev	r6, r6	)
@@ -429,7 +427,6 @@ ARM_BE8(rev	r8, r8	)
 ARM_BE8(rev	r9, r9	)
 ARM_BE8(rev	r10, r10	)
 
-	str	r3, [r11, #VGIC_V2_CPU_HCR]
 	str	r4, [r11, #VGIC_V2_CPU_VMCR]
 	str	r5, [r11, #VGIC_V2_CPU_MISR]
 #ifdef CONFIG_CPU_ENDIAN_BE8
@@ -591,8 +588,13 @@ ARM_BE8(rev	r6, r6  )
 .endm
 
 /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return
- * (hardware reset value is 0). Keep previous value in r2. */
-.macro set_hcptr operation, mask
+ * (hardware reset value is 0). Keep previous value in r2.
+ * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if
+ * VFP wasn't already enabled (always executed on vmtrap).
+ * If a label is specified with vmexit, it is branched to if VFP wasn't
+ * enabled.
+ */
+.macro set_hcptr operation, mask, label = none
 	mrc	p15, 4, r2, c1, c1, 2
 	ldr	r3, =\mask
 	.if \operation == vmentry
@@ -601,6 +603,17 @@ ARM_BE8(rev	r6, r6  )
 	bic	r3, r2, r3		@ Don't trap defined coproc-accesses
 	.endif
 	mcr	p15, 4, r3, c1, c1, 2
+	.if \operation != vmentry
+	.if \operation == vmexit
+	tst	r2, #(HCPTR_TCP(10) | HCPTR_TCP(11))
+	beq	1f
+	.endif
+	isb
+	.if \label != none
+	b	\label
+	.endif
+1:
+	.endif
 .endm
 
 /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return

arch/arm/kvm/mmu.c

@@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
 		 * work.  This is not used by the hardware and we have no
 		 * alignment requirement for this allocation.
 		 */
-		pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
-				       GFP_KERNEL | __GFP_ZERO);
+		pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t),
+				GFP_KERNEL | __GFP_ZERO);
 
 		if (!pgd) {
 			kvm_free_hwpgd(hwpgd);

arch/arm/kvm/psci.c

@@ -230,10 +230,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 	case PSCI_0_2_FN64_AFFINITY_INFO:
 		val = kvm_psci_vcpu_affinity_info(vcpu);
 		break;
-	case PSCI_0_2_FN_MIGRATE:
-	case PSCI_0_2_FN64_MIGRATE:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 		/*
 		 * Trusted OS is MP hence does not require migration
@@ -242,10 +238,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		 */
 		val = PSCI_0_2_TOS_MP;
 		break;
-	case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
-	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
-		val = PSCI_RET_NOT_SUPPORTED;
-		break;
 	case PSCI_0_2_FN_SYSTEM_OFF:
 		kvm_psci_system_off(vcpu);
 		/*
@@ -271,7 +263,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		ret = 0;
 		break;
 	default:
-		return -EINVAL;
+		val = PSCI_RET_NOT_SUPPORTED;
+		break;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;
@@ -291,12 +284,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 	case KVM_PSCI_FN_CPU_ON:
 		val = kvm_psci_vcpu_on(vcpu);
 		break;
-	case KVM_PSCI_FN_CPU_SUSPEND:
-	case KVM_PSCI_FN_MIGRATE:
+	default:
 		val = PSCI_RET_NOT_SUPPORTED;
 		break;
-	default:
-		return -EINVAL;
 	}
 
 	*vcpu_reg(vcpu, 0) = val;

arch/arm64/kvm/Kconfig

@@ -28,6 +28,7 @@ config KVM
 	select KVM_ARM_HOST
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select SRCU
+	select KVM_VFIO
 	select HAVE_KVM_EVENTFD
 	select HAVE_KVM_IRQFD
 	---help---

arch/arm64/kvm/Makefile

@@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm
 
 obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
 
-kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
 

arch/arm64/kvm/hyp.S

@@ -50,8 +50,8 @@
 	stp	x29, lr, [x3, #80]
 
 	mrs	x19, sp_el0
-	mrs	x20, elr_el2		// EL1 PC
-	mrs	x21, spsr_el2		// EL1 pstate
+	mrs	x20, elr_el2		// pc before entering el2
+	mrs	x21, spsr_el2		// pstate before entering el2
 
 	stp	x19, x20, [x3, #96]
 	str	x21, [x3, #112]
@@ -82,8 +82,8 @@
 	ldr	x21, [x3, #16]
 
 	msr	sp_el0, x19
-	msr	elr_el2, x20 				// EL1 PC
-	msr	spsr_el2, x21 				// EL1 pstate
+	msr	elr_el2, x20 		// pc on return from el2
+	msr	spsr_el2, x21 		// pstate on return from el2
 
 	add	x3, x2, #CPU_XREG_OFFSET(19)
 	ldp	x19, x20, [x3]

arch/arm64/kvm/vgic-v2-switch.S

@@ -47,7 +47,6 @@ __save_vgic_v2_state:
 	add	x3, x0, #VCPU_VGIC_CPU
 
 	/* Save all interesting registers */
-	ldr	w4, [x2, #GICH_HCR]
 	ldr	w5, [x2, #GICH_VMCR]
 	ldr	w6, [x2, #GICH_MISR]
 	ldr	w7, [x2, #GICH_EISR0]
@@ -55,7 +54,6 @@ __save_vgic_v2_state:
 	ldr	w9, [x2, #GICH_ELRSR0]
 	ldr	w10, [x2, #GICH_ELRSR1]
 	ldr	w11, [x2, #GICH_APR]
-CPU_BE(	rev	w4,  w4  )
 CPU_BE(	rev	w5,  w5  )
 CPU_BE(	rev	w6,  w6  )
 CPU_BE(	rev	w7,  w7  )
@@ -64,7 +62,6 @@ CPU_BE(	rev	w9,  w9  )
 CPU_BE(	rev	w10, w10 )
 CPU_BE(	rev	w11, w11 )
 
-	str	w4, [x3, #VGIC_V2_CPU_HCR]
 	str	w5, [x3, #VGIC_V2_CPU_VMCR]
 	str	w6, [x3, #VGIC_V2_CPU_MISR]
 CPU_LE(	str	w7, [x3, #VGIC_V2_CPU_EISR] )

arch/arm64/kvm/vgic-v3-switch.S

@@ -48,13 +48,11 @@
 	dsb	st
 
 	// Save all interesting registers
-	mrs_s	x4, ICH_HCR_EL2
 	mrs_s	x5, ICH_VMCR_EL2
 	mrs_s	x6, ICH_MISR_EL2
 	mrs_s	x7, ICH_EISR_EL2
 	mrs_s	x8, ICH_ELSR_EL2
 
-	str	w4, [x3, #VGIC_V3_CPU_HCR]
 	str	w5, [x3, #VGIC_V3_CPU_VMCR]
 	str	w6, [x3, #VGIC_V3_CPU_MISR]
 	str	w7, [x3, #VGIC_V3_CPU_EISR]

include/uapi/linux/kvm.h

@@ -897,7 +897,7 @@ struct kvm_xen_hvm_config {
  *
  * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
  * the irqfd to operate in resampling mode for level triggered interrupt
- * emlation.  See Documentation/virtual/kvm/api.txt.
+ * emulation.  See Documentation/virtual/kvm/api.txt.
  */
 #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 

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

@@ -76,8 +76,6 @@ static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu,
 	vgic_reg_access(mmio, &reg, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
 	if (mmio->is_write) {
-		if (reg & GICD_CTLR_ENABLE_SS_G0)
-			kvm_info("guest tried to enable unsupported Group0 interrupts\n");
 		vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1);
 		vgic_update_state(vcpu->kvm);
 		return true;
@@ -173,6 +171,32 @@ static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static bool handle_mmio_set_active_reg_dist(struct kvm_vcpu *vcpu,
+					    struct kvm_exit_mmio *mmio,
+					    phys_addr_t offset)
+{
+	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
+		return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
+						   vcpu->vcpu_id);
+
+	vgic_reg_access(mmio, NULL, offset,
+			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+	return false;
+}
+
+static bool handle_mmio_clear_active_reg_dist(struct kvm_vcpu *vcpu,
+					      struct kvm_exit_mmio *mmio,
+					      phys_addr_t offset)
+{
+	if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8))
+		return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
+						    vcpu->vcpu_id);
+
+	vgic_reg_access(mmio, NULL, offset,
+			ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+	return false;
+}
+
 static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu,
 					  struct kvm_exit_mmio *mmio,
 					  phys_addr_t offset)
@@ -428,13 +452,13 @@ static const struct vgic_io_range vgic_v3_dist_ranges[] = {
 		.base		= GICD_ISACTIVER,
 		.len		= 0x80,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_set_active_reg_dist,
 	},
 	{
 		.base		= GICD_ICACTIVER,
 		.len		= 0x80,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_clear_active_reg_dist,
 	},
 	{
 		.base		= GICD_IPRIORITYR,
@@ -561,6 +585,26 @@ static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu,
 				      ACCESS_WRITE_CLEARBIT);
 }
 
+static bool handle_mmio_set_active_reg_redist(struct kvm_vcpu *vcpu,
+					      struct kvm_exit_mmio *mmio,
+					      phys_addr_t offset)
+{
+	struct kvm_vcpu *redist_vcpu = mmio->private;
+
+	return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset,
+					  redist_vcpu->vcpu_id);
+}
+
+static bool handle_mmio_clear_active_reg_redist(struct kvm_vcpu *vcpu,
+						struct kvm_exit_mmio *mmio,
+						phys_addr_t offset)
+{
+	struct kvm_vcpu *redist_vcpu = mmio->private;
+
+	return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset,
+					     redist_vcpu->vcpu_id);
+}
+
 static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu,
 					       struct kvm_exit_mmio *mmio,
 					       phys_addr_t offset)
@@ -674,13 +718,13 @@ static const struct vgic_io_range vgic_redist_ranges[] = {
 		.base		= SGI_base(GICR_ISACTIVER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_set_active_reg_redist,
 	},
 	{
 		.base		= SGI_base(GICR_ICACTIVER0),
 		.len		= 0x04,
 		.bits_per_irq	= 1,
-		.handle_mmio	= handle_mmio_raz_wi,
+		.handle_mmio	= handle_mmio_clear_active_reg_redist,
 	},
 	{
 		.base		= SGI_base(GICR_IPRIORITYR0),

virt/kvm/arm/vgic.c

@@ -26,8 +26,6 @@
 #include <linux/of_irq.h>
 #include <linux/uaccess.h>
 
-#include <linux/irqchip/arm-gic.h>
-
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
@@ -1561,7 +1559,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			goto out;
 	}
 
-	if (irq_num >= kvm->arch.vgic.nr_irqs)
+	if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
 		return -EINVAL;
 
 	vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
@@ -2161,10 +2159,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id,
 
 	BUG_ON(!vgic_initialized(kvm));
 
-	if (spi > kvm->arch.vgic.nr_irqs)
-		return -EINVAL;
 	return kvm_vgic_inject_irq(kvm, 0, spi, level);
-
 }
 
 /* MSI not implemented yet */