diff options
author | Marc Zyngier <maz@kernel.org> | 2020-05-13 13:40:34 +0300 |
---|---|---|
committer | Marc Zyngier <maz@kernel.org> | 2020-05-16 17:03:59 +0300 |
commit | 9ed24f4b712b855dcf7be3025b75b051cb73a2b7 (patch) | |
tree | 2979a0b689ba9ba130504f12b0e7b4562f2fac22 /virt/kvm/arm/vgic | |
parent | 2ef96a5bb12be62ef75b5828c0aab838ebb29cb8 (diff) | |
download | linux-9ed24f4b712b855dcf7be3025b75b051cb73a2b7.tar.xz |
KVM: arm64: Move virt/kvm/arm to arch/arm64
Now that the 32bit KVM/arm host is a distant memory, let's move the
whole of the KVM/arm64 code into the arm64 tree.
As they said in the song: Welcome Home (Sanitarium).
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20200513104034.74741-1-maz@kernel.org
Diffstat (limited to 'virt/kvm/arm/vgic')
-rw-r--r-- | virt/kvm/arm/vgic/trace.h | 38 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-debug.c | 300 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-init.c | 556 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-irqfd.c | 141 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-its.c | 2783 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-kvm-device.c | 741 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio-v2.c | 550 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio-v3.c | 1063 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio.c | 1088 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-mmio.h | 227 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v2.c | 504 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v3.c | 693 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic-v4.c | 453 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic.c | 1011 | ||||
-rw-r--r-- | virt/kvm/arm/vgic/vgic.h | 321 |
15 files changed, 0 insertions, 10469 deletions
diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h deleted file mode 100644 index 4fd4f6db181b..000000000000 --- a/virt/kvm/arm/vgic/trace.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_VGIC_H - -#include <linux/tracepoint.h> - -#undef TRACE_SYSTEM -#define TRACE_SYSTEM kvm - -TRACE_EVENT(vgic_update_irq_pending, - TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level), - TP_ARGS(vcpu_id, irq, level), - - TP_STRUCT__entry( - __field( unsigned long, vcpu_id ) - __field( __u32, irq ) - __field( bool, level ) - ), - - TP_fast_assign( - __entry->vcpu_id = vcpu_id; - __entry->irq = irq; - __entry->level = level; - ), - - TP_printk("VCPU: %ld, IRQ %d, level: %d", - __entry->vcpu_id, __entry->irq, __entry->level) -); - -#endif /* _TRACE_VGIC_H */ - -#undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic -#undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE trace - -/* This part must be outside protection */ -#include <trace/define_trace.h> diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c deleted file mode 100644 index b13a9e3f99dd..000000000000 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ /dev/null @@ -1,300 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2016 Linaro - * Author: Christoffer Dall <christoffer.dall@linaro.org> - */ - -#include <linux/cpu.h> -#include <linux/debugfs.h> -#include <linux/interrupt.h> -#include <linux/kvm_host.h> -#include <linux/seq_file.h> -#include <kvm/arm_vgic.h> -#include <asm/kvm_mmu.h> -#include "vgic.h" - -/* - * Structure to control looping through the entire vgic state. We start at - * zero for each field and move upwards. So, if dist_id is 0 we print the - * distributor info. When dist_id is 1, we have already printed it and move - * on. - * - * When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and - * so on. - */ -struct vgic_state_iter { - int nr_cpus; - int nr_spis; - int nr_lpis; - int dist_id; - int vcpu_id; - int intid; - int lpi_idx; - u32 *lpi_array; -}; - -static void iter_next(struct vgic_state_iter *iter) -{ - if (iter->dist_id == 0) { - iter->dist_id++; - return; - } - - iter->intid++; - if (iter->intid == VGIC_NR_PRIVATE_IRQS && - ++iter->vcpu_id < iter->nr_cpus) - iter->intid = 0; - - if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS)) { - if (iter->lpi_idx < iter->nr_lpis) - iter->intid = iter->lpi_array[iter->lpi_idx]; - iter->lpi_idx++; - } -} - -static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter, - loff_t pos) -{ - int nr_cpus = atomic_read(&kvm->online_vcpus); - - memset(iter, 0, sizeof(*iter)); - - iter->nr_cpus = nr_cpus; - iter->nr_spis = kvm->arch.vgic.nr_spis; - if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - iter->nr_lpis = vgic_copy_lpi_list(kvm, NULL, &iter->lpi_array); - if (iter->nr_lpis < 0) - iter->nr_lpis = 0; - } - - /* Fast forward to the right position if needed */ - while (pos--) - iter_next(iter); -} - -static bool end_of_vgic(struct vgic_state_iter *iter) -{ - return iter->dist_id > 0 && - iter->vcpu_id == iter->nr_cpus && - iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && - iter->lpi_idx > iter->nr_lpis; -} - -static void *vgic_debug_start(struct seq_file *s, loff_t *pos) -{ - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter; - - mutex_lock(&kvm->lock); - iter = kvm->arch.vgic.iter; - if (iter) { - iter = ERR_PTR(-EBUSY); - goto out; - } - - iter = kmalloc(sizeof(*iter), GFP_KERNEL); - if (!iter) { - iter = ERR_PTR(-ENOMEM); - goto out; - } - - iter_init(kvm, iter, *pos); - kvm->arch.vgic.iter = iter; - - if (end_of_vgic(iter)) - iter = NULL; -out: - mutex_unlock(&kvm->lock); - return iter; -} - -static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) -{ - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter = kvm->arch.vgic.iter; - - ++*pos; - iter_next(iter); - if (end_of_vgic(iter)) - iter = NULL; - return iter; -} - -static void vgic_debug_stop(struct seq_file *s, void *v) -{ - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter; - - /* - * If the seq file wasn't properly opened, there's nothing to clearn - * up. - */ - if (IS_ERR(v)) - return; - - mutex_lock(&kvm->lock); - iter = kvm->arch.vgic.iter; - kfree(iter->lpi_array); - kfree(iter); - kvm->arch.vgic.iter = NULL; - mutex_unlock(&kvm->lock); -} - -static void print_dist_state(struct seq_file *s, struct vgic_dist *dist) -{ - bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3; - - seq_printf(s, "Distributor\n"); - seq_printf(s, "===========\n"); - seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2"); - seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis); - if (v3) - seq_printf(s, "nr_lpis:\t%d\n", dist->lpi_list_count); - seq_printf(s, "enabled:\t%d\n", dist->enabled); - seq_printf(s, "\n"); - - seq_printf(s, "P=pending_latch, L=line_level, A=active\n"); - seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n"); - seq_printf(s, "G=group\n"); -} - -static void print_header(struct seq_file *s, struct vgic_irq *irq, - struct kvm_vcpu *vcpu) -{ - int id = 0; - char *hdr = "SPI "; - - if (vcpu) { - hdr = "VCPU"; - id = vcpu->vcpu_id; - } - - seq_printf(s, "\n"); - seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id); - seq_printf(s, "----------------------------------------------------------------\n"); -} - -static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, - struct kvm_vcpu *vcpu) -{ - char *type; - bool pending; - - if (irq->intid < VGIC_NR_SGIS) - type = "SGI"; - else if (irq->intid < VGIC_NR_PRIVATE_IRQS) - type = "PPI"; - else if (irq->intid < VGIC_MAX_SPI) - type = "SPI"; - else - type = "LPI"; - - if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) - print_header(s, irq, vcpu); - - pending = irq->pending_latch; - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - int err; - - err = irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &pending); - WARN_ON_ONCE(err); - } - - seq_printf(s, " %s %4d " - " %2d " - "%d%d%d%d%d%d%d " - "%8d " - "%8x " - " %2x " - "%3d " - " %2d " - "\n", - type, irq->intid, - (irq->target_vcpu) ? irq->target_vcpu->vcpu_id : -1, - pending, - irq->line_level, - irq->active, - irq->enabled, - irq->hw, - irq->config == VGIC_CONFIG_LEVEL, - irq->group, - irq->hwintid, - irq->mpidr, - irq->source, - irq->priority, - (irq->vcpu) ? irq->vcpu->vcpu_id : -1); -} - -static int vgic_debug_show(struct seq_file *s, void *v) -{ - struct kvm *kvm = (struct kvm *)s->private; - struct vgic_state_iter *iter = (struct vgic_state_iter *)v; - struct vgic_irq *irq; - struct kvm_vcpu *vcpu = NULL; - unsigned long flags; - - if (iter->dist_id == 0) { - print_dist_state(s, &kvm->arch.vgic); - return 0; - } - - if (!kvm->arch.vgic.initialized) - return 0; - - if (iter->vcpu_id < iter->nr_cpus) - vcpu = kvm_get_vcpu(kvm, iter->vcpu_id); - - irq = vgic_get_irq(kvm, vcpu, iter->intid); - if (!irq) { - seq_printf(s, " LPI %4d freed\n", iter->intid); - return 0; - } - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - print_irq_state(s, irq, vcpu); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(kvm, irq); - return 0; -} - -static const struct seq_operations vgic_debug_seq_ops = { - .start = vgic_debug_start, - .next = vgic_debug_next, - .stop = vgic_debug_stop, - .show = vgic_debug_show -}; - -static int debug_open(struct inode *inode, struct file *file) -{ - int ret; - ret = seq_open(file, &vgic_debug_seq_ops); - if (!ret) { - struct seq_file *seq; - /* seq_open will have modified file->private_data */ - seq = file->private_data; - seq->private = inode->i_private; - } - - return ret; -}; - -static const struct file_operations vgic_debug_fops = { - .owner = THIS_MODULE, - .open = debug_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release -}; - -void vgic_debug_init(struct kvm *kvm) -{ - debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, - &vgic_debug_fops); -} - -void vgic_debug_destroy(struct kvm *kvm) -{ -} diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c deleted file mode 100644 index 32e32d67a127..000000000000 --- a/virt/kvm/arm/vgic/vgic-init.c +++ /dev/null @@ -1,556 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ - -#include <linux/uaccess.h> -#include <linux/interrupt.h> -#include <linux/cpu.h> -#include <linux/kvm_host.h> -#include <kvm/arm_vgic.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_mmu.h> -#include "vgic.h" - -/* - * Initialization rules: there are multiple stages to the vgic - * initialization, both for the distributor and the CPU interfaces. The basic - * idea is that even though the VGIC is not functional or not requested from - * user space, the critical path of the run loop can still call VGIC functions - * that just won't do anything, without them having to check additional - * initialization flags to ensure they don't look at uninitialized data - * structures. - * - * Distributor: - * - * - kvm_vgic_early_init(): initialization of static data that doesn't - * depend on any sizing information or emulation type. No allocation - * is allowed there. - * - * - vgic_init(): allocation and initialization of the generic data - * structures that depend on sizing information (number of CPUs, - * number of interrupts). Also initializes the vcpu specific data - * structures. Can be executed lazily for GICv2. - * - * CPU Interface: - * - * - kvm_vgic_vcpu_init(): initialization of static data that - * doesn't depend on any sizing information or emulation type. No - * allocation is allowed there. - */ - -/* EARLY INIT */ - -/** - * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures - * @kvm: The VM whose VGIC districutor should be initialized - * - * Only do initialization of static structures that don't require any - * allocation or sizing information from userspace. vgic_init() called - * kvm_vgic_dist_init() which takes care of the rest. - */ -void kvm_vgic_early_init(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - - INIT_LIST_HEAD(&dist->lpi_list_head); - INIT_LIST_HEAD(&dist->lpi_translation_cache); - raw_spin_lock_init(&dist->lpi_list_lock); -} - -/* CREATION */ - -/** - * kvm_vgic_create: triggered by the instantiation of the VGIC device by - * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) - * or through the generic KVM_CREATE_DEVICE API ioctl. - * irqchip_in_kernel() tells you if this function succeeded or not. - * @kvm: kvm struct pointer - * @type: KVM_DEV_TYPE_ARM_VGIC_V[23] - */ -int kvm_vgic_create(struct kvm *kvm, u32 type) -{ - int i, ret; - struct kvm_vcpu *vcpu; - - if (irqchip_in_kernel(kvm)) - return -EEXIST; - - /* - * This function is also called by the KVM_CREATE_IRQCHIP handler, - * which had no chance yet to check the availability of the GICv2 - * emulation. So check this here again. KVM_CREATE_DEVICE does - * the proper checks already. - */ - if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && - !kvm_vgic_global_state.can_emulate_gicv2) - return -ENODEV; - - ret = -EBUSY; - if (!lock_all_vcpus(kvm)) - return ret; - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu->arch.has_run_once) - goto out_unlock; - } - ret = 0; - - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) - kvm->arch.max_vcpus = VGIC_V2_MAX_CPUS; - else - kvm->arch.max_vcpus = VGIC_V3_MAX_CPUS; - - if (atomic_read(&kvm->online_vcpus) > kvm->arch.max_vcpus) { - ret = -E2BIG; - goto out_unlock; - } - - kvm->arch.vgic.in_kernel = true; - kvm->arch.vgic.vgic_model = type; - - kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - - if (type == KVM_DEV_TYPE_ARM_VGIC_V2) - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - else - INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); - -out_unlock: - unlock_all_vcpus(kvm); - return ret; -} - -/* INIT/DESTROY */ - -/** - * kvm_vgic_dist_init: initialize the dist data structures - * @kvm: kvm struct pointer - * @nr_spis: number of spis, frozen by caller - */ -static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0); - int i; - - dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL); - if (!dist->spis) - return -ENOMEM; - - /* - * In the following code we do not take the irq struct lock since - * no other action on irq structs can happen while the VGIC is - * not initialized yet: - * If someone wants to inject an interrupt or does a MMIO access, we - * require prior initialization in case of a virtual GICv3 or trigger - * initialization when using a virtual GICv2. - */ - for (i = 0; i < nr_spis; i++) { - struct vgic_irq *irq = &dist->spis[i]; - - irq->intid = i + VGIC_NR_PRIVATE_IRQS; - INIT_LIST_HEAD(&irq->ap_list); - raw_spin_lock_init(&irq->irq_lock); - irq->vcpu = NULL; - irq->target_vcpu = vcpu0; - kref_init(&irq->refcount); - switch (dist->vgic_model) { - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->targets = 0; - irq->group = 0; - break; - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->mpidr = 0; - irq->group = 1; - break; - default: - kfree(dist->spis); - dist->spis = NULL; - return -EINVAL; - } - } - return 0; -} - -/** - * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data - * structures and register VCPU-specific KVM iodevs - * - * @vcpu: pointer to the VCPU being created and initialized - * - * Only do initialization, but do not actually enable the - * VGIC CPU interface - */ -int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - int ret = 0; - int i; - - vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; - - INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - raw_spin_lock_init(&vgic_cpu->ap_list_lock); - atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); - - /* - * Enable and configure all SGIs to be edge-triggered and - * configure all PPIs as level-triggered. - */ - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; - - INIT_LIST_HEAD(&irq->ap_list); - raw_spin_lock_init(&irq->irq_lock); - irq->intid = i; - irq->vcpu = NULL; - irq->target_vcpu = vcpu; - kref_init(&irq->refcount); - if (vgic_irq_is_sgi(i)) { - /* SGIs */ - irq->enabled = 1; - irq->config = VGIC_CONFIG_EDGE; - } else { - /* PPIs */ - irq->config = VGIC_CONFIG_LEVEL; - } - } - - if (!irqchip_in_kernel(vcpu->kvm)) - return 0; - - /* - * If we are creating a VCPU with a GICv3 we must also register the - * KVM io device for the redistributor that belongs to this VCPU. - */ - if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - mutex_lock(&vcpu->kvm->lock); - ret = vgic_register_redist_iodev(vcpu); - mutex_unlock(&vcpu->kvm->lock); - } - return ret; -} - -static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_enable(vcpu); - else - vgic_v3_enable(vcpu); -} - -/* - * vgic_init: allocates and initializes dist and vcpu data structures - * depending on two dimensioning parameters: - * - the number of spis - * - the number of vcpus - * The function is generally called when nr_spis has been explicitly set - * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. - * vgic_initialized() returns true when this function has succeeded. - * Must be called with kvm->lock held! - */ -int vgic_init(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int ret = 0, i, idx; - - if (vgic_initialized(kvm)) - return 0; - - /* Are we also in the middle of creating a VCPU? */ - if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) - return -EBUSY; - - /* freeze the number of spis */ - if (!dist->nr_spis) - dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; - - ret = kvm_vgic_dist_init(kvm, dist->nr_spis); - if (ret) - goto out; - - /* Initialize groups on CPUs created before the VGIC type was known */ - kvm_for_each_vcpu(idx, vcpu, kvm) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; - switch (dist->vgic_model) { - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->group = 1; - irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - break; - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->group = 0; - irq->targets = 1U << idx; - break; - default: - ret = -EINVAL; - goto out; - } - } - } - - if (vgic_has_its(kvm)) - vgic_lpi_translation_cache_init(kvm); - - /* - * If we have GICv4.1 enabled, unconditionnaly request enable the - * v4 support so that we get HW-accelerated vSGIs. Otherwise, only - * enable it if we present a virtual ITS to the guest. - */ - if (vgic_supports_direct_msis(kvm)) { - ret = vgic_v4_init(kvm); - if (ret) - goto out; - } - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_enable(vcpu); - - ret = kvm_vgic_setup_default_irq_routing(kvm); - if (ret) - goto out; - - vgic_debug_init(kvm); - - dist->implementation_rev = 2; - dist->initialized = true; - -out: - return ret; -} - -static void kvm_vgic_dist_destroy(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_redist_region *rdreg, *next; - - dist->ready = false; - dist->initialized = false; - - kfree(dist->spis); - dist->spis = NULL; - dist->nr_spis = 0; - - if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) { - list_del(&rdreg->list); - kfree(rdreg); - } - INIT_LIST_HEAD(&dist->rd_regions); - } - - if (vgic_has_its(kvm)) - vgic_lpi_translation_cache_destroy(kvm); - - if (vgic_supports_direct_msis(kvm)) - vgic_v4_teardown(kvm); -} - -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - /* - * Retire all pending LPIs on this vcpu anyway as we're - * going to destroy it. - */ - vgic_flush_pending_lpis(vcpu); - - INIT_LIST_HEAD(&vgic_cpu->ap_list_head); -} - -/* To be called with kvm->lock held */ -static void __kvm_vgic_destroy(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - int i; - - vgic_debug_destroy(kvm); - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_destroy(vcpu); - - kvm_vgic_dist_destroy(kvm); -} - -void kvm_vgic_destroy(struct kvm *kvm) -{ - mutex_lock(&kvm->lock); - __kvm_vgic_destroy(kvm); - mutex_unlock(&kvm->lock); -} - -/** - * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest - * is a GICv2. A GICv3 must be explicitly initialized by the guest using the - * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. - * @kvm: kvm struct pointer - */ -int vgic_lazy_init(struct kvm *kvm) -{ - int ret = 0; - - if (unlikely(!vgic_initialized(kvm))) { - /* - * We only provide the automatic initialization of the VGIC - * for the legacy case of a GICv2. Any other type must - * be explicitly initialized once setup with the respective - * KVM device call. - */ - if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) - return -EBUSY; - - mutex_lock(&kvm->lock); - ret = vgic_init(kvm); - mutex_unlock(&kvm->lock); - } - - return ret; -} - -/* RESOURCE MAPPING */ - -/** - * Map the MMIO regions depending on the VGIC model exposed to the guest - * called on the first VCPU run. - * Also map the virtual CPU interface into the VM. - * v2/v3 derivatives call vgic_init if not already done. - * vgic_ready() returns true if this function has succeeded. - * @kvm: kvm struct pointer - */ -int kvm_vgic_map_resources(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - int ret = 0; - - mutex_lock(&kvm->lock); - if (!irqchip_in_kernel(kvm)) - goto out; - - if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) - ret = vgic_v2_map_resources(kvm); - else - ret = vgic_v3_map_resources(kvm); - - if (ret) - __kvm_vgic_destroy(kvm); - -out: - mutex_unlock(&kvm->lock); - return ret; -} - -/* GENERIC PROBE */ - -static int vgic_init_cpu_starting(unsigned int cpu) -{ - enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); - return 0; -} - - -static int vgic_init_cpu_dying(unsigned int cpu) -{ - disable_percpu_irq(kvm_vgic_global_state.maint_irq); - return 0; -} - -static irqreturn_t vgic_maintenance_handler(int irq, void *data) -{ - /* - * We cannot rely on the vgic maintenance interrupt to be - * delivered synchronously. This means we can only use it to - * exit the VM, and we perform the handling of EOIed - * interrupts on the exit path (see vgic_fold_lr_state). - */ - return IRQ_HANDLED; -} - -/** - * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware - * - * For a specific CPU, initialize the GIC VE hardware. - */ -void kvm_vgic_init_cpu_hardware(void) -{ - BUG_ON(preemptible()); - - /* - * We want to make sure the list registers start out clear so that we - * only have the program the used registers. - */ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_init_lrs(); - else - kvm_call_hyp(__vgic_v3_init_lrs); -} - -/** - * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable - * according to the host GIC model. Accordingly calls either - * vgic_v2/v3_probe which registers the KVM_DEVICE that can be - * instantiated by a guest later on . - */ -int kvm_vgic_hyp_init(void) -{ - const struct gic_kvm_info *gic_kvm_info; - int ret; - - gic_kvm_info = gic_get_kvm_info(); - if (!gic_kvm_info) - return -ENODEV; - - if (!gic_kvm_info->maint_irq) { - kvm_err("No vgic maintenance irq\n"); - return -ENXIO; - } - - switch (gic_kvm_info->type) { - case GIC_V2: - ret = vgic_v2_probe(gic_kvm_info); - break; - case GIC_V3: - ret = vgic_v3_probe(gic_kvm_info); - if (!ret) { - static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif); - kvm_info("GIC system register CPU interface enabled\n"); - } - break; - default: - ret = -ENODEV; - } - - if (ret) - return ret; - - kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq; - ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, - vgic_maintenance_handler, - "vgic", kvm_get_running_vcpus()); - if (ret) { - kvm_err("Cannot register interrupt %d\n", - kvm_vgic_global_state.maint_irq); - return ret; - } - - ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - "kvm/arm/vgic:starting", - vgic_init_cpu_starting, vgic_init_cpu_dying); - if (ret) { - kvm_err("Cannot register vgic CPU notifier\n"); - goto out_free_irq; - } - - kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); - return 0; - -out_free_irq: - free_percpu_irq(kvm_vgic_global_state.maint_irq, - kvm_get_running_vcpus()); - return ret; -} diff --git a/virt/kvm/arm/vgic/vgic-irqfd.c b/virt/kvm/arm/vgic/vgic-irqfd.c deleted file mode 100644 index d8cdfea5cc96..000000000000 --- a/virt/kvm/arm/vgic/vgic-irqfd.c +++ /dev/null @@ -1,141 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ - -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <trace/events/kvm.h> -#include <kvm/arm_vgic.h> -#include "vgic.h" - -/** - * vgic_irqfd_set_irq: inject the IRQ corresponding to the - * irqchip routing entry - * - * This is the entry point for irqfd IRQ injection - */ -static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, - int level, bool line_status) -{ - unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS; - - if (!vgic_valid_spi(kvm, spi_id)) - return -EINVAL; - return kvm_vgic_inject_irq(kvm, 0, spi_id, level, NULL); -} - -/** - * kvm_set_routing_entry: populate a kvm routing entry - * from a user routing entry - * - * @kvm: the VM this entry is applied to - * @e: kvm kernel routing entry handle - * @ue: user api routing entry handle - * return 0 on success, -EINVAL on errors. - */ -int kvm_set_routing_entry(struct kvm *kvm, - struct kvm_kernel_irq_routing_entry *e, - const struct kvm_irq_routing_entry *ue) -{ - int r = -EINVAL; - - switch (ue->type) { - case KVM_IRQ_ROUTING_IRQCHIP: - e->set = vgic_irqfd_set_irq; - e->irqchip.irqchip = ue->u.irqchip.irqchip; - e->irqchip.pin = ue->u.irqchip.pin; - if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || - (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) - goto out; - break; - case KVM_IRQ_ROUTING_MSI: - e->set = kvm_set_msi; - e->msi.address_lo = ue->u.msi.address_lo; - e->msi.address_hi = ue->u.msi.address_hi; - e->msi.data = ue->u.msi.data; - e->msi.flags = ue->flags; - e->msi.devid = ue->u.msi.devid; - break; - default: - goto out; - } - r = 0; -out: - return r; -} - -static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm_msi *msi) -{ - msi->address_lo = e->msi.address_lo; - msi->address_hi = e->msi.address_hi; - msi->data = e->msi.data; - msi->flags = e->msi.flags; - msi->devid = e->msi.devid; -} -/** - * kvm_set_msi: inject the MSI corresponding to the - * MSI routing entry - * - * This is the entry point for irqfd MSI injection - * and userspace MSI injection. - */ -int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, - int level, bool line_status) -{ - struct kvm_msi msi; - - if (!vgic_has_its(kvm)) - return -ENODEV; - - if (!level) - return -1; - - kvm_populate_msi(e, &msi); - return vgic_its_inject_msi(kvm, &msi); -} - -/** - * kvm_arch_set_irq_inatomic: fast-path for irqfd injection - * - * Currently only direct MSI injection is supported. - */ -int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int irq_source_id, int level, - bool line_status) -{ - if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) { - struct kvm_msi msi; - - kvm_populate_msi(e, &msi); - if (!vgic_its_inject_cached_translation(kvm, &msi)) - return 0; - } - - return -EWOULDBLOCK; -} - -int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) -{ - struct kvm_irq_routing_entry *entries; - struct vgic_dist *dist = &kvm->arch.vgic; - u32 nr = dist->nr_spis; - int i, ret; - - entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL); - if (!entries) - return -ENOMEM; - - for (i = 0; i < nr; i++) { - entries[i].gsi = i; - entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; - entries[i].u.irqchip.irqchip = 0; - entries[i].u.irqchip.pin = i; - } - ret = kvm_set_irq_routing(kvm, entries, nr, 0); - kfree(entries); - return ret; -} diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c deleted file mode 100644 index c012a52b19f5..000000000000 --- a/virt/kvm/arm/vgic/vgic-its.c +++ /dev/null @@ -1,2783 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * GICv3 ITS emulation - * - * Copyright (C) 2015,2016 ARM Ltd. - * Author: Andre Przywara <andre.przywara@arm.com> - */ - -#include <linux/cpu.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/interrupt.h> -#include <linux/list.h> -#include <linux/uaccess.h> -#include <linux/list_sort.h> - -#include <linux/irqchip/arm-gic-v3.h> - -#include <asm/kvm_emulate.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> - -#include "vgic.h" -#include "vgic-mmio.h" - -static int vgic_its_save_tables_v0(struct vgic_its *its); -static int vgic_its_restore_tables_v0(struct vgic_its *its); -static int vgic_its_commit_v0(struct vgic_its *its); -static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, - struct kvm_vcpu *filter_vcpu, bool needs_inv); - -/* - * Creates a new (reference to a) struct vgic_irq for a given LPI. - * If this LPI is already mapped on another ITS, we increase its refcount - * and return a pointer to the existing structure. - * If this is a "new" LPI, we allocate and initialize a new struct vgic_irq. - * This function returns a pointer to the _unlocked_ structure. - */ -static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, - struct kvm_vcpu *vcpu) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; - unsigned long flags; - int ret; - - /* In this case there is no put, since we keep the reference. */ - if (irq) - return irq; - - irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); - if (!irq) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(&irq->lpi_list); - INIT_LIST_HEAD(&irq->ap_list); - raw_spin_lock_init(&irq->irq_lock); - - irq->config = VGIC_CONFIG_EDGE; - kref_init(&irq->refcount); - irq->intid = intid; - irq->target_vcpu = vcpu; - irq->group = 1; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - - /* - * There could be a race with another vgic_add_lpi(), so we need to - * check that we don't add a second list entry with the same LPI. - */ - list_for_each_entry(oldirq, &dist->lpi_list_head, lpi_list) { - if (oldirq->intid != intid) - continue; - - /* Someone was faster with adding this LPI, lets use that. */ - kfree(irq); - irq = oldirq; - - /* - * This increases the refcount, the caller is expected to - * call vgic_put_irq() on the returned pointer once it's - * finished with the IRQ. - */ - vgic_get_irq_kref(irq); - - goto out_unlock; - } - - list_add_tail(&irq->lpi_list, &dist->lpi_list_head); - dist->lpi_list_count++; - -out_unlock: - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); - - /* - * We "cache" the configuration table entries in our struct vgic_irq's. - * However we only have those structs for mapped IRQs, so we read in - * the respective config data from memory here upon mapping the LPI. - * - * Should any of these fail, behave as if we couldn't create the LPI - * by dropping the refcount and returning the error. - */ - ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) { - vgic_put_irq(kvm, irq); - return ERR_PTR(ret); - } - - ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) { - vgic_put_irq(kvm, irq); - return ERR_PTR(ret); - } - - return irq; -} - -struct its_device { - struct list_head dev_list; - - /* the head for the list of ITTEs */ - struct list_head itt_head; - u32 num_eventid_bits; - gpa_t itt_addr; - u32 device_id; -}; - -#define COLLECTION_NOT_MAPPED ((u32)~0) - -struct its_collection { - struct list_head coll_list; - - u32 collection_id; - u32 target_addr; -}; - -#define its_is_collection_mapped(coll) ((coll) && \ - ((coll)->target_addr != COLLECTION_NOT_MAPPED)) - -struct its_ite { - struct list_head ite_list; - - struct vgic_irq *irq; - struct its_collection *collection; - u32 event_id; -}; - -struct vgic_translation_cache_entry { - struct list_head entry; - phys_addr_t db; - u32 devid; - u32 eventid; - struct vgic_irq *irq; -}; - -/** - * struct vgic_its_abi - ITS abi ops and settings - * @cte_esz: collection table entry size - * @dte_esz: device table entry size - * @ite_esz: interrupt translation table entry size - * @save tables: save the ITS tables into guest RAM - * @restore_tables: restore the ITS internal structs from tables - * stored in guest RAM - * @commit: initialize the registers which expose the ABI settings, - * especially the entry sizes - */ -struct vgic_its_abi { - int cte_esz; - int dte_esz; - int ite_esz; - int (*save_tables)(struct vgic_its *its); - int (*restore_tables)(struct vgic_its *its); - int (*commit)(struct vgic_its *its); -}; - -#define ABI_0_ESZ 8 -#define ESZ_MAX ABI_0_ESZ - -static const struct vgic_its_abi its_table_abi_versions[] = { - [0] = { - .cte_esz = ABI_0_ESZ, - .dte_esz = ABI_0_ESZ, - .ite_esz = ABI_0_ESZ, - .save_tables = vgic_its_save_tables_v0, - .restore_tables = vgic_its_restore_tables_v0, - .commit = vgic_its_commit_v0, - }, -}; - -#define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions) - -inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its) -{ - return &its_table_abi_versions[its->abi_rev]; -} - -static int vgic_its_set_abi(struct vgic_its *its, u32 rev) -{ - const struct vgic_its_abi *abi; - - its->abi_rev = rev; - abi = vgic_its_get_abi(its); - return abi->commit(its); -} - -/* - * Find and returns a device in the device table for an ITS. - * Must be called with the its_lock mutex held. - */ -static struct its_device *find_its_device(struct vgic_its *its, u32 device_id) -{ - struct its_device *device; - - list_for_each_entry(device, &its->device_list, dev_list) - if (device_id == device->device_id) - return device; - - return NULL; -} - -/* - * Find and returns an interrupt translation table entry (ITTE) for a given - * Device ID/Event ID pair on an ITS. - * Must be called with the its_lock mutex held. - */ -static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, - u32 event_id) -{ - struct its_device *device; - struct its_ite *ite; - - device = find_its_device(its, device_id); - if (device == NULL) - return NULL; - - list_for_each_entry(ite, &device->itt_head, ite_list) - if (ite->event_id == event_id) - return ite; - - return NULL; -} - -/* To be used as an iterator this macro misses the enclosing parentheses */ -#define for_each_lpi_its(dev, ite, its) \ - list_for_each_entry(dev, &(its)->device_list, dev_list) \ - list_for_each_entry(ite, &(dev)->itt_head, ite_list) - -#define GIC_LPI_OFFSET 8192 - -#define VITS_TYPER_IDBITS 16 -#define VITS_TYPER_DEVBITS 16 -#define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1) -#define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1) - -/* - * Finds and returns a collection in the ITS collection table. - * Must be called with the its_lock mutex held. - */ -static struct its_collection *find_collection(struct vgic_its *its, int coll_id) -{ - struct its_collection *collection; - - list_for_each_entry(collection, &its->collection_list, coll_list) { - if (coll_id == collection->collection_id) - return collection; - } - - return NULL; -} - -#define LPI_PROP_ENABLE_BIT(p) ((p) & LPI_PROP_ENABLED) -#define LPI_PROP_PRIORITY(p) ((p) & 0xfc) - -/* - * Reads the configuration data for a given LPI from guest memory and - * updates the fields in struct vgic_irq. - * If filter_vcpu is not NULL, applies only if the IRQ is targeting this - * VCPU. Unconditionally applies if filter_vcpu is NULL. - */ -static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, - struct kvm_vcpu *filter_vcpu, bool needs_inv) -{ - u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser); - u8 prop; - int ret; - unsigned long flags; - - ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, - &prop, 1); - - if (ret) - return ret; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { - irq->priority = LPI_PROP_PRIORITY(prop); - irq->enabled = LPI_PROP_ENABLE_BIT(prop); - - if (!irq->hw) { - vgic_queue_irq_unlock(kvm, irq, flags); - return 0; - } - } - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - if (irq->hw) - return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); - - return 0; -} - -/* - * Create a snapshot of the current LPIs targeting @vcpu, so that we can - * enumerate those LPIs without holding any lock. - * Returns their number and puts the kmalloc'ed array into intid_ptr. - */ -int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_irq *irq; - unsigned long flags; - u32 *intids; - int irq_count, i = 0; - - /* - * There is an obvious race between allocating the array and LPIs - * being mapped/unmapped. If we ended up here as a result of a - * command, we're safe (locks are held, preventing another - * command). If coming from another path (such as enabling LPIs), - * we must be careful not to overrun the array. - */ - irq_count = READ_ONCE(dist->lpi_list_count); - intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL); - if (!intids) - return -ENOMEM; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { - if (i == irq_count) - break; - /* We don't need to "get" the IRQ, as we hold the list lock. */ - if (vcpu && irq->target_vcpu != vcpu) - continue; - intids[i++] = irq->intid; - } - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); - - *intid_ptr = intids; - return i; -} - -static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) -{ - int ret = 0; - unsigned long flags; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->target_vcpu = vcpu; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - if (irq->hw) { - struct its_vlpi_map map; - - ret = its_get_vlpi(irq->host_irq, &map); - if (ret) - return ret; - - if (map.vpe) - atomic_dec(&map.vpe->vlpi_count); - map.vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; - atomic_inc(&map.vpe->vlpi_count); - - ret = its_map_vlpi(irq->host_irq, &map); - } - - return ret; -} - -/* - * Promotes the ITS view of affinity of an ITTE (which redistributor this LPI - * is targeting) to the VGIC's view, which deals with target VCPUs. - * Needs to be called whenever either the collection for a LPIs has - * changed or the collection itself got retargeted. - */ -static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite) -{ - struct kvm_vcpu *vcpu; - - if (!its_is_collection_mapped(ite->collection)) - return; - - vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr); - update_affinity(ite->irq, vcpu); -} - -/* - * Updates the target VCPU for every LPI targeting this collection. - * Must be called with the its_lock mutex held. - */ -static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its, - struct its_collection *coll) -{ - struct its_device *device; - struct its_ite *ite; - - for_each_lpi_its(device, ite, its) { - if (!ite->collection || coll != ite->collection) - continue; - - update_affinity_ite(kvm, ite); - } -} - -static u32 max_lpis_propbaser(u64 propbaser) -{ - int nr_idbits = (propbaser & 0x1f) + 1; - - return 1U << min(nr_idbits, INTERRUPT_ID_BITS_ITS); -} - -/* - * Sync the pending table pending bit of LPIs targeting @vcpu - * with our own data structures. This relies on the LPI being - * mapped before. - */ -static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) -{ - gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); - struct vgic_irq *irq; - int last_byte_offset = -1; - int ret = 0; - u32 *intids; - int nr_irqs, i; - unsigned long flags; - u8 pendmask; - - nr_irqs = vgic_copy_lpi_list(vcpu->kvm, vcpu, &intids); - if (nr_irqs < 0) - return nr_irqs; - - for (i = 0; i < nr_irqs; i++) { - int byte_offset, bit_nr; - - byte_offset = intids[i] / BITS_PER_BYTE; - bit_nr = intids[i] % BITS_PER_BYTE; - - /* - * For contiguously allocated LPIs chances are we just read - * this very same byte in the last iteration. Reuse that. - */ - if (byte_offset != last_byte_offset) { - ret = kvm_read_guest_lock(vcpu->kvm, - pendbase + byte_offset, - &pendmask, 1); - if (ret) { - kfree(intids); - return ret; - } - last_byte_offset = byte_offset; - } - - irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = pendmask & (1U << bit_nr); - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - vgic_put_irq(vcpu->kvm, irq); - } - - kfree(intids); - - return ret; -} - -static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 reg = GITS_TYPER_PLPIS; - - /* - * We use linear CPU numbers for redistributor addressing, - * so GITS_TYPER.PTA is 0. - * Also we force all PROPBASER registers to be the same, so - * CommonLPIAff is 0 as well. - * To avoid memory waste in the guest, we keep the number of IDBits and - * DevBits low - as least for the time being. - */ - reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT; - reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT; - reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT; - - return extract_bytes(reg, addr & 7, len); -} - -static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - u32 val; - - val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK; - val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM; - return val; -} - -static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 rev = GITS_IIDR_REV(val); - - if (rev >= NR_ITS_ABIS) - return -EINVAL; - return vgic_its_set_abi(its, rev); -} - -static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - switch (addr & 0xffff) { - case GITS_PIDR0: - return 0x92; /* part number, bits[7:0] */ - case GITS_PIDR1: - return 0xb4; /* part number, bits[11:8] */ - case GITS_PIDR2: - return GIC_PIDR2_ARCH_GICv3 | 0x0b; - case GITS_PIDR4: - return 0x40; /* This is a 64K software visible page */ - /* The following are the ID registers for (any) GIC. */ - case GITS_CIDR0: - return 0x0d; - case GITS_CIDR1: - return 0xf0; - case GITS_CIDR2: - return 0x05; - case GITS_CIDR3: - return 0xb1; - } - - return 0; -} - -static struct vgic_irq *__vgic_its_check_cache(struct vgic_dist *dist, - phys_addr_t db, - u32 devid, u32 eventid) -{ - struct vgic_translation_cache_entry *cte; - - list_for_each_entry(cte, &dist->lpi_translation_cache, entry) { - /* - * If we hit a NULL entry, there is nothing after this - * point. - */ - if (!cte->irq) - break; - - if (cte->db != db || cte->devid != devid || - cte->eventid != eventid) - continue; - - /* - * Move this entry to the head, as it is the most - * recently used. - */ - if (!list_is_first(&cte->entry, &dist->lpi_translation_cache)) - list_move(&cte->entry, &dist->lpi_translation_cache); - - return cte->irq; - } - - return NULL; -} - -static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db, - u32 devid, u32 eventid) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_irq *irq; - unsigned long flags; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - irq = __vgic_its_check_cache(dist, db, devid, eventid); - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); - - return irq; -} - -static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid, - struct vgic_irq *irq) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_translation_cache_entry *cte; - unsigned long flags; - phys_addr_t db; - - /* Do not cache a directly injected interrupt */ - if (irq->hw) - return; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - - if (unlikely(list_empty(&dist->lpi_translation_cache))) - goto out; - - /* - * We could have raced with another CPU caching the same - * translation behind our back, so let's check it is not in - * already - */ - db = its->vgic_its_base + GITS_TRANSLATER; - if (__vgic_its_check_cache(dist, db, devid, eventid)) - goto out; - - /* Always reuse the last entry (LRU policy) */ - cte = list_last_entry(&dist->lpi_translation_cache, - typeof(*cte), entry); - - /* - * Caching the translation implies having an extra reference - * to the interrupt, so drop the potential reference on what - * was in the cache, and increment it on the new interrupt. - */ - if (cte->irq) - __vgic_put_lpi_locked(kvm, cte->irq); - - vgic_get_irq_kref(irq); - - cte->db = db; - cte->devid = devid; - cte->eventid = eventid; - cte->irq = irq; - - /* Move the new translation to the head of the list */ - list_move(&cte->entry, &dist->lpi_translation_cache); - -out: - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); -} - -void vgic_its_invalidate_cache(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_translation_cache_entry *cte; - unsigned long flags; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - - list_for_each_entry(cte, &dist->lpi_translation_cache, entry) { - /* - * If we hit a NULL entry, there is nothing after this - * point. - */ - if (!cte->irq) - break; - - __vgic_put_lpi_locked(kvm, cte->irq); - cte->irq = NULL; - } - - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); -} - -int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid, struct vgic_irq **irq) -{ - struct kvm_vcpu *vcpu; - struct its_ite *ite; - - if (!its->enabled) - return -EBUSY; - - ite = find_ite(its, devid, eventid); - if (!ite || !its_is_collection_mapped(ite->collection)) - return E_ITS_INT_UNMAPPED_INTERRUPT; - - vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr); - if (!vcpu) - return E_ITS_INT_UNMAPPED_INTERRUPT; - - if (!vcpu->arch.vgic_cpu.lpis_enabled) - return -EBUSY; - - vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq); - - *irq = ite->irq; - return 0; -} - -struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi) -{ - u64 address; - struct kvm_io_device *kvm_io_dev; - struct vgic_io_device *iodev; - - if (!vgic_has_its(kvm)) - return ERR_PTR(-ENODEV); - - if (!(msi->flags & KVM_MSI_VALID_DEVID)) - return ERR_PTR(-EINVAL); - - address = (u64)msi->address_hi << 32 | msi->address_lo; - - kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); - if (!kvm_io_dev) - return ERR_PTR(-EINVAL); - - if (kvm_io_dev->ops != &kvm_io_gic_ops) - return ERR_PTR(-EINVAL); - - iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); - if (iodev->iodev_type != IODEV_ITS) - return ERR_PTR(-EINVAL); - - return iodev->its; -} - -/* - * Find the target VCPU and the LPI number for a given devid/eventid pair - * and make this IRQ pending, possibly injecting it. - * Must be called with the its_lock mutex held. - * Returns 0 on success, a positive error value for any ITS mapping - * related errors and negative error values for generic errors. - */ -static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) -{ - struct vgic_irq *irq = NULL; - unsigned long flags; - int err; - - err = vgic_its_resolve_lpi(kvm, its, devid, eventid, &irq); - if (err) - return err; - - if (irq->hw) - return irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, true); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - vgic_queue_irq_unlock(kvm, irq, flags); - - return 0; -} - -int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) -{ - struct vgic_irq *irq; - unsigned long flags; - phys_addr_t db; - - db = (u64)msi->address_hi << 32 | msi->address_lo; - irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); - - if (!irq) - return -1; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - vgic_queue_irq_unlock(kvm, irq, flags); - - return 0; -} - -/* - * Queries the KVM IO bus framework to get the ITS pointer from the given - * doorbell address. - * We then call vgic_its_trigger_msi() with the decoded data. - * According to the KVM_SIGNAL_MSI API description returns 1 on success. - */ -int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) -{ - struct vgic_its *its; - int ret; - - if (!vgic_its_inject_cached_translation(kvm, msi)) - return 1; - - its = vgic_msi_to_its(kvm, msi); - if (IS_ERR(its)) - return PTR_ERR(its); - - mutex_lock(&its->its_lock); - ret = vgic_its_trigger_msi(kvm, its, msi->devid, msi->data); - mutex_unlock(&its->its_lock); - - if (ret < 0) - return ret; - - /* - * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 - * if the guest has blocked the MSI. So we map any LPI mapping - * related error to that. - */ - if (ret) - return 0; - else - return 1; -} - -/* Requires the its_lock to be held. */ -static void its_free_ite(struct kvm *kvm, struct its_ite *ite) -{ - list_del(&ite->ite_list); - - /* This put matches the get in vgic_add_lpi. */ - if (ite->irq) { - if (ite->irq->hw) - WARN_ON(its_unmap_vlpi(ite->irq->host_irq)); - - vgic_put_irq(kvm, ite->irq); - } - - kfree(ite); -} - -static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size) -{ - return (le64_to_cpu(its_cmd[word]) >> shift) & (BIT_ULL(size) - 1); -} - -#define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8) -#define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32) -#define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1) -#define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32) -#define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32) -#define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16) -#define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8) -#define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32) -#define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1) - -/* - * The DISCARD command frees an Interrupt Translation Table Entry (ITTE). - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - u32 event_id = its_cmd_get_id(its_cmd); - struct its_ite *ite; - - ite = find_ite(its, device_id, event_id); - if (ite && its_is_collection_mapped(ite->collection)) { - /* - * Though the spec talks about removing the pending state, we - * don't bother here since we clear the ITTE anyway and the - * pending state is a property of the ITTE struct. - */ - vgic_its_invalidate_cache(kvm); - - its_free_ite(kvm, ite); - return 0; - } - - return E_ITS_DISCARD_UNMAPPED_INTERRUPT; -} - -/* - * The MOVI command moves an ITTE to a different collection. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - u32 event_id = its_cmd_get_id(its_cmd); - u32 coll_id = its_cmd_get_collection(its_cmd); - struct kvm_vcpu *vcpu; - struct its_ite *ite; - struct its_collection *collection; - - ite = find_ite(its, device_id, event_id); - if (!ite) - return E_ITS_MOVI_UNMAPPED_INTERRUPT; - - if (!its_is_collection_mapped(ite->collection)) - return E_ITS_MOVI_UNMAPPED_COLLECTION; - - collection = find_collection(its, coll_id); - if (!its_is_collection_mapped(collection)) - return E_ITS_MOVI_UNMAPPED_COLLECTION; - - ite->collection = collection; - vcpu = kvm_get_vcpu(kvm, collection->target_addr); - - vgic_its_invalidate_cache(kvm); - - return update_affinity(ite->irq, vcpu); -} - -/* - * Check whether an ID can be stored into the corresponding guest table. - * For a direct table this is pretty easy, but gets a bit nasty for - * indirect tables. We check whether the resulting guest physical address - * is actually valid (covered by a memslot and guest accessible). - * For this we have to read the respective first level entry. - */ -static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, - gpa_t *eaddr) -{ - int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; - u64 indirect_ptr, type = GITS_BASER_TYPE(baser); - phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); - int esz = GITS_BASER_ENTRY_SIZE(baser); - int index, idx; - gfn_t gfn; - bool ret; - - switch (type) { - case GITS_BASER_TYPE_DEVICE: - if (id >= BIT_ULL(VITS_TYPER_DEVBITS)) - return false; - break; - case GITS_BASER_TYPE_COLLECTION: - /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */ - if (id >= BIT_ULL(16)) - return false; - break; - default: - return false; - } - - if (!(baser & GITS_BASER_INDIRECT)) { - phys_addr_t addr; - - if (id >= (l1_tbl_size / esz)) - return false; - - addr = base + id * esz; - gfn = addr >> PAGE_SHIFT; - - if (eaddr) - *eaddr = addr; - - goto out; - } - - /* calculate and check the index into the 1st level */ - index = id / (SZ_64K / esz); - if (index >= (l1_tbl_size / sizeof(u64))) - return false; - - /* Each 1st level entry is represented by a 64-bit value. */ - if (kvm_read_guest_lock(its->dev->kvm, - base + index * sizeof(indirect_ptr), - &indirect_ptr, sizeof(indirect_ptr))) - return false; - - indirect_ptr = le64_to_cpu(indirect_ptr); - - /* check the valid bit of the first level entry */ - if (!(indirect_ptr & BIT_ULL(63))) - return false; - - /* Mask the guest physical address and calculate the frame number. */ - indirect_ptr &= GENMASK_ULL(51, 16); - - /* Find the address of the actual entry */ - index = id % (SZ_64K / esz); - indirect_ptr += index * esz; - gfn = indirect_ptr >> PAGE_SHIFT; - - if (eaddr) - *eaddr = indirect_ptr; - -out: - idx = srcu_read_lock(&its->dev->kvm->srcu); - ret = kvm_is_visible_gfn(its->dev->kvm, gfn); - srcu_read_unlock(&its->dev->kvm->srcu, idx); - return ret; -} - -static int vgic_its_alloc_collection(struct vgic_its *its, - struct its_collection **colp, - u32 coll_id) -{ - struct its_collection *collection; - - if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL)) - 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; - - list_add_tail(&collection->coll_list, &its->collection_list); - *colp = collection; - - return 0; -} - -static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id) -{ - struct its_collection *collection; - struct its_device *device; - struct its_ite *ite; - - /* - * Clearing the mapping for that collection ID removes the - * entry from the list. If there wasn't any before, we can - * go home early. - */ - collection = find_collection(its, coll_id); - if (!collection) - return; - - for_each_lpi_its(device, ite, its) - if (ite->collection && - ite->collection->collection_id == coll_id) - ite->collection = NULL; - - list_del(&collection->coll_list); - kfree(collection); -} - -/* Must be called with its_lock mutex held */ -static struct its_ite *vgic_its_alloc_ite(struct its_device *device, - struct its_collection *collection, - u32 event_id) -{ - struct its_ite *ite; - - ite = kzalloc(sizeof(*ite), GFP_KERNEL); - if (!ite) - return ERR_PTR(-ENOMEM); - - ite->event_id = event_id; - ite->collection = collection; - - list_add_tail(&ite->ite_list, &device->itt_head); - return ite; -} - -/* - * The MAPTI and MAPI commands map LPIs to ITTEs. - * Must be called with its_lock mutex held. - */ -static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - u32 event_id = its_cmd_get_id(its_cmd); - u32 coll_id = its_cmd_get_collection(its_cmd); - struct its_ite *ite; - struct kvm_vcpu *vcpu = NULL; - struct its_device *device; - struct its_collection *collection, *new_coll = NULL; - struct vgic_irq *irq; - int lpi_nr; - - device = find_its_device(its, device_id); - if (!device) - return E_ITS_MAPTI_UNMAPPED_DEVICE; - - if (event_id >= BIT_ULL(device->num_eventid_bits)) - return E_ITS_MAPTI_ID_OOR; - - if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI) - lpi_nr = its_cmd_get_physical_id(its_cmd); - else - lpi_nr = event_id; - if (lpi_nr < GIC_LPI_OFFSET || - lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) - return E_ITS_MAPTI_PHYSICALID_OOR; - - /* If there is an existing mapping, behavior is UNPREDICTABLE. */ - if (find_ite(its, device_id, event_id)) - return 0; - - collection = find_collection(its, coll_id); - if (!collection) { - int ret = vgic_its_alloc_collection(its, &collection, coll_id); - if (ret) - return ret; - new_coll = collection; - } - - ite = vgic_its_alloc_ite(device, collection, event_id); - if (IS_ERR(ite)) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - return PTR_ERR(ite); - } - - if (its_is_collection_mapped(collection)) - vcpu = kvm_get_vcpu(kvm, collection->target_addr); - - irq = vgic_add_lpi(kvm, lpi_nr, vcpu); - if (IS_ERR(irq)) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - its_free_ite(kvm, ite); - return PTR_ERR(irq); - } - ite->irq = irq; - - return 0; -} - -/* Requires the its_lock to be held. */ -static void vgic_its_free_device(struct kvm *kvm, struct its_device *device) -{ - struct its_ite *ite, *temp; - - /* - * The spec says that unmapping a device with still valid - * ITTEs associated is UNPREDICTABLE. We remove all ITTEs, - * since we cannot leave the memory unreferenced. - */ - list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list) - its_free_ite(kvm, ite); - - vgic_its_invalidate_cache(kvm); - - list_del(&device->dev_list); - kfree(device); -} - -/* its lock must be held */ -static void vgic_its_free_device_list(struct kvm *kvm, struct vgic_its *its) -{ - struct its_device *cur, *temp; - - list_for_each_entry_safe(cur, temp, &its->device_list, dev_list) - vgic_its_free_device(kvm, cur); -} - -/* its lock must be held */ -static void vgic_its_free_collection_list(struct kvm *kvm, struct vgic_its *its) -{ - struct its_collection *cur, *temp; - - list_for_each_entry_safe(cur, temp, &its->collection_list, coll_list) - vgic_its_free_collection(its, cur->collection_id); -} - -/* Must be called with its_lock mutex held */ -static struct its_device *vgic_its_alloc_device(struct vgic_its *its, - u32 device_id, gpa_t itt_addr, - u8 num_eventid_bits) -{ - struct its_device *device; - - device = kzalloc(sizeof(*device), GFP_KERNEL); - if (!device) - return ERR_PTR(-ENOMEM); - - device->device_id = device_id; - device->itt_addr = itt_addr; - device->num_eventid_bits = num_eventid_bits; - INIT_LIST_HEAD(&device->itt_head); - - list_add_tail(&device->dev_list, &its->device_list); - return device; -} - -/* - * MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs). - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - bool valid = its_cmd_get_validbit(its_cmd); - u8 num_eventid_bits = its_cmd_get_size(its_cmd); - gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd); - struct its_device *device; - - if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL)) - return E_ITS_MAPD_DEVICE_OOR; - - if (valid && num_eventid_bits > VITS_TYPER_IDBITS) - return E_ITS_MAPD_ITTSIZE_OOR; - - device = find_its_device(its, device_id); - - /* - * The spec says that calling MAPD on an already mapped device - * invalidates all cached data for this device. We implement this - * by removing the mapping and re-establishing it. - */ - if (device) - vgic_its_free_device(kvm, device); - - /* - * The spec does not say whether unmapping a not-mapped device - * is an error, so we are done in any case. - */ - if (!valid) - return 0; - - device = vgic_its_alloc_device(its, device_id, itt_addr, - num_eventid_bits); - - return PTR_ERR_OR_ZERO(device); -} - -/* - * The MAPC command maps collection IDs to redistributors. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u16 coll_id; - u32 target_addr; - struct its_collection *collection; - bool valid; - - valid = its_cmd_get_validbit(its_cmd); - coll_id = its_cmd_get_collection(its_cmd); - target_addr = its_cmd_get_target_addr(its_cmd); - - if (target_addr >= atomic_read(&kvm->online_vcpus)) - return E_ITS_MAPC_PROCNUM_OOR; - - if (!valid) { - vgic_its_free_collection(its, coll_id); - vgic_its_invalidate_cache(kvm); - } else { - collection = find_collection(its, coll_id); - - if (!collection) { - int ret; - - ret = vgic_its_alloc_collection(its, &collection, - coll_id); - if (ret) - return ret; - collection->target_addr = target_addr; - } else { - collection->target_addr = target_addr; - update_affinity_collection(kvm, its, collection); - } - } - - return 0; -} - -/* - * The CLEAR command removes the pending state for a particular LPI. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - u32 event_id = its_cmd_get_id(its_cmd); - struct its_ite *ite; - - - ite = find_ite(its, device_id, event_id); - if (!ite) - return E_ITS_CLEAR_UNMAPPED_INTERRUPT; - - ite->irq->pending_latch = false; - - if (ite->irq->hw) - return irq_set_irqchip_state(ite->irq->host_irq, - IRQCHIP_STATE_PENDING, false); - - return 0; -} - -/* - * The INV command syncs the configuration bits from the memory table. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 device_id = its_cmd_get_deviceid(its_cmd); - u32 event_id = its_cmd_get_id(its_cmd); - struct its_ite *ite; - - - ite = find_ite(its, device_id, event_id); - if (!ite) - return E_ITS_INV_UNMAPPED_INTERRUPT; - - return update_lpi_config(kvm, ite->irq, NULL, true); -} - -/* - * The INVALL command requests flushing of all IRQ data in this collection. - * Find the VCPU mapped to that collection, then iterate over the VM's list - * of mapped LPIs and update the configuration for each IRQ which targets - * the specified vcpu. The configuration will be read from the in-memory - * configuration table. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 coll_id = its_cmd_get_collection(its_cmd); - struct its_collection *collection; - struct kvm_vcpu *vcpu; - struct vgic_irq *irq; - u32 *intids; - int irq_count, i; - - collection = find_collection(its, coll_id); - if (!its_is_collection_mapped(collection)) - return E_ITS_INVALL_UNMAPPED_COLLECTION; - - vcpu = kvm_get_vcpu(kvm, collection->target_addr); - - irq_count = vgic_copy_lpi_list(kvm, vcpu, &intids); - if (irq_count < 0) - return irq_count; - - for (i = 0; i < irq_count; i++) { - irq = vgic_get_irq(kvm, NULL, intids[i]); - if (!irq) - continue; - update_lpi_config(kvm, irq, vcpu, false); - vgic_put_irq(kvm, irq); - } - - kfree(intids); - - if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.its_vm) - its_invall_vpe(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe); - - return 0; -} - -/* - * The MOVALL command moves the pending state of all IRQs targeting one - * redistributor to another. We don't hold the pending state in the VCPUs, - * but in the IRQs instead, so there is really not much to do for us here. - * However the spec says that no IRQ must target the old redistributor - * afterwards, so we make sure that no LPI is using the associated target_vcpu. - * This command affects all LPIs in the system that target that redistributor. - */ -static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 target1_addr = its_cmd_get_target_addr(its_cmd); - u32 target2_addr = its_cmd_mask_field(its_cmd, 3, 16, 32); - struct kvm_vcpu *vcpu1, *vcpu2; - struct vgic_irq *irq; - u32 *intids; - int irq_count, i; - - if (target1_addr >= atomic_read(&kvm->online_vcpus) || - target2_addr >= atomic_read(&kvm->online_vcpus)) - return E_ITS_MOVALL_PROCNUM_OOR; - - if (target1_addr == target2_addr) - return 0; - - vcpu1 = kvm_get_vcpu(kvm, target1_addr); - vcpu2 = kvm_get_vcpu(kvm, target2_addr); - - irq_count = vgic_copy_lpi_list(kvm, vcpu1, &intids); - if (irq_count < 0) - return irq_count; - - for (i = 0; i < irq_count; i++) { - irq = vgic_get_irq(kvm, NULL, intids[i]); - - update_affinity(irq, vcpu2); - - vgic_put_irq(kvm, irq); - } - - vgic_its_invalidate_cache(kvm); - - kfree(intids); - return 0; -} - -/* - * The INT command injects the LPI associated with that DevID/EvID pair. - * Must be called with the its_lock mutex held. - */ -static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - u32 msi_data = its_cmd_get_id(its_cmd); - u64 msi_devid = its_cmd_get_deviceid(its_cmd); - - return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); -} - -/* - * This function is called with the its_cmd lock held, but the ITS data - * structure lock dropped. - */ -static int vgic_its_handle_command(struct kvm *kvm, struct vgic_its *its, - u64 *its_cmd) -{ - int ret = -ENODEV; - - mutex_lock(&its->its_lock); - switch (its_cmd_get_command(its_cmd)) { - case GITS_CMD_MAPD: - ret = vgic_its_cmd_handle_mapd(kvm, its, its_cmd); - break; - case GITS_CMD_MAPC: - ret = vgic_its_cmd_handle_mapc(kvm, its, its_cmd); - break; - case GITS_CMD_MAPI: - ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); - break; - case GITS_CMD_MAPTI: - ret = vgic_its_cmd_handle_mapi(kvm, its, its_cmd); - break; - case GITS_CMD_MOVI: - ret = vgic_its_cmd_handle_movi(kvm, its, its_cmd); - break; - case GITS_CMD_DISCARD: - ret = vgic_its_cmd_handle_discard(kvm, its, its_cmd); - break; - case GITS_CMD_CLEAR: - ret = vgic_its_cmd_handle_clear(kvm, its, its_cmd); - break; - case GITS_CMD_MOVALL: - ret = vgic_its_cmd_handle_movall(kvm, its, its_cmd); - break; - case GITS_CMD_INT: - ret = vgic_its_cmd_handle_int(kvm, its, its_cmd); - break; - case GITS_CMD_INV: - ret = vgic_its_cmd_handle_inv(kvm, its, its_cmd); - break; - case GITS_CMD_INVALL: - ret = vgic_its_cmd_handle_invall(kvm, its, its_cmd); - break; - case GITS_CMD_SYNC: - /* we ignore this command: we are in sync all of the time */ - ret = 0; - break; - } - mutex_unlock(&its->its_lock); - - return ret; -} - -static u64 vgic_sanitise_its_baser(u64 reg) -{ - reg = vgic_sanitise_field(reg, GITS_BASER_SHAREABILITY_MASK, - GITS_BASER_SHAREABILITY_SHIFT, - vgic_sanitise_shareability); - reg = vgic_sanitise_field(reg, GITS_BASER_INNER_CACHEABILITY_MASK, - GITS_BASER_INNER_CACHEABILITY_SHIFT, - vgic_sanitise_inner_cacheability); - reg = vgic_sanitise_field(reg, GITS_BASER_OUTER_CACHEABILITY_MASK, - GITS_BASER_OUTER_CACHEABILITY_SHIFT, - vgic_sanitise_outer_cacheability); - - /* We support only one (ITS) page size: 64K */ - reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; - - return reg; -} - -static u64 vgic_sanitise_its_cbaser(u64 reg) -{ - reg = vgic_sanitise_field(reg, GITS_CBASER_SHAREABILITY_MASK, - GITS_CBASER_SHAREABILITY_SHIFT, - vgic_sanitise_shareability); - reg = vgic_sanitise_field(reg, GITS_CBASER_INNER_CACHEABILITY_MASK, - GITS_CBASER_INNER_CACHEABILITY_SHIFT, - vgic_sanitise_inner_cacheability); - reg = vgic_sanitise_field(reg, GITS_CBASER_OUTER_CACHEABILITY_MASK, - GITS_CBASER_OUTER_CACHEABILITY_SHIFT, - vgic_sanitise_outer_cacheability); - - /* Sanitise the physical address to be 64k aligned. */ - reg &= ~GENMASK_ULL(15, 12); - - return reg; -} - -static unsigned long vgic_mmio_read_its_cbaser(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - return extract_bytes(its->cbaser, addr & 7, len); -} - -static void vgic_mmio_write_its_cbaser(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - /* When GITS_CTLR.Enable is 1, this register is RO. */ - if (its->enabled) - return; - - mutex_lock(&its->cmd_lock); - its->cbaser = update_64bit_reg(its->cbaser, addr & 7, len, val); - its->cbaser = vgic_sanitise_its_cbaser(its->cbaser); - its->creadr = 0; - /* - * CWRITER is architecturally UNKNOWN on reset, but we need to reset - * it to CREADR to make sure we start with an empty command buffer. - */ - its->cwriter = its->creadr; - mutex_unlock(&its->cmd_lock); -} - -#define ITS_CMD_BUFFER_SIZE(baser) ((((baser) & 0xff) + 1) << 12) -#define ITS_CMD_SIZE 32 -#define ITS_CMD_OFFSET(reg) ((reg) & GENMASK(19, 5)) - -/* Must be called with the cmd_lock held. */ -static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) -{ - gpa_t cbaser; - u64 cmd_buf[4]; - - /* Commands are only processed when the ITS is enabled. */ - if (!its->enabled) - return; - - cbaser = GITS_CBASER_ADDRESS(its->cbaser); - - while (its->cwriter != its->creadr) { - int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, - cmd_buf, ITS_CMD_SIZE); - /* - * If kvm_read_guest() fails, this could be due to the guest - * programming a bogus value in CBASER or something else going - * wrong from which we cannot easily recover. - * According to section 6.3.2 in the GICv3 spec we can just - * ignore that command then. - */ - if (!ret) - vgic_its_handle_command(kvm, its, cmd_buf); - - its->creadr += ITS_CMD_SIZE; - if (its->creadr == ITS_CMD_BUFFER_SIZE(its->cbaser)) - its->creadr = 0; - } -} - -/* - * By writing to CWRITER the guest announces new commands to be processed. - * To avoid any races in the first place, we take the its_cmd lock, which - * protects our ring buffer variables, so that there is only one user - * per ITS handling commands at a given time. - */ -static void vgic_mmio_write_its_cwriter(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u64 reg; - - if (!its) - return; - - mutex_lock(&its->cmd_lock); - - reg = update_64bit_reg(its->cwriter, addr & 7, len, val); - reg = ITS_CMD_OFFSET(reg); - if (reg >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { - mutex_unlock(&its->cmd_lock); - return; - } - its->cwriter = reg; - - vgic_its_process_commands(kvm, its); - - mutex_unlock(&its->cmd_lock); -} - -static unsigned long vgic_mmio_read_its_cwriter(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - return extract_bytes(its->cwriter, addr & 0x7, len); -} - -static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - return extract_bytes(its->creadr, addr & 0x7, len); -} - -static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 cmd_offset; - int ret = 0; - - mutex_lock(&its->cmd_lock); - - if (its->enabled) { - ret = -EBUSY; - goto out; - } - - cmd_offset = ITS_CMD_OFFSET(val); - if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) { - ret = -EINVAL; - goto out; - } - - its->creadr = cmd_offset; -out: - mutex_unlock(&its->cmd_lock); - return ret; -} - -#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7) -static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - u64 reg; - - switch (BASER_INDEX(addr)) { - case 0: - reg = its->baser_device_table; - break; - case 1: - reg = its->baser_coll_table; - break; - default: - reg = 0; - break; - } - - return extract_bytes(reg, addr & 7, len); -} - -#define GITS_BASER_RO_MASK (GENMASK_ULL(52, 48) | GENMASK_ULL(58, 56)) -static void vgic_mmio_write_its_baser(struct kvm *kvm, - struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 entry_size, table_type; - u64 reg, *regptr, clearbits = 0; - - /* When GITS_CTLR.Enable is 1, we ignore write accesses. */ - if (its->enabled) - return; - - switch (BASER_INDEX(addr)) { - case 0: - regptr = &its->baser_device_table; - entry_size = abi->dte_esz; - table_type = GITS_BASER_TYPE_DEVICE; - break; - case 1: - regptr = &its->baser_coll_table; - entry_size = abi->cte_esz; - table_type = GITS_BASER_TYPE_COLLECTION; - clearbits = GITS_BASER_INDIRECT; - break; - default: - return; - } - - reg = update_64bit_reg(*regptr, addr & 7, len, val); - reg &= ~GITS_BASER_RO_MASK; - reg &= ~clearbits; - - reg |= (entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT; - reg |= table_type << GITS_BASER_TYPE_SHIFT; - reg = vgic_sanitise_its_baser(reg); - - *regptr = reg; - - if (!(reg & GITS_BASER_VALID)) { - /* Take the its_lock to prevent a race with a save/restore */ - mutex_lock(&its->its_lock); - switch (table_type) { - case GITS_BASER_TYPE_DEVICE: - vgic_its_free_device_list(kvm, its); - break; - case GITS_BASER_TYPE_COLLECTION: - vgic_its_free_collection_list(kvm, its); - break; - } - mutex_unlock(&its->its_lock); - } -} - -static unsigned long vgic_mmio_read_its_ctlr(struct kvm *vcpu, - struct vgic_its *its, - gpa_t addr, unsigned int len) -{ - u32 reg = 0; - - mutex_lock(&its->cmd_lock); - if (its->creadr == its->cwriter) - reg |= GITS_CTLR_QUIESCENT; - if (its->enabled) - reg |= GITS_CTLR_ENABLE; - mutex_unlock(&its->cmd_lock); - - return reg; -} - -static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val) -{ - mutex_lock(&its->cmd_lock); - - /* - * It is UNPREDICTABLE to enable the ITS if any of the CBASER or - * device/collection BASER are invalid - */ - if (!its->enabled && (val & GITS_CTLR_ENABLE) && - (!(its->baser_device_table & GITS_BASER_VALID) || - !(its->baser_coll_table & GITS_BASER_VALID) || - !(its->cbaser & GITS_CBASER_VALID))) - goto out; - - its->enabled = !!(val & GITS_CTLR_ENABLE); - if (!its->enabled) - vgic_its_invalidate_cache(kvm); - - /* - * Try to process any pending commands. This function bails out early - * if the ITS is disabled or no commands have been queued. - */ - vgic_its_process_commands(kvm, its); - -out: - mutex_unlock(&its->cmd_lock); -} - -#define REGISTER_ITS_DESC(off, rd, wr, length, acc) \ -{ \ - .reg_offset = off, \ - .len = length, \ - .access_flags = acc, \ - .its_read = rd, \ - .its_write = wr, \ -} - -#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\ -{ \ - .reg_offset = off, \ - .len = length, \ - .access_flags = acc, \ - .its_read = rd, \ - .its_write = wr, \ - .uaccess_its_write = uwr, \ -} - -static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, unsigned long val) -{ - /* Ignore */ -} - -static struct vgic_register_region its_registers[] = { - REGISTER_ITS_DESC(GITS_CTLR, - vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4, - VGIC_ACCESS_32bit), - REGISTER_ITS_DESC_UACCESS(GITS_IIDR, - vgic_mmio_read_its_iidr, its_mmio_write_wi, - vgic_mmio_uaccess_write_its_iidr, 4, - VGIC_ACCESS_32bit), - REGISTER_ITS_DESC(GITS_TYPER, - vgic_mmio_read_its_typer, its_mmio_write_wi, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_ITS_DESC(GITS_CBASER, - vgic_mmio_read_its_cbaser, vgic_mmio_write_its_cbaser, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_ITS_DESC(GITS_CWRITER, - vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_ITS_DESC_UACCESS(GITS_CREADR, - vgic_mmio_read_its_creadr, its_mmio_write_wi, - vgic_mmio_uaccess_write_its_creadr, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_ITS_DESC(GITS_BASER, - vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_ITS_DESC(GITS_IDREGS_BASE, - vgic_mmio_read_its_idregs, its_mmio_write_wi, 0x30, - VGIC_ACCESS_32bit), -}; - -/* This is called on setting the LPI enable bit in the redistributor. */ -void vgic_enable_lpis(struct kvm_vcpu *vcpu) -{ - if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ)) - its_sync_lpi_pending_table(vcpu); -} - -static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its, - u64 addr) -{ - struct vgic_io_device *iodev = &its->iodev; - int ret; - - mutex_lock(&kvm->slots_lock); - if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { - ret = -EBUSY; - goto out; - } - - its->vgic_its_base = addr; - iodev->regions = its_registers; - iodev->nr_regions = ARRAY_SIZE(its_registers); - kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops); - - iodev->base_addr = its->vgic_its_base; - iodev->iodev_type = IODEV_ITS; - iodev->its = its; - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr, - KVM_VGIC_V3_ITS_SIZE, &iodev->dev); -out: - mutex_unlock(&kvm->slots_lock); - - return ret; -} - -/* Default is 16 cached LPIs per vcpu */ -#define LPI_DEFAULT_PCPU_CACHE_SIZE 16 - -void vgic_lpi_translation_cache_init(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - unsigned int sz; - int i; - - if (!list_empty(&dist->lpi_translation_cache)) - return; - - sz = atomic_read(&kvm->online_vcpus) * LPI_DEFAULT_PCPU_CACHE_SIZE; - - for (i = 0; i < sz; i++) { - struct vgic_translation_cache_entry *cte; - - /* An allocation failure is not fatal */ - cte = kzalloc(sizeof(*cte), GFP_KERNEL); - if (WARN_ON(!cte)) - break; - - INIT_LIST_HEAD(&cte->entry); - list_add(&cte->entry, &dist->lpi_translation_cache); - } -} - -void vgic_lpi_translation_cache_destroy(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_translation_cache_entry *cte, *tmp; - - vgic_its_invalidate_cache(kvm); - - list_for_each_entry_safe(cte, tmp, - &dist->lpi_translation_cache, entry) { - list_del(&cte->entry); - kfree(cte); - } -} - -#define INITIAL_BASER_VALUE \ - (GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \ - GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \ - GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \ - GITS_BASER_PAGE_SIZE_64K) - -#define INITIAL_PROPBASER_VALUE \ - (GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWb) | \ - GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, SameAsInner) | \ - GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable)) - -static int vgic_its_create(struct kvm_device *dev, u32 type) -{ - struct vgic_its *its; - - if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) - return -ENODEV; - - its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL); - if (!its) - return -ENOMEM; - - if (vgic_initialized(dev->kvm)) { - int ret = vgic_v4_init(dev->kvm); - if (ret < 0) { - kfree(its); - return ret; - } - - vgic_lpi_translation_cache_init(dev->kvm); - } - - mutex_init(&its->its_lock); - mutex_init(&its->cmd_lock); - - its->vgic_its_base = VGIC_ADDR_UNDEF; - - INIT_LIST_HEAD(&its->device_list); - INIT_LIST_HEAD(&its->collection_list); - - dev->kvm->arch.vgic.msis_require_devid = true; - dev->kvm->arch.vgic.has_its = true; - its->enabled = false; - its->dev = dev; - - its->baser_device_table = INITIAL_BASER_VALUE | - ((u64)GITS_BASER_TYPE_DEVICE << GITS_BASER_TYPE_SHIFT); - its->baser_coll_table = INITIAL_BASER_VALUE | - ((u64)GITS_BASER_TYPE_COLLECTION << GITS_BASER_TYPE_SHIFT); - dev->kvm->arch.vgic.propbaser = INITIAL_PROPBASER_VALUE; - - dev->private = its; - - return vgic_its_set_abi(its, NR_ITS_ABIS - 1); -} - -static void vgic_its_destroy(struct kvm_device *kvm_dev) -{ - struct kvm *kvm = kvm_dev->kvm; - struct vgic_its *its = kvm_dev->private; - - mutex_lock(&its->its_lock); - - vgic_its_free_device_list(kvm, its); - vgic_its_free_collection_list(kvm, its); - - mutex_unlock(&its->its_lock); - kfree(its); - kfree(kvm_dev);/* alloc by kvm_ioctl_create_device, free by .destroy */ -} - -static int vgic_its_has_attr_regs(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - const struct vgic_register_region *region; - gpa_t offset = attr->attr; - int align; - - align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7; - - if (offset & align) - return -EINVAL; - - region = vgic_find_mmio_region(its_registers, - ARRAY_SIZE(its_registers), - offset); - if (!region) - return -ENXIO; - - return 0; -} - -static int vgic_its_attr_regs_access(struct kvm_device *dev, - struct kvm_device_attr *attr, - u64 *reg, bool is_write) -{ - const struct vgic_register_region *region; - struct vgic_its *its; - gpa_t addr, offset; - unsigned int len; - int align, ret = 0; - - its = dev->private; - offset = attr->attr; - - /* - * Although the spec supports upper/lower 32-bit accesses to - * 64-bit ITS registers, the userspace ABI requires 64-bit - * accesses to all 64-bit wide registers. We therefore only - * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID - * registers - */ - if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4)) - align = 0x3; - else - align = 0x7; - - if (offset & align) - return -EINVAL; - - mutex_lock(&dev->kvm->lock); - - if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { - ret = -ENXIO; - goto out; - } - - region = vgic_find_mmio_region(its_registers, - ARRAY_SIZE(its_registers), - offset); - if (!region) { - ret = -ENXIO; - goto out; - } - - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - - addr = its->vgic_its_base + offset; - - len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; - - if (is_write) { - if (region->uaccess_its_write) - ret = region->uaccess_its_write(dev->kvm, its, addr, - len, *reg); - else - region->its_write(dev->kvm, its, addr, len, *reg); - } else { - *reg = region->its_read(dev->kvm, its, addr, len); - } - unlock_all_vcpus(dev->kvm); -out: - mutex_unlock(&dev->kvm->lock); - return ret; -} - -static u32 compute_next_devid_offset(struct list_head *h, - struct its_device *dev) -{ - struct its_device *next; - u32 next_offset; - - if (list_is_last(&dev->dev_list, h)) - return 0; - next = list_next_entry(dev, dev_list); - next_offset = next->device_id - dev->device_id; - - return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET); -} - -static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite) -{ - struct its_ite *next; - u32 next_offset; - - if (list_is_last(&ite->ite_list, h)) - return 0; - next = list_next_entry(ite, ite_list); - next_offset = next->event_id - ite->event_id; - - return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET); -} - -/** - * entry_fn_t - Callback called on a table entry restore path - * @its: its handle - * @id: id of the entry - * @entry: pointer to the entry - * @opaque: pointer to an opaque data - * - * Return: < 0 on error, 0 if last element was identified, id offset to next - * element otherwise - */ -typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry, - void *opaque); - -/** - * scan_its_table - Scan a contiguous table in guest RAM and applies a function - * to each entry - * - * @its: its handle - * @base: base gpa of the table - * @size: size of the table in bytes - * @esz: entry size in bytes - * @start_id: the ID of the first entry in the table - * (non zero for 2d level tables) - * @fn: function to apply on each entry - * - * Return: < 0 on error, 0 if last element was identified, 1 otherwise - * (the last element may not be found on second level tables) - */ -static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz, - int start_id, entry_fn_t fn, void *opaque) -{ - struct kvm *kvm = its->dev->kvm; - unsigned long len = size; - int id = start_id; - gpa_t gpa = base; - char entry[ESZ_MAX]; - int ret; - - memset(entry, 0, esz); - - while (len > 0) { - int next_offset; - size_t byte_offset; - - ret = kvm_read_guest_lock(kvm, gpa, entry, esz); - if (ret) - return ret; - - next_offset = fn(its, id, entry, opaque); - if (next_offset <= 0) - return next_offset; - - byte_offset = next_offset * esz; - id += next_offset; - gpa += byte_offset; - len -= byte_offset; - } - return 1; -} - -/** - * vgic_its_save_ite - Save an interrupt translation entry at @gpa - */ -static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, - struct its_ite *ite, gpa_t gpa, int ite_esz) -{ - struct kvm *kvm = its->dev->kvm; - u32 next_offset; - u64 val; - - next_offset = compute_next_eventid_offset(&dev->itt_head, ite); - val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) | - ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | - ite->collection->collection_id; - val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); -} - -/** - * vgic_its_restore_ite - restore an interrupt translation entry - * @event_id: id used for indexing - * @ptr: pointer to the ITE entry - * @opaque: pointer to the its_device - */ -static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id, - void *ptr, void *opaque) -{ - struct its_device *dev = (struct its_device *)opaque; - struct its_collection *collection; - struct kvm *kvm = its->dev->kvm; - struct kvm_vcpu *vcpu = NULL; - u64 val; - u64 *p = (u64 *)ptr; - struct vgic_irq *irq; - u32 coll_id, lpi_id; - struct its_ite *ite; - u32 offset; - - val = *p; - - val = le64_to_cpu(val); - - coll_id = val & KVM_ITS_ITE_ICID_MASK; - lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT; - - if (!lpi_id) - return 1; /* invalid entry, no choice but to scan next entry */ - - if (lpi_id < VGIC_MIN_LPI) - return -EINVAL; - - offset = val >> KVM_ITS_ITE_NEXT_SHIFT; - if (event_id + offset >= BIT_ULL(dev->num_eventid_bits)) - return -EINVAL; - - collection = find_collection(its, coll_id); - if (!collection) - return -EINVAL; - - ite = vgic_its_alloc_ite(dev, collection, event_id); - if (IS_ERR(ite)) - return PTR_ERR(ite); - - if (its_is_collection_mapped(collection)) - vcpu = kvm_get_vcpu(kvm, collection->target_addr); - - irq = vgic_add_lpi(kvm, lpi_id, vcpu); - if (IS_ERR(irq)) - return PTR_ERR(irq); - ite->irq = irq; - - return offset; -} - -static int vgic_its_ite_cmp(void *priv, struct list_head *a, - struct list_head *b) -{ - struct its_ite *itea = container_of(a, struct its_ite, ite_list); - struct its_ite *iteb = container_of(b, struct its_ite, ite_list); - - if (itea->event_id < iteb->event_id) - return -1; - else - return 1; -} - -static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - gpa_t base = device->itt_addr; - struct its_ite *ite; - int ret; - int ite_esz = abi->ite_esz; - - list_sort(NULL, &device->itt_head, vgic_its_ite_cmp); - - list_for_each_entry(ite, &device->itt_head, ite_list) { - gpa_t gpa = base + ite->event_id * ite_esz; - - /* - * If an LPI carries the HW bit, this means that this - * interrupt is controlled by GICv4, and we do not - * have direct access to that state. Let's simply fail - * the save operation... - */ - if (ite->irq->hw) - return -EACCES; - - ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz); - if (ret) - return ret; - } - return 0; -} - -/** - * vgic_its_restore_itt - restore the ITT of a device - * - * @its: its handle - * @dev: device handle - * - * Return 0 on success, < 0 on error - */ -static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - gpa_t base = dev->itt_addr; - int ret; - int ite_esz = abi->ite_esz; - size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz; - - ret = scan_its_table(its, base, max_size, ite_esz, 0, - vgic_its_restore_ite, dev); - - /* scan_its_table returns +1 if all ITEs are invalid */ - if (ret > 0) - ret = 0; - - return ret; -} - -/** - * vgic_its_save_dte - Save a device table entry at a given GPA - * - * @its: ITS handle - * @dev: ITS device - * @ptr: GPA - */ -static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, - gpa_t ptr, int dte_esz) -{ - struct kvm *kvm = its->dev->kvm; - u64 val, itt_addr_field; - u32 next_offset; - - itt_addr_field = dev->itt_addr >> 8; - next_offset = compute_next_devid_offset(&its->device_list, dev); - val = (1ULL << KVM_ITS_DTE_VALID_SHIFT | - ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) | - (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | - (dev->num_eventid_bits - 1)); - val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); -} - -/** - * vgic_its_restore_dte - restore a device table entry - * - * @its: its handle - * @id: device id the DTE corresponds to - * @ptr: kernel VA where the 8 byte DTE is located - * @opaque: unused - * - * Return: < 0 on error, 0 if the dte is the last one, id offset to the - * next dte otherwise - */ -static int vgic_its_restore_dte(struct vgic_its *its, u32 id, - void *ptr, void *opaque) -{ - struct its_device *dev; - gpa_t itt_addr; - u8 num_eventid_bits; - u64 entry = *(u64 *)ptr; - bool valid; - u32 offset; - int ret; - - entry = le64_to_cpu(entry); - - valid = entry >> KVM_ITS_DTE_VALID_SHIFT; - num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1; - itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK) - >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8; - - if (!valid) - return 1; - - /* dte entry is valid */ - offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT; - - dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits); - if (IS_ERR(dev)) - return PTR_ERR(dev); - - ret = vgic_its_restore_itt(its, dev); - if (ret) { - vgic_its_free_device(its->dev->kvm, dev); - return ret; - } - - return offset; -} - -static int vgic_its_device_cmp(void *priv, struct list_head *a, - struct list_head *b) -{ - struct its_device *deva = container_of(a, struct its_device, dev_list); - struct its_device *devb = container_of(b, struct its_device, dev_list); - - if (deva->device_id < devb->device_id) - return -1; - else - return 1; -} - -/** - * vgic_its_save_device_tables - Save the device table and all ITT - * into guest RAM - * - * L1/L2 handling is hidden by vgic_its_check_id() helper which directly - * returns the GPA of the device entry - */ -static int vgic_its_save_device_tables(struct vgic_its *its) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 baser = its->baser_device_table; - struct its_device *dev; - int dte_esz = abi->dte_esz; - - if (!(baser & GITS_BASER_VALID)) - return 0; - - list_sort(NULL, &its->device_list, vgic_its_device_cmp); - - list_for_each_entry(dev, &its->device_list, dev_list) { - int ret; - gpa_t eaddr; - - if (!vgic_its_check_id(its, baser, - dev->device_id, &eaddr)) - return -EINVAL; - - ret = vgic_its_save_itt(its, dev); - if (ret) - return ret; - - ret = vgic_its_save_dte(its, dev, eaddr, dte_esz); - if (ret) - return ret; - } - return 0; -} - -/** - * handle_l1_dte - callback used for L1 device table entries (2 stage case) - * - * @its: its handle - * @id: index of the entry in the L1 table - * @addr: kernel VA - * @opaque: unused - * - * L1 table entries are scanned by steps of 1 entry - * Return < 0 if error, 0 if last dte was found when scanning the L2 - * table, +1 otherwise (meaning next L1 entry must be scanned) - */ -static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr, - void *opaque) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - int l2_start_id = id * (SZ_64K / abi->dte_esz); - u64 entry = *(u64 *)addr; - int dte_esz = abi->dte_esz; - gpa_t gpa; - int ret; - - entry = le64_to_cpu(entry); - - if (!(entry & KVM_ITS_L1E_VALID_MASK)) - return 1; - - gpa = entry & KVM_ITS_L1E_ADDR_MASK; - - ret = scan_its_table(its, gpa, SZ_64K, dte_esz, - l2_start_id, vgic_its_restore_dte, NULL); - - return ret; -} - -/** - * vgic_its_restore_device_tables - Restore the device table and all ITT - * from guest RAM to internal data structs - */ -static int vgic_its_restore_device_tables(struct vgic_its *its) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 baser = its->baser_device_table; - int l1_esz, ret; - int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; - gpa_t l1_gpa; - - if (!(baser & GITS_BASER_VALID)) - return 0; - - l1_gpa = GITS_BASER_ADDR_48_to_52(baser); - - if (baser & GITS_BASER_INDIRECT) { - l1_esz = GITS_LVL1_ENTRY_SIZE; - ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, - handle_l1_dte, NULL); - } else { - l1_esz = abi->dte_esz; - ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0, - vgic_its_restore_dte, NULL); - } - - /* scan_its_table returns +1 if all entries are invalid */ - if (ret > 0) - ret = 0; - - return ret; -} - -static int vgic_its_save_cte(struct vgic_its *its, - struct its_collection *collection, - gpa_t gpa, int esz) -{ - u64 val; - - val = (1ULL << KVM_ITS_CTE_VALID_SHIFT | - ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | - collection->collection_id); - val = cpu_to_le64(val); - return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); -} - -static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) -{ - struct its_collection *collection; - struct kvm *kvm = its->dev->kvm; - u32 target_addr, coll_id; - u64 val; - int ret; - - BUG_ON(esz > sizeof(val)); - ret = kvm_read_guest_lock(kvm, gpa, &val, esz); - if (ret) - return ret; - val = le64_to_cpu(val); - if (!(val & KVM_ITS_CTE_VALID_MASK)) - return 0; - - target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT); - coll_id = val & KVM_ITS_CTE_ICID_MASK; - - if (target_addr != COLLECTION_NOT_MAPPED && - target_addr >= atomic_read(&kvm->online_vcpus)) - return -EINVAL; - - collection = find_collection(its, coll_id); - if (collection) - return -EEXIST; - ret = vgic_its_alloc_collection(its, &collection, coll_id); - if (ret) - return ret; - collection->target_addr = target_addr; - return 1; -} - -/** - * vgic_its_save_collection_table - Save the collection table into - * guest RAM - */ -static int vgic_its_save_collection_table(struct vgic_its *its) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 baser = its->baser_coll_table; - gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); - struct its_collection *collection; - u64 val; - size_t max_size, filled = 0; - int ret, cte_esz = abi->cte_esz; - - if (!(baser & GITS_BASER_VALID)) - return 0; - - max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; - - list_for_each_entry(collection, &its->collection_list, coll_list) { - ret = vgic_its_save_cte(its, collection, gpa, cte_esz); - if (ret) - return ret; - gpa += cte_esz; - filled += cte_esz; - } - - if (filled == max_size) - return 0; - - /* - * table is not fully filled, add a last dummy element - * with valid bit unset - */ - val = 0; - BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); - return ret; -} - -/** - * vgic_its_restore_collection_table - reads the collection table - * in guest memory and restores the ITS internal state. Requires the - * BASER registers to be restored before. - */ -static int vgic_its_restore_collection_table(struct vgic_its *its) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - u64 baser = its->baser_coll_table; - int cte_esz = abi->cte_esz; - size_t max_size, read = 0; - gpa_t gpa; - int ret; - - if (!(baser & GITS_BASER_VALID)) - return 0; - - gpa = GITS_BASER_ADDR_48_to_52(baser); - - max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; - - while (read < max_size) { - ret = vgic_its_restore_cte(its, gpa, cte_esz); - if (ret <= 0) - break; - gpa += cte_esz; - read += cte_esz; - } - - if (ret > 0) - return 0; - - return ret; -} - -/** - * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM - * according to v0 ABI - */ -static int vgic_its_save_tables_v0(struct vgic_its *its) -{ - int ret; - - ret = vgic_its_save_device_tables(its); - if (ret) - return ret; - - return vgic_its_save_collection_table(its); -} - -/** - * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM - * to internal data structs according to V0 ABI - * - */ -static int vgic_its_restore_tables_v0(struct vgic_its *its) -{ - int ret; - - ret = vgic_its_restore_collection_table(its); - if (ret) - return ret; - - return vgic_its_restore_device_tables(its); -} - -static int vgic_its_commit_v0(struct vgic_its *its) -{ - const struct vgic_its_abi *abi; - - abi = vgic_its_get_abi(its); - its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK; - its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK; - - its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5) - << GITS_BASER_ENTRY_SIZE_SHIFT); - - its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5) - << GITS_BASER_ENTRY_SIZE_SHIFT); - return 0; -} - -static void vgic_its_reset(struct kvm *kvm, struct vgic_its *its) -{ - /* We need to keep the ABI specific field values */ - its->baser_coll_table &= ~GITS_BASER_VALID; - its->baser_device_table &= ~GITS_BASER_VALID; - its->cbaser = 0; - its->creadr = 0; - its->cwriter = 0; - its->enabled = 0; - vgic_its_free_device_list(kvm, its); - vgic_its_free_collection_list(kvm, its); -} - -static int vgic_its_has_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: - switch (attr->attr) { - case KVM_VGIC_ITS_ADDR_TYPE: - return 0; - } - break; - case KVM_DEV_ARM_VGIC_GRP_CTRL: - switch (attr->attr) { - case KVM_DEV_ARM_VGIC_CTRL_INIT: - return 0; - case KVM_DEV_ARM_ITS_CTRL_RESET: - return 0; - case KVM_DEV_ARM_ITS_SAVE_TABLES: - return 0; - case KVM_DEV_ARM_ITS_RESTORE_TABLES: - return 0; - } - break; - case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: - return vgic_its_has_attr_regs(dev, attr); - } - return -ENXIO; -} - -static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) -{ - const struct vgic_its_abi *abi = vgic_its_get_abi(its); - int ret = 0; - - if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ - return 0; - - mutex_lock(&kvm->lock); - mutex_lock(&its->its_lock); - - if (!lock_all_vcpus(kvm)) { - mutex_unlock(&its->its_lock); - mutex_unlock(&kvm->lock); - return -EBUSY; - } - - switch (attr) { - case KVM_DEV_ARM_ITS_CTRL_RESET: - vgic_its_reset(kvm, its); - break; - case KVM_DEV_ARM_ITS_SAVE_TABLES: - ret = abi->save_tables(its); - break; - case KVM_DEV_ARM_ITS_RESTORE_TABLES: - ret = abi->restore_tables(its); - break; - } - - unlock_all_vcpus(kvm); - mutex_unlock(&its->its_lock); - mutex_unlock(&kvm->lock); - return ret; -} - -static int vgic_its_set_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - struct vgic_its *its = dev->private; - int ret; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - unsigned long type = (unsigned long)attr->attr; - u64 addr; - - if (type != KVM_VGIC_ITS_ADDR_TYPE) - return -ENODEV; - - if (copy_from_user(&addr, uaddr, sizeof(addr))) - return -EFAULT; - - ret = vgic_check_ioaddr(dev->kvm, &its->vgic_its_base, - addr, SZ_64K); - if (ret) - return ret; - - return vgic_register_its_iodev(dev->kvm, its, addr); - } - case KVM_DEV_ARM_VGIC_GRP_CTRL: - return vgic_its_ctrl(dev->kvm, its, attr->attr); - case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 reg; - - if (get_user(reg, uaddr)) - return -EFAULT; - - return vgic_its_attr_regs_access(dev, attr, ®, true); - } - } - return -ENXIO; -} - -static int vgic_its_get_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: { - struct vgic_its *its = dev->private; - u64 addr = its->vgic_its_base; - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - unsigned long type = (unsigned long)attr->attr; - - if (type != KVM_VGIC_ITS_ADDR_TYPE) - return -ENODEV; - - if (copy_to_user(uaddr, &addr, sizeof(addr))) - return -EFAULT; - break; - } - case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 reg; - int ret; - - ret = vgic_its_attr_regs_access(dev, attr, ®, false); - if (ret) - return ret; - return put_user(reg, uaddr); - } - default: - return -ENXIO; - } - - return 0; -} - -static struct kvm_device_ops kvm_arm_vgic_its_ops = { - .name = "kvm-arm-vgic-its", - .create = vgic_its_create, - .destroy = vgic_its_destroy, - .set_attr = vgic_its_set_attr, - .get_attr = vgic_its_get_attr, - .has_attr = vgic_its_has_attr, -}; - -int kvm_vgic_register_its_device(void) -{ - return kvm_register_device_ops(&kvm_arm_vgic_its_ops, - KVM_DEV_TYPE_ARM_VGIC_ITS); -} diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c deleted file mode 100644 index 44419679f91a..000000000000 --- a/virt/kvm/arm/vgic/vgic-kvm-device.c +++ /dev/null @@ -1,741 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGIC: KVM DEVICE API - * - * Copyright (C) 2015 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ -#include <linux/kvm_host.h> -#include <kvm/arm_vgic.h> -#include <linux/uaccess.h> -#include <asm/kvm_mmu.h> -#include <asm/cputype.h> -#include "vgic.h" - -/* common helpers */ - -int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr, - phys_addr_t addr, phys_addr_t alignment) -{ - if (addr & ~kvm_phys_mask(kvm)) - return -E2BIG; - - if (!IS_ALIGNED(addr, alignment)) - return -EINVAL; - - if (!IS_VGIC_ADDR_UNDEF(*ioaddr)) - return -EEXIST; - - return 0; -} - -static int vgic_check_type(struct kvm *kvm, int type_needed) -{ - if (kvm->arch.vgic.vgic_model != type_needed) - return -ENODEV; - else - return 0; -} - -/** - * kvm_vgic_addr - set or get vgic VM base addresses - * @kvm: pointer to the vm struct - * @type: the VGIC addr type, one of KVM_VGIC_V[23]_ADDR_TYPE_XXX - * @addr: pointer to address value - * @write: if true set the address in the VM address space, if false read the - * address - * - * Set or get the vgic base addresses for the distributor and the virtual CPU - * interface in the VM physical address space. These addresses are properties - * of the emulated core/SoC and therefore user space initially knows this - * information. - * Check them for sanity (alignment, double assignment). We can't check for - * overlapping regions in case of a virtual GICv3 here, since we don't know - * the number of VCPUs yet, so we defer this check to map_resources(). - */ -int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) -{ - int r = 0; - struct vgic_dist *vgic = &kvm->arch.vgic; - phys_addr_t *addr_ptr, alignment; - u64 undef_value = VGIC_ADDR_UNDEF; - - mutex_lock(&kvm->lock); - switch (type) { - case KVM_VGIC_V2_ADDR_TYPE_DIST: - r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); - addr_ptr = &vgic->vgic_dist_base; - alignment = SZ_4K; - break; - case KVM_VGIC_V2_ADDR_TYPE_CPU: - r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); - addr_ptr = &vgic->vgic_cpu_base; - alignment = SZ_4K; - break; - case KVM_VGIC_V3_ADDR_TYPE_DIST: - r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); - addr_ptr = &vgic->vgic_dist_base; - alignment = SZ_64K; - break; - case KVM_VGIC_V3_ADDR_TYPE_REDIST: { - struct vgic_redist_region *rdreg; - - r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); - if (r) - break; - if (write) { - r = vgic_v3_set_redist_base(kvm, 0, *addr, 0); - goto out; - } - rdreg = list_first_entry(&vgic->rd_regions, - struct vgic_redist_region, list); - if (!rdreg) - addr_ptr = &undef_value; - else - addr_ptr = &rdreg->base; - break; - } - case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: - { - struct vgic_redist_region *rdreg; - u8 index; - - r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); - if (r) - break; - - index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK; - - if (write) { - gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK; - u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK) - >> KVM_VGIC_V3_RDIST_COUNT_SHIFT; - u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK) - >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT; - - if (!count || flags) - r = -EINVAL; - else - r = vgic_v3_set_redist_base(kvm, index, - base, count); - goto out; - } - - rdreg = vgic_v3_rdist_region_from_index(kvm, index); - if (!rdreg) { - r = -ENOENT; - goto out; - } - - *addr = index; - *addr |= rdreg->base; - *addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; - goto out; - } - default: - r = -ENODEV; - } - - if (r) - goto out; - - if (write) { - r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment); - if (!r) - *addr_ptr = *addr; - } else { - *addr = *addr_ptr; - } - -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int vgic_set_common_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int r; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 addr; - unsigned long type = (unsigned long)attr->attr; - - if (copy_from_user(&addr, uaddr, sizeof(addr))) - return -EFAULT; - - r = kvm_vgic_addr(dev->kvm, type, &addr, true); - return (r == -ENODEV) ? -ENXIO : r; - } - case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u32 val; - int ret = 0; - - if (get_user(val, uaddr)) - return -EFAULT; - - /* - * We require: - * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs - * - at most 1024 interrupts - * - a multiple of 32 interrupts - */ - if (val < (VGIC_NR_PRIVATE_IRQS + 32) || - val > VGIC_MAX_RESERVED || - (val & 31)) - return -EINVAL; - - mutex_lock(&dev->kvm->lock); - - if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) - ret = -EBUSY; - else - dev->kvm->arch.vgic.nr_spis = - val - VGIC_NR_PRIVATE_IRQS; - - mutex_unlock(&dev->kvm->lock); - - return ret; - } - case KVM_DEV_ARM_VGIC_GRP_CTRL: { - switch (attr->attr) { - case KVM_DEV_ARM_VGIC_CTRL_INIT: - mutex_lock(&dev->kvm->lock); - r = vgic_init(dev->kvm); - mutex_unlock(&dev->kvm->lock); - return r; - } - break; - } - } - - return -ENXIO; -} - -static int vgic_get_common_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int r = -ENXIO; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 addr; - unsigned long type = (unsigned long)attr->attr; - - r = kvm_vgic_addr(dev->kvm, type, &addr, false); - if (r) - return (r == -ENODEV) ? -ENXIO : r; - - if (copy_to_user(uaddr, &addr, sizeof(addr))) - return -EFAULT; - break; - } - case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - - r = put_user(dev->kvm->arch.vgic.nr_spis + - VGIC_NR_PRIVATE_IRQS, uaddr); - break; - } - } - - return r; -} - -static int vgic_create(struct kvm_device *dev, u32 type) -{ - return kvm_vgic_create(dev->kvm, type); -} - -static void vgic_destroy(struct kvm_device *dev) -{ - kfree(dev); -} - -int kvm_register_vgic_device(unsigned long type) -{ - int ret = -ENODEV; - - switch (type) { - case KVM_DEV_TYPE_ARM_VGIC_V2: - ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, - KVM_DEV_TYPE_ARM_VGIC_V2); - break; - case KVM_DEV_TYPE_ARM_VGIC_V3: - ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, - KVM_DEV_TYPE_ARM_VGIC_V3); - - if (ret) - break; - ret = kvm_vgic_register_its_device(); - break; - } - - return ret; -} - -int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, - struct vgic_reg_attr *reg_attr) -{ - int cpuid; - - cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >> - KVM_DEV_ARM_VGIC_CPUID_SHIFT; - - if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) - return -EINVAL; - - reg_attr->vcpu = kvm_get_vcpu(dev->kvm, cpuid); - reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; - - return 0; -} - -/* unlocks vcpus from @vcpu_lock_idx and smaller */ -static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) -{ - struct kvm_vcpu *tmp_vcpu; - - for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { - tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); - mutex_unlock(&tmp_vcpu->mutex); - } -} - -void unlock_all_vcpus(struct kvm *kvm) -{ - unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); -} - -/* Returns true if all vcpus were locked, false otherwise */ -bool lock_all_vcpus(struct kvm *kvm) -{ - struct kvm_vcpu *tmp_vcpu; - int c; - - /* - * Any time a vcpu is run, vcpu_load is called which tries to grab the - * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure - * that no other VCPUs are run and fiddle with the vgic state while we - * access it. - */ - kvm_for_each_vcpu(c, tmp_vcpu, kvm) { - if (!mutex_trylock(&tmp_vcpu->mutex)) { - unlock_vcpus(kvm, c - 1); - return false; - } - } - - return true; -} - -/** - * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state - * - * @dev: kvm device handle - * @attr: kvm device attribute - * @reg: address the value is read or written - * @is_write: true if userspace is writing a register - */ -static int vgic_v2_attr_regs_access(struct kvm_device *dev, - struct kvm_device_attr *attr, - u32 *reg, bool is_write) -{ - struct vgic_reg_attr reg_attr; - gpa_t addr; - struct kvm_vcpu *vcpu; - int ret; - - ret = vgic_v2_parse_attr(dev, attr, ®_attr); - if (ret) - return ret; - - vcpu = reg_attr.vcpu; - addr = reg_attr.addr; - - mutex_lock(&dev->kvm->lock); - - ret = vgic_init(dev->kvm); - if (ret) - goto out; - - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: - ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, reg); - break; - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, reg); - break; - default: - ret = -EINVAL; - break; - } - - unlock_all_vcpus(dev->kvm); -out: - mutex_unlock(&dev->kvm->lock); - return ret; -} - -static int vgic_v2_set_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int ret; - - ret = vgic_set_common_attr(dev, attr); - if (ret != -ENXIO) - return ret; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u32 reg; - - if (get_user(reg, uaddr)) - return -EFAULT; - - return vgic_v2_attr_regs_access(dev, attr, ®, true); - } - } - - return -ENXIO; -} - -static int vgic_v2_get_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int ret; - - ret = vgic_get_common_attr(dev, attr); - if (ret != -ENXIO) - return ret; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u32 reg = 0; - - ret = vgic_v2_attr_regs_access(dev, attr, ®, false); - if (ret) - return ret; - return put_user(reg, uaddr); - } - } - - return -ENXIO; -} - -static int vgic_v2_has_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: - switch (attr->attr) { - case KVM_VGIC_V2_ADDR_TYPE_DIST: - case KVM_VGIC_V2_ADDR_TYPE_CPU: - return 0; - } - break; - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: - return vgic_v2_has_attr_regs(dev, attr); - case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: - return 0; - case KVM_DEV_ARM_VGIC_GRP_CTRL: - switch (attr->attr) { - case KVM_DEV_ARM_VGIC_CTRL_INIT: - return 0; - } - } - return -ENXIO; -} - -struct kvm_device_ops kvm_arm_vgic_v2_ops = { - .name = "kvm-arm-vgic-v2", - .create = vgic_create, - .destroy = vgic_destroy, - .set_attr = vgic_v2_set_attr, - .get_attr = vgic_v2_get_attr, - .has_attr = vgic_v2_has_attr, -}; - -int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, - struct vgic_reg_attr *reg_attr) -{ - unsigned long vgic_mpidr, mpidr_reg; - - /* - * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, - * attr might not hold MPIDR. Hence assume vcpu0. - */ - if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { - vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> - KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; - - mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); - reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); - } else { - reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); - } - - if (!reg_attr->vcpu) - return -EINVAL; - - reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; - - return 0; -} - -/* - * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state - * - * @dev: kvm device handle - * @attr: kvm device attribute - * @reg: address the value is read or written - * @is_write: true if userspace is writing a register - */ -static int vgic_v3_attr_regs_access(struct kvm_device *dev, - struct kvm_device_attr *attr, - u64 *reg, bool is_write) -{ - struct vgic_reg_attr reg_attr; - gpa_t addr; - struct kvm_vcpu *vcpu; - int ret; - u32 tmp32; - - ret = vgic_v3_parse_attr(dev, attr, ®_attr); - if (ret) - return ret; - - vcpu = reg_attr.vcpu; - addr = reg_attr.addr; - - mutex_lock(&dev->kvm->lock); - - if (unlikely(!vgic_initialized(dev->kvm))) { - ret = -EBUSY; - goto out; - } - - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - if (is_write) - tmp32 = *reg; - - ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &tmp32); - if (!is_write) - *reg = tmp32; - break; - case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: - if (is_write) - tmp32 = *reg; - - ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &tmp32); - if (!is_write) - *reg = tmp32; - break; - case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { - u64 regid; - - regid = (attr->attr & KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK); - ret = vgic_v3_cpu_sysregs_uaccess(vcpu, is_write, - regid, reg); - break; - } - case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { - unsigned int info, intid; - - info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> - KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; - if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { - intid = attr->attr & - KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; - ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, - intid, reg); - } else { - ret = -EINVAL; - } - break; - } - default: - ret = -EINVAL; - break; - } - - unlock_all_vcpus(dev->kvm); -out: - mutex_unlock(&dev->kvm->lock); - return ret; -} - -static int vgic_v3_set_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int ret; - - ret = vgic_set_common_attr(dev, attr); - if (ret != -ENXIO) - return ret; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u32 tmp32; - u64 reg; - - if (get_user(tmp32, uaddr)) - return -EFAULT; - - reg = tmp32; - return vgic_v3_attr_regs_access(dev, attr, ®, true); - } - case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 reg; - - if (get_user(reg, uaddr)) - return -EFAULT; - - return vgic_v3_attr_regs_access(dev, attr, ®, true); - } - case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u64 reg; - u32 tmp32; - - if (get_user(tmp32, uaddr)) - return -EFAULT; - - reg = tmp32; - return vgic_v3_attr_regs_access(dev, attr, ®, true); - } - case KVM_DEV_ARM_VGIC_GRP_CTRL: { - int ret; - - switch (attr->attr) { - case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: - mutex_lock(&dev->kvm->lock); - - if (!lock_all_vcpus(dev->kvm)) { - mutex_unlock(&dev->kvm->lock); - return -EBUSY; - } - ret = vgic_v3_save_pending_tables(dev->kvm); - unlock_all_vcpus(dev->kvm); - mutex_unlock(&dev->kvm->lock); - return ret; - } - break; - } - } - return -ENXIO; -} - -static int vgic_v3_get_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - int ret; - - ret = vgic_get_common_attr(dev, attr); - if (ret != -ENXIO) - return ret; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u64 reg; - u32 tmp32; - - ret = vgic_v3_attr_regs_access(dev, attr, ®, false); - if (ret) - return ret; - tmp32 = reg; - return put_user(tmp32, uaddr); - } - case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { - u64 __user *uaddr = (u64 __user *)(long)attr->addr; - u64 reg; - - ret = vgic_v3_attr_regs_access(dev, attr, ®, false); - if (ret) - return ret; - return put_user(reg, uaddr); - } - case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { - u32 __user *uaddr = (u32 __user *)(long)attr->addr; - u64 reg; - u32 tmp32; - - ret = vgic_v3_attr_regs_access(dev, attr, ®, false); - if (ret) - return ret; - tmp32 = reg; - return put_user(tmp32, uaddr); - } - } - return -ENXIO; -} - -static int vgic_v3_has_attr(struct kvm_device *dev, - struct kvm_device_attr *attr) -{ - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_ADDR: - switch (attr->attr) { - case KVM_VGIC_V3_ADDR_TYPE_DIST: - case KVM_VGIC_V3_ADDR_TYPE_REDIST: - case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: - return 0; - } - break; - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: - case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: - return vgic_v3_has_attr_regs(dev, attr); - case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: - return 0; - case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { - if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> - KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == - VGIC_LEVEL_INFO_LINE_LEVEL) - return 0; - break; - } - case KVM_DEV_ARM_VGIC_GRP_CTRL: - switch (attr->attr) { - case KVM_DEV_ARM_VGIC_CTRL_INIT: - return 0; - case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: - return 0; - } - } - return -ENXIO; -} - -struct kvm_device_ops kvm_arm_vgic_v3_ops = { - .name = "kvm-arm-vgic-v3", - .create = vgic_create, - .destroy = vgic_destroy, - .set_attr = vgic_v3_set_attr, - .get_attr = vgic_v3_get_attr, - .has_attr = vgic_v3_has_attr, -}; diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c deleted file mode 100644 index a016f07adc28..000000000000 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ /dev/null @@ -1,550 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGICv2 MMIO handling functions - */ - -#include <linux/irqchip/arm-gic.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/nospec.h> - -#include <kvm/iodev.h> -#include <kvm/arm_vgic.h> - -#include "vgic.h" -#include "vgic-mmio.h" - -/* - * The Revision field in the IIDR have the following meanings: - * - * Revision 1: Report GICv2 interrupts as group 0 instead of group 1 - * Revision 2: Interrupt groups are guest-configurable and signaled using - * their configured groups. - */ - -static unsigned long vgic_mmio_read_v2_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; - u32 value; - - switch (addr & 0x0c) { - case GIC_DIST_CTRL: - value = vgic->enabled ? GICD_ENABLE : 0; - break; - case GIC_DIST_CTR: - value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; - value = (value >> 5) - 1; - value |= (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5; - break; - case GIC_DIST_IIDR: - value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | - (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | - (IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT); - break; - default: - return 0; - } - - return value; -} - -static void vgic_mmio_write_v2_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - bool was_enabled = dist->enabled; - - switch (addr & 0x0c) { - case GIC_DIST_CTRL: - dist->enabled = val & GICD_ENABLE; - if (!was_enabled && dist->enabled) - vgic_kick_vcpus(vcpu->kvm); - break; - case GIC_DIST_CTR: - case GIC_DIST_IIDR: - /* Nothing to do */ - return; - } -} - -static int vgic_mmio_uaccess_write_v2_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - switch (addr & 0x0c) { - case GIC_DIST_IIDR: - if (val != vgic_mmio_read_v2_misc(vcpu, addr, len)) - return -EINVAL; - - /* - * If we observe a write to GICD_IIDR we know that userspace - * has been updated and has had a chance to cope with older - * kernels (VGICv2 IIDR.Revision == 0) incorrectly reporting - * interrupts as group 1, and therefore we now allow groups to - * be user writable. Doing this by default would break - * migration from old kernels to new kernels with legacy - * userspace. - */ - vcpu->kvm->arch.vgic.v2_groups_user_writable = true; - return 0; - } - - vgic_mmio_write_v2_misc(vcpu, addr, len, val); - return 0; -} - -static int vgic_mmio_uaccess_write_v2_group(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - if (vcpu->kvm->arch.vgic.v2_groups_user_writable) - vgic_mmio_write_group(vcpu, addr, len, val); - - return 0; -} - -static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - int nr_vcpus = atomic_read(&source_vcpu->kvm->online_vcpus); - int intid = val & 0xf; - int targets = (val >> 16) & 0xff; - int mode = (val >> 24) & 0x03; - int c; - struct kvm_vcpu *vcpu; - unsigned long flags; - - switch (mode) { - case 0x0: /* as specified by targets */ - break; - case 0x1: - targets = (1U << nr_vcpus) - 1; /* all, ... */ - targets &= ~(1U << source_vcpu->vcpu_id); /* but self */ - break; - case 0x2: /* this very vCPU only */ - targets = (1U << source_vcpu->vcpu_id); - break; - case 0x3: /* reserved */ - return; - } - - kvm_for_each_vcpu(c, vcpu, source_vcpu->kvm) { - struct vgic_irq *irq; - - if (!(targets & (1U << c))) - continue; - - irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - irq->source |= 1U << source_vcpu->vcpu_id; - - vgic_queue_irq_unlock(source_vcpu->kvm, irq, flags); - vgic_put_irq(source_vcpu->kvm, irq); - } -} - -static unsigned long vgic_mmio_read_target(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 8); - int i; - u64 val = 0; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - val |= (u64)irq->targets << (i * 8); - - vgic_put_irq(vcpu->kvm, irq); - } - - return val; -} - -static void vgic_mmio_write_target(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 8); - u8 cpu_mask = GENMASK(atomic_read(&vcpu->kvm->online_vcpus) - 1, 0); - int i; - unsigned long flags; - - /* GICD_ITARGETSR[0-7] are read-only */ - if (intid < VGIC_NR_PRIVATE_IRQS) - return; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i); - int target; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - irq->targets = (val >> (i * 8)) & cpu_mask; - target = irq->targets ? __ffs(irq->targets) : 0; - irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target); - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -static unsigned long vgic_mmio_read_sgipend(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = addr & 0x0f; - int i; - u64 val = 0; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - val |= (u64)irq->source << (i * 8); - - vgic_put_irq(vcpu->kvm, irq); - } - return val; -} - -static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = addr & 0x0f; - int i; - unsigned long flags; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - irq->source &= ~((val >> (i * 8)) & 0xff); - if (!irq->source) - irq->pending_latch = false; - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = addr & 0x0f; - int i; - unsigned long flags; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - irq->source |= (val >> (i * 8)) & 0xff; - - if (irq->source) { - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } else { - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - } - vgic_put_irq(vcpu->kvm, irq); - } -} - -#define GICC_ARCH_VERSION_V2 0x2 - -/* These are for userland accesses only, there is no guest-facing emulation. */ -static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_vmcr vmcr; - u32 val; - - vgic_get_vmcr(vcpu, &vmcr); - - switch (addr & 0xff) { - case GIC_CPU_CTRL: - val = vmcr.grpen0 << GIC_CPU_CTRL_EnableGrp0_SHIFT; - val |= vmcr.grpen1 << GIC_CPU_CTRL_EnableGrp1_SHIFT; - val |= vmcr.ackctl << GIC_CPU_CTRL_AckCtl_SHIFT; - val |= vmcr.fiqen << GIC_CPU_CTRL_FIQEn_SHIFT; - val |= vmcr.cbpr << GIC_CPU_CTRL_CBPR_SHIFT; - val |= vmcr.eoim << GIC_CPU_CTRL_EOImodeNS_SHIFT; - - break; - case GIC_CPU_PRIMASK: - /* - * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the - * the PMR field as GICH_VMCR.VMPriMask rather than - * GICC_PMR.Priority, so we expose the upper five bits of - * priority mask to userspace using the lower bits in the - * unsigned long. - */ - val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >> - GICV_PMR_PRIORITY_SHIFT; - break; - case GIC_CPU_BINPOINT: - val = vmcr.bpr; - break; - case GIC_CPU_ALIAS_BINPOINT: - val = vmcr.abpr; - break; - case GIC_CPU_IDENT: - val = ((PRODUCT_ID_KVM << 20) | - (GICC_ARCH_VERSION_V2 << 16) | - IMPLEMENTER_ARM); - break; - default: - return 0; - } - - return val; -} - -static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_vmcr vmcr; - - vgic_get_vmcr(vcpu, &vmcr); - - switch (addr & 0xff) { - case GIC_CPU_CTRL: - vmcr.grpen0 = !!(val & GIC_CPU_CTRL_EnableGrp0); - vmcr.grpen1 = !!(val & GIC_CPU_CTRL_EnableGrp1); - vmcr.ackctl = !!(val & GIC_CPU_CTRL_AckCtl); - vmcr.fiqen = !!(val & GIC_CPU_CTRL_FIQEn); - vmcr.cbpr = !!(val & GIC_CPU_CTRL_CBPR); - vmcr.eoim = !!(val & GIC_CPU_CTRL_EOImodeNS); - - break; - case GIC_CPU_PRIMASK: - /* - * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the - * the PMR field as GICH_VMCR.VMPriMask rather than - * GICC_PMR.Priority, so we expose the upper five bits of - * priority mask to userspace using the lower bits in the - * unsigned long. - */ - vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) & - GICV_PMR_PRIORITY_MASK; - break; - case GIC_CPU_BINPOINT: - vmcr.bpr = val; - break; - case GIC_CPU_ALIAS_BINPOINT: - vmcr.abpr = val; - break; - } - - vgic_set_vmcr(vcpu, &vmcr); -} - -static unsigned long vgic_mmio_read_apr(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - int n; /* which APRn is this */ - - n = (addr >> 2) & 0x3; - - if (kvm_vgic_global_state.type == VGIC_V2) { - /* GICv2 hardware systems support max. 32 groups */ - if (n != 0) - return 0; - return vcpu->arch.vgic_cpu.vgic_v2.vgic_apr; - } else { - struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; - - if (n > vgic_v3_max_apr_idx(vcpu)) - return 0; - - n = array_index_nospec(n, 4); - - /* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */ - return vgicv3->vgic_ap1r[n]; - } -} - -static void vgic_mmio_write_apr(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - int n; /* which APRn is this */ - - n = (addr >> 2) & 0x3; - - if (kvm_vgic_global_state.type == VGIC_V2) { - /* GICv2 hardware systems support max. 32 groups */ - if (n != 0) - return; - vcpu->arch.vgic_cpu.vgic_v2.vgic_apr = val; - } else { - struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; - - if (n > vgic_v3_max_apr_idx(vcpu)) - return; - - n = array_index_nospec(n, 4); - - /* GICv3 only uses ICH_AP1Rn for memory mapped (GICv2) guests */ - vgicv3->vgic_ap1r[n] = val; - } -} - -static const struct vgic_register_region vgic_v2_dist_registers[] = { - REGISTER_DESC_WITH_LENGTH_UACCESS(GIC_DIST_CTRL, - vgic_mmio_read_v2_misc, vgic_mmio_write_v2_misc, - NULL, vgic_mmio_uaccess_write_v2_misc, - 12, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_IGROUP, - vgic_mmio_read_group, vgic_mmio_write_group, - NULL, vgic_mmio_uaccess_write_v2_group, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, - vgic_mmio_read_enable, vgic_mmio_write_senable, - NULL, vgic_uaccess_write_senable, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, - vgic_mmio_read_enable, vgic_mmio_write_cenable, - NULL, vgic_uaccess_write_cenable, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, - NULL, vgic_uaccess_write_spending, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, - NULL, vgic_uaccess_write_cpending, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, - vgic_mmio_read_active, vgic_mmio_write_sactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, - vgic_mmio_read_active, vgic_mmio_write_cactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, - vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, - 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_TARGET, - vgic_mmio_read_target, vgic_mmio_write_target, NULL, NULL, 8, - VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_CONFIG, - vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_DIST_SOFTINT, - vgic_mmio_read_raz, vgic_mmio_write_sgir, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_CLEAR, - vgic_mmio_read_sgipend, vgic_mmio_write_sgipendc, 16, - VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_LENGTH(GIC_DIST_SGI_PENDING_SET, - vgic_mmio_read_sgipend, vgic_mmio_write_sgipends, 16, - VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), -}; - -static const struct vgic_register_region vgic_v2_cpu_registers[] = { - REGISTER_DESC_WITH_LENGTH(GIC_CPU_CTRL, - vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_CPU_PRIMASK, - vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_CPU_BINPOINT, - vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_CPU_ALIAS_BINPOINT, - vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_CPU_ACTIVEPRIO, - vgic_mmio_read_apr, vgic_mmio_write_apr, 16, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GIC_CPU_IDENT, - vgic_mmio_read_vcpuif, vgic_mmio_write_vcpuif, 4, - VGIC_ACCESS_32bit), -}; - -unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev) -{ - dev->regions = vgic_v2_dist_registers; - dev->nr_regions = ARRAY_SIZE(vgic_v2_dist_registers); - - kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops); - - return SZ_4K; -} - -int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) -{ - const struct vgic_register_region *region; - struct vgic_io_device iodev; - struct vgic_reg_attr reg_attr; - struct kvm_vcpu *vcpu; - gpa_t addr; - int ret; - - ret = vgic_v2_parse_attr(dev, attr, ®_attr); - if (ret) - return ret; - - vcpu = reg_attr.vcpu; - addr = reg_attr.addr; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - iodev.regions = vgic_v2_dist_registers; - iodev.nr_regions = ARRAY_SIZE(vgic_v2_dist_registers); - iodev.base_addr = 0; - break; - case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: - iodev.regions = vgic_v2_cpu_registers; - iodev.nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers); - iodev.base_addr = 0; - break; - default: - return -ENXIO; - } - - /* We only support aligned 32-bit accesses. */ - if (addr & 3) - return -ENXIO; - - region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32)); - if (!region) - return -ENXIO; - - return 0; -} - -int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val) -{ - struct vgic_io_device dev = { - .regions = vgic_v2_cpu_registers, - .nr_regions = ARRAY_SIZE(vgic_v2_cpu_registers), - .iodev_type = IODEV_CPUIF, - }; - - return vgic_uaccess(vcpu, &dev, is_write, offset, val); -} - -int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val) -{ - struct vgic_io_device dev = { - .regions = vgic_v2_dist_registers, - .nr_regions = ARRAY_SIZE(vgic_v2_dist_registers), - .iodev_type = IODEV_DIST, - }; - - return vgic_uaccess(vcpu, &dev, is_write, offset, val); -} diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c deleted file mode 100644 index 89a14ec8b33b..000000000000 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ /dev/null @@ -1,1063 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGICv3 MMIO handling functions - */ - -#include <linux/bitfield.h> -#include <linux/irqchip/arm-gic-v3.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/interrupt.h> -#include <kvm/iodev.h> -#include <kvm/arm_vgic.h> - -#include <asm/kvm_emulate.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> - -#include "vgic.h" -#include "vgic-mmio.h" - -/* extract @num bytes at @offset bytes offset in data */ -unsigned long extract_bytes(u64 data, unsigned int offset, - unsigned int num) -{ - return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0); -} - -/* allows updates of any half of a 64-bit register (or the whole thing) */ -u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len, - unsigned long val) -{ - int lower = (offset & 4) * 8; - int upper = lower + 8 * len - 1; - - reg &= ~GENMASK_ULL(upper, lower); - val &= GENMASK_ULL(len * 8 - 1, 0); - - return reg | ((u64)val << lower); -} - -bool vgic_has_its(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - - if (dist->vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3) - return false; - - return dist->has_its; -} - -bool vgic_supports_direct_msis(struct kvm *kvm) -{ - return (kvm_vgic_global_state.has_gicv4_1 || - (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); -} - -/* - * The Revision field in the IIDR have the following meanings: - * - * Revision 2: Interrupt groups are guest-configurable and signaled using - * their configured groups. - */ - -static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; - u32 value = 0; - - switch (addr & 0x0c) { - case GICD_CTLR: - if (vgic->enabled) - value |= GICD_CTLR_ENABLE_SS_G1; - value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS; - if (vgic->nassgireq) - value |= GICD_CTLR_nASSGIreq; - break; - case GICD_TYPER: - value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS; - value = (value >> 5) - 1; - if (vgic_has_its(vcpu->kvm)) { - value |= (INTERRUPT_ID_BITS_ITS - 1) << 19; - value |= GICD_TYPER_LPIS; - } else { - value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19; - } - break; - case GICD_TYPER2: - if (kvm_vgic_global_state.has_gicv4_1) - value = GICD_TYPER2_nASSGIcap; - break; - case GICD_IIDR: - value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) | - (vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) | - (IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT); - break; - default: - return 0; - } - - return value; -} - -static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - switch (addr & 0x0c) { - case GICD_CTLR: { - bool was_enabled, is_hwsgi; - - mutex_lock(&vcpu->kvm->lock); - - was_enabled = dist->enabled; - is_hwsgi = dist->nassgireq; - - dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; - - /* Not a GICv4.1? No HW SGIs */ - if (!kvm_vgic_global_state.has_gicv4_1) - val &= ~GICD_CTLR_nASSGIreq; - - /* Dist stays enabled? nASSGIreq is RO */ - if (was_enabled && dist->enabled) { - val &= ~GICD_CTLR_nASSGIreq; - val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi); - } - - /* Switching HW SGIs? */ - dist->nassgireq = val & GICD_CTLR_nASSGIreq; - if (is_hwsgi != dist->nassgireq) - vgic_v4_configure_vsgis(vcpu->kvm); - - if (kvm_vgic_global_state.has_gicv4_1 && - was_enabled != dist->enabled) - kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4); - else if (!was_enabled && dist->enabled) - vgic_kick_vcpus(vcpu->kvm); - - mutex_unlock(&vcpu->kvm->lock); - break; - } - case GICD_TYPER: - case GICD_TYPER2: - case GICD_IIDR: - /* This is at best for documentation purposes... */ - return; - } -} - -static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - switch (addr & 0x0c) { - case GICD_TYPER2: - case GICD_IIDR: - if (val != vgic_mmio_read_v3_misc(vcpu, addr, len)) - return -EINVAL; - return 0; - case GICD_CTLR: - /* Not a GICv4.1? No HW SGIs */ - if (!kvm_vgic_global_state.has_gicv4_1) - val &= ~GICD_CTLR_nASSGIreq; - - dist->enabled = val & GICD_CTLR_ENABLE_SS_G1; - dist->nassgireq = val & GICD_CTLR_nASSGIreq; - return 0; - } - - vgic_mmio_write_v3_misc(vcpu, addr, len, val); - return 0; -} - -static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - int intid = VGIC_ADDR_TO_INTID(addr, 64); - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid); - unsigned long ret = 0; - - if (!irq) - return 0; - - /* The upper word is RAZ for us. */ - if (!(addr & 4)) - ret = extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len); - - vgic_put_irq(vcpu->kvm, irq); - return ret; -} - -static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - int intid = VGIC_ADDR_TO_INTID(addr, 64); - struct vgic_irq *irq; - unsigned long flags; - - /* The upper word is WI for us since we don't implement Aff3. */ - if (addr & 4) - return; - - irq = vgic_get_irq(vcpu->kvm, NULL, intid); - - if (!irq) - return; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - /* We only care about and preserve Aff0, Aff1 and Aff2. */ - irq->mpidr = val & GENMASK(23, 0); - irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr); - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); -} - -static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0; -} - - -static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - bool was_enabled = vgic_cpu->lpis_enabled; - - if (!vgic_has_its(vcpu->kvm)) - return; - - vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS; - - if (was_enabled && !vgic_cpu->lpis_enabled) { - vgic_flush_pending_lpis(vcpu); - vgic_its_invalidate_cache(vcpu->kvm); - } - - if (!was_enabled && vgic_cpu->lpis_enabled) - vgic_enable_lpis(vcpu); -} - -static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_redist_region *rdreg = vgic_cpu->rdreg; - int target_vcpu_id = vcpu->vcpu_id; - gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + - (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; - u64 value; - - value = (u64)(mpidr & GENMASK(23, 0)) << 32; - value |= ((target_vcpu_id & 0xffff) << 8); - - if (addr == last_rdist_typer) - value |= GICR_TYPER_LAST; - if (vgic_has_its(vcpu->kvm)) - value |= GICR_TYPER_PLPIS; - - return extract_bytes(value, addr & 7, len); -} - -static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0); -} - -static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - switch (addr & 0xffff) { - case GICD_PIDR2: - /* report a GICv3 compliant implementation */ - return 0x3b; - } - - return 0; -} - -static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* - * pending state of interrupt is latched in pending_latch variable. - * Userspace will save and restore pending state and line_level - * separately. - * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt - * for handling of ISPENDR and ICPENDR. - */ - for (i = 0; i < len * 8; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - bool state = irq->pending_latch; - - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - int err; - - err = irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &state); - WARN_ON(err); - } - - if (state) - value |= (1U << i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for (i = 0; i < len * 8; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (test_bit(i, &val)) { - /* - * pending_latch is set irrespective of irq type - * (level or edge) to avoid dependency that VM should - * restore irq config before pending info. - */ - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } else { - irq->pending_latch = false; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - } - - vgic_put_irq(vcpu->kvm, irq); - } - - return 0; -} - -/* We want to avoid outer shareable. */ -u64 vgic_sanitise_shareability(u64 field) -{ - switch (field) { - case GIC_BASER_OuterShareable: - return GIC_BASER_InnerShareable; - default: - return field; - } -} - -/* Avoid any inner non-cacheable mapping. */ -u64 vgic_sanitise_inner_cacheability(u64 field) -{ - switch (field) { - case GIC_BASER_CACHE_nCnB: - case GIC_BASER_CACHE_nC: - return GIC_BASER_CACHE_RaWb; - default: - return field; - } -} - -/* Non-cacheable or same-as-inner are OK. */ -u64 vgic_sanitise_outer_cacheability(u64 field) -{ - switch (field) { - case GIC_BASER_CACHE_SameAsInner: - case GIC_BASER_CACHE_nC: - return field; - default: - return GIC_BASER_CACHE_nC; - } -} - -u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift, - u64 (*sanitise_fn)(u64)) -{ - u64 field = (reg & field_mask) >> field_shift; - - field = sanitise_fn(field) << field_shift; - return (reg & ~field_mask) | field; -} - -#define PROPBASER_RES0_MASK \ - (GENMASK_ULL(63, 59) | GENMASK_ULL(55, 52) | GENMASK_ULL(6, 5)) -#define PENDBASER_RES0_MASK \ - (BIT_ULL(63) | GENMASK_ULL(61, 59) | GENMASK_ULL(55, 52) | \ - GENMASK_ULL(15, 12) | GENMASK_ULL(6, 0)) - -static u64 vgic_sanitise_pendbaser(u64 reg) -{ - reg = vgic_sanitise_field(reg, GICR_PENDBASER_SHAREABILITY_MASK, - GICR_PENDBASER_SHAREABILITY_SHIFT, - vgic_sanitise_shareability); - reg = vgic_sanitise_field(reg, GICR_PENDBASER_INNER_CACHEABILITY_MASK, - GICR_PENDBASER_INNER_CACHEABILITY_SHIFT, - vgic_sanitise_inner_cacheability); - reg = vgic_sanitise_field(reg, GICR_PENDBASER_OUTER_CACHEABILITY_MASK, - GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT, - vgic_sanitise_outer_cacheability); - - reg &= ~PENDBASER_RES0_MASK; - - return reg; -} - -static u64 vgic_sanitise_propbaser(u64 reg) -{ - reg = vgic_sanitise_field(reg, GICR_PROPBASER_SHAREABILITY_MASK, - GICR_PROPBASER_SHAREABILITY_SHIFT, - vgic_sanitise_shareability); - reg = vgic_sanitise_field(reg, GICR_PROPBASER_INNER_CACHEABILITY_MASK, - GICR_PROPBASER_INNER_CACHEABILITY_SHIFT, - vgic_sanitise_inner_cacheability); - reg = vgic_sanitise_field(reg, GICR_PROPBASER_OUTER_CACHEABILITY_MASK, - GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT, - vgic_sanitise_outer_cacheability); - - reg &= ~PROPBASER_RES0_MASK; - return reg; -} - -static unsigned long vgic_mmio_read_propbase(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - - return extract_bytes(dist->propbaser, addr & 7, len); -} - -static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 old_propbaser, propbaser; - - /* Storing a value with LPIs already enabled is undefined */ - if (vgic_cpu->lpis_enabled) - return; - - do { - old_propbaser = READ_ONCE(dist->propbaser); - propbaser = old_propbaser; - propbaser = update_64bit_reg(propbaser, addr & 4, len, val); - propbaser = vgic_sanitise_propbaser(propbaser); - } while (cmpxchg64(&dist->propbaser, old_propbaser, - propbaser) != old_propbaser); -} - -static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 value = vgic_cpu->pendbaser; - - value &= ~GICR_PENDBASER_PTZ; - - return extract_bytes(value, addr & 7, len); -} - -static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 old_pendbaser, pendbaser; - - /* Storing a value with LPIs already enabled is undefined */ - if (vgic_cpu->lpis_enabled) - return; - - do { - old_pendbaser = READ_ONCE(vgic_cpu->pendbaser); - pendbaser = old_pendbaser; - pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); - pendbaser = vgic_sanitise_pendbaser(pendbaser); - } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, - pendbaser) != old_pendbaser); -} - -/* - * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the - * redistributors, while SPIs are covered by registers in the distributor - * block. Trying to set private IRQs in this block gets ignored. - * We take some special care here to fix the calculation of the register - * offset. - */ -#define REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(off, rd, wr, ur, uw, bpi, acc) \ - { \ - .reg_offset = off, \ - .bits_per_irq = bpi, \ - .len = (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ - .access_flags = acc, \ - .read = vgic_mmio_read_raz, \ - .write = vgic_mmio_write_wi, \ - }, { \ - .reg_offset = off + (bpi * VGIC_NR_PRIVATE_IRQS) / 8, \ - .bits_per_irq = bpi, \ - .len = (bpi * (1024 - VGIC_NR_PRIVATE_IRQS)) / 8, \ - .access_flags = acc, \ - .read = rd, \ - .write = wr, \ - .uaccess_read = ur, \ - .uaccess_write = uw, \ - } - -static const struct vgic_register_region vgic_v3_dist_registers[] = { - REGISTER_DESC_WITH_LENGTH_UACCESS(GICD_CTLR, - vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc, - NULL, vgic_mmio_uaccess_write_v3_misc, - 16, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICD_STATUSR, - vgic_mmio_read_rao, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR, - vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, - vgic_mmio_read_enable, vgic_mmio_write_senable, - NULL, vgic_uaccess_write_senable, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, - vgic_mmio_read_enable, vgic_mmio_write_cenable, - NULL, vgic_uaccess_write_cenable, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, - vgic_mmio_read_pending, vgic_mmio_write_spending, - vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, - vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, - vgic_mmio_read_active, vgic_mmio_write_sactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, - vgic_mmio_read_active, vgic_mmio_write_cactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, - 1, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, - vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, - 8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ITARGETSR, - vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 8, - VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICFGR, - vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGRPMODR, - vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 1, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IROUTER, - vgic_mmio_read_irouter, vgic_mmio_write_irouter, NULL, NULL, 64, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICD_IDREGS, - vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, - VGIC_ACCESS_32bit), -}; - -static const struct vgic_register_region vgic_v3_rd_registers[] = { - /* RD_base registers */ - REGISTER_DESC_WITH_LENGTH(GICR_CTLR, - vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_STATUSR, - vgic_mmio_read_raz, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_IIDR, - vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_TYPER, - vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_WAKER, - vgic_mmio_read_raz, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER, - vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER, - vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8, - VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(GICR_IDREGS, - vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48, - VGIC_ACCESS_32bit), - /* SGI_base registers */ - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, - vgic_mmio_read_group, vgic_mmio_write_group, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_senable, - NULL, vgic_uaccess_write_senable, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_cenable, - NULL, vgic_uaccess_write_cenable, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, - vgic_mmio_read_pending, vgic_mmio_write_spending, - vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0, - vgic_mmio_read_pending, vgic_mmio_write_cpending, - vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, - vgic_mmio_read_active, vgic_mmio_write_sactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, - vgic_mmio_read_active, vgic_mmio_write_cactive, - vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, - vgic_mmio_read_priority, vgic_mmio_write_priority, 32, - VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICFGR0, - vgic_mmio_read_config, vgic_mmio_write_config, 8, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGRPMODR0, - vgic_mmio_read_raz, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_NSACR, - vgic_mmio_read_raz, vgic_mmio_write_wi, 4, - VGIC_ACCESS_32bit), -}; - -unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev) -{ - dev->regions = vgic_v3_dist_registers; - dev->nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); - - kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops); - - return SZ_64K; -} - -/** - * vgic_register_redist_iodev - register a single redist iodev - * @vcpu: The VCPU to which the redistributor belongs - * - * Register a KVM iodev for this VCPU's redistributor using the address - * provided. - * - * Return 0 on success, -ERRNO otherwise. - */ -int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = vcpu->kvm; - struct vgic_dist *vgic = &kvm->arch.vgic; - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; - struct vgic_redist_region *rdreg; - gpa_t rd_base; - int ret; - - if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) - return 0; - - /* - * We may be creating VCPUs before having set the base address for the - * redistributor region, in which case we will come back to this - * function for all VCPUs when the base address is set. Just return - * without doing any work for now. - */ - rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); - if (!rdreg) - return 0; - - if (!vgic_v3_check_base(kvm)) - return -EINVAL; - - vgic_cpu->rdreg = rdreg; - - rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; - - kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); - rd_dev->base_addr = rd_base; - rd_dev->iodev_type = IODEV_REDIST; - rd_dev->regions = vgic_v3_rd_registers; - rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); - rd_dev->redist_vcpu = vcpu; - - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, - 2 * SZ_64K, &rd_dev->dev); - mutex_unlock(&kvm->slots_lock); - - if (ret) - return ret; - - rdreg->free_index++; - return 0; -} - -static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) -{ - struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; - - kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev); -} - -static int vgic_register_all_redist_iodevs(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - int c, ret = 0; - - kvm_for_each_vcpu(c, vcpu, kvm) { - ret = vgic_register_redist_iodev(vcpu); - if (ret) - break; - } - - if (ret) { - /* The current c failed, so we start with the previous one. */ - mutex_lock(&kvm->slots_lock); - for (c--; c >= 0; c--) { - vcpu = kvm_get_vcpu(kvm, c); - vgic_unregister_redist_iodev(vcpu); - } - mutex_unlock(&kvm->slots_lock); - } - - return ret; -} - -/** - * vgic_v3_insert_redist_region - Insert a new redistributor region - * - * Performs various checks before inserting the rdist region in the list. - * Those tests depend on whether the size of the rdist region is known - * (ie. count != 0). The list is sorted by rdist region index. - * - * @kvm: kvm handle - * @index: redist region index - * @base: base of the new rdist region - * @count: number of redistributors the region is made of (0 in the old style - * single region, whose size is induced from the number of vcpus) - * - * Return 0 on success, < 0 otherwise - */ -static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, - gpa_t base, uint32_t count) -{ - struct vgic_dist *d = &kvm->arch.vgic; - struct vgic_redist_region *rdreg; - struct list_head *rd_regions = &d->rd_regions; - size_t size = count * KVM_VGIC_V3_REDIST_SIZE; - int ret; - - /* single rdist region already set ?*/ - if (!count && !list_empty(rd_regions)) - return -EINVAL; - - /* cross the end of memory ? */ - if (base + size < base) - return -EINVAL; - - if (list_empty(rd_regions)) { - if (index != 0) - return -EINVAL; - } else { - rdreg = list_last_entry(rd_regions, - struct vgic_redist_region, list); - if (index != rdreg->index + 1) - return -EINVAL; - - /* Cannot add an explicitly sized regions after legacy region */ - if (!rdreg->count) - return -EINVAL; - } - - /* - * For legacy single-region redistributor regions (!count), - * check that the redistributor region does not overlap with the - * distributor's address space. - */ - if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && - vgic_dist_overlap(kvm, base, size)) - return -EINVAL; - - /* collision with any other rdist region? */ - if (vgic_v3_rdist_overlap(kvm, base, size)) - return -EINVAL; - - rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL); - if (!rdreg) - return -ENOMEM; - - rdreg->base = VGIC_ADDR_UNDEF; - - ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K); - if (ret) - goto free; - - rdreg->base = base; - rdreg->count = count; - rdreg->free_index = 0; - rdreg->index = index; - - list_add_tail(&rdreg->list, rd_regions); - return 0; -free: - kfree(rdreg); - return ret; -} - -int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) -{ - int ret; - - ret = vgic_v3_insert_redist_region(kvm, index, addr, count); - if (ret) - return ret; - - /* - * Register iodevs for each existing VCPU. Adding more VCPUs - * afterwards will register the iodevs when needed. - */ - ret = vgic_register_all_redist_iodevs(kvm); - if (ret) - return ret; - - return 0; -} - -int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr) -{ - const struct vgic_register_region *region; - struct vgic_io_device iodev; - struct vgic_reg_attr reg_attr; - struct kvm_vcpu *vcpu; - gpa_t addr; - int ret; - - ret = vgic_v3_parse_attr(dev, attr, ®_attr); - if (ret) - return ret; - - vcpu = reg_attr.vcpu; - addr = reg_attr.addr; - - switch (attr->group) { - case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: - iodev.regions = vgic_v3_dist_registers; - iodev.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers); - iodev.base_addr = 0; - break; - case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{ - iodev.regions = vgic_v3_rd_registers; - iodev.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); - iodev.base_addr = 0; - break; - } - case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: { - u64 reg, id; - - id = (attr->attr & KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK); - return vgic_v3_has_cpu_sysregs_attr(vcpu, 0, id, ®); - } - default: - return -ENXIO; - } - - /* We only support aligned 32-bit accesses. */ - if (addr & 3) - return -ENXIO; - - region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32)); - if (!region) - return -ENXIO; - - return 0; -} -/* - * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI - * generation register ICC_SGI1R_EL1) with a given VCPU. - * If the VCPU's MPIDR matches, return the level0 affinity, otherwise - * return -1. - */ -static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu) -{ - unsigned long affinity; - int level0; - - /* - * Split the current VCPU's MPIDR into affinity level 0 and the - * rest as this is what we have to compare against. - */ - affinity = kvm_vcpu_get_mpidr_aff(vcpu); - level0 = MPIDR_AFFINITY_LEVEL(affinity, 0); - affinity &= ~MPIDR_LEVEL_MASK; - - /* bail out if the upper three levels don't match */ - if (sgi_aff != affinity) - return -1; - - /* Is this VCPU's bit set in the mask ? */ - if (!(sgi_cpu_mask & BIT(level0))) - return -1; - - return level0; -} - -/* - * The ICC_SGI* registers encode the affinity differently from the MPIDR, - * so provide a wrapper to use the existing defines to isolate a certain - * affinity level. - */ -#define SGI_AFFINITY_LEVEL(reg, level) \ - ((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \ - >> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) - -/** - * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs - * @vcpu: The VCPU requesting a SGI - * @reg: The value written into ICC_{ASGI1,SGI0,SGI1}R by that VCPU - * @allow_group1: Does the sysreg access allow generation of G1 SGIs - * - * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register. - * This will trap in sys_regs.c and call this function. - * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the - * target processors as well as a bitmask of 16 Aff0 CPUs. - * If the interrupt routing mode bit is not set, we iterate over all VCPUs to - * check for matching ones. If this bit is set, we signal all, but not the - * calling VCPU. - */ -void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) -{ - struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu *c_vcpu; - u16 target_cpus; - u64 mpidr; - int sgi, c; - int vcpu_id = vcpu->vcpu_id; - bool broadcast; - unsigned long flags; - - sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; - broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); - target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT; - mpidr = SGI_AFFINITY_LEVEL(reg, 3); - mpidr |= SGI_AFFINITY_LEVEL(reg, 2); - mpidr |= SGI_AFFINITY_LEVEL(reg, 1); - - /* - * We iterate over all VCPUs to find the MPIDRs matching the request. - * If we have handled one CPU, we clear its bit to detect early - * if we are already finished. This avoids iterating through all - * VCPUs when most of the times we just signal a single VCPU. - */ - kvm_for_each_vcpu(c, c_vcpu, kvm) { - struct vgic_irq *irq; - - /* Exit early if we have dealt with all requested CPUs */ - if (!broadcast && target_cpus == 0) - break; - - /* Don't signal the calling VCPU */ - if (broadcast && c == vcpu_id) - continue; - - if (!broadcast) { - int level0; - - level0 = match_mpidr(mpidr, target_cpus, c_vcpu); - if (level0 == -1) - continue; - - /* remove this matching VCPU from the mask */ - target_cpus &= ~BIT(level0); - } - - irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - /* - * An access targetting Group0 SGIs can only generate - * those, while an access targetting Group1 SGIs can - * generate interrupts of either group. - */ - if (!irq->group || allow_group1) { - if (!irq->hw) { - irq->pending_latch = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } else { - /* HW SGI? Ask the GIC to inject it */ - int err; - err = irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - true); - WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - } - } else { - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - } - - vgic_put_irq(vcpu->kvm, irq); - } -} - -int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val) -{ - struct vgic_io_device dev = { - .regions = vgic_v3_dist_registers, - .nr_regions = ARRAY_SIZE(vgic_v3_dist_registers), - }; - - return vgic_uaccess(vcpu, &dev, is_write, offset, val); -} - -int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val) -{ - struct vgic_io_device rd_dev = { - .regions = vgic_v3_rd_registers, - .nr_regions = ARRAY_SIZE(vgic_v3_rd_registers), - }; - - return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val); -} - -int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, - u32 intid, u64 *val) -{ - if (intid % 32) - return -EINVAL; - - if (is_write) - vgic_write_irq_line_level_info(vcpu, intid, *val); - else - *val = vgic_read_irq_line_level_info(vcpu, intid); - - return 0; -} diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c deleted file mode 100644 index b2d73fc0d1ef..000000000000 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ /dev/null @@ -1,1088 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * VGIC MMIO handling functions - */ - -#include <linux/bitops.h> -#include <linux/bsearch.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <kvm/iodev.h> -#include <kvm/arm_arch_timer.h> -#include <kvm/arm_vgic.h> - -#include "vgic.h" -#include "vgic-mmio.h" - -unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - return 0; -} - -unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - return -1UL; -} - -void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val) -{ - /* Ignore */ -} - -int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val) -{ - /* Ignore */ - return 0; -} - -unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* 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); - - if (irq->group) - value |= BIT(i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -static void vgic_update_vsgi(struct vgic_irq *irq) -{ - WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); -} - -void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for (i = 0; i < len * 8; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->group = !!(val & BIT(i)); - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - vgic_update_vsgi(irq); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - } else { - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - } - - vgic_put_irq(vcpu->kvm, irq); - } -} - -/* - * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value - * of the enabled bit, so there is only one function for both here. - */ -unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* 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); - - if (irq->enabled) - value |= (1U << i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - if (!irq->enabled) { - struct irq_data *data; - - irq->enabled = true; - data = &irq_to_desc(irq->host_irq)->irq_data; - while (irqd_irq_disabled(data)) - enable_irq(irq->host_irq); - } - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - - continue; - } else if (vgic_irq_is_mapped_level(irq)) { - bool was_high = irq->line_level; - - /* - * We need to update the state of the interrupt because - * the guest might have changed the state of the device - * while the interrupt was disabled at the VGIC level. - */ - irq->line_level = vgic_get_phys_line_level(irq); - /* - * Deactivate the physical interrupt so the GIC will let - * us know when it is asserted again. - */ - if (!irq->active && was_high && !irq->line_level) - vgic_irq_set_phys_active(irq, false); - } - irq->enabled = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - - vgic_put_irq(vcpu->kvm, irq); - } -} - -void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) - disable_irq_nosync(irq->host_irq); - - irq->enabled = false; - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->enabled = true; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - - vgic_put_irq(vcpu->kvm, irq); - } - - return 0; -} - -int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->enabled = false; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(vcpu->kvm, irq); - } - - return 0; -} - -unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* 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; - bool val; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - int err; - - val = false; - err = irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &val); - WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); - } else { - val = irq_is_pending(irq); - } - - value |= ((u32)val << i); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) -{ - return (vgic_irq_is_sgi(irq->intid) && - vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2); -} - -void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - /* GICD_ISPENDR0 SGI bits are WI */ - if (is_vgic_v2_sgi(vcpu, irq)) { - vgic_put_irq(vcpu->kvm, irq); - continue; - } - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - /* HW SGI? Ask the GIC to inject it */ - int err; - err = irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - true); - WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - - continue; - } - - irq->pending_latch = true; - if (irq->hw) - vgic_irq_set_phys_active(irq, true); - - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - - /* - * GICv2 SGIs are terribly broken. We can't restore - * the source of the interrupt, so just pick the vcpu - * itself as the source... - */ - if (is_vgic_v2_sgi(vcpu, irq)) - irq->source |= BIT(vcpu->vcpu_id); - - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - - vgic_put_irq(vcpu->kvm, irq); - } - - return 0; -} - -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) -{ - irq->pending_latch = false; - - /* - * We don't want the guest to effectively mask the physical - * interrupt by doing a write to SPENDR followed by a write to - * CPENDR for HW interrupts, so we clear the active state on - * the physical side if the virtual interrupt is not active. - * This may lead to taking an additional interrupt on the - * host, but that should not be a problem as the worst that - * can happen is an additional vgic injection. We also clear - * the pending state to maintain proper semantics for edge HW - * interrupts. - */ - vgic_irq_set_phys_pending(irq, false); - if (!irq->active) - vgic_irq_set_phys_active(irq, false); -} - -void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - /* GICD_ICPENDR0 SGI bits are WI */ - if (is_vgic_v2_sgi(vcpu, irq)) { - vgic_put_irq(vcpu->kvm, irq); - continue; - } - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - /* HW SGI? Ask the GIC to clear its pending bit */ - int err; - err = irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - false); - WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - - continue; - } - - if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq); - else - irq->pending_latch = false; - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - unsigned long flags; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - /* - * More fun with GICv2 SGIs! If we're clearing one of them - * from userspace, which source vcpu to clear? Let's not - * even think of it, and blow the whole set. - */ - if (is_vgic_v2_sgi(vcpu, irq)) - irq->source = 0; - - irq->pending_latch = false; - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(vcpu->kvm, irq); - } - - return 0; -} - -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts as well as GICv3 private interrupts, we have to - * stop all the VCPUs because interrupts can be migrated while we don't hold - * the IRQ locks and we don't want to be chasing moving targets. - * - * For GICv2 private interrupts we don't have to do anything because - * userspace accesses to the VGIC state already require all VCPUs to be - * stopped, and only the VCPU itself can modify its private interrupts - * active state, which guarantees that the VCPU is not running. - */ -static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid >= VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} - -/* See vgic_access_active_prepare */ -static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid >= VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); -} - -static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 value = 0; - int i; - - /* 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); - - /* - * Even for HW interrupts, don't evaluate the HW state as - * all the guest is interested in is the virtual state. - */ - if (irq->active) - value |= (1U << i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - u32 val; - - mutex_lock(&vcpu->kvm->lock); - vgic_access_active_prepare(vcpu, intid); - - val = __vgic_mmio_read_active(vcpu, addr, len); - - vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); - - return val; -} - -unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - return __vgic_mmio_read_active(vcpu, addr, len); -} - -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool active, bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->active = active; - vgic_irq_set_phys_active(irq, active); -} - -static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool active) -{ - unsigned long flags; - struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { - vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); - } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { - /* - * GICv4.1 VSGI feature doesn't track an active state, - * so let's not kid ourselves, there is nothing we can - * do here. - */ - irq->active = false; - } else { - u32 model = vcpu->kvm->arch.vgic.vgic_model; - u8 active_source; - - irq->active = active; - - /* - * The GICv2 architecture indicates that the source CPUID for - * an SGI should be provided during an EOI which implies that - * the active state is stored somewhere, but at the same time - * this state is not architecturally exposed anywhere and we - * have no way of knowing the right source. - * - * This may lead to a VCPU not being able to receive - * additional instances of a particular SGI after migration - * for a GICv2 VM on some GIC implementations. Oh well. - */ - active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; - - if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && - active && vgic_irq_is_sgi(irq->intid)) - irq->active_source = active_source; - } - - if (irq->active) - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - else - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); -} - -static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - vgic_mmio_change_active(vcpu, irq, false); - vgic_put_irq(vcpu->kvm, irq); - } -} - -void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - - mutex_lock(&vcpu->kvm->lock); - vgic_access_active_prepare(vcpu, intid); - - __vgic_mmio_write_cactive(vcpu, addr, len, val); - - vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); -} - -int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - __vgic_mmio_write_cactive(vcpu, addr, len, val); - return 0; -} - -static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - int i; - - for_each_set_bit(i, &val, len * 8) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - vgic_mmio_change_active(vcpu, irq, true); - vgic_put_irq(vcpu->kvm, irq); - } -} - -void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - - mutex_lock(&vcpu->kvm->lock); - vgic_access_active_prepare(vcpu, intid); - - __vgic_mmio_write_sactive(vcpu, addr, len, val); - - vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); -} - -int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - __vgic_mmio_write_sactive(vcpu, addr, len, val); - return 0; -} - -unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 8); - int i; - u64 val = 0; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - val |= (u64)irq->priority << (i * 8); - - vgic_put_irq(vcpu->kvm, irq); - } - - return val; -} - -/* - * We currently don't handle changing the priority of an interrupt that - * is already pending on a VCPU. If there is a need for this, we would - * need to make this VCPU exit and re-evaluate the priorities, potentially - * leading to this interrupt getting presented now to the guest (if it has - * been masked by the priority mask before). - */ -void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 8); - int i; - unsigned long flags; - - for (i = 0; i < len; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - /* Narrow the priority range to what we actually support */ - irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); - if (irq->hw && vgic_irq_is_sgi(irq->intid)) - vgic_update_vsgi(irq); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(vcpu->kvm, irq); - } -} - -unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 2); - u32 value = 0; - int i; - - for (i = 0; i < len * 4; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - if (irq->config == VGIC_CONFIG_EDGE) - value |= (2U << (i * 2)); - - vgic_put_irq(vcpu->kvm, irq); - } - - return value; -} - -void vgic_mmio_write_config(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val) -{ - u32 intid = VGIC_ADDR_TO_INTID(addr, 2); - int i; - unsigned long flags; - - for (i = 0; i < len * 4; i++) { - struct vgic_irq *irq; - - /* - * The configuration cannot be changed for SGIs in general, - * for PPIs this is IMPLEMENTATION DEFINED. The arch timer - * code relies on PPIs being level triggered, so we also - * make them read-only here. - */ - if (intid + i < VGIC_NR_PRIVATE_IRQS) - continue; - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (test_bit(i * 2 + 1, &val)) - irq->config = VGIC_CONFIG_EDGE; - else - irq->config = VGIC_CONFIG_LEVEL; - - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -u64 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid) -{ - int i; - u64 val = 0; - int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; - - for (i = 0; i < 32; i++) { - struct vgic_irq *irq; - - if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) - continue; - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) - val |= (1U << i); - - vgic_put_irq(vcpu->kvm, irq); - } - - return val; -} - -void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, - const u64 val) -{ - int i; - int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; - unsigned long flags; - - for (i = 0; i < 32; i++) { - struct vgic_irq *irq; - bool new_level; - - if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) - continue; - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - - /* - * Line level is set irrespective of irq type - * (level or edge) to avoid dependency that VM should - * restore irq config before line level. - */ - new_level = !!(val & (1U << i)); - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->line_level = new_level; - if (new_level) - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - else - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - vgic_put_irq(vcpu->kvm, irq); - } -} - -static int match_region(const void *key, const void *elt) -{ - const unsigned int offset = (unsigned long)key; - const struct vgic_register_region *region = elt; - - if (offset < region->reg_offset) - return -1; - - if (offset >= region->reg_offset + region->len) - return 1; - - return 0; -} - -const struct vgic_register_region * -vgic_find_mmio_region(const struct vgic_register_region *regions, - int nr_regions, unsigned int offset) -{ - return bsearch((void *)(uintptr_t)offset, regions, nr_regions, - sizeof(regions[0]), match_region); -} - -void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_set_vmcr(vcpu, vmcr); - else - vgic_v3_set_vmcr(vcpu, vmcr); -} - -void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_get_vmcr(vcpu, vmcr); - else - vgic_v3_get_vmcr(vcpu, vmcr); -} - -/* - * kvm_mmio_read_buf() returns a value in a format where it can be converted - * to a byte array and be directly observed as the guest wanted it to appear - * in memory if it had done the store itself, which is LE for the GIC, as the - * guest knows the GIC is always LE. - * - * We convert this value to the CPUs native format to deal with it as a data - * value. - */ -unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len) -{ - unsigned long data = kvm_mmio_read_buf(val, len); - - switch (len) { - case 1: - return data; - case 2: - return le16_to_cpu(data); - case 4: - return le32_to_cpu(data); - default: - return le64_to_cpu(data); - } -} - -/* - * kvm_mmio_write_buf() expects a value in a format such that if converted to - * a byte array it is observed as the guest would see it if it could perform - * the load directly. Since the GIC is LE, and the guest knows this, the - * guest expects a value in little endian format. - * - * We convert the data value from the CPUs native format to LE so that the - * value is returned in the proper format. - */ -void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, - unsigned long data) -{ - switch (len) { - case 1: - break; - case 2: - data = cpu_to_le16(data); - break; - case 4: - data = cpu_to_le32(data); - break; - default: - data = cpu_to_le64(data); - } - - kvm_mmio_write_buf(buf, len, data); -} - -static -struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) -{ - return container_of(dev, struct vgic_io_device, dev); -} - -static bool check_region(const struct kvm *kvm, - const struct vgic_register_region *region, - gpa_t addr, int len) -{ - int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; - - switch (len) { - case sizeof(u8): - flags = VGIC_ACCESS_8bit; - break; - case sizeof(u32): - flags = VGIC_ACCESS_32bit; - break; - case sizeof(u64): - flags = VGIC_ACCESS_64bit; - break; - default: - return false; - } - - if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { - if (!region->bits_per_irq) - return true; - - /* Do we access a non-allocated IRQ? */ - return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; - } - - return false; -} - -const struct vgic_register_region * -vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, - gpa_t addr, int len) -{ - const struct vgic_register_region *region; - - region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, - addr - iodev->base_addr); - if (!region || !check_region(vcpu->kvm, region, addr, len)) - return NULL; - - return region; -} - -static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, - gpa_t addr, u32 *val) -{ - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); - const struct vgic_register_region *region; - struct kvm_vcpu *r_vcpu; - - region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); - if (!region) { - *val = 0; - return 0; - } - - r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; - if (region->uaccess_read) - *val = region->uaccess_read(r_vcpu, addr, sizeof(u32)); - else - *val = region->read(r_vcpu, addr, sizeof(u32)); - - return 0; -} - -static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, - gpa_t addr, const u32 *val) -{ - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); - const struct vgic_register_region *region; - struct kvm_vcpu *r_vcpu; - - region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); - if (!region) - return 0; - - r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; - if (region->uaccess_write) - return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); - - region->write(r_vcpu, addr, sizeof(u32), *val); - return 0; -} - -/* - * Userland access to VGIC registers. - */ -int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, - bool is_write, int offset, u32 *val) -{ - if (is_write) - return vgic_uaccess_write(vcpu, &dev->dev, offset, val); - else - return vgic_uaccess_read(vcpu, &dev->dev, offset, val); -} - -static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, - gpa_t addr, int len, void *val) -{ - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); - const struct vgic_register_region *region; - unsigned long data = 0; - - region = vgic_get_mmio_region(vcpu, iodev, addr, len); - if (!region) { - memset(val, 0, len); - return 0; - } - - switch (iodev->iodev_type) { - case IODEV_CPUIF: - data = region->read(vcpu, addr, len); - break; - case IODEV_DIST: - data = region->read(vcpu, addr, len); - break; - case IODEV_REDIST: - data = region->read(iodev->redist_vcpu, addr, len); - break; - case IODEV_ITS: - data = region->its_read(vcpu->kvm, iodev->its, addr, len); - break; - } - - vgic_data_host_to_mmio_bus(val, len, data); - return 0; -} - -static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, - gpa_t addr, int len, const void *val) -{ - struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); - const struct vgic_register_region *region; - unsigned long data = vgic_data_mmio_bus_to_host(val, len); - - region = vgic_get_mmio_region(vcpu, iodev, addr, len); - if (!region) - return 0; - - switch (iodev->iodev_type) { - case IODEV_CPUIF: - region->write(vcpu, addr, len, data); - break; - case IODEV_DIST: - region->write(vcpu, addr, len, data); - break; - case IODEV_REDIST: - region->write(iodev->redist_vcpu, addr, len, data); - break; - case IODEV_ITS: - region->its_write(vcpu->kvm, iodev->its, addr, len, data); - break; - } - - return 0; -} - -struct kvm_io_device_ops kvm_io_gic_ops = { - .read = dispatch_mmio_read, - .write = dispatch_mmio_write, -}; - -int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, - enum vgic_type type) -{ - struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; - int ret = 0; - unsigned int len; - - switch (type) { - case VGIC_V2: - len = vgic_v2_init_dist_iodev(io_device); - break; - case VGIC_V3: - len = vgic_v3_init_dist_iodev(io_device); - break; - default: - BUG_ON(1); - } - - io_device->base_addr = dist_base_address; - io_device->iodev_type = IODEV_DIST; - io_device->redist_vcpu = NULL; - - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, - len, &io_device->dev); - mutex_unlock(&kvm->slots_lock); - - return ret; -} diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h deleted file mode 100644 index fefcca2b14dc..000000000000 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ /dev/null @@ -1,227 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ -#ifndef __KVM_ARM_VGIC_MMIO_H__ -#define __KVM_ARM_VGIC_MMIO_H__ - -struct vgic_register_region { - unsigned int reg_offset; - unsigned int len; - unsigned int bits_per_irq; - unsigned int access_flags; - union { - unsigned long (*read)(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len); - unsigned long (*its_read)(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len); - }; - union { - void (*write)(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val); - void (*its_write)(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val); - }; - unsigned long (*uaccess_read)(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len); - union { - int (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val); - int (*uaccess_its_write)(struct kvm *kvm, struct vgic_its *its, - gpa_t addr, unsigned int len, - unsigned long val); - }; -}; - -extern struct kvm_io_device_ops kvm_io_gic_ops; - -#define VGIC_ACCESS_8bit 1 -#define VGIC_ACCESS_32bit 2 -#define VGIC_ACCESS_64bit 4 - -/* - * Generate a mask that covers the number of bytes required to address - * up to 1024 interrupts, each represented by <bits> bits. This assumes - * that <bits> is a power of two. - */ -#define VGIC_ADDR_IRQ_MASK(bits) (((bits) * 1024 / 8) - 1) - -/* - * (addr & mask) gives us the _byte_ offset for the INT ID. - * We multiply this by 8 the get the _bit_ offset, then divide this by - * the number of bits to learn the actual INT ID. - * But instead of a division (which requires a "long long div" implementation), - * we shift by the binary logarithm of <bits>. - * This assumes that <bits> is a power of two. - */ -#define VGIC_ADDR_TO_INTID(addr, bits) (((addr) & VGIC_ADDR_IRQ_MASK(bits)) * \ - 8 >> ilog2(bits)) - -/* - * Some VGIC registers store per-IRQ information, with a different number - * of bits per IRQ. For those registers this macro is used. - * The _WITH_LENGTH version instantiates registers with a fixed length - * and is mutually exclusive with the _PER_IRQ version. - */ -#define REGISTER_DESC_WITH_BITS_PER_IRQ(off, rd, wr, ur, uw, bpi, acc) \ - { \ - .reg_offset = off, \ - .bits_per_irq = bpi, \ - .len = bpi * 1024 / 8, \ - .access_flags = acc, \ - .read = rd, \ - .write = wr, \ - .uaccess_read = ur, \ - .uaccess_write = uw, \ - } - -#define REGISTER_DESC_WITH_LENGTH(off, rd, wr, length, acc) \ - { \ - .reg_offset = off, \ - .bits_per_irq = 0, \ - .len = length, \ - .access_flags = acc, \ - .read = rd, \ - .write = wr, \ - } - -#define REGISTER_DESC_WITH_LENGTH_UACCESS(off, rd, wr, urd, uwr, length, acc) \ - { \ - .reg_offset = off, \ - .bits_per_irq = 0, \ - .len = length, \ - .access_flags = acc, \ - .read = rd, \ - .write = wr, \ - .uaccess_read = urd, \ - .uaccess_write = uwr, \ - } - -unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len); - -void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, - unsigned long data); - -unsigned long extract_bytes(u64 data, unsigned int offset, - unsigned int num); - -u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len, - unsigned long val); - -unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val); - -int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val); - -unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len); - -void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, - unsigned int len, unsigned long val); - -unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len); - -void vgic_mmio_write_config(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len, - unsigned long val); - -int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, - bool is_write, int offset, u32 *val); - -u64 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid); - -void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, - const u64 val); - -unsigned int vgic_v2_init_dist_iodev(struct vgic_io_device *dev); - -unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev); - -u64 vgic_sanitise_outer_cacheability(u64 reg); -u64 vgic_sanitise_inner_cacheability(u64 reg); -u64 vgic_sanitise_shareability(u64 reg); -u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift, - u64 (*sanitise_fn)(u64)); - -/* Find the proper register handler entry given a certain address offset */ -const struct vgic_register_region * -vgic_find_mmio_region(const struct vgic_register_region *regions, - int nr_regions, unsigned int offset); - -#endif diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c deleted file mode 100644 index 621cc168fe3f..000000000000 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ /dev/null @@ -1,504 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ - -#include <linux/irqchip/arm-gic.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <kvm/arm_vgic.h> -#include <asm/kvm_mmu.h> - -#include "vgic.h" - -static inline void vgic_v2_write_lr(int lr, u32 val) -{ - void __iomem *base = kvm_vgic_global_state.vctrl_base; - - writel_relaxed(val, base + GICH_LR0 + (lr * 4)); -} - -void vgic_v2_init_lrs(void) -{ - int i; - - for (i = 0; i < kvm_vgic_global_state.nr_lr; i++) - vgic_v2_write_lr(i, 0); -} - -void vgic_v2_set_underflow(struct kvm_vcpu *vcpu) -{ - struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; - - cpuif->vgic_hcr |= GICH_HCR_UIE; -} - -static bool lr_signals_eoi_mi(u32 lr_val) -{ - return !(lr_val & GICH_LR_STATE) && (lr_val & GICH_LR_EOI) && - !(lr_val & GICH_LR_HW); -} - -/* - * transfer the content of the LRs back into the corresponding ap_list: - * - active bit is transferred as is - * - pending bit is - * - transferred as is in case of edge sensitive IRQs - * - set to the line-level (resample time) for level sensitive IRQs - */ -void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_v2_cpu_if *cpuif = &vgic_cpu->vgic_v2; - int lr; - - DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - - cpuif->vgic_hcr &= ~GICH_HCR_UIE; - - for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { - u32 val = cpuif->vgic_lr[lr]; - u32 cpuid, intid = val & GICH_LR_VIRTUALID; - struct vgic_irq *irq; - - /* Extract the source vCPU id from the LR */ - cpuid = val & GICH_LR_PHYSID_CPUID; - cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; - cpuid &= 7; - - /* Notify fds when the guest EOI'ed a level-triggered SPI */ - if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - - raw_spin_lock(&irq->irq_lock); - - /* Always preserve the active bit */ - irq->active = !!(val & GICH_LR_ACTIVE_BIT); - - if (irq->active && vgic_irq_is_sgi(intid)) - irq->active_source = cpuid; - - /* Edge is the only case where we preserve the pending bit */ - if (irq->config == VGIC_CONFIG_EDGE && - (val & GICH_LR_PENDING_BIT)) { - irq->pending_latch = true; - - if (vgic_irq_is_sgi(intid)) - irq->source |= (1 << cpuid); - } - - /* - * Clear soft pending state when level irqs have been acked. - */ - if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE)) - irq->pending_latch = false; - - /* - * Level-triggered mapped IRQs are special because we only - * observe rising edges as input to the VGIC. - * - * If the guest never acked the interrupt we have to sample - * the physical line and set the line level, because the - * device state could have changed or we simply need to - * process the still pending interrupt later. - * - * If this causes us to lower the level, we have to also clear - * the physical active state, since we will otherwise never be - * told when the interrupt becomes asserted again. - */ - if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) { - irq->line_level = vgic_get_phys_line_level(irq); - - if (!irq->line_level) - vgic_irq_set_phys_active(irq, false); - } - - raw_spin_unlock(&irq->irq_lock); - vgic_put_irq(vcpu->kvm, irq); - } - - vgic_cpu->used_lrs = 0; -} - -/* - * Populates the particular LR with the state of a given IRQ: - * - for an edge sensitive IRQ the pending state is cleared in struct vgic_irq - * - for a level sensitive IRQ the pending state value is unchanged; - * it is dictated directly by the input level - * - * If @irq describes an SGI with multiple sources, we choose the - * lowest-numbered source VCPU and clear that bit in the source bitmap. - * - * The irq_lock must be held by the caller. - */ -void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) -{ - u32 val = irq->intid; - bool allow_pending = true; - - if (irq->active) { - val |= GICH_LR_ACTIVE_BIT; - if (vgic_irq_is_sgi(irq->intid)) - val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; - if (vgic_irq_is_multi_sgi(irq)) { - allow_pending = false; - val |= GICH_LR_EOI; - } - } - - if (irq->group) - val |= GICH_LR_GROUP1; - - if (irq->hw) { - val |= GICH_LR_HW; - val |= irq->hwintid << GICH_LR_PHYSID_CPUID_SHIFT; - /* - * Never set pending+active on a HW interrupt, as the - * pending state is kept at the physical distributor - * level. - */ - if (irq->active) - allow_pending = false; - } else { - if (irq->config == VGIC_CONFIG_LEVEL) { - val |= GICH_LR_EOI; - - /* - * Software resampling doesn't work very well - * if we allow P+A, so let's not do that. - */ - if (irq->active) - allow_pending = false; - } - } - - if (allow_pending && irq_is_pending(irq)) { - val |= GICH_LR_PENDING_BIT; - - if (irq->config == VGIC_CONFIG_EDGE) - irq->pending_latch = false; - - if (vgic_irq_is_sgi(irq->intid)) { - u32 src = ffs(irq->source); - - if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", - irq->intid)) - return; - - val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; - irq->source &= ~(1 << (src - 1)); - if (irq->source) { - irq->pending_latch = true; - val |= GICH_LR_EOI; - } - } - } - - /* - * Level-triggered mapped IRQs are special because we only observe - * rising edges as input to the VGIC. We therefore lower the line - * level here, so that we can take new virtual IRQs. See - * vgic_v2_fold_lr_state for more info. - */ - if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) - irq->line_level = false; - - /* The GICv2 LR only holds five bits of priority. */ - val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT; - - vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = val; -} - -void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr) -{ - vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = 0; -} - -void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - u32 vmcr; - - vmcr = (vmcrp->grpen0 << GICH_VMCR_ENABLE_GRP0_SHIFT) & - GICH_VMCR_ENABLE_GRP0_MASK; - vmcr |= (vmcrp->grpen1 << GICH_VMCR_ENABLE_GRP1_SHIFT) & - GICH_VMCR_ENABLE_GRP1_MASK; - vmcr |= (vmcrp->ackctl << GICH_VMCR_ACK_CTL_SHIFT) & - GICH_VMCR_ACK_CTL_MASK; - vmcr |= (vmcrp->fiqen << GICH_VMCR_FIQ_EN_SHIFT) & - GICH_VMCR_FIQ_EN_MASK; - vmcr |= (vmcrp->cbpr << GICH_VMCR_CBPR_SHIFT) & - GICH_VMCR_CBPR_MASK; - vmcr |= (vmcrp->eoim << GICH_VMCR_EOI_MODE_SHIFT) & - GICH_VMCR_EOI_MODE_MASK; - vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & - GICH_VMCR_ALIAS_BINPOINT_MASK; - vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & - GICH_VMCR_BINPOINT_MASK; - vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) << - GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK; - - cpu_if->vgic_vmcr = vmcr; -} - -void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - u32 vmcr; - - vmcr = cpu_if->vgic_vmcr; - - vmcrp->grpen0 = (vmcr & GICH_VMCR_ENABLE_GRP0_MASK) >> - GICH_VMCR_ENABLE_GRP0_SHIFT; - vmcrp->grpen1 = (vmcr & GICH_VMCR_ENABLE_GRP1_MASK) >> - GICH_VMCR_ENABLE_GRP1_SHIFT; - vmcrp->ackctl = (vmcr & GICH_VMCR_ACK_CTL_MASK) >> - GICH_VMCR_ACK_CTL_SHIFT; - vmcrp->fiqen = (vmcr & GICH_VMCR_FIQ_EN_MASK) >> - GICH_VMCR_FIQ_EN_SHIFT; - vmcrp->cbpr = (vmcr & GICH_VMCR_CBPR_MASK) >> - GICH_VMCR_CBPR_SHIFT; - vmcrp->eoim = (vmcr & GICH_VMCR_EOI_MODE_MASK) >> - GICH_VMCR_EOI_MODE_SHIFT; - - vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> - GICH_VMCR_ALIAS_BINPOINT_SHIFT; - vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> - GICH_VMCR_BINPOINT_SHIFT; - vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >> - GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT; -} - -void vgic_v2_enable(struct kvm_vcpu *vcpu) -{ - /* - * By forcing VMCR to zero, the GIC will restore the binary - * points to their reset values. Anything else resets to zero - * anyway. - */ - vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0; - - /* Get the show on the road... */ - vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN; -} - -/* check for overlapping regions and for regions crossing the end of memory */ -static bool vgic_v2_check_base(gpa_t dist_base, gpa_t cpu_base) -{ - if (dist_base + KVM_VGIC_V2_DIST_SIZE < dist_base) - return false; - if (cpu_base + KVM_VGIC_V2_CPU_SIZE < cpu_base) - return false; - - if (dist_base + KVM_VGIC_V2_DIST_SIZE <= cpu_base) - return true; - if (cpu_base + KVM_VGIC_V2_CPU_SIZE <= dist_base) - return true; - - return false; -} - -int vgic_v2_map_resources(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - int ret = 0; - - if (vgic_ready(kvm)) - goto out; - - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { - kvm_err("Need to set vgic cpu and dist addresses first\n"); - ret = -ENXIO; - goto out; - } - - if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) { - kvm_err("VGIC CPU and dist frames overlap\n"); - ret = -EINVAL; - goto out; - } - - /* - * Initialize the vgic if this hasn't already been done on demand by - * accessing the vgic state from userspace. - */ - ret = vgic_init(kvm); - if (ret) { - kvm_err("Unable to initialize VGIC dynamic data structures\n"); - goto out; - } - - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); - if (ret) { - kvm_err("Unable to register VGIC MMIO regions\n"); - goto out; - } - - if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { - ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base, - kvm_vgic_global_state.vcpu_base, - KVM_VGIC_V2_CPU_SIZE, true); - if (ret) { - kvm_err("Unable to remap VGIC CPU to VCPU\n"); - goto out; - } - } - - dist->ready = true; - -out: - return ret; -} - -DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap); - -/** - * vgic_v2_probe - probe for a VGICv2 compatible interrupt controller - * @info: pointer to the GIC description - * - * Returns 0 if the VGICv2 has been probed successfully, returns an error code - * otherwise - */ -int vgic_v2_probe(const struct gic_kvm_info *info) -{ - int ret; - u32 vtr; - - if (!info->vctrl.start) { - kvm_err("GICH not present in the firmware table\n"); - return -ENXIO; - } - - if (!PAGE_ALIGNED(info->vcpu.start) || - !PAGE_ALIGNED(resource_size(&info->vcpu))) { - kvm_info("GICV region size/alignment is unsafe, using trapping (reduced performance)\n"); - - ret = create_hyp_io_mappings(info->vcpu.start, - resource_size(&info->vcpu), - &kvm_vgic_global_state.vcpu_base_va, - &kvm_vgic_global_state.vcpu_hyp_va); - if (ret) { - kvm_err("Cannot map GICV into hyp\n"); - goto out; - } - - static_branch_enable(&vgic_v2_cpuif_trap); - } - - ret = create_hyp_io_mappings(info->vctrl.start, - resource_size(&info->vctrl), - &kvm_vgic_global_state.vctrl_base, - &kvm_vgic_global_state.vctrl_hyp); - if (ret) { - kvm_err("Cannot map VCTRL into hyp\n"); - goto out; - } - - vtr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VTR); - kvm_vgic_global_state.nr_lr = (vtr & 0x3f) + 1; - - ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); - if (ret) { - kvm_err("Cannot register GICv2 KVM device\n"); - goto out; - } - - kvm_vgic_global_state.can_emulate_gicv2 = true; - kvm_vgic_global_state.vcpu_base = info->vcpu.start; - kvm_vgic_global_state.type = VGIC_V2; - kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS; - - kvm_debug("vgic-v2@%llx\n", info->vctrl.start); - - return 0; -out: - if (kvm_vgic_global_state.vctrl_base) - iounmap(kvm_vgic_global_state.vctrl_base); - if (kvm_vgic_global_state.vcpu_base_va) - iounmap(kvm_vgic_global_state.vcpu_base_va); - - return ret; -} - -static void save_lrs(struct kvm_vcpu *vcpu, void __iomem *base) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs; - u64 elrsr; - int i; - - elrsr = readl_relaxed(base + GICH_ELRSR0); - if (unlikely(used_lrs > 32)) - elrsr |= ((u64)readl_relaxed(base + GICH_ELRSR1)) << 32; - - for (i = 0; i < used_lrs; i++) { - if (elrsr & (1UL << i)) - cpu_if->vgic_lr[i] &= ~GICH_LR_STATE; - else - cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4)); - - writel_relaxed(0, base + GICH_LR0 + (i * 4)); - } -} - -void vgic_v2_save_state(struct kvm_vcpu *vcpu) -{ - void __iomem *base = kvm_vgic_global_state.vctrl_base; - u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs; - - if (!base) - return; - - if (used_lrs) { - save_lrs(vcpu, base); - writel_relaxed(0, base + GICH_HCR); - } -} - -void vgic_v2_restore_state(struct kvm_vcpu *vcpu) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - void __iomem *base = kvm_vgic_global_state.vctrl_base; - u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs; - int i; - - if (!base) - return; - - if (used_lrs) { - writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR); - for (i = 0; i < used_lrs; i++) { - writel_relaxed(cpu_if->vgic_lr[i], - base + GICH_LR0 + (i * 4)); - } - } -} - -void vgic_v2_load(struct kvm_vcpu *vcpu) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - - writel_relaxed(cpu_if->vgic_vmcr, - kvm_vgic_global_state.vctrl_base + GICH_VMCR); - writel_relaxed(cpu_if->vgic_apr, - kvm_vgic_global_state.vctrl_base + GICH_APR); -} - -void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - - cpu_if->vgic_vmcr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VMCR); -} - -void vgic_v2_put(struct kvm_vcpu *vcpu) -{ - struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; - - vgic_v2_vmcr_sync(vcpu); - cpu_if->vgic_apr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_APR); -} diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c deleted file mode 100644 index 2c9fc13e2c59..000000000000 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ /dev/null @@ -1,693 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include <linux/irqchip/arm-gic-v3.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <kvm/arm_vgic.h> -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> -#include <asm/kvm_asm.h> - -#include "vgic.h" - -static bool group0_trap; -static bool group1_trap; -static bool common_trap; -static bool gicv4_enable; - -void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; - - cpuif->vgic_hcr |= ICH_HCR_UIE; -} - -static bool lr_signals_eoi_mi(u64 lr_val) -{ - return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && - !(lr_val & ICH_LR_HW); -} - -void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; - u32 model = vcpu->kvm->arch.vgic.vgic_model; - int lr; - - DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - - cpuif->vgic_hcr &= ~ICH_HCR_UIE; - - for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { - u64 val = cpuif->vgic_lr[lr]; - u32 intid, cpuid; - struct vgic_irq *irq; - bool is_v2_sgi = false; - - cpuid = val & GICH_LR_PHYSID_CPUID; - cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; - - if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { - intid = val & ICH_LR_VIRTUAL_ID_MASK; - } else { - intid = val & GICH_LR_VIRTUALID; - is_v2_sgi = vgic_irq_is_sgi(intid); - } - - /* Notify fds when the guest EOI'ed a level-triggered IRQ */ - if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - if (!irq) /* An LPI could have been unmapped. */ - continue; - - raw_spin_lock(&irq->irq_lock); - - /* Always preserve the active bit */ - irq->active = !!(val & ICH_LR_ACTIVE_BIT); - - if (irq->active && is_v2_sgi) - irq->active_source = cpuid; - - /* Edge is the only case where we preserve the pending bit */ - if (irq->config == VGIC_CONFIG_EDGE && - (val & ICH_LR_PENDING_BIT)) { - irq->pending_latch = true; - - if (is_v2_sgi) - irq->source |= (1 << cpuid); - } - - /* - * Clear soft pending state when level irqs have been acked. - */ - if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) - irq->pending_latch = false; - - /* - * Level-triggered mapped IRQs are special because we only - * observe rising edges as input to the VGIC. - * - * If the guest never acked the interrupt we have to sample - * the physical line and set the line level, because the - * device state could have changed or we simply need to - * process the still pending interrupt later. - * - * If this causes us to lower the level, we have to also clear - * the physical active state, since we will otherwise never be - * told when the interrupt becomes asserted again. - */ - if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) { - irq->line_level = vgic_get_phys_line_level(irq); - - if (!irq->line_level) - vgic_irq_set_phys_active(irq, false); - } - - raw_spin_unlock(&irq->irq_lock); - vgic_put_irq(vcpu->kvm, irq); - } - - vgic_cpu->used_lrs = 0; -} - -/* Requires the irq to be locked already */ -void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) -{ - u32 model = vcpu->kvm->arch.vgic.vgic_model; - u64 val = irq->intid; - bool allow_pending = true, is_v2_sgi; - - is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && - model == KVM_DEV_TYPE_ARM_VGIC_V2); - - if (irq->active) { - val |= ICH_LR_ACTIVE_BIT; - if (is_v2_sgi) - val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; - if (vgic_irq_is_multi_sgi(irq)) { - allow_pending = false; - val |= ICH_LR_EOI; - } - } - - if (irq->hw) { - val |= ICH_LR_HW; - val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; - /* - * Never set pending+active on a HW interrupt, as the - * pending state is kept at the physical distributor - * level. - */ - if (irq->active) - allow_pending = false; - } else { - if (irq->config == VGIC_CONFIG_LEVEL) { - val |= ICH_LR_EOI; - - /* - * Software resampling doesn't work very well - * if we allow P+A, so let's not do that. - */ - if (irq->active) - allow_pending = false; - } - } - - if (allow_pending && irq_is_pending(irq)) { - val |= ICH_LR_PENDING_BIT; - - if (irq->config == VGIC_CONFIG_EDGE) - irq->pending_latch = false; - - if (vgic_irq_is_sgi(irq->intid) && - model == KVM_DEV_TYPE_ARM_VGIC_V2) { - u32 src = ffs(irq->source); - - if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", - irq->intid)) - return; - - val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; - irq->source &= ~(1 << (src - 1)); - if (irq->source) { - irq->pending_latch = true; - val |= ICH_LR_EOI; - } - } - } - - /* - * Level-triggered mapped IRQs are special because we only observe - * rising edges as input to the VGIC. We therefore lower the line - * level here, so that we can take new virtual IRQs. See - * vgic_v3_fold_lr_state for more info. - */ - if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) - irq->line_level = false; - - if (irq->group) - val |= ICH_LR_GROUP; - - val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; - - vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; -} - -void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) -{ - vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; -} - -void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - u32 model = vcpu->kvm->arch.vgic.vgic_model; - u32 vmcr; - - if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { - vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & - ICH_VMCR_ACK_CTL_MASK; - vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & - ICH_VMCR_FIQ_EN_MASK; - } else { - /* - * When emulating GICv3 on GICv3 with SRE=1 on the - * VFIQEn bit is RES1 and the VAckCtl bit is RES0. - */ - vmcr = ICH_VMCR_FIQ_EN_MASK; - } - - vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; - vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; - vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; - vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; - vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; - vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; - vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; - - cpu_if->vgic_vmcr = vmcr; -} - -void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - u32 model = vcpu->kvm->arch.vgic.vgic_model; - u32 vmcr; - - vmcr = cpu_if->vgic_vmcr; - - if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { - vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> - ICH_VMCR_ACK_CTL_SHIFT; - vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> - ICH_VMCR_FIQ_EN_SHIFT; - } else { - /* - * When emulating GICv3 on GICv3 with SRE=1 on the - * VFIQEn bit is RES1 and the VAckCtl bit is RES0. - */ - vmcrp->fiqen = 1; - vmcrp->ackctl = 0; - } - - vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; - vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; - vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; - vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; - vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; - vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; - vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; -} - -#define INITIAL_PENDBASER_VALUE \ - (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ - GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ - GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) - -void vgic_v3_enable(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; - - /* - * By forcing VMCR to zero, the GIC will restore the binary - * points to their reset values. Anything else resets to zero - * anyway. - */ - vgic_v3->vgic_vmcr = 0; - - /* - * If we are emulating a GICv3, we do it in an non-GICv2-compatible - * way, so we force SRE to 1 to demonstrate this to the guest. - * Also, we don't support any form of IRQ/FIQ bypass. - * This goes with the spec allowing the value to be RAO/WI. - */ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | - ICC_SRE_EL1_DFB | - ICC_SRE_EL1_SRE); - vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; - } else { - vgic_v3->vgic_sre = 0; - } - - vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & - ICH_VTR_ID_BITS_MASK) >> - ICH_VTR_ID_BITS_SHIFT; - vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & - ICH_VTR_PRI_BITS_MASK) >> - ICH_VTR_PRI_BITS_SHIFT) + 1; - - /* Get the show on the road... */ - vgic_v3->vgic_hcr = ICH_HCR_EN; - if (group0_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TALL0; - if (group1_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TALL1; - if (common_trap) - vgic_v3->vgic_hcr |= ICH_HCR_TC; -} - -int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) -{ - struct kvm_vcpu *vcpu; - int byte_offset, bit_nr; - gpa_t pendbase, ptr; - bool status; - u8 val; - int ret; - unsigned long flags; - -retry: - vcpu = irq->target_vcpu; - if (!vcpu) - return 0; - - pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); - - byte_offset = irq->intid / BITS_PER_BYTE; - bit_nr = irq->intid % BITS_PER_BYTE; - ptr = pendbase + byte_offset; - - ret = kvm_read_guest_lock(kvm, ptr, &val, 1); - if (ret) - return ret; - - status = val & (1 << bit_nr); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->target_vcpu != vcpu) { - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - goto retry; - } - irq->pending_latch = status; - vgic_queue_irq_unlock(vcpu->kvm, irq, flags); - - if (status) { - /* clear consumed data */ - val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); - if (ret) - return ret; - } - return 0; -} - -/** - * vgic_v3_save_pending_tables - Save the pending tables into guest RAM - * kvm lock and all vcpu lock must be held - */ -int vgic_v3_save_pending_tables(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_irq *irq; - gpa_t last_ptr = ~(gpa_t)0; - 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; - - vcpu = irq->target_vcpu; - if (!vcpu) - continue; - - pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); - - byte_offset = irq->intid / BITS_PER_BYTE; - bit_nr = irq->intid % BITS_PER_BYTE; - ptr = pendbase + byte_offset; - - if (ptr != last_ptr) { - ret = kvm_read_guest_lock(kvm, ptr, &val, 1); - if (ret) - return ret; - last_ptr = ptr; - } - - stored = val & (1U << bit_nr); - if (stored == irq->pending_latch) - continue; - - if (irq->pending_latch) - val |= 1 << bit_nr; - else - val &= ~(1 << bit_nr); - - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); - if (ret) - return ret; - } - return 0; -} - -/** - * vgic_v3_rdist_overlap - check if a region overlaps with any - * existing redistributor region - * - * @kvm: kvm handle - * @base: base of the region - * @size: size of region - * - * Return: true if there is an overlap - */ -bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) -{ - struct vgic_dist *d = &kvm->arch.vgic; - struct vgic_redist_region *rdreg; - - list_for_each_entry(rdreg, &d->rd_regions, list) { - if ((base + size > rdreg->base) && - (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) - return true; - } - return false; -} - -/* - * Check for overlapping regions and for regions crossing the end of memory - * for base addresses which have already been set. - */ -bool vgic_v3_check_base(struct kvm *kvm) -{ - struct vgic_dist *d = &kvm->arch.vgic; - struct vgic_redist_region *rdreg; - - if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && - d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) - return false; - - list_for_each_entry(rdreg, &d->rd_regions, list) { - if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) < - rdreg->base) - return false; - } - - if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) - return true; - - return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, - KVM_VGIC_V3_DIST_SIZE); -} - -/** - * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one - * which has free space to put a new rdist region. - * - * @rd_regions: redistributor region list head - * - * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). - * Stride between redistributors is 0 and regions are filled in the index order. - * - * Return: the redist region handle, if any, that has space to map a new rdist - * region. - */ -struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) -{ - struct vgic_redist_region *rdreg; - - list_for_each_entry(rdreg, rd_regions, list) { - if (!vgic_v3_redist_region_full(rdreg)) - return rdreg; - } - return NULL; -} - -struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, - u32 index) -{ - struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; - struct vgic_redist_region *rdreg; - - list_for_each_entry(rdreg, rd_regions, list) { - if (rdreg->index == index) - return rdreg; - } - return NULL; -} - - -int vgic_v3_map_resources(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int ret = 0; - int c; - - if (vgic_ready(kvm)) - goto out; - - kvm_for_each_vcpu(c, vcpu, kvm) { - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { - kvm_debug("vcpu %d redistributor base not set\n", c); - ret = -ENXIO; - goto out; - } - } - - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { - kvm_err("Need to set vgic distributor addresses first\n"); - ret = -ENXIO; - goto out; - } - - if (!vgic_v3_check_base(kvm)) { - kvm_err("VGIC redist and dist frames overlap\n"); - ret = -EINVAL; - goto out; - } - - /* - * For a VGICv3 we require the userland to explicitly initialize - * the VGIC before we need to use it. - */ - if (!vgic_initialized(kvm)) { - ret = -EBUSY; - goto out; - } - - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); - if (ret) { - kvm_err("Unable to register VGICv3 dist MMIO regions\n"); - goto out; - } - - if (kvm_vgic_global_state.has_gicv4_1) - vgic_v4_configure_vsgis(kvm); - dist->ready = true; - -out: - return ret; -} - -DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); - -static int __init early_group0_trap_cfg(char *buf) -{ - return strtobool(buf, &group0_trap); -} -early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); - -static int __init early_group1_trap_cfg(char *buf) -{ - return strtobool(buf, &group1_trap); -} -early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); - -static int __init early_common_trap_cfg(char *buf) -{ - return strtobool(buf, &common_trap); -} -early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); - -static int __init early_gicv4_enable(char *buf) -{ - return strtobool(buf, &gicv4_enable); -} -early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); - -/** - * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller - * @info: pointer to the GIC description - * - * Returns 0 if the VGICv3 has been probed successfully, returns an error code - * otherwise - */ -int vgic_v3_probe(const struct gic_kvm_info *info) -{ - u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2); - int ret; - - /* - * The ListRegs field is 5 bits, but there is a architectural - * maximum of 16 list registers. Just ignore bit 4... - */ - kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; - kvm_vgic_global_state.can_emulate_gicv2 = false; - kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; - - /* GICv4 support? */ - if (info->has_v4) { - kvm_vgic_global_state.has_gicv4 = gicv4_enable; - kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; - kvm_info("GICv4%s support %sabled\n", - kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", - gicv4_enable ? "en" : "dis"); - } - - if (!info->vcpu.start) { - kvm_info("GICv3: no GICV resource entry\n"); - kvm_vgic_global_state.vcpu_base = 0; - } else if (!PAGE_ALIGNED(info->vcpu.start)) { - pr_warn("GICV physical address 0x%llx not page aligned\n", - (unsigned long long)info->vcpu.start); - kvm_vgic_global_state.vcpu_base = 0; - } else { - kvm_vgic_global_state.vcpu_base = info->vcpu.start; - kvm_vgic_global_state.can_emulate_gicv2 = true; - ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); - if (ret) { - kvm_err("Cannot register GICv2 KVM device.\n"); - return ret; - } - kvm_info("vgic-v2@%llx\n", info->vcpu.start); - } - ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); - if (ret) { - kvm_err("Cannot register GICv3 KVM device.\n"); - kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); - return ret; - } - - if (kvm_vgic_global_state.vcpu_base == 0) - kvm_info("disabling GICv2 emulation\n"); - -#ifdef CONFIG_ARM64 - if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_30115)) { - group0_trap = true; - group1_trap = true; - } -#endif - - if (group0_trap || group1_trap || common_trap) { - kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n", - group0_trap ? "G0" : "", - group1_trap ? "G1" : "", - common_trap ? "C" : ""); - static_branch_enable(&vgic_v3_cpuif_trap); - } - - kvm_vgic_global_state.vctrl_base = NULL; - kvm_vgic_global_state.type = VGIC_V3; - kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; - - return 0; -} - -void vgic_v3_load(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - - /* - * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen - * is dependent on ICC_SRE_EL1.SRE, and we have to perform the - * VMCR_EL2 save/restore in the world switch. - */ - if (likely(cpu_if->vgic_sre)) - kvm_call_hyp(__vgic_v3_write_vmcr, cpu_if->vgic_vmcr); - - kvm_call_hyp(__vgic_v3_restore_aprs, vcpu); - - if (has_vhe()) - __vgic_v3_activate_traps(vcpu); - - WARN_ON(vgic_v4_load(vcpu)); -} - -void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu) -{ - struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; - - if (likely(cpu_if->vgic_sre)) - cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr); -} - -void vgic_v3_put(struct kvm_vcpu *vcpu) -{ - WARN_ON(vgic_v4_put(vcpu, false)); - - vgic_v3_vmcr_sync(vcpu); - - kvm_call_hyp(__vgic_v3_save_aprs, vcpu); - - if (has_vhe()) - __vgic_v3_deactivate_traps(vcpu); -} diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c deleted file mode 100644 index 27ac833e5ec7..000000000000 --- a/virt/kvm/arm/vgic/vgic-v4.c +++ /dev/null @@ -1,453 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2017 ARM Ltd. - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/irqdomain.h> -#include <linux/kvm_host.h> -#include <linux/irqchip/arm-gic-v3.h> - -#include "vgic.h" - -/* - * How KVM uses GICv4 (insert rude comments here): - * - * The vgic-v4 layer acts as a bridge between several entities: - * - The GICv4 ITS representation offered by the ITS driver - * - VFIO, which is in charge of the PCI endpoint - * - The virtual ITS, which is the only thing the guest sees - * - * The configuration of VLPIs is triggered by a callback from VFIO, - * instructing KVM that a PCI device has been configured to deliver - * MSIs to a vITS. - * - * kvm_vgic_v4_set_forwarding() is thus called with the routing entry, - * and this is used to find the corresponding vITS data structures - * (ITS instance, device, event and irq) using a process that is - * extremely similar to the injection of an MSI. - * - * At this stage, we can link the guest's view of an LPI (uniquely - * identified by the routing entry) and the host irq, using the GICv4 - * driver mapping operation. Should the mapping succeed, we've then - * successfully upgraded the guest's LPI to a VLPI. We can then start - * with updating GICv4's view of the property table and generating an - * INValidation in order to kickstart the delivery of this VLPI to the - * guest directly, without software intervention. Well, almost. - * - * When the PCI endpoint is deconfigured, this operation is reversed - * with VFIO calling kvm_vgic_v4_unset_forwarding(). - * - * Once the VLPI has been mapped, it needs to follow any change the - * guest performs on its LPI through the vITS. For that, a number of - * command handlers have hooks to communicate these changes to the HW: - * - Any invalidation triggers a call to its_prop_update_vlpi() - * - The INT command results in a irq_set_irqchip_state(), which - * generates an INT on the corresponding VLPI. - * - The CLEAR command results in a irq_set_irqchip_state(), which - * generates an CLEAR on the corresponding VLPI. - * - DISCARD translates into an unmap, similar to a call to - * kvm_vgic_v4_unset_forwarding(). - * - MOVI is translated by an update of the existing mapping, changing - * the target vcpu, resulting in a VMOVI being generated. - * - MOVALL is translated by a string of mapping updates (similar to - * the handling of MOVI). MOVALL is horrible. - * - * Note that a DISCARD/MAPTI sequence emitted from the guest without - * reprogramming the PCI endpoint after MAPTI does not result in a - * VLPI being mapped, as there is no callback from VFIO (the guest - * will get the interrupt via the normal SW injection). Fixing this is - * not trivial, and requires some horrible messing with the VFIO - * internals. Not fun. Don't do that. - * - * Then there is the scheduling. Each time a vcpu is about to run on a - * physical CPU, KVM must tell the corresponding redistributor about - * it. And if we've migrated our vcpu from one CPU to another, we must - * tell the ITS (so that the messages reach the right redistributor). - * This is done in two steps: first issue a irq_set_affinity() on the - * irq corresponding to the vcpu, then call its_make_vpe_resident(). - * You must be in a non-preemptible context. On exit, a call to - * its_make_vpe_non_resident() tells the redistributor that we're done - * with the vcpu. - * - * Finally, the doorbell handling: Each vcpu is allocated an interrupt - * which will fire each time a VLPI is made pending whilst the vcpu is - * not running. Each time the vcpu gets blocked, the doorbell - * interrupt gets enabled. When the vcpu is unblocked (for whatever - * reason), the doorbell interrupt is disabled. - */ - -#define DB_IRQ_FLAGS (IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY | IRQ_NO_BALANCING) - -static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) -{ - struct kvm_vcpu *vcpu = info; - - /* We got the message, no need to fire again */ - if (!kvm_vgic_global_state.has_gicv4_1 && - !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) - disable_irq_nosync(irq); - - vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; - kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); - kvm_vcpu_kick(vcpu); - - return IRQ_HANDLED; -} - -static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) -{ - vpe->sgi_config[irq->intid].enabled = irq->enabled; - vpe->sgi_config[irq->intid].group = irq->group; - vpe->sgi_config[irq->intid].priority = irq->priority; -} - -static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) -{ - struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; - int i; - - /* - * With GICv4.1, every virtual SGI can be directly injected. So - * let's pretend that they are HW interrupts, tied to a host - * IRQ. The SGI code will do its magic. - */ - for (i = 0; i < VGIC_NR_SGIS; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); - struct irq_desc *desc; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (irq->hw) - goto unlock; - - irq->hw = true; - irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); - - /* Transfer the full irq state to the vPE */ - vgic_v4_sync_sgi_config(vpe, irq); - desc = irq_to_desc(irq->host_irq); - ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), - false); - if (!WARN_ON(ret)) { - /* Transfer pending state */ - ret = irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - irq->pending_latch); - WARN_ON(ret); - irq->pending_latch = false; - } - unlock: - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) -{ - int i; - - for (i = 0; i < VGIC_NR_SGIS; i++) { - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, i); - struct irq_desc *desc; - unsigned long flags; - int ret; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (!irq->hw) - goto unlock; - - irq->hw = false; - ret = irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &irq->pending_latch); - WARN_ON(ret); - - desc = irq_to_desc(irq->host_irq); - irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); - unlock: - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - } -} - -/* Must be called with the kvm lock held */ -void vgic_v4_configure_vsgis(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int i; - - kvm_arm_halt_guest(kvm); - - kvm_for_each_vcpu(i, vcpu, kvm) { - if (dist->nassgireq) - vgic_v4_enable_vsgis(vcpu); - else - vgic_v4_disable_vsgis(vcpu); - } - - kvm_arm_resume_guest(kvm); -} - -/** - * vgic_v4_init - Initialize the GICv4 data structures - * @kvm: Pointer to the VM being initialized - * - * We may be called each time a vITS is created, or when the - * vgic is initialized. This relies on kvm->lock to be - * held. In both cases, the number of vcpus should now be - * fixed. - */ -int vgic_v4_init(struct kvm *kvm) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct kvm_vcpu *vcpu; - int i, nr_vcpus, ret; - - if (!kvm_vgic_global_state.has_gicv4) - return 0; /* Nothing to see here... move along. */ - - if (dist->its_vm.vpes) - return 0; - - nr_vcpus = atomic_read(&kvm->online_vcpus); - - dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes), - GFP_KERNEL); - if (!dist->its_vm.vpes) - return -ENOMEM; - - dist->its_vm.nr_vpes = nr_vcpus; - - kvm_for_each_vcpu(i, vcpu, kvm) - dist->its_vm.vpes[i] = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; - - ret = its_alloc_vcpu_irqs(&dist->its_vm); - if (ret < 0) { - kvm_err("VPE IRQ allocation failure\n"); - kfree(dist->its_vm.vpes); - dist->its_vm.nr_vpes = 0; - dist->its_vm.vpes = NULL; - return ret; - } - - kvm_for_each_vcpu(i, vcpu, kvm) { - int irq = dist->its_vm.vpes[i]->irq; - unsigned long irq_flags = DB_IRQ_FLAGS; - - /* - * Don't automatically enable the doorbell, as we're - * flipping it back and forth when the vcpu gets - * blocked. Also disable the lazy disabling, as the - * doorbell could kick us out of the guest too - * early... - * - * On GICv4.1, the doorbell is managed in HW and must - * be left enabled. - */ - if (kvm_vgic_global_state.has_gicv4_1) - irq_flags &= ~IRQ_NOAUTOEN; - irq_set_status_flags(irq, irq_flags); - - ret = request_irq(irq, vgic_v4_doorbell_handler, - 0, "vcpu", vcpu); - if (ret) { - kvm_err("failed to allocate vcpu IRQ%d\n", irq); - /* - * Trick: adjust the number of vpes so we know - * how many to nuke on teardown... - */ - dist->its_vm.nr_vpes = i; - break; - } - } - - if (ret) - vgic_v4_teardown(kvm); - - return ret; -} - -/** - * vgic_v4_teardown - Free the GICv4 data structures - * @kvm: Pointer to the VM being destroyed - * - * Relies on kvm->lock to be held. - */ -void vgic_v4_teardown(struct kvm *kvm) -{ - struct its_vm *its_vm = &kvm->arch.vgic.its_vm; - int i; - - if (!its_vm->vpes) - return; - - for (i = 0; i < its_vm->nr_vpes; i++) { - struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, i); - int irq = its_vm->vpes[i]->irq; - - irq_clear_status_flags(irq, DB_IRQ_FLAGS); - free_irq(irq, vcpu); - } - - its_free_vcpu_irqs(its_vm); - kfree(its_vm->vpes); - its_vm->nr_vpes = 0; - its_vm->vpes = NULL; -} - -int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db) -{ - struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; - - if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) - return 0; - - return its_make_vpe_non_resident(vpe, need_db); -} - -int vgic_v4_load(struct kvm_vcpu *vcpu) -{ - struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; - int err; - - if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) - return 0; - - /* - * Before making the VPE resident, make sure the redistributor - * corresponding to our current CPU expects us here. See the - * doc in drivers/irqchip/irq-gic-v4.c to understand how this - * turns into a VMOVP command at the ITS level. - */ - err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); - if (err) - return err; - - err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled); - if (err) - return err; - - /* - * Now that the VPE is resident, let's get rid of a potential - * doorbell interrupt that would still be pending. This is a - * GICv4.0 only "feature"... - */ - if (!kvm_vgic_global_state.has_gicv4_1) - err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); - - return err; -} - -static struct vgic_its *vgic_get_its(struct kvm *kvm, - struct kvm_kernel_irq_routing_entry *irq_entry) -{ - struct kvm_msi msi = (struct kvm_msi) { - .address_lo = irq_entry->msi.address_lo, - .address_hi = irq_entry->msi.address_hi, - .data = irq_entry->msi.data, - .flags = irq_entry->msi.flags, - .devid = irq_entry->msi.devid, - }; - - return vgic_msi_to_its(kvm, &msi); -} - -int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, - struct kvm_kernel_irq_routing_entry *irq_entry) -{ - struct vgic_its *its; - struct vgic_irq *irq; - struct its_vlpi_map map; - int ret; - - if (!vgic_supports_direct_msis(kvm)) - return 0; - - /* - * Get the ITS, and escape early on error (not a valid - * doorbell for any of our vITSs). - */ - its = vgic_get_its(kvm, irq_entry); - if (IS_ERR(its)) - return 0; - - mutex_lock(&its->its_lock); - - /* Perform the actual DevID/EventID -> LPI translation. */ - ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, - irq_entry->msi.data, &irq); - if (ret) - goto out; - - /* - * Emit the mapping request. If it fails, the ITS probably - * isn't v4 compatible, so let's silently bail out. Holding - * the ITS lock should ensure that nothing can modify the - * target vcpu. - */ - map = (struct its_vlpi_map) { - .vm = &kvm->arch.vgic.its_vm, - .vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe, - .vintid = irq->intid, - .properties = ((irq->priority & 0xfc) | - (irq->enabled ? LPI_PROP_ENABLED : 0) | - LPI_PROP_GROUP1), - .db_enabled = true, - }; - - ret = its_map_vlpi(virq, &map); - if (ret) - goto out; - - irq->hw = true; - irq->host_irq = virq; - atomic_inc(&map.vpe->vlpi_count); - -out: - mutex_unlock(&its->its_lock); - return ret; -} - -int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, - struct kvm_kernel_irq_routing_entry *irq_entry) -{ - struct vgic_its *its; - struct vgic_irq *irq; - int ret; - - if (!vgic_supports_direct_msis(kvm)) - return 0; - - /* - * Get the ITS, and escape early on error (not a valid - * doorbell for any of our vITSs). - */ - its = vgic_get_its(kvm, irq_entry); - if (IS_ERR(its)) - return 0; - - mutex_lock(&its->its_lock); - - ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, - irq_entry->msi.data, &irq); - if (ret) - goto out; - - WARN_ON(!(irq->hw && irq->host_irq == virq)); - if (irq->hw) { - atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); - irq->hw = false; - ret = its_unmap_vlpi(virq); - } - -out: - mutex_unlock(&its->its_lock); - return ret; -} diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c deleted file mode 100644 index 99b02ca730a8..000000000000 --- a/virt/kvm/arm/vgic/vgic.c +++ /dev/null @@ -1,1011 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ - -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/kvm.h> -#include <linux/kvm_host.h> -#include <linux/list_sort.h> -#include <linux/nospec.h> - -#include <asm/kvm_hyp.h> - -#include "vgic.h" - -#define CREATE_TRACE_POINTS -#include "trace.h" - -struct vgic_global kvm_vgic_global_state __ro_after_init = { - .gicv3_cpuif = STATIC_KEY_FALSE_INIT, -}; - -/* - * Locking order is always: - * kvm->lock (mutex) - * its->cmd_lock (mutex) - * its->its_lock (mutex) - * vgic_cpu->ap_list_lock must be taken with IRQs disabled - * kvm->lpi_list_lock must be taken with IRQs disabled - * vgic_irq->irq_lock must be taken with IRQs disabled - * - * As the ap_list_lock might be taken from the timer interrupt handler, - * we have to disable IRQs before taking this lock and everything lower - * than it. - * - * If you need to take multiple locks, always take the upper lock first, - * then the lower ones, e.g. first take the its_lock, then the irq_lock. - * If you are already holding a lock and need to take a higher one, you - * have to drop the lower ranking lock first and re-aquire it after having - * taken the upper one. - * - * When taking more than one ap_list_lock at the same time, always take the - * lowest numbered VCPU's ap_list_lock first, so: - * vcpuX->vcpu_id < vcpuY->vcpu_id: - * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); - * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); - * - * Since the VGIC must support injecting virtual interrupts from ISRs, we have - * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer - * spinlocks for any lock that may be taken while injecting an interrupt. - */ - -/* - * Iterate over the VM's list of mapped LPIs to find the one with a - * matching interrupt ID and return a reference to the IRQ structure. - */ -static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - struct vgic_irq *irq = NULL; - unsigned long flags; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - - list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { - if (irq->intid != intid) - continue; - - /* - * This increases the refcount, the caller is expected to - * call vgic_put_irq() later once it's finished with the IRQ. - */ - vgic_get_irq_kref(irq); - goto out_unlock; - } - irq = NULL; - -out_unlock: - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); - - return irq; -} - -/* - * This looks up the virtual interrupt ID to get the corresponding - * struct vgic_irq. It also increases the refcount, so any caller is expected - * to call vgic_put_irq() once it's finished with this IRQ. - */ -struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, - u32 intid) -{ - /* SGIs and PPIs */ - if (intid <= VGIC_MAX_PRIVATE) { - intid = array_index_nospec(intid, VGIC_MAX_PRIVATE + 1); - return &vcpu->arch.vgic_cpu.private_irqs[intid]; - } - - /* SPIs */ - if (intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) { - intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS); - return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS]; - } - - /* LPIs */ - if (intid >= VGIC_MIN_LPI) - return vgic_get_lpi(kvm, intid); - - WARN(1, "Looking up struct vgic_irq for reserved INTID"); - return NULL; -} - -/* - * We can't do anything in here, because we lack the kvm pointer to - * lock and remove the item from the lpi_list. So we keep this function - * empty and use the return value of kref_put() to trigger the freeing. - */ -static void vgic_irq_release(struct kref *ref) -{ -} - -/* - * Drop the refcount on the LPI. Must be called with lpi_list_lock held. - */ -void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - - if (!kref_put(&irq->refcount, vgic_irq_release)) - return; - - list_del(&irq->lpi_list); - dist->lpi_list_count--; - - kfree(irq); -} - -void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) -{ - struct vgic_dist *dist = &kvm->arch.vgic; - unsigned long flags; - - if (irq->intid < VGIC_MIN_LPI) - return; - - raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); - __vgic_put_lpi_locked(kvm, irq); - raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); -} - -void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_irq *irq, *tmp; - unsigned long flags; - - raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); - - list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { - if (irq->intid >= VGIC_MIN_LPI) { - raw_spin_lock(&irq->irq_lock); - list_del(&irq->ap_list); - irq->vcpu = NULL; - raw_spin_unlock(&irq->irq_lock); - vgic_put_irq(vcpu->kvm, irq); - } - } - - raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); -} - -void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) -{ - WARN_ON(irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - pending)); -} - -bool vgic_get_phys_line_level(struct vgic_irq *irq) -{ - bool line_level; - - BUG_ON(!irq->hw); - - if (irq->get_input_level) - return irq->get_input_level(irq->intid); - - WARN_ON(irq_get_irqchip_state(irq->host_irq, - IRQCHIP_STATE_PENDING, - &line_level)); - return line_level; -} - -/* Set/Clear the physical active state */ -void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active) -{ - - BUG_ON(!irq->hw); - WARN_ON(irq_set_irqchip_state(irq->host_irq, - IRQCHIP_STATE_ACTIVE, - active)); -} - -/** - * kvm_vgic_target_oracle - compute the target vcpu for an irq - * - * @irq: The irq to route. Must be already locked. - * - * Based on the current state of the interrupt (enabled, pending, - * active, vcpu and target_vcpu), compute the next vcpu this should be - * given to. Return NULL if this shouldn't be injected at all. - * - * Requires the IRQ lock to be held. - */ -static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq) -{ - lockdep_assert_held(&irq->irq_lock); - - /* If the interrupt is active, it must stay on the current vcpu */ - if (irq->active) - return irq->vcpu ? : irq->target_vcpu; - - /* - * If the IRQ is not active but enabled and pending, we should direct - * it to its configured target VCPU. - * If the distributor is disabled, pending interrupts shouldn't be - * forwarded. - */ - if (irq->enabled && irq_is_pending(irq)) { - if (unlikely(irq->target_vcpu && - !irq->target_vcpu->kvm->arch.vgic.enabled)) - return NULL; - - return irq->target_vcpu; - } - - /* If neither active nor pending and enabled, then this IRQ should not - * be queued to any VCPU. - */ - return NULL; -} - -/* - * The order of items in the ap_lists defines how we'll pack things in LRs as - * well, the first items in the list being the first things populated in the - * LRs. - * - * A hard rule is that active interrupts can never be pushed out of the LRs - * (and therefore take priority) since we cannot reliably trap on deactivation - * of IRQs and therefore they have to be present in the LRs. - * - * Otherwise things should be sorted by the priority field and the GIC - * hardware support will take care of preemption of priority groups etc. - * - * Return negative if "a" sorts before "b", 0 to preserve order, and positive - * to sort "b" before "a". - */ -static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) -{ - struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list); - struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list); - bool penda, pendb; - int ret; - - /* - * list_sort may call this function with the same element when - * the list is fairly long. - */ - if (unlikely(irqa == irqb)) - return 0; - - raw_spin_lock(&irqa->irq_lock); - raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); - - if (irqa->active || irqb->active) { - ret = (int)irqb->active - (int)irqa->active; - goto out; - } - - penda = irqa->enabled && irq_is_pending(irqa); - pendb = irqb->enabled && irq_is_pending(irqb); - - if (!penda || !pendb) { - ret = (int)pendb - (int)penda; - goto out; - } - - /* Both pending and enabled, sort by priority */ - ret = irqa->priority - irqb->priority; -out: - raw_spin_unlock(&irqb->irq_lock); - raw_spin_unlock(&irqa->irq_lock); - return ret; -} - -/* Must be called with the ap_list_lock held */ -static void vgic_sort_ap_list(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - lockdep_assert_held(&vgic_cpu->ap_list_lock); - - list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp); -} - -/* - * Only valid injection if changing level for level-triggered IRQs or for a - * rising edge, and in-kernel connected IRQ lines can only be controlled by - * their owner. - */ -static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner) -{ - if (irq->owner != owner) - return false; - - switch (irq->config) { - case VGIC_CONFIG_LEVEL: - return irq->line_level != level; - case VGIC_CONFIG_EDGE: - return level; - } - - return false; -} - -/* - * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list. - * Do the queuing if necessary, taking the right locks in the right order. - * Returns true when the IRQ was queued, false otherwise. - * - * Needs to be entered with the IRQ lock already held, but will return - * with all locks dropped. - */ -bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags) -{ - struct kvm_vcpu *vcpu; - - lockdep_assert_held(&irq->irq_lock); - -retry: - vcpu = vgic_target_oracle(irq); - if (irq->vcpu || !vcpu) { - /* - * If this IRQ is already on a VCPU's ap_list, then it - * cannot be moved or modified and there is no more work for - * us to do. - * - * Otherwise, if the irq is not pending and enabled, it does - * not need to be inserted into an ap_list and there is also - * no more work for us to do. - */ - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - /* - * We have to kick the VCPU here, because we could be - * queueing an edge-triggered interrupt for which we - * get no EOI maintenance interrupt. In that case, - * while the IRQ is already on the VCPU's AP list, the - * VCPU could have EOI'ed the original interrupt and - * won't see this one until it exits for some other - * reason. - */ - if (vcpu) { - kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); - kvm_vcpu_kick(vcpu); - } - return false; - } - - /* - * We must unlock the irq lock to take the ap_list_lock where - * we are going to insert this new pending interrupt. - */ - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - /* someone can do stuff here, which we re-check below */ - - raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); - raw_spin_lock(&irq->irq_lock); - - /* - * Did something change behind our backs? - * - * There are two cases: - * 1) The irq lost its pending state or was disabled behind our - * backs and/or it was queued to another VCPU's ap_list. - * 2) Someone changed the affinity on this irq behind our - * backs and we are now holding the wrong ap_list_lock. - * - * In both cases, drop the locks and retry. - */ - - if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) { - raw_spin_unlock(&irq->irq_lock); - raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, - flags); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - goto retry; - } - - /* - * Grab a reference to the irq to reflect the fact that it is - * now in the ap_list. - */ - vgic_get_irq_kref(irq); - list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); - irq->vcpu = vcpu; - - raw_spin_unlock(&irq->irq_lock); - raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); - - kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); - kvm_vcpu_kick(vcpu); - - return true; -} - -/** - * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic - * @kvm: The VM structure pointer - * @cpuid: The CPU for PPIs - * @intid: The INTID to inject a new state to. - * @level: Edge-triggered: true: to trigger the interrupt - * false: to ignore the call - * Level-sensitive true: raise the input signal - * false: lower the input signal - * @owner: The opaque pointer to the owner of the IRQ being raised to verify - * that the caller is allowed to inject this IRQ. Userspace - * injections will have owner == NULL. - * - * The VGIC is not concerned with devices being active-LOW or active-HIGH for - * level-sensitive interrupts. You can think of the level parameter as 1 - * being HIGH and 0 being LOW and all devices being active-HIGH. - */ -int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, - bool level, void *owner) -{ - struct kvm_vcpu *vcpu; - struct vgic_irq *irq; - unsigned long flags; - int ret; - - trace_vgic_update_irq_pending(cpuid, intid, level); - - ret = vgic_lazy_init(kvm); - if (ret) - return ret; - - vcpu = kvm_get_vcpu(kvm, cpuid); - if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS) - return -EINVAL; - - irq = vgic_get_irq(kvm, vcpu, intid); - if (!irq) - return -EINVAL; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - - if (!vgic_validate_injection(irq, level, owner)) { - /* Nothing to see here, move along... */ - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(kvm, irq); - return 0; - } - - if (irq->config == VGIC_CONFIG_LEVEL) - irq->line_level = level; - else - irq->pending_latch = true; - - vgic_queue_irq_unlock(kvm, irq, flags); - vgic_put_irq(kvm, irq); - - return 0; -} - -/* @irq->irq_lock must be held */ -static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - unsigned int host_irq, - bool (*get_input_level)(int vindid)) -{ - struct irq_desc *desc; - struct irq_data *data; - - /* - * Find the physical IRQ number corresponding to @host_irq - */ - desc = irq_to_desc(host_irq); - if (!desc) { - kvm_err("%s: no interrupt descriptor\n", __func__); - return -EINVAL; - } - data = irq_desc_get_irq_data(desc); - while (data->parent_data) - data = data->parent_data; - - irq->hw = true; - irq->host_irq = host_irq; - irq->hwintid = data->hwirq; - irq->get_input_level = get_input_level; - return 0; -} - -/* @irq->irq_lock must be held */ -static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) -{ - irq->hw = false; - irq->hwintid = 0; - irq->get_input_level = NULL; -} - -int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, - u32 vintid, bool (*get_input_level)(int vindid)) -{ - struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); - unsigned long flags; - int ret; - - BUG_ON(!irq); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, 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; - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - irq->active = false; - irq->pending_latch = false; - irq->line_level = false; - raw_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; - unsigned long flags; - - if (!vgic_initialized(vcpu->kvm)) - return -EAGAIN; - - irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); - BUG_ON(!irq); - - raw_spin_lock_irqsave(&irq->irq_lock, flags); - kvm_vgic_unmap_irq(irq); - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - - return 0; -} - -/** - * kvm_vgic_set_owner - Set the owner of an interrupt for a VM - * - * @vcpu: Pointer to the VCPU (used for PPIs) - * @intid: The virtual INTID identifying the interrupt (PPI or SPI) - * @owner: Opaque pointer to the owner - * - * Returns 0 if intid is not already used by another in-kernel device and the - * owner is set, otherwise returns an error code. - */ -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)) - return -EAGAIN; - - /* SGIs and LPIs cannot be wired up to any device */ - if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid)) - return -EINVAL; - - irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - raw_spin_lock_irqsave(&irq->irq_lock, flags); - if (irq->owner && irq->owner != owner) - ret = -EEXIST; - else - irq->owner = owner; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - - return ret; -} - -/** - * vgic_prune_ap_list - Remove non-relevant interrupts from the list - * - * @vcpu: The VCPU pointer - * - * Go over the list of "interesting" interrupts, and prune those that we - * won't have to consider in the near future. - */ -static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_irq *irq, *tmp; - - DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - -retry: - raw_spin_lock(&vgic_cpu->ap_list_lock); - - list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { - struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; - bool target_vcpu_needs_kick = false; - - raw_spin_lock(&irq->irq_lock); - - BUG_ON(vcpu != irq->vcpu); - - target_vcpu = vgic_target_oracle(irq); - - if (!target_vcpu) { - /* - * We don't need to process this interrupt any - * further, move it off the list. - */ - list_del(&irq->ap_list); - irq->vcpu = NULL; - raw_spin_unlock(&irq->irq_lock); - - /* - * This vgic_put_irq call matches the - * vgic_get_irq_kref in vgic_queue_irq_unlock, - * where we added the LPI to the ap_list. As - * we remove the irq from the list, we drop - * also drop the refcount. - */ - vgic_put_irq(vcpu->kvm, irq); - continue; - } - - if (target_vcpu == vcpu) { - /* We're on the right CPU */ - raw_spin_unlock(&irq->irq_lock); - continue; - } - - /* This interrupt looks like it has to be migrated. */ - - raw_spin_unlock(&irq->irq_lock); - raw_spin_unlock(&vgic_cpu->ap_list_lock); - - /* - * Ensure locking order by always locking the smallest - * ID first. - */ - if (vcpu->vcpu_id < target_vcpu->vcpu_id) { - vcpuA = vcpu; - vcpuB = target_vcpu; - } else { - vcpuA = target_vcpu; - vcpuB = vcpu; - } - - raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); - raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, - SINGLE_DEPTH_NESTING); - raw_spin_lock(&irq->irq_lock); - - /* - * If the affinity has been preserved, move the - * interrupt around. Otherwise, it means things have - * changed while the interrupt was unlocked, and we - * need to replay this. - * - * In all cases, we cannot trust the list not to have - * changed, so we restart from the beginning. - */ - if (target_vcpu == vgic_target_oracle(irq)) { - struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu; - - list_del(&irq->ap_list); - irq->vcpu = target_vcpu; - list_add_tail(&irq->ap_list, &new_cpu->ap_list_head); - target_vcpu_needs_kick = true; - } - - raw_spin_unlock(&irq->irq_lock); - raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); - raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); - - if (target_vcpu_needs_kick) { - kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); - kvm_vcpu_kick(target_vcpu); - } - - goto retry; - } - - raw_spin_unlock(&vgic_cpu->ap_list_lock); -} - -static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_fold_lr_state(vcpu); - else - vgic_v3_fold_lr_state(vcpu); -} - -/* Requires the irq_lock to be held. */ -static inline void vgic_populate_lr(struct kvm_vcpu *vcpu, - struct vgic_irq *irq, int lr) -{ - lockdep_assert_held(&irq->irq_lock); - - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_populate_lr(vcpu, irq, lr); - else - vgic_v3_populate_lr(vcpu, irq, lr); -} - -static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_clear_lr(vcpu, lr); - else - vgic_v3_clear_lr(vcpu, lr); -} - -static inline void vgic_set_underflow(struct kvm_vcpu *vcpu) -{ - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_set_underflow(vcpu); - else - vgic_v3_set_underflow(vcpu); -} - -/* Requires the ap_list_lock to be held. */ -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; - - lockdep_assert_held(&vgic_cpu->ap_list_lock); - - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - int w; - - raw_spin_lock(&irq->irq_lock); - /* GICv2 SGIs can count for more than one... */ - w = vgic_irq_get_lr_count(irq); - raw_spin_unlock(&irq->irq_lock); - - count += w; - *multi_sgi |= (w > 1); - } - return count; -} - -/* Requires the VCPU's ap_list_lock to be held. */ -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; - bool multi_sgi; - u8 prio = 0xff; - - lockdep_assert_held(&vgic_cpu->ap_list_lock); - - 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) { - raw_spin_lock(&irq->irq_lock); - - /* - * If we have multi-SGIs in the pipeline, we need to - * 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. - */ - if (multi_sgi && irq->priority > prio) { - _raw_spin_unlock(&irq->irq_lock); - break; - } - - if (likely(vgic_target_oracle(irq) == vcpu)) { - vgic_populate_lr(vcpu, irq, count++); - - if (irq->source) - prio = irq->priority; - } - - raw_spin_unlock(&irq->irq_lock); - - if (count == kvm_vgic_global_state.nr_lr) { - if (!list_is_last(&irq->ap_list, - &vgic_cpu->ap_list_head)) - vgic_set_underflow(vcpu); - break; - } - } - - vcpu->arch.vgic_cpu.used_lrs = count; - - /* Nuke remaining LRs */ - for ( ; count < kvm_vgic_global_state.nr_lr; count++) - vgic_clear_lr(vcpu, count); -} - -static inline bool can_access_vgic_from_kernel(void) -{ - /* - * GICv2 can always be accessed from the kernel because it is - * memory-mapped, and VHE systems can access GICv3 EL2 system - * registers. - */ - return !static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) || has_vhe(); -} - -static inline void vgic_save_state(struct kvm_vcpu *vcpu) -{ - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) - vgic_v2_save_state(vcpu); - else - __vgic_v3_save_state(vcpu); -} - -/* Sync back the hardware VGIC state into our emulation after a guest's run. */ -void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - /* An empty ap_list_head implies used_lrs == 0 */ - if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) - return; - - if (can_access_vgic_from_kernel()) - vgic_save_state(vcpu); - - if (vgic_cpu->used_lrs) - vgic_fold_lr_state(vcpu); - vgic_prune_ap_list(vcpu); -} - -static inline void vgic_restore_state(struct kvm_vcpu *vcpu) -{ - if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) - vgic_v2_restore_state(vcpu); - else - __vgic_v3_restore_state(vcpu); -} - -/* Flush our emulation state into the GIC hardware before entering the guest. */ -void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) -{ - /* - * If there are no virtual interrupts active or pending for this - * VCPU, then there is no work to do and we can bail out without - * taking any lock. There is a potential race with someone injecting - * interrupts to the VCPU, but it is a benign race as the VCPU will - * either observe the new interrupt before or after doing this check, - * and introducing additional synchronization mechanism doesn't change - * this. - * - * Note that we still need to go through the whole thing if anything - * can be directly injected (GICv4). - */ - if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) && - !vgic_supports_direct_msis(vcpu->kvm)) - return; - - DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - - if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) { - raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); - vgic_flush_lr_state(vcpu); - raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); - } - - if (can_access_vgic_from_kernel()) - vgic_restore_state(vcpu); -} - -void kvm_vgic_load(struct kvm_vcpu *vcpu) -{ - if (unlikely(!vgic_initialized(vcpu->kvm))) - return; - - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_load(vcpu); - else - vgic_v3_load(vcpu); -} - -void kvm_vgic_put(struct kvm_vcpu *vcpu) -{ - if (unlikely(!vgic_initialized(vcpu->kvm))) - return; - - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_put(vcpu); - else - vgic_v3_put(vcpu); -} - -void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu) -{ - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) - return; - - if (kvm_vgic_global_state.type == VGIC_V2) - vgic_v2_vmcr_sync(vcpu); - else - vgic_v3_vmcr_sync(vcpu); -} - -int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_irq *irq; - bool pending = false; - unsigned long flags; - struct vgic_vmcr vmcr; - - if (!vcpu->kvm->arch.vgic.enabled) - return false; - - if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last) - return true; - - vgic_get_vmcr(vcpu, &vmcr); - - raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); - - list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - raw_spin_lock(&irq->irq_lock); - pending = irq_is_pending(irq) && irq->enabled && - !irq->active && - irq->priority < vmcr.pmr; - raw_spin_unlock(&irq->irq_lock); - - if (pending) - break; - } - - raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); - - return pending; -} - -void vgic_kick_vcpus(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu; - int c; - - /* - * We've injected an interrupt, time to find out who deserves - * a good kick... - */ - kvm_for_each_vcpu(c, vcpu, kvm) { - if (kvm_vgic_vcpu_pending_irq(vcpu)) { - kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); - kvm_vcpu_kick(vcpu); - } - } -} - -bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int 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); - raw_spin_lock_irqsave(&irq->irq_lock, flags); - map_is_active = irq->hw && irq->active; - raw_spin_unlock_irqrestore(&irq->irq_lock, flags); - vgic_put_irq(vcpu->kvm, irq); - - return map_is_active; -} diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h deleted file mode 100644 index 769e4802645e..000000000000 --- a/virt/kvm/arm/vgic/vgic.h +++ /dev/null @@ -1,321 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2015, 2016 ARM Ltd. - */ -#ifndef __KVM_ARM_VGIC_NEW_H__ -#define __KVM_ARM_VGIC_NEW_H__ - -#include <linux/irqchip/arm-gic-common.h> - -#define PRODUCT_ID_KVM 0x4b /* ASCII code K */ -#define IMPLEMENTER_ARM 0x43b - -#define VGIC_ADDR_UNDEF (-1) -#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF) - -#define INTERRUPT_ID_BITS_SPIS 10 -#define INTERRUPT_ID_BITS_ITS 16 -#define VGIC_PRI_BITS 5 - -#define vgic_irq_is_sgi(intid) ((intid) < VGIC_NR_SGIS) - -#define VGIC_AFFINITY_0_SHIFT 0 -#define VGIC_AFFINITY_0_MASK (0xffUL << VGIC_AFFINITY_0_SHIFT) -#define VGIC_AFFINITY_1_SHIFT 8 -#define VGIC_AFFINITY_1_MASK (0xffUL << VGIC_AFFINITY_1_SHIFT) -#define VGIC_AFFINITY_2_SHIFT 16 -#define VGIC_AFFINITY_2_MASK (0xffUL << VGIC_AFFINITY_2_SHIFT) -#define VGIC_AFFINITY_3_SHIFT 24 -#define VGIC_AFFINITY_3_MASK (0xffUL << VGIC_AFFINITY_3_SHIFT) - -#define VGIC_AFFINITY_LEVEL(reg, level) \ - ((((reg) & VGIC_AFFINITY_## level ##_MASK) \ - >> VGIC_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level)) - -/* - * The Userspace encodes the affinity differently from the MPIDR, - * Below macro converts vgic userspace format to MPIDR reg format. - */ -#define VGIC_TO_MPIDR(val) (VGIC_AFFINITY_LEVEL(val, 0) | \ - VGIC_AFFINITY_LEVEL(val, 1) | \ - VGIC_AFFINITY_LEVEL(val, 2) | \ - VGIC_AFFINITY_LEVEL(val, 3)) - -/* - * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt, - * below macros are defined for CPUREG encoding. - */ -#define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000 -#define KVM_REG_ARM_VGIC_SYSREG_OP0_SHIFT 14 -#define KVM_REG_ARM_VGIC_SYSREG_OP1_MASK 0x0000000000003800 -#define KVM_REG_ARM_VGIC_SYSREG_OP1_SHIFT 11 -#define KVM_REG_ARM_VGIC_SYSREG_CRN_MASK 0x0000000000000780 -#define KVM_REG_ARM_VGIC_SYSREG_CRN_SHIFT 7 -#define KVM_REG_ARM_VGIC_SYSREG_CRM_MASK 0x0000000000000078 -#define KVM_REG_ARM_VGIC_SYSREG_CRM_SHIFT 3 -#define KVM_REG_ARM_VGIC_SYSREG_OP2_MASK 0x0000000000000007 -#define KVM_REG_ARM_VGIC_SYSREG_OP2_SHIFT 0 - -#define KVM_DEV_ARM_VGIC_SYSREG_MASK (KVM_REG_ARM_VGIC_SYSREG_OP0_MASK | \ - KVM_REG_ARM_VGIC_SYSREG_OP1_MASK | \ - KVM_REG_ARM_VGIC_SYSREG_CRN_MASK | \ - KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \ - KVM_REG_ARM_VGIC_SYSREG_OP2_MASK) - -/* - * As per Documentation/virt/kvm/devices/arm-vgic-its.txt, - * below macros are defined for ITS table entry encoding. - */ -#define KVM_ITS_CTE_VALID_SHIFT 63 -#define KVM_ITS_CTE_VALID_MASK BIT_ULL(63) -#define KVM_ITS_CTE_RDBASE_SHIFT 16 -#define KVM_ITS_CTE_ICID_MASK GENMASK_ULL(15, 0) -#define KVM_ITS_ITE_NEXT_SHIFT 48 -#define KVM_ITS_ITE_PINTID_SHIFT 16 -#define KVM_ITS_ITE_PINTID_MASK GENMASK_ULL(47, 16) -#define KVM_ITS_ITE_ICID_MASK GENMASK_ULL(15, 0) -#define KVM_ITS_DTE_VALID_SHIFT 63 -#define KVM_ITS_DTE_VALID_MASK BIT_ULL(63) -#define KVM_ITS_DTE_NEXT_SHIFT 49 -#define KVM_ITS_DTE_NEXT_MASK GENMASK_ULL(62, 49) -#define KVM_ITS_DTE_ITTADDR_SHIFT 5 -#define KVM_ITS_DTE_ITTADDR_MASK GENMASK_ULL(48, 5) -#define KVM_ITS_DTE_SIZE_MASK GENMASK_ULL(4, 0) -#define KVM_ITS_L1E_VALID_MASK BIT_ULL(63) -/* we only support 64 kB translation table page size */ -#define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) - -#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0) -#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12) -#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12 -#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16) -#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52) -#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52 - -#ifdef CONFIG_DEBUG_SPINLOCK -#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p) -#else -#define DEBUG_SPINLOCK_BUG_ON(p) -#endif - -/* 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) - return irq->pending_latch; - else - return irq->pending_latch || irq->line_level; -} - -static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq) -{ - return irq->config == VGIC_CONFIG_LEVEL && irq->hw; -} - -static inline int vgic_irq_get_lr_count(struct vgic_irq *irq) -{ - /* Account for the active state as an interrupt */ - if (vgic_irq_is_sgi(irq->intid) && irq->source) - return hweight8(irq->source) + irq->active; - - return irq_is_pending(irq) || irq->active; -} - -static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) -{ - return vgic_irq_get_lr_count(irq) > 1; -} - -/* - * This struct provides an intermediate representation of the fields contained - * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC - * state to userspace can generate either GICv2 or GICv3 CPU interface - * registers regardless of the hardware backed GIC used. - */ -struct vgic_vmcr { - u32 grpen0; - u32 grpen1; - - u32 ackctl; - u32 fiqen; - u32 cbpr; - u32 eoim; - - u32 abpr; - u32 bpr; - u32 pmr; /* Priority mask field in the GICC_PMR and - * ICC_PMR_EL1 priority field format */ -}; - -struct vgic_reg_attr { - struct kvm_vcpu *vcpu; - gpa_t addr; -}; - -int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, - struct vgic_reg_attr *reg_attr); -int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, - struct vgic_reg_attr *reg_attr); -const struct vgic_register_region * -vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, - gpa_t addr, int len); -struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, - u32 intid); -void __vgic_put_lpi_locked(struct kvm *kvm, struct vgic_irq *irq); -void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq); -bool vgic_get_phys_line_level(struct vgic_irq *irq); -void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); -void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); -bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, - unsigned long flags); -void vgic_kick_vcpus(struct kvm *kvm); - -int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr, - phys_addr_t addr, phys_addr_t alignment); - -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); -int vgic_v2_cpuif_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val); -void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); -void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); -void vgic_v2_enable(struct kvm_vcpu *vcpu); -int vgic_v2_probe(const struct gic_kvm_info *info); -int vgic_v2_map_resources(struct kvm *kvm); -int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, - enum vgic_type); - -void vgic_v2_init_lrs(void); -void vgic_v2_load(struct kvm_vcpu *vcpu); -void vgic_v2_put(struct kvm_vcpu *vcpu); -void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu); - -void vgic_v2_save_state(struct kvm_vcpu *vcpu); -void vgic_v2_restore_state(struct kvm_vcpu *vcpu); - -static inline void vgic_get_irq_kref(struct vgic_irq *irq) -{ - if (irq->intid < VGIC_MIN_LPI) - return; - - kref_get(&irq->refcount); -} - -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); -int vgic_v3_probe(const struct gic_kvm_info *info); -int vgic_v3_map_resources(struct kvm *kvm); -int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); -int vgic_v3_save_pending_tables(struct kvm *kvm); -int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); -int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); -bool vgic_v3_check_base(struct kvm *kvm); - -void vgic_v3_load(struct kvm_vcpu *vcpu); -void vgic_v3_put(struct kvm_vcpu *vcpu); -void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu); - -bool vgic_has_its(struct kvm *kvm); -int kvm_vgic_register_its_device(void); -void vgic_enable_lpis(struct kvm_vcpu *vcpu); -void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu); -int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi); -int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); -int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val); -int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write, - int offset, u32 *val); -int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, - u64 id, u64 *val); -int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id, - u64 *reg); -int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write, - u32 intid, u64 *val); -int kvm_register_vgic_device(unsigned long type); -void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); -void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); -int vgic_lazy_init(struct kvm *kvm); -int vgic_init(struct kvm *kvm); - -void vgic_debug_init(struct kvm *kvm); -void vgic_debug_destroy(struct kvm *kvm); - -bool lock_all_vcpus(struct kvm *kvm); -void unlock_all_vcpus(struct kvm *kvm); - -static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *cpu_if = &vcpu->arch.vgic_cpu; - - /* - * num_pri_bits are initialized with HW supported values. - * We can rely safely on num_pri_bits even if VM has not - * restored ICC_CTLR_EL1 before restoring APnR registers. - */ - switch (cpu_if->num_pri_bits) { - case 7: return 3; - case 6: return 1; - default: return 0; - } -} - -static inline bool -vgic_v3_redist_region_full(struct vgic_redist_region *region) -{ - if (!region->count) - return false; - - return (region->free_index >= region->count); -} - -struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); - -static inline size_t -vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) -{ - if (!rdreg->count) - return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE; - else - return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; -} - -struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, - u32 index); - -bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); - -static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) -{ - struct vgic_dist *d = &kvm->arch.vgic; - - return (base + size > d->vgic_dist_base) && - (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); -} - -int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr); -int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid, struct vgic_irq **irq); -struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); -int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi); -void vgic_lpi_translation_cache_init(struct kvm *kvm); -void vgic_lpi_translation_cache_destroy(struct kvm *kvm); -void vgic_its_invalidate_cache(struct kvm *kvm); - -bool vgic_supports_direct_msis(struct kvm *kvm); -int vgic_v4_init(struct kvm *kvm); -void vgic_v4_teardown(struct kvm *kvm); -void vgic_v4_configure_vsgis(struct kvm *kvm); - -#endif |