#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/uaccess.h>
+#include <linux/list_sort.h>
#include <linux/irqchip/arm-gic-v3.h>
}
/*
- * Create a snapshot of the current LPI list, so that we can enumerate all
- * LPIs without holding any lock.
- * Returns the array length and puts the kmalloc'ed array into intid_ptr.
+ * 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.
*/
-static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
+static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
u32 *intids;
int irq_count = dist->lpi_list_count, i = 0;
spin_lock(&dist->lpi_list_lock);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
/* We don't need to "get" the IRQ, as we hold the list lock. */
- intids[i] = irq->intid;
- if (++i == irq_count)
- break;
+ if (irq->target_vcpu != vcpu)
+ continue;
+ intids[i++] = irq->intid;
}
spin_unlock(&dist->lpi_list_lock);
*intid_ptr = intids;
- return irq_count;
+ return i;
}
/*
}
/*
- * Scan the whole LPI pending table and sync the pending bit in there
+ * Sync the pending table pending bit of LPIs targeting @vcpu
* with our own data structures. This relies on the LPI being
* mapped before.
*/
u32 *intids;
int nr_irqs, i;
- nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
+ nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
if (nr_irqs < 0)
return nr_irqs;
vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- irq_count = vgic_copy_lpi_list(kvm, &intids);
+ irq_count = vgic_copy_lpi_list(vcpu, &intids);
if (irq_count < 0)
return irq_count;
its_sync_lpi_pending_table(vcpu);
}
-static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its,
+ u64 addr)
{
struct vgic_io_device *iodev = &its->iodev;
int ret;
- if (!its->initialized)
- return -EBUSY;
-
- if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
- return -ENXIO;
+ 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;
- mutex_lock(&kvm->slots_lock);
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;
INIT_LIST_HEAD(&its->collection_list);
dev->kvm->arch.vgic.has_its = true;
- its->initialized = false;
its->enabled = false;
its->dev = dev;
return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
}
+static void vgic_its_free_device(struct kvm *kvm, struct its_device *dev)
+{
+ struct its_ite *ite, *tmp;
+
+ list_for_each_entry_safe(ite, tmp, &dev->itt_head, ite_list)
+ its_free_ite(kvm, ite);
+ list_del(&dev->dev_list);
+ kfree(dev);
+}
+
static void vgic_its_destroy(struct kvm_device *kvm_dev)
{
struct kvm *kvm = kvm_dev->kvm;
struct vgic_its *its = kvm_dev->private;
- struct its_device *dev;
- struct its_ite *ite;
- struct list_head *dev_cur, *dev_temp;
struct list_head *cur, *temp;
/*
return;
mutex_lock(&its->its_lock);
- list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
- dev = container_of(dev_cur, struct its_device, dev_list);
- list_for_each_safe(cur, temp, &dev->itt_head) {
- ite = (container_of(cur, struct its_ite, ite_list));
- its_free_ite(kvm, ite);
- }
- list_del(dev_cur);
- kfree(dev);
+ list_for_each_safe(cur, temp, &its->device_list) {
+ struct its_device *dev;
+
+ dev = list_entry(cur, struct its_device, dev_list);
+ vgic_its_free_device(kvm, dev);
}
list_for_each_safe(cur, temp, &its->collection_list) {
+ struct its_collection *coll;
+
+ coll = list_entry(cur, struct its_collection, coll_list);
list_del(cur);
- kfree(container_of(cur, struct its_collection, coll_list));
+ kfree(coll);
}
mutex_unlock(&its->its_lock);
return ret;
}
-u32 compute_next_devid_offset(struct list_head *h, struct its_device *dev)
+static u32 compute_next_devid_offset(struct list_head *h,
+ struct its_device *dev)
{
struct its_device *next;
u32 next_offset;
return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET);
}
-u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
+static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
{
struct its_ite *next;
u32 next_offset;
* Return: < 0 on error, 0 if last element was identified, 1 otherwise
* (the last element may not be found on second level tables)
*/
-int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
- int start_id, entry_fn_t fn, void *opaque)
+static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
+ int start_id, entry_fn_t fn, void *opaque)
{
void *entry = kzalloc(esz, GFP_KERNEL);
struct kvm *kvm = its->dev->kvm;
return ret;
}
+/**
+ * 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->lpi << KVM_ITS_ITE_PINTID_SHIFT) |
+ ite->collection->collection_id;
+ val = cpu_to_le64(val);
+ return kvm_write_guest(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, lpi_id, 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;
+
+ ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+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);
+
+ 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(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)
{
- return -ENXIO;
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ struct its_device *dev;
+ int dte_esz = abi->dte_esz;
+ u64 baser;
+
+ baser = its->baser_device_table;
+
+ 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);
+
+ if (ret <= 0)
+ return ret;
+
+ return 1;
}
/**
*/
static int vgic_its_restore_device_tables(struct vgic_its *its)
{
- return -ENXIO;
+ 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 = BASER_ADDRESS(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);
+ }
+
+ if (ret > 0)
+ ret = -EINVAL;
+
+ return ret;
}
static int vgic_its_save_cte(struct vgic_its *its,
goto out;
ret = vgic_its_restore_device_tables(its);
-
out:
unlock_all_vcpus(kvm);
mutex_unlock(&its->its_lock);
mutex_unlock(&kvm->lock);
- if (ret)
- return ret;
-
- /*
- * On restore path, MSI injections can happen before the
- * first VCPU run so let's complete the GIC init here.
- */
- return kvm_vgic_map_resources(its->dev->kvm);
+ return ret;
}
static int vgic_its_commit_v0(struct vgic_its *its)
if (ret)
return ret;
- its->vgic_its_base = addr;
-
- return 0;
+ return vgic_register_its_iodev(dev->kvm, its, addr);
}
case KVM_DEV_ARM_VGIC_GRP_CTRL: {
const struct vgic_its_abi *abi = vgic_its_get_abi(its);
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
- its->initialized = true;
-
+ /* Nothing to do */
return 0;
case KVM_DEV_ARM_ITS_SAVE_TABLES:
return abi->save_tables(its);
return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
KVM_DEV_TYPE_ARM_VGIC_ITS);
}
-
-/*
- * Registers all ITSes with the kvm_io_bus framework.
- * To follow the existing VGIC initialization sequence, this has to be
- * done as late as possible, just before the first VCPU runs.
- */
-int vgic_register_its_iodevs(struct kvm *kvm)
-{
- struct kvm_device *dev;
- int ret = 0;
-
- list_for_each_entry(dev, &kvm->devices, vm_node) {
- if (dev->ops != &kvm_arm_vgic_its_ops)
- continue;
-
- ret = vgic_register_its_iodev(kvm, dev->private);
- if (ret)
- return ret;
- /*
- * We don't need to care about tearing down previously
- * registered ITSes, as the kvm_io_bus framework removes
- * them for us if the VM gets destroyed.
- */
- }
-
- return ret;
-}
projects / karo-tx-linux.git / blobdiff