PTFF_QAF);
if (test_facility(17)) { /* MSA */
- __cpacf_query(CPACF_KMAC, kvm_s390_available_subfunc.kmac);
- __cpacf_query(CPACF_KMC, kvm_s390_available_subfunc.kmc);
- __cpacf_query(CPACF_KM, kvm_s390_available_subfunc.km);
- __cpacf_query(CPACF_KIMD, kvm_s390_available_subfunc.kimd);
- __cpacf_query(CPACF_KLMD, kvm_s390_available_subfunc.klmd);
+ __cpacf_query(CPACF_KMAC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmac);
+ __cpacf_query(CPACF_KMC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmc);
+ __cpacf_query(CPACF_KM, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.km);
+ __cpacf_query(CPACF_KIMD, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kimd);
+ __cpacf_query(CPACF_KLMD, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.klmd);
}
if (test_facility(76)) /* MSA3 */
- __cpacf_query(CPACF_PCKMO, kvm_s390_available_subfunc.pckmo);
+ __cpacf_query(CPACF_PCKMO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.pckmo);
if (test_facility(77)) { /* MSA4 */
- __cpacf_query(CPACF_KMCTR, kvm_s390_available_subfunc.kmctr);
- __cpacf_query(CPACF_KMF, kvm_s390_available_subfunc.kmf);
- __cpacf_query(CPACF_KMO, kvm_s390_available_subfunc.kmo);
- __cpacf_query(CPACF_PCC, kvm_s390_available_subfunc.pcc);
+ __cpacf_query(CPACF_KMCTR, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmctr);
+ __cpacf_query(CPACF_KMF, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmf);
+ __cpacf_query(CPACF_KMO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.kmo);
+ __cpacf_query(CPACF_PCC, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.pcc);
}
if (test_facility(57)) /* MSA5 */
- __cpacf_query(CPACF_PPNO, kvm_s390_available_subfunc.ppno);
+ __cpacf_query(CPACF_PPNO, (cpacf_mask_t *)
+ kvm_s390_available_subfunc.ppno);
if (MACHINE_HAS_ESOP)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
r = KVM_S390_BSCA_CPU_SLOTS;
- if (sclp.has_esca && sclp.has_64bscao)
+ if (!kvm_s390_use_sca_entries())
+ r = KVM_MAX_VCPUS;
+ else if (sclp.has_esca && sclp.has_64bscao)
r = KVM_S390_ESCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
static void sca_del_vcpu(struct kvm_vcpu *vcpu)
{
+ if (!kvm_s390_use_sca_entries())
+ return;
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
{
+ if (!kvm_s390_use_sca_entries()) {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ /* we still need the basic sca for the ipte control */
+ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
+ vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ }
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
{
int rc;
+ if (!kvm_s390_use_sca_entries()) {
+ if (id < KVM_MAX_VCPUS)
+ return true;
+ return false;
+ }
if (id < KVM_S390_BSCA_CPU_SLOTS)
return true;
if (!sclp.has_esca || !sclp.has_64bscao)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
- if (test_kvm_facility(vcpu->kvm, 64))
- vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID)
kvm_clear_async_pf_completion_queue(vcpu);
}
+ /*
+ * If userspace sets the riccb (e.g. after migration) to a valid state,
+ * we should enable RI here instead of doing the lazy enablement.
+ */
+ if ((kvm_run->kvm_dirty_regs & KVM_SYNC_RICCB) &&
+ test_kvm_facility(vcpu->kvm, 64)) {
+ struct runtime_instr_cb *riccb =
+ (struct runtime_instr_cb *) &kvm_run->s.regs.riccb;
+
+ if (riccb->valid)
+ vcpu->arch.sie_block->ecb3 |= 0x01;
+ }
+
kvm_run->kvm_dirty_regs = 0;
}
return kvm_s390_store_status_unloaded(vcpu, addr);
}
- /*
- * store additional status at address
- */
- int kvm_s390_store_adtl_status_unloaded(struct kvm_vcpu *vcpu,
- unsigned long gpa)
- {
- /* Only bits 0-53 are used for address formation */
- if (!(gpa & ~0x3ff))
- return 0;
-
- return write_guest_abs(vcpu, gpa & ~0x3ff,
- (void *)&vcpu->run->s.regs.vrs, 512);
- }
-
- int kvm_s390_vcpu_store_adtl_status(struct kvm_vcpu *vcpu, unsigned long addr)
- {
- if (!test_kvm_facility(vcpu->kvm, 129))
- return 0;
-
- /*
- * The guest VXRS are in the host VXRs due to the lazy
- * copying in vcpu load/put. We can simply call save_fpu_regs()
- * to save the current register state because we are in the
- * middle of a load/put cycle.
- *
- * Let's update our copies before we save it into the save area.
- */
- save_fpu_regs();
-
- return kvm_s390_store_adtl_status_unloaded(vcpu, addr);
- }
-
static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
{
kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
#include <linux/sched.h>
#include <linux/trace_events.h>
#include <linux/slab.h>
+ #include <linux/amd-iommu.h>
+ #include <linux/hashtable.h>
#include <asm/apic.h>
#include <asm/perf_event.h>
#include <asm/desc.h>
#include <asm/debugreg.h>
#include <asm/kvm_para.h>
+ #include <asm/irq_remapping.h>
#include <asm/virtext.h>
#include "trace.h"
#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0
#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF
+ /* AVIC GATAG is encoded using VM and VCPU IDs */
+ #define AVIC_VCPU_ID_BITS 8
+ #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1)
+
+ #define AVIC_VM_ID_BITS 24
+ #define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS)
+ #define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1)
+
+ #define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
+ (y & AVIC_VCPU_ID_MASK))
+ #define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
+ #define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)
+
static bool erratum_383_found __read_mostly;
static const u32 host_save_user_msrs[] = {
struct page *avic_backing_page;
u64 *avic_physical_id_cache;
bool avic_is_running;
+
+ /*
+ * Per-vcpu list of struct amd_svm_iommu_ir:
+ * This is used mainly to store interrupt remapping information used
+ * when update the vcpu affinity. This avoids the need to scan for
+ * IRTE and try to match ga_tag in the IOMMU driver.
+ */
+ struct list_head ir_list;
+ spinlock_t ir_list_lock;
+ };
+
+ /*
+ * This is a wrapper of struct amd_iommu_ir_data.
+ */
+ struct amd_svm_iommu_ir {
+ struct list_head node; /* Used by SVM for per-vcpu ir_list */
+ void *data; /* Storing pointer to struct amd_ir_data */
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
module_param(avic, int, S_IRUGO);
#endif
+ /* AVIC VM ID bit masks and lock */
+ static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR);
+ static DEFINE_SPINLOCK(avic_vm_id_lock);
+
static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
+ /* Note:
+ * This hash table is used to map VM_ID to a struct kvm_arch,
+ * when handling AMD IOMMU GALOG notification to schedule in
+ * a particular vCPU.
+ */
+ #define SVM_VM_DATA_HASH_BITS 8
+ DECLARE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
+ static spinlock_t svm_vm_data_hash_lock;
+
+ /* Note:
+ * This function is called from IOMMU driver to notify
+ * SVM to schedule in a particular vCPU of a particular VM.
+ */
+ static int avic_ga_log_notifier(u32 ga_tag)
+ {
+ unsigned long flags;
+ struct kvm_arch *ka = NULL;
+ struct kvm_vcpu *vcpu = NULL;
+ u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag);
+ u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag);
+
+ pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id);
+
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_for_each_possible(svm_vm_data_hash, ka, hnode, vm_id) {
+ struct kvm *kvm = container_of(ka, struct kvm, arch);
+ struct kvm_arch *vm_data = &kvm->arch;
+
+ if (vm_data->avic_vm_id != vm_id)
+ continue;
+ vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
+ break;
+ }
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
+
+ if (!vcpu)
+ return 0;
+
+ /* Note:
+ * At this point, the IOMMU should have already set the pending
+ * bit in the vAPIC backing page. So, we just need to schedule
+ * in the vcpu.
+ */
+ if (vcpu->mode == OUTSIDE_GUEST_MODE)
+ kvm_vcpu_wake_up(vcpu);
+
+ return 0;
+ }
+
static __init int svm_hardware_setup(void)
{
int cpu;
if (avic) {
if (!npt_enabled ||
!boot_cpu_has(X86_FEATURE_AVIC) ||
- !IS_ENABLED(CONFIG_X86_LOCAL_APIC))
+ !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) {
avic = false;
- else
+ } else {
pr_info("AVIC enabled\n");
+
+ hash_init(svm_vm_data_hash);
+ spin_lock_init(&svm_vm_data_hash_lock);
+ amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+ }
}
return 0;
return 0;
}
+ static inline int avic_get_next_vm_id(void)
+ {
+ int id;
+
+ spin_lock(&avic_vm_id_lock);
+
+ /* AVIC VM ID is one-based. */
+ id = find_next_zero_bit(avic_vm_id_bitmap, AVIC_VM_ID_NR, 1);
+ if (id <= AVIC_VM_ID_MASK)
+ __set_bit(id, avic_vm_id_bitmap);
+ else
+ id = -EAGAIN;
+
+ spin_unlock(&avic_vm_id_lock);
+ return id;
+ }
+
+ static inline int avic_free_vm_id(int id)
+ {
+ if (id <= 0 || id > AVIC_VM_ID_MASK)
+ return -EINVAL;
+
+ spin_lock(&avic_vm_id_lock);
+ __clear_bit(id, avic_vm_id_bitmap);
+ spin_unlock(&avic_vm_id_lock);
+ return 0;
+ }
+
static void avic_vm_destroy(struct kvm *kvm)
{
+ unsigned long flags;
struct kvm_arch *vm_data = &kvm->arch;
+ avic_free_vm_id(vm_data->avic_vm_id);
+
if (vm_data->avic_logical_id_table_page)
__free_page(vm_data->avic_logical_id_table_page);
if (vm_data->avic_physical_id_table_page)
__free_page(vm_data->avic_physical_id_table_page);
+
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_del(&vm_data->hnode);
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
}
static int avic_vm_init(struct kvm *kvm)
{
+ unsigned long flags;
int err = -ENOMEM;
struct kvm_arch *vm_data = &kvm->arch;
struct page *p_page;
if (!avic)
return 0;
+ vm_data->avic_vm_id = avic_get_next_vm_id();
+ if (vm_data->avic_vm_id < 0)
+ return vm_data->avic_vm_id;
+
/* Allocating physical APIC ID table (4KB) */
p_page = alloc_page(GFP_KERNEL);
if (!p_page)
vm_data->avic_logical_id_table_page = l_page;
clear_page(page_address(l_page));
+ spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
+ hash_add(svm_vm_data_hash, &vm_data->hnode, vm_data->avic_vm_id);
+ spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
+
return 0;
free_avic:
return err;
}
- /**
- * This function is called during VCPU halt/unhalt.
- */
- static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+ static inline int
+ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
{
- u64 entry;
- int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
+ int ret = 0;
+ unsigned long flags;
+ struct amd_svm_iommu_ir *ir;
struct vcpu_svm *svm = to_svm(vcpu);
- if (!kvm_vcpu_apicv_active(vcpu))
- return;
-
- svm->avic_is_running = is_run;
+ if (!kvm_arch_has_assigned_device(vcpu->kvm))
+ return 0;
- /* ID = 0xff (broadcast), ID > 0xff (reserved) */
- if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
- return;
+ /*
+ * Here, we go through the per-vcpu ir_list to update all existing
+ * interrupt remapping table entry targeting this vcpu.
+ */
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
- entry = READ_ONCE(*(svm->avic_physical_id_cache));
- WARN_ON(is_run == !!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK));
+ if (list_empty(&svm->ir_list))
+ goto out;
- entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- if (is_run)
- entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+ list_for_each_entry(ir, &svm->ir_list, node) {
+ ret = amd_iommu_update_ga(cpu, r, ir->data);
+ if (ret)
+ break;
+ }
+ out:
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ return ret;
}
static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+ avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
+ svm->avic_is_running);
}
static void avic_vcpu_put(struct kvm_vcpu *vcpu)
return;
entry = READ_ONCE(*(svm->avic_physical_id_cache));
+ if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+ avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
}
+ /**
+ * This function is called during VCPU halt/unhalt.
+ */
+ static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+ {
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ svm->avic_is_running = is_run;
+ if (is_run)
+ avic_vcpu_load(vcpu, vcpu->cpu);
+ else
+ avic_vcpu_put(vcpu);
+ }
+
static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct vcpu_svm *svm = to_svm(vcpu);
err = avic_init_backing_page(&svm->vcpu);
if (err)
goto free_page4;
+
+ INIT_LIST_HEAD(&svm->ir_list);
+ spin_lock_init(&svm->ir_list_lock);
}
/* We initialize this flag to true to make sure that the is_running
kvm_vcpu_wake_up(vcpu);
}
+ static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+ {
+ unsigned long flags;
+ struct amd_svm_iommu_ir *cur;
+
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+ list_for_each_entry(cur, &svm->ir_list, node) {
+ if (cur->data != pi->ir_data)
+ continue;
+ list_del(&cur->node);
+ kfree(cur);
+ break;
+ }
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ }
+
+ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+ {
+ int ret = 0;
+ unsigned long flags;
+ struct amd_svm_iommu_ir *ir;
+
+ /**
+ * In some cases, the existing irte is updaed and re-set,
+ * so we need to check here if it's already been * added
+ * to the ir_list.
+ */
+ if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+ struct kvm *kvm = svm->vcpu.kvm;
+ u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
+ struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
+ struct vcpu_svm *prev_svm;
+
+ if (!prev_vcpu) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ prev_svm = to_svm(prev_vcpu);
+ svm_ir_list_del(prev_svm, pi);
+ }
+
+ /**
+ * Allocating new amd_iommu_pi_data, which will get
+ * add to the per-vcpu ir_list.
+ */
+ ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL);
+ if (!ir) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ir->data = pi->ir_data;
+
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+ list_add(&ir->node, &svm->ir_list);
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+ out:
+ return ret;
+ }
+
+ /**
+ * Note:
+ * The HW cannot support posting multicast/broadcast
+ * interrupts to a vCPU. So, we still use legacy interrupt
+ * remapping for these kind of interrupts.
+ *
+ * For lowest-priority interrupts, we only support
+ * those with single CPU as the destination, e.g. user
+ * configures the interrupts via /proc/irq or uses
+ * irqbalance to make the interrupts single-CPU.
+ */
+ static int
+ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
+ struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
+ {
+ struct kvm_lapic_irq irq;
+ struct kvm_vcpu *vcpu = NULL;
+
+ kvm_set_msi_irq(kvm, e, &irq);
+
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+ pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
+ __func__, irq.vector);
+ return -1;
+ }
+
+ pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
+ irq.vector);
+ *svm = to_svm(vcpu);
+ vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page);
+ vcpu_info->vector = irq.vector;
+
+ return 0;
+ }
+
+ /*
+ * svm_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+ uint32_t guest_irq, bool set)
+ {
+ struct kvm_kernel_irq_routing_entry *e;
+ struct kvm_irq_routing_table *irq_rt;
+ int idx, ret = -EINVAL;
+
+ if (!kvm_arch_has_assigned_device(kvm) ||
+ !irq_remapping_cap(IRQ_POSTING_CAP))
+ return 0;
+
+ pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
+ __func__, host_irq, guest_irq, set);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+ WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+ hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+ struct vcpu_data vcpu_info;
+ struct vcpu_svm *svm = NULL;
+
+ if (e->type != KVM_IRQ_ROUTING_MSI)
+ continue;
+
+ /**
+ * Here, we setup with legacy mode in the following cases:
+ * 1. When cannot target interrupt to a specific vcpu.
+ * 2. Unsetting posted interrupt.
+ * 3. APIC virtialization is disabled for the vcpu.
+ */
+ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
+ kvm_vcpu_apicv_active(&svm->vcpu)) {
+ struct amd_iommu_pi_data pi;
+
+ /* Try to enable guest_mode in IRTE */
+ pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK;
+ pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id,
+ svm->vcpu.vcpu_id);
+ pi.is_guest_mode = true;
+ pi.vcpu_data = &vcpu_info;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Here, we successfully setting up vcpu affinity in
+ * IOMMU guest mode. Now, we need to store the posted
+ * interrupt information in a per-vcpu ir_list so that
+ * we can reference to them directly when we update vcpu
+ * scheduling information in IOMMU irte.
+ */
+ if (!ret && pi.is_guest_mode)
+ svm_ir_list_add(svm, &pi);
+ } else {
+ /* Use legacy mode in IRTE */
+ struct amd_iommu_pi_data pi;
+
+ /**
+ * Here, pi is used to:
+ * - Tell IOMMU to use legacy mode for this interrupt.
+ * - Retrieve ga_tag of prior interrupt remapping data.
+ */
+ pi.is_guest_mode = false;
+ ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+ /**
+ * Check if the posted interrupt was previously
+ * setup with the guest_mode by checking if the ga_tag
+ * was cached. If so, we need to clean up the per-vcpu
+ * ir_list.
+ */
+ if (!ret && pi.prev_ga_tag) {
+ int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+ struct kvm_vcpu *vcpu;
+
+ vcpu = kvm_get_vcpu_by_id(kvm, id);
+ if (vcpu)
+ svm_ir_list_del(to_svm(vcpu), &pi);
+ }
+ }
+
+ if (!ret && svm) {
+ trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
+ host_irq, e->gsi,
+ vcpu_info.vector,
+ vcpu_info.pi_desc_addr, set);
+ }
+
+ if (ret < 0) {
+ pr_err("%s: failed to update PI IRTE\n", __func__);
+ goto out;
+ }
+ }
+
+ ret = 0;
+ out:
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return ret;
+ }
+
static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
avic_handle_ldr_update(vcpu);
}
-static struct kvm_x86_ops svm_x86_ops = {
+static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
.hardware_setup = svm_hardware_setup,
.pmu_ops = &amd_pmu_ops,
.deliver_posted_interrupt = svm_deliver_avic_intr,
+ .update_pi_irte = svm_update_pi_irte,
};
static int __init svm_init(void)
static struct vmcs_config {
int size;
int order;
+ u32 basic_cap;
u32 revision_id;
u32 pin_based_exec_ctrl;
u32 cpu_based_exec_ctrl;
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
+ static inline bool cpu_has_vmx_basic_inout(void)
+ {
+ return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT);
+ }
+
static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
{
return flexpriority_enabled && lapic_in_kernel(vcpu);
*pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS |
((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
(VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
+ if (cpu_has_vmx_basic_inout())
+ *pdata |= VMX_BASIC_INOUT;
break;
case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
case MSR_IA32_VMX_PINBASED_CTLS:
return -EIO;
vmcs_conf->size = vmx_msr_high & 0x1fff;
- vmcs_conf->order = get_order(vmcs_config.size);
+ vmcs_conf->order = get_order(vmcs_conf->size);
+ vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
vmcs_conf->revision_id = vmx_msr_low;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
gla_validity = (exit_qualification >> 7) & 0x3;
- if (gla_validity != 0x3 && gla_validity != 0x1 && gla_validity != 0) {
+ if (gla_validity == 0x2) {
printk(KERN_ERR "EPT: Handling EPT violation failed!\n");
printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
(long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
{
/* TODO: not to reset guest simply here. */
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
- pr_warn("kvm: nested vmx abort, indicator %d\n", indicator);
+ pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
}
static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer)
vmx->nested.vmcs02_num = 0;
hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL);
+ HRTIMER_MODE_REL_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
vmx->nested.vmxon = true;
maxphyaddr = cpuid_maxphyaddr(vcpu);
if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
(addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)",
addr_field, maxphyaddr, count, addr);
return -EINVAL;
for (i = 0; i < count; i++) {
if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
&e, sizeof(e))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
goto fail;
}
if (nested_vmx_load_msr_check(vcpu, &e)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s check failed (%u, 0x%x, 0x%x)\n",
__func__, i, e.index, e.reserved);
goto fail;
msr.index = e.index;
msr.data = e.value;
if (kvm_set_msr(vcpu, &msr)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
__func__, i, e.index, e.value);
goto fail;
if (kvm_vcpu_read_guest(vcpu,
gpa + i * sizeof(e),
&e, 2 * sizeof(u32))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR entry (%u, 0x%08llx)\n",
__func__, i, gpa + i * sizeof(e));
return -EINVAL;
}
if (nested_vmx_store_msr_check(vcpu, &e)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s check failed (%u, 0x%x, 0x%x)\n",
__func__, i, e.index, e.reserved);
return -EINVAL;
msr_info.host_initiated = false;
msr_info.index = e.index;
if (kvm_get_msr(vcpu, &msr_info)) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot read MSR (%u, 0x%x)\n",
__func__, i, e.index);
return -EINVAL;
gpa + i * sizeof(e) +
offsetof(struct vmx_msr_entry, value),
&msr_info.data, sizeof(msr_info.data))) {
- pr_warn_ratelimited(
+ pr_debug_ratelimited(
"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
__func__, i, e.index, msr_info.data);
return -EINVAL;
vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
}
+ if (nested_cpu_has_ept(vmcs12))
+ vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS);
+
if (nested_cpu_has_vid(vmcs12))
vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS);
~FEATURE_CONTROL_LMCE;
}
-static struct kvm_x86_ops vmx_x86_ops = {
+static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.hardware_setup = hardware_setup,