@@ -4111,6 +4111,25 @@ Valid values for 'action':
#define KVM_PMU_EVENT_ALLOW 0
#define KVM_PMU_EVENT_DENY 1
+4.121 KVM_PPC_SVM_OFF
+
+Capability: basic
+Architectures: powerpc
+Type: vm ioctl
+Parameters: none
+Returns: 0 on successful completion,
+Errors:
+ EINVAL: if ultravisor failed to terminate the secure guest
+ ENOMEM: if hypervisor failed to allocate new radix page tables for guest
+
+This ioctl is used to turn off the secure mode of the guest or transition
+the guest from secure mode to normal mode. This is invoked when the guest
+is reset. This has no effect if called for a normal guest.
+
+This ioctl issues an ultravisor call to terminate the secure guest,
+unpins the VPA pages, reinitializes guest's partition scoped page
+tables and releases all the device pages that are used to track the
+secure pages by hypervisor.
5. The kvm_run structure
------------------------
@@ -13,6 +13,7 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
unsigned long page_shift);
unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
+void kvmppc_devm_free_memslot_pfns(struct kvm *kvm, struct kvm_memslots *slots);
#else
static inline unsigned long
kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra,
@@ -37,5 +38,10 @@ static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
{
return H_UNSUPPORTED;
}
+
+static inline void kvmppc_devm_free_memslot_pfns(struct kvm *kvm,
+ struct kvm_memslots *slots)
+{
+}
#endif /* CONFIG_PPC_UV */
#endif /* __POWERPC_KVM_PPC_HMM_H__ */
@@ -177,6 +177,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm);
extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm);
extern void kvmppc_setup_partition_table(struct kvm *kvm);
+extern int kvmppc_reinit_partition_table(struct kvm *kvm);
extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
struct kvm_create_spapr_tce_64 *args);
@@ -321,6 +322,7 @@ struct kvmppc_ops {
int size);
int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
int size);
+ int (*svm_off)(struct kvm *kvm);
};
extern struct kvmppc_ops *kvmppc_hv_ops;
@@ -30,5 +30,6 @@
#define UV_PAGE_IN 0xF128
#define UV_PAGE_OUT 0xF12C
#define UV_PAGE_INVAL 0xF138
+#define UV_SVM_TERMINATE 0xF13C
#endif /* _ASM_POWERPC_ULTRAVISOR_API_H */
@@ -62,4 +62,9 @@ static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift)
return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift);
}
+static inline int uv_svm_terminate(u64 lpid)
+{
+ return ucall_norets(UV_SVM_TERMINATE, lpid);
+}
+
#endif /* _ASM_POWERPC_ULTRAVISOR_H */
@@ -2433,6 +2433,15 @@ static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
vpa->dirty);
}
+static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa)
+{
+ unpin_vpa(kvm, vpa);
+ vpa->gpa = 0;
+ vpa->pinned_addr = NULL;
+ vpa->dirty = false;
+ vpa->update_pending = 0;
+}
+
static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->arch.vpa_update_lock);
@@ -4576,6 +4585,22 @@ void kvmppc_setup_partition_table(struct kvm *kvm)
kvmhv_set_ptbl_entry(kvm->arch.lpid, dw0, dw1);
}
+/*
+ * Called from KVM_PPC_SVM_OFF ioctl at guest reset time when secure
+ * guest is converted back to normal guest.
+ */
+int kvmppc_reinit_partition_table(struct kvm *kvm)
+{
+ int ret;
+
+ ret = kvmppc_init_vm_radix(kvm);
+ if (ret)
+ return ret;
+
+ kvmppc_setup_partition_table(kvm);
+ return 0;
+}
+
/*
* Set up HPT (hashed page table) and RMA (real-mode area).
* Must be called with kvm->arch.mmu_setup_lock held.
@@ -4963,6 +4988,7 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
if (nesting_enabled(kvm))
kvmhv_release_all_nested(kvm);
kvm->arch.process_table = 0;
+ uv_svm_terminate(kvm->arch.lpid);
kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
}
kvmppc_free_lpid(kvm->arch.lpid);
@@ -5404,6 +5430,49 @@ static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
return rc;
}
+/*
+ * IOCTL handler to turn off secure mode of guest
+ *
+ * - Issue ucall to terminate the guest on the UV side
+ * - Unpin the VPA pages (Enables these pages to be migrated back
+ * when VM becomes secure again)
+ * - Recreate partition table as the guest is transitioning back to
+ * normal mode
+ * - Release all device pages
+ */
+static int kvmhv_svm_off(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int ret = 0;
+ int i;
+
+ if (kvmppc_is_guest_secure(kvm)) {
+ ret = uv_svm_terminate(kvm->arch.lpid);
+ if (ret != U_SUCCESS) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ spin_lock(&vcpu->arch.vpa_update_lock);
+ unpin_vpa_reset(kvm, &vcpu->arch.dtl);
+ unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow);
+ unpin_vpa_reset(kvm, &vcpu->arch.vpa);
+ spin_unlock(&vcpu->arch.vpa_update_lock);
+ }
+
+ ret = kvmppc_reinit_partition_table(kvm);
+ if (ret)
+ goto out;
+ kvm->arch.secure_guest = 0;
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
+ kvmppc_devm_free_memslot_pfns(kvm,
+ __kvm_memslots(kvm, i));
+ }
+out:
+ return ret;
+}
+
static struct kvmppc_ops kvm_ops_hv = {
.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -5446,6 +5515,7 @@ static struct kvmppc_ops kvm_ops_hv = {
.enable_nested = kvmhv_enable_nested,
.load_from_eaddr = kvmhv_load_from_eaddr,
.store_to_eaddr = kvmhv_store_to_eaddr,
+ .svm_off = kvmhv_svm_off,
};
static int kvm_init_subcore_bitmap(void)
@@ -37,6 +37,7 @@
#include <linux/migrate.h>
#include <linux/kvm_host.h>
#include <asm/ultravisor.h>
+#include <asm/kvm_ppc.h>
static struct dev_pagemap kvmppc_devm_pgmap;
static unsigned long *kvmppc_devm_pfn_bitmap;
@@ -85,9 +86,68 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
return H_UNSUPPORTED;
kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
+ if (kvm_is_radix(kvm)) {
+ pr_info("LPID %d went secure, freeing HV side radix pgtables\n",
+ kvm->arch.lpid);
+ kvmppc_free_radix(kvm);
+ }
+
return H_SUCCESS;
}
+/*
+ * Drop device pages that we maintain for the secure guest
+ *
+ * We first mark the pages to be skipped from UV_PAGE_OUT when there
+ * is HV side fault on these pages. Next we *get* these pages, forcing
+ * fault on them, do fault time migration to replace the device PTEs in
+ * QEMU page table with normal PTEs from newly allocated pages.
+ */
+static void kvmppc_devm_drop_pages(struct kvm_memory_slot *free,
+ struct kvm *kvm)
+{
+ int i;
+ struct kvmppc_devm_page_pvt *pvt;
+ unsigned long pfn;
+
+ for (i = 0; i < free->npages; i++) {
+ unsigned long *rmap = &free->arch.rmap[i];
+ struct page *devm_page;
+
+ if (kvmppc_rmap_is_devm_pfn(*rmap)) {
+ devm_page = pfn_to_page(*rmap & ~KVMPPC_RMAP_DEVM_PFN);
+ pvt = (struct kvmppc_devm_page_pvt *)
+ devm_page->zone_device_data;
+ pvt->skip_page_out = true;
+
+ pfn = gfn_to_pfn(kvm, pvt->gpa >> PAGE_SHIFT);
+ if (is_error_noslot_pfn(pfn))
+ continue;
+ kvm_release_pfn_clean(pfn);
+ }
+ }
+}
+
+/*
+ * Called from KVM_PPC_SVM_OFF ioctl when secure guest is reset
+ *
+ * UV has already cleaned up the guest, we release any device pages
+ * that we maintain
+ */
+void kvmppc_devm_free_memslot_pfns(struct kvm *kvm, struct kvm_memslots *slots)
+{
+ struct kvm_memory_slot *memslot;
+ int srcu_idx;
+
+ if (!slots)
+ return;
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+ kvm_for_each_memslot(memslot, slots)
+ kvmppc_devm_drop_pages(memslot, kvm);
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
/*
* Get a free device PFN from the pool
*
@@ -31,6 +31,8 @@
#include <asm/hvcall.h>
#include <asm/plpar_wrappers.h>
#endif
+#include <asm/ultravisor.h>
+#include <asm/kvm_host.h>
#include "timing.h"
#include "irq.h"
@@ -2415,6 +2417,16 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
break;
}
+ case KVM_PPC_SVM_OFF: {
+ struct kvm *kvm = filp->private_data;
+
+ r = 0;
+ if (!kvm->arch.kvm_ops->svm_off)
+ goto out;
+
+ r = kvm->arch.kvm_ops->svm_off(kvm);
+ break;
+ }
default: {
struct kvm *kvm = filp->private_data;
r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);
@@ -1332,6 +1332,7 @@ struct kvm_s390_ucas_mapping {
#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
/* Available with KVM_CAP_PMU_EVENT_FILTER */
#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3)
/* ioctl for vm fd */
#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)