diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 325b578c734d..b100d4b3aa29 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -310,6 +310,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
* @start: The intermediate physical base address of the range to unmap
* @size: The size of the area to unmap
* @may_block: Whether or not we are permitted to block
+ * @only_shared: If true then protected mappings should not be unmapped
*
* Clear a range of stage-2 mappings, lowering the various ref-counts. Must
* be called while holding mmu_lock (unless for freeing the stage2 pgd before
@@ -317,7 +318,7 @@ static void invalidate_icache_guest_page(void *va, size_t size)
* with things behind our backs.
*/
static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size,
- bool may_block)
+ bool may_block, bool only_shared)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
phys_addr_t end = start + size;
@@ -331,7 +332,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
u64 size, bool may_block)
{
- __unmap_stage2_range(mmu, start, size, may_block);
+ __unmap_stage2_range(mmu, start, size, may_block, false);
}
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1932,7 +1933,8 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
__unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT,
(range->end - range->start) << PAGE_SHIFT,
- range->may_block);
+ range->may_block,
+ range->only_shared);
kvm_nested_s2_unmap(kvm, range->may_block);
return false;
diff --git a/arch/arm64/kvm/rme.c b/arch/arm64/kvm/rme.c
index 72778d8ab52b..e8ad04405ecd 100644
--- a/arch/arm64/kvm/rme.c
+++ b/arch/arm64/kvm/rme.c
@@ -62,6 +62,51 @@ static int get_start_level(struct realm *realm)
return 4 - stage2_pgtable_levels(realm->ia_bits);
}
+static int find_map_level(struct realm *realm,
+ unsigned long start,
+ unsigned long end)
+{
+ int level = RMM_RTT_MAX_LEVEL;
+
+ while (level > get_start_level(realm)) {
+ unsigned long map_size = rme_rtt_level_mapsize(level - 1);
+
+ if (!IS_ALIGNED(start, map_size) ||
+ (start + map_size) > end)
+ break;
+
+ level--;
+ }
+
+ return level;
+}
+
+static phys_addr_t alloc_delegated_granule(struct kvm_mmu_memory_cache *mc,
+ gfp_t flags)
+{
+ phys_addr_t phys = PHYS_ADDR_MAX;
+ void *virt;
+
+ if (mc)
+ virt = kvm_mmu_memory_cache_alloc(mc);
+ else
+ virt = (void *)__get_free_page(flags);
+
+ if (!virt)
+ goto out;
+
+ phys = virt_to_phys(virt);
+
+ if (rmi_granule_delegate(phys)) {
+ free_page((unsigned long)virt);
+
+ phys = PHYS_ADDR_MAX;
+ }
+
+out:
+ return phys;
+}
+
static void free_delegated_granule(phys_addr_t phys)
{
if (WARN_ON(rmi_granule_undelegate(phys))) {
@@ -72,6 +117,132 @@ static void free_delegated_granule(phys_addr_t phys)
free_page((unsigned long)phys_to_virt(phys));
}
+static int realm_rtt_create(struct realm *realm,
+ unsigned long addr,
+ int level,
+ phys_addr_t phys)
+{
+ addr = ALIGN_DOWN(addr, rme_rtt_level_mapsize(level - 1));
+ return rmi_rtt_create(virt_to_phys(realm->rd), phys, addr, level);
+}
+
+static int realm_rtt_fold(struct realm *realm,
+ unsigned long addr,
+ int level,
+ phys_addr_t *rtt_granule)
+{
+ unsigned long out_rtt;
+ int ret;
+
+ ret = rmi_rtt_fold(virt_to_phys(realm->rd), addr, level, &out_rtt);
+
+ if (RMI_RETURN_STATUS(ret) == RMI_SUCCESS && rtt_granule)
+ *rtt_granule = out_rtt;
+
+ return ret;
+}
+
+static int realm_destroy_protected(struct realm *realm,
+ unsigned long ipa,
+ unsigned long *next_addr)
+{
+ unsigned long rd = virt_to_phys(realm->rd);
+ unsigned long addr;
+ phys_addr_t rtt;
+ int ret;
+
+loop:
+ ret = rmi_data_destroy(rd, ipa, &addr, next_addr);
+ if (RMI_RETURN_STATUS(ret) == RMI_ERROR_RTT) {
+ if (*next_addr > ipa)
+ return 0; /* UNASSIGNED */
+ rtt = alloc_delegated_granule(NULL, GFP_KERNEL);
+ if (WARN_ON(rtt == PHYS_ADDR_MAX))
+ return -1;
+ /*
+ * ASSIGNED - ipa is mapped as a block, so split. The index
+ * from the return code should be 2 otherwise it appears
+ * there's a huge page bigger than KVM currently supports
+ */
+ WARN_ON(RMI_RETURN_INDEX(ret) != 2);
+ ret = realm_rtt_create(realm, ipa, 3, rtt);
+ if (WARN_ON(ret)) {
+ free_delegated_granule(rtt);
+ return -1;
+ }
+ /* retry */
+ goto loop;
+ } else if (WARN_ON(ret)) {
+ return -1;
+ }
+ ret = rmi_granule_undelegate(addr);
+
+ /*
+ * If the undelegate fails then something has gone seriously
+ * wrong: take an extra reference to just leak the page
+ */
+ if (!WARN_ON(ret))
+ put_page(phys_to_page(addr));
+
+ return 0;
+}
+
+static void realm_unmap_shared_range(struct kvm *kvm,
+ int level,
+ unsigned long start,
+ unsigned long end)
+{
+ struct realm *realm = &kvm->arch.realm;
+ unsigned long rd = virt_to_phys(realm->rd);
+ ssize_t map_size = rme_rtt_level_mapsize(level);
+ unsigned long next_addr, addr;
+ unsigned long shared_bit = BIT(realm->ia_bits - 1);
+
+ if (WARN_ON(level > RMM_RTT_MAX_LEVEL))
+ return;
+
+ start |= shared_bit;
+ end |= shared_bit;
+
+ for (addr = start; addr < end; addr = next_addr) {
+ unsigned long align_addr = ALIGN(addr, map_size);
+ int ret;
+
+ next_addr = ALIGN(addr + 1, map_size);
+
+ if (align_addr != addr || next_addr > end) {
+ /* Need to recurse deeper */
+ if (addr < align_addr)
+ next_addr = align_addr;
+ realm_unmap_shared_range(kvm, level + 1, addr,
+ min(next_addr, end));
+ continue;
+ }
+
+ ret = rmi_rtt_unmap_unprotected(rd, addr, level, &next_addr);
+ switch (RMI_RETURN_STATUS(ret)) {
+ case RMI_SUCCESS:
+ break;
+ case RMI_ERROR_RTT:
+ if (next_addr == addr) {
+ /*
+ * There's a mapping here, but it's not a block
+ * mapping, so reset next_addr to the next block
+ * boundary and recurse to clear out the pages
+ * one level deeper.
+ */
+ next_addr = ALIGN(addr + 1, map_size);
+ realm_unmap_shared_range(kvm, level + 1, addr,
+ next_addr);
+ }
+ break;
+ default:
+ WARN_ON(1);
+ return;
+ }
+ }
+}
+
static int realm_create_rd(struct kvm *kvm)
{
struct realm *realm = &kvm->arch.realm;
@@ -161,6 +332,30 @@ static int realm_rtt_destroy(struct realm *realm, unsigned long addr,
return ret;
}
+static int realm_create_rtt_levels(struct realm *realm,
+ unsigned long ipa,
+ int level,
+ int max_level,
+ struct kvm_mmu_memory_cache *mc)
+{
+ if (WARN_ON(level == max_level))
+ return 0;
+
+ while (level++ < max_level) {
+ phys_addr_t rtt = alloc_delegated_granule(mc, GFP_KERNEL);
+
+ if (rtt == PHYS_ADDR_MAX)
+ return -ENOMEM;
+
+ if (realm_rtt_create(realm, ipa, level, rtt)) {
+ free_delegated_granule(rtt);
+ return -ENXIO;
+ }
+ }
+
+ return 0;
+}
+
static int realm_tear_down_rtt_level(struct realm *realm, int level,
unsigned long start, unsigned long end)
{
@@ -251,6 +446,61 @@ static int realm_tear_down_rtt_range(struct realm *realm,
start, end);
}
+/*
+ * Returns 0 on successful fold, a negative value on error, a positive value if
+ * we were not able to fold all tables at this level.
+ */
+static int realm_fold_rtt_level(struct realm *realm, int level,
+ unsigned long start, unsigned long end)
+{
+ int not_folded = 0;
+ ssize_t map_size;
+ unsigned long addr, next_addr;
+
+ if (WARN_ON(level > RMM_RTT_MAX_LEVEL))
+ return -EINVAL;
+
+ map_size = rme_rtt_level_mapsize(level - 1);
+
+ for (addr = start; addr < end; addr = next_addr) {
+ phys_addr_t rtt_granule;
+ int ret;
+ unsigned long align_addr = ALIGN(addr, map_size);
+
+ next_addr = ALIGN(addr + 1, map_size);
+
+ ret = realm_rtt_fold(realm, align_addr, level, &rtt_granule);
+
+ switch (RMI_RETURN_STATUS(ret)) {
+ case RMI_SUCCESS:
+ free_delegated_granule(rtt_granule);
+ break;
+ case RMI_ERROR_RTT:
+ if (level == RMM_RTT_MAX_LEVEL ||
+ RMI_RETURN_INDEX(ret) < level) {
+ not_folded++;
+ break;
+ }
+ /* Recurse a level deeper */
+ ret = realm_fold_rtt_level(realm,
+ level + 1,
+ addr,
+ next_addr);
+ if (ret < 0)
+ return ret;
+ else if (ret == 0)
+ /* Try again at this level */
+ next_addr = addr;
+ break;
+ default:
+ WARN_ON(1);
+ return -ENXIO;
+ }
+ }
+
+ return not_folded;
+}
+
void kvm_realm_destroy_rtts(struct kvm *kvm, u32 ia_bits)
{
struct realm *realm = &kvm->arch.realm;
@@ -258,6 +508,155 @@ void kvm_realm_destroy_rtts(struct kvm *kvm, u32 ia_bits)
WARN_ON(realm_tear_down_rtt_range(realm, 0, (1UL << ia_bits)));
}
+static void realm_unmap_private_range(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct realm *realm = &kvm->arch.realm;
+ unsigned long next_addr, addr;
+
+ for (addr = start; addr < end; addr = next_addr) {
+ int ret;
+
+ ret = realm_destroy_protected(realm, addr, &next_addr);
+
+ if (WARN_ON(ret))
+ break;
+ }
+
+ realm_fold_rtt_level(realm, get_start_level(realm) + 1,
+ start, end);
+}
+
+void kvm_realm_unmap_range(struct kvm *kvm, unsigned long start, u64 size,
+ bool unmap_private)
+{
+ unsigned long end = start + size;
+ struct realm *realm = &kvm->arch.realm;
+
+ end = min(BIT(realm->ia_bits - 1), end);
+
+ if (realm->state == REALM_STATE_NONE)
+ return;
+
+ realm_unmap_shared_range(kvm, find_map_level(realm, start, end),
+ start, end);
+ if (unmap_private)
+ realm_unmap_private_range(kvm, start, end);
+}
+
+int realm_set_ipa_state(struct kvm_vcpu *vcpu,
+ unsigned long start,
+ unsigned long end,
+ unsigned long ripas,
+ unsigned long *top_ipa)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct realm *realm = &kvm->arch.realm;
+ struct realm_rec *rec = &vcpu->arch.rec;
+ phys_addr_t rd_phys = virt_to_phys(realm->rd);
+ phys_addr_t rec_phys = virt_to_phys(rec->rec_page);
+ struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+ unsigned long ipa = start;
+ int ret = 0;
+
+ while (ipa < end) {
+ unsigned long next;
+
+ ret = rmi_rtt_set_ripas(rd_phys, rec_phys, ipa, end, &next);
+
+ if (RMI_RETURN_STATUS(ret) == RMI_ERROR_RTT) {
+ int walk_level = RMI_RETURN_INDEX(ret);
+ int level = find_map_level(realm, ipa, end);
+
+ /*
+ * If the RMM walk ended early then more tables are
+ * needed to reach the required depth to set the RIPAS.
+ */
+ if (walk_level < level) {
+ ret = realm_create_rtt_levels(realm, ipa,
+ walk_level,
+ level,
+ memcache);
+ /* Retry with RTTs created */
+ if (!ret)
+ continue;
+ } else {
+ ret = -EINVAL;
+ }
+
+ break;
+ } else if (RMI_RETURN_STATUS(ret) != RMI_SUCCESS) {
+ WARN(1, "Unexpected error in %s: %#x\n", __func__,
+ ret);
+ ret = -EINVAL;
+ break;
+ }
+ ipa = next;
+ }
+
+ *top_ipa = ipa;
+
+ if (ripas == RMI_EMPTY && ipa != start)
+ realm_unmap_private_range(kvm, start, ipa);
+
+ return ret;
+}
+
+static int realm_init_ipa_state(struct realm *realm,
+ unsigned long ipa,
+ unsigned long end)
+{
+ phys_addr_t rd_phys = virt_to_phys(realm->rd);
+ int ret;
+
+ while (ipa < end) {
+ unsigned long next;
+
+ ret = rmi_rtt_init_ripas(rd_phys, ipa, end, &next);
+
+ if (RMI_RETURN_STATUS(ret) == RMI_ERROR_RTT) {
+ int err_level = RMI_RETURN_INDEX(ret);
+ int level = find_map_level(realm, ipa, end);
+
+ if (WARN_ON(err_level >= level))
+ return -ENXIO;
+
+ ret = realm_create_rtt_levels(realm, ipa,
+ err_level,
+ level, NULL);
+ if (ret)
+ return ret;
+ /* Retry with the RTT levels in place */
+ continue;
+ } else if (WARN_ON(ret)) {
+ return -ENXIO;
+ }
+
+ ipa = next;
+ }
+
+ return 0;
+}
+
+static int kvm_init_ipa_range_realm(struct kvm *kvm,
+ struct kvm_cap_arm_rme_init_ipa_args *args)
+{
+ gpa_t addr, end;
+ struct realm *realm = &kvm->arch.realm;
+
+ addr = args->init_ipa_base;
+ end = addr + args->init_ipa_size;
+
+ if (end < addr)
+ return -EINVAL;
+
+ if (kvm_realm_state(kvm) != REALM_STATE_NEW)
+ return -EINVAL;
+
+ return realm_init_ipa_state(realm, addr, end);
+}
+
/* Protects access to rme_vmid_bitmap */
static DEFINE_SPINLOCK(rme_vmid_lock);
static unsigned long *rme_vmid_bitmap;
@@ -383,6 +782,18 @@ int kvm_realm_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
case KVM_CAP_ARM_RME_CREATE_RD:
r = kvm_create_realm(kvm);
break;
+ case KVM_CAP_ARM_RME_INIT_IPA_REALM: {
+ struct kvm_cap_arm_rme_init_ipa_args args;
+ void __user *argp = u64_to_user_ptr(cap->args[1]);
+
+ if (copy_from_user(&args, argp, sizeof(args))) {
+ r = -EFAULT;
+ break;
+ }
+
+ r = kvm_init_ipa_range_realm(kvm, &args);
+ break;
+ }
default:
r = -EINVAL;
break;
