[PATCH v15 10/37] KVM: arm64: CCA: Tear down RTTs

[Steven Price <steven.price@arm.com>]

The RMM owns the stage 2 page tables for a realm, and KVM must request
that the RMM creates/destroys entries as necessary. The physical pages
to store the page tables are delegated to the realm as required, and can
be undelegated when no longer used.

Creating new RTTs is the easy part, tearing down is a little more
tricky. The result of realm_rtt_destroy() can be used to effectively
walk the tree and destroy the entries (undelegating pages that were
given to the realm).

Signed-off-by: Steven Price <steven.price@arm.com>
---
Changes since v14:
 * Teardown is now serialized under config_lock and idempotent.
Changes since v13:
 * Avoid the double call of kvm_free_stage2_pgd() by splitting the work
   across that and a new function kvm_realm_uninit_stage2() which is
   only called for realm guests.
Changes since v12:
 * Simplify some functions now we know RMM page size is the same as the
   host's.
Changes since v11:
 * Moved some code from earlier in the series to this one so that it's
   added when it's first used.
Changes since v10:
 * RME->RMI rename.
 * Some code to handle freeing stage 2 PGD moved into this patch where
   it belongs.
Changes since v9:
 * Add a comment clarifying that root level RTTs are not destroyed until
   after the RD is destroyed.
Changes since v8:
 * Introduce free_rtt() wrapper which calls free_delegated_granule()
   followed by kvm_account_pgtable_pages(). This makes it clear where an
   RTT is being freed rather than just a delegated granule.
Changes since v6:
 * Move rme_rtt_level_mapsize() and supporting defines from kvm_rme.h
   into rme.c as they are only used in that file.
Changes since v5:
 * Rename some RME_xxx defines to do with page sizes as RMM_xxx - they are
   a property of the RMM specification not the RME architecture.
Changes since v2:
 * Moved {alloc,free}_delegated_page() and ensure_spare_page() to a
   later patch when they are actually used.
 * Some simplifications now rmi_xxx() functions allow NULL as an output
   parameter.
 * Improved comments and code layout.
---
 arch/arm64/include/asm/kvm_rmi.h |  11 ++
 arch/arm64/kvm/mmu.c             |  17 ++-
 arch/arm64/kvm/rmi.c             | 196 +++++++++++++++++++++++++++++++
 3 files changed, 223 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_rmi.h b/arch/arm64/include/asm/kvm_rmi.h
index 5c40616aa1a1..31ec856561c6 100644
--- a/arch/arm64/include/asm/kvm_rmi.h
+++ b/arch/arm64/include/asm/kvm_rmi.h
@@ -57,6 +57,8 @@ enum realm_state {
  * @sro: Preallocated SRO state context for Realm MMU operations
  * @state: The lifetime state machine for the realm
  * @ia_bits: Number of valid Input Address bits in the IPA
+ * @stage2_unmapped: The Realm stage-2 mappings have been removed
+ * @rtts_destroyed: The non-root RTTs have been torn down
  */
 struct realm {
 	void *rd;
@@ -71,6 +73,8 @@ struct realm {
 	struct rmi_sro_state *sro;
 	enum realm_state state;
 	unsigned int ia_bits;
+	bool stage2_unmapped;
+	bool rtts_destroyed;
 };
 
 void kvm_init_rmi(void);
@@ -78,5 +82,12 @@ u32 kvm_rmm_ipa_limit(void);
 
 int kvm_init_realm(struct kvm *kvm);
 void kvm_destroy_realm(struct kvm *kvm);
+int kvm_realm_teardown_stage2(struct kvm *kvm);
+
+static inline bool kvm_realm_is_private_address(struct realm *realm,
+						unsigned long addr)
+{
+	return !(addr & BIT(realm->ia_bits - 1));
+}
 
 #endif /* __ASM_KVM_RMI_H */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 8b9efa8a3539..cd06881c1497 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1060,9 +1060,24 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return err;
 }
 
+static void kvm_realm_uninit_stage2(struct kvm_s2_mmu *mmu)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu);
+
+	mutex_lock(&kvm->arch.config_lock);
+	if (kvm_realm_state(kvm) == REALM_STATE_ACTIVE) {
+		kvm_set_realm_state(kvm, REALM_STATE_DYING);
+		WARN_ON(kvm_realm_teardown_stage2(kvm));
+	}
+	mutex_unlock(&kvm->arch.config_lock);
+}
+
 void kvm_uninit_stage2_mmu(struct kvm *kvm)
 {
-	kvm_free_stage2_pgd(&kvm->arch.mmu);
+	if (kvm_is_realm(kvm))
+		kvm_realm_uninit_stage2(&kvm->arch.mmu);
+	else
+		kvm_free_stage2_pgd(&kvm->arch.mmu);
 	kvm_mmu_free_memory_cache(&kvm->arch.mmu.split_page_cache);
 }
 
diff --git a/arch/arm64/kvm/rmi.c b/arch/arm64/kvm/rmi.c
index b81c404ead9f..db32448a0fc1 100644
--- a/arch/arm64/kvm/rmi.c
+++ b/arch/arm64/kvm/rmi.c
@@ -11,6 +11,14 @@
 #include <asm/rmi_cmds.h>
 #include <asm/virt.h>
 
+static inline unsigned long rmi_rtt_level_mapsize(int level)
+{
+	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
+		return PAGE_SIZE;
+
+	return (1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
+}
+
 static bool rmi_has_feature(int reg, unsigned long feature)
 {
 	return !!u64_get_bits(rmi_feat_reg(reg), feature);
@@ -21,11 +29,187 @@ u32 kvm_rmm_ipa_limit(void)
 	return u64_get_bits(rmi_feat_reg(0), RMI_FEATURE_REGISTER_0_S2SZ);
 }
 
+static int get_start_level(struct realm *realm)
+{
+	return 4 - stage2_pgtable_levels(realm->ia_bits);
+}
+
+static void free_rtt(phys_addr_t phys)
+{
+	if (free_delegated_page(phys))
+		return;
+
+	kvm_account_pgtable_pages(phys_to_virt(phys), -1);
+}
+
+/*
+ * realm_rtt_destroy - Destroy an RTT at @level for @addr.
+ *
+ * Returns - Result of the RMI_RTT_DESTROY call, and:
+ * @rtt_granule:	RTT granule, if the RTT was destroyed.
+ * @next_addr:		IPA corresponding to the next possible valid entry we
+ *			can target
+ */
+static int realm_rtt_destroy(struct realm *realm, unsigned long addr,
+			     int level, phys_addr_t *rtt_granule,
+			     unsigned long *next_addr)
+{
+	unsigned long out_rtt;
+	int ret;
+
+	ret = rmi_rtt_destroy(virt_to_phys(realm->rd), addr, level,
+			      &out_rtt, next_addr);
+
+	*rtt_granule = out_rtt;
+
+	return ret;
+}
+
+static int realm_tear_down_rtt_level(struct realm *realm, int level,
+				     unsigned long start, unsigned long end)
+{
+	ssize_t map_size;
+	unsigned long addr, next_addr;
+
+	if (WARN_ON(level > KVM_PGTABLE_LAST_LEVEL))
+		return -EINVAL;
+
+	map_size = rmi_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);
+
+		if (next_addr > end || align_addr != addr) {
+			/*
+			 * The target range is smaller than what this level
+			 * covers, recurse deeper.
+			 */
+			ret = realm_tear_down_rtt_level(realm,
+							level + 1,
+							addr,
+							min(next_addr, end));
+			if (ret)
+				return ret;
+			continue;
+		}
+
+		ret = realm_rtt_destroy(realm, addr, level,
+					&rtt_granule, &next_addr);
+
+		switch (RMI_RETURN_STATUS(ret)) {
+		case RMI_SUCCESS:
+			free_rtt(rtt_granule);
+			break;
+		case RMI_ERROR_RTT:
+			if (next_addr > addr) {
+				/* Missing RTT, skip */
+				break;
+			}
+			/*
+			 * We tear down the RTT range for the full IPA
+			 * space, after everything is unmapped. Also we
+			 * descend down only if we cannot tear down a
+			 * top level RTT. Thus RMM must be able to walk
+			 * to the requested level. e.g., a block mapping
+			 * exists at L1 or L2.
+			 */
+			if (WARN_ON(RMI_RETURN_INDEX(ret) != level))
+				return -EBUSY;
+			if (WARN_ON(level == KVM_PGTABLE_LAST_LEVEL))
+				return -EBUSY;
+
+			/*
+			 * The table has active entries in it, recurse deeper
+			 * and tear down the RTTs.
+			 */
+			next_addr = ALIGN(addr + 1, map_size);
+			ret = realm_tear_down_rtt_level(realm,
+							level + 1,
+							addr,
+							next_addr);
+			if (ret)
+				return ret;
+			/*
+			 * Now that the child RTTs are destroyed,
+			 * retry at this level.
+			 */
+			next_addr = addr;
+			break;
+		default:
+			WARN_ON(1);
+			return -ENXIO;
+		}
+	}
+
+	return 0;
+}
+
+static int realm_tear_down_rtt_range(struct realm *realm,
+				     unsigned long start, unsigned long end)
+{
+	/*
+	 * Root level RTTs can only be destroyed after the RD is destroyed. So
+	 * tear down everything below the root level
+	 */
+	return realm_tear_down_rtt_level(realm, get_start_level(realm) + 1,
+					 start, end);
+}
+
+static int realm_destroy_rtts(struct kvm *kvm)
+{
+	struct realm *realm = &kvm->arch.realm;
+	unsigned int ia_bits = realm->ia_bits;
+	int ret;
+
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	if (realm->rtts_destroyed)
+		return 0;
+
+	ret = realm_tear_down_rtt_range(realm, 0, (1UL << ia_bits));
+	if (ret)
+		return ret;
+
+	realm->rtts_destroyed = true;
+	return 0;
+}
+
+static void realm_unmap_stage2(struct kvm *kvm)
+{
+	struct realm *realm = &kvm->arch.realm;
+
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	if (realm->stage2_unmapped)
+		return;
+
+	write_lock(&kvm->mmu_lock);
+	kvm_stage2_unmap_range(&kvm->arch.mmu, 0,
+			       BIT(realm->ia_bits - 1), true);
+	write_unlock(&kvm->mmu_lock);
+
+	realm->stage2_unmapped = true;
+}
+
+int kvm_realm_teardown_stage2(struct kvm *kvm)
+{
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	realm_unmap_stage2(kvm);
+	return realm_destroy_rtts(kvm);
+}
+
 void kvm_destroy_realm(struct kvm *kvm)
 {
 	struct realm *realm = &kvm->arch.realm;
 	size_t pgd_size = kvm_pgtable_stage2_pgd_size(kvm->arch.mmu.vtcr);
 
+	guard(mutex)(&kvm->arch.config_lock);
+
 	if (realm->params) {
 		free_page((unsigned long)realm->params);
 		realm->params = NULL;
@@ -39,12 +223,24 @@ void kvm_destroy_realm(struct kvm *kvm)
 
 	kvm_set_realm_state(kvm, REALM_STATE_DYING);
 
+	/*
+	 * REALM_DESTROY requires the realm to be non-live: all RECs must have
+	 * been destroyed and the root RTTs must be empty. Unmap the IPA space
+	 * and destroy any non-root RTTs before tearing down the RD. The root
+	 * RTT pages are still owned by the RMM at this point, so keep the KVM
+	 * pgtable alive until after REALM_DESTROY and undelegation.
+	 */
+	realm_unmap_stage2(kvm);
+
 	if (realm->rd) {
 		phys_addr_t rd_phys = virt_to_phys(realm->rd);
 
 		if (WARN_ON(rmi_realm_terminate(rd_phys, realm->sro)))
 			return;
 
+		if (WARN_ON(realm_destroy_rtts(kvm)))
+			return;
+
 		if (WARN_ON(rmi_realm_destroy(rd_phys, realm->sro)))
 			return;
 		free_delegated_page(rd_phys);
-- 
2.43.0