1 files changed, 64 insertions, 86 deletions

diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 0f89157d31fd..fcd70bfe44fb 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -5,12 +5,12 @@
  */
 
 #include <linux/init.h>
+#include <linux/interval_tree_generic.h>
 #include <linux/kmemleak.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_mmu.h>
 #include <linux/memblock.h>
 #include <linux/mutex.h>
-#include <linux/sort.h>
 
 #include <asm/kvm_pkvm.h>
 
@@ -24,23 +24,6 @@ static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr);
 phys_addr_t hyp_mem_base;
 phys_addr_t hyp_mem_size;
 
-static int cmp_hyp_memblock(const void *p1, const void *p2)
-{
-	const struct memblock_region *r1 = p1;
-	const struct memblock_region *r2 = p2;
-
-	return r1->base < r2->base ? -1 : (r1->base > r2->base);
-}
-
-static void __init sort_memblock_regions(void)
-{
-	sort(hyp_memory,
-	     *hyp_memblock_nr_ptr,
-	     sizeof(struct memblock_region),
-	     cmp_hyp_memblock,
-	     NULL);
-}
-
 static int __init register_memblock_regions(void)
 {
 	struct memblock_region *reg;
@@ -52,7 +35,6 @@ static int __init register_memblock_regions(void)
 		hyp_memory[*hyp_memblock_nr_ptr] = *reg;
 		(*hyp_memblock_nr_ptr)++;
 	}
-	sort_memblock_regions();
 
 	return 0;
 }
@@ -79,6 +61,7 @@ void __init kvm_hyp_reserve(void)
 	hyp_mem_pages += host_s2_pgtable_pages();
 	hyp_mem_pages += hyp_vm_table_pages();
 	hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE);
+	hyp_mem_pages += pkvm_selftest_pages();
 	hyp_mem_pages += hyp_ffa_proxy_pages();
 
 	/*
@@ -262,6 +245,7 @@ static int __init finalize_pkvm(void)
 	 * at, which would end badly once inaccessible.
 	 */
 	kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
+	kmemleak_free_part(__hyp_data_start, __hyp_data_end - __hyp_data_start);
 	kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start);
 	kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);
 
@@ -273,80 +257,68 @@ static int __init finalize_pkvm(void)
 }
 device_initcall_sync(finalize_pkvm);
 
-static int cmp_mappings(struct rb_node *node, const struct rb_node *parent)
+static u64 __pkvm_mapping_start(struct pkvm_mapping *m)
 {
-	struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node);
-	struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node);
-
-	if (a->gfn < b->gfn)
-		return -1;
-	if (a->gfn > b->gfn)
-		return 1;
-	return 0;
+	return m->gfn * PAGE_SIZE;
 }
 
-static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn)
+static u64 __pkvm_mapping_end(struct pkvm_mapping *m)
 {
-	struct rb_node *node = root->rb_node, *prev = NULL;
-	struct pkvm_mapping *mapping;
-
-	while (node) {
-		mapping = rb_entry(node, struct pkvm_mapping, node);
-		if (mapping->gfn == gfn)
-			return node;
-		prev = node;
-		node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right;
-	}
-
-	return prev;
+	return (m->gfn + m->nr_pages) * PAGE_SIZE - 1;
 }
 
+INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last,
+		     __pkvm_mapping_start, __pkvm_mapping_end, static,
+		     pkvm_mapping);
+
 /*
- * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing
- * of __map inline.
+ * __tmp is updated to iter_first(pkvm_mappings) *before* entering the body of the loop to allow
+ * freeing of __map inline.
  */
 #define for_each_mapping_in_range_safe(__pgt, __start, __end, __map)				\
-	for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings,		\
-							     ((__start) >> PAGE_SHIFT));	\
+	for (struct pkvm_mapping *__tmp = pkvm_mapping_iter_first(&(__pgt)->pkvm_mappings,	\
+								  __start, __end - 1);		\
 	     __tmp && ({									\
-				__map = rb_entry(__tmp, struct pkvm_mapping, node);		\
-				__tmp = rb_next(__tmp);						\
+				__map = __tmp;							\
+				__tmp = pkvm_mapping_iter_next(__map, __start, __end - 1);	\
 				true;								\
 		       });									\
-	    )											\
-		if (__map->gfn < ((__start) >> PAGE_SHIFT))					\
-			continue;								\
-		else if (__map->gfn >= ((__end) >> PAGE_SHIFT))					\
-			break;									\
-		else
+	    )
 
 int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			     struct kvm_pgtable_mm_ops *mm_ops)
 {
-	pgt->pkvm_mappings	= RB_ROOT;
+	pgt->pkvm_mappings	= RB_ROOT_CACHED;
 	pgt->mmu		= mmu;
 
 	return 0;
 }
 
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 end)
 {
 	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
 	pkvm_handle_t handle = kvm->arch.pkvm.handle;
 	struct pkvm_mapping *mapping;
-	struct rb_node *node;
+	int ret;
 
 	if (!handle)
-		return;
+		return 0;
 
-	node = rb_first(&pgt->pkvm_mappings);
-	while (node) {
-		mapping = rb_entry(node, struct pkvm_mapping, node);
-		kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
-		node = rb_next(node);
-		rb_erase(&mapping->node, &pgt->pkvm_mappings);
+	for_each_mapping_in_range_safe(pgt, start, end, mapping) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
+					mapping->nr_pages);
+		if (WARN_ON(ret))
+			return ret;
+		pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
 		kfree(mapping);
 	}
+
+	return 0;
+}
+
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	__pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL));
 }
 
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
@@ -360,42 +332,46 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	u64 pfn = phys >> PAGE_SHIFT;
 	int ret;
 
-	if (size != PAGE_SIZE)
+	if (size != PAGE_SIZE && size != PMD_SIZE)
 		return -EINVAL;
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
-	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot);
-	if (ret) {
-		/* Is the gfn already mapped due to a racing vCPU? */
-		if (ret == -EPERM)
+
+	/*
+	 * Calling stage2_map() on top of existing mappings is either happening because of a race
+	 * with another vCPU, or because we're changing between page and block mappings. As per
+	 * user_mem_abort(), same-size permission faults are handled in the relax_perms() path.
+	 */
+	mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, addr + size - 1);
+	if (mapping) {
+		if (size == (mapping->nr_pages * PAGE_SIZE))
 			return -EAGAIN;
+
+		/* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */
+		ret = __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+		if (ret)
+			return ret;
+		mapping = NULL;
 	}
 
+	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, size / PAGE_SIZE, prot);
+	if (WARN_ON(ret))
+		return ret;
+
 	swap(mapping, cache->mapping);
 	mapping->gfn = gfn;
 	mapping->pfn = pfn;
-	WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings));
+	mapping->nr_pages = size / PAGE_SIZE;
+	pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
 
 	return ret;
 }
 
 int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
-	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
-	pkvm_handle_t handle = kvm->arch.pkvm.handle;
-	struct pkvm_mapping *mapping;
-	int ret = 0;
-
-	lockdep_assert_held_write(&kvm->mmu_lock);
-	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
-		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
-		if (WARN_ON(ret))
-			break;
-		rb_erase(&mapping->node, &pgt->pkvm_mappings);
-		kfree(mapping);
-	}
+	lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(pgt->mmu)->mmu_lock);
 
-	return ret;
+	return __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
 }
 
 int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
@@ -407,7 +383,8 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
-		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn);
+		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
+					mapping->nr_pages);
 		if (WARN_ON(ret))
 			break;
 	}
@@ -422,7 +399,8 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
 
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
-		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE);
+		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
+					  PAGE_SIZE * mapping->nr_pages);
 
 	return 0;
 }
@@ -437,7 +415,7 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
 	lockdep_assert_held(&kvm->mmu_lock);
 	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
 		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
-					   mkold);
+					   mapping->nr_pages, mkold);
 
 	return young;
 }