[RFC,v1,07/26] KVM: arm64: Turn llist of pinned pages into an rb-tree

Commit Message

Fuad Tabba Feb. 22, 2024, 4:10 p.m. UTC

From: Quentin Perret <[e-mail]>

Indexed by IPA, so we can efficiently lookup.

Signed-off-by: Quentin Perret <[e-mail]>
Signed-off-by: Fuad Tabba <[e-mail]>
---
 arch/arm64/include/asm/kvm_host.h |  5 +++--
 arch/arm64/kvm/mmu.c              | 30 ++++++++++++++++++++++++++----
 arch/arm64/kvm/pkvm.c             | 12 +++++++-----
 3 files changed, 36 insertions(+), 11 deletions(-)

Patch

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2777b0fe1b12..55de71791233 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -207,8 +207,9 @@  struct kvm_smccc_features {
 };
 
 struct kvm_pinned_page {
-	struct list_head	link;
+	struct rb_node		node;
 	struct page		*page;
+	u64			ipa;
 };
 
 typedef unsigned int pkvm_handle_t;
@@ -216,7 +217,7 @@  typedef unsigned int pkvm_handle_t;
 struct kvm_protected_vm {
 	pkvm_handle_t handle;
 	struct kvm_hyp_memcache teardown_mc;
-	struct list_head pinned_pages;
+	struct rb_root pinned_pages;
 	bool enabled;
 };
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index ac088dc198e6..f796e092a921 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -337,6 +337,7 @@  static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si
 static void pkvm_stage2_flush(struct kvm *kvm)
 {
 	struct kvm_pinned_page *ppage;
+	struct rb_node *node;
 
 	/*
 	 * Contrary to stage2_apply_range(), we don't need to check
@@ -344,7 +345,8 @@  static void pkvm_stage2_flush(struct kvm *kvm)
 	 * from a vcpu thread, and the list is only ever freed on VM
 	 * destroy (which only occurs when all vcpu are gone).
 	 */
-	list_for_each_entry(ppage, &kvm->arch.pkvm.pinned_pages, link) {
+	for (node = rb_first(&kvm->arch.pkvm.pinned_pages); node; node = rb_next(node)) {
+		ppage = rb_entry(node, struct kvm_pinned_page, node);
 		__clean_dcache_guest_page(page_address(ppage->page), PAGE_SIZE);
 		cond_resched_rwlock_write(&kvm->mmu_lock);
 	}
@@ -913,7 +915,7 @@  int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
 	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
 	mmu->vtcr = kvm_get_vtcr(mmfr0, mmfr1, phys_shift);
-	INIT_LIST_HEAD(&kvm->arch.pkvm.pinned_pages);
+	kvm->arch.pkvm.pinned_pages = RB_ROOT;
 	mmu->arch = &kvm->arch;
 
 	if (is_protected_kvm_enabled())
@@ -1412,6 +1414,26 @@  static int pkvm_host_map_guest(u64 pfn, u64 gfn)
 	return (ret == -EPERM) ? -EAGAIN : ret;
 }
 
+static int cmp_ppages(struct rb_node *node, const struct rb_node *parent)
+{
+	struct kvm_pinned_page *a = container_of(node, struct kvm_pinned_page, node);
+	struct kvm_pinned_page *b = container_of(parent, struct kvm_pinned_page, node);
+
+	if (a->ipa < b->ipa)
+		return -1;
+	if (a->ipa > b->ipa)
+		return 1;
+	return 0;
+}
+
+static int insert_ppage(struct kvm *kvm, struct kvm_pinned_page *ppage)
+{
+	if (rb_find_add(&ppage->node, &kvm->arch.pkvm.pinned_pages, cmp_ppages))
+		return -EEXIST;
+
+	return 0;
+}
+
 static int pkvm_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			  struct kvm_memory_slot *memslot)
 {
@@ -1479,8 +1501,8 @@  static int pkvm_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	ppage->page = page;
-	INIT_LIST_HEAD(&ppage->link);
-	list_add(&ppage->link, &kvm->arch.pkvm.pinned_pages);
+	ppage->ipa = fault_ipa;
+	WARN_ON(insert_ppage(kvm, ppage));
 	write_unlock(&kvm->mmu_lock);
 
 	return 0;
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 10a619b257c4..11355980e18d 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -246,9 +246,9 @@  static bool pkvm_teardown_vm(struct kvm *host_kvm)
 
 void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 {
-	struct kvm_pinned_page *ppage, *tmp;
+	struct kvm_pinned_page *ppage;
 	struct mm_struct *mm = current->mm;
-	struct list_head *ppages;
+	struct rb_node *node;
 	unsigned long pages = 0;
 
 	if (!pkvm_teardown_vm(host_kvm))
@@ -256,14 +256,16 @@  void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
 
 	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
 
-	ppages = &host_kvm->arch.pkvm.pinned_pages;
-	list_for_each_entry_safe(ppage, tmp, ppages, link) {
+	node = rb_first(&host_kvm->arch.pkvm.pinned_pages);
+	while (node) {
+		ppage = rb_entry(node, struct kvm_pinned_page, node);
 		WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_reclaim_page,
 					  page_to_pfn(ppage->page)));
 		cond_resched();
 
 		unpin_user_pages_dirty_lock(&ppage->page, 1, true);
-		list_del(&ppage->link);
+		node = rb_next(node);
+		rb_erase(&ppage->node, &host_kvm->arch.pkvm.pinned_pages);
 		kfree(ppage);
 		pages++;
 	}