KVM: Use interval tree to do fast hva lookup in memslots

The current memslots implementation only allows quick binary search by gfn,
quick lookup by hva is not possible - the implementation has to do a linear
scan of the whole memslots array, even though the operation being performed
might apply just to a single memslot.

This significantly hurts performance of per-hva operations with higher
memslot counts.

Since hva ranges can overlap between memslots an interval tree is needed
for tracking them.

[sean: handle interval tree updates in kvm_replace_memslot()]
Signed-off-by: Maciej S. Szmigiero <[e-mail]>
Message-Id: <d66b9974[e-mail]>

arch/arm64/kvm/Kconfig

···
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	select SCHED_INFO
+	select INTERVAL_TREE
 	help
 	  Support hosting virtualized guest machines.
 

arch/mips/kvm/Kconfig

···
 	select KVM_MMIO
 	select MMU_NOTIFIER
 	select SRCU
+	select INTERVAL_TREE
 	help
 	  Support for hosting Guest kernels.
 

arch/powerpc/kvm/Kconfig

···
 	select KVM_VFIO
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
+	select INTERVAL_TREE
 
 config KVM_BOOK3S_HANDLER
 	bool

arch/s390/kvm/Kconfig

···
 	select HAVE_KVM_NO_POLL
 	select SRCU
 	select KVM_VFIO
+	select INTERVAL_TREE
 	help
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/x86/kvm/Kconfig

···
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
 	select SRCU
+	select INTERVAL_TREE
 	select HAVE_KVM_PM_NOTIFIER if PM
 	help
 	  Support hosting fully virtualized guest machines using hardware

include/linux/kvm_host.h

···
 #include <linux/nospec.h>
 #include <linux/notifier.h>
 #include <linux/hashtable.h>
+#include <linux/interval_tree.h>
 #include <linux/xarray.h>
 #include <asm/signal.h>
 
···
 
 struct kvm_memory_slot {
 	struct hlist_node id_node;
+	struct interval_tree_node hva_node;
 	gfn_t base_gfn;
 	unsigned long npages;
 	unsigned long *dirty_bitmap;
···
  */
 struct kvm_memslots {
 	u64 generation;
+	struct rb_root_cached hva_tree;
 	/*
 	 * The mapping table from slot id to the index in memslots[].
 	 *

virt/kvm/kvm_main.c

···
 }
 #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
 
+/* Iterate over each memslot intersecting [start, last] (inclusive) range */
+#define kvm_for_each_memslot_in_hva_range(node, slots, start, last)	     \
+	for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \
+	     node;							     \
+	     node = interval_tree_iter_next(node, start, last))	     \
+
 static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 						  const struct kvm_hva_range *range)
 {
···
 	struct kvm_memslots *slots;
 	int i, idx;
 
+	if (WARN_ON_ONCE(range->end <= range->start))
+		return 0;
+
 	/* A null handler is allowed if and only if on_lock() is provided. */
 	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
 			 IS_KVM_NULL_FN(range->handler)))
···
 	idx = srcu_read_lock(&kvm->srcu);
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		struct interval_tree_node *node;
+
 		slots = __kvm_memslots(kvm, i);
-		kvm_for_each_memslot(slot, slots) {
+		kvm_for_each_memslot_in_hva_range(node, slots,
+						  range->start, range->end - 1) {
 			unsigned long hva_start, hva_end;
 
+			slot = container_of(node, struct kvm_memory_slot, hva_node);
 			hva_start = max(range->start, slot->userspace_addr);
 			hva_end = min(range->end, slot->userspace_addr +
 						  (slot->npages << PAGE_SHIFT));
-			if (hva_start >= hva_end)
-				continue;
 
 			/*
 			 * To optimize for the likely case where the address
···
 	if (!slots)
 		return NULL;
 
+	slots->hva_tree = RB_ROOT_CACHED;
 	hash_init(slots->id_hash);
 
 	return slots;
···
 				struct kvm_memory_slot *new)
 {
 	/*
-	 * Remove the old memslot from the hash list, copying the node data
-	 * would corrupt the list.
+	 * Remove the old memslot from the hash list and interval tree, copying
+	 * the node data would corrupt the structures.
 	 */
 	if (old) {
 		hash_del(&old->id_node);
+		interval_tree_remove(&old->hva_node, &slots->hva_tree);
 
 		if (!new)
 			return;
 
 		/* Copy the source *data*, not the pointer, to the destination. */
 		*new = *old;
+	} else {
+		/* If @old is NULL, initialize @new's hva range. */
+		new->hva_node.start = new->userspace_addr;
+		new->hva_node.last = new->userspace_addr +
+			(new->npages << PAGE_SHIFT) - 1;
 	}
 
 	/* (Re)Add the new memslot. */
 	hash_add(slots->id_hash, &new->id_node, new->id);
+	interval_tree_insert(&new->hva_node, &slots->hva_tree);
 }
 
 static void kvm_shift_memslot(struct kvm_memslots *slots, int dst, int src)
···
 		atomic_set(&slots->last_used_slot, 0);
 
 	/*
-	 * Remove the to-be-deleted memslot from the list _before_ shifting
+	 * Remove the to-be-deleted memslot from the list/tree _before_ shifting
 	 * the trailing memslots forward, its data will be overwritten.
 	 * Defer the (somewhat pointless) copying of the memslot until after
 	 * the last slot has been shifted to avoid overwriting said last slot.
···
  * itself is not preserved in the array, i.e. not swapped at this time, only
  * its new index into the array is tracked.  Returns the changed memslot's
  * current index into the memslots array.
- * The memslot at the returned index will not be in @slots->id_hash by then.
+ * The memslot at the returned index will not be in @slots->hva_tree or
+ * @slots->id_hash by then.
  * @memslot is a detached struct with desired final data of the changed slot.
  */
 static inline int kvm_memslot_move_backward(struct kvm_memslots *slots,
···
 		return -1;
 
 	/*
-	 * Delete the slot from the hash table before sorting the remaining
-	 * slots, the slot's data may be overwritten when copying slots as part
-	 * of the sorting proccess.  update_memslots() will unconditionally
-	 * rewrite the entire slot and re-add it to the hash table.
+	 * Delete the slot from the hash table and interval tree before sorting
+	 * the remaining slots, the slot's data may be overwritten when copying
+	 * slots as part of the sorting proccess.  update_memslots() will
+	 * unconditionally rewrite and re-add the entire slot.
 	 */
 	kvm_replace_memslot(slots, oldslot, NULL);
 
···
  * is not preserved in the array, i.e. not swapped at this time, only its new
  * index into the array is tracked.  Returns the changed memslot's final index
  * into the memslots array.
- * The memslot at the returned index will not be in @slots->id_hash by then.
+ * The memslot at the returned index will not be in @slots->hva_tree or
+ * @slots->id_hash by then.
  * @memslot is a detached struct with desired final data of the new or
  * changed slot.
- * Assumes that the memslot at @start index is not in @slots->id_hash.
+ * Assumes that the memslot at @start index is not in @slots->hva_tree or
+ * @slots->id_hash.
  */
 static inline int kvm_memslot_move_forward(struct kvm_memslots *slots,
 					   struct kvm_memory_slot *memslot,
···
 
 	memcpy(slots, old, kvm_memslots_size(old->used_slots));
 
+	slots->hva_tree = RB_ROOT_CACHED;
 	hash_init(slots->id_hash);
-	kvm_for_each_memslot(memslot, slots)
+	kvm_for_each_memslot(memslot, slots) {
+		interval_tree_insert(&memslot->hva_node, &slots->hva_tree);
 		hash_add(slots->id_hash, &memslot->id_node, memslot->id);
+	}
 
 	return slots;
 }