diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 8ffcbe29395e0c4fff5293ac2ec28f71a57d98b3..f1f8fc069a9705201877473bf549b48ed0504929 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -39,6 +39,7 @@ menuconfig KVM
select HAVE_KVM_IRQ_BYPASS
select HAVE_KVM_VCPU_RUN_PID_CHANGE
select SCHED_INFO
+ select INTERVAL_TREE
help
Support hosting virtualized guest machines.
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index a77297480f56f17eee1290c32df3f02e810f7168..91d197bee9c0a551672dd8b7992cfff1f1ea4633 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -27,6 +27,7 @@ config KVM
select KVM_MMIO
select MMU_NOTIFIER
select SRCU
+ select INTERVAL_TREE
help
Support for hosting Guest kernels.
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index ff581d70f20cf1bbcafa10f1e6bbd0a5edaed2b4..e4c24f524ba877a3421a6a71b6ba233fe0b9c21a 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -26,6 +26,7 @@ config KVM
select KVM_VFIO
select IRQ_BYPASS_MANAGER
select HAVE_KVM_IRQ_BYPASS
+ select INTERVAL_TREE
config KVM_BOOK3S_HANDLER
bool
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 67a8e770e369f69cd8a8aece6f90fddf939d4fa1..2e84d3922f7cd92938d0486b4fb3e4fe5e534d54 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -33,6 +33,7 @@ config KVM
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
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 6191861381768c60e5aa409e05934fba3a21d4a6..7618bef0a4a993d689db1cb20ae59739222717a0 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -43,6 +43,7 @@ config KVM
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
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 79db70a8323ec2f09492e4dc2efeba9eb0fe6711..9552ad6d6652dfb4b359c1caea94215eb6762c5f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -30,6 +30,7 @@
#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>
@@ -428,6 +429,7 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
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;
@@ -529,6 +531,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
*/
struct kvm_memslots {
u64 generation;
+ struct rb_root_cached hva_tree;
/*
* The mapping table from slot id to the index in memslots[].
*
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dbff2ac9a8e3035dddf9d48fe0c469f3dba5c5fa..6ba7468bdbe302443c5cd9dd9efaefc5ae0b3957 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -512,6 +512,12 @@ static void kvm_null_fn(void)
}
#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)
{
@@ -521,6 +527,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
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)))
@@ -529,15 +538,17 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
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
@@ -873,6 +884,7 @@ static struct kvm_memslots *kvm_alloc_memslots(void)
if (!slots)
return NULL;
+ slots->hva_tree = RB_ROOT_CACHED;
hash_init(slots->id_hash);
return slots;
@@ -1277,21 +1289,28 @@ static void kvm_replace_memslot(struct kvm_memslots *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)
@@ -1322,7 +1341,7 @@ static inline void kvm_memslot_delete(struct kvm_memslots *slots,
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.
@@ -1349,7 +1368,8 @@ static inline int kvm_memslot_insert_back(struct kvm_memslots *slots)
* 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,
@@ -1363,10 +1383,10 @@ 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);
@@ -1392,10 +1412,12 @@ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots,
* 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,
@@ -1588,9 +1610,12 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old,
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;
}