1 files changed, 253 insertions, 12 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1c65ce0098a9..95d77770353c 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -14,7 +14,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
+	(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -59,6 +59,10 @@ int array_map_alloc_check(union bpf_attr *attr)
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
+	if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
+	    attr->map_flags & BPF_F_MMAPABLE)
+		return -EINVAL;
+
 	if (attr->value_size > KMALLOC_MAX_SIZE)
 		/* if value_size is bigger, the user space won't be able to
 		 * access the elements.
@@ -102,10 +106,19 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	}
 
 	array_size = sizeof(*array);
-	if (percpu)
+	if (percpu) {
 		array_size += (u64) max_entries * sizeof(void *);
-	else
-		array_size += (u64) max_entries * elem_size;
+	} else {
+		/* rely on vmalloc() to return page-aligned memory and
+		 * ensure array->value is exactly page-aligned
+		 */
+		if (attr->map_flags & BPF_F_MMAPABLE) {
+			array_size = PAGE_ALIGN(array_size);
+			array_size += PAGE_ALIGN((u64) max_entries * elem_size);
+		} else {
+			array_size += (u64) max_entries * elem_size;
+		}
+	}
 
 	/* make sure there is no u32 overflow later in round_up() */
 	cost = array_size;
@@ -117,7 +130,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
-	array = bpf_map_area_alloc(array_size, numa_node);
+	if (attr->map_flags & BPF_F_MMAPABLE) {
+		void *data;
+
+		/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
+		data = bpf_map_area_mmapable_alloc(array_size, numa_node);
+		if (!data) {
+			bpf_map_charge_finish(&mem);
+			return ERR_PTR(-ENOMEM);
+		}
+		array = data + PAGE_ALIGN(sizeof(struct bpf_array))
+			- offsetof(struct bpf_array, value);
+	} else {
+		array = bpf_map_area_alloc(array_size, numa_node);
+	}
 	if (!array) {
 		bpf_map_charge_finish(&mem);
 		return ERR_PTR(-ENOMEM);
@@ -350,6 +376,11 @@ static int array_map_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
+static void *array_map_vmalloc_addr(struct bpf_array *array)
+{
+	return (void *)round_down((unsigned long)array, PAGE_SIZE);
+}
+
 /* Called when map->refcnt goes to zero, either from workqueue or from syscall */
 static void array_map_free(struct bpf_map *map)
 {
@@ -365,7 +396,10 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
-	bpf_map_area_free(array);
+	if (array->map.map_flags & BPF_F_MMAPABLE)
+		bpf_map_area_free(array_map_vmalloc_addr(array));
+	else
+		bpf_map_area_free(array);
 }
 
 static void array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -444,6 +478,17 @@ static int array_map_check_btf(const struct bpf_map *map,
 	return 0;
 }
 
+static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
+
+	if (!(map->map_flags & BPF_F_MMAPABLE))
+		return -EINVAL;
+
+	return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -455,8 +500,11 @@ const struct bpf_map_ops array_map_ops = {
 	.map_gen_lookup = array_map_gen_lookup,
 	.map_direct_value_addr = array_map_direct_value_addr,
 	.map_direct_value_meta = array_map_direct_value_meta,
+	.map_mmap = array_map_mmap,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
+	.map_lookup_batch = generic_map_lookup_batch,
+	.map_update_batch = generic_map_update_batch,
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {
@@ -540,10 +588,17 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 	if (IS_ERR(new_ptr))
 		return PTR_ERR(new_ptr);
 
-	old_ptr = xchg(array->ptrs + index, new_ptr);
+	if (map->ops->map_poke_run) {
+		mutex_lock(&array->aux->poke_mutex);
+		old_ptr = xchg(array->ptrs + index, new_ptr);
+		map->ops->map_poke_run(map, index, old_ptr, new_ptr);
+		mutex_unlock(&array->aux->poke_mutex);
+	} else {
+		old_ptr = xchg(array->ptrs + index, new_ptr);
+	}
+
 	if (old_ptr)
 		map->ops->map_fd_put_ptr(old_ptr);
-
 	return 0;
 }
 
@@ -556,7 +611,15 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 	if (index >= array->map.max_entries)
 		return -E2BIG;
 
-	old_ptr = xchg(array->ptrs + index, NULL);
+	if (map->ops->map_poke_run) {
+		mutex_lock(&array->aux->poke_mutex);
+		old_ptr = xchg(array->ptrs + index, NULL);
+		map->ops->map_poke_run(map, index, old_ptr, NULL);
+		mutex_unlock(&array->aux->poke_mutex);
+	} else {
+		old_ptr = xchg(array->ptrs + index, NULL);
+	}
+
 	if (old_ptr) {
 		map->ops->map_fd_put_ptr(old_ptr);
 		return 0;
@@ -625,17 +688,195 @@ static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
+struct prog_poke_elem {
+	struct list_head list;
+	struct bpf_prog_aux *aux;
+};
+
+static int prog_array_map_poke_track(struct bpf_map *map,
+				     struct bpf_prog_aux *prog_aux)
+{
+	struct prog_poke_elem *elem;
+	struct bpf_array_aux *aux;
+	int ret = 0;
+
+	aux = container_of(map, struct bpf_array, map)->aux;
+	mutex_lock(&aux->poke_mutex);
+	list_for_each_entry(elem, &aux->poke_progs, list) {
+		if (elem->aux == prog_aux)
+			goto out;
+	}
+
+	elem = kmalloc(sizeof(*elem), GFP_KERNEL);
+	if (!elem) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&elem->list);
+	/* We must track the program's aux info at this point in time
+	 * since the program pointer itself may not be stable yet, see
+	 * also comment in prog_array_map_poke_run().
+	 */
+	elem->aux = prog_aux;
+
+	list_add_tail(&elem->list, &aux->poke_progs);
+out:
+	mutex_unlock(&aux->poke_mutex);
+	return ret;
+}
+
+static void prog_array_map_poke_untrack(struct bpf_map *map,
+					struct bpf_prog_aux *prog_aux)
+{
+	struct prog_poke_elem *elem, *tmp;
+	struct bpf_array_aux *aux;
+
+	aux = container_of(map, struct bpf_array, map)->aux;
+	mutex_lock(&aux->poke_mutex);
+	list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) {
+		if (elem->aux == prog_aux) {
+			list_del_init(&elem->list);
+			kfree(elem);
+			break;
+		}
+	}
+	mutex_unlock(&aux->poke_mutex);
+}
+
+static void prog_array_map_poke_run(struct bpf_map *map, u32 key,
+				    struct bpf_prog *old,
+				    struct bpf_prog *new)
+{
+	struct prog_poke_elem *elem;
+	struct bpf_array_aux *aux;
+
+	aux = container_of(map, struct bpf_array, map)->aux;
+	WARN_ON_ONCE(!mutex_is_locked(&aux->poke_mutex));
+
+	list_for_each_entry(elem, &aux->poke_progs, list) {
+		struct bpf_jit_poke_descriptor *poke;
+		int i, ret;
+
+		for (i = 0; i < elem->aux->size_poke_tab; i++) {
+			poke = &elem->aux->poke_tab[i];
+
+			/* Few things to be aware of:
+			 *
+			 * 1) We can only ever access aux in this context, but
+			 *    not aux->prog since it might not be stable yet and
+			 *    there could be danger of use after free otherwise.
+			 * 2) Initially when we start tracking aux, the program
+			 *    is not JITed yet and also does not have a kallsyms
+			 *    entry. We skip these as poke->ip_stable is not
+			 *    active yet. The JIT will do the final fixup before
+			 *    setting it stable. The various poke->ip_stable are
+			 *    successively activated, so tail call updates can
+			 *    arrive from here while JIT is still finishing its
+			 *    final fixup for non-activated poke entries.
+			 * 3) On program teardown, the program's kallsym entry gets
+			 *    removed out of RCU callback, but we can only untrack
+			 *    from sleepable context, therefore bpf_arch_text_poke()
+			 *    might not see that this is in BPF text section and
+			 *    bails out with -EINVAL. As these are unreachable since
+			 *    RCU grace period already passed, we simply skip them.
+			 * 4) Also programs reaching refcount of zero while patching
+			 *    is in progress is okay since we're protected under
+			 *    poke_mutex and untrack the programs before the JIT
+			 *    buffer is freed. When we're still in the middle of
+			 *    patching and suddenly kallsyms entry of the program
+			 *    gets evicted, we just skip the rest which is fine due
+			 *    to point 3).
+			 * 5) Any other error happening below from bpf_arch_text_poke()
+			 *    is a unexpected bug.
+			 */
+			if (!READ_ONCE(poke->ip_stable))
+				continue;
+			if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
+				continue;
+			if (poke->tail_call.map != map ||
+			    poke->tail_call.key != key)
+				continue;
+
+			ret = bpf_arch_text_poke(poke->ip, BPF_MOD_JUMP,
+						 old ? (u8 *)old->bpf_func +
+						 poke->adj_off : NULL,
+						 new ? (u8 *)new->bpf_func +
+						 poke->adj_off : NULL);
+			BUG_ON(ret < 0 && ret != -EINVAL);
+		}
+	}
+}
+
+static void prog_array_map_clear_deferred(struct work_struct *work)
+{
+	struct bpf_map *map = container_of(work, struct bpf_array_aux,
+					   work)->map;
+	bpf_fd_array_map_clear(map);
+	bpf_map_put(map);
+}
+
+static void prog_array_map_clear(struct bpf_map *map)
+{
+	struct bpf_array_aux *aux = container_of(map, struct bpf_array,
+						 map)->aux;
+	bpf_map_inc(map);
+	schedule_work(&aux->work);
+}
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_array_aux *aux;
+	struct bpf_map *map;
+
+	aux = kzalloc(sizeof(*aux), GFP_KERNEL);
+	if (!aux)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
+	INIT_LIST_HEAD(&aux->poke_progs);
+	mutex_init(&aux->poke_mutex);
+
+	map = array_map_alloc(attr);
+	if (IS_ERR(map)) {
+		kfree(aux);
+		return map;
+	}
+
+	container_of(map, struct bpf_array, map)->aux = aux;
+	aux->map = map;
+
+	return map;
+}
+
+static void prog_array_map_free(struct bpf_map *map)
+{
+	struct prog_poke_elem *elem, *tmp;
+	struct bpf_array_aux *aux;
+
+	aux = container_of(map, struct bpf_array, map)->aux;
+	list_for_each_entry_safe(elem, tmp, &aux->poke_progs, list) {
+		list_del_init(&elem->list);
+		kfree(elem);
+	}
+	kfree(aux);
+	fd_array_map_free(map);
+}
+
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
-	.map_alloc = array_map_alloc,
-	.map_free = fd_array_map_free,
+	.map_alloc = prog_array_map_alloc,
+	.map_free = prog_array_map_free,
+	.map_poke_track = prog_array_map_poke_track,
+	.map_poke_untrack = prog_array_map_poke_untrack,
+	.map_poke_run = prog_array_map_poke_run,
 	.map_get_next_key = array_map_get_next_key,
 	.map_lookup_elem = fd_array_map_lookup_elem,
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
-	.map_release_uref = bpf_fd_array_map_clear,
+	.map_release_uref = prog_array_map_clear,
 	.map_seq_show_elem = prog_array_map_seq_show_elem,
 };