Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-01-24

We've added 80 non-merge commits during the last 14 day(s) which contain
a total of 128 files changed, 4990 insertions(+), 895 deletions(-).

The main changes are:

1) Add XDP multi-buffer support and implement it for the mvneta driver,
   from Lorenzo Bianconi, Eelco Chaudron and Toke Høiland-Jørgensen.

2) Add unstable conntrack lookup helpers for BPF by using the BPF kfunc
   infra, from Kumar Kartikeya Dwivedi.

3) Extend BPF cgroup programs to export custom ret value to userspace via
   two helpers bpf_get_retval() and bpf_set_retval(), from YiFei Zhu.

4) Add support for AF_UNIX iterator batching, from Kuniyuki Iwashima.

5) Complete missing UAPI BPF helper description and change bpf_doc.py script
   to enforce consistent & complete helper documentation, from Usama Arif.

6) Deprecate libbpf's legacy BPF map definitions and streamline XDP APIs to
   follow tc-based APIs, from Andrii Nakryiko.

7) Support BPF_PROG_QUERY for BPF programs attached to sockmap, from Di Zhu.

8) Deprecate libbpf's bpf_map__def() API and replace users with proper getters
   and setters, from Christy Lee.

9) Extend libbpf's btf__add_btf() with an additional hashmap for strings to
   reduce overhead, from Kui-Feng Lee.

10) Fix bpftool and libbpf error handling related to libbpf's hashmap__new()
    utility function, from Mauricio Vásquez.

11) Add support to BTF program names in bpftool's program dump, from Raman Shukhau.

12) Fix resolve_btfids build to pick up host flags, from Connor O'Brien.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (80 commits)
  selftests, bpf: Do not yet switch to new libbpf XDP APIs
  selftests, xsk: Fix rx_full stats test
  bpf: Fix flexible_array.cocci warnings
  xdp: disable XDP_REDIRECT for xdp frags
  bpf: selftests: add CPUMAP/DEVMAP selftests for xdp frags
  bpf: selftests: introduce bpf_xdp_{load,store}_bytes selftest
  net: xdp: introduce bpf_xdp_pointer utility routine
  bpf: generalise tail call map compatibility check
  libbpf: Add SEC name for xdp frags programs
  bpf: selftests: update xdp_adjust_tail selftest to include xdp frags
  bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature
  bpf: introduce frags support to bpf_prog_test_run_xdp()
  bpf: move user_size out of bpf_test_init
  bpf: add frags support to xdp copy helpers
  bpf: add frags support to the bpf_xdp_adjust_tail() API
  bpf: introduce bpf_xdp_get_buff_len helper
  net: mvneta: enable jumbo frames if the loaded XDP program support frags
  bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program
  net: mvneta: add frags support to XDP_TX
  xdp: add frags support to xdp_return_{buff/frame}
  ...
====================

Link: https://lore.kernel.org/r/20220124221235.18993-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 591 insertions, 192 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c7a5be3bf8be..7f145aefbff8 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -837,13 +837,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 static void *prog_fd_array_get_ptr(struct bpf_map *map,
 				   struct file *map_file, int fd)
 {
-	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	struct bpf_prog *prog = bpf_prog_get(fd);
 
 	if (IS_ERR(prog))
 		return prog;
 
-	if (!bpf_prog_array_compatible(array, prog)) {
+	if (!bpf_prog_map_compatible(map, prog)) {
 		bpf_prog_put(prog);
 		return ERR_PTR(-EINVAL);
 	}
@@ -1071,7 +1070,6 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
 	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
 	INIT_LIST_HEAD(&aux->poke_progs);
 	mutex_init(&aux->poke_mutex);
-	spin_lock_init(&aux->owner.lock);
 
 	map = array_map_alloc(attr);
 	if (IS_ERR(map)) {
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e16dafeb2450..a1c44c17ea9c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -198,6 +198,21 @@
 DEFINE_IDR(btf_idr);
 DEFINE_SPINLOCK(btf_idr_lock);
 
+enum btf_kfunc_hook {
+	BTF_KFUNC_HOOK_XDP,
+	BTF_KFUNC_HOOK_TC,
+	BTF_KFUNC_HOOK_STRUCT_OPS,
+	BTF_KFUNC_HOOK_MAX,
+};
+
+enum {
+	BTF_KFUNC_SET_MAX_CNT = 32,
+};
+
+struct btf_kfunc_set_tab {
+	struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX];
+};
+
 struct btf {
 	void *data;
 	struct btf_type **types;
@@ -212,6 +227,7 @@ struct btf {
 	refcount_t refcnt;
 	u32 id;
 	struct rcu_head rcu;
+	struct btf_kfunc_set_tab *kfunc_set_tab;
 
 	/* split BTF support */
 	struct btf *base_btf;
@@ -1531,8 +1547,30 @@ static void btf_free_id(struct btf *btf)
 	spin_unlock_irqrestore(&btf_idr_lock, flags);
 }
 
+static void btf_free_kfunc_set_tab(struct btf *btf)
+{
+	struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab;
+	int hook, type;
+
+	if (!tab)
+		return;
+	/* For module BTF, we directly assign the sets being registered, so
+	 * there is nothing to free except kfunc_set_tab.
+	 */
+	if (btf_is_module(btf))
+		goto free_tab;
+	for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) {
+		for (type = 0; type < ARRAY_SIZE(tab->sets[0]); type++)
+			kfree(tab->sets[hook][type]);
+	}
+free_tab:
+	kfree(tab);
+	btf->kfunc_set_tab = NULL;
+}
+
 static void btf_free(struct btf *btf)
 {
+	btf_free_kfunc_set_tab(btf);
 	kvfree(btf->types);
 	kvfree(btf->resolved_sizes);
 	kvfree(btf->resolved_ids);
@@ -5616,17 +5654,45 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log,
 	return true;
 }
 
+static bool is_kfunc_arg_mem_size(const struct btf *btf,
+				  const struct btf_param *arg,
+				  const struct bpf_reg_state *reg)
+{
+	int len, sfx_len = sizeof("__sz") - 1;
+	const struct btf_type *t;
+	const char *param_name;
+
+	t = btf_type_skip_modifiers(btf, arg->type, NULL);
+	if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE)
+		return false;
+
+	/* In the future, this can be ported to use BTF tagging */
+	param_name = btf_name_by_offset(btf, arg->name_off);
+	if (str_is_empty(param_name))
+		return false;
+	len = strlen(param_name);
+	if (len < sfx_len)
+		return false;
+	param_name += len - sfx_len;
+	if (strncmp(param_name, "__sz", sfx_len))
+		return false;
+
+	return true;
+}
+
 static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 				    const struct btf *btf, u32 func_id,
 				    struct bpf_reg_state *regs,
 				    bool ptr_to_mem_ok)
 {
 	struct bpf_verifier_log *log = &env->log;
+	u32 i, nargs, ref_id, ref_obj_id = 0;
 	bool is_kfunc = btf_is_kernel(btf);
 	const char *func_name, *ref_tname;
 	const struct btf_type *t, *ref_t;
 	const struct btf_param *args;
-	u32 i, nargs, ref_id;
+	int ref_regno = 0;
+	bool rel = false;
 
 	t = btf_type_by_id(btf, func_id);
 	if (!t || !btf_type_is_func(t)) {
@@ -5704,6 +5770,16 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			if (reg->type == PTR_TO_BTF_ID) {
 				reg_btf = reg->btf;
 				reg_ref_id = reg->btf_id;
+				/* Ensure only one argument is referenced PTR_TO_BTF_ID */
+				if (reg->ref_obj_id) {
+					if (ref_obj_id) {
+						bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+							regno, reg->ref_obj_id, ref_obj_id);
+						return -EFAULT;
+					}
+					ref_regno = regno;
+					ref_obj_id = reg->ref_obj_id;
+				}
 			} else {
 				reg_btf = btf_vmlinux;
 				reg_ref_id = *reg2btf_ids[reg->type];
@@ -5727,17 +5803,33 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			u32 type_size;
 
 			if (is_kfunc) {
+				bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], &regs[regno + 1]);
+
 				/* Permit pointer to mem, but only when argument
 				 * type is pointer to scalar, or struct composed
 				 * (recursively) of scalars.
+				 * When arg_mem_size is true, the pointer can be
+				 * void *.
 				 */
 				if (!btf_type_is_scalar(ref_t) &&
-				    !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) {
+				    !__btf_type_is_scalar_struct(log, btf, ref_t, 0) &&
+				    (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) {
 					bpf_log(log,
-						"arg#%d pointer type %s %s must point to scalar or struct with scalar\n",
-						i, btf_type_str(ref_t), ref_tname);
+						"arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n",
+						i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : "");
 					return -EINVAL;
 				}
+
+				/* Check for mem, len pair */
+				if (arg_mem_size) {
+					if (check_kfunc_mem_size_reg(env, &regs[regno + 1], regno + 1)) {
+						bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n",
+							i, i + 1);
+						return -EINVAL;
+					}
+					i++;
+					continue;
+				}
 			}
 
 			resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
@@ -5758,7 +5850,23 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		}
 	}
 
-	return 0;
+	/* Either both are set, or neither */
+	WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno));
+	if (is_kfunc) {
+		rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
+						BTF_KFUNC_TYPE_RELEASE, func_id);
+		/* We already made sure ref_obj_id is set only for one argument */
+		if (rel && !ref_obj_id) {
+			bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n",
+				func_name);
+			return -EINVAL;
+		}
+		/* Allow (!rel && ref_obj_id), so that passing such referenced PTR_TO_BTF_ID to
+		 * other kfuncs works
+		 */
+	}
+	/* returns argument register number > 0 in case of reference release kfunc */
+	return rel ? ref_regno : 0;
 }
 
 /* Compare BTF of a function with given bpf_reg_state.
@@ -6200,12 +6308,17 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
 }
 
+enum {
+	BTF_MODULE_F_LIVE = (1 << 0),
+};
+
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 struct btf_module {
 	struct list_head list;
 	struct module *module;
 	struct btf *btf;
 	struct bin_attribute *sysfs_attr;
+	int flags;
 };
 
 static LIST_HEAD(btf_modules);
@@ -6233,7 +6346,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 	int err = 0;
 
 	if (mod->btf_data_size == 0 ||
-	    (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+	    (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE &&
+	     op != MODULE_STATE_GOING))
 		goto out;
 
 	switch (op) {
@@ -6292,6 +6406,17 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 		}
 
 		break;
+	case MODULE_STATE_LIVE:
+		mutex_lock(&btf_module_mutex);
+		list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+			if (btf_mod->module != module)
+				continue;
+
+			btf_mod->flags |= BTF_MODULE_F_LIVE;
+			break;
+		}
+		mutex_unlock(&btf_module_mutex);
+		break;
 	case MODULE_STATE_GOING:
 		mutex_lock(&btf_module_mutex);
 		list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
@@ -6338,7 +6463,12 @@ struct module *btf_try_get_module(const struct btf *btf)
 		if (btf_mod->btf != btf)
 			continue;
 
-		if (try_module_get(btf_mod->module))
+		/* We must only consider module whose __init routine has
+		 * finished, hence we must check for BTF_MODULE_F_LIVE flag,
+		 * which is set from the notifier callback for
+		 * MODULE_STATE_LIVE.
+		 */
+		if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module))
 			res = btf_mod->module;
 
 		break;
@@ -6349,6 +6479,36 @@ struct module *btf_try_get_module(const struct btf *btf)
 	return res;
 }
 
+/* Returns struct btf corresponding to the struct module
+ *
+ * This function can return NULL or ERR_PTR. Note that caller must
+ * release reference for struct btf iff btf_is_module is true.
+ */
+static struct btf *btf_get_module_btf(const struct module *module)
+{
+	struct btf *btf = NULL;
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+	struct btf_module *btf_mod, *tmp;
+#endif
+
+	if (!module)
+		return bpf_get_btf_vmlinux();
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+	mutex_lock(&btf_module_mutex);
+	list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+		if (btf_mod->module != module)
+			continue;
+
+		btf_get(btf_mod->btf);
+		btf = btf_mod->btf;
+		break;
+	}
+	mutex_unlock(&btf_module_mutex);
+#endif
+
+	return btf;
+}
+
 BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags)
 {
 	struct btf *btf;
@@ -6416,53 +6576,181 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE)
 BTF_TRACING_TYPE_xxx
 #undef BTF_TRACING_TYPE
 
-/* BTF ID set registration API for modules */
-
-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+/* Kernel Function (kfunc) BTF ID set registration API */
 
-void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-			       struct kfunc_btf_id_set *s)
+static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
+				    enum btf_kfunc_type type,
+				    struct btf_id_set *add_set, bool vmlinux_set)
 {
-	mutex_lock(&l->mutex);
-	list_add(&s->list, &l->list);
-	mutex_unlock(&l->mutex);
+	struct btf_kfunc_set_tab *tab;
+	struct btf_id_set *set;
+	u32 set_cnt;
+	int ret;
+
+	if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	if (!add_set->cnt)
+		return 0;
+
+	tab = btf->kfunc_set_tab;
+	if (!tab) {
+		tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN);
+		if (!tab)
+			return -ENOMEM;
+		btf->kfunc_set_tab = tab;
+	}
+
+	set = tab->sets[hook][type];
+	/* Warn when register_btf_kfunc_id_set is called twice for the same hook
+	 * for module sets.
+	 */
+	if (WARN_ON_ONCE(set && !vmlinux_set)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	/* We don't need to allocate, concatenate, and sort module sets, because
+	 * only one is allowed per hook. Hence, we can directly assign the
+	 * pointer and return.
+	 */
+	if (!vmlinux_set) {
+		tab->sets[hook][type] = add_set;
+		return 0;
+	}
+
+	/* In case of vmlinux sets, there may be more than one set being
+	 * registered per hook. To create a unified set, we allocate a new set
+	 * and concatenate all individual sets being registered. While each set
+	 * is individually sorted, they may become unsorted when concatenated,
+	 * hence re-sorting the final set again is required to make binary
+	 * searching the set using btf_id_set_contains function work.
+	 */
+	set_cnt = set ? set->cnt : 0;
+
+	if (set_cnt > U32_MAX - add_set->cnt) {
+		ret = -EOVERFLOW;
+		goto end;
+	}
+
+	if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) {
+		ret = -E2BIG;
+		goto end;
+	}
+
+	/* Grow set */
+	set = krealloc(tab->sets[hook][type],
+		       offsetof(struct btf_id_set, ids[set_cnt + add_set->cnt]),
+		       GFP_KERNEL | __GFP_NOWARN);
+	if (!set) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	/* For newly allocated set, initialize set->cnt to 0 */
+	if (!tab->sets[hook][type])
+		set->cnt = 0;
+	tab->sets[hook][type] = set;
+
+	/* Concatenate the two sets */
+	memcpy(set->ids + set->cnt, add_set->ids, add_set->cnt * sizeof(set->ids[0]));
+	set->cnt += add_set->cnt;
+
+	sort(set->ids, set->cnt, sizeof(set->ids[0]), btf_id_cmp_func, NULL);
+
+	return 0;
+end:
+	btf_free_kfunc_set_tab(btf);
+	return ret;
 }
-EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set);
 
-void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
-				 struct kfunc_btf_id_set *s)
+static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
+				  const struct btf_kfunc_id_set *kset)
 {
-	mutex_lock(&l->mutex);
-	list_del_init(&s->list);
-	mutex_unlock(&l->mutex);
+	bool vmlinux_set = !btf_is_module(btf);
+	int type, ret;
+
+	for (type = 0; type < ARRAY_SIZE(kset->sets); type++) {
+		if (!kset->sets[type])
+			continue;
+
+		ret = __btf_populate_kfunc_set(btf, hook, type, kset->sets[type], vmlinux_set);
+		if (ret)
+			break;
+	}
+	return ret;
 }
-EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set);
 
-bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
-			      struct module *owner)
+static bool __btf_kfunc_id_set_contains(const struct btf *btf,
+					enum btf_kfunc_hook hook,
+					enum btf_kfunc_type type,
+					u32 kfunc_btf_id)
 {
-	struct kfunc_btf_id_set *s;
+	struct btf_id_set *set;
 
-	mutex_lock(&klist->mutex);
-	list_for_each_entry(s, &klist->list, list) {
-		if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
-			mutex_unlock(&klist->mutex);
-			return true;
-		}
+	if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX)
+		return false;
+	if (!btf->kfunc_set_tab)
+		return false;
+	set = btf->kfunc_set_tab->sets[hook][type];
+	if (!set)
+		return false;
+	return btf_id_set_contains(set, kfunc_btf_id);
+}
+
+static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
+{
+	switch (prog_type) {
+	case BPF_PROG_TYPE_XDP:
+		return BTF_KFUNC_HOOK_XDP;
+	case BPF_PROG_TYPE_SCHED_CLS:
+		return BTF_KFUNC_HOOK_TC;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return BTF_KFUNC_HOOK_STRUCT_OPS;
+	default:
+		return BTF_KFUNC_HOOK_MAX;
 	}
-	mutex_unlock(&klist->mutex);
-	return false;
 }
 
-#define DEFINE_KFUNC_BTF_ID_LIST(name)                                         \
-	struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list),           \
-					  __MUTEX_INITIALIZER(name.mutex) };   \
-	EXPORT_SYMBOL_GPL(name)
+/* Caution:
+ * Reference to the module (obtained using btf_try_get_module) corresponding to
+ * the struct btf *MUST* be held when calling this function from verifier
+ * context. This is usually true as we stash references in prog's kfunc_btf_tab;
+ * keeping the reference for the duration of the call provides the necessary
+ * protection for looking up a well-formed btf->kfunc_set_tab.
+ */
+bool btf_kfunc_id_set_contains(const struct btf *btf,
+			       enum bpf_prog_type prog_type,
+			       enum btf_kfunc_type type, u32 kfunc_btf_id)
+{
+	enum btf_kfunc_hook hook;
 
-DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
-DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+	hook = bpf_prog_type_to_kfunc_hook(prog_type);
+	return __btf_kfunc_id_set_contains(btf, hook, type, kfunc_btf_id);
+}
 
-#endif
+/* This function must be invoked only from initcalls/module init functions */
+int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+			      const struct btf_kfunc_id_set *kset)
+{
+	enum btf_kfunc_hook hook;
+	struct btf *btf;
+	int ret;
+
+	btf = btf_get_module_btf(kset->owner);
+	if (IS_ERR_OR_NULL(btf))
+		return btf ? PTR_ERR(btf) : -ENOENT;
+
+	hook = bpf_prog_type_to_kfunc_hook(prog_type);
+	ret = btf_populate_kfunc_set(btf, hook, kset);
+	/* reference is only taken for module BTF */
+	if (btf_is_module(btf))
+		btf_put(btf);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set);
 
 int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
 			      const struct btf *targ_btf, __u32 targ_id)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 514b4681a90a..279ebbed75a5 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1044,7 +1044,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  *   NET_XMIT_DROP       (1)	- drop packet and notify TCP to call cwr
  *   NET_XMIT_CN         (2)	- continue with packet output and notify TCP
  *				  to call cwr
- *   -EPERM			- drop packet
+ *   -err			- drop packet
  *
  * For ingress packets, this function will return -EPERM if any
  * attached program was found and if it returned != 1 during execution.
@@ -1079,8 +1079,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 			cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb);
 	} else {
 		ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb,
-					    __bpf_prog_run_save_cb);
-		ret = (ret == 1 ? 0 : -EPERM);
+					    __bpf_prog_run_save_cb, 0);
+		if (ret && !IS_ERR_VALUE((long)ret))
+			ret = -EFAULT;
 	}
 	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
@@ -1107,10 +1108,9 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 			       enum cgroup_bpf_attach_type atype)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	int ret;
 
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, bpf_prog_run);
-	return ret == 1 ? 0 : -EPERM;
+	return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk,
+				     bpf_prog_run, 0);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
 
@@ -1142,7 +1142,6 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	};
 	struct sockaddr_storage unspec;
 	struct cgroup *cgrp;
-	int ret;
 
 	/* Check socket family since not all sockets represent network
 	 * endpoint (e.g. AF_UNIX).
@@ -1156,10 +1155,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	}
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx,
-				          bpf_prog_run, flags);
-
-	return ret == 1 ? 0 : -EPERM;
+	return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx,
+					   bpf_prog_run, 0, flags);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
 
@@ -1184,11 +1181,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 				     enum cgroup_bpf_attach_type atype)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	int ret;
 
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops,
-				    bpf_prog_run);
-	return ret == 1 ? 0 : -EPERM;
+	return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops,
+				     bpf_prog_run, 0);
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
 
@@ -1201,17 +1196,47 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 		.major = major,
 		.minor = minor,
 	};
-	int allow;
+	int ret;
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
-				      bpf_prog_run);
+	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
+				    bpf_prog_run, 0);
 	rcu_read_unlock();
 
-	return !allow;
+	return ret;
 }
 
+BPF_CALL_0(bpf_get_retval)
+{
+	struct bpf_cg_run_ctx *ctx =
+		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+	return ctx->retval;
+}
+
+static const struct bpf_func_proto bpf_get_retval_proto = {
+	.func		= bpf_get_retval,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_1(bpf_set_retval, int, retval)
+{
+	struct bpf_cg_run_ctx *ctx =
+		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+	ctx->retval = retval;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_set_retval_proto = {
+	.func		= bpf_set_retval,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1224,6 +1249,10 @@ cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_retval:
+		return &bpf_get_retval_proto;
+	case BPF_FUNC_set_retval:
+		return &bpf_set_retval_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -1337,7 +1366,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
-	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run);
+	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
+				    bpf_prog_run, 0);
 	rcu_read_unlock();
 
 	kfree(ctx.cur_val);
@@ -1350,7 +1380,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		kfree(ctx.new_val);
 	}
 
-	return ret == 1 ? 0 : -EPERM;
+	return ret;
 }
 
 #ifdef CONFIG_NET
@@ -1452,13 +1482,11 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 
 	lock_sock(sk);
 	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT],
-				    &ctx, bpf_prog_run);
+				    &ctx, bpf_prog_run, 0);
 	release_sock(sk);
 
-	if (!ret) {
-		ret = -EPERM;
+	if (ret)
 		goto out;
-	}
 
 	if (ctx.optlen == -1) {
 		/* optlen set to -1, bypass kernel */
@@ -1518,7 +1546,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		.sk = sk,
 		.level = level,
 		.optname = optname,
-		.retval = retval,
+		.current_task = current,
 	};
 	int ret;
 
@@ -1562,27 +1590,17 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 
 	lock_sock(sk);
 	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
-				    &ctx, bpf_prog_run);
+				    &ctx, bpf_prog_run, retval);
 	release_sock(sk);
 
-	if (!ret) {
-		ret = -EPERM;
+	if (ret < 0)
 		goto out;
-	}
 
 	if (ctx.optlen > max_optlen || ctx.optlen < 0) {
 		ret = -EFAULT;
 		goto out;
 	}
 
-	/* BPF programs only allowed to set retval to 0, not some
-	 * arbitrary value.
-	 */
-	if (ctx.retval != 0 && ctx.retval != retval) {
-		ret = -EFAULT;
-		goto out;
-	}
-
 	if (ctx.optlen != 0) {
 		if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
 		    put_user(ctx.optlen, optlen)) {
@@ -1591,8 +1609,6 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		}
 	}
 
-	ret = ctx.retval;
-
 out:
 	sockopt_free_buf(&ctx, &buf);
 	return ret;
@@ -1607,10 +1623,10 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
 		.sk = sk,
 		.level = level,
 		.optname = optname,
-		.retval = retval,
 		.optlen = *optlen,
 		.optval = optval,
 		.optval_end = optval + *optlen,
+		.current_task = current,
 	};
 	int ret;
 
@@ -1623,25 +1639,19 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
 	 */
 
 	ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
-				    &ctx, bpf_prog_run);
-	if (!ret)
-		return -EPERM;
+				    &ctx, bpf_prog_run, retval);
+	if (ret < 0)
+		return ret;
 
 	if (ctx.optlen > *optlen)
 		return -EFAULT;
 
-	/* BPF programs only allowed to set retval to 0, not some
-	 * arbitrary value.
-	 */
-	if (ctx.retval != 0 && ctx.retval != retval)
-		return -EFAULT;
-
 	/* BPF programs can shrink the buffer, export the modifications.
 	 */
 	if (ctx.optlen != 0)
 		*optlen = ctx.optlen;
 
-	return ctx.retval;
+	return ret;
 }
 #endif
 
@@ -2057,10 +2067,39 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type,
 			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
 		break;
 	case offsetof(struct bpf_sockopt, retval):
-		if (type == BPF_WRITE)
-			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
-		else
-			*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
+		BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0);
+
+		if (type == BPF_WRITE) {
+			int treg = BPF_REG_9;
+
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			*insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg,
+					      offsetof(struct bpf_sockopt_kern, tmp_reg));
+			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
+					      treg, si->dst_reg,
+					      offsetof(struct bpf_sockopt_kern, current_task));
+			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
+					      treg, treg,
+					      offsetof(struct task_struct, bpf_ctx));
+			*insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
+					      treg, si->src_reg,
+					      offsetof(struct bpf_cg_run_ctx, retval));
+			*insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg,
+					      offsetof(struct bpf_sockopt_kern, tmp_reg));
+		} else {
+			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
+					      si->dst_reg, si->src_reg,
+					      offsetof(struct bpf_sockopt_kern, current_task));
+			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
+					      si->dst_reg, si->dst_reg,
+					      offsetof(struct task_struct, bpf_ctx));
+			*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
+					      si->dst_reg, si->dst_reg,
+					      offsetof(struct bpf_cg_run_ctx, retval));
+		}
 		break;
 	case offsetof(struct bpf_sockopt, optval):
 		*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index de3e5bc6781f..0a1cfd8544b9 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1829,28 +1829,30 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 }
 #endif
 
-bool bpf_prog_array_compatible(struct bpf_array *array,
-			       const struct bpf_prog *fp)
+bool bpf_prog_map_compatible(struct bpf_map *map,
+			     const struct bpf_prog *fp)
 {
 	bool ret;
 
 	if (fp->kprobe_override)
 		return false;
 
-	spin_lock(&array->aux->owner.lock);
-
-	if (!array->aux->owner.type) {
+	spin_lock(&map->owner.lock);
+	if (!map->owner.type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.
 		 */
-		array->aux->owner.type  = fp->type;
-		array->aux->owner.jited = fp->jited;
+		map->owner.type  = fp->type;
+		map->owner.jited = fp->jited;
+		map->owner.xdp_has_frags = fp->aux->xdp_has_frags;
 		ret = true;
 	} else {
-		ret = array->aux->owner.type  == fp->type &&
-		      array->aux->owner.jited == fp->jited;
+		ret = map->owner.type  == fp->type &&
+		      map->owner.jited == fp->jited &&
+		      map->owner.xdp_has_frags == fp->aux->xdp_has_frags;
 	}
-	spin_unlock(&array->aux->owner.lock);
+	spin_unlock(&map->owner.lock);
+
 	return ret;
 }
 
@@ -1862,13 +1864,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
-		struct bpf_array *array;
 
-		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+		if (!map_type_contains_progs(map))
 			continue;
 
-		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp)) {
+		if (!bpf_prog_map_compatible(map, fp)) {
 			ret = -EINVAL;
 			goto out;
 		}
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index b3e6b9422238..650e5d21f90d 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -397,7 +397,8 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu,
+				      struct bpf_map *map, int fd)
 {
 	struct bpf_prog *prog;
 
@@ -405,7 +406,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP ||
+	    !bpf_prog_map_compatible(map, prog)) {
 		bpf_prog_put(prog);
 		return -EINVAL;
 	}
@@ -457,7 +459,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	rcpu->map_id = map->id;
 	rcpu->value.qsize  = value->qsize;
 
-	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
 		goto free_ptr_ring;
 
 	/* Setup kthread */
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index fe019dbdb3f0..038f6d7a83e4 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -858,7 +858,8 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 					     BPF_PROG_TYPE_XDP, false);
 		if (IS_ERR(prog))
 			goto err_put_dev;
-		if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+		if (prog->expected_attach_type != BPF_XDP_DEVMAP ||
+		    !bpf_prog_map_compatible(&dtab->map, prog))
 			goto err_put_prog;
 	}
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index fa4505f9b611..72ce1edde950 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -556,16 +556,14 @@ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
 
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
-	const struct bpf_map *map = filp->private_data;
-	const struct bpf_array *array;
+	struct bpf_map *map = filp->private_data;
 	u32 type = 0, jited = 0;
 
-	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
-		array = container_of(map, struct bpf_array, map);
-		spin_lock(&array->aux->owner.lock);
-		type  = array->aux->owner.type;
-		jited = array->aux->owner.jited;
-		spin_unlock(&array->aux->owner.lock);
+	if (map_type_contains_progs(map)) {
+		spin_lock(&map->owner.lock);
+		type  = map->owner.type;
+		jited = map->owner.jited;
+		spin_unlock(&map->owner.lock);
 	}
 
 	seq_printf(m,
@@ -874,6 +872,7 @@ static int map_create(union bpf_attr *attr)
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
 	mutex_init(&map->freeze_mutex);
+	spin_lock_init(&map->owner.lock);
 
 	map->spin_lock_off = -EINVAL;
 	map->timer_off = -EINVAL;
@@ -2217,7 +2216,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 				 BPF_F_ANY_ALIGNMENT |
 				 BPF_F_TEST_STATE_FREQ |
 				 BPF_F_SLEEPABLE |
-				 BPF_F_TEST_RND_HI32))
+				 BPF_F_TEST_RND_HI32 |
+				 BPF_F_XDP_HAS_FRAGS))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -2303,6 +2303,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 	prog->aux->dst_prog = dst_prog;
 	prog->aux->offload_requested = !!attr->prog_ifindex;
 	prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
+	prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
 
 	err = security_bpf_prog_alloc(prog->aux);
 	if (err)
@@ -3318,6 +3319,11 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_FLOW_DISSECTOR:
 	case BPF_SK_LOOKUP:
 		return netns_bpf_prog_query(attr, uattr);
+	case BPF_SK_SKB_STREAM_PARSER:
+	case BPF_SK_SKB_STREAM_VERDICT:
+	case BPF_SK_MSG_VERDICT:
+	case BPF_SK_SKB_VERDICT:
+		return sock_map_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a39eedecc93a..dcf065ec2774 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -452,7 +452,8 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
 {
 	return base_type(type) == PTR_TO_SOCKET ||
 		base_type(type) == PTR_TO_TCP_SOCK ||
-		base_type(type) == PTR_TO_MEM;
+		base_type(type) == PTR_TO_MEM ||
+		base_type(type) == PTR_TO_BTF_ID;
 }
 
 static bool type_is_rdonly_mem(u32 type)
@@ -1743,7 +1744,7 @@ find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset)
 }
 
 static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
-					 s16 offset, struct module **btf_modp)
+					 s16 offset)
 {
 	struct bpf_kfunc_btf kf_btf = { .offset = offset };
 	struct bpf_kfunc_btf_tab *tab;
@@ -1797,8 +1798,6 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
 		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
 		     kfunc_btf_cmp_by_off, NULL);
 	}
-	if (btf_modp)
-		*btf_modp = b->module;
 	return b->btf;
 }
 
@@ -1815,8 +1814,7 @@ void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab)
 }
 
 static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env,
-				       u32 func_id, s16 offset,
-				       struct module **btf_modp)
+				       u32 func_id, s16 offset)
 {
 	if (offset) {
 		if (offset < 0) {
@@ -1827,7 +1825,7 @@ static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env,
 			return ERR_PTR(-EINVAL);
 		}
 
-		return __find_kfunc_desc_btf(env, offset, btf_modp);
+		return __find_kfunc_desc_btf(env, offset);
 	}
 	return btf_vmlinux ?: ERR_PTR(-ENOENT);
 }
@@ -1890,7 +1888,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
 		prog_aux->kfunc_btf_tab = btf_tab;
 	}
 
-	desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL);
+	desc_btf = find_kfunc_desc_btf(env, func_id, offset);
 	if (IS_ERR(desc_btf)) {
 		verbose(env, "failed to find BTF for kernel function\n");
 		return PTR_ERR(desc_btf);
@@ -2351,7 +2349,7 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
 	if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
 		return NULL;
 
-	desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL);
+	desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off);
 	if (IS_ERR(desc_btf))
 		return "<error>";
 
@@ -3498,11 +3496,6 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 
 #define MAX_PACKET_OFF 0xffff
 
-static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
-{
-	return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
-}
-
 static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 				       const struct bpf_call_arg_meta *meta,
 				       enum bpf_access_type t)
@@ -4877,6 +4870,62 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 	}
 }
 
+static int check_mem_size_reg(struct bpf_verifier_env *env,
+			      struct bpf_reg_state *reg, u32 regno,
+			      bool zero_size_allowed,
+			      struct bpf_call_arg_meta *meta)
+{
+	int err;
+
+	/* This is used to refine r0 return value bounds for helpers
+	 * that enforce this value as an upper bound on return values.
+	 * See do_refine_retval_range() for helpers that can refine
+	 * the return value. C type of helper is u32 so we pull register
+	 * bound from umax_value however, if negative verifier errors
+	 * out. Only upper bounds can be learned because retval is an
+	 * int type and negative retvals are allowed.
+	 */
+	if (meta)
+		meta->msize_max_value = reg->umax_value;
+
+	/* The register is SCALAR_VALUE; the access check
+	 * happens using its boundaries.
+	 */
+	if (!tnum_is_const(reg->var_off))
+		/* For unprivileged variable accesses, disable raw
+		 * mode so that the program is required to
+		 * initialize all the memory that the helper could
+		 * just partially fill up.
+		 */
+		meta = NULL;
+
+	if (reg->smin_value < 0) {
+		verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
+			regno);
+		return -EACCES;
+	}
+
+	if (reg->umin_value == 0) {
+		err = check_helper_mem_access(env, regno - 1, 0,
+					      zero_size_allowed,
+					      meta);
+		if (err)
+			return err;
+	}
+
+	if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
+		verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
+			regno);
+		return -EACCES;
+	}
+	err = check_helper_mem_access(env, regno - 1,
+				      reg->umax_value,
+				      zero_size_allowed, meta);
+	if (!err)
+		err = mark_chain_precision(env, regno);
+	return err;
+}
+
 int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 		   u32 regno, u32 mem_size)
 {
@@ -4900,6 +4949,28 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
 	return check_helper_mem_access(env, regno, mem_size, true, NULL);
 }
 
+int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+			     u32 regno)
+{
+	struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1];
+	bool may_be_null = type_may_be_null(mem_reg->type);
+	struct bpf_reg_state saved_reg;
+	int err;
+
+	WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5);
+
+	if (may_be_null) {
+		saved_reg = *mem_reg;
+		mark_ptr_not_null_reg(mem_reg);
+	}
+
+	err = check_mem_size_reg(env, reg, regno, true, NULL);
+
+	if (may_be_null)
+		*mem_reg = saved_reg;
+	return err;
+}
+
 /* Implementation details:
  * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
  * Two bpf_map_lookups (even with the same key) will have different reg->id.
@@ -5439,51 +5510,7 @@ skip_type_check:
 	} else if (arg_type_is_mem_size(arg_type)) {
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
-		/* This is used to refine r0 return value bounds for helpers
-		 * that enforce this value as an upper bound on return values.
-		 * See do_refine_retval_range() for helpers that can refine
-		 * the return value. C type of helper is u32 so we pull register
-		 * bound from umax_value however, if negative verifier errors
-		 * out. Only upper bounds can be learned because retval is an
-		 * int type and negative retvals are allowed.
-		 */
-		meta->msize_max_value = reg->umax_value;
-
-		/* The register is SCALAR_VALUE; the access check
-		 * happens using its boundaries.
-		 */
-		if (!tnum_is_const(reg->var_off))
-			/* For unprivileged variable accesses, disable raw
-			 * mode so that the program is required to
-			 * initialize all the memory that the helper could
-			 * just partially fill up.
-			 */
-			meta = NULL;
-
-		if (reg->smin_value < 0) {
-			verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
-				regno);
-			return -EACCES;
-		}
-
-		if (reg->umin_value == 0) {
-			err = check_helper_mem_access(env, regno - 1, 0,
-						      zero_size_allowed,
-						      meta);
-			if (err)
-				return err;
-		}
-
-		if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
-			verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
-				regno);
-			return -EACCES;
-		}
-		err = check_helper_mem_access(env, regno - 1,
-					      reg->umax_value,
-					      zero_size_allowed, meta);
-		if (!err)
-			err = mark_chain_precision(env, regno);
+		err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta);
 	} else if (arg_type_is_alloc_size(arg_type)) {
 		if (!tnum_is_const(reg->var_off)) {
 			verbose(env, "R%d is not a known constant'\n",
@@ -6842,22 +6869,23 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno,
 	}
 }
 
-static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
+static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+			    int *insn_idx_p)
 {
 	const struct btf_type *t, *func, *func_proto, *ptr_type;
 	struct bpf_reg_state *regs = cur_regs(env);
 	const char *func_name, *ptr_type_name;
 	u32 i, nargs, func_id, ptr_type_id;
-	struct module *btf_mod = NULL;
+	int err, insn_idx = *insn_idx_p;
 	const struct btf_param *args;
 	struct btf *desc_btf;
-	int err;
+	bool acq;
 
 	/* skip for now, but return error when we find this in fixup_kfunc_call */
 	if (!insn->imm)
 		return 0;
 
-	desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod);
+	desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off);
 	if (IS_ERR(desc_btf))
 		return PTR_ERR(desc_btf);
 
@@ -6866,23 +6894,43 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	func_name = btf_name_by_offset(desc_btf, func->name_off);
 	func_proto = btf_type_by_id(desc_btf, func->type);
 
-	if (!env->ops->check_kfunc_call ||
-	    !env->ops->check_kfunc_call(func_id, btf_mod)) {
+	if (!btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+				      BTF_KFUNC_TYPE_CHECK, func_id)) {
 		verbose(env, "calling kernel function %s is not allowed\n",
 			func_name);
 		return -EACCES;
 	}
 
+	acq = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+					BTF_KFUNC_TYPE_ACQUIRE, func_id);
+
 	/* Check the arguments */
 	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs);
-	if (err)
+	if (err < 0)
 		return err;
+	/* In case of release function, we get register number of refcounted
+	 * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now
+	 */
+	if (err) {
+		err = release_reference(env, regs[err].ref_obj_id);
+		if (err) {
+			verbose(env, "kfunc %s#%d reference has not been acquired before\n",
+				func_name, func_id);
+			return err;
+		}
+	}
 
 	for (i = 0; i < CALLER_SAVED_REGS; i++)
 		mark_reg_not_init(env, regs, caller_saved[i]);
 
 	/* Check return type */
 	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
+
+	if (acq && !btf_type_is_ptr(t)) {
+		verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
+		return -EINVAL;
+	}
+
 	if (btf_type_is_scalar(t)) {
 		mark_reg_unknown(env, regs, BPF_REG_0);
 		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
@@ -6901,7 +6949,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		regs[BPF_REG_0].btf = desc_btf;
 		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
 		regs[BPF_REG_0].btf_id = ptr_type_id;
+		if (btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+					      BTF_KFUNC_TYPE_RET_NULL, func_id)) {
+			regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
+			/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
+			regs[BPF_REG_0].id = ++env->id_gen;
+		}
 		mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
+		if (acq) {
+			int id = acquire_reference_state(env, insn_idx);
+
+			if (id < 0)
+				return id;
+			regs[BPF_REG_0].id = id;
+			regs[BPF_REG_0].ref_obj_id = id;
+		}
 	} /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */
 
 	nargs = btf_type_vlen(func_proto);
@@ -11549,7 +11611,7 @@ static int do_check(struct bpf_verifier_env *env)
 				if (insn->src_reg == BPF_PSEUDO_CALL)
 					err = check_func_call(env, insn, &env->insn_idx);
 				else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
-					err = check_kfunc_call(env, insn);
+					err = check_kfunc_call(env, insn, &env->insn_idx);
 				else
 					err = check_helper_call(env, insn, &env->insn_idx);
 				if (err)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 21aa30644219..06a9e220069e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1562,6 +1562,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 
 extern const struct bpf_func_proto bpf_skb_output_proto;
 extern const struct bpf_func_proto bpf_xdp_output_proto;
+extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto;
 
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
@@ -1661,6 +1662,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_from_file_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_ptr_cookie_proto;
+	case BPF_FUNC_xdp_get_buff_len:
+		return &bpf_xdp_get_buff_len_trace_proto;
 #endif
 	case BPF_FUNC_seq_printf:
 		return prog->expected_attach_type == BPF_TRACE_ITER ?