1 files changed, 749 insertions, 564 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eba603cec2c5..f7dd8af06413 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -19,6 +19,7 @@
 #include <linux/bpf_verifier.h>
 #include <linux/btf.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf_lsm.h>
 #include <linux/skmsg.h>
 #include <linux/perf_event.h>
 #include <linux/bsearch.h>
@@ -199,11 +200,13 @@ DEFINE_IDR(btf_idr);
 DEFINE_SPINLOCK(btf_idr_lock);
 
 enum btf_kfunc_hook {
+	BTF_KFUNC_HOOK_COMMON,
 	BTF_KFUNC_HOOK_XDP,
 	BTF_KFUNC_HOOK_TC,
 	BTF_KFUNC_HOOK_STRUCT_OPS,
 	BTF_KFUNC_HOOK_TRACING,
 	BTF_KFUNC_HOOK_SYSCALL,
+	BTF_KFUNC_HOOK_FMODRET,
 	BTF_KFUNC_HOOK_MAX,
 };
 
@@ -237,6 +240,7 @@ struct btf {
 	struct rcu_head rcu;
 	struct btf_kfunc_set_tab *kfunc_set_tab;
 	struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab;
+	struct btf_struct_metas *struct_meta_tab;
 
 	/* split BTF support */
 	struct btf *base_btf;
@@ -477,16 +481,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t)
 	return !t || btf_type_nosize(t);
 }
 
-static bool __btf_type_is_struct(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT;
-}
-
-static bool btf_type_is_array(const struct btf_type *t)
-{
-	return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY;
-}
-
 static bool btf_type_is_datasec(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
@@ -1642,8 +1636,30 @@ static void btf_free_dtor_kfunc_tab(struct btf *btf)
 	btf->dtor_kfunc_tab = NULL;
 }
 
+static void btf_struct_metas_free(struct btf_struct_metas *tab)
+{
+	int i;
+
+	if (!tab)
+		return;
+	for (i = 0; i < tab->cnt; i++) {
+		btf_record_free(tab->types[i].record);
+		kfree(tab->types[i].field_offs);
+	}
+	kfree(tab);
+}
+
+static void btf_free_struct_meta_tab(struct btf *btf)
+{
+	struct btf_struct_metas *tab = btf->struct_meta_tab;
+
+	btf_struct_metas_free(tab);
+	btf->struct_meta_tab = NULL;
+}
+
 static void btf_free(struct btf *btf)
 {
+	btf_free_struct_meta_tab(btf);
 	btf_free_dtor_kfunc_tab(btf);
 	btf_free_kfunc_set_tab(btf);
 	kvfree(btf->types);
@@ -3191,7 +3207,7 @@ static void btf_struct_log(struct btf_verifier_env *env,
 	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
 }
 
-enum btf_field_type {
+enum btf_field_info_type {
 	BTF_FIELD_SPIN_LOCK,
 	BTF_FIELD_TIMER,
 	BTF_FIELD_KPTR,
@@ -3203,18 +3219,28 @@ enum {
 };
 
 struct btf_field_info {
-	u32 type_id;
+	enum btf_field_type type;
 	u32 off;
-	enum bpf_kptr_type type;
+	union {
+		struct {
+			u32 type_id;
+		} kptr;
+		struct {
+			const char *node_name;
+			u32 value_btf_id;
+		} list_head;
+	};
 };
 
 static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
-			   u32 off, int sz, struct btf_field_info *info)
+			   u32 off, int sz, enum btf_field_type field_type,
+			   struct btf_field_info *info)
 {
 	if (!__btf_type_is_struct(t))
 		return BTF_FIELD_IGNORE;
 	if (t->size != sz)
 		return BTF_FIELD_IGNORE;
+	info->type = field_type;
 	info->off = off;
 	return BTF_FIELD_FOUND;
 }
@@ -3222,9 +3248,12 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t,
 static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 			 u32 off, int sz, struct btf_field_info *info)
 {
-	enum bpf_kptr_type type;
+	enum btf_field_type type;
 	u32 res_id;
 
+	/* Permit modifiers on the pointer itself */
+	if (btf_type_is_volatile(t))
+		t = btf_type_by_id(btf, t->type);
 	/* For PTR, sz is always == 8 */
 	if (!btf_type_is_ptr(t))
 		return BTF_FIELD_IGNORE;
@@ -3248,28 +3277,135 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
 	if (!__btf_type_is_struct(t))
 		return -EINVAL;
 
-	info->type_id = res_id;
-	info->off = off;
 	info->type = type;
+	info->off = off;
+	info->kptr.type_id = res_id;
+	return BTF_FIELD_FOUND;
+}
+
+static const char *btf_find_decl_tag_value(const struct btf *btf,
+					   const struct btf_type *pt,
+					   int comp_idx, const char *tag_key)
+{
+	int i;
+
+	for (i = 1; i < btf_nr_types(btf); i++) {
+		const struct btf_type *t = btf_type_by_id(btf, i);
+		int len = strlen(tag_key);
+
+		if (!btf_type_is_decl_tag(t))
+			continue;
+		if (pt != btf_type_by_id(btf, t->type) ||
+		    btf_type_decl_tag(t)->component_idx != comp_idx)
+			continue;
+		if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len))
+			continue;
+		return __btf_name_by_offset(btf, t->name_off) + len;
+	}
+	return NULL;
+}
+
+static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt,
+			      const struct btf_type *t, int comp_idx,
+			      u32 off, int sz, struct btf_field_info *info)
+{
+	const char *value_type;
+	const char *list_node;
+	s32 id;
+
+	if (!__btf_type_is_struct(t))
+		return BTF_FIELD_IGNORE;
+	if (t->size != sz)
+		return BTF_FIELD_IGNORE;
+	value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:");
+	if (!value_type)
+		return -EINVAL;
+	list_node = strstr(value_type, ":");
+	if (!list_node)
+		return -EINVAL;
+	value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN);
+	if (!value_type)
+		return -ENOMEM;
+	id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT);
+	kfree(value_type);
+	if (id < 0)
+		return id;
+	list_node++;
+	if (str_is_empty(list_node))
+		return -EINVAL;
+	info->type = BPF_LIST_HEAD;
+	info->off = off;
+	info->list_head.value_btf_id = id;
+	info->list_head.node_name = list_node;
 	return BTF_FIELD_FOUND;
 }
 
-static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t,
-				 const char *name, int sz, int align,
-				 enum btf_field_type field_type,
+static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask,
+			      int *align, int *sz)
+{
+	int type = 0;
+
+	if (field_mask & BPF_SPIN_LOCK) {
+		if (!strcmp(name, "bpf_spin_lock")) {
+			if (*seen_mask & BPF_SPIN_LOCK)
+				return -E2BIG;
+			*seen_mask |= BPF_SPIN_LOCK;
+			type = BPF_SPIN_LOCK;
+			goto end;
+		}
+	}
+	if (field_mask & BPF_TIMER) {
+		if (!strcmp(name, "bpf_timer")) {
+			if (*seen_mask & BPF_TIMER)
+				return -E2BIG;
+			*seen_mask |= BPF_TIMER;
+			type = BPF_TIMER;
+			goto end;
+		}
+	}
+	if (field_mask & BPF_LIST_HEAD) {
+		if (!strcmp(name, "bpf_list_head")) {
+			type = BPF_LIST_HEAD;
+			goto end;
+		}
+	}
+	if (field_mask & BPF_LIST_NODE) {
+		if (!strcmp(name, "bpf_list_node")) {
+			type = BPF_LIST_NODE;
+			goto end;
+		}
+	}
+	/* Only return BPF_KPTR when all other types with matchable names fail */
+	if (field_mask & BPF_KPTR) {
+		type = BPF_KPTR_REF;
+		goto end;
+	}
+	return 0;
+end:
+	*sz = btf_field_type_size(type);
+	*align = btf_field_type_align(type);
+	return type;
+}
+
+static int btf_find_struct_field(const struct btf *btf,
+				 const struct btf_type *t, u32 field_mask,
 				 struct btf_field_info *info, int info_cnt)
 {
+	int ret, idx = 0, align, sz, field_type;
 	const struct btf_member *member;
 	struct btf_field_info tmp;
-	int ret, idx = 0;
-	u32 i, off;
+	u32 i, off, seen_mask = 0;
 
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								    member->type);
 
-		if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name))
+		field_type = btf_get_field_type(__btf_name_by_offset(btf, member_type->name_off),
+						field_mask, &seen_mask, &align, &sz);
+		if (field_type == 0)
 			continue;
+		if (field_type < 0)
+			return field_type;
 
 		off = __btf_member_bit_offset(t, member);
 		if (off % 8)
@@ -3277,22 +3413,30 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 			return -EINVAL;
 		off /= 8;
 		if (off % align)
-			return -EINVAL;
+			continue;
 
 		switch (field_type) {
-		case BTF_FIELD_SPIN_LOCK:
-		case BTF_FIELD_TIMER:
-			ret = btf_find_struct(btf, member_type, off, sz,
+		case BPF_SPIN_LOCK:
+		case BPF_TIMER:
+		case BPF_LIST_NODE:
+			ret = btf_find_struct(btf, member_type, off, sz, field_type,
 					      idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
 				return ret;
 			break;
-		case BTF_FIELD_KPTR:
+		case BPF_KPTR_UNREF:
+		case BPF_KPTR_REF:
 			ret = btf_find_kptr(btf, member_type, off, sz,
 					    idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
 				return ret;
 			break;
+		case BPF_LIST_HEAD:
+			ret = btf_find_list_head(btf, t, member_type, i, off, sz,
+						 idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
@@ -3307,42 +3451,53 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t
 }
 
 static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
-				const char *name, int sz, int align,
-				enum btf_field_type field_type,
-				struct btf_field_info *info, int info_cnt)
+				u32 field_mask, struct btf_field_info *info,
+				int info_cnt)
 {
+	int ret, idx = 0, align, sz, field_type;
 	const struct btf_var_secinfo *vsi;
 	struct btf_field_info tmp;
-	int ret, idx = 0;
-	u32 i, off;
+	u32 i, off, seen_mask = 0;
 
 	for_each_vsi(i, t, vsi) {
 		const struct btf_type *var = btf_type_by_id(btf, vsi->type);
 		const struct btf_type *var_type = btf_type_by_id(btf, var->type);
 
-		off = vsi->offset;
-
-		if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name))
+		field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off),
+						field_mask, &seen_mask, &align, &sz);
+		if (field_type == 0)
 			continue;
+		if (field_type < 0)
+			return field_type;
+
+		off = vsi->offset;
 		if (vsi->size != sz)
 			continue;
 		if (off % align)
-			return -EINVAL;
+			continue;
 
 		switch (field_type) {
-		case BTF_FIELD_SPIN_LOCK:
-		case BTF_FIELD_TIMER:
-			ret = btf_find_struct(btf, var_type, off, sz,
+		case BPF_SPIN_LOCK:
+		case BPF_TIMER:
+		case BPF_LIST_NODE:
+			ret = btf_find_struct(btf, var_type, off, sz, field_type,
 					      idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
 				return ret;
 			break;
-		case BTF_FIELD_KPTR:
+		case BPF_KPTR_UNREF:
+		case BPF_KPTR_REF:
 			ret = btf_find_kptr(btf, var_type, off, sz,
 					    idx < info_cnt ? &info[idx] : &tmp);
 			if (ret < 0)
 				return ret;
 			break;
+		case BPF_LIST_HEAD:
+			ret = btf_find_list_head(btf, var, var_type, -1, off, sz,
+						 idx < info_cnt ? &info[idx] : &tmp);
+			if (ret < 0)
+				return ret;
+			break;
 		default:
 			return -EFAULT;
 		}
@@ -3357,169 +3512,327 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
 }
 
 static int btf_find_field(const struct btf *btf, const struct btf_type *t,
-			  enum btf_field_type field_type,
-			  struct btf_field_info *info, int info_cnt)
+			  u32 field_mask, struct btf_field_info *info,
+			  int info_cnt)
 {
-	const char *name;
-	int sz, align;
-
-	switch (field_type) {
-	case BTF_FIELD_SPIN_LOCK:
-		name = "bpf_spin_lock";
-		sz = sizeof(struct bpf_spin_lock);
-		align = __alignof__(struct bpf_spin_lock);
-		break;
-	case BTF_FIELD_TIMER:
-		name = "bpf_timer";
-		sz = sizeof(struct bpf_timer);
-		align = __alignof__(struct bpf_timer);
-		break;
-	case BTF_FIELD_KPTR:
-		name = NULL;
-		sz = sizeof(u64);
-		align = 8;
-		break;
-	default:
-		return -EFAULT;
-	}
-
 	if (__btf_type_is_struct(t))
-		return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt);
+		return btf_find_struct_field(btf, t, field_mask, info, info_cnt);
 	else if (btf_type_is_datasec(t))
-		return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt);
+		return btf_find_datasec_var(btf, t, field_mask, info, info_cnt);
 	return -EINVAL;
 }
 
-/* find 'struct bpf_spin_lock' in map value.
- * return >= 0 offset if found
- * and < 0 in case of error
- */
-int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t)
+static int btf_parse_kptr(const struct btf *btf, struct btf_field *field,
+			  struct btf_field_info *info)
 {
-	struct btf_field_info info;
+	struct module *mod = NULL;
+	const struct btf_type *t;
+	struct btf *kernel_btf;
 	int ret;
+	s32 id;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1);
-	if (ret < 0)
-		return ret;
-	if (!ret)
-		return -ENOENT;
-	return info.off;
+	/* Find type in map BTF, and use it to look up the matching type
+	 * in vmlinux or module BTFs, by name and kind.
+	 */
+	t = btf_type_by_id(btf, info->kptr.type_id);
+	id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info),
+			     &kernel_btf);
+	if (id < 0)
+		return id;
+
+	/* Find and stash the function pointer for the destruction function that
+	 * needs to be eventually invoked from the map free path.
+	 */
+	if (info->type == BPF_KPTR_REF) {
+		const struct btf_type *dtor_func;
+		const char *dtor_func_name;
+		unsigned long addr;
+		s32 dtor_btf_id;
+
+		/* This call also serves as a whitelist of allowed objects that
+		 * can be used as a referenced pointer and be stored in a map at
+		 * the same time.
+		 */
+		dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id);
+		if (dtor_btf_id < 0) {
+			ret = dtor_btf_id;
+			goto end_btf;
+		}
+
+		dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id);
+		if (!dtor_func) {
+			ret = -ENOENT;
+			goto end_btf;
+		}
+
+		if (btf_is_module(kernel_btf)) {
+			mod = btf_try_get_module(kernel_btf);
+			if (!mod) {
+				ret = -ENXIO;
+				goto end_btf;
+			}
+		}
+
+		/* We already verified dtor_func to be btf_type_is_func
+		 * in register_btf_id_dtor_kfuncs.
+		 */
+		dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off);
+		addr = kallsyms_lookup_name(dtor_func_name);
+		if (!addr) {
+			ret = -EINVAL;
+			goto end_mod;
+		}
+		field->kptr.dtor = (void *)addr;
+	}
+
+	field->kptr.btf_id = id;
+	field->kptr.btf = kernel_btf;
+	field->kptr.module = mod;
+	return 0;
+end_mod:
+	module_put(mod);
+end_btf:
+	btf_put(kernel_btf);
+	return ret;
 }
 
-int btf_find_timer(const struct btf *btf, const struct btf_type *t)
+static int btf_parse_list_head(const struct btf *btf, struct btf_field *field,
+			       struct btf_field_info *info)
 {
-	struct btf_field_info info;
-	int ret;
+	const struct btf_type *t, *n = NULL;
+	const struct btf_member *member;
+	u32 offset;
+	int i;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1);
-	if (ret < 0)
-		return ret;
-	if (!ret)
+	t = btf_type_by_id(btf, info->list_head.value_btf_id);
+	/* We've already checked that value_btf_id is a struct type. We
+	 * just need to figure out the offset of the list_node, and
+	 * verify its type.
+	 */
+	for_each_member(i, t, member) {
+		if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off)))
+			continue;
+		/* Invalid BTF, two members with same name */
+		if (n)
+			return -EINVAL;
+		n = btf_type_by_id(btf, member->type);
+		if (!__btf_type_is_struct(n))
+			return -EINVAL;
+		if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off)))
+			return -EINVAL;
+		offset = __btf_member_bit_offset(n, member);
+		if (offset % 8)
+			return -EINVAL;
+		offset /= 8;
+		if (offset % __alignof__(struct bpf_list_node))
+			return -EINVAL;
+
+		field->list_head.btf = (struct btf *)btf;
+		field->list_head.value_btf_id = info->list_head.value_btf_id;
+		field->list_head.node_offset = offset;
+	}
+	if (!n)
 		return -ENOENT;
-	return info.off;
+	return 0;
 }
 
-struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf,
-					  const struct btf_type *t)
+struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t,
+				    u32 field_mask, u32 value_size)
 {
-	struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX];
-	struct bpf_map_value_off *tab;
-	struct btf *kernel_btf = NULL;
-	struct module *mod = NULL;
-	int ret, i, nr_off;
+	struct btf_field_info info_arr[BTF_FIELDS_MAX];
+	struct btf_record *rec;
+	u32 next_off = 0;
+	int ret, i, cnt;
 
-	ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr));
+	ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr));
 	if (ret < 0)
 		return ERR_PTR(ret);
 	if (!ret)
 		return NULL;
 
-	nr_off = ret;
-	tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN);
-	if (!tab)
+	cnt = ret;
+	/* This needs to be kzalloc to zero out padding and unused fields, see
+	 * comment in btf_record_equal.
+	 */
+	rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN);
+	if (!rec)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < nr_off; i++) {
-		const struct btf_type *t;
-		s32 id;
+	rec->spin_lock_off = -EINVAL;
+	rec->timer_off = -EINVAL;
+	for (i = 0; i < cnt; i++) {
+		if (info_arr[i].off + btf_field_type_size(info_arr[i].type) > value_size) {
+			WARN_ONCE(1, "verifier bug off %d size %d", info_arr[i].off, value_size);
+			ret = -EFAULT;
+			goto end;
+		}
+		if (info_arr[i].off < next_off) {
+			ret = -EEXIST;
+			goto end;
+		}
+		next_off = info_arr[i].off + btf_field_type_size(info_arr[i].type);
 
-		/* Find type in map BTF, and use it to look up the matching type
-		 * in vmlinux or module BTFs, by name and kind.
-		 */
-		t = btf_type_by_id(btf, info_arr[i].type_id);
-		id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info),
-				     &kernel_btf);
-		if (id < 0) {
-			ret = id;
+		rec->field_mask |= info_arr[i].type;
+		rec->fields[i].offset = info_arr[i].off;
+		rec->fields[i].type = info_arr[i].type;
+
+		switch (info_arr[i].type) {
+		case BPF_SPIN_LOCK:
+			WARN_ON_ONCE(rec->spin_lock_off >= 0);
+			/* Cache offset for faster lookup at runtime */
+			rec->spin_lock_off = rec->fields[i].offset;
+			break;
+		case BPF_TIMER:
+			WARN_ON_ONCE(rec->timer_off >= 0);
+			/* Cache offset for faster lookup at runtime */
+			rec->timer_off = rec->fields[i].offset;
+			break;
+		case BPF_KPTR_UNREF:
+		case BPF_KPTR_REF:
+			ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]);
+			if (ret < 0)
+				goto end;
+			break;
+		case BPF_LIST_HEAD:
+			ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]);
+			if (ret < 0)
+				goto end;
+			break;
+		case BPF_LIST_NODE:
+			break;
+		default:
+			ret = -EFAULT;
 			goto end;
 		}
+		rec->cnt++;
+	}
 
-		/* Find and stash the function pointer for the destruction function that
-		 * needs to be eventually invoked from the map free path.
-		 */
-		if (info_arr[i].type == BPF_KPTR_REF) {
-			const struct btf_type *dtor_func;
-			const char *dtor_func_name;
-			unsigned long addr;
-			s32 dtor_btf_id;
-
-			/* This call also serves as a whitelist of allowed objects that
-			 * can be used as a referenced pointer and be stored in a map at
-			 * the same time.
-			 */
-			dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id);
-			if (dtor_btf_id < 0) {
-				ret = dtor_btf_id;
-				goto end_btf;
-			}
+	/* bpf_list_head requires bpf_spin_lock */
+	if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) {
+		ret = -EINVAL;
+		goto end;
+	}
 
-			dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id);
-			if (!dtor_func) {
-				ret = -ENOENT;
-				goto end_btf;
-			}
+	return rec;
+end:
+	btf_record_free(rec);
+	return ERR_PTR(ret);
+}
 
-			if (btf_is_module(kernel_btf)) {
-				mod = btf_try_get_module(kernel_btf);
-				if (!mod) {
-					ret = -ENXIO;
-					goto end_btf;
-				}
-			}
+int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec)
+{
+	int i;
 
-			/* We already verified dtor_func to be btf_type_is_func
-			 * in register_btf_id_dtor_kfuncs.
-			 */
-			dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off);
-			addr = kallsyms_lookup_name(dtor_func_name);
-			if (!addr) {
-				ret = -EINVAL;
-				goto end_mod;
-			}
-			tab->off[i].kptr.dtor = (void *)addr;
-		}
+	/* There are two owning types, kptr_ref and bpf_list_head. The former
+	 * only supports storing kernel types, which can never store references
+	 * to program allocated local types, atleast not yet. Hence we only need
+	 * to ensure that bpf_list_head ownership does not form cycles.
+	 */
+	if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD))
+		return 0;
+	for (i = 0; i < rec->cnt; i++) {
+		struct btf_struct_meta *meta;
+		u32 btf_id;
+
+		if (!(rec->fields[i].type & BPF_LIST_HEAD))
+			continue;
+		btf_id = rec->fields[i].list_head.value_btf_id;
+		meta = btf_find_struct_meta(btf, btf_id);
+		if (!meta)
+			return -EFAULT;
+		rec->fields[i].list_head.value_rec = meta->record;
 
-		tab->off[i].offset = info_arr[i].off;
-		tab->off[i].type = info_arr[i].type;
-		tab->off[i].kptr.btf_id = id;
-		tab->off[i].kptr.btf = kernel_btf;
-		tab->off[i].kptr.module = mod;
+		if (!(rec->field_mask & BPF_LIST_NODE))
+			continue;
+
+		/* We need to ensure ownership acyclicity among all types. The
+		 * proper way to do it would be to topologically sort all BTF
+		 * IDs based on the ownership edges, since there can be multiple
+		 * bpf_list_head in a type. Instead, we use the following
+		 * reasoning:
+		 *
+		 * - A type can only be owned by another type in user BTF if it
+		 *   has a bpf_list_node.
+		 * - A type can only _own_ another type in user BTF if it has a
+		 *   bpf_list_head.
+		 *
+		 * We ensure that if a type has both bpf_list_head and
+		 * bpf_list_node, its element types cannot be owning types.
+		 *
+		 * To ensure acyclicity:
+		 *
+		 * When A only has bpf_list_head, ownership chain can be:
+		 *	A -> B -> C
+		 * Where:
+		 * - B has both bpf_list_head and bpf_list_node.
+		 * - C only has bpf_list_node.
+		 *
+		 * When A has both bpf_list_head and bpf_list_node, some other
+		 * type already owns it in the BTF domain, hence it can not own
+		 * another owning type through any of the bpf_list_head edges.
+		 *	A -> B
+		 * Where:
+		 * - B only has bpf_list_node.
+		 */
+		if (meta->record->field_mask & BPF_LIST_HEAD)
+			return -ELOOP;
 	}
-	tab->nr_off = nr_off;
-	return tab;
-end_mod:
-	module_put(mod);
-end_btf:
-	btf_put(kernel_btf);
-end:
-	while (i--) {
-		btf_put(tab->off[i].kptr.btf);
-		if (tab->off[i].kptr.module)
-			module_put(tab->off[i].kptr.module);
+	return 0;
+}
+
+static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv)
+{
+	const u32 a = *(const u32 *)_a;
+	const u32 b = *(const u32 *)_b;
+
+	if (a < b)
+		return -1;
+	else if (a > b)
+		return 1;
+	return 0;
+}
+
+static void btf_field_offs_swap(void *_a, void *_b, int size, const void *priv)
+{
+	struct btf_field_offs *foffs = (void *)priv;
+	u32 *off_base = foffs->field_off;
+	u32 *a = _a, *b = _b;
+	u8 *sz_a, *sz_b;
+
+	sz_a = foffs->field_sz + (a - off_base);
+	sz_b = foffs->field_sz + (b - off_base);
+
+	swap(*a, *b);
+	swap(*sz_a, *sz_b);
+}
+
+struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec)
+{
+	struct btf_field_offs *foffs;
+	u32 i, *off;
+	u8 *sz;
+
+	BUILD_BUG_ON(ARRAY_SIZE(foffs->field_off) != ARRAY_SIZE(foffs->field_sz));
+	if (IS_ERR_OR_NULL(rec))
+		return NULL;
+
+	foffs = kzalloc(sizeof(*foffs), GFP_KERNEL | __GFP_NOWARN);
+	if (!foffs)
+		return ERR_PTR(-ENOMEM);
+
+	off = foffs->field_off;
+	sz = foffs->field_sz;
+	for (i = 0; i < rec->cnt; i++) {
+		off[i] = rec->fields[i].offset;
+		sz[i] = btf_field_type_size(rec->fields[i].type);
 	}
-	kfree(tab);
-	return ERR_PTR(ret);
+	foffs->cnt = rec->cnt;
+
+	if (foffs->cnt == 1)
+		return foffs;
+	sort_r(foffs->field_off, foffs->cnt, sizeof(foffs->field_off[0]),
+	       btf_field_offs_cmp, btf_field_offs_swap, foffs);
+	return foffs;
 }
 
 static void __btf_struct_show(const struct btf *btf, const struct btf_type *t,
@@ -4436,6 +4749,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
+		if (btf_type_is_resolve_source_only(ret_type)) {
+			btf_verifier_log_type(env, t, "Invalid return type");
+			return -EINVAL;
+		}
+
 		if (btf_type_needs_resolve(ret_type) &&
 		    !env_type_is_resolved(env, ret_type_id)) {
 			err = btf_resolve(env, ret_type, ret_type_id);
@@ -4463,7 +4781,6 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 		nr_args--;
 	}
 
-	err = 0;
 	for (i = 0; i < nr_args; i++) {
 		const struct btf_type *arg_type;
 		u32 arg_type_id;
@@ -4472,8 +4789,12 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 		arg_type = btf_type_by_id(btf, arg_type_id);
 		if (!arg_type) {
 			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
-			err = -EINVAL;
-			break;
+			return -EINVAL;
+		}
+
+		if (btf_type_is_resolve_source_only(arg_type)) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			return -EINVAL;
 		}
 
 		if (args[i].name_off &&
@@ -4481,25 +4802,23 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 		     !btf_name_valid_identifier(btf, args[i].name_off))) {
 			btf_verifier_log_type(env, t,
 					      "Invalid arg#%u", i + 1);
-			err = -EINVAL;
-			break;
+			return -EINVAL;
 		}
 
 		if (btf_type_needs_resolve(arg_type) &&
 		    !env_type_is_resolved(env, arg_type_id)) {
 			err = btf_resolve(env, arg_type, arg_type_id);
 			if (err)
-				break;
+				return err;
 		}
 
 		if (!btf_type_id_size(btf, &arg_type_id, NULL)) {
 			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
-			err = -EINVAL;
-			break;
+			return -EINVAL;
 		}
 	}
 
-	return err;
+	return 0;
 }
 
 static int btf_func_check(struct btf_verifier_env *env,
@@ -4913,6 +5232,119 @@ static int btf_parse_hdr(struct btf_verifier_env *env)
 	return btf_check_sec_info(env, btf_data_size);
 }
 
+static const char *alloc_obj_fields[] = {
+	"bpf_spin_lock",
+	"bpf_list_head",
+	"bpf_list_node",
+};
+
+static struct btf_struct_metas *
+btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf)
+{
+	union {
+		struct btf_id_set set;
+		struct {
+			u32 _cnt;
+			u32 _ids[ARRAY_SIZE(alloc_obj_fields)];
+		} _arr;
+	} aof;
+	struct btf_struct_metas *tab = NULL;
+	int i, n, id, ret;
+
+	BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0);
+	BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32));
+
+	memset(&aof, 0, sizeof(aof));
+	for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) {
+		/* Try to find whether this special type exists in user BTF, and
+		 * if so remember its ID so we can easily find it among members
+		 * of structs that we iterate in the next loop.
+		 */
+		id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT);
+		if (id < 0)
+			continue;
+		aof.set.ids[aof.set.cnt++] = id;
+	}
+
+	if (!aof.set.cnt)
+		return NULL;
+	sort(&aof.set.ids, aof.set.cnt, sizeof(aof.set.ids[0]), btf_id_cmp_func, NULL);
+
+	n = btf_nr_types(btf);
+	for (i = 1; i < n; i++) {
+		struct btf_struct_metas *new_tab;
+		const struct btf_member *member;
+		struct btf_field_offs *foffs;
+		struct btf_struct_meta *type;
+		struct btf_record *record;
+		const struct btf_type *t;
+		int j, tab_cnt;
+
+		t = btf_type_by_id(btf, i);
+		if (!t) {
+			ret = -EINVAL;
+			goto free;
+		}
+		if (!__btf_type_is_struct(t))
+			continue;
+
+		cond_resched();
+
+		for_each_member(j, t, member) {
+			if (btf_id_set_contains(&aof.set, member->type))
+				goto parse;
+		}
+		continue;
+	parse:
+		tab_cnt = tab ? tab->cnt : 0;
+		new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]),
+				   GFP_KERNEL | __GFP_NOWARN);
+		if (!new_tab) {
+			ret = -ENOMEM;
+			goto free;
+		}
+		if (!tab)
+			new_tab->cnt = 0;
+		tab = new_tab;
+
+		type = &tab->types[tab->cnt];
+		type->btf_id = i;
+		record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size);
+		/* The record cannot be unset, treat it as an error if so */
+		if (IS_ERR_OR_NULL(record)) {
+			ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT;
+			goto free;
+		}
+		foffs = btf_parse_field_offs(record);
+		/* We need the field_offs to be valid for a valid record,
+		 * either both should be set or both should be unset.
+		 */
+		if (IS_ERR_OR_NULL(foffs)) {
+			btf_record_free(record);
+			ret = -EFAULT;
+			goto free;
+		}
+		type->record = record;
+		type->field_offs = foffs;
+		tab->cnt++;
+	}
+	return tab;
+free:
+	btf_struct_metas_free(tab);
+	return ERR_PTR(ret);
+}
+
+struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id)
+{
+	struct btf_struct_metas *tab;
+
+	BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0);
+	tab = btf->struct_meta_tab;
+	if (!tab)
+		return NULL;
+	return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func);
+}
+
 static int btf_check_type_tags(struct btf_verifier_env *env,
 			       struct btf *btf, int start_id)
 {
@@ -4963,6 +5395,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env,
 static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 			     u32 log_level, char __user *log_ubuf, u32 log_size)
 {
+	struct btf_struct_metas *struct_meta_tab;
 	struct btf_verifier_env *env = NULL;
 	struct bpf_verifier_log *log;
 	struct btf *btf = NULL;
@@ -5031,15 +5464,34 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size,
 	if (err)
 		goto errout;
 
+	struct_meta_tab = btf_parse_struct_metas(log, btf);
+	if (IS_ERR(struct_meta_tab)) {
+		err = PTR_ERR(struct_meta_tab);
+		goto errout;
+	}
+	btf->struct_meta_tab = struct_meta_tab;
+
+	if (struct_meta_tab) {
+		int i;
+
+		for (i = 0; i < struct_meta_tab->cnt; i++) {
+			err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record);
+			if (err < 0)
+				goto errout_meta;
+		}
+	}
+
 	if (log->level && bpf_verifier_log_full(log)) {
 		err = -ENOSPC;
-		goto errout;
+		goto errout_meta;
 	}
 
 	btf_verifier_env_free(env);
 	refcount_set(&btf->refcnt, 1);
 	return btf;
 
+errout_meta:
+	btf_free_struct_meta_tab(btf);
 errout:
 	btf_verifier_env_free(env);
 	if (btf)
@@ -5081,7 +5533,7 @@ static u8 bpf_ctx_convert_map[] = {
 #undef BPF_MAP_TYPE
 #undef BPF_LINK_TYPE
 
-static const struct btf_member *
+const struct btf_member *
 btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
 		      const struct btf_type *t, enum bpf_prog_type prog_type,
 		      int arg)
@@ -5154,6 +5606,26 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log,
 	return kern_ctx_type->type;
 }
 
+int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type)
+{
+	const struct btf_member *kctx_member;
+	const struct btf_type *conv_struct;
+	const struct btf_type *kctx_type;
+	u32 kctx_type_id;
+
+	conv_struct = bpf_ctx_convert.t;
+	/* get member for kernel ctx type */
+	kctx_member = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1;
+	kctx_type_id = kctx_member->type;
+	kctx_type = btf_type_by_id(btf_vmlinux, kctx_type_id);
+	if (!btf_type_is_struct(kctx_type)) {
+		bpf_log(log, "kern ctx type id %u is not a struct\n", kctx_type_id);
+		return -EINVAL;
+	}
+
+	return kctx_type_id;
+}
+
 BTF_ID_LIST(bpf_ctx_convert_btf_id)
 BTF_ID(struct, bpf_ctx_convert)
 
@@ -5351,6 +5823,22 @@ static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto,
 	return nr_args + 1;
 }
 
+static bool prog_args_trusted(const struct bpf_prog *prog)
+{
+	enum bpf_attach_type atype = prog->expected_attach_type;
+
+	switch (prog->type) {
+	case BPF_PROG_TYPE_TRACING:
+		return atype == BPF_TRACE_RAW_TP || atype == BPF_TRACE_ITER;
+	case BPF_PROG_TYPE_LSM:
+		return bpf_lsm_is_trusted(prog);
+	case BPF_PROG_TYPE_STRUCT_OPS:
+		return true;
+	default:
+		return false;
+	}
+}
+
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
@@ -5494,6 +5982,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	}
 
 	info->reg_type = PTR_TO_BTF_ID;
+	if (prog_args_trusted(prog))
+		info->reg_type |= PTR_TRUSTED;
+
 	if (tgt_prog) {
 		enum bpf_prog_type tgt_type;
 
@@ -5760,6 +6251,9 @@ error:
 				/* check __percpu tag */
 				if (strcmp(tag_value, "percpu") == 0)
 					tmp_flag = MEM_PERCPU;
+				/* check __rcu tag */
+				if (strcmp(tag_value, "rcu") == 0)
+					tmp_flag = MEM_RCU;
 			}
 
 			stype = btf_type_skip_modifiers(btf, mtype->type, &id);
@@ -5789,20 +6283,50 @@ error:
 	return -EINVAL;
 }
 
-int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, int off, int size,
-		      enum bpf_access_type atype __maybe_unused,
+int btf_str