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

Andrii Nakryiko says:

====================
bpf-next 2022-08-17

We've added 45 non-merge commits during the last 14 day(s) which contain
a total of 61 files changed, 986 insertions(+), 372 deletions(-).

The main changes are:

1) New bpf_ktime_get_tai_ns() BPF helper to access CLOCK_TAI, from Kurt
   Kanzenbach and Jesper Dangaard Brouer.

2) Few clean ups and improvements for libbpf 1.0, from Andrii Nakryiko.

3) Expose crash_kexec() as kfunc for BPF programs, from Artem Savkov.

4) Add ability to define sleepable-only kfuncs, from Benjamin Tissoires.

5) Teach libbpf's bpf_prog_load() and bpf_map_create() to gracefully handle
   unsupported names on old kernels, from Hangbin Liu.

6) Allow opting out from auto-attaching BPF programs by libbpf's BPF skeleton,
   from Hao Luo.

7) Relax libbpf's requirement for shared libs to be marked executable, from
   Henqgi Chen.

8) Improve bpf_iter internals handling of error returns, from Hao Luo.

9) Few accommodations in libbpf to support GCC-BPF quirks, from James Hilliard.

10) Fix BPF verifier logic around tracking dynptr ref_obj_id, from Joanne Koong.

11) bpftool improvements to handle full BPF program names better, from Manu
    Bretelle.

12) bpftool fixes around libcap use, from Quentin Monnet.

13) BPF map internals clean ups and improvements around memory allocations,
    from Yafang Shao.

14) Allow to use cgroup_get_from_file() on cgroupv1, allowing BPF cgroup
    iterator to work on cgroupv1, from Yosry Ahmed.

15) BPF verifier internal clean ups, from Dave Marchevsky and Joanne Koong.

16) Various fixes and clean ups for selftests/bpf and vmtest.sh, from Daniel
    Xu, Artem Savkov, Joanne Koong, Andrii Nakryiko, Shibin Koikkara Reeny.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (45 commits)
  selftests/bpf: Few fixes for selftests/bpf built in release mode
  libbpf: Clean up deprecated and legacy aliases
  libbpf: Streamline bpf_attr and perf_event_attr initialization
  libbpf: Fix potential NULL dereference when parsing ELF
  selftests/bpf: Tests libbpf autoattach APIs
  libbpf: Allows disabling auto attach
  selftests/bpf: Fix attach point for non-x86 arches in test_progs/lsm
  libbpf: Making bpf_prog_load() ignore name if kernel doesn't support
  selftests/bpf: Update CI kconfig
  selftests/bpf: Add connmark read test
  selftests/bpf: Add existing connection bpf_*_ct_lookup() test
  bpftool: Clear errno after libcap's checks
  bpf: Clear up confusion in bpf_skb_adjust_room()'s documentation
  bpftool: Fix a typo in a comment
  libbpf: Add names for auxiliary maps
  bpf: Use bpf_map_area_alloc consistently on bpf map creation
  bpf: Make __GFP_NOWARN consistent in bpf map creation
  bpf: Use bpf_map_area_free instread of kvfree
  bpf: Remove unneeded memset in queue_stack_map creation
  libbpf: preserve errno across pr_warn/pr_info/pr_debug
  ...
====================

Link: https://lore.kernel.org/r/20220817215656.1180215-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/bpf/kfuncs.rst

@@ -146,6 +146,21 @@ that operate (change some property, perform some operation) on an object that
 was obtained using an acquire kfunc. Such kfuncs need an unchanged pointer to
 ensure the integrity of the operation being performed on the expected object.
 
+2.4.6 KF_SLEEPABLE flag
+-----------------------
+
+The KF_SLEEPABLE flag is used for kfuncs that may sleep. Such kfuncs can only
+be called by sleepable BPF programs (BPF_F_SLEEPABLE).
+
+2.4.7 KF_DESTRUCTIVE flag
+--------------------------
+
+The KF_DESTRUCTIVE flag is used to indicate functions calling which is
+destructive to the system. For example such a call can result in system
+rebooting or panicking. Due to this additional restrictions apply to these
+calls. At the moment they only require CAP_SYS_BOOT capability, but more can be
+added later.
+
 2.5 Registering the kfuncs
 --------------------------
 

include/linux/bpf.h

@@ -2349,6 +2349,7 @@ extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
 extern const struct bpf_func_proto bpf_tail_call_proto;
 extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
 extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto;
+extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto;
 extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
 extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;

include/linux/btf.h

@@ -49,6 +49,8 @@
  * for this case.
  */
 #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */
+#define KF_SLEEPABLE    (1 << 5) /* kfunc may sleep */
+#define KF_DESTRUCTIVE  (1 << 6) /* kfunc performs destructive actions */
 
 struct btf;
 struct btf_member;

include/net/netfilter/nf_conntrack_core.h

@@ -86,10 +86,6 @@ extern spinlock_t nf_conntrack_expect_lock;
 
 /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
 
-#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
-    (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) || \
-    IS_ENABLED(CONFIG_NF_CT_NETLINK))
-
 static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout)
 {
 	if (timeout > INT_MAX)
@@ -101,6 +97,4 @@ int __nf_ct_change_timeout(struct nf_conn *ct, u64 cta_timeout);
 void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off);
 int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status);
 
-#endif
-
 #endif /* _NF_CONNTRACK_CORE_H */

include/uapi/linux/bpf.h

@@ -2573,10 +2573,12 @@ union bpf_attr {
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- *		  (room space is added or removed below the layer 2 header).
+ * 		  (room space is added or removed between the layer 2 and
+ * 		  layer 3 headers).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 		  (room space is added or removed below the layer 3 header).
+ * 		  (room space is added or removed between the layer 3 and
+ * 		  layer 4 headers).
  *
  *		The following flags are supported at this time:
  *
@@ -3008,8 +3010,18 @@ union bpf_attr {
  * 		**BPF_F_USER_STACK**
  * 			Collect a user space stack instead of a kernel stack.
  * 		**BPF_F_USER_BUILD_ID**
- * 			Collect buildid+offset instead of ips for user stack,
- * 			only valid if **BPF_F_USER_STACK** is also specified.
+ * 			Collect (build_id, file_offset) instead of ips for user
+ * 			stack, only valid if **BPF_F_USER_STACK** is also
+ * 			specified.
+ *
+ * 			*file_offset* is an offset relative to the beginning
+ * 			of the executable or shared object file backing the vma
+ * 			which the *ip* falls in. It is *not* an offset relative
+ * 			to that object's base address. Accordingly, it must be
+ * 			adjusted by adding (sh_addr - sh_offset), where
+ * 			sh_{addr,offset} correspond to the executable section
+ * 			containing *file_offset* in the object, for comparisons
+ * 			to symbols' st_value to be valid.
  *
  * 		**bpf_get_stack**\ () can collect up to
  * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -5331,6 +5343,18 @@ union bpf_attr {
  *		**-EACCES** if the SYN cookie is not valid.
  *
  *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ *	Description
+ *		A nonsettable system-wide clock derived from wall-clock time but
+ *		ignoring leap seconds.  This clock does not experience
+ *		discontinuities and backwards jumps caused by NTP inserting leap
+ *		seconds as CLOCK_REALTIME does.
+ *
+ *		See: **clock_gettime**\ (**CLOCK_TAI**)
+ *	Return
+ *		Current *ktime*.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5541,6 +5565,7 @@ union bpf_attr {
 	FN(tcp_raw_gen_syncookie_ipv6),	\
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
+	FN(ktime_get_tai_ns),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/bpf_iter.c

@@ -202,6 +202,11 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 	}
 stop:
 	offs = seq->count;
+	if (IS_ERR(p)) {
+		seq->op->stop(seq, NULL);
+		err = PTR_ERR(p);
+		goto done;
+	}
 	/* bpf program called if !p */
 	seq->op->stop(seq, p);
 	if (!p) {

kernel/bpf/bpf_local_storage.c

@@ -582,7 +582,7 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap,
 	synchronize_rcu();
 
 	kvfree(smap->buckets);
-	kfree(smap);
+	bpf_map_area_free(smap);
 }
 
 int bpf_local_storage_map_alloc_check(union bpf_attr *attr)
@@ -610,7 +610,7 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 	unsigned int i;
 	u32 nbuckets;
 
-	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
+	smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE);
 	if (!smap)
 		return ERR_PTR(-ENOMEM);
 	bpf_map_init_from_attr(&smap->map, attr);
@@ -623,7 +623,7 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr)
 	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
 				 GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
 	if (!smap->buckets) {
-		kfree(smap);
+		bpf_map_area_free(smap);
 		return ERR_PTR(-ENOMEM);
 	}
 

kernel/bpf/btf.c

@@ -5864,26 +5864,25 @@ again:
 }
 
 static int __get_type_size(struct btf *btf, u32 btf_id,
-			   const struct btf_type **bad_type)
+			   const struct btf_type **ret_type)
 {
 	const struct btf_type *t;
 
+	*ret_type = btf_type_by_id(btf, 0);
 	if (!btf_id)
 		/* void */
 		return 0;
 	t = btf_type_by_id(btf, btf_id);
 	while (t && btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
-	if (!t) {
-		*bad_type = btf_type_by_id(btf, 0);
+	if (!t)
 		return -EINVAL;
-	}
+	*ret_type = t;
 	if (btf_type_is_ptr(t))
 		/* kernel size of pointer. Not BPF's size of pointer*/
 		return sizeof(void *);
 	if (btf_type_is_int(t) || btf_is_any_enum(t))
 		return t->size;
-	*bad_type = t;
 	return -EINVAL;
 }
 
@@ -6175,6 +6174,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	bool rel = false, kptr_get = false, trusted_arg = false;
+	bool sleepable = false;
 	struct bpf_verifier_log *log = &env->log;
 	u32 i, nargs, ref_id, ref_obj_id = 0;
 	bool is_kfunc = btf_is_kernel(btf);
@@ -6212,6 +6212,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 		rel = kfunc_flags & KF_RELEASE;
 		kptr_get = kfunc_flags & KF_KPTR_GET;
 		trusted_arg = kfunc_flags & KF_TRUSTED_ARGS;
+		sleepable = kfunc_flags & KF_SLEEPABLE;
 	}
 
 	/* check that BTF function arguments match actual types that the
@@ -6419,6 +6420,13 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env,
 			func_name);
 		return -EINVAL;
 	}
+
+	if (sleepable && !env->prog->aux->sleepable) {
+		bpf_log(log, "kernel function %s is sleepable but the program is not\n",
+			func_name);
+		return -EINVAL;
+	}
+
 	/* returns argument register number > 0 in case of reference release kfunc */
 	return rel ? ref_regno : 0;
 }

kernel/bpf/core.c

@@ -2623,6 +2623,7 @@ const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak;
 const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_tai_ns_proto __weak;
 
 const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;

kernel/bpf/cpumap.c

@@ -97,7 +97,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~BPF_F_NUMA_NODE)
 		return ERR_PTR(-EINVAL);
 
-	cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT);
+	cmap = bpf_map_area_alloc(sizeof(*cmap), NUMA_NO_NODE);
 	if (!cmap)
 		return ERR_PTR(-ENOMEM);
 
@@ -118,7 +118,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 
 	return &cmap->map;
 free_cmap:
-	kfree(cmap);
+	bpf_map_area_free(cmap);
 	return ERR_PTR(err);
 }
 
@@ -623,7 +623,7 @@ static void cpu_map_free(struct bpf_map *map)
 		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
 	}
 	bpf_map_area_free(cmap->cpu_map);
-	kfree(cmap);
+	bpf_map_area_free(cmap);
 }
 
 /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or

kernel/bpf/devmap.c

@@ -163,13 +163,13 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT);
+	dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE);
 	if (!dtab)
 		return ERR_PTR(-ENOMEM);
 
 	err = dev_map_init_map(dtab, attr);
 	if (err) {
-		kfree(dtab);
+		bpf_map_area_free(dtab);
 		return ERR_PTR(err);
 	}
 
@@ -240,7 +240,7 @@ static void dev_map_free(struct bpf_map *map)
 		bpf_map_area_free(dtab->netdev_map);
 	}
 
-	kfree(dtab);
+	bpf_map_area_free(dtab);
 }
 
 static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)

kernel/bpf/hashtab.c

@@ -491,7 +491,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 	struct bpf_htab *htab;
 	int err, i;
 
-	htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
+	htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
@@ -575,7 +575,7 @@ free_map_locked:
 	bpf_map_area_free(htab->buckets);
 free_htab:
 	lockdep_unregister_key(&htab->lockdep_key);
-	kfree(htab);
+	bpf_map_area_free(htab);
 	return ERR_PTR(err);
 }
 
@@ -1492,7 +1492,7 @@ static void htab_map_free(struct bpf_map *map)
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
 		free_percpu(htab->map_locked[i]);
 	lockdep_unregister_key(&htab->lockdep_key);
-	kfree(htab);
+	bpf_map_area_free(htab);
 }
 
 static void htab_map_seq_show_elem(struct bpf_map *map, void *key,

kernel/bpf/helpers.c

@@ -198,6 +198,18 @@ const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = {
 	.ret_type	= RET_INTEGER,
 };
 
+BPF_CALL_0(bpf_ktime_get_tai_ns)
+{
+	/* NMI safe access to clock tai */
+	return ktime_get_tai_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_tai_ns_proto = {
+	.func		= bpf_ktime_get_tai_ns,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 BPF_CALL_0(bpf_get_current_pid_tgid)
 {
 	struct task_struct *task = current;
@@ -1617,6 +1629,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
+	case BPF_FUNC_ktime_get_tai_ns:
+		return &bpf_ktime_get_tai_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
@@ -1711,3 +1725,21 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return NULL;
 	}
 }
+
+BTF_SET8_START(tracing_btf_ids)
+#ifdef CONFIG_KEXEC_CORE
+BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
+#endif
+BTF_SET8_END(tracing_btf_ids)
+
+static const struct btf_kfunc_id_set tracing_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &tracing_btf_ids,
+};
+
+static int __init kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &tracing_kfunc_set);
+}
+
+late_initcall(kfunc_init);

kernel/bpf/local_storage.c

@@ -313,8 +313,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 		/* max_entries is not used and enforced to be 0 */
 		return ERR_PTR(-EINVAL);
 
-	map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
-			   __GFP_ZERO | GFP_USER | __GFP_ACCOUNT, numa_node);
+	map = bpf_map_area_alloc(sizeof(struct bpf_cgroup_storage_map), numa_node);
 	if (!map)
 		return ERR_PTR(-ENOMEM);
 
@@ -346,7 +345,7 @@ static void cgroup_storage_map_free(struct bpf_map *_map)
 	WARN_ON(!RB_EMPTY_ROOT(&map->root));
 	WARN_ON(!list_empty(&map->list));
 
-	kfree(map);
+	bpf_map_area_free(map);
 }
 
 static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)

kernel/bpf/lpm_trie.c

@@ -558,7 +558,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	    attr->value_size > LPM_VAL_SIZE_MAX)
 		return ERR_PTR(-EINVAL);
 
-	trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT);
+	trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE);
 	if (!trie)
 		return ERR_PTR(-ENOMEM);
 
@@ -609,7 +609,7 @@ static void trie_free(struct bpf_map *map)
 	}
 
 out:
-	kfree(trie);
+	bpf_map_area_free(trie);
 }
 
 static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)

kernel/bpf/offload.c

@@ -372,7 +372,7 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 	    attr->map_type != BPF_MAP_TYPE_HASH)
 		return ERR_PTR(-EINVAL);
 
-	offmap = kzalloc(sizeof(*offmap), GFP_USER);
+	offmap = bpf_map_area_alloc(sizeof(*offmap), NUMA_NO_NODE);
 	if (!offmap)
 		return ERR_PTR(-ENOMEM);
 
@@ -404,7 +404,7 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 err_unlock:
 	up_write(&bpf_devs_lock);
 	rtnl_unlock();
-	kfree(offmap);
+	bpf_map_area_free(offmap);
 	return ERR_PTR(err);
 }
 
@@ -428,7 +428,7 @@ void bpf_map_offload_map_free(struct bpf_map *map)
 	up_write(&bpf_devs_lock);
 	rtnl_unlock();
 
-	kfree(offmap);
+	bpf_map_area_free(offmap);
 }
 
 int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)

kernel/bpf/queue_stack_maps.c

@@ -78,8 +78,6 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
 	if (!qs)
 		return ERR_PTR(-ENOMEM);
 
-	memset(qs, 0, sizeof(*qs));
-
 	bpf_map_init_from_attr(&qs->map, attr);
 
 	qs->size = size;

kernel/bpf/ringbuf.c

@@ -116,7 +116,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
 err_free_pages:
 	for (i = 0; i < nr_pages; i++)
 		__free_page(pages[i]);
-	kvfree(pages);
+	bpf_map_area_free(pages);
 	return NULL;
 }
 
@@ -164,7 +164,7 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-E2BIG);
 #endif
 
-	rb_map = kzalloc(sizeof(*rb_map), GFP_USER | __GFP_ACCOUNT);
+	rb_map = bpf_map_area_alloc(sizeof(*rb_map), NUMA_NO_NODE);
 	if (!rb_map)
 		return ERR_PTR(-ENOMEM);
 
@@ -172,7 +172,7 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
 
 	rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node);
 	if (!rb_map->rb) {
-		kfree(rb_map);
+		bpf_map_area_free(rb_map);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -190,7 +190,7 @@ static void bpf_ringbuf_free(struct bpf_ringbuf *rb)
 	vunmap(rb);
 	for (i = 0; i < nr_pages; i++)
 		__free_page(pages[i]);
-	kvfree(pages);
+	bpf_map_area_free(pages);
 }
 
 static void ringbuf_map_free(struct bpf_map *map)
@@ -199,7 +199,7 @@ static void ringbuf_map_free(struct bpf_map *map)
 
 	rb_map = container_of(map, struct bpf_ringbuf_map, map);
 	bpf_ringbuf_free(rb_map->rb);
-	kfree(rb_map);
+	bpf_map_area_free(rb_map);
 }
 
 static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key)

kernel/bpf/verifier.c

@@ -427,6 +427,7 @@ static void verbose_invalid_scalar(struct bpf_verifier_env *env,
 
 static bool type_is_pkt_pointer(enum bpf_reg_type type)
 {
+	type = base_type(type);
 	return type == PTR_TO_PACKET ||
 	       type == PTR_TO_PACKET_META;
 }
@@ -456,10 +457,9 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 
 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_BTF_ID;
+	type = base_type(type);
+	return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_MEM || type == PTR_TO_BTF_ID;
 }
 
 static bool type_is_rdonly_mem(u32 type)
@@ -467,25 +467,11 @@ static bool type_is_rdonly_mem(u32 type)
 	return type & MEM_RDONLY;
 }
 
-static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
-{
-	return type == ARG_PTR_TO_SOCK_COMMON;
-}
-
 static bool type_may_be_null(u32 type)
 {
 	return type & PTR_MAYBE_NULL;
 }
 
-static bool may_be_acquire_function(enum bpf_func_id func_id)
-{
-	return func_id == BPF_FUNC_sk_lookup_tcp ||
-		func_id == BPF_FUNC_sk_lookup_udp ||
-		func_id == BPF_FUNC_skc_lookup_tcp ||
-		func_id == BPF_FUNC_map_lookup_elem ||
-	        func_id == BPF_FUNC_ringbuf_reserve;
-}
-
 static bool is_acquire_function(enum bpf_func_id func_id,
 				const struct bpf_map *map)
 {
@@ -518,6 +504,26 @@ static bool is_ptr_cast_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_skc_to_tcp_request_sock;
 }
 
+static bool is_dynptr_ref_function(enum bpf_func_id func_id)
+{
+	return func_id == BPF_FUNC_dynptr_data;
+}
+
+static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id,
+					const struct bpf_map *map)
+{
+	int ref_obj_uses = 0;
+
+	if (is_ptr_cast_function(func_id))
+		ref_obj_uses++;
+	if (is_acquire_function(func_id, map))
+		ref_obj_uses++;
+	if (is_dynptr_ref_function(func_id))
+		ref_obj_uses++;
+
+	return ref_obj_uses > 1;
+}
+
 static bool is_cmpxchg_insn(const struct bpf_insn *insn)
 {
 	return BPF_CLASS(insn->code) == BPF_STX &&
@@ -6453,33 +6459,6 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
-{
-	int count = 0;
-
-	if (arg_type_may_be_refcounted(fn->arg1_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg2_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg3_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg4_type))
-		count++;
-	if (arg_type_may_be_refcounted(fn->arg5_type))
-		count++;
-
-	/* A reference acquiring function cannot acquire
-	 * another refcounted ptr.
-	 */
-	if (may_be_acquire_function(func_id) && count)
-		return false;
-
-	/* We only support one arg being unreferenced at the moment,
-	 * which is sufficient for the helper functions we have right now.
-	 */
-	return count <= 1;
-}
-
 static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 {
 	int i;
@@ -6498,13 +6477,11 @@ static bool check_btf_id_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static int check_func_proto(const struct bpf_func_proto *fn, int func_id,
-			    struct bpf_call_arg_meta *meta)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
-	       check_btf_id_ok(fn) &&
-	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
+	       check_btf_id_ok(fn) ? 0 : -EINVAL;
 }
 
 /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
@@ -7218,7 +7195,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
 
-	err = check_func_proto(fn, func_id, &meta);
+	err = check_func_proto(fn, func_id);
 	if (err) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
@@ -7343,6 +7320,23 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			}
 		}
 		break;
+	case BPF_FUNC_dynptr_data:
+		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
+			if (arg_type_is_dynptr(fn->arg_type[i])) {
+				if (meta.ref_obj_id) {
+					verbose(env, "verifier internal error: meta.ref_obj_id already set\n");
+					return -EFAULT;
+				}
+				/* Find the id of the dynptr we're tracking the reference of */
+				meta.ref_obj_id = stack_slot_get_id(env, &regs[BPF_REG_1 + i]);
+				break;
+			}
+		}
+		if (i == MAX_BPF_FUNC_REG_ARGS) {
+			verbose(env, "verifier internal error: no dynptr in bpf_dynptr_data()\n");
+			return -EFAULT;
+		}
+		break;
 	}
 
 	if (err)
@@ -7359,13 +7353,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	/* update return register (already marked as written above) */
 	ret_type = fn->ret_type;
-	ret_flag = type_flag(fn->ret_type);
-	if (ret_type == RET_INTEGER) {
+	ret_flag = type_flag(ret_type);
+
+	switch (base_type(ret_type)) {
+	case RET_INTEGER:
 		/* sets type to SCALAR_VALUE */
 		mark_reg_unknown(env, regs, BPF_REG_0);
-	} else if (ret_type == RET_VOID) {
+		break;
+	case RET_VOID:
 		regs[BPF_REG_0].type = NOT_INIT;
-	} else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) {
+		break;
+	case RET_PTR_TO_MAP_VALUE:
 		/* There is no offset yet applied, variable or fixed */
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		/* remember map_ptr, so that check_map_access()
@@ -7384,20 +7382,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		    map_value_has_spin_lock(meta.map_ptr)) {
 			regs[BPF_REG_0].id = ++env->id_gen;
 		}
-	} else if (base_type(ret_type) == RET_PTR_TO_SOCKET) {
+		break;
+	case RET_PTR_TO_SOCKET:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) {
+		break;
+	case RET_PTR_TO_SOCK_COMMON:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) {
+		break;
+	case RET_PTR_TO_TCP_SOCK:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
-	} else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) {
+		break;
+	case RET_PTR_TO_ALLOC_MEM:
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
 		regs[BPF_REG_0].mem_size = meta.mem_size;
-	} else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) {
+		break;
+	case RET_PTR_TO_MEM_OR_BTF_ID:
+	{
 		const struct btf_type *t;
 
 		mark_reg_known_zero(env, regs, BPF_REG_0);
@@ -7429,7 +7433,10 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			regs[BPF_REG_0].btf = meta.ret_btf;
 			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
 		}
-	} else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) {
+		break;
+	}
+	case RET_PTR_TO_BTF_ID:
+	{
 		struct btf *ret_btf;
 		int ret_btf_id;
 
@@ -7450,7 +7457,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		regs[BPF_REG_0].btf = ret_btf;
 		regs[BPF_REG_0].btf_id = ret_btf_id;
-	} else {
+		break;
+	}
+	default:
 		verbose(env, "unknown return type %u of func %s#%d\n",
 			base_type(ret_type), func_id_name(func_id), func_id);
 		return -EINVAL;
@@ -7459,7 +7468,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	if (type_may_be_null(regs[BPF_REG_0].type))
 		regs[BPF_REG_0].id = ++env->id_gen;
 
-	if (is_ptr_cast_function(func_id)) {
+	if (helper_multiple_ref_obj_use(func_id, meta.map_ptr)) {
+		verbose(env, "verifier internal error: func %s#%d sets ref_obj_id more than once\n",
+			func_id_name(func_id), func_id);
+		return -EFAULT;
+	}
+
+	if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) {
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
 	} else if (is_acquire_function(func_id, meta.map_ptr)) {
@@ -7471,21 +7486,6 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].id = id;
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = id;
-	} else if (func_id == BPF_FUNC_dynptr_data) {
-		int dynptr_id = 0, i;
-
-		/* Find the id of the dynptr we're acquiring a reference to */
-		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
-			if (arg_type_is_dynptr(fn->arg_type[i])) {
-				if (dynptr_id) {
-					verbose(env, "verifier internal error: multiple dynptr args in func\n");
-					return -EFAULT;
-				}
-				dynptr_id = stack_slot_get_id(env, &regs[BPF_REG_1 + i]);
-			}
-		}
-		/* For release_reference() */
-		regs[BPF_REG_0].ref_obj_id = dynptr_id;
 	}
 
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
@@ -7584,6 +7584,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			func_name);
 		return -EACCES;
 	}
+	if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) {
+		verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n");
+		return -EACCES;
+	}
+
 	acq = *kfunc_flags & KF_ACQUIRE;
 
 	/* Check the arguments */

kernel/cgroup/cgroup.c

@@ -6132,11 +6132,6 @@ static struct cgroup *cgroup_get_from_file(struct file *f)
 		return ERR_CAST(css);
 
 	cgrp = css->cgroup;
-	if (!cgroup_on_dfl(cgrp)) {
-		cgroup_put(cgrp);
-		return ERR_PTR(-EBADF);
-	}
-
 	return cgrp;
 }
 

net/bpf/test_run.c

@@ -695,6 +695,10 @@ noinline void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
 {
 }
 
+noinline void bpf_kfunc_call_test_destructive(void)
+{
+}
+
 __diag_pop();
 
 ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
@@ -719,6 +723,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
 BTF_SET8_END(test_sk_check_kfunc_ids)
 
 static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,

net/core/sock_map.c

@@ -41,7 +41,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
-	stab = kzalloc(sizeof(*stab), GFP_USER | __GFP_ACCOUNT);
+	stab = bpf_map_area_alloc(sizeof(*stab), NUMA_NO_NODE);
 	if (!stab)
 		return ERR_PTR(-ENOMEM);
 
@@ -52,7 +52,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 				       sizeof(struct sock *),
 				       stab->map.numa_node);
 	if (!stab->sks) {
-		kfree(stab);
+		bpf_map_area_free(stab);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -361,7 +361,7 @@ static void sock_map_free(struct bpf_map *map)
 	synchronize_rcu();
 
 	bpf_map_area_free(stab->sks);
-	kfree(stab);
+	bpf_map_area_free(stab);
 }
 
 static void sock_map_release_progs(struct bpf_map *map)
@@ -1085,7 +1085,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 	if (attr->key_size > MAX_BPF_STACK)
 		return ERR_PTR(-E2BIG);
 
-	htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
+	htab = bpf_map_area_alloc(sizeof(*htab), NUMA_NO_NODE);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
@@ -1115,7 +1115,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 
 	return &htab->map;
 free_htab:
-	kfree(htab);
+	bpf_map_area_free(htab);
 	return ERR_PTR(err);
 }
 
@@ -1168,7 +1168,7 @@ static void sock_hash_free(struct bpf_map *map)
 	synchronize_rcu();
 
 	bpf_map_area_free(htab->buckets);
-	kfree(htab);
+	bpf_map_area_free(htab);
 }
 
 static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)

net/netfilter/nf_conntrack_core.c

@@ -2807,10 +2807,6 @@ err_expect:
 	return ret;
 }
 
-#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
-    (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) || \
-    IS_ENABLED(CONFIG_NF_CT_NETLINK))
-
 /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */
 
 int __nf_ct_change_timeout(struct nf_conn *ct, u64 timeout)
@@ -2866,5 +2862,3 @@ int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_ct_change_status_common);
-
-#endif

tools/bpf/bpftool/common.c

@@ -722,6 +722,7 @@ print_all_levels(__maybe_unused enum libbpf_print_level level,
 
 static int prog_fd_by_nametag(void *nametag, int **fds, bool tag)
 {
+	char prog_name[MAX_PROG_FULL_NAME];
 	unsigned int id = 0;
 	int fd, nb_fds = 0;
 	void *tmp;
@@ -754,12 +755,20 @@ static int prog_fd_by_nametag(void *nametag, int **fds, bool tag)
 			goto err_close_fd;
 		}
 
-		if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) ||
-		    (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) {
+		if (tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) {
 			close(fd);
 			continue;
 		}
 
+		if (!tag) {
+			get_prog_full_name(&info, fd, prog_name,
+					   sizeof(prog_name));
+			if (strncmp(nametag, prog_name, sizeof(prog_name))) {
+				close(fd);
+				continue;
+			}
+		}
+
 		if (nb_fds > 0) {
 			tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
 			if (!tmp) {
@@ -820,7 +829,7 @@ int prog_parse_fds(int *argc, char ***argv, int **fds)
 		NEXT_ARGP();
 
 		name = **argv;
-		if (strlen(name) > BPF_OBJ_NAME_LEN - 1) {
+		if (strlen(name) > MAX_PROG_FULL_NAME - 1) {
 			p_err("can't parse name");
 			return -1;
 		}

tools/bpf/bpftool/feature.c

@@ -1147,7 +1147,7 @@ exit_free:
 	return res;
 #else
 	/* Detection assumes user has specific privileges.
-	 * We do not use libpcap so let's approximate, and restrict usage to
+	 * We do not use libcap so let's approximate, and restrict usage to
 	 * root user only.
 	 */
 	if (geteuid()) {

tools/bpf/bpftool/main.c

@@ -435,6 +435,16 @@ int main(int argc, char **argv)
 
 	setlinebuf(stdout);
 
+#ifdef USE_LIBCAP
+	/* Libcap < 2.63 hooks before main() to compute the number of
+	 * capabilities of the running kernel, and doing so it calls prctl()
+	 * which may fail and set errno to non-zero.
+	 * Let's reset errno to make sure this does not interfere with the
+	 * batch mode.
+	 */
+	errno = 0;
+#endif
+
 	last_do_help = do_help;
 	pretty_output = false;
 	json_output = false;

tools/include/uapi/linux/bpf.h

@@ -2573,10 +2573,12 @@ union bpf_attr {
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- *		  (room space is added or removed below the layer 2 header).
+ * 		  (room space is added or removed between the layer 2 and
+ * 		  layer 3 headers).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 		  (room space is added or removed below the layer 3 header).
+ * 		  (room space is added or removed between the layer 3 and
+ * 		  layer 4 headers).
  *
  *		The following flags are supported at this time:
  *
@@ -3008,8 +3010,18 @@ union bpf_attr {
  * 		**BPF_F_USER_STACK**
  * 			Collect a user space stack instead of a kernel stack.
  * 		**BPF_F_USER_BUILD_ID**
- * 			Collect buildid+offset instead of ips for user stack,
- * 			only valid if **BPF_F_USER_STACK** is also specified.
+ * 			Collect (build_id, file_offset) instead of ips for user
+ * 			stack, only valid if **BPF_F_USER_STACK** is also
+ * 			specified.
+ *
+ * 			*file_offset* is an offset relative to the beginning
+ * 			of the executable or shared object file backing the vma
+ * 			which the *ip* falls in. It is *not* an offset relative
+ * 			to that object's base address. Accordingly, it must be
+ * 			adjusted by adding (sh_addr - sh_offset), where
+ * 			sh_{addr,offset} correspond to the executable section
+ * 			containing *file_offset* in the object, for comparisons
+ * 			to symbols' st_value to be valid.
  *
  * 		**bpf_get_stack**\ () can collect up to
  * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -5331,6 +5343,18 @@ union bpf_attr {
  *		**-EACCES** if the SYN cookie is not valid.
  *
  *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ *	Description
+ *		A nonsettable system-wide clock derived from wall-clock time but
+ *		ignoring leap seconds.  This clock does not experience
+ *		discontinuities and backwards jumps caused by NTP inserting leap
+ *		seconds as CLOCK_REALTIME does.
+ *
+ *		See: **clock_gettime**\ (**CLOCK_TAI**)
+ *	Return
+ *		Current *ktime*.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5541,6 +5565,7 @@ union bpf_attr {
 	FN(tcp_raw_gen_syncookie_ipv6),	\
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
+	FN(ktime_get_tai_ns),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

tools/lib/bpf/bpf.c

@@ -84,9 +84,7 @@ static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
 	return ensure_good_fd(fd);
 }
 
-#define PROG_LOAD_ATTEMPTS 5
-
-static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
+int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts)
 {
 	int fd;
 
@@ -107,7 +105,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int
  */
 int probe_memcg_account(void)
 {
-	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
+	const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd);
 	struct bpf_insn insns[] = {
 		BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns),
 		BPF_EXIT_INSN(),
@@ -117,13 +115,13 @@ int probe_memcg_account(void)
 	int prog_fd;
 
 	/* attempt loading freplace trying to use custom BTF */
-	memset(&attr, 0, prog_load_attr_sz);
+	memset(&attr, 0, attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	attr.insns = ptr_to_u64(insns);
 	attr.insn_cnt = insn_cnt;
 	attr.license = ptr_to_u64("GPL");
 
-	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
+	prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz);
 	if (prog_fd >= 0) {
 		close(prog_fd);
 		return 1;
@@ -183,7 +181,7 @@ int bpf_map_create(enum bpf_map_type map_type,
 		return libbpf_err(-EINVAL);
 
 	attr.map_type = map_type;
-	if (map_name)
+	if (map_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name));
 	attr.key_size = key_size;
 	attr.value_size = value_size;
@@ -234,6 +232,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, size_t insn_cnt,
 		  const struct bpf_prog_load_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, fd_array);
 	void *finfo = NULL, *linfo = NULL;
 	const char *func_info, *line_info;
 	__u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd;
@@ -253,7 +252,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	if (attempts == 0)
 		attempts = PROG_LOAD_ATTEMPTS;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 
 	attr.prog_type = prog_type;
 	attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0);
@@ -263,7 +262,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0);
 	attr.kern_version = OPTS_GET(opts, kern_version, 0);
 
-	if (prog_name)
+	if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME))
 		libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name));
 	attr.license = ptr_to_u64(license);
 
@@ -316,7 +315,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		attr.log_level = log_level;
 	}
 
-	fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+	fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 	if (fd >= 0)
 		return fd;
 
@@ -356,7 +355,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 			break;
 		}
 
-		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+		fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 		if (fd >= 0)
 			goto done;
 	}
@@ -370,7 +369,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		attr.log_size = log_size;
 		attr.log_level = 1;
 
-		fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts);
+		fd = sys_bpf_prog_load(&attr, attr_sz, attempts);
 	}
 done:
 	/* free() doesn't affect errno, so we don't need to restore it */
@@ -382,127 +381,136 @@ done:
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_elem(int fd, const void *key)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
-	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.flags = flags;
 
-	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, next_key);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
 
-	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_map_freeze(int fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, map_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_fd = fd;
 
-	ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
@@ -511,13 +519,14 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 				__u32 *count,
 				const struct bpf_map_batch_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, batch);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_map_batch_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.batch.map_fd = fd;
 	attr.batch.in_batch = ptr_to_u64(in_batch);
 	attr.batch.out_batch = ptr_to_u64(out_batch);
@@ -527,7 +536,7 @@ static int bpf_map_batch_common(int cmd, int fd, void  *in_batch,
 	attr.batch.elem_flags  = OPTS_GET(opts, elem_flags, 0);
 	attr.batch.flags = OPTS_GET(opts, flags, 0);
 
-	ret = sys_bpf(cmd, &attr, sizeof(attr));
+	ret = sys_bpf(cmd, &attr, attr_sz);
 	*count = attr.batch.count;
 
 	return libbpf_err_errno(ret);
@@ -566,14 +575,15 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co
 
 int bpf_obj_pin(int fd, const char *pathname)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
-	ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
@@ -584,17 +594,18 @@ int bpf_obj_get(const char *pathname)
 
 int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, file_flags);
 	union bpf_attr attr;
 	int fd;
 
 	if (!OPTS_VALID(opts, bpf_obj_get_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.file_flags = OPTS_GET(opts, file_flags, 0);
 
-	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -612,52 +623,50 @@ int bpf_prog_attach_opts(int prog_fd, int target_fd,
 			  enum bpf_attach_type type,
 			  const struct bpf_prog_attach_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_attach_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
 	attr.attach_flags  = OPTS_GET(opts, flags, 0);
 	attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0);
 
-	ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
-__attribute__((alias("bpf_prog_attach_opts")))
-int bpf_prog_attach_xattr(int prog_fd, int target_fd,
-			  enum bpf_attach_type type,
-			  const struct bpf_prog_attach_opts *opts);
-
 int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
-	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
 
-	ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
@@ -665,6 +674,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		    enum bpf_attach_type attach_type,
 		    const struct bpf_link_create_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_create);
 	__u32 target_btf_id, iter_info_len;
 	union bpf_attr attr;
 	int fd, err;
@@ -683,7 +693,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 			return libbpf_err(-EINVAL);
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_create.prog_fd = prog_fd;
 	attr.link_create.target_fd = target_fd;
 	attr.link_create.attach_type = attach_type;
@@ -727,7 +737,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		break;
 	}
 proceed:
-	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, attr_sz);
 	if (fd >= 0)
 		return fd;
 	/* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry
@@ -763,44 +773,47 @@ proceed:
 
 int bpf_link_detach(int link_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_detach);
 	union bpf_attr attr;
 	int ret;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_detach.link_fd = link_fd;
 
-	ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_DETACH, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_link_update(int link_fd, int new_prog_fd,
 		    const struct bpf_link_update_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, link_update);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_link_update_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_update.link_fd = link_fd;
 	attr.link_update.new_prog_fd = new_prog_fd;
 	attr.link_update.flags = OPTS_GET(opts, flags, 0);
 	attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
 
-	ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }
 
 int bpf_iter_create(int link_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, iter_create);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.iter_create.link_fd = link_fd;
 
-	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -808,13 +821,14 @@ int bpf_prog_query_opts(int target_fd,
 			enum bpf_attach_type type,
 			struct bpf_prog_query_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, query);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_query_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 
 	attr.query.target_fd	= target_fd;
 	attr.query.attach_type	= type;
@@ -823,7 +837,7 @@ int bpf_prog_query_opts(int target_fd,
 	attr.query.prog_ids	= ptr_to_u64(OPTS_GET(opts, prog_ids, NULL));
 	attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL));
 
-	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz);
 
 	OPTS_SET(opts, attach_flags, attr.query.attach_flags);
 	OPTS_SET(opts, prog_cnt, attr.query.prog_cnt);
@@ -852,13 +866,14 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 
 int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, test);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_test_run_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.test.prog_fd = prog_fd;
 	attr.test.batch_size = OPTS_GET(opts, batch_size, 0);
 	attr.test.cpu = OPTS_GET(opts, cpu, 0);
@@ -874,7 +889,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 	attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL));
 	attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL));
 
-	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, attr_sz);
 
 	OPTS_SET(opts, data_size_out, attr.test.data_size_out);
 	OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out);
@@ -886,13 +901,14 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts)
 
 static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int err;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.start_id = start_id;
 
-	err = sys_bpf(cmd, &attr, sizeof(attr));
+	err = sys_bpf(cmd, &attr, attr_sz);
 	if (!err)
 		*next_id = attr.next_id;
 
@@ -921,80 +937,84 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id)
 
 int bpf_prog_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.prog_id = id;
 
-	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_map_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.map_id = id;
 
-	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_btf_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.btf_id = id;
 
-	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_link_get_fd_by_id(__u32 id)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, open_flags);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.link_id = id;
 
-	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, info);
 	union bpf_attr attr;
 	int err;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.info.bpf_fd = bpf_fd;
 	attr.info.info_len = *info_len;
 	attr.info.info = ptr_to_u64(info);
 
-	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr));
-
+	err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz);
 	if (!err)
 		*info_len = attr.info.info_len;
-
 	return libbpf_err_errno(err);
 }
 
 int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
@@ -1050,16 +1070,18 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 		      __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset,
 		      __u64 *probe_addr)
 {
-	union bpf_attr attr = {};
+	const size_t attr_sz = offsetofend(union bpf_attr, task_fd_query);
+	union bpf_attr attr;
 	int err;
 
+	memset(&attr, 0, attr_sz);
 	attr.task_fd_query.pid = pid;
 	attr.task_fd_query.fd = fd;
 	attr.task_fd_query.flags = flags;
 	attr.task_fd_query.buf = ptr_to_u64(buf);
 	attr.task_fd_query.buf_len = *buf_len;
 
-	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr));
+	err = sys_bpf(BPF_TASK_FD_QUERY, &attr, attr_sz);
 
 	*buf_len = attr.task_fd_query.buf_len;
 	*prog_id = attr.task_fd_query.prog_id;
@@ -1072,30 +1094,32 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len,
 
 int bpf_enable_stats(enum bpf_stats_type type)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, enable_stats);
 	union bpf_attr attr;
 	int fd;
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.enable_stats.type = type;
 
-	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, attr_sz);
 	return libbpf_err_errno(fd);
 }
 
 int bpf_prog_bind_map(int prog_fd, int map_fd,
 		      const struct bpf_prog_bind_opts *opts)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_bind_map);
 	union bpf_attr attr;
 	int ret;
 
 	if (!OPTS_VALID(opts, bpf_prog_bind_opts))
 		return libbpf_err(-EINVAL);
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, attr_sz);
 	attr.prog_bind_map.prog_fd = prog_fd;
 	attr.prog_bind_map.map_fd = map_fd;
 	attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0);
 
-	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz);
 	return libbpf_err_errno(ret);
 }

tools/lib/bpf/bpf_tracing.h

@@ -426,7 +426,7 @@ struct pt_regs;
  */
 #define BPF_PROG(name, args...)						    \
 name(unsigned long long *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args);				    \
 typeof(name(0)) name(unsigned long long *ctx)				    \
 {									    \
@@ -435,7 +435,7 @@ typeof(name(0)) name(unsigned long long *ctx)				    \
 	return ____##name(___bpf_ctx_cast(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(unsigned long long *ctx, ##args)
 
 struct pt_regs;
@@ -460,7 +460,7 @@ struct pt_regs;
  */
 #define BPF_KPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -469,7 +469,7 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 	return ____##name(___bpf_kprobe_args(args));			    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
 #define ___bpf_kretprobe_args0()       ctx
@@ -484,7 +484,7 @@ ____##name(struct pt_regs *ctx, ##args)
  */
 #define BPF_KRETPROBE(name, args...)					    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -540,7 +540,7 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 #define BPF_KSYSCALL(name, args...)					    \
 name(struct pt_regs *ctx);						    \
 extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig;			    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -555,7 +555,7 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 		return ____##name(___bpf_syscall_args(args));		    \
 	_Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
 #define BPF_KPROBE_SYSCALL BPF_KSYSCALL

tools/lib/bpf/btf.c

@@ -1225,8 +1225,6 @@ int btf__load_into_kernel(struct btf *btf)
 	return btf_load_into_kernel(btf, NULL, 0, 0);
 }
 
-int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel")));
-
 int btf__fd(const struct btf *btf)
 {
 	return btf->fd;

tools/lib/bpf/btf.h

@@ -116,7 +116,6 @@ LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_b
 
 LIBBPF_API struct btf *btf__load_vmlinux_btf(void);
 LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf);
-LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
 LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
 LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);

tools/lib/bpf/libbpf.c

@@ -223,13 +223,18 @@ __printf(2, 3)
 void libbpf_print(enum libbpf_print_level level, const char *format, ...)
 {
 	va_list args;
+	int old_errno;
 
 	if (!__libbpf_pr)
 		return;
 
+	old_errno = errno;
+
 	va_start(args, format);
 	__libbpf_pr(level, format, args);
 	va_end(args);
+
+	errno = old_errno;
 }
 
 static void pr_perm_msg(int err)
@@ -412,6 +417,7 @@ struct bpf_program {
 
 	int fd;
 	bool autoload;
+	bool autoattach;
 	bool mark_btf_static;
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
@@ -591,7 +597,6 @@ struct elf_state {
 	size_t strtabidx;
 	struct elf_sec_desc *secs;
 	int sec_cnt;
-	int maps_shndx;
 	int btf_maps_shndx;
 	__u32 btf_maps_sec_btf_id;
 	int text_shndx;
@@ -751,6 +756,8 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
 		prog->autoload = true;
 	}
 
+	prog->autoattach = true;
+
 	/* inherit object's log_level */
 	prog->log_level = obj->log_level;
 
@@ -1272,7 +1279,6 @@ static struct bpf_object *bpf_object__new(const char *path,
 	 */
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
-	obj->efile.maps_shndx = -1;
 	obj->efile.btf_maps_shndx = -1;
 	obj->efile.st_ops_shndx = -1;
 	obj->kconfig_map_idx = -1;
@@ -1642,6 +1648,10 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 	for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) {
 		sec_desc = &obj->efile.secs[sec_idx];
 
+		/* Skip recognized sections with size 0. */
+		if (!sec_desc->data || sec_desc->data->d_size == 0)
+			continue;
+
 		switch (sec_desc->sec_type) {
 		case SEC_DATA:
 			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
@@ -3359,7 +3369,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			if (err)
 				return err;
 		} else if (strcmp(name, "maps") == 0) {
-			obj->efile.maps_shndx = idx;
+			pr_warn("elf: legacy map definitions in 'maps' section are not supported by libbpf v1.0+\n");
+			return -ENOTSUP;
 		} else if (strcmp(name, MAPS_ELF_SEC) == 0) {
 			obj->efile.btf_maps_shndx = idx;
 		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
@@ -3891,8 +3902,7 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
 static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
 				      int shndx)
 {
-	return shndx == obj->efile.maps_shndx ||
-	       shndx == obj->efile.btf_maps_shndx;
+	return shndx == obj->efile.btf_maps_shndx;
 }
 
 static enum libbpf_map_type
@@ -4277,11 +4287,12 @@ int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate)
 
 int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 {
-	struct bpf_map_info info = {};
+	struct bpf_map_info info;
 	__u32 len = sizeof(info), name_len;
 	int new_fd, err;
 	char *new_name;
 
+	memset(&info, 0, len);
 	err = bpf_obj_get_info_by_fd(fd, &info, &len);
 	if (err && errno == EINVAL)
 		err = bpf_get_map_info_from_fdinfo(fd, &info);
@@ -4408,14 +4419,23 @@ static int probe_fd(int fd)
 
 static int probe_kern_prog_name(void)
 {
+	const size_t attr_sz = offsetofend(union bpf_attr, prog_name);
 	struct bpf_insn insns[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	int ret, insn_cnt = ARRAY_SIZE(insns);
+	union bpf_attr attr;
+	int ret;
+
+	memset(&attr, 0, attr_sz);
+	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	attr.license = ptr_to_u64("GPL");
+	attr.insns = ptr_to_u64(insns);
+	attr.insn_cnt = (__u32)ARRAY_SIZE(insns);
+	libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name));
 
 	/* make sure loading with name works */
-	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "test", "GPL", insns, insn_cnt, NULL);
+	ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS);
 	return probe_fd(ret);
 }
 
@@ -4430,7 +4450,7 @@ static int probe_kern_global_data(void)
 	};
 	int ret, map, insn_cnt = ARRAY_SIZE(insns);
 
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL);
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL);
 	if (map < 0) {
 		ret = -errno;
 		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
@@ -4563,7 +4583,7 @@ static int probe_kern_array_mmap(void)
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE);
 	int fd;
 
-	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(int), 1, &opts);
+	fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts);
 	return probe_fd(fd);
 }
 
@@ -4610,7 +4630,7 @@ static int probe_prog_bind_map(void)
 	};
 	int ret, map, prog, insn_cnt = ARRAY_SIZE(insns);
 
-	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL);
+	map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL);
 	if (map < 0) {
 		ret = -errno;
 		cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg));
@@ -4814,13 +4834,12 @@ bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
 
 static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 {
-	struct bpf_map_info map_info = {};
+	struct bpf_map_info map_info;
 	char msg[STRERR_BUFSIZE];
-	__u32 map_info_len;
+	__u32 map_info_len = sizeof(map_info);
 	int err;
 
-	map_info_len = sizeof(map_info);
-
+	memset(&map_info, 0, map_info_len);
 	err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
 	if (err && errno == EINVAL)
 		err = bpf_get_map_info_from_fdinfo(map_fd, &map_info);
@@ -7244,8 +7263,6 @@ static int bpf_object_unload(struct bpf_object *obj)
 	return 0;
 }
 
-int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload")));
-
 static int bpf_object__sanitize_maps(struct bpf_object *obj)
 {
 	struct bpf_map *m;
@@ -8298,6 +8315,16 @@ int bpf_program__set_autoload(struct bpf_program *prog, bool autoload)
 	return 0;
 }
 
+bool bpf_program__autoattach(const struct bpf_program *prog)
+{
+	return prog->autoattach;
+}
+
+void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach)
+{
+	prog->autoattach = autoattach;
+}
+
 const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog)
 {
 	return prog->insns;
@@ -8978,11 +9005,12 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 {
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
 	struct btf *btf;
 	int err;
 
+	memset(&info, 0, info_len);
 	err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
 	if (err) {
 		pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n",
@@ -9810,13 +9838,16 @@ static int determine_uprobe_retprobe_bit(void)
 static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 				 uint64_t offset, int pid, size_t ref_ctr_off)
 {
-	struct perf_event_attr attr = {};
+	const size_t attr_sz = sizeof(struct perf_event_attr);
+	struct perf_event_attr attr;
 	char errmsg[STRERR_BUFSIZE];
 	int type, pfd;
 
 	if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS))
 		return -EINVAL;
 
+	memset(&attr, 0, attr_sz);
+
 	type = uprobe ? determine_uprobe_perf_type()
 		      : determine_kprobe_perf_type();
 	if (type < 0) {
@@ -9837,7 +9868,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 		}
 		attr.config |= 1 << bit;
 	}
-	attr.size = sizeof(attr);
+	attr.size = attr_sz;
 	attr.type = type;
 	attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT;
 	attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
@@ -9936,7 +9967,8 @@ static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retpro
 static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe,
 					 const char *kfunc_name, size_t offset, int pid)
 {
-	struct perf_event_attr attr = {};
+	const size_t attr_sz = sizeof(struct perf_event_attr);
+	struct perf_event_attr attr;
 	char errmsg[STRERR_BUFSIZE];
 	int type, pfd, err;
 
@@ -9955,7 +9987,9 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		goto err_clean_legacy;
 	}
-	attr.size = sizeof(attr);
+
+	memset(&attr, 0, attr_sz);
+	attr.size = attr_sz;
 	attr.config = type;
 	attr.type = PERF_TYPE_TRACEPOINT;
 
@@ -10412,6 +10446,7 @@ static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retpro
 static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe,
 					 const char *binary_path, size_t offset, int pid)
 {
+	const size_t attr_sz = sizeof(struct perf_event_attr);
 	struct perf_event_attr attr;
 	int type, pfd, err;
 
@@ -10429,8 +10464,8 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe,
 		goto err_clean_legacy;
 	}
 
-	memset(&attr, 0, sizeof(attr));
-	attr.size = sizeof(attr);
+	memset(&attr, 0, attr_sz);
+	attr.size = attr_sz;
 	attr.config = type;
 	attr.type = PERF_TYPE_TRACEPOINT;
 
@@ -10662,15 +10697,17 @@ static const char *arch_specific_lib_paths(void)
 static int resolve_full_path(const char *file, char *result, size_t result_sz)
 {
 	const char *search_paths[3] = {};
-	int i;
+	int i, perm;
 
 	if (str_has_sfx(file, ".so") || strstr(file, ".so.")) {
 		search_paths[0] = getenv("LD_LIBRARY_PATH");
 		search_paths[1] = "/usr/lib64:/usr/lib";
 		search_paths[2] = arch_specific_lib_paths();
+		perm = R_OK;
 	} else {
 		search_paths[0] = getenv("PATH");
 		search_paths[1] = "/usr/bin:/usr/sbin";
+		perm = R_OK | X_OK;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(search_paths); i++) {
@@ -10689,8 +10726,8 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz)
 			if (!seg_len)
 				continue;
 			snprintf(result, result_sz, "%.*s/%s", seg_len, s, file);
-			/* ensure it is an executable file/link */
-			if (access(result, R_OK | X_OK) < 0)
+			/* ensure it has required permissions */
+			if (access(result, perm) < 0)
 				continue;
 			pr_debug("resolved '%s' to '%s'\n", file, result);
 			return 0;
@@ -10967,7 +11004,8 @@ static int determine_tracepoint_id(const char *tp_category,
 static int perf_event_open_tracepoint(const char *tp_category,
 				      const char *tp_name)
 {
-	struct perf_event_attr attr = {};
+	const size_t attr_sz = sizeof(struct perf_event_attr);
+	struct perf_event_attr attr;
 	char errmsg[STRERR_BUFSIZE];
 	int tp_id, pfd, err;
 
@@ -10979,8 +11017,9 @@ static int perf_event_open_tracepoint(const char *tp_category,
 		return tp_id;
 	}
 
+	memset(&attr, 0, attr_sz);
 	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.size = sizeof(attr);
+	attr.size = attr_sz;
 	attr.config = tp_id;
 
 	pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */,
@@ -11600,12 +11639,15 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt,
 				     void *ctx,
 				     const struct perf_buffer_opts *opts)
 {
+	const size_t attr_sz = sizeof(struct perf_event_attr);
 	struct perf_buffer_params p = {};
-	struct perf_event_attr attr = {};
+	struct perf_event_attr attr;
 
 	if (!OPTS_VALID(opts, perf_buffer_opts))
 		return libbpf_err_ptr(-EINVAL);
 
+	memset(&attr, 0, attr_sz);
+	attr.size = attr_sz;
 	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.sample_type = PERF_SAMPLE_RAW;
@@ -12328,7 +12370,7 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 		struct bpf_program *prog = *s->progs[i].prog;
 		struct bpf_link **link = s->progs[i].link;
 
-		if (!prog->autoload)
+		if (!prog->autoload || !prog->autoattach)
 			continue;
 
 		/* auto-attaching not supported for this program */

tools/lib/bpf/libbpf.h

@@ -260,6 +260,8 @@ LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog);
 LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog);
 LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
+LIBBPF_API bool bpf_program__autoattach(const struct bpf_program *prog);
+LIBBPF_API void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach);
 
 struct bpf_insn;
 

tools/lib/bpf/libbpf.map

@@ -358,6 +358,8 @@ LIBBPF_1.0.0 {
 		bpf_obj_get_opts;
 		bpf_prog_query_opts;
 		bpf_program__attach_ksyscall;
+		bpf_program__autoattach;
+		bpf_program__set_autoattach;
 		btf__add_enum64;
 		btf__add_enum64_value;
 		libbpf_bpf_attach_type_str;

tools/lib/bpf/libbpf_internal.h

@@ -573,4 +573,7 @@ static inline bool is_pow_of_2(size_t x)
 	return x && (x & (x - 1)) == 0;
 }
 
+#define PROG_LOAD_ATTEMPTS 5
+int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts);
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */

tools/lib/bpf/libbpf_legacy.h

@@ -125,6 +125,8 @@ struct bpf_map;
 struct btf;
 struct btf_ext;
 
+LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
+
 LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog);
 LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog);
 LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);

tools/lib/bpf/libbpf_probes.c

@@ -193,7 +193,7 @@ static int probe_map_create(enum bpf_map_type map_type)
 	LIBBPF_OPTS(bpf_map_create_opts, opts);
 	int key_size, value_size, max_entries;
 	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
-	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err;
+	int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);

tools/lib/bpf/netlink.c

@@ -587,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
 
 static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd)
 {
-	struct bpf_prog_info info = {};
+	struct bpf_prog_info info;
 	__u32 info_len = sizeof(info);
 	char name[256];
 	int len, ret;
 
+	memset(&info, 0, info_len);
 	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
 	if (ret < 0)
 		return ret;

tools/lib/bpf/skel_internal.h

@@ -285,6 +285,8 @@ static inline int skel_link_create(int prog_fd, int target_fd,
 
 static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 {
+	const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array);
+	const size_t test_run_attr_sz = offsetofend(union bpf_attr, test);
 	int map_fd = -1, prog_fd = -1, key = 0, err;
 	union bpf_attr attr;
 
@@ -302,7 +304,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, prog_load_attr_sz);
 	attr.prog_type = BPF_PROG_TYPE_SYSCALL;
 	attr.insns = (long) opts->insns;
 	attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn);
@@ -313,18 +315,18 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	attr.log_size = opts->ctx->log_size;
 	attr.log_buf = opts->ctx->log_buf;
 	attr.prog_flags = BPF_F_SLEEPABLE;
-	err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+	err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, prog_load_attr_sz);
 	if (prog_fd < 0) {
 		opts->errstr = "failed to load loader prog";
 		set_err;
 		goto out;
 	}
 
-	memset(&attr, 0, sizeof(attr));
+	memset(&attr, 0, test_run_attr_sz);
 	attr.test.prog_fd = prog_fd;
 	attr.test.ctx_in = (long) opts->ctx;
 	attr.test.ctx_size_in = opts->ctx->sz;
-	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
+	err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz);
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
 		if (err < 0) {

tools/lib/bpf/usdt.bpf.h

@@ -232,7 +232,7 @@ long bpf_usdt_cookie(struct pt_regs *ctx)
  */
 #define BPF_USDT(name, args...)						    \
 name(struct pt_regs *ctx);						    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args);				    \
 typeof(name(0)) name(struct pt_regs *ctx)				    \
 {									    \
@@ -241,7 +241,7 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
         return ____##name(___bpf_usdt_args(args));			    \
         _Pragma("GCC diagnostic pop")					    \
 }									    \
-static __attribute__((always_inline)) typeof(name(0))			    \
+static __always_inline typeof(name(0))					    \
 ____##name(struct pt_regs *ctx, ##args)
 
 #endif /* __USDT_BPF_H__ */

tools/testing/selftests/bpf/DENYLIST.s390x

@@ -43,7 +43,7 @@ test_bpffs                               # bpffs test  failed 255
 test_bprm_opts                           # failed to auto-attach program 'secure_exec': -524                           (trampoline)
 test_ima                                 # failed to auto-attach program 'ima': -524                                   (trampoline)
 test_local_storage                       # failed to auto-attach program 'unlink_hook': -524                           (trampoline)
-test_lsm                                 # failed to find kernel BTF type ID of '__x64_sys_setdomainname': -3          (?)
+test_lsm                                 # attach unexpected error: -524                                               (trampoline)
 test_overhead                            # attach_fentry unexpected error: -524                                        (trampoline)
 test_profiler                            # unknown func bpf_probe_read_str#45                                          (overlapping)
 timer                                    # failed to auto-attach program 'test1': -524                                 (trampoline)

tools/testing/selftests/bpf/config

@@ -50,9 +50,11 @@ CONFIG_NET_SCHED=y
 CONFIG_NETDEVSIM=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_SYNPROXY=y
+CONFIG_NETFILTER_XT_CONNMARK=y
 CONFIG_NETFILTER_XT_MATCH_STATE=y
 CONFIG_NETFILTER_XT_TARGET_CT=y
 CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_DEFRAG_IPV4=y
 CONFIG_NF_DEFRAG_IPV6=y
 CONFIG_RC_CORE=y

tools/testing/selftests/bpf/prog_tests/attach_probe.c

@@ -6,19 +6,19 @@
 volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
 
 /* uprobe attach point */
-static void trigger_func(void)
+static noinline void trigger_func(void)
 {
 	asm volatile ("");
 }
 
 /* attach point for byname uprobe */
-static void trigger_func2(void)
+static noinline void trigger_func2(void)
 {
 	asm volatile ("");
 }
 
 /* attach point for byname sleepable uprobe */
-static void trigger_func3(void)
+static noinline void trigger_func3(void)
 {
 	asm volatile ("");
 }

tools/testing/selftests/bpf/prog_tests/autoattach.c

@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Google */
+
+#include <test_progs.h>
+#include "test_autoattach.skel.h"
+
+void test_autoattach(void)
+{
+	struct test_autoattach *skel;
+
+	skel = test_autoattach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto cleanup;
+
+	/* disable auto-attach for prog2 */
+	bpf_program__set_autoattach(skel->progs.prog2, false);
+	ASSERT_TRUE(bpf_program__autoattach(skel->progs.prog1), "autoattach_prog1");
+	ASSERT_FALSE(bpf_program__autoattach(skel->progs.prog2), "autoattach_prog2");
+	if (!ASSERT_OK(test_autoattach__attach(skel), "skel_attach"))
+		goto cleanup;
+
+	usleep(1);
+
+	ASSERT_TRUE(skel->bss->prog1_called, "attached_prog1");
+	ASSERT_FALSE(skel->bss->prog2_called, "attached_prog2");
+
+cleanup:
+	test_autoattach__destroy(skel);
+}
+

tools/testing/selftests/bpf/prog_tests/bpf_cookie.c

@@ -13,7 +13,7 @@
 #include "kprobe_multi.skel.h"
 
 /* uprobe attach point */
-static void trigger_func(void)
+static noinline void trigger_func(void)
 {
 	asm volatile ("");
 }

tools/testing/selftests/bpf/prog_tests/bpf_nf.c

@@ -24,10 +24,34 @@ enum {
 	TEST_TC_BPF,
 };
 
+#define TIMEOUT_MS 3000
+
+static int connect_to_server(int srv_fd)
+{
+	int fd = -1;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(fd, 0, "socket"))
+		goto out;
+
+	if (!ASSERT_EQ(connect_fd_to_fd(fd, srv_fd, TIMEOUT_MS), 0, "connect_fd_to_fd")) {
+		close(fd);
+		fd = -1;
+	}
+out:
+	return fd;
+}
+
 static void test_bpf_nf_ct(int mode)
 {
+	const char *iptables = "iptables -t raw %s PREROUTING -j CONNMARK --set-mark 42/0";
+	int srv_fd = -1, client_fd = -1, srv_client_fd = -1;
+	struct sockaddr_in peer_addr = {};
 	struct test_bpf_nf *skel;
 	int prog_fd, err;
+	socklen_t len;
+	u16 srv_port;
+	char cmd[64];
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
@@ -38,6 +62,32 @@ static void test_bpf_nf_ct(int mode)
 	if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load"))
 		return;
 
+	/* Enable connection tracking */
+	snprintf(cmd, sizeof(cmd), iptables, "-A");
+	if (!ASSERT_OK(system(cmd), "iptables"))
+		goto end;
+
+	srv_port = (mode == TEST_XDP) ? 5005 : 5006;
+	srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", srv_port, TIMEOUT_MS);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto end;
+
+	client_fd = connect_to_server(srv_fd);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_server"))
+		goto end;
+
+	len = sizeof(peer_addr);
+	srv_client_fd = accept(srv_fd, (struct sockaddr *)&peer_addr, &len);
+	if (!ASSERT_GE(srv_client_fd, 0, "accept"))
+		goto end;
+	if (!ASSERT_EQ(len, sizeof(struct sockaddr_in), "sockaddr len"))
+		goto end;
+
+	skel->bss->saddr = peer_addr.sin_addr.s_addr;
+	skel->bss->sport = peer_addr.sin_port;
+	skel->bss->daddr = peer_addr.sin_addr.s_addr;
+	skel->bss->dport = htons(srv_port);
+
 	if (mode == TEST_XDP)
 		prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test);
 	else
@@ -63,7 +113,17 @@ static void test_bpf_nf_ct(int mode)
 	ASSERT_LE(skel->bss->test_delta_timeout, 10, "Test for max ct timeout update");
 	/* expected status is IPS_SEEN_REPLY */
 	ASSERT_EQ(skel->bss->test_status, 2, "Test for ct status update ");
+	ASSERT_EQ(skel->data->test_exist_lookup, 0, "Test existing connection lookup");
+	ASSERT_EQ(skel->bss->test_exist_lookup_mark, 43, "Test existing connection lookup ctmark");
 end:
+	if (srv_client_fd != -1)
+		close(srv_client_fd);
+	if (client_fd != -1)
+		close(client_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	snprintf(cmd, sizeof(cmd), iptables, "-D");
+	system(cmd);
 	test_bpf_nf__destroy(skel);
 }
 

tools/testing/selftests/bpf/prog_tests/dynptr.c

@@ -22,7 +22,8 @@ static struct {
 	{"add_dynptr_to_map2", "invalid indirect read from stack"},
 	{"data_slice_out_of_bounds_ringbuf", "value is outside of the allowed memory range"},
 	{"data_slice_out_of_bounds_map_value", "value is outside of the allowed memory range"},
-	{"data_slice_use_after_release", "invalid mem access 'scalar'"},
+	{"data_slice_use_after_release1", "invalid mem access 'scalar'"},
+	{"data_slice_use_after_release2", "invalid mem access 'scalar'"},
 	{"data_slice_missing_null_check1", "invalid mem access 'mem_or_null'"},
 	{"data_slice_missing_null_check2", "invalid mem access 'mem_or_null'"},
 	{"invalid_helper1", "invalid indirect read from stack"},

tools/testing/selftests/bpf/prog_tests/kfunc_call.c

@@ -5,6 +5,9 @@
 #include "kfunc_call_test.lskel.h"
 #include "kfunc_call_test_subprog.skel.h"
 #include "kfunc_call_test_subprog.lskel.h"
+#include "kfunc_call_destructive.skel.h"
+
+#include "cap_helpers.h"
 
 static void test_main(void)
 {
@@ -86,6 +89,36 @@ static void test_subprog_lskel(void)
 	kfunc_call_test_subprog_lskel__destroy(skel);
 }
 
+static int test_destructive_open_and_load(void)
+{
+	struct kfunc_call_destructive *skel;
+	int err;
+
+	skel = kfunc_call_destructive__open();
+	if (!ASSERT_OK_PTR(skel, "prog_open"))
+		return -1;
+
+	err = kfunc_call_destructive__load(skel);
+
+	kfunc_call_destructive__destroy(skel);
+
+	return err;
+}
+
+static void test_destructive(void)
+{
+	__u64 save_caps = 0;
+
+	ASSERT_OK(test_destructive_open_and_load(), "succesful_load");
+
+	if (!ASSERT_OK(cap_disable_effective(1ULL << CAP_SYS_BOOT, &save_caps), "drop_caps"))
+		return;
+
+	ASSERT_EQ(test_destructive_open_and_load(), -13, "no_caps_failure");
+
+	cap_enable_effective(save_caps, NULL);
+}
+
 void test_kfunc_call(void)
 {
 	if (test__start_subtest("main"))
@@ -96,4 +129,7 @@ void test_kfunc_call(void)
 
 	if (test__start_subtest("subprog_lskel"))
 		test_subprog_lskel();
+
+	if (test__start_subtest("destructive"))
+		test_destructive();
 }

tools/testing/selftests/bpf/prog_tests/task_pt_regs.c

@@ -4,7 +4,7 @@
 #include "test_task_pt_regs.skel.h"
 
 /* uprobe attach point */
-static void trigger_func(void)
+static noinline void trigger_func(void)
 {
 	asm volatile ("");
 }

tools/testing/selftests/bpf/prog_tests/time_tai.c

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022 Linutronix GmbH */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "test_time_tai.skel.h"
+
+#include <time.h>
+#include <stdint.h>
+
+#define TAI_THRESHOLD	1000000000ULL /* 1s */
+#define NSEC_PER_SEC	1000000000ULL
+
+static __u64 ts_to_ns(const struct timespec *ts)
+{
+	return ts->tv_sec * NSEC_PER_SEC + ts->tv_nsec;
+}
+
+void test_time_tai(void)
+{
+	struct __sk_buff skb = {
+		.cb[0] = 0,
+		.cb[1] = 0,
+		.tstamp = 0,
+	};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.ctx_in = &skb,
+		.ctx_size_in = sizeof(skb),
+		.ctx_out = &skb,
+		.ctx_size_out = sizeof(skb),
+	);
+	struct test_time_tai *skel;
+	struct timespec now_tai;
+	__u64 ts1, ts2, now;
+	int ret, prog_fd;
+
+	/* Open and load */
+	skel = test_time_tai__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "tai_open"))
+		return;
+
+	/* Run test program */
+	prog_fd = bpf_program__fd(skel->progs.time_tai);
+	ret = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(ret, "test_run");
+
+	/* Retrieve generated TAI timestamps */
+	ts1 = skb.tstamp;
+	ts2 = skb.cb[0] | ((__u64)skb.cb[1] << 32);
+
+	/* TAI != 0 */
+	ASSERT_NEQ(ts1, 0, "tai_ts1");
+	ASSERT_NEQ(ts2, 0, "tai_ts2");
+
+	/* TAI is moving forward only */
+	ASSERT_GT(ts2, ts1, "tai_forward");
+
+	/* Check for future */
+	ret = clock_gettime(CLOCK_TAI, &now_tai);
+	ASSERT_EQ(ret, 0, "tai_gettime");
+	now = ts_to_ns(&now_tai);
+
+	ASSERT_TRUE(now > ts1, "tai_future_ts1");
+	ASSERT_TRUE(now > ts2, "tai_future_ts2");
+
+	/* Check for reasonable range */
+	ASSERT_TRUE(now - ts1 < TAI_THRESHOLD, "tai_range_ts1");
+	ASSERT_TRUE(now - ts2 < TAI_THRESHOLD, "tai_range_ts2");
+
+	test_time_tai__destroy(skel);
+}

tools/testing/selftests/bpf/progs/dynptr_fail.c

@@ -65,7 +65,7 @@ static int get_map_val_dynptr(struct bpf_dynptr *ptr)
 /* Every bpf_ringbuf_reserve_dynptr call must have a corresponding
  * bpf_ringbuf_submit/discard_dynptr call
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int ringbuf_missing_release1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -77,7 +77,7 @@ int ringbuf_missing_release1(void *ctx)
 	return 0;
 }
 
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int ringbuf_missing_release2(void *ctx)
 {
 	struct bpf_dynptr ptr1, ptr2;
@@ -112,7 +112,7 @@ static int missing_release_callback_fn(__u32 index, void *data)
 }
 
 /* Any dynptr initialized within a callback must have bpf_dynptr_put called */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int ringbuf_missing_release_callback(void *ctx)
 {
 	bpf_loop(10, missing_release_callback_fn, NULL, 0);
@@ -120,7 +120,7 @@ int ringbuf_missing_release_callback(void *ctx)
 }
 
 /* Can't call bpf_ringbuf_submit/discard_dynptr on a non-initialized dynptr */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int ringbuf_release_uninit_dynptr(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -132,7 +132,7 @@ int ringbuf_release_uninit_dynptr(void *ctx)
 }
 
 /* A dynptr can't be used after it has been invalidated */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int use_after_invalid(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -151,7 +151,7 @@ int use_after_invalid(void *ctx)
 }
 
 /* Can't call non-dynptr ringbuf APIs on a dynptr ringbuf sample */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int ringbuf_invalid_api(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -173,7 +173,7 @@ done:
 }
 
 /* Can't add a dynptr to a map */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int add_dynptr_to_map1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -190,7 +190,7 @@ int add_dynptr_to_map1(void *ctx)
 }
 
 /* Can't add a struct with an embedded dynptr to a map */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int add_dynptr_to_map2(void *ctx)
 {
 	struct test_info x;
@@ -207,7 +207,7 @@ int add_dynptr_to_map2(void *ctx)
 }
 
 /* A data slice can't be accessed out of bounds */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int data_slice_out_of_bounds_ringbuf(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -227,7 +227,7 @@ done:
 	return 0;
 }
 
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int data_slice_out_of_bounds_map_value(void *ctx)
 {
 	__u32 key = 0, map_val;
@@ -247,8 +247,8 @@ int data_slice_out_of_bounds_map_value(void *ctx)
 }
 
 /* A data slice can't be used after it has been released */
-SEC("?raw_tp/sys_nanosleep")
-int data_slice_use_after_release(void *ctx)
+SEC("?raw_tp")
+int data_slice_use_after_release1(void *ctx)
 {
 	struct bpf_dynptr ptr;
 	struct sample *sample;
@@ -272,8 +272,44 @@ done:
 	return 0;
 }
 
+/* A data slice can't be used after it has been released.
+ *
+ * This tests the case where the data slice tracks a dynptr (ptr2)
+ * that is at a non-zero offset from the frame pointer (ptr1 is at fp,
+ * ptr2 is at fp - 16).
+ */
+SEC("?raw_tp")
+int data_slice_use_after_release2(void *ctx)
+{
+	struct bpf_dynptr ptr1, ptr2;
+	struct sample *sample;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr1);
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(*sample), 0, &ptr2);
+
+	sample = bpf_dynptr_data(&ptr2, 0, sizeof(*sample));
+	if (!sample)
+		goto done;
+
+	sample->pid = 23;
+
+	bpf_ringbuf_submit_dynptr(&ptr2, 0);
+
+	/* this should fail */
+	sample->pid = 23;
+
+	bpf_ringbuf_submit_dynptr(&ptr1, 0);
+
+	return 0;
+
+done:
+	bpf_ringbuf_discard_dynptr(&ptr2, 0);
+	bpf_ringbuf_discard_dynptr(&ptr1, 0);
+	return 0;
+}
+
 /* A data slice must be first checked for NULL */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int data_slice_missing_null_check1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -293,7 +329,7 @@ int data_slice_missing_null_check1(void *ctx)
 }
 
 /* A data slice can't be dereferenced if it wasn't checked for null */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int data_slice_missing_null_check2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -315,7 +351,7 @@ done:
 /* Can't pass in a dynptr as an arg to a helper function that doesn't take in a
  * dynptr argument
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_helper1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -329,7 +365,7 @@ int invalid_helper1(void *ctx)
 }
 
 /* A dynptr can't be passed into a helper function at a non-zero offset */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_helper2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -344,7 +380,7 @@ int invalid_helper2(void *ctx)
 }
 
 /* A bpf_dynptr is invalidated if it's been written into */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_write1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -365,7 +401,7 @@ int invalid_write1(void *ctx)
  * A bpf_dynptr can't be used as a dynptr if it has been written into at a fixed
  * offset
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_write2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -388,7 +424,7 @@ int invalid_write2(void *ctx)
  * A bpf_dynptr can't be used as a dynptr if it has been written into at a
  * non-const offset
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_write3(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -419,7 +455,7 @@ static int invalid_write4_callback(__u32 index, void *data)
 /* If the dynptr is written into in a callback function, it should
  * be invalidated as a dynptr
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_write4(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -436,7 +472,7 @@ int invalid_write4(void *ctx)
 
 /* A globally-defined bpf_dynptr can't be used (it must reside as a stack frame) */
 struct bpf_dynptr global_dynptr;
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int global(void *ctx)
 {
 	/* this should fail */
@@ -448,7 +484,7 @@ int global(void *ctx)
 }
 
 /* A direct read should fail */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_read1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -464,7 +500,7 @@ int invalid_read1(void *ctx)
 }
 
 /* A direct read at an offset should fail */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_read2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -479,7 +515,7 @@ int invalid_read2(void *ctx)
 }
 
 /* A direct read at an offset into the lower stack slot should fail */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_read3(void *ctx)
 {
 	struct bpf_dynptr ptr1, ptr2;
@@ -505,7 +541,7 @@ static int invalid_read4_callback(__u32 index, void *data)
 }
 
 /* A direct read within a callback function should fail */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_read4(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -520,7 +556,7 @@ int invalid_read4(void *ctx)
 }
 
 /* Initializing a dynptr on an offset should fail */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int invalid_offset(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -534,7 +570,7 @@ int invalid_offset(void *ctx)
 }
 
 /* Can't release a dynptr twice */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int release_twice(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -560,7 +596,7 @@ static int release_twice_callback_fn(__u32 index, void *data)
 /* Test that releasing a dynptr twice, where one of the releases happens
  * within a calback function, fails
  */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int release_twice_callback(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -575,7 +611,7 @@ int release_twice_callback(void *ctx)
 }
 
 /* Reject unsupported local mem types for dynptr_from_mem API */
-SEC("?raw_tp/sys_nanosleep")
+SEC("?raw_tp")
 int dynptr_from_mem_invalid_api(void *ctx)
 {
 	struct bpf_dynptr ptr;

tools/testing/selftests/bpf/progs/kfunc_call_destructive.c

@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+extern void bpf_kfunc_call_test_destructive(void) __ksym;
+
+SEC("tc")
+int kfunc_destructive_test(void)
+{
+	bpf_kfunc_call_test_destructive();
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/lsm.c

@@ -4,6 +4,7 @@
  * Copyright 2020 Google LLC.
  */
 
+#include "bpf_misc.h"
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
@@ -160,7 +161,7 @@ int BPF_PROG(test_task_free, struct task_struct *task)
 
 int copy_test = 0;
 
-SEC("fentry.s/__x64_sys_setdomainname")
+SEC("fentry.s/" SYS_PREFIX "sys_setdomainname")
 int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs)
 {
 	void *ptr = (void *)PT_REGS_PARM1(regs);

tools/testing/selftests/bpf/progs/test_autoattach.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Google */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+bool prog1_called = false;
+bool prog2_called = false;
+
+SEC("raw_tp/sys_enter")
+int prog1(const void *ctx)
+{
+	prog1_called = true;
+	return 0;
+}
+
+SEC("raw_tp/sys_exit")
+int prog2(const void *ctx)
+{
+	prog2_called = true;
+	return 0;
+}
+

tools/testing/selftests/bpf/progs/test_bpf_cookie.c

@@ -28,14 +28,14 @@ static void update(void *ctx, __u64 *res)
 	*res |= bpf_get_attach_cookie(ctx);
 }
 
-SEC("kprobe/sys_nanosleep")
+SEC("kprobe")
 int handle_kprobe(struct pt_regs *ctx)
 {
 	update(ctx, &kprobe_res);
 	return 0;
 }
 
-SEC("kretprobe/sys_nanosleep")
+SEC("kretprobe")
 int handle_kretprobe(struct pt_regs *ctx)
 {
 	update(ctx, &kretprobe_res);

tools/testing/selftests/bpf/progs/test_bpf_nf.c

@@ -23,6 +23,12 @@ int test_insert_entry = -EAFNOSUPPORT;
 int test_succ_lookup = -ENOENT;
 u32 test_delta_timeout = 0;
 u32 test_status = 0;
+__be32 saddr = 0;
+__be16 sport = 0;
+__be32 daddr = 0;
+__be16 dport = 0;
+int test_exist_lookup = -ENOENT;
+u32 test_exist_lookup_mark = 0;
 
 struct nf_conn;
 
@@ -160,6 +166,21 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 		}
 		test_alloc_entry = 0;
 	}
+
+	bpf_tuple.ipv4.saddr = saddr;
+	bpf_tuple.ipv4.daddr = daddr;
+	bpf_tuple.ipv4.sport = sport;
+	bpf_tuple.ipv4.dport = dport;
+	ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+		       sizeof(opts_def));
+	if (ct) {
+		test_exist_lookup = 0;
+		if (ct->mark == 42)
+			test_exist_lookup_mark = 43;
+		bpf_ct_release(ct);
+	} else {
+		test_exist_lookup = opts_def.error;
+	}
 }
 
 SEC("xdp")

tools/testing/selftests/bpf/progs/test_helper_restricted.c

@@ -72,7 +72,7 @@ int tp_timer(void *ctx)
 	return 0;
 }
 
-SEC("?kprobe/sys_nanosleep")
+SEC("?kprobe")
 int kprobe_timer(void *ctx)
 {
 	timer_work();
@@ -104,7 +104,7 @@ int tp_spin_lock(void *ctx)
 	return 0;
 }
 
-SEC("?kprobe/sys_nanosleep")
+SEC("?kprobe")
 int kprobe_spin_lock(void *ctx)
 {
 	spin_lock_work();

tools/testing/selftests/bpf/progs/test_time_tai.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2022 Linutronix GmbH */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tc")
+int time_tai(struct __sk_buff *skb)
+{
+	__u64 ts1, ts2;
+
+	/* Get TAI timestamps */
+	ts1 = bpf_ktime_get_tai_ns();
+	ts2 = bpf_ktime_get_tai_ns();
+
+	/* Save TAI timestamps (Note: skb->hwtstamp is read-only) */
+	skb->tstamp = ts1;
+	skb->cb[0] = ts2 & 0xffffffff;
+	skb->cb[1] = ts2 >> 32;
+
+	return 0;
+}

tools/testing/selftests/bpf/vmtest.sh

@@ -307,6 +307,20 @@ update_kconfig()
 	fi
 }
 
+catch()
+{
+	local exit_code=$1
+	local exit_status_file="${OUTPUT_DIR}/${EXIT_STATUS_FILE}"
+	# This is just a cleanup and the directory may
+	# have already been unmounted. So, don't let this
+	# clobber the error code we intend to return.
+	unmount_image || true
+	if [[ -f "${exit_status_file}" ]]; then
+		exit_code="$(cat ${exit_status_file})"
+	fi
+	exit ${exit_code}
+}
+
 main()
 {
 	local script_dir="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
@@ -319,7 +333,7 @@ main()
 	local exit_command="poweroff -f"
 	local debug_shell="no"
 
-	while getopts 'hskid:j:' opt; do
+	while getopts ':hskid:j:' opt; do
 		case ${opt} in
 		i)
 			update_image="yes"
@@ -353,6 +367,8 @@ main()
 	done
 	shift $((OPTIND -1))
 
+	trap 'catch "$?"' EXIT
+
 	if [[ $# -eq 0  && "${debug_shell}" == "no" ]]; then
 		echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
 	else
@@ -409,20 +425,4 @@ main()
 	fi
 }
 
-catch()
-{
-	local exit_code=$1
-	local exit_status_file="${OUTPUT_DIR}/${EXIT_STATUS_FILE}"
-	# This is just a cleanup and the directory may
-	# have already been unmounted. So, don't let this
-	# clobber the error code we intend to return.
-	unmount_image || true
-	if [[ -f "${exit_status_file}" ]]; then
-		exit_code="$(cat ${exit_status_file})"
-	fi
-	exit ${exit_code}
-}
-
-trap 'catch "$?"' EXIT
-
 main "$@"

tools/testing/selftests/bpf/xskxceiver.c

@@ -244,6 +244,11 @@ static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject,
 	memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE);
 }
 
+static bool is_umem_valid(struct ifobject *ifobj)
+{
+	return !!ifobj->umem->umem;
+}
+
 static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
 {
 	udp_hdr->check = 0;
@@ -817,12 +822,13 @@ static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 	return TEST_PASS;
 }
 
-static int receive_pkts(struct ifobject *ifobj, struct pollfd *fds)
+static int receive_pkts(struct test_spec *test, struct pollfd *fds)
 {
-	struct timeval tv_end, tv_now, tv_timeout = {RECV_TMOUT, 0};
+	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
+	struct pkt_stream *pkt_stream = test->ifobj_rx->pkt_stream;
 	u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkts_sent = 0;
-	struct pkt_stream *pkt_stream = ifobj->pkt_stream;
-	struct xsk_socket_info *xsk = ifobj->xsk;
+	struct xsk_socket_info *xsk = test->ifobj_rx->xsk;
+	struct ifobject *ifobj = test->ifobj_rx;
 	struct xsk_umem_info *umem = xsk->umem;
 	struct pkt *pkt;
 	int ret;
@@ -843,16 +849,27 @@ static int receive_pkts(struct ifobject *ifobj, struct pollfd *fds)
 		}
 
 		kick_rx(xsk);
+		if (ifobj->use_poll) {
+			ret = poll(fds, 1, POLL_TMOUT);
+			if (ret < 0)
+				exit_with_error(-ret);
+
+			if (!ret) {
+				if (!is_umem_valid(test->ifobj_tx))
+					return TEST_PASS;
+
+				ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
+				return TEST_FAILURE;
+
+			}
+
+			if (!(fds->revents & POLLIN))
+				continue;
+		}
 
 		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
-		if (!rcvd) {
-			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
-				ret = poll(fds, 1, POLL_TMOUT);
-				if (ret < 0)
-					exit_with_error(-ret);
-			}
+		if (!rcvd)
 			continue;
-		}
 
 		if (ifobj->use_fill_ring) {
 			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
@@ -900,13 +917,35 @@ static int receive_pkts(struct ifobject *ifobj, struct pollfd *fds)
 	return TEST_PASS;
 }
 
-static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb)
+static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds,
+		       bool timeout)
 {
 	struct xsk_socket_info *xsk = ifobject->xsk;
-	u32 i, idx, valid_pkts = 0;
+	bool use_poll = ifobject->use_poll;
+	u32 i, idx = 0, ret, valid_pkts = 0;
+
+	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) {
+		if (use_poll) {
+			ret = poll(fds, 1, POLL_TMOUT);
+			if (timeout) {
+				if (ret < 0) {
+					ksft_print_msg("ERROR: [%s] Poll error %d\n",
+						       __func__, ret);
+					return TEST_FAILURE;
+				}
+				if (ret == 0)
+					return TEST_PASS;
+				break;
+			}
+			if (ret <= 0) {
+				ksft_print_msg("ERROR: [%s] Poll error %d\n",
+					       __func__, ret);
+				return TEST_FAILURE;
+			}
+		}
 
-	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE)
 		complete_pkts(xsk, BATCH_SIZE);
+	}
 
 	for (i = 0; i < BATCH_SIZE; i++) {
 		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
@@ -933,11 +972,27 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb)
 
 	xsk_ring_prod__submit(&xsk->tx, i);
 	xsk->outstanding_tx += valid_pkts;
-	if (complete_pkts(xsk, i))
-		return TEST_FAILURE;
 
-	usleep(10);
-	return TEST_PASS;
+	if (use_poll) {
+		ret = poll(fds, 1, POLL_TMOUT);
+		if (ret <= 0) {
+			if (ret == 0 && timeout)
+				return TEST_PASS;
+
+			ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret);
+			return TEST_FAILURE;
+		}
+	}
+
+	if (!timeout) {
+		if (complete_pkts(xsk, i))
+			return TEST_FAILURE;
+
+		usleep(10);
+		return TEST_PASS;
+	}
+
+	return TEST_CONTINUE;
 }
 
 static void wait_for_tx_completion(struct xsk_socket_info *xsk)
@@ -948,29 +1003,19 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk)
 
 static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
 {
+	bool timeout = !is_umem_valid(test->ifobj_rx);
 	struct pollfd fds = { };
-	u32 pkt_cnt = 0;
+	u32 pkt_cnt = 0, ret;
 
 	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds.events = POLLOUT;
 
 	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
-		int err;
-
-		if (ifobject->use_poll) {
-			int ret;
-
-			ret = poll(&fds, 1, POLL_TMOUT);
-			if (ret <= 0)
-				continue;
-
-			if (!(fds.revents & POLLOUT))
-				continue;
-		}
-
-		err = __send_pkts(ifobject, &pkt_cnt);
-		if (err || test->fail)
+		ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout);
+		if ((ret || test->fail) && !timeout)
 			return TEST_FAILURE;
+		else if (ret == TEST_PASS && timeout)
+			return ret;
 	}
 
 	wait_for_tx_completion(ifobject->xsk);
@@ -1235,7 +1280,7 @@ static void *worker_testapp_validate_rx(void *arg)
 
 	pthread_barrier_wait(&barr);
 
-	err = receive_pkts(ifobject, &fds);
+	err = receive_pkts(test, &fds);
 
 	if (!err && ifobject->validation_func)
 		err = ifobject->validation_func(ifobject);
@@ -1251,6 +1296,33 @@ static void *worker_testapp_validate_rx(void *arg)
 	pthread_exit(NULL);
 }
 
+static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj,
+						  enum test_type type)
+{
+	pthread_t t0;
+
+	if (pthread_barrier_init(&barr, NULL, 2))
+		exit_with_error(errno);
+
+	test->current_step++;
+	if (type  == TEST_TYPE_POLL_RXQ_TMOUT)
+		pkt_stream_reset(ifobj->pkt_stream);
+	pkts_in_flight = 0;
+
+	/*Spawn thread */
+	pthread_create(&t0, NULL, ifobj->func_ptr, test);
+
+	if (type != TEST_TYPE_POLL_TXQ_TMOUT)
+		pthread_barrier_wait(&barr);
+
+	if (pthread_barrier_destroy(&barr))
+		exit_with_error(errno);
+
+	pthread_join(t0, NULL);
+
+	return !!test->fail;
+}
+
 static int testapp_validate_traffic(struct test_spec *test)
 {
 	struct ifobject *ifobj_tx = test->ifobj_tx;
@@ -1548,12 +1620,30 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 
 		pkt_stream_restore_default(test);
 		break;
-	case TEST_TYPE_POLL:
-		test->ifobj_tx->use_poll = true;
+	case TEST_TYPE_RX_POLL:
 		test->ifobj_rx->use_poll = true;
-		test_spec_set_name(test, "POLL");
+		test_spec_set_name(test, "POLL_RX");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_TX_POLL:
+		test->ifobj_tx->use_poll = true;
+		test_spec_set_name(test, "POLL_TX");
+		testapp_validate_traffic(test);
+		break;
+	case TEST_TYPE_POLL_TXQ_TMOUT:
+		test_spec_set_name(test, "POLL_TXQ_FULL");
+		test->ifobj_tx->use_poll = true;
+		/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
+		test->ifobj_tx->umem->frame_size = 2048;
+		pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048);
+		testapp_validate_traffic_single_thread(test, test->ifobj_tx, type);
+		pkt_stream_restore_default(test);
+		break;
+	case TEST_TYPE_POLL_RXQ_TMOUT:
+		test_spec_set_name(test, "POLL_RXQ_EMPTY");
+		test->ifobj_rx->use_poll = true;
+		testapp_validate_traffic_single_thread(test, test->ifobj_rx, type);
+		break;
 	case TEST_TYPE_ALIGNED_INV_DESC:
 		test_spec_set_name(test, "ALIGNED_INV_DESC");
 		testapp_invalid_desc(test);

tools/testing/selftests/bpf/xskxceiver.h

@@ -27,6 +27,7 @@
 
 #define TEST_PASS 0
 #define TEST_FAILURE -1
+#define TEST_CONTINUE 1
 #define MAX_INTERFACES 2
 #define MAX_INTERFACE_NAME_CHARS 7
 #define MAX_INTERFACES_NAMESPACE_CHARS 10
@@ -48,7 +49,7 @@
 #define SOCK_RECONF_CTR 10
 #define BATCH_SIZE 64
 #define POLL_TMOUT 1000
-#define RECV_TMOUT 3
+#define THREAD_TMOUT 3
 #define DEFAULT_PKT_CNT (4 * 1024)
 #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
 #define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE)
@@ -68,7 +69,10 @@ enum test_type {
 	TEST_TYPE_RUN_TO_COMPLETION,
 	TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME,
 	TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT,
-	TEST_TYPE_POLL,
+	TEST_TYPE_RX_POLL,
+	TEST_TYPE_TX_POLL,
+	TEST_TYPE_POLL_RXQ_TMOUT,
+	TEST_TYPE_POLL_TXQ_TMOUT,
 	TEST_TYPE_UNALIGNED,
 	TEST_TYPE_ALIGNED_INV_DESC,
 	TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME,