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

Andrii Nakryiko says:

====================
pull-request: bpf-next 2023-03-08

We've added 23 non-merge commits during the last 2 day(s) which contain
a total of 28 files changed, 414 insertions(+), 104 deletions(-).

The main changes are:

1) Add more precise memory usage reporting for all BPF map types,
   from Yafang Shao.

2) Add ARM32 USDT support to libbpf, from Puranjay Mohan.

3) Fix BTF_ID_LIST size causing problems in !CONFIG_DEBUG_INFO_BTF,
   from Nathan Chancellor.

4) IMA selftests fix, from Roberto Sassu.

5) libbpf fix in APK support code, from Daniel Müller.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (23 commits)
  selftests/bpf: Fix IMA test
  libbpf: USDT arm arg parsing support
  libbpf: Refactor parse_usdt_arg() to re-use code
  libbpf: Fix theoretical u32 underflow in find_cd() function
  bpf: enforce all maps having memory usage callback
  bpf: offload map memory usage
  bpf, net: xskmap memory usage
  bpf, net: sock_map memory usage
  bpf, net: bpf_local_storage memory usage
  bpf: local_storage memory usage
  bpf: bpf_struct_ops memory usage
  bpf: queue_stack_maps memory usage
  bpf: devmap memory usage
  bpf: cpumap memory usage
  bpf: bloom_filter memory usage
  bpf: ringbuf memory usage
  bpf: reuseport_array memory usage
  bpf: stackmap memory usage
  bpf: arraymap memory usage
  bpf: hashtab memory usage
  ...
====================

Link: https://lore.kernel.org/r/20230308193533.1671597-1-andrii@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

28 files changed, 414 insertions, 104 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d3456804f7aa64..6792a7940e1e6e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -161,6 +161,8 @@ struct bpf_map_ops {
 				     bpf_callback_t callback_fn,
 				     void *callback_ctx, u64 flags);
 
+	u64 (*map_mem_usage)(const struct bpf_map *map);
+
 	/* BTF id of struct allocated by map_alloc */
 	int *map_btf_id;
 
@@ -2622,6 +2624,7 @@ static inline bool bpf_map_is_offloaded(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
+u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map);
 int bpf_prog_test_run_syscall(struct bpf_prog *prog,
 			      const union bpf_attr *kattr,
 			      union bpf_attr __user *uattr);
@@ -2693,6 +2696,11 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
 
+static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map)
+{
+	return 0;
+}
+
 static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog,
 					    const union bpf_attr *kattr,
 					    union bpf_attr __user *uattr)
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 6d37a40cd90e8d..d934248b8e8134 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -164,5 +164,6 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
 			 void *value, u64 map_flags, gfp_t gfp_flags);
 
 void bpf_local_storage_free_rcu(struct rcu_head *rcu);
+u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map);
 
 #endif /* _BPF_LOCAL_STORAGE_H */
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 3a4f7cd882cac0..00950cc03bff23 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -204,7 +204,7 @@ extern struct btf_id_set8 name;
 
 #else
 
-#define BTF_ID_LIST(name) static u32 __maybe_unused name[16];
+#define BTF_ID_LIST(name) static u32 __maybe_unused name[64];
 #define BTF_ID(prefix, name)
 #define BTF_ID_FLAGS(prefix, name, ...)
 #define BTF_ID_UNUSED
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 3057e1a4a11c63..e96a1151ec759f 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -38,6 +38,7 @@ struct xdp_umem {
 struct xsk_map {
 	struct bpf_map map;
 	spinlock_t lock; /* Synchronize map updates */
+	atomic_t count;
 	struct xdp_sock __rcu *xsk_map[];
 };
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 4847069595569d..1588c793a715c2 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -721,6 +721,28 @@ static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_
 	return num_elems;
 }
 
+static u64 array_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
+	u32 elem_size = array->elem_size;
+	u64 entries = map->max_entries;
+	u64 usage = sizeof(*array);
+
+	if (percpu) {
+		usage += entries * sizeof(void *);
+		usage += entries * elem_size * num_possible_cpus();
+	} else {
+		if (map->map_flags & BPF_F_MMAPABLE) {
+			usage = PAGE_ALIGN(usage);
+			usage += PAGE_ALIGN(entries * elem_size);
+		} else {
+			usage += entries * elem_size;
+		}
+	}
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(array_map_btf_ids, struct, bpf_array)
 const struct bpf_map_ops array_map_ops = {
 	.map_meta_equal = array_map_meta_equal,
@@ -742,6 +764,7 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_array_elem,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
@@ -762,6 +785,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_array_elem,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
@@ -1156,6 +1180,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
 	.map_release_uref = prog_array_map_clear,
 	.map_seq_show_elem = prog_array_map_seq_show_elem,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 };
 
@@ -1257,6 +1282,7 @@ const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
 	.map_release = perf_event_fd_array_release,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 };
 
@@ -1291,6 +1317,7 @@ const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 };
 #endif
@@ -1379,5 +1406,6 @@ const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_lookup_batch = generic_map_lookup_batch,
 	.map_update_batch = generic_map_update_batch,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = array_map_mem_usage,
 	.map_btf_id = &array_map_btf_ids[0],
 };
diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c
index 48ee750849f257..6350c5d35a9bee 100644
--- a/kernel/bpf/bloom_filter.c
+++ b/kernel/bpf/bloom_filter.c
@@ -193,6 +193,17 @@ static int bloom_map_check_btf(const struct bpf_map *map,
 	return btf_type_is_void(key_type) ? 0 : -EINVAL;
 }
 
+static u64 bloom_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_bloom_filter *bloom;
+	u64 bitset_bytes;
+
+	bloom = container_of(map, struct bpf_bloom_filter, map);
+	bitset_bytes = BITS_TO_BYTES((u64)bloom->bitset_mask + 1);
+	bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long));
+	return sizeof(*bloom) + bitset_bytes;
+}
+
 BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter)
 const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -206,5 +217,6 @@ const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_update_elem = bloom_map_update_elem,
 	.map_delete_elem = bloom_map_delete_elem,
 	.map_check_btf = bloom_map_check_btf,
+	.map_mem_usage = bloom_map_mem_usage,
 	.map_btf_id = &bpf_bloom_map_btf_ids[0],
 };
diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c
index 6cdf6d9ed91df9..9ae07aedaf2332 100644
--- a/kernel/bpf/bpf_cgrp_storage.c
+++ b/kernel/bpf/bpf_cgrp_storage.c
@@ -221,6 +221,7 @@ const struct bpf_map_ops cgrp_storage_map_ops = {
 	.map_update_elem = bpf_cgrp_storage_update_elem,
 	.map_delete_elem = bpf_cgrp_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_mem_usage = bpf_local_storage_map_mem_usage,
 	.map_btf_id = &bpf_local_storage_map_btf_id[0],
 	.map_owner_storage_ptr = cgroup_storage_ptr,
 };
diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c
index 05f4c66c9089f6..43e2619c8167d0 100644
--- a/kernel/bpf/bpf_inode_storage.c
+++ b/kernel/bpf/bpf_inode_storage.c
@@ -223,6 +223,7 @@ const struct bpf_map_ops inode_storage_map_ops = {
 	.map_update_elem = bpf_fd_inode_storage_update_elem,
 	.map_delete_elem = bpf_fd_inode_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_mem_usage = bpf_local_storage_map_mem_usage,
 	.map_btf_id = &bpf_local_storage_map_btf_id[0],
 	.map_owner_storage_ptr = inode_storage_ptr,
 };
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index 3d320393a12c9b..d3ba3f2db64051 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -685,6 +685,16 @@ bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage)
 	return free_storage;
 }
 
+u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map;
+	u64 usage = sizeof(*smap);
+
+	/* The dynamically callocated selems are not counted currently. */
+	usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log);
+	return usage;
+}
+
 struct bpf_map *
 bpf_local_storage_map_alloc(union bpf_attr *attr,
 			    struct bpf_local_storage_cache *cache)
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index ece9870cab68e5..38903fb52f98b5 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -641,6 +641,21 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
 	return map;
 }
 
+static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map;
+	const struct bpf_struct_ops *st_ops = st_map->st_ops;
+	const struct btf_type *vt = st_ops->value_type;
+	u64 usage;
+
+	usage = sizeof(*st_map) +
+			vt->size - sizeof(struct bpf_struct_ops_value);
+	usage += vt->size;
+	usage += btf_type_vlen(vt) * sizeof(struct bpf_links *);
+	usage += PAGE_SIZE;
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(bpf_struct_ops_map_btf_ids, struct, bpf_struct_ops_map)
 const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_alloc_check = bpf_struct_ops_map_alloc_check,
@@ -651,6 +666,7 @@ const struct bpf_map_ops bpf_struct_ops_map_ops = {
 	.map_delete_elem = bpf_struct_ops_map_delete_elem,
 	.map_update_elem = bpf_struct_ops_map_update_elem,
 	.map_seq_show_elem = bpf_struct_ops_map_seq_show_elem,
+	.map_mem_usage = bpf_struct_ops_map_mem_usage,
 	.map_btf_id = &bpf_struct_ops_map_btf_ids[0],
 };
 
diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index 1e486055a523dd..20f942229f3c90 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -335,6 +335,7 @@ const struct bpf_map_ops task_storage_map_ops = {
 	.map_update_elem = bpf_pid_task_storage_update_elem,
 	.map_delete_elem = bpf_pid_task_storage_delete_elem,
 	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_mem_usage = bpf_local_storage_map_mem_usage,
 	.map_btf_id = &bpf_local_storage_map_btf_id[0],
 	.map_owner_storage_ptr = task_storage_ptr,
 };
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index d2110c1f6fa64d..871809e71b4e2e 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -673,6 +673,15 @@ static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags)
 				      __cpu_map_lookup_elem);
 }
 
+static u64 cpu_map_mem_usage(const struct bpf_map *map)
+{
+	u64 usage = sizeof(struct bpf_cpu_map);
+
+	/* Currently the dynamically allocated elements are not counted */
+	usage += (u64)map->max_entries * sizeof(struct bpf_cpu_map_entry *);
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map)
 const struct bpf_map_ops cpu_map_ops = {
 	.map_meta_equal		= bpf_map_meta_equal,
@@ -683,6 +692,7 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_lookup_elem	= cpu_map_lookup_elem,
 	.map_get_next_key	= cpu_map_get_next_key,
 	.map_check_btf		= map_check_no_btf,
+	.map_mem_usage		= cpu_map_mem_usage,
 	.map_btf_id		= &cpu_map_btf_ids[0],
 	.map_redirect		= cpu_map_redirect,
 };
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2675fefc6cb626..19b036a228f783 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -819,8 +819,10 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
 		return -EINVAL;
 
 	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
-	if (old_dev)
+	if (old_dev) {
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+		atomic_dec((atomic_t *)&dtab->items);
+	}
 	return 0;
 }
 
@@ -931,6 +933,8 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
 	if (old_dev)
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
+	else
+		atomic_inc((atomic_t *)&dtab->items);
 
 	return 0;
 }
@@ -1016,6 +1020,20 @@ static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags)
 				      __dev_map_hash_lookup_elem);
 }
 
+static u64 dev_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+	u64 usage = sizeof(struct bpf_dtab);
+
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)
+		usage += (u64)dtab->n_buckets * sizeof(struct hlist_head);
+	else
+		usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *);
+	usage += atomic_read((atomic_t *)&dtab->items) *
+			 (u64)sizeof(struct bpf_dtab_netdev);
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab)
 const struct bpf_map_ops dev_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -1026,6 +1044,7 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_update_elem = dev_map_update_elem,
 	.map_delete_elem = dev_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = dev_map_mem_usage,
 	.map_btf_id = &dev_map_btf_ids[0],
 	.map_redirect = dev_map_redirect,
 };
@@ -1039,6 +1058,7 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_update_elem = dev_map_hash_update_elem,
 	.map_delete_elem = dev_map_hash_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = dev_map_mem_usage,
 	.map_btf_id = &dev_map_btf_ids[0],
 	.map_redirect = dev_hash_map_redirect,
 };
@@ -1109,9 +1129,11 @@ static int dev_map_notification(struct notifier_block *notifier,
 				if (!dev || netdev != dev->dev)
 					continue;
 				odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL));
-				if (dev == odev)
+				if (dev == odev) {
 					call_rcu(&dev->rcu,
 						 __dev_map_entry_free);
+					atomic_dec((atomic_t *)&dtab->items);
+				}
 			}
 		}
 		rcu_read_unlock();
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 653aeb481c794b..0df4b0c10f5954 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2190,6 +2190,44 @@ out:
 	return num_elems;
 }
 
+static u64 htab_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+	u32 value_size = round_up(htab->map.value_size, 8);
+	bool prealloc = htab_is_prealloc(htab);
+	bool percpu = htab_is_percpu(htab);
+	bool lru = htab_is_lru(htab);
+	u64 num_entries;
+	u64 usage = sizeof(struct bpf_htab);
+
+	usage += sizeof(struct bucket) * htab->n_buckets;
+	usage += sizeof(int) * num_possible_cpus() * HASHTAB_MAP_LOCK_COUNT;
+	if (prealloc) {
+		num_entries = map->max_entries;
+		if (htab_has_extra_elems(htab))
+			num_entries += num_possible_cpus();
+
+		usage += htab->elem_size * num_entries;
+
+		if (percpu)
+			usage += value_size * num_possible_cpus() * num_entries;
+		else if (!lru)
+			usage += sizeof(struct htab_elem *) * num_possible_cpus();
+	} else {
+#define LLIST_NODE_SZ sizeof(struct llist_node)
+
+		num_entries = htab->use_percpu_counter ?
+					  percpu_counter_sum(&htab->pcount) :
+					  atomic_read(&htab->count);
+		usage += (htab->elem_size + LLIST_NODE_SZ) * num_entries;
+		if (percpu) {
+			usage += (LLIST_NODE_SZ + sizeof(void *)) * num_entries;
+			usage += value_size * num_possible_cpus() * num_entries;
+		}
+	}
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab)
 const struct bpf_map_ops htab_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -2206,6 +2244,7 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab),
 	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
@@ -2227,6 +2266,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_seq_show_elem = htab_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru),
 	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
@@ -2378,6 +2418,7 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
@@ -2397,6 +2438,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
+	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab_lru_percpu),
 	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
@@ -2534,6 +2576,7 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = htab_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = htab_map_mem_usage,
 	BATCH_OPS(htab),
 	.map_btf_id = &htab_map_btf_ids[0],
 };
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index e90d9f63edc5d3..a993560f200acf 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -446,6 +446,12 @@ static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
+static u64 cgroup_storage_map_usage(const struct bpf_map *map)
+{
+	/* Currently the dynamically allocated elements are not counted. */
+	return sizeof(struct bpf_cgroup_storage_map);
+}
+
 BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct,
 		   bpf_cgroup_storage_map)
 const struct bpf_map_ops cgroup_storage_map_ops = {
@@ -457,6 +463,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_delete_elem = cgroup_storage_delete_elem,
 	.map_check_btf = cgroup_storage_check_btf,
 	.map_seq_show_elem = cgroup_storage_seq_show_elem,
+	.map_mem_usage = cgroup_storage_map_usage,
 	.map_btf_id = &cgroup_storage_map_btf_ids[0],
 };
 
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index d833496e9e4263..dc23f2ac9cde15 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -720,6 +720,16 @@ static int trie_check_btf(const struct bpf_map *map,
 	       -EINVAL : 0;
 }
 
+static u64 trie_mem_usage(const struct bpf_map *map)
+{
+	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
+	u64 elem_size;
+
+	elem_size = sizeof(struct lpm_trie_node) + trie->data_size +
+			    trie->map.value_size;
+	return elem_size * READ_ONCE(trie->n_entries);
+}
+
 BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie)
 const struct bpf_map_ops trie_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -733,5 +743,6 @@ const struct bpf_map_ops trie_map_ops = {
 	.map_update_batch = generic_map_update_batch,
 	.map_delete_batch = generic_map_delete_batch,
 	.map_check_btf = trie_check_btf,
+	.map_mem_usage = trie_mem_usage,
 	.map_btf_id = &trie_map_btf_ids[0],
 };
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 0c85e06f7ea7f8..d9c9f45e3529c1 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -563,6 +563,12 @@ void bpf_map_offload_map_free(struct bpf_map *map)
 	bpf_map_area_free(offmap);
 }
 
+u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map)
+{
+	/* The memory dynamically allocated in netdev dev_ops is not counted */
+	return sizeof(struct bpf_offloaded_map);
+}
+
 int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value)
 {
 	struct bpf_offloaded_map *offmap = map_to_offmap(map);
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8a5e060de63bc8..63ecbbcb349dc0 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -246,6 +246,14 @@ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
 	return -EINVAL;
 }
 
+static u64 queue_stack_map_mem_usage(const struct bpf_map *map)
+{
+	u64 usage = sizeof(struct bpf_queue_stack);
+
+	usage += ((u64)map->max_entries + 1) * map->value_size;
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack)
 const struct bpf_map_ops queue_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -259,6 +267,7 @@ const struct bpf_map_ops queue_map_ops = {
 	.map_pop_elem = queue_map_pop_elem,
 	.map_peek_elem = queue_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
+	.map_mem_usage = queue_stack_map_mem_usage,
 	.map_btf_id = &queue_map_btf_ids[0],
 };
 
@@ -274,5 +283,6 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_pop_elem = stack_map_pop_elem,
 	.map_peek_elem = stack_map_peek_elem,
 	.map_get_next_key = queue_stack_map_get_next_key,
+	.map_mem_usage = queue_stack_map_mem_usage,
 	.map_btf_id = &queue_map_btf_ids[0],
 };
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 82c61612f382a6..71cb72f5b73362 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -335,6 +335,13 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
 	return 0;
 }
 
+static u64 reuseport_array_mem_usage(const struct bpf_map *map)
+{
+	struct reuseport_array *array;
+
+	return struct_size(array, ptrs, map->max_entries);
+}
+
 BTF_ID_LIST_SINGLE(reuseport_array_map_btf_ids, struct, reuseport_array)
 const struct bpf_map_ops reuseport_array_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -344,5 +351,6 @@ const struct bpf_map_ops reuseport_array_ops = {
 	.map_lookup_elem = reuseport_array_lookup_elem,
 	.map_get_next_key = reuseport_array_get_next_key,
 	.map_delete_elem = reuseport_array_delete_elem,
+	.map_mem_usage = reuseport_array_mem_usage,
 	.map_btf_id = &reuseport_array_map_btf_ids[0],
 };
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 8732e0aadf3660..0d2a45ff83f15e 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -19,6 +19,7 @@
 	(offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT)
 /* consumer page and producer page */
 #define RINGBUF_POS_PAGES 2
+#define RINGBUF_NR_META_PAGES (RINGBUF_PGOFF + RINGBUF_POS_PAGES)
 
 #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4)
 
@@ -96,7 +97,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node)
 {
 	const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL |
 			    __GFP_NOWARN | __GFP_ZERO;
-	int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES;
+	int nr_meta_pages = RINGBUF_NR_META_PAGES;
 	int nr_data_pages = data_sz >> PAGE_SHIFT;
 	int nr_pages = nr_meta_pages + nr_data_pages;
 	struct page **pages, *page;
@@ -336,6 +337,21 @@ static __poll_t ringbuf_map_poll_user(struct bpf_map *map, struct file *filp,
 	return 0;
 }
 
+static u64 ringbuf_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_ringbuf *rb;
+	int nr_data_pages;
+	int nr_meta_pages;
+	u64 usage = sizeof(struct bpf_ringbuf_map);
+
+	rb = container_of(map, struct bpf_ringbuf_map, map)->rb;
+	usage += (u64)rb->nr_pages << PAGE_SHIFT;
+	nr_meta_pages = RINGBUF_NR_META_PAGES;
+	nr_data_pages = map->max_entries >> PAGE_SHIFT;
+	usage += (nr_meta_pages + 2 * nr_data_pages) * sizeof(struct page *);
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(ringbuf_map_btf_ids, struct, bpf_ringbuf_map)
 const struct bpf_map_ops ringbuf_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -347,6 +363,7 @@ const struct bpf_map_ops ringbuf_map_ops = {
 	.map_update_elem = ringbuf_map_update_elem,
 	.map_delete_elem = ringbuf_map_delete_elem,
 	.map_get_next_key = ringbuf_map_get_next_key,
+	.map_mem_usage = ringbuf_map_mem_usage,
 	.map_btf_id = &ringbuf_map_btf_ids[0],
 };
 
@@ -361,6 +378,7 @@ const struct bpf_map_ops user_ringbuf_map_ops = {
 	.map_update_elem = ringbuf_map_update_elem,
 	.map_delete_elem = ringbuf_map_delete_elem,
 	.map_get_next_key = ringbuf_map_get_next_key,
+	.map_mem_usage = ringbuf_map_mem_usage,
 	.map_btf_id = &user_ringbuf_map_btf_ids[0],
 };
 
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index aecea7451b6103..0f1d8dced9337e 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -654,6 +654,19 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
+static u64 stack_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	u64 value_size = map->value_size;
+	u64 n_buckets = smap->n_buckets;
+	u64 enties = map->max_entries;
+	u64 usage = sizeof(*smap);
+
+	usage += n_buckets * sizeof(struct stack_map_bucket *);
+	usage += enties * (sizeof(struct stack_map_bucket) + value_size);
+	return usage;
+}
+
 BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map)
 const struct bpf_map_ops stack_trace_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
@@ -664,5 +677,6 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = stack_map_mem_usage,
 	.map_btf_id = &stack_trace_map_btf_ids[0],
 };
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ede5f987484f08..f406dfa137924a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -105,6 +105,7 @@ const struct bpf_map_ops bpf_map_offload_ops = {
 	.map_alloc = bpf_map_offload_map_alloc,
 	.map_free = bpf_map_offload_map_free,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = bpf_map_offload_map_mem_usage,
 };
 
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
@@ -128,6 +129,8 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	}
 	if (attr->map_ifindex)
 		ops = &bpf_map_offload_ops;
+	if (!ops->map_mem_usage)
+		return ERR_PTR(-EINVAL);
 	map = ops->map_alloc(attr);
 	if (IS_ERR(map))
 		return map;
@@ -771,17 +774,10 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
 }
 
 #ifdef CONFIG_PROC_FS
-/* Provides an approximation of the map's memory footprint.
- * Used only to provide a backward compatibility and display
- * a reasonable "memlock" info.
- */
-static unsigned long bpf_map_memory_footprint(const struct bpf_map *map)
+/* Show the memory usage of a bpf map */
+static u64 bpf_map_memory_usage(const struct bpf_map *map)
 {
-	unsigned long size;
-
-	size = round_up(map->key_size + bpf_map_value_size(map), 8);
-
-	return round_up(map->max_entries * size, PAGE_SIZE);
+	return map->ops->map_mem_usage(map);
 }
 
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
@@ -803,7 +799,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
 		   "map_extra:\t%#llx\n"
-		   "memlock:\t%lu\n"
+		   "memlock:\t%llu\n"
 		   "map_id:\t%u\n"
 		   "frozen:\t%u\n",
 		   map->map_type,
@@ -812,7 +808,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->max_entries,
 		   map->map_flags,
 		   (unsigned long long)map->map_extra,
-		   bpf_map_memory_footprint(map),
+		   bpf_map_memory_usage(map),
 		   map->id,
 		   READ_ONCE(map->frozen));
 	if (type) {
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index bb378c33f542c2..7a36353dbc22c6 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -324,6 +324,7 @@ const struct bpf_map_ops sk_storage_map_ops = {
 	.map_local_storage_charge = bpf_sk_storage_charge,
 	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
 	.map_owner_storage_ptr = bpf_sk_storage_ptr,
+	.map_mem_usage = bpf_local_storage_map_mem_usage,
 };
 
 const struct bpf_func_proto bpf_sk_storage_get_proto = {
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index a68a7290a3b2b1..9b854e236d2360 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -797,6 +797,14 @@ static void sock_map_fini_seq_private(void *priv_data)
 	bpf_map_put_with_uref(info->map);
 }
 
+static u64 sock_map_mem_usage(const struct bpf_map *map)
+{
+	u64 usage = sizeof(struct bpf_stab);
+
+	usage += (u64)map->max_entries * sizeof(struct sock *);
+	return usage;
+}
+
 static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
 	.seq_ops		= &sock_map_seq_ops,
 	.init_seq_private	= sock_map_init_seq_private,
@@ -816,6 +824,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_lookup_elem	= sock_map_lookup,
 	.map_release_uref	= sock_map_release_progs,
 	.map_check_btf		= map_check_no_btf,
+	.map_mem_usage		= sock_map_mem_usage,
 	.map_btf_id		= &sock_map_btf_ids[0],
 	.iter_seq_info		= &sock_map_iter_seq_info,
 };
@@ -1397,6 +1406,16 @@ static void sock_hash_fini_seq_private(void *priv_data)
 	bpf_map_put_with_uref(info->map);
 }
 
+static u64 sock_hash_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_shtab *htab = container_of(map, struct bpf_shtab, map);
+	u64 usage = sizeof(*htab);
+
+	usage += htab->buckets_num * sizeof(struct bpf_shtab_bucket);
+	usage += atomic_read(&htab->count) * (u64)htab->elem_size;
+	return usage;
+}
+
 static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
 	.seq_ops		= &sock_hash_seq_ops,
 	.init_seq_private	= sock_hash_init_seq_private,
@@ -1416,6 +1435,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_lookup_elem_sys_only = sock_hash_lookup_sys,
 	.map_release_uref	= sock_hash_release_progs,
 	.map_check_btf		= map_check_no_btf,
+	.map_mem_usage		= sock_hash_mem_usage,
 	.map_btf_id		= &sock_hash_map_btf_ids[0],
 	.iter_seq_info		= &sock_hash_iter_seq_info,
 };
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 771d0fa90ef58e..0c38d717592284 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -24,6 +24,7 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_inc(&map->map);
+	atomic_inc(&map->count);
 
 	node->map = map;
 	node->map_entry = map_entry;
@@ -32,8 +33,11 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 
 static void xsk_map_node_free(struct xsk_map_node *node)
 {
+	struct xsk_map *map = node->map;
+
 	bpf_map_put(&node->map->map);
 	kfree(node);
+	atomic_dec(&map->count);
 }
 
 static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
@@ -85,6 +89,14 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 	return &m->map;
 }
 
+static u64 xsk_map_mem_usage(const struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+	return struct_size(m, xsk_map, map->max_entries) +
+		   (u64)atomic_read(&m->count) * sizeof(struct xsk_map_node);
+}
+
 static void xsk_map_free(struct bpf_map *map)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
@@ -267,6 +279,7 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
+	.map_mem_usage = xsk_map_mem_usage,
 	.map_btf_id = &xsk_map_btf_ids[0],
 	.map_redirect = xsk_map_redirect,
 };
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 75b411fc2c77b6..b8402e3f9eb223 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -1141,12 +1141,13 @@ static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr,
 	return 0;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg);
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz);
 
 static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie)
 {
+	struct usdt_arg_spec *arg;
 	const char *s;
-	int len;
+	int arg_sz, len;
 
 	spec->usdt_cookie = usdt_cookie;
 	spec->arg_cnt = 0;
@@ -1159,10 +1160,25 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note,
 			return -E2BIG;
 		}
 
-		len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]);
+		arg = &spec->args[spec->arg_cnt];
+		len = parse_usdt_arg(s, spec->arg_cnt, arg, &arg_sz);
 		if (len < 0)
 			return len;
 
+		arg->arg_signed = arg_sz < 0;
+		if (arg_sz < 0)
+			arg_sz = -arg_sz;
+
+		switch (arg_sz) {
+		case 1: case 2: case 4: case 8:
+			arg->arg_bitshift = 64 - arg_sz * 8;
+			break;
+		default:
+			pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
+				spec->arg_cnt, s, arg_sz);
+			return -EINVAL;
+		}
+
 		s += len;
 		spec->arg_cnt++;
 	}
@@ -1219,13 +1235,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	char reg_name[16];
-	int arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -4@-20(%rbp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1233,7 +1249,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case without offset, e.g., 8@(%rsp) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
@@ -1241,7 +1257,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %%%15s %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -4@%eax */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1250,7 +1266,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ $%ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@$71 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
@@ -1260,20 +1276,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1281,13 +1283,13 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 
 /* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	unsigned int reg;
-	int arg_sz, len;
+	int len;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, &reg, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", arg_sz, &off, &reg, &len) == 3) {
 		/* Memory dereference case, e.g., -2@-28(%r15) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1296,7 +1298,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 			return -EINVAL;
 		}
 		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
-	} else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, &reg, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %%r%u %n", arg_sz, &reg, &len) == 2) {
 		/* Register read case, e.g., -8@%r0 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1305,7 +1307,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 			return -EINVAL;
 		}
 		arg->reg_off = offsetof(user_pt_regs, gprs[reg]);
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@71 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
@@ -1315,20 +1317,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1348,13 +1336,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	char reg_name[16];
-	int arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) {
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , %ld ] %n", arg_sz, reg_name, &off, &len) == 3) {
 		/* Memory dereference case, e.g., -4@[sp, 96] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1362,7 +1350,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) {
 		/* Memory dereference case, e.g., -4@[sp] */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = 0;
@@ -1370,12 +1358,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@5 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@x4 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1388,20 +1376,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
-
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
-		return -EINVAL;
-	}
-
 	return len;
 }
 
@@ -1456,13 +1430,13 @@ static int calc_pt_regs_off(const char *reg_name)
 	return -ENOENT;
 }
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	char reg_name[16];
-	int arg_sz, len, reg_off;
+	int len, reg_off;
 	long off;
 
-	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", &arg_sz, &off, reg_name, &len) == 3) {
+	if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", arg_sz, &off, reg_name, &len) == 3) {
 		/* Memory dereference case, e.g., -8@-88(s0) */
 		arg->arg_type = USDT_ARG_REG_DEREF;
 		arg->val_off = off;
@@ -1470,12 +1444,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		if (reg_off < 0)
 			return reg_off;
 		arg->reg_off = reg_off;
-	} else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) {
 		/* Constant value case, e.g., 4@5 */
 		arg->arg_type = USDT_ARG_CONST;
 		arg->val_off = off;
 		arg->reg_off = 0;
-	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) {
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
 		/* Register read case, e.g., -8@a1 */
 		arg->arg_type = USDT_ARG_REG;
 		arg->val_off = 0;
@@ -1488,17 +1462,83 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 		return -EINVAL;
 	}
 
-	arg->arg_signed = arg_sz < 0;
-	if (arg_sz < 0)
-		arg_sz = -arg_sz;
+	return len;
+}
 
-	switch (arg_sz) {
-	case 1: case 2: case 4: case 8:
-		arg->arg_bitshift = 64 - arg_sz * 8;
-		break;
-	default:
-		pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n",
-			arg_num, arg_str, arg_sz);
+#elif defined(__arm__)
+
+static int calc_pt_regs_off(const char *reg_name)
+{
+	static struct {
+		const char *name;
+		size_t pt_regs_off;
+	} reg_map[] = {
+		{ "r0", offsetof(struct pt_regs, uregs[0]) },
+		{ "r1", offsetof(struct pt_regs, uregs[1]) },
+		{ "r2", offsetof(struct pt_regs, uregs[2]) },
+		{ "r3", offsetof(struct pt_regs, uregs[3]) },
+		{ "r4", offsetof(struct pt_regs, uregs[4]) },
+		{ "r5", offsetof(struct pt_regs, uregs[5]) },
+		{ "r6", offsetof(struct pt_regs, uregs[6]) },
+		{ "r7", offsetof(struct pt_regs, uregs[7]) },
+		{ "r8", offsetof(struct pt_regs, uregs[8]) },
+		{ "r9", offsetof(struct pt_regs, uregs[9]) },
+		{ "r10", offsetof(struct pt_regs, uregs[10]) },
+		{ "fp", offsetof(struct pt_regs, uregs[11]) },
+		{ "ip", offsetof(struct pt_regs, uregs[12]) },
+		{ "sp", offsetof(struct pt_regs, uregs[13]) },
+		{ "lr", offsetof(struct pt_regs, uregs[14]) },
+		{ "pc", offsetof(struct pt_regs, uregs[15]) },
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(reg_map); i++) {
+		if (strcmp(reg_name, reg_map[i].name) == 0)
+			return reg_map[i].pt_regs_off;
+	}
+
+	pr_warn("usdt: unrecognized register '%s'\n", reg_name);
+	return -ENOENT;
+}
+
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
+{
+	char reg_name[16];
+	int len, reg_off;
+	long off;
+
+	if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , #%ld ] %n",
+		   arg_sz, reg_name, &off, &len) == 3) {
+		/* Memory dereference case, e.g., -4@[fp, #96] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = off;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) {
+		/* Memory dereference case, e.g., -4@[sp] */
+		arg->arg_type = USDT_ARG_REG_DEREF;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else if (sscanf(arg_str, " %d @ #%ld %n", arg_sz, &off, &len) == 2) {
+		/* Constant value case, e.g., 4@#5 */
+		arg->arg_type = USDT_ARG_CONST;
+		arg->val_off = off;
+		arg->reg_off = 0;
+	} else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) {
+		/* Register read case, e.g., -8@r4 */
+		arg->arg_type = USDT_ARG_REG;
+		arg->val_off = 0;
+		reg_off = calc_pt_regs_off(reg_name);
+		if (reg_off < 0)
+			return reg_off;
+		arg->reg_off = reg_off;
+	} else {
+		pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str);
 		return -EINVAL;
 	}
 
@@ -1507,7 +1547,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec
 
 #else
 
-static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg)
+static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz)
 {
 	pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n");
 	return -ENOTSUP;
diff --git a/tools/lib/bpf/zip.c b/tools/lib/bpf/zip.c
index 8458c2dd0e3bcb..f561aa07438f59 100644
--- a/tools/lib/bpf/zip.c
+++ b/tools/lib/bpf/zip.c
@@ -168,9 +168,8 @@ static int try_parse_end_of_cd(struct zip_archive *archive, __u32 offset)
 
 static int find_cd(struct zip_archive *archive)
 {
+	int64_t limit, offset;
 	int rc = -EINVAL;
-	int64_t limit;
-	__u32 offset;
 
 	if (archive->size <= sizeof(struct end_of_cd_record))
 		return -EINVAL;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index b13feceb38f1a4..810b14981c2eb2 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -70,7 +70,7 @@ void test_test_ima(void)
 	u64 bin_true_sample;
 	char cmd[256];
 
-	int err, duration = 0;
+	int err, duration = 0, fresh_digest_idx = 0;
 	struct ima *skel = NULL;
 
 	skel = ima__open_and_load();
@@ -129,7 +129,15 @@ void test_test_ima(void)
 	/*
 	 * Test #3
 	 * - Goal: confirm that bpf_ima_inode_hash() returns a non-fresh digest
-	 * - Expected result: 2 samples (/bin/true: non-fresh, fresh)
+	 * - Expected result:
+	 *   1 sample (/bin/true: fresh) if commit 62622dab0a28 applied
+	 *   2 samples (/bin/true: non-fresh, fresh) if commit 62622dab0a28 is
+	 *     not applied
+	 *
+	 * If commit 62622dab0a28 ("ima: return IMA digest value only when
+	 * IMA_COLLECTED flag is set") is applied, bpf_ima_inode_hash() refuses
+	 * to give a non-fresh digest, hence the correct result is 1 instead of
+	 * 2.
 	 */
 	test_init(skel->bss);
 
@@ -144,13 +152,18 @@ void test_test_ima(void)
 		goto close_clean;
 
 	err = ring_buffer__consume(ringbuf);
-	ASSERT_EQ(err, 2, "num_samples_or_err");
-	ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash");
-	ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash");
-	ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample, "sample_equal_or_err");
+	ASSERT_GE(err, 1, "num_samples_or_err");
+	if (err == 2) {
+		ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash");
+		ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample,
+			  "sample_equal_or_err");
+		fresh_digest_idx = 1;
+	}
+
+	ASSERT_NEQ(ima_hash_from_bpf[fresh_digest_idx], 0, "ima_hash");
 	/* IMA refreshed the digest. */
-	ASSERT_NEQ(ima_hash_from_bpf[1], bin_true_sample,
-		   "sample_different_or_err");
+	ASSERT_NEQ(ima_hash_from_bpf[fresh_digest_idx], bin_true_sample,
+		   "sample_equal_or_err");
 
 	/*
 	 * Test #4