diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 248b4818178c..34865701f7f7 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -259,6 +259,37 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
 	return this_cpu_ptr(array->pptrs[index & array->index_mask]);
 }
 
+static int percpu_array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	if (!bpf_jit_supports_percpu_insn())
+		return -EOPNOTSUPP;
+	if (map->max_entries != 1)
+		return -EOPNOTSUPP;
+	if (off >= map->value_size)
+		return -EINVAL;
+
+	*imm = (u64)(__force unsigned long) array->pptrs[0];
+	return 0;
+}
+
+static int percpu_array_map_direct_value_meta(const struct bpf_map *map, u64 imm, u32 *off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 base = (u64)(__force unsigned long) array->pptrs[0];
+
+	if (!bpf_jit_supports_percpu_insn())
+		return -EOPNOTSUPP;
+	if (map->max_entries != 1)
+		return -EOPNOTSUPP;
+	if (imm < base || imm >= base + array->elem_size)
+		return -ENOENT;
+
+	*off = imm - base;
+	return 0;
+}
+
 /* emit BPF instructions equivalent to C code of percpu_array_map_lookup_elem() */
 static int percpu_array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
@@ -551,9 +582,10 @@ static int array_map_check_btf(struct bpf_map *map,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
 {
-	/* One exception for keyless BTF: .bss/.data/.rodata map */
+	/* One exception for keyless BTF: .bss/.data/.rodata/.percpu map */
 	if (btf_type_is_void(key_type)) {
-		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+		if ((map->map_type != BPF_MAP_TYPE_ARRAY &&
+		     map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) ||
 		    map->max_entries != 1)
 			return -EINVAL;
 
@@ -832,6 +864,8 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_get_next_key = bpf_array_get_next_key,
 	.map_lookup_elem = percpu_array_map_lookup_elem,
 	.map_gen_lookup = percpu_array_map_gen_lookup,
+	.map_direct_value_addr = percpu_array_map_direct_value_addr,
+	.map_direct_value_meta = percpu_array_map_direct_value_meta,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_lookup_percpu_elem = percpu_array_map_lookup_percpu_elem,
diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c
index 40bd04421a99..a2b18a9f1694 100644
--- a/kernel/bpf/backtrack.c
+++ b/kernel/bpf/backtrack.c
@@ -214,7 +214,6 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
 	return bt->reg_masks[bt->frame] & (1 << reg);
 }
 
-
 /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
 static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask)
 {
@@ -254,7 +253,6 @@ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
 	}
 }
 
-
 /* For given verifier state backtrack_insn() is called from the last insn to
  * the first insn. Its purpose is to compute a bitmask of registers and
  * stack slots that needs precision in the parent verifier state.
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 6606187ed4f4..87ffde865a50 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2534,7 +2534,6 @@ static void btf_bitfield_show(void *data, u8 bits_offset,
 	btf_int128_print(show, print_num);
 }
 
-
 static void btf_int_bits_show(const struct btf *btf,
 			      const struct btf_type *t,
 			      void *data, u8 bits_offset,
diff --git a/kernel/bpf/cfg.c b/kernel/bpf/cfg.c
index db3416a7c904..818f7afac83a 100644
--- a/kernel/bpf/cfg.c
+++ b/kernel/bpf/cfg.c
@@ -47,7 +47,6 @@ enum {
 	BRANCH = 2,
 };
 
-
 static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off)
 {
 	struct bpf_subprog_info *subprog;
diff --git a/kernel/bpf/const_fold.c b/kernel/bpf/const_fold.c
index 4cf120c7b2cb..7f1b30059cc8 100644
--- a/kernel/bpf/const_fold.c
+++ b/kernel/bpf/const_fold.c
@@ -182,7 +182,6 @@ static void const_reg_xfer(struct bpf_verifier_env *env, struct const_arg_info *
 		u64 val = 0;
 
 		if (!bpf_map_is_rdonly(map) || !map->ops->map_direct_value_addr ||
-		    map->map_type == BPF_MAP_TYPE_INSN_ARRAY ||
 		    off < 0 || off + size > map->value_size ||
 		    bpf_map_direct_read(map, off, size, &val, is_ldsx)) {
 			*dst = unknown;
diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 2417a3461652..177a3fcbb63a 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -1466,7 +1466,6 @@ int bpf_fixup_call_args(struct bpf_verifier_env *env)
 	return err;
 }
 
-
 /* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */
 static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
 {
@@ -1835,6 +1834,43 @@ int bpf_do_misc_fixups(struct bpf_verifier_env *env)
 			goto next_insn;
 		}
 
+		if (bpf_jit_supports_percpu_insn() &&
+		    insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
+		    (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
+		     insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE)) {
+			struct bpf_map *map;
+
+			aux = &env->insn_aux_data[i + delta];
+			map = env->used_maps[aux->map_index];
+			if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY)
+				goto next_insn;
+
+			prog->jit_required = true;
+
+			/*
+			 * We are *skipping* first half of ld_imm64 insn
+			 * with 'i++;', patching over second half of it
+			 * with that same half + mov64_percpu_reg insn.
+			 * All because bpf_patch_insn_data() can only
+			 * replace one 8-byte insn, which does not work
+			 * well for ld_imm64 insn.
+			 */
+
+			insn_buf[0] = insn[1];
+			insn_buf[1] = BPF_MOV64_PERCPU_REG(insn->dst_reg, insn->dst_reg);
+			cnt = 2;
+
+			i++;
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			goto next_insn;
+		}
+
 		if (insn->code != (BPF_JMP | BPF_CALL))
 			goto next_insn;
 		if (insn->src_reg == BPF_PSEUDO_CALL)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 9f394e1aa2e8..d40cb5dd446c 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -998,7 +998,6 @@ static void dec_elem_count(struct bpf_htab *htab)
 		atomic_dec(&htab->count);
 }
 
-
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
 	htab_put_fd_value(htab, l);
@@ -2970,7 +2969,6 @@ static int rhtab_delete_elem(struct bpf_rhtab *rhtab, struct rhtab_elem *elem, v
 	return 0;
 }
 
-
 static long rhtab_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_rhtab *rhtab = container_of(map, struct bpf_rhtab, map);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6388b6b23e49..45e2f19387b2 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -4871,7 +4871,6 @@ static const struct btf_kfunc_id_set generic_kfunc_set = {
 	.set   = &generic_btf_ids,
 };
 
-
 BTF_ID_LIST(generic_dtor_ids)
 BTF_ID(struct, task_struct)
 BTF_ID(func, bpf_task_release_dtor)
diff --git a/kernel/bpf/liveness.c b/kernel/bpf/liveness.c
index 1c997aeba6fa..74fc4b3f80d6 100644
--- a/kernel/bpf/liveness.c
+++ b/kernel/bpf/liveness.c
@@ -269,7 +269,6 @@ bpf_insn_successors(struct bpf_verifier_env *env, u32 idx)
 
 __diag_pop();
 
-
 static inline bool update_insn(struct bpf_verifier_env *env,
 			       struct func_instance *instance, u32 frame, u32 insn_idx)
 {
@@ -1862,7 +1861,6 @@ static int analyze_subprog(struct bpf_verifier_env *env,
 	if (need_resched())
 		cond_resched();
 
-
 	/*
 	 * When an instance is reused (must_write_initialized == true),
 	 * record into a fresh instance and merge afterward.  This avoids
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index c1c9dee4dcdd..6e8b18c32a10 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -123,7 +123,6 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	return err;
 }
 
-
 static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 {
 	struct bpf_queue_stack *qs = bpf_queue_stack(map);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8d111da88655..7d8c3e8e6d62 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -636,7 +636,6 @@ int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
 	return ret;
 }
 
-
 static int btf_field_cmp(const void *a, const void *b)
 {
 	const struct btf_field *f1 = a, *f2 = b;
@@ -1830,7 +1829,6 @@ static int map_lookup_elem(union bpf_attr *attr)
 	return err;
 }
 
-
 #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
 static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
@@ -3497,7 +3495,6 @@ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer)
 	if (fd < 0)
 		return fd;
 
-
 	id = bpf_link_alloc_id(link);
 	if (id < 0) {
 		put_unused_fd(fd);
@@ -5505,7 +5502,6 @@ static int bpf_link_get_info_by_fd(struct file *file,
 	return 0;
 }
 
-
 static int token_get_info_by_fd(struct file *file,
 				struct bpf_token *token,
 				const union bpf_attr *attr,
@@ -6507,7 +6503,6 @@ BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size)
 	return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size, KERNEL_BPFPTR(NULL), 0);
 }
 
-
 /* To shut up -Wmissing-prototypes.
  * This function is used by the kernel light skeleton
  * to load bpf programs when modules are loaded or during kernel boot.
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 164d16c243ca..6ac1afced20b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -635,7 +635,6 @@ static void __mark_dynptr_reg(struct bpf_reg_state *reg,
 			      enum bpf_dynptr_type type,
 			      bool first_slot, int id, int parent_id);
 
-
 static void mark_dynptr_stack_regs(struct bpf_verifier_env *env,
 				   struct bpf_reg_state *sreg1,
 				   struct bpf_reg_state *sreg2,
@@ -1674,7 +1673,6 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta
 	return true;
 }
 
-
 void bpf_free_backedges(struct bpf_scc_visit *visit)
 {
 	struct bpf_scc_backedge *backedge, *next;
@@ -2291,7 +2289,6 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
 	return &elem->st;
 }
 
-
 static int cmp_subprogs(const void *a, const void *b)
 {
 	return ((struct bpf_subprog_info *)a)->start -
@@ -3969,7 +3966,6 @@ static int check_stack_read(struct bpf_verifier_env *env,
 	return err;
 }
 
-
 /* check_stack_write dispatches to check_stack_write_fixed_off or
  * check_stack_write_var_off.
  *
@@ -4767,7 +4763,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
 		valid = false;
 	}
 
-
 	if (valid) {
 		env->insn_aux_data[insn_idx].ctx_field_size =
 			info.ctx_field_size;
@@ -5587,6 +5582,8 @@ int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
 	u64 addr;
 	int err;
 
+	if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+		return -EINVAL;
 	err = map->ops->map_direct_value_addr(map, &addr, off);
 	if (err)
 		return err;
@@ -6083,6 +6080,51 @@ static void add_scalar_to_reg(struct bpf_reg_state *dst_reg, s64 val)
 	reg_bounds_sync(dst_reg);
 }
 
+static int check_map_mem_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int off,
+			      int bpf_size, int value_regno, bool is_ldsx)
+{
+	struct bpf_reg_state *regs = cur_regs(env);
+	int size = bpf_size_to_bytes(bpf_size);
+	struct bpf_map *map = reg->map_ptr;
+
+	switch (map->map_type) {
+	case BPF_MAP_TYPE_INSN_ARRAY:
+		if (bpf_size != BPF_DW) {
+			verbose(env, "Invalid read of %d bytes from insn_array\n", size);
+			return -EACCES;
+		}
+		regs[value_regno] = *reg;
+		add_scalar_to_reg(&regs[value_regno], off);
+		regs[value_regno].type = PTR_TO_INSN;
+		return 0;
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+		goto reg_unknown;
+	default:
+		break;
+	}
+
+	/* If map is read-only, track its contents as scalars. */
+	if (tnum_is_const(reg->var_off) &&
+	    bpf_map_is_rdonly(map) &&
+	    map->ops->map_direct_value_addr) {
+		int map_off = off + reg->var_off.value;
+		u64 val = 0;
+		int err;
+
+		err = bpf_map_direct_read(map, map_off, size, &val, is_ldsx);
+		if (err)
+			return err;
+
+		regs[value_regno].type = SCALAR_VALUE;
+		__mark_reg_known(&regs[value_regno], val);
+		return 0;
+	}
+
+reg_unknown:
+	mark_reg_unknown(env, regs, value_regno);
+	return 0;
+}
+
 /* check whether memory at (regno + off) is accessible for t = (read | write)
  * if t==write, value_regno is a register which value is stored into memory
  * if t==read, value_regno is a register which will receive the value from memory
@@ -6137,38 +6179,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, struct b
 		if (kptr_field) {
 			err = check_map_kptr_access(env, value_regno, insn_idx, kptr_field);
 		} else if (t == BPF_READ && value_regno >= 0) {
-			struct bpf_map *map = reg->map_ptr;
-
-			/*
-			 * If map is read-only, track its contents as scalars,
-			 * unless it is an insn array (see the special case below)
-			 */
-			if (tnum_is_const(reg->var_off) &&
-			    bpf_map_is_rdonly(map) &&
-			    map->ops->map_direct_value_addr &&
-			    map->map_type != BPF_MAP_TYPE_INSN_ARRAY) {
-				int map_off = off + reg->var_off.value;
-				u64 val = 0;
-
-				err = bpf_map_direct_read(map, map_off, size,
-							  &val, is_ldsx);
-				if (err)
-					return err;
-
-				regs[value_regno].type = SCALAR_VALUE;
-				__mark_reg_known(&regs[value_regno], val);
-			} else if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) {
-				if (bpf_size != BPF_DW) {
-					verbose(env, "Invalid read of %d bytes from insn_array\n",
-						     size);
-					return -EACCES;
-				}
-				regs[value_regno] = *reg;
-				add_scalar_to_reg(&regs[value_regno], off);
-				regs[value_regno].type = PTR_TO_INSN;
-			} else {
-				mark_reg_unknown(env, regs, value_regno);
-			}
+			err = check_map_mem_read(env, reg, off, bpf_size, value_regno, is_ldsx);
 		}
 	} else if (base_type(reg->type) == PTR_TO_MEM) {
 		bool rdonly_mem = type_is_rdonly_mem(reg->type);
@@ -6635,7 +6646,6 @@ static int check_stack_range_initialized(
 	if (err)
 		return err;
 
-
 	if (tnum_is_const(reg->var_off)) {
 		min_off = max_off = reg->var_off.value + off;
 	} else {
@@ -7347,7 +7357,6 @@ static bool is_iter_new_kfunc(struct bpf_call_arg_meta *meta)
 	return meta->kfunc_flags & KF_ITER_NEW;
 }
 
-
 static bool is_iter_destroy_kfunc(struct bpf_call_arg_meta *meta)
 {
 	return meta->kfunc_flags & KF_ITER_DESTROY;
@@ -8125,6 +8134,12 @@ static int check_arg_const_str(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+		verbose(env, "%s points to percpu_array map which cannot be used as const string\n",
+			reg_arg_name(env, argno));
+		return -EACCES;
+	}
+
 	if (!bpf_map_is_rdonly(map)) {
 		verbose(env, "%s does not point to a readonly map'\n", reg_arg_name(env, argno));
 		return -EACCES;
@@ -11607,7 +11622,6 @@ static int process_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *
 	return 0;
 }
 
-
 static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
 {
 	struct btf_record *rec = reg_btf_record(reg);
@@ -16412,7 +16426,6 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
-
 static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_range *range)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
@@ -18361,8 +18374,6 @@ static void release_insn_arrays(struct bpf_verifier_env *env)
 		bpf_insn_array_release(env->insn_array_maps[i]);
 }
 
-
-
 /* The verifier does more data flow analysis than llvm and will not
  * explore branches that are dead at run time. Malicious programs can
  * have dead code too. Therefore replace all dead at-run-time code
@@ -18390,8 +18401,6 @@ static void sanitize_dead_code(struct bpf_verifier_env *env)
 	}
 }
 
-
-
 static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl;
@@ -18678,7 +18687,6 @@ static int do_check_main(struct bpf_verifier_env *env)
 	return ret;
 }
 
-
 static void print_verification_stats(struct bpf_verifier_env *env)
 {
 	/* Skip over hidden subprogs which are not verified. */
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index a01d06d22d1a..a50540ef6521 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -101,6 +101,12 @@ static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
 		return true;
 	}
 
+	if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY) {
+		snprintf(buf, buf_sz, "%s", name + 1);
+		sanitize_identifier(buf);
+		return true;
+	}
+
 	for  (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) {
 		const char *sfx = sfxs[i], *p;
 
@@ -117,7 +123,7 @@ static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
 
 static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz)
 {
-	static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
+	static const char *pfxs[] = { ".data", ".rodata", ".bss", ".percpu", ".kconfig" };
 	int i, n;
 
 	/* recognize hard coded LLVM section name */
@@ -254,7 +260,7 @@ static const struct btf_type *find_type_for_map(struct btf *btf, const char *map
 	return NULL;
 }
 
-static bool is_mmapable_map(const struct bpf_map *map, char *buf, size_t sz)
+static bool is_skel_data(const struct bpf_map *map, char *buf, size_t sz)
 {
 	size_t tmp_sz;
 
@@ -263,13 +269,24 @@ static bool is_mmapable_map(const struct bpf_map *map, char *buf, size_t sz)
 		return true;
 	}
 
-	if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE))
+	if (!bpf_map__is_internal(map))
 		return false;
 
 	if (!get_map_ident(map, buf, sz))
 		return false;
 
-	return true;
+	if (bpf_map__map_flags(map) & BPF_F_MMAPABLE)
+		return true;
+
+	if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY)
+		return bpf_map__btf_value_type_id(map) != 0;
+
+	return false;
+}
+
+static bool is_mmapable_map(const struct bpf_map *map, char *buf, size_t sz)
+{
+	return is_skel_data(map, buf, sz) && bpf_map__type(map) != BPF_MAP_TYPE_PERCPU_ARRAY;
 }
 
 static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
@@ -287,7 +304,7 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 
 	bpf_object__for_each_map(map, obj) {
 		/* only generate definitions for memory-mapped internal maps */
-		if (!is_mmapable_map(map, map_ident, sizeof(map_ident)))
+		if (!is_skel_data(map, map_ident, sizeof(map_ident)))
 			continue;
 
 		sec = find_type_for_map(btf, map_ident);
@@ -517,7 +534,7 @@ static void codegen_asserts(struct bpf_object *obj, const char *obj_name)
 		", obj_name);
 
 	bpf_object__for_each_map(map, obj) {
-		if (!is_mmapable_map(map, map_ident, sizeof(map_ident)))
+		if (!is_skel_data(map, map_ident, sizeof(map_ident)))
 			continue;
 
 		sec = find_type_for_map(btf, map_ident);
@@ -668,8 +685,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 	bpf_object__for_each_map(map, obj) {
 		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
-		if (bpf_map__is_internal(map) &&
-		    (bpf_map__map_flags(map) & BPF_F_MMAPABLE))
+		if (is_skel_data(map, ident, sizeof(ident)))
 			printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zu);\n",
 			       ident, bpf_map_mmap_sz(map));
 		codegen("\
@@ -741,7 +757,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		const void *mmap_data = NULL;
 		size_t mmap_size = 0;
 
-		if (!is_mmapable_map(map, ident, sizeof(ident)))
+		if (!is_skel_data(map, ident, sizeof(ident)))
 			continue;
 
 		codegen("\
@@ -849,9 +865,23 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 	bpf_object__for_each_map(map, obj) {
 		const char *mmap_flags;
 
-		if (!is_mmapable_map(map, ident, sizeof(ident)))
+		if (!is_skel_data(map, ident, sizeof(ident)))
 			continue;
 
+		if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY) {
+			codegen("\
+		\n\
+			err = skel_protect_map_data(skel->%1$s, &skel->maps.%1$s.initial_value, %2$zd);\n\
+			if (err)					    \n\
+				return err;				    \n\
+		#ifdef __KERNEL__					    \n\
+			skel->%1$s = NULL;				    \n\
+		#endif							    \n\
+			",
+			ident, bpf_map_mmap_sz(map));
+			continue;
+		}
+
 		if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG)
 			mmap_flags = "PROT_READ";
 		else
@@ -955,8 +985,7 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool
 				map->map = &obj->maps.%s;	    \n\
 			",
 			i, bpf_map__name(map), ident);
-		/* memory-mapped internal maps */
-		if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) {
+		if (mmaped && is_skel_data(map, ident, sizeof(ident))) {
 			printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
 		}
 
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index 042569187752..6c5ad6c55e8a 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -65,7 +65,8 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 			enum bpf_prog_type prog_type, const char *prog_name,
 			const char *license, struct bpf_insn *insns, size_t insn_cnt,
 			struct bpf_prog_load_opts *load_attr, int prog_idx);
-void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
+void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size,
+			      __u64 flags);
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
 void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index b7e388f99d0b..ef9581c11303 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -620,6 +620,38 @@ static int probe_bpf_syscall_common_attrs(int token_fd)
 	return probe_sys_bpf_ext();
 }
 
+static int probe_kern_percpu_data(int token_fd)
+{
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.token_fd = token_fd,
+		.map_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	int ret, map, insn_cnt = ARRAY_SIZE(insns);
+
+	map = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "libbpf_percpu", sizeof(int), 8, 1,
+			     &map_opts);
+	if (map < 0) {
+		pr_warn("Error in %s(): %s. Couldn't create simple percpu_array map.\n",
+			__func__, errstr(map));
+		return map;
+	}
+
+	insns[0].imm = map;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	close(map);
+	return probe_fd(ret);
+}
+
 typedef int (*feature_probe_fn)(int /* token_fd */);
 
 static struct kern_feature_cache feature_cache;
@@ -707,6 +739,9 @@ static struct kern_feature_desc {
 	[FEAT_BPF_SYSCALL_COMMON_ATTRS] = {
 		"BPF syscall common attributes support", probe_bpf_syscall_common_attrs,
 	},
+	[FEAT_PERCPU_DATA] = {
+		"kernel supports percpu data", probe_kern_percpu_data,
+	},
 };
 
 bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 6e3dd5242761..af3a04f161ac 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -1128,7 +1128,7 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 }
 
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
-			      __u32 value_size)
+			      __u32 value_size, __u64 flags)
 {
 	int attr_size = offsetofend(union bpf_attr, flags);
 	int map_update_attr, value, key;
@@ -1136,6 +1136,7 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	int zero = 0;
 
 	memset(&attr, 0, attr_size);
+	attr.flags = tgt_endian(flags);
 
 	value = add_data(gen, pvalue, value_size);
 	key = add_data(gen, &zero, sizeof(zero));
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 514e4e9daa82..e574870fb716 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -541,6 +541,7 @@ struct bpf_struct_ops {
 };
 
 #define DATA_SEC ".data"
+#define PERCPU_SEC ".percpu"
 #define BSS_SEC ".bss"
 #define RODATA_SEC ".rodata"
 #define KCONFIG_SEC ".kconfig"
@@ -555,6 +556,7 @@ enum libbpf_map_type {
 	LIBBPF_MAP_BSS,
 	LIBBPF_MAP_RODATA,
 	LIBBPF_MAP_KCONFIG,
+	LIBBPF_MAP_PERCPU,
 };
 
 struct bpf_map_def {
@@ -666,6 +668,7 @@ enum sec_type {
 	SEC_DATA,
 	SEC_RODATA,
 	SEC_ST_OPS,
+	SEC_PERCPU,
 };
 
 struct elf_sec_desc {
@@ -1839,6 +1842,8 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 	switch (map->def.type) {
 	case BPF_MAP_TYPE_ARRAY:
 		return array_map_mmap_sz(map->def.value_size, map->def.max_entries);
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+		return map->def.value_size;
 	case BPF_MAP_TYPE_ARENA:
 		return page_sz * map->def.max_entries;
 	default:
@@ -1866,7 +1871,8 @@ static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz
 	return 0;
 }
 
-static char *internal_map_name(struct bpf_object *obj, const char *real_name)
+static char *internal_map_name(struct bpf_object *obj, const char *real_name,
+			       enum libbpf_map_type type)
 {
 	char map_name[BPF_OBJ_NAME_LEN], *p;
 	int pfx_len, sfx_len = max((size_t)7, strlen(real_name));
@@ -1907,8 +1913,11 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 	if (sfx_len >= BPF_OBJ_NAME_LEN)
 		sfx_len = BPF_OBJ_NAME_LEN - 1;
 
-	/* if there are two or more dots in map name, it's a custom dot map */
-	if (strchr(real_name + 1, '.') != NULL)
+	/*
+	 * Don't prefix the bpf_object name if this is a custom dot map
+	 * (containing two or more dots) or a percpu data map.
+	 */
+	if (strchr(real_name + 1, '.') != NULL || type == LIBBPF_MAP_PERCPU)
 		pfx_len = 0;
 	else
 		pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, strlen(obj->name));
@@ -1941,6 +1950,13 @@ static bool map_is_mmapable(struct bpf_object *obj, struct bpf_map *map)
 	if (!map->btf_value_type_id)
 		return false;
 
+	/*
+	 * The internal PERCPU maps are not mmapble because the underlying
+	 * percpu_array maps do not have mmap support.
+	 */
+	if (map->libbpf_type == LIBBPF_MAP_PERCPU)
+		return false;
+
 	t = btf__type_by_id(obj->btf, map->btf_value_type_id);
 	if (!btf_is_datasec(t))
 		return false;
@@ -1962,6 +1978,7 @@ static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 			      const char *real_name, int sec_idx, void *data, size_t data_sz)
 {
+	bool is_percpu = type == LIBBPF_MAP_PERCPU;
 	struct bpf_map_def *def;
 	struct bpf_map *map;
 	size_t mmap_sz;
@@ -1975,7 +1992,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	map->sec_idx = sec_idx;
 	map->sec_offset = 0;
 	map->real_name = strdup(real_name);
-	map->name = internal_map_name(obj, real_name);
+	map->name = internal_map_name(obj, real_name, type);
 	if (!map->real_name || !map->name) {
 		zfree(&map->real_name);
 		zfree(&map->name);
@@ -1983,7 +2000,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	}
 
 	def = &map->def;
-	def->type = BPF_MAP_TYPE_ARRAY;
+	def->type = is_percpu ? BPF_MAP_TYPE_PERCPU_ARRAY : BPF_MAP_TYPE_ARRAY;
 	def->key_size = sizeof(int);
 	def->value_size = data_sz;
 	def->max_entries = 1;
@@ -1996,8 +2013,9 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	if (map_is_mmapable(obj, map))
 		def->map_flags |= BPF_F_MMAPABLE;
 
-	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n",
-		 map->name, map->sec_idx, map->sec_offset, def->map_flags);
+	pr_debug("map '%s' (global %sdata): at sec_idx %d, offset %zu, flags %x.\n",
+		 map->name, is_percpu ? "percpu " : "", map->sec_idx,
+		 map->sec_offset, def->map_flags);
 
 	mmap_sz = bpf_map_mmap_sz(map);
 	map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
@@ -2057,6 +2075,13 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 							    NULL,
 							    sec_desc->data->d_size);
 			break;
+		case SEC_PERCPU:
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_PERCPU,
+							    sec_name, sec_idx,
+							    sec_desc->data->d_buf,
+							    sec_desc->data->d_size);
+			break;
 		default:
 			/* skip */
 			break;
@@ -4016,6 +4041,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				sec_desc->sec_type = SEC_RODATA;
 				sec_desc->shdr = sh;
 				sec_desc->data = data;
+			} else if (strcmp(name, PERCPU_SEC) == 0 ||
+				   str_has_pfx(name, PERCPU_SEC ".")) {
+				sec_desc->sec_type = SEC_PERCPU;
+				sec_desc->shdr = sh;
+				sec_desc->data = data;
 			} else if (strcmp(name, STRUCT_OPS_SEC) == 0 ||
 				   strcmp(name, STRUCT_OPS_LINK_SEC) == 0 ||
 				   strcmp(name, "?" STRUCT_OPS_SEC) == 0 ||
@@ -4544,6 +4574,7 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
 	case SEC_BSS:
 	case SEC_DATA:
 	case SEC_RODATA:
+	case SEC_PERCPU:
 		return true;
 	default:
 		return false;
@@ -4569,6 +4600,8 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
 		return LIBBPF_MAP_DATA;
 	case SEC_RODATA:
 		return LIBBPF_MAP_RODATA;
+	case SEC_PERCPU:
+		return LIBBPF_MAP_PERCPU;
 	default:
 		return LIBBPF_MAP_UNSPEC;
 	}
@@ -4944,7 +4977,7 @@ static int map_fill_btf_type_info(struct bpf_object *obj, struct bpf_map *map)
 
 	/*
 	 * LLVM annotates global data differently in BTF, that is,
-	 * only as '.data', '.bss' or '.rodata'.
+	 * only as '.data', '.bss', '.percpu' or '.rodata'.
 	 */
 	if (!bpf_map__is_internal(map))
 		return -ENOENT;
@@ -5293,18 +5326,20 @@ static int
 bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 {
 	enum libbpf_map_type map_type = map->libbpf_type;
+	bool is_percpu = map_type == LIBBPF_MAP_PERCPU;
+	const __u64 update_flags = is_percpu ? BPF_F_ALL_CPUS : 0;
 	int err, zero = 0;
 	size_t mmap_sz;
 
 	if (obj->gen_loader) {
 		bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps,
-					 map->mmaped, map->def.value_size);
+					 map->mmaped, map->def.value_size, update_flags);
 		if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG)
 			bpf_gen__map_freeze(obj->gen_loader, map - obj->maps);
 		return 0;
 	}
 
-	err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0);
+	err = bpf_map_update_elem(map->fd, &zero, map->mmaped, update_flags);
 	if (err) {
 		err = -errno;
 		pr_warn("map '%s': failed to set initial contents: %s\n",
@@ -5349,6 +5384,13 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 			return err;
 		}
 		map->mmaped = mmaped;
+	} else if (is_percpu) {
+		if (mprotect(map->mmaped, mmap_sz, PROT_READ)) {
+			err = -errno;
+			pr_warn("map '%s': failed to mprotect() contents: %s\n",
+				bpf_map__name(map), errstr(err));
+			return err;
+		}
 	} else if (map->mmaped) {
 		munmap(map->mmaped, mmap_sz);
 		map->mmaped = NULL;
@@ -5624,9 +5666,16 @@ bpf_object__create_maps(struct bpf_object *obj)
 		 * runtime due to bpf_program__set_autoload(prog, false),
 		 * bpf_object loading will succeed just fine even on old
 		 * kernels.
+		 * Same skipping applies to percpu data.
 		 */
-		if (bpf_map__is_internal(map) && !kernel_supports(obj, FEAT_GLOBAL_DATA))
-			map->autocreate = false;
+		if (bpf_map__is_internal(map)) {
+			bool is_percpu = map->libbpf_type == LIBBPF_MAP_PERCPU;
+			enum kern_feature_id feat_id;
+
+			feat_id = is_percpu ? FEAT_PERCPU_DATA : FEAT_GLOBAL_DATA;
+			if (!kernel_supports(obj, feat_id))
+				map->autocreate = false;
+		}
 
 		if (!map->autocreate) {
 			pr_debug("map '%s': skipped auto-creating...\n", map->name);
@@ -10807,11 +10856,16 @@ static bool map_uses_real_name(const struct bpf_map *map)
 	 * such map's corresponding ELF section name as a map name.
 	 * This check distinguishes .data/.rodata from .data.* and .rodata.*
 	 * maps to know which name has to be returned to the user.
+	 * Map name of the custom .percpu.* maps might be truncated to
+	 * BPF_OBJ_NAME_LEN-1 chars in internal_map_name(). Hence, percpu data
+	 * maps must use real name for their user-visible name.
 	 */
 	if (map->libbpf_type == LIBBPF_MAP_DATA && strcmp(map->real_name, DATA_SEC) != 0)
 		return true;
 	if (map->libbpf_type == LIBBPF_MAP_RODATA && strcmp(map->real_name, RODATA_SEC) != 0)
 		return true;
+	if (map->libbpf_type == LIBBPF_MAP_PERCPU)
+		return true;
 	return false;
 }
 
@@ -10976,7 +11030,8 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 		size_t mmap_old_sz, mmap_new_sz;
 		int err;
 
-		if (map->def.type != BPF_MAP_TYPE_ARRAY)
+		if (map->def.type != BPF_MAP_TYPE_ARRAY &&
+		    map->def.type != BPF_MAP_TYPE_PERCPU_ARRAY)
 			return libbpf_err(-EOPNOTSUPP);
 
 		mmap_old_sz = bpf_map_mmap_sz(map);
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 7a74abb904f8..4c46d34fc055 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -401,6 +401,8 @@ enum kern_feature_id {
 	FEAT_BTF_LAYOUT,
 	/* Kernel supports BPF syscall common attributes */
 	FEAT_BPF_SYSCALL_COMMON_ATTRS,
+	/* Kernel supports percpu data */
+	FEAT_PERCPU_DATA,
 	__FEAT_CNT,
 };
 
diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index 53fee53d36d5..1f3f332dffbe 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -131,8 +131,10 @@ static inline void skel_free_map_data(void *p, __u64 addr, size_t sz)
 {
 	if (addr != ~0ULL)
 		kvfree(p);
-	/* When addr == ~0ULL the 'p' points to
-	 * ((struct bpf_array *)map)->value. See skel_finalize_map_data.
+	/*
+	 * When addr == ~0ULL the init buffer has already been released.
+	 * For skel_finalize_map_data(), 'p' points to
+	 * ((struct bpf_array *)map)->value.
 	 */
 }
 
@@ -170,6 +172,15 @@ static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int
 	return addr;
 }
 
+static inline int skel_protect_map_data(void *p, __u64 *init_val, size_t sz)
+{
+	(void)sz;
+
+	kvfree(p);
+	*init_val = ~0ULL;
+	return 0;
+}
+
 #else
 
 static inline void *skel_alloc(size_t size)
@@ -208,6 +219,15 @@ static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int
 		return NULL;
 	return addr;
 }
+
+static inline int skel_protect_map_data(void *p, __u64 *init_val, size_t sz)
+{
+	(void)init_val;
+
+	if (mprotect(p, sz, PROT_READ))
+		return -errno;
+	return 0;
+}
 #endif
 
 static inline int skel_closenz(int fd)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index d3655a706482..560ce4016fbf 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -531,7 +531,7 @@ LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c
 
 # Generate both light skeleton and libbpf skeleton for these
 LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
-	kfunc_call_test_subprog.c
+	kfunc_call_test_subprog.c test_global_percpu_data.c
 SKEL_BLACKLIST += $$(LSKELS) $$(LSKELS_SIGNED)
 
 test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index 8466332d7406..7d6bda909295 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "bpf/libbpf_internal.h"
+#include "test_global_percpu_data.skel.h"
+#include "test_global_percpu_data.lskel.h"
 
 void test_global_data_init(void)
 {
@@ -60,3 +63,336 @@ void test_global_data_init(void)
 	free(newval);
 	bpf_object__close(obj);
 }
+
+static void test_percpu_data_on_cpus(struct bpf_map *map, int map_fd, int prog_fd, int *runp)
+{
+	struct test_global_percpu_data__percpu *data = NULL;
+	int i, err, key = 0, num_online, run = 0;
+	__u64 args[2] = {0x1234ULL, 0x5678ULL};
+	size_t data_sz;
+	bool *online;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .ctx_in = args,
+		    .ctx_size_in = sizeof(args),
+		    .flags = BPF_F_TEST_RUN_ON_CPU,
+	);
+
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online", &online, &num_online);
+	if (!ASSERT_OK(err, "parse_cpu_mask_file"))
+		return;
+
+	data_sz = map ? bpf_map__value_size(map) : sizeof(*data);
+	data = calloc(1, data_sz);
+	if (!ASSERT_OK_PTR(data, "calloc percpu data"))
+		goto out;
+
+	/* run on every online-CPU */
+	for (i = 0; i < num_online; i++) {
+		__u64 flags;
+
+		if (!online[i])
+			continue;
+
+		topts.cpu = i;
+		topts.retval = -1;
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		ASSERT_OK(err, "bpf_prog_test_run_opts");
+		ASSERT_EQ(topts.retval, 0, "bpf_prog_test_run_opts retval");
+
+		memset(data, 0, data_sz);
+		flags = ((__u64) i << 32) | BPF_F_CPU;
+		if (map)
+			err = bpf_map__lookup_elem(map, &key, sizeof(key), data, data_sz, flags);
+		else
+			err = bpf_map_lookup_elem_flags(map_fd, &key, data, flags);
+		if (!ASSERT_OK(err, "lookup_elem on cpu"))
+			break;
+
+		ASSERT_EQ(*runp, ++run, "run");
+		ASSERT_EQ(data->cpu_id[0], i, "cpu_id");
+		ASSERT_EQ(data->data, 1, "data");
+		ASSERT_TRUE(data->set, "set");
+		ASSERT_EQ(data->nums[6], 0xc0de, "nums[6]");
+		ASSERT_EQ(data->struct_data.i, 1, "struct_data.i");
+		ASSERT_TRUE(data->struct_data.set, "struct_data.set");
+		ASSERT_EQ(data->struct_data.nums[6], 0xc0de, "struct_data.nums[6]");
+	}
+
+out:
+	free(data);
+	free(online);
+}
+
+static void test_global_percpu_data_init(void)
+{
+	struct test_global_percpu_data__percpu init_value = {};
+	struct test_global_percpu_data__percpu *init_data;
+	const __u32 desired_sz = sysconf(_SC_PAGE_SIZE);
+	struct test_global_percpu_data *skel = NULL;
+	size_t init_data_sz;
+	struct bpf_map *map;
+	int prog_fd, err;
+
+	skel = test_global_percpu_data__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_percpu_data__open"))
+		goto out;
+	if (!ASSERT_OK_PTR(skel->percpu, "skel->percpu"))
+		goto out;
+	if (!ASSERT_OK_PTR(skel->data_percpu, "skel->data_percpu"))
+		goto out;
+	if (!ASSERT_OK_PTR(skel->percpu_data, "skel->percpu_data"))
+		goto out;
+	if (!ASSERT_OK_PTR(skel->percpu_looooooooong, "skel->percpu_looooooooong"))
+		goto out;
+
+	ASSERT_STREQ(bpf_map__name(skel->maps.percpu_data), ".percpu.data",
+		     ".percpu.data map name");
+	ASSERT_STREQ(bpf_map__name(skel->maps.data_percpu), ".data.percpu",
+		     ".data.percpu map name");
+	ASSERT_STREQ(bpf_map__name(skel->maps.percpu_looooooooong), ".percpu.looooooooong",
+		     "long map name");
+	ASSERT_STREQ(bpf_map__name(skel->maps.percpu), ".percpu", "map name");
+	ASSERT_EQ(skel->percpu->data, -1, "skel->percpu->data");
+	ASSERT_FALSE(skel->percpu->set, "skel->percpu->set");
+	ASSERT_EQ(skel->percpu->nums[6], 0, "skel->percpu->nums[6]");
+	ASSERT_EQ(skel->percpu->struct_data.i, -1, "struct_data.i");
+	ASSERT_FALSE(skel->percpu->struct_data.set, "struct_data.set");
+	ASSERT_EQ(skel->percpu->struct_data.nums[6], 0, "struct_data.nums[6]");
+
+	map = skel->maps.percpu;
+	if (!ASSERT_EQ(bpf_map__type(map), BPF_MAP_TYPE_PERCPU_ARRAY, "bpf_map__type"))
+		goto out;
+
+	init_value.data = 2;
+	init_value.nums[6] = -1;
+	init_value.struct_data.i = 2;
+	init_value.struct_data.nums[6] = -1;
+	err = bpf_map__set_initial_value(map, &init_value, sizeof(init_value));
+	if (!ASSERT_OK(err, "bpf_map__set_initial_value"))
+		goto out;
+
+	init_data = bpf_map__initial_value(map, &init_data_sz);
+	if (!ASSERT_OK_PTR(init_data, "bpf_map__initial_value"))
+		goto out;
+
+	ASSERT_EQ(init_data->data, init_value.data, "init_value data");
+	ASSERT_EQ(init_data->set, init_value.set, "init_value set");
+	ASSERT_EQ(init_data->struct_data.i, init_value.struct_data.i, "init_value struct_data.i");
+	ASSERT_EQ(init_data->struct_data.nums[6], init_value.struct_data.nums[6],
+		  "init_value struct_data.nums[6]");
+	ASSERT_EQ(init_data_sz, sizeof(init_value), "init_value size");
+	ASSERT_EQ((void *) init_data, (void *) skel->percpu, "skel->percpu eq init_data");
+	ASSERT_EQ(skel->percpu->data, init_value.data, "skel->percpu->data");
+	ASSERT_EQ(skel->percpu->set, init_value.set, "skel->percpu->set");
+	ASSERT_EQ(skel->percpu->struct_data.i, init_value.struct_data.i,
+		  "skel->percpu->struct_data.i");
+	ASSERT_EQ(skel->percpu->struct_data.nums[6], init_value.struct_data.nums[6],
+		  "skel->percpu->struct_data.nums[6]");
+
+	ASSERT_GT(desired_sz, sizeof(init_value), "desired_sz");
+	err = bpf_map__set_value_size(map, desired_sz);
+	if (!ASSERT_OK(err, "bpf_map__set_value_size"))
+		goto out;
+	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "percpu value size"))
+		goto out;
+	if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, "percpu BTF value type"))
+		goto out;
+
+	init_data = bpf_map__initial_value(map, &init_data_sz);
+	if (!ASSERT_OK_PTR(init_data, "resized bpf_map__initial_value"))
+		goto out;
+	if (!ASSERT_EQ(init_data_sz, desired_sz, "resized initial value size"))
+		goto out;
+	if (!ASSERT_EQ(init_data->data, init_value.data, "resized initial value data"))
+		goto out;
+
+	err = test_global_percpu_data__load(skel);
+	if (!ASSERT_OK(err, "test_global_percpu_data__load"))
+		goto out;
+
+	ASSERT_OK_PTR(skel->percpu, "skel->percpu");
+
+	prog_fd = bpf_program__fd(skel->progs.update_percpu_data);
+	test_percpu_data_on_cpus(map, bpf_map__fd(map), prog_fd, &skel->bss->run);
+
+out:
+	test_global_percpu_data__destroy(skel);
+}
+
+static void test_global_percpu_data_lskel(void)
+{
+	struct test_global_percpu_data_lskel *lskel = NULL;
+	int prog_fd, map_fd;
+
+	lskel = test_global_percpu_data_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(lskel, "test_global_percpu_data_lskel__open_and_load"))
+		goto out;
+
+	map_fd = lskel->maps.percpu.map_fd;
+	prog_fd = lskel->progs.update_percpu_data.prog_fd;
+	test_percpu_data_on_cpus(NULL, map_fd, prog_fd, &lskel->bss->run);
+
+out:
+	test_global_percpu_data_lskel__destroy(lskel);
+}
+
+static int create_rdonly_percpu_array(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		    .map_flags = BPF_F_RDONLY_PROG,
+	);
+	int key = 0, map_fd, err;
+	__u64 value = 0;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "percpu_ro_map", sizeof(int),
+				sizeof(__u64), 1, &map_opts);
+	if (!ASSERT_GE(map_fd, 0, "bpf_map_create"))
+		return -1;
+
+	err = bpf_map_update_elem(map_fd, &key, &value, BPF_F_ALL_CPUS);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto out;
+
+	err = bpf_map_freeze(map_fd);
+	if (!ASSERT_OK(err, "bpf_map_freeze"))
+		goto out;
+
+	return map_fd;
+
+out:
+	close(map_fd);
+	return -1;
+}
+
+static void test_global_percpu_data_rdonly_direct_read(void)
+{
+	/*
+	 * Raw instructions with manually prepared rdonly percpu_array map
+	 * for testing direct-read global percpu data, because libbpf
+	 * doesn't have rdonly internal percpu_array map support for
+	 * global percpu data.
+	 */
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+		BPF_EXIT_INSN(),
+	};
+	int map_fd, prog_fd;
+
+	map_fd = create_rdonly_percpu_array();
+	if (map_fd < 0)
+		return;
+
+	insns[0].imm = map_fd;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "percpu_ro_prog", "GPL", insns,
+				ARRAY_SIZE(insns), NULL);
+	if (ASSERT_GE(prog_fd, 0, "bpf_prog_load"))
+		close(prog_fd);
+	close(map_fd);
+}
+
+static void test_global_percpu_data_rdonly_direct_write(void)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts);
+	/* See the comment in test_global_percpu_data_rdonly_direct_read() */
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
+		BPF_EXIT_INSN(),
+	};
+	char log_buf[256] = {};
+	int map_fd, prog_fd;
+
+	prog_opts.log_buf = log_buf;
+	prog_opts.log_size = sizeof(log_buf);
+	prog_opts.log_level = 1;
+
+	map_fd = create_rdonly_percpu_array();
+	if (map_fd < 0)
+		return;
+
+	insns[0].imm = map_fd;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "percpu_ro_prog", "GPL", insns,
+				ARRAY_SIZE(insns), &prog_opts);
+	if (!ASSERT_LT(prog_fd, 0, "bpf_prog_load"))
+		close(prog_fd);
+	else
+		ASSERT_HAS_SUBSTR(log_buf, "write into map forbidden", "verifier log");
+	close(map_fd);
+}
+
+static void test_global_percpu_data_verifier_log(void)
+{
+	RUN_TESTS(test_global_percpu_data);
+}
+
+static void test_global_percpu_data_iter(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct test_global_percpu_data *skel;
+	union bpf_iter_link_info linfo = {};
+	struct bpf_link *link = NULL;
+	int fd, num_cpus, len, err;
+	char buf[16];
+
+	num_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	skel = test_global_percpu_data__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_percpu_data__open"))
+		return;
+
+	skel->rodata->num_cpus = num_cpus;
+	skel->rodata->offsetof_num = offsetof(struct test_global_percpu_data__percpu, struct_data);
+	skel->rodata->offsetof_num += sizeof(skel->percpu->struct_data) - sizeof(int);
+	skel->rodata->elem_sz = roundup(sizeof(struct test_global_percpu_data__percpu), 8);
+	skel->percpu->struct_data.nums[6] = 0xc0de;
+
+	err = test_global_percpu_data__load(skel);
+	if (!ASSERT_OK(err, "test_global_percpu_data__load"))
+		goto out;
+
+	linfo.map.map_fd = bpf_map__fd(skel->maps.percpu);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_percpu_data, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto out;
+
+	fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(fd, 0, "bpf_iter_create"))
+		goto out;
+
+	while ((len = read(fd, buf, sizeof(buf))) > 0)
+		do { } while (0);
+	ASSERT_EQ(len, 0, "read iter");
+	ASSERT_TRUE(skel->bss->run_iter, "run_iter");
+	ASSERT_EQ(skel->bss->percpu_data_sum, 0xc0de * num_cpus, "percpu_data_sum");
+
+	close(fd);
+out:
+	bpf_link__destroy(link);
+	test_global_percpu_data__destroy(skel);
+}
+
+void test_global_percpu_data(void)
+{
+	if (!feat_supported(NULL, FEAT_PERCPU_DATA)) {
+		test__skip();
+		return;
+	}
+
+	if (test__start_subtest("init"))
+		test_global_percpu_data_init();
+	if (test__start_subtest("lskel"))
+		test_global_percpu_data_lskel();
+	if (test__start_subtest("rdonly_direct_read"))
+		test_global_percpu_data_rdonly_direct_read();
+	if (test__start_subtest("rdonly_direct_write"))
+		test_global_percpu_data_rdonly_direct_write();
+	test_global_percpu_data_verifier_log();
+	if (test__start_subtest("iter"))
+		test_global_percpu_data_iter();
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_percpu_data.c b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
new file mode 100644
index 000000000000..71ff8d1bf49e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* Used for testing map name. */
+int loong SEC(".percpu.looooooooong");
+int data3 SEC(".data.percpu");
+int data2 SEC(".percpu.data");
+
+int run;
+/* cpu_id as array to verify map value resizing. */
+int cpu_id[1] SEC(".percpu");
+int data SEC(".percpu") = -1;
+int nums[7] SEC(".percpu");
+bool set SEC(".percpu") = false;
+struct {
+	char set;
+	int i;
+	int nums[7];
+} struct_data SEC(".percpu") = {
+	.set = 0,
+	.i = -1,
+};
+
+SEC("raw_tp/task_rename")
+__auxiliary
+int update_percpu_data(void *ctx)
+{
+	struct_data.nums[6] = 0xc0de;
+	struct_data.set = 1;
+	struct_data.i = 1;
+	nums[6] = 0xc0de;
+	data = 1;
+	run++;
+	set = true;
+	cpu_id[0] = bpf_get_smp_processor_id();
+	return 0;
+}
+
+static const char fmt[] SEC(".percpu.fmt") = "data %d\n";
+
+SEC("?kprobe")
+__failure __msg("R{{[0-9]+}} points to percpu_array map which cannot be used as const string")
+int verifier_strncmp(void *ctx)
+{
+	return bpf_strncmp("test", 5, fmt);
+}
+
+SEC("?kprobe")
+__failure __msg("R{{[0-9]+}} points to percpu_array map which cannot be used as const string")
+int verifier_snprintf(void *ctx)
+{
+	u64 args[] = { data };
+	char buf[128];
+	int len;
+
+	len = bpf_snprintf(buf, sizeof(buf), fmt, args, sizeof(args));
+	if (len > 0)
+		bpf_printk("snprintf: %s\n", buf);
+	return 0;
+}
+
+volatile const __u32 num_cpus = 0;
+volatile const int offsetof_num;
+volatile const int elem_sz;
+__u32 percpu_data_sum = 0;
+bool run_iter = false;
+
+SEC("iter/bpf_map_elem")
+__auxiliary
+int dump_percpu_data(struct bpf_iter__bpf_map_elem *ctx)
+{
+	void *pptr = ctx->value;
+	int i;
+
+	if (!pptr)
+		return 0;
+
+	run_iter = true;
+
+	for (i = 0; i < num_cpus; i++) {
+		percpu_data_sum += *(int *) (pptr + offsetof_num);
+		pptr += elem_sz;
+	}
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";