diff mbox series

[bpf-next,3/4] bpf, bpftool: Generate skeleton for global percpu data

Message ID 20250127162158.84906-4-leon.hwang@linux.dev (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf: Introduce global percpu data | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success Errors and warnings before: 26 (+1) this patch: 26 (+1)
netdev/cc_maintainers warning 6 maintainers not CCed: john.fastabend@gmail.com kpsingh@kernel.org sdf@fomichev.me haoluo@google.com jolsa@kernel.org martin.lau@linux.dev
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 0 this patch: 0
netdev/checkpatch warning WARNING: line length of 84 exceeds 80 columns WARNING: line length of 86 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: static const char * array should probably be static const char * const
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 264 this patch: 264
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-12 success Logs for aarch64-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-11 success Logs for aarch64-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for s390x-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-19 success Logs for s390x-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-21 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-18 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-17 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-17 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-43 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-44 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-50 success Logs for x86_64-llvm-18 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-51 success Logs for x86_64-llvm-18 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-gcc / veristat-kernel / x86_64-gcc veristat_kernel
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-gcc / veristat-meta / x86_64-gcc veristat_meta
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-45 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-46 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-47 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-48 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-49 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18

Commit Message

Leon Hwang Jan. 27, 2025, 4:21 p.m. UTC 
This patch enhances bpftool to generate skeletons for global percpu
variables. The generated skeleton includes a dedicated structure for
percpu data, allowing users to initialize and access percpu variables
efficiently.

Changes:

1. skeleton structure:

For global percpu variables, the skeleton now includes a nested
structure, e.g.:

struct test_global_percpu_data {
	struct bpf_object_skeleton *skeleton;
	struct bpf_object *obj;
	struct {
		struct bpf_map *bss;
		struct bpf_map *percpu;
	} maps;
	// ...
	struct test_global_percpu_data__percpu {
		int percpu_data;
	} *percpu;

	// ...
};

  * The "struct test_global_percpu_data__percpu" points to initialized
    data, which is actually "maps.percpu->data".
  * Before loading the skeleton, updating the
    "struct test_global_percpu_data__percpu" modifies the initial value
    of the corresponding global percpu variables.
  * After loading the skeleton, accessing or updating this struct is no
    longer meaningful. Instead, users must interact with the global
    percpu variables via the "maps.percpu" map.

2. code changes:

  * Added support for ".percpu" sections in bpftool's map identification
    logic.
  * Modified skeleton generation to handle percpu data maps
    appropriately.
  * Updated libbpf to make "percpu" pointing to "maps.percpu->data".

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 tools/bpf/bpftool/gen.c | 13 +++++++++----
 tools/lib/bpf/libbpf.c  |  3 +++
 tools/lib/bpf/libbpf.h  |  1 +
 3 files changed, 13 insertions(+), 4 deletions(-)

Comments

Andrii Nakryiko Feb. 6, 2025, 12:09 a.m. UTC | #1 
On Mon, Jan 27, 2025 at 8:22 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> This patch enhances bpftool to generate skeletons for global percpu
> variables. The generated skeleton includes a dedicated structure for
> percpu data, allowing users to initialize and access percpu variables
> efficiently.
>
> Changes:
>
> 1. skeleton structure:
>
> For global percpu variables, the skeleton now includes a nested
> structure, e.g.:
>
> struct test_global_percpu_data {
>         struct bpf_object_skeleton *skeleton;
>         struct bpf_object *obj;
>         struct {
>                 struct bpf_map *bss;
>                 struct bpf_map *percpu;
>         } maps;
>         // ...
>         struct test_global_percpu_data__percpu {
>                 int percpu_data;
>         } *percpu;
>
>         // ...
> };
>
>   * The "struct test_global_percpu_data__percpu" points to initialized
>     data, which is actually "maps.percpu->data".
>   * Before loading the skeleton, updating the
>     "struct test_global_percpu_data__percpu" modifies the initial value
>     of the corresponding global percpu variables.
>   * After loading the skeleton, accessing or updating this struct is no
>     longer meaningful. Instead, users must interact with the global
>     percpu variables via the "maps.percpu" map.

can we set this pointer to NULL after load to avoid accidental
(successful) reads/writes to it?

>
> 2. code changes:
>
>   * Added support for ".percpu" sections in bpftool's map identification
>     logic.
>   * Modified skeleton generation to handle percpu data maps
>     appropriately.
>   * Updated libbpf to make "percpu" pointing to "maps.percpu->data".
>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
> ---
>  tools/bpf/bpftool/gen.c | 13 +++++++++----
>  tools/lib/bpf/libbpf.c  |  3 +++
>  tools/lib/bpf/libbpf.h  |  1 +
>  3 files changed, 13 insertions(+), 4 deletions(-)
>
> diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
> index 5a4d3240689ed..975775683ca12 100644
> --- a/tools/bpf/bpftool/gen.c
> +++ b/tools/bpf/bpftool/gen.c
> @@ -92,7 +92,7 @@ static void get_header_guard(char *guard, const char *obj_name, const char *suff
>
>  static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
>  {
> -       static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
> +       static const char *sfxs[] = { ".data", ".rodata", ".percpu", ".bss", ".kconfig" };
>         const char *name = bpf_map__name(map);
>         int i, n;
>
> @@ -117,7 +117,7 @@ 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", ".percpu", ".bss", ".kconfig" };
>         int i, n;
>
>         /* recognize hard coded LLVM section name */
> @@ -263,7 +263,9 @@ 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) ||
> +           (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE) &&
> +            bpf_map__type(map) != BPF_MAP_TYPE_PERCPU_ARRAY))

there will be no BPF_F_MMAPABLE set for PERCPU_ARRAY, why adding these
unnecessary extra conditionals?

>                 return false;
>
>         if (!get_map_ident(map, buf, sz))
> @@ -903,7 +905,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool
>                         i, bpf_map__name(map), ident);
>                 /* memory-mapped internal maps */
>                 if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) {
> -                       printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
> +                       if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY)
> +                               printf("\tmap->data = (void **)&obj->%s;\n", ident);
> +                       else
> +                               printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
>                 }
>
>                 if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) {
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 6da6004c5c84d..dafb419bc5b86 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -13915,6 +13915,7 @@ static int populate_skeleton_maps(const struct bpf_object *obj,
>                 struct bpf_map **map = map_skel->map;
>                 const char *name = map_skel->name;
>                 void **mmaped = map_skel->mmaped;
> +               void **data = map_skel->data;
>
>                 *map = bpf_object__find_map_by_name(obj, name);
>                 if (!*map) {
> @@ -13925,6 +13926,8 @@ static int populate_skeleton_maps(const struct bpf_object *obj,
>                 /* externs shouldn't be pre-setup from user code */
>                 if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG)
>                         *mmaped = (*map)->mmaped;
> +               if (data && (*map)->libbpf_type == LIBBPF_MAP_PERCPU_DATA)
> +                       *data = (*map)->data;
>         }
>         return 0;
>  }
> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
> index 3020ee45303a0..c49d6e44b5630 100644
> --- a/tools/lib/bpf/libbpf.h
> +++ b/tools/lib/bpf/libbpf.h
> @@ -1701,6 +1701,7 @@ struct bpf_map_skeleton {
>         const char *name;
>         struct bpf_map **map;
>         void **mmaped;
> +       void **data;

this is breaking backwards/forward compatibility. let's try to reuse mmaped

>         struct bpf_link **link;
>  };
>
> --
> 2.47.1
>
Leon Hwang Feb. 7, 2025, 9:52 a.m. UTC | #2 
On 6/2/25 08:09, Andrii Nakryiko wrote:
> On Mon, Jan 27, 2025 at 8:22 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>>
>> This patch enhances bpftool to generate skeletons for global percpu
>> variables. The generated skeleton includes a dedicated structure for
>> percpu data, allowing users to initialize and access percpu variables
>> efficiently.
>>
>> Changes:
>>
>> 1. skeleton structure:
>>
>> For global percpu variables, the skeleton now includes a nested
>> structure, e.g.:
>>
>> struct test_global_percpu_data {
>>         struct bpf_object_skeleton *skeleton;
>>         struct bpf_object *obj;
>>         struct {
>>                 struct bpf_map *bss;
>>                 struct bpf_map *percpu;
>>         } maps;
>>         // ...
>>         struct test_global_percpu_data__percpu {
>>                 int percpu_data;
>>         } *percpu;
>>
>>         // ...
>> };
>>
>>   * The "struct test_global_percpu_data__percpu" points to initialized
>>     data, which is actually "maps.percpu->data".
>>   * Before loading the skeleton, updating the
>>     "struct test_global_percpu_data__percpu" modifies the initial value
>>     of the corresponding global percpu variables.
>>   * After loading the skeleton, accessing or updating this struct is no
>>     longer meaningful. Instead, users must interact with the global
>>     percpu variables via the "maps.percpu" map.
> 
> can we set this pointer to NULL after load to avoid accidental
> (successful) reads/writes to it?
> 

Good idea. I'll try to achieve it.

>>
>> 2. code changes:
>>
>>   * Added support for ".percpu" sections in bpftool's map identification
>>     logic.
>>   * Modified skeleton generation to handle percpu data maps
>>     appropriately.
>>   * Updated libbpf to make "percpu" pointing to "maps.percpu->data".
>>
>> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
>> ---
>>  tools/bpf/bpftool/gen.c | 13 +++++++++----
>>  tools/lib/bpf/libbpf.c  |  3 +++
>>  tools/lib/bpf/libbpf.h  |  1 +
>>  3 files changed, 13 insertions(+), 4 deletions(-)
>>
>> diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
>> index 5a4d3240689ed..975775683ca12 100644
>> --- a/tools/bpf/bpftool/gen.c
>> +++ b/tools/bpf/bpftool/gen.c
>> @@ -92,7 +92,7 @@ static void get_header_guard(char *guard, const char *obj_name, const char *suff
>>
>>  static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
>>  {
>> -       static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
>> +       static const char *sfxs[] = { ".data", ".rodata", ".percpu", ".bss", ".kconfig" };
>>         const char *name = bpf_map__name(map);
>>         int i, n;
>>
>> @@ -117,7 +117,7 @@ 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", ".percpu", ".bss", ".kconfig" };
>>         int i, n;
>>
>>         /* recognize hard coded LLVM section name */
>> @@ -263,7 +263,9 @@ 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) ||
>> +           (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE) &&
>> +            bpf_map__type(map) != BPF_MAP_TYPE_PERCPU_ARRAY))
> 
> there will be no BPF_F_MMAPABLE set for PERCPU_ARRAY, why adding these
> unnecessary extra conditionals?
> 

Ack. It's unnecessary.

>>                 return false;
>>
>>         if (!get_map_ident(map, buf, sz))
>> @@ -903,7 +905,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool
>>                         i, bpf_map__name(map), ident);
>>                 /* memory-mapped internal maps */
>>                 if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) {
>> -                       printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
>> +                       if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY)
>> +                               printf("\tmap->data = (void **)&obj->%s;\n", ident);
>> +                       else
>> +                               printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
>>                 }
>>
>>                 if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) {
>> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
>> index 6da6004c5c84d..dafb419bc5b86 100644
>> --- a/tools/lib/bpf/libbpf.c
>> +++ b/tools/lib/bpf/libbpf.c
>> @@ -13915,6 +13915,7 @@ static int populate_skeleton_maps(const struct bpf_object *obj,
>>                 struct bpf_map **map = map_skel->map;
>>                 const char *name = map_skel->name;
>>                 void **mmaped = map_skel->mmaped;
>> +               void **data = map_skel->data;
>>
>>                 *map = bpf_object__find_map_by_name(obj, name);
>>                 if (!*map) {
>> @@ -13925,6 +13926,8 @@ static int populate_skeleton_maps(const struct bpf_object *obj,
>>                 /* externs shouldn't be pre-setup from user code */
>>                 if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG)
>>                         *mmaped = (*map)->mmaped;
>> +               if (data && (*map)->libbpf_type == LIBBPF_MAP_PERCPU_DATA)
>> +                       *data = (*map)->data;
>>         }
>>         return 0;
>>  }
>> diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
>> index 3020ee45303a0..c49d6e44b5630 100644
>> --- a/tools/lib/bpf/libbpf.h
>> +++ b/tools/lib/bpf/libbpf.h
>> @@ -1701,6 +1701,7 @@ struct bpf_map_skeleton {
>>         const char *name;
>>         struct bpf_map **map;
>>         void **mmaped;
>> +       void **data;
> 
> this is breaking backwards/forward compatibility. let's try to reuse mmaped
> 

Indeed. If reuse map->mmaped for global percpu variables, it's
unnecessary to add this "data".

>>         struct bpf_link **link;
>>  };
>>
>> --
>> 2.47.1
>>

Thanks,
Leon
diff mbox series

Patch

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 5a4d3240689ed..975775683ca12 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -92,7 +92,7 @@  static void get_header_guard(char *guard, const char *obj_name, const char *suff
 
 static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
 {
-	static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
+	static const char *sfxs[] = { ".data", ".rodata", ".percpu", ".bss", ".kconfig" };
 	const char *name = bpf_map__name(map);
 	int i, n;
 
@@ -117,7 +117,7 @@  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", ".percpu", ".bss", ".kconfig" };
 	int i, n;
 
 	/* recognize hard coded LLVM section name */
@@ -263,7 +263,9 @@  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) ||
+	    (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE) &&
+	     bpf_map__type(map) != BPF_MAP_TYPE_PERCPU_ARRAY))
 		return false;
 
 	if (!get_map_ident(map, buf, sz))
@@ -903,7 +905,10 @@  codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped, bool
 			i, bpf_map__name(map), ident);
 		/* memory-mapped internal maps */
 		if (mmaped && is_mmapable_map(map, ident, sizeof(ident))) {
-			printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
+			if (bpf_map__type(map) == BPF_MAP_TYPE_PERCPU_ARRAY)
+				printf("\tmap->data = (void **)&obj->%s;\n", ident);
+			else
+				printf("\tmap->mmaped = (void **)&obj->%s;\n", ident);
 		}
 
 		if (populate_links && bpf_map__type(map) == BPF_MAP_TYPE_STRUCT_OPS) {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6da6004c5c84d..dafb419bc5b86 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -13915,6 +13915,7 @@  static int populate_skeleton_maps(const struct bpf_object *obj,
 		struct bpf_map **map = map_skel->map;
 		const char *name = map_skel->name;
 		void **mmaped = map_skel->mmaped;
+		void **data = map_skel->data;
 
 		*map = bpf_object__find_map_by_name(obj, name);
 		if (!*map) {
@@ -13925,6 +13926,8 @@  static int populate_skeleton_maps(const struct bpf_object *obj,
 		/* externs shouldn't be pre-setup from user code */
 		if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG)
 			*mmaped = (*map)->mmaped;
+		if (data && (*map)->libbpf_type == LIBBPF_MAP_PERCPU_DATA)
+			*data = (*map)->data;
 	}
 	return 0;
 }
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 3020ee45303a0..c49d6e44b5630 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1701,6 +1701,7 @@  struct bpf_map_skeleton {
 	const char *name;
 	struct bpf_map **map;
 	void **mmaped;
+	void **data;
 	struct bpf_link **link;
 };