Re: [PAHOLE v4 2/3] dwarf_loader: Add support for DW_TAG_GNU_annotation

Hi Yonghong,

Thanks for reviewing the patches.

On 6/3/26 1:08 PM, Yonghong Song wrote:
>> [3] https://lore.kernel.org/bpf/[email protected]/
>> [2] https://lore.kernel.org/bpf/[email protected]/
>> [1] https://lore.kernel.org/bpf/[email protected]/
> I download and build gcc-16.1 which will be used for gcc compilation.
> I did some experiments with this patch set for both type tag and decl tag.
> See below.

FWIW, you definitely need a fix [1] on top of gcc 16.1.
The patch explains the reasoning and did cause some missing entries in 
type chain.
I haven't checked if this changes anything specific to issues you point 
below.

[1] https://gcc.gnu.org/pipermail/bpf/2026-May/000147.html


>
> For type tag
> ============
>
> $ cat type_tag.c
> /* btf_type_tag test cases.
>    *
>    * btf_type_tag annotates a *type* and the tag becomes part of the type
>    * chain in BTF (TYPE_TAG kind), e.g. used by the kernel for __user / __rcu
>    * / __percpu style annotations.
>    *
>    * Placement matters: the tag is written *before* the '*' so it annotates
>    * the pointee type.  This produces  PTR -> TYPE_TAG 'x' -> <pointee>.
>    *
>    * Build:  clang -O2 -g -target bpf -c type_tag.c -o type_tag.o
>    *         /home/yhs/work/gcc-build/opt/gcc-16.1/bin/gcc -O2 -gbtf -g -c type_tag.c -o type_tag.o
>    * Dump:   bpftool btf dump file type_tag.o
>    */
>
> #define __type_tag(x) __attribute__((btf_type_tag(x)))
>
> /* a single type tag on a pointer's pointee */
> int __type_tag("user") *user_ptr_var;
>
> /* stacked type tags: the chain is preserved, outermost first */
> int __type_tag("tag1") __type_tag("tag2") *stacked_var;
>
> /* type tags inside struct members */
> struct bar {
>           char __type_tag("rcu") *name;
>           int  __type_tag("percpu") *counter;
> };
>
> /* type tag on a function parameter's pointee */
> int read_user(int __type_tag("user") *p)
> {
>           return *p;
> }
>
> /* keep things referenced */
> int use(struct bar *b)
> {
>           return read_user(user_ptr_var) + (stacked_var ? *stacked_var : 0) +
>                  (b->counter ? *b->counter : 0);
> }
>
> $ /home/yhs/work/gcc-build/opt/gcc-16.1/bin/gcc -O2 -gbtf -g -c type_tag.c -o type_tag.o
> $ bpftool btf dump file type_tag.o
> [1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
> [2] PTR '(anon)' type_id=15
> [3] PTR '(anon)' type_id=17
> [4] STRUCT 'bar' size=16 vlen=2
>           'name' type_id=6 bits_offset=0
>           'counter' type_id=7 bits_offset=64
> [5] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED
> [6] PTR '(anon)' type_id=18
> [7] PTR '(anon)' type_id=19
> [8] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1
>           'b' type_id=9
> [9] PTR '(anon)' type_id=4
> [10] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1
>           'p' type_id=2
> [11] VAR 'stacked_var' type_id=3, linkage=global
> [12] VAR 'user_ptr_var' type_id=2, linkage=global
> [13] FUNC 'use' type_id=8 linkage=global
> [14] FUNC 'read_user' type_id=10 linkage=global
> [15] TYPE_TAG 'user' type_id=1
> [16] TYPE_TAG 'tag1' type_id=1
> [17] TYPE_TAG 'tag2' type_id=16
> [18] TYPE_TAG 'rcu' type_id=5
> [19] TYPE_TAG 'percpu' type_id=1
> [20] DATASEC '.bss' size=0 vlen=2
>           type_id=11 offset=0 size=8 (VAR 'stacked_var')
>           type_id=12 offset=0 size=8 (VAR 'user_ptr_var')
> $
>
> $ clang -O2 -g -target bpf -c type_tag.c -o type_tag.o
> $ bpftool btf dump file type_tag.o
> [1] TYPE_TAG 'user' type_id=3
> [2] PTR '(anon)' type_id=1
> [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
> [4] FUNC_PROTO '(anon)' ret_type_id=3 vlen=1
>           'p' type_id=2
> [5] FUNC 'read_user' type_id=4 linkage=global
> [6] PTR '(anon)' type_id=7
> [7] STRUCT 'bar' size=16 vlen=2
>           'name' type_id=9 bits_offset=0
>           'counter' type_id=12 bits_offset=64
> [8] TYPE_TAG 'rcu' type_id=10
> [9] PTR '(anon)' type_id=8
> [10] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED
> [11] TYPE_TAG 'percpu' type_id=3
> [12] PTR '(anon)' type_id=11
> [13] FUNC_PROTO '(anon)' ret_type_id=3 vlen=1
>           'b' type_id=6
> [14] FUNC 'use' type_id=13 linkage=global
> [15] VAR 'user_ptr_var' type_id=2, linkage=global
> [16] TYPE_TAG 'tag1' type_id=3
> [17] TYPE_TAG 'tag2' type_id=16
> [18] PTR '(anon)' type_id=17
> [19] VAR 'stacked_var' type_id=18, linkage=global
> [20] DATASEC '.bss' size=0 vlen=2
>           type_id=15 offset=0 size=8 (VAR 'user_ptr_var')
>           type_id=19 offset=0 size=8 (VAR 'stacked_var')
> $
>
> So type tag matches between clang and gcc.

Nice, thanks for cross-checking and confirming.


> For decl tag
> ============
>
> $ cat decl_tag.c
> /* btf_decl_tag test cases.
>    *
>    * btf_decl_tag can be attached to:
>    *   - global (incl. static) variables
>    *   - functions
>    *   - function parameters
>    *   - struct/union types and their members
>    *   - typedefs
>    *
>    * Build:  clang -O2 -target bpf -g -c decl_tag.c -o decl_tag.o
>    *         /home/yhs/work/gcc-build/opt/gcc-16.1/bin/gcc -O2 -gbtf -g -c decl_tag.c -o decl_tag.o
>    * Dump:   bpftool btf dump file decl_tag.o
>    */
>
> #define __tag(x) __attribute__((btf_decl_tag(x)))
>
> /* tag on a global variable */
> int global_var __tag("global_var_tag");
>
> /* tag on a static variable */
> static int static_var __tag("static_var_tag");
>
> /* multiple tags on one declaration */
> int multi_tag_var __tag("tag_a") __tag("tag_b");
>
> /* tag on struct type and its members */
> struct foo {
>           int a __tag("member_a_tag");
>           int b __tag("member_b_tag");
> } __tag("struct_foo_tag");
>
> /* tag on a typedef */
> typedef struct foo foo_t1 __tag("typedef_foo_tag");
> typedef struct {int foo2;} foo_t2 __tag("typedef_foo2_tag");
>
> /* tag on a function and its parameters */
> __tag("func_add_tag")
> int add(int x __tag("param_x_tag"), int y __tag("param_y_tag"))
> {
>           return x + y;
> }
>
> /* keep the globals/types alive so they land in BTF */
> int use(foo_t1 *f, foo_t2 *g)
> {
>           return add(global_var + static_var + multi_tag_var, f->a + g->foo2);
> }
>
> $ /home/yhs/work/gcc-build/opt/gcc-16.1/bin/gcc -O2 -gbtf -g -c decl_tag.c -o decl_tag.o
> decl_tag.c:30:1: warning: ‘btf_decl_tag’ attribute does not apply to types [-Wattributes]
>      30 | } __tag("struct_foo_tag");
>         | ^
>
> $ bpftool btf dump file decl_tag.o
> [1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
> [2] STRUCT 'foo' size=8 vlen=2
>           'a' type_id=1 bits_offset=0
>           'b' type_id=1 bits_offset=32
> [3] TYPEDEF 'foo_t1' type_id=2
> [4] STRUCT '(anon)' size=4 vlen=1
>           'foo2' type_id=1 bits_offset=0
> [5] TYPEDEF 'foo_t2' type_id=4
> [6] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2
>           'f' type_id=7
>           'g' type_id=8
> [7] PTR '(anon)' type_id=3
> [8] PTR '(anon)' type_id=5
> [9] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2
>           'x' type_id=1
>           'y' type_id=1
> [10] VAR 'multi_tag_var' type_id=1, linkage=global
> [11] VAR 'global_var' type_id=1, linkage=global
> [12] FUNC 'use' type_id=6 linkage=global
> [13] FUNC 'add' type_id=9 linkage=global
> [14] DECL_TAG 'global_var_tag' type_id=11 component_idx=-1
> [15] DECL_TAG 'static_var_tag' type_id=0 component_idx=-1
> [16] DECL_TAG 'tag_b' type_id=10 component_idx=-1
> [17] DECL_TAG 'tag_a' type_id=10 component_idx=-1
> [18] DECL_TAG 'member_a_tag' type_id=2 component_idx=0
> [19] DECL_TAG 'member_b_tag' type_id=2 component_idx=1
> [20] DECL_TAG 'param_x_tag' type_id=13 component_idx=0
> [21] DECL_TAG 'param_y_tag' type_id=13 component_idx=1
> [22] DECL_TAG 'func_add_tag' type_id=13 component_idx=-1
> [23] DATASEC '.bss' size=0 vlen=2
>           type_id=10 offset=0 size=4 (VAR 'multi_tag_var')
>           type_id=11 offset=0 size=4 (VAR 'global_var')
> $ bpftool btf dump file decl_tag.o | grep DECL_TAG
> [14] DECL_TAG 'global_var_tag' type_id=11 component_idx=-1
> [15] DECL_TAG 'static_var_tag' type_id=0 component_idx=-1
> [16] DECL_TAG 'tag_b' type_id=10 component_idx=-1
> [17] DECL_TAG 'tag_a' type_id=10 component_idx=-1
> [18] DECL_TAG 'member_a_tag' type_id=2 component_idx=0
> [19] DECL_TAG 'member_b_tag' type_id=2 component_idx=1
> [20] DECL_TAG 'param_x_tag' type_id=13 component_idx=0
> [21] DECL_TAG 'param_y_tag' type_id=13 component_idx=1
> [22] DECL_TAG 'func_add_tag' type_id=13 component_idx=-1
> $
>
> Three decl tags (struct_foo_tag, typedef_foo_tag and typedef_foo2_tag)
> are missing here:

I'll double check, once I'm back from PTO.

> struct foo {
>           int a __tag("member_a_tag");
>           int b __tag("member_b_tag");
> } __tag("struct_foo_tag");
>
> /* tag on a typedef */
> typedef struct foo foo_t1 __tag("typedef_foo_tag");
> typedef struct {int foo2;} foo_t2 __tag("typedef_foo2_tag");
>
> $ clang -O2 -g -target bpf -c decl_tag.c -o decl_tag.o
> $ bpftool btf dump file decl_tag.o
> [1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED
> [2] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2
>           'x' type_id=1
>           'y' type_id=1
> [3] FUNC 'add' type_id=2 linkage=global
> [4] DECL_TAG 'param_x_tag' type_id=3 component_idx=0
> [5] DECL_TAG 'param_y_tag' type_id=3 component_idx=1
> [6] DECL_TAG 'func_add_tag' type_id=3 component_idx=-1
> [7] PTR '(anon)' type_id=8
> [8] TYPEDEF 'foo_t1' type_id=10
> [9] DECL_TAG 'typedef_foo_tag' type_id=8 component_idx=-1
> [10] STRUCT 'foo' size=8 vlen=2
>           'a' type_id=1 bits_offset=0
>           'b' type_id=1 bits_offset=32
> [11] DECL_TAG 'struct_foo_tag' type_id=10 component_idx=-1
> [12] DECL_TAG 'member_a_tag' type_id=10 component_idx=0
> [13] DECL_TAG 'member_b_tag' type_id=10 component_idx=1
> [14] PTR '(anon)' type_id=15
> [15] TYPEDEF 'foo_t2' type_id=17
> [16] DECL_TAG 'typedef_foo2_tag' type_id=15 component_idx=-1
> [17] STRUCT '(anon)' size=4 vlen=1
>           'foo2' type_id=1 bits_offset=0
> [18] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2
>           'f' type_id=7
>           'g' type_id=14
> [19] FUNC 'use' type_id=18 linkage=global
> [20] VAR 'global_var' type_id=1, linkage=global
> [21] DECL_TAG 'global_var_tag' type_id=20 component_idx=-1
> [22] VAR 'multi_tag_var' type_id=1, linkage=global
> [23] DECL_TAG 'tag_a' type_id=22 component_idx=-1
> [24] DECL_TAG 'tag_b' type_id=22 component_idx=-1
> [25] DATASEC '.bss' size=0 vlen=2
>           type_id=20 offset=0 size=4 (VAR 'global_var')
>           type_id=22 offset=0 size=4 (VAR 'multi_tag_var')
> $ bpftool btf dump file decl_tag.o | grep DECL_TAG
> [4] DECL_TAG 'param_x_tag' type_id=3 component_idx=0
> [5] DECL_TAG 'param_y_tag' type_id=3 component_idx=1
> [6] DECL_TAG 'func_add_tag' type_id=3 component_idx=-1
> [9] DECL_TAG 'typedef_foo_tag' type_id=8 component_idx=-1
> [11] DECL_TAG 'struct_foo_tag' type_id=10 component_idx=-1
> [12] DECL_TAG 'member_a_tag' type_id=10 component_idx=0
> [13] DECL_TAG 'member_b_tag' type_id=10 component_idx=1
> [16] DECL_TAG 'typedef_foo2_tag' type_id=15 component_idx=-1
> [21] DECL_TAG 'global_var_tag' type_id=20 component_idx=-1
> [23] DECL_TAG 'tag_a' type_id=22 component_idx=-1
> [24] DECL_TAG 'tag_b' type_id=22 component_idx=-1
>
> DECL_TAG 'static_var_tag' type_id=0 component_idx=-1 is missing in llvm.
> This is execpted for llvm since 'static_var' is 'inlined' since it is
> value is 0 and the compiler optimization removed it in function use().
> In llvm Dwarf->BTF conversion is very late and we only emit survived
> globals.
>
> gcc emits 'static_var_tag' probably in frontend. Emitting
> 'static_var_tag' is okay, just not used.
>
> I think gcc should support
>    - declaration tag for typedef, and
>    - declaration tag for the whole struct (like above 'struct_foo_tag')
> to be compatible with llvm.

OK we will look into this.

Thx,
-Vineet