libbpf: Handle <orig_name>.llvm.<hash> symbol properly

With CONFIG_LTO_CLANG_THIN enabled, with some of previous
version of kernel code base ([1]), I hit the following
error:
   test_ksyms:PASS:kallsyms_fopen 0 nsec
   test_ksyms:FAIL:ksym_find symbol 'bpf_link_fops' not found
   #118     ksyms:FAIL

The reason is that 'bpf_link_fops' is renamed to
   bpf_link_fops.llvm.8325593422554671469
Due to cross-file inlining, the static variable 'bpf_link_fops'
in syscall.c is used by a function in another file. To avoid
potential duplicated names, the llvm added suffix
'.llvm.<hash>' ([2]) to 'bpf_link_fops' variable.
Such renaming caused a problem in libbpf if 'bpf_link_fops'
is used in bpf prog as a ksym but 'bpf_link_fops' does not
match any symbol in /proc/kallsyms.

To fix this issue, libbpf needs to understand that suffix '.llvm.<hash>'
is caused by clang lto kernel and to process such symbols properly.

With latest bpf-next code base built with CONFIG_LTO_CLANG_THIN,
I cannot reproduce the above failure any more. But such an issue
could happen with other symbols or in the future for bpf_link_fops symbol.

For example, with my current kernel, I got the following from
/proc/kallsyms:
  ffffffff84782154 d __func__.net_ratelimit.llvm.6135436931166841955
  ffffffff85f0a500 d tk_core.llvm.726630847145216431
  ffffffff85fdb960 d __fs_reclaim_map.llvm.10487989720912350772
  ffffffff864c7300 d fake_dst_ops.llvm.54750082607048300

I could not easily create a selftest to test newly-added
libbpf functionality with a static C test since I do not know
which symbol is cross-file inlined. But based on my particular kernel,
the following test change can run successfully.

>  diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c
>  index 6a86d1f07800..904a103f7b1d 100644
>  --- a/tools/testing/selftests/bpf/prog_tests/ksyms.c
>  +++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c
>  @@ -42,6 +42,7 @@ void test_ksyms(void)
>          ASSERT_EQ(data->out__bpf_link_fops, link_fops_addr, "bpf_link_fops");
>          ASSERT_EQ(data->out__bpf_link_fops1, 0, "bpf_link_fops1");
>          ASSERT_EQ(data->out__btf_size, btf_size, "btf_size");
>  +       ASSERT_NEQ(data->out__fake_dst_ops, 0, "fake_dst_ops");
>          ASSERT_EQ(data->out__per_cpu_start, per_cpu_start_addr, "__per_cpu_start");
>
>   cleanup:
>  diff --git a/tools/testing/selftests/bpf/progs/test_ksyms.c b/tools/testing/selftests/bpf/progs/test_ksyms.c
>  index 6c9cbb5a3bdf..fe91eef54b66 100644
>  --- a/tools/testing/selftests/bpf/progs/test_ksyms.c
>  +++ b/tools/testing/selftests/bpf/progs/test_ksyms.c
>  @@ -9,11 +9,13 @@ __u64 out__bpf_link_fops = -1;
>   __u64 out__bpf_link_fops1 = -1;
>   __u64 out__btf_size = -1;
>   __u64 out__per_cpu_start = -1;
>  +__u64 out__fake_dst_ops = -1;
>
>   extern const void bpf_link_fops __ksym;
>   extern const void __start_BTF __ksym;
>   extern const void __stop_BTF __ksym;
>   extern const void __per_cpu_start __ksym;
>  +extern const void fake_dst_ops __ksym;
>   /* non-existing symbol, weak, default to zero */
>   extern const void bpf_link_fops1 __ksym __weak;
>
>  @@ -23,6 +25,7 @@ int handler(const void *ctx)
>          out__bpf_link_fops = (__u64)&bpf_link_fops;
>          out__btf_size = (__u64)(&__stop_BTF - &__start_BTF);
>          out__per_cpu_start = (__u64)&__per_cpu_start;
>  +       out__fake_dst_ops = (__u64)&fake_dst_ops;
>
>          out__bpf_link_fops1 = (__u64)&bpf_link_fops1;

This patch fixed the issue in libbpf such that
the suffix '.llvm.<hash>' will be ignored during comparison of
bpf prog ksym vs. symbols in /proc/kallsyms, this resolved the issue.
Currently, only static variables in /proc/kallsyms are checked
with '.llvm.<hash>' suffix since in bpf programs function ksyms
with '.llvm.<hash>' suffix are most likely kfunc's and unlikely
to be cross-file inlined.

Note that currently kernel does not support gcc build with lto.

  [1] https://lore.kernel.org/bpf/20240302165017.1627295-1-yonghong.song@linux.dev/
  [2] https://github.com/llvm/llvm-project/blob/release/18.x/llvm/include/llvm/IR/ModuleSummaryIndex.h#L1714-L1719

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20240326041458.1198161-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1822fb8a02d2335ec641073579e91233a604f173..b091154bc5b58462fbb80065df64444d935f4340 100644 (file)
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1970,6 +1970,20 @@ static struct extern_desc *find_extern_by_name(const struct bpf_object *obj,
        return NULL;
 }
 
+static struct extern_desc *find_extern_by_name_with_len(const struct bpf_object *obj,
+                                                       const void *name, int len)
+{
+       const char *ext_name;
+       int i;
+
+       for (i = 0; i < obj->nr_extern; i++) {
+               ext_name = obj->externs[i].name;
+               if (strlen(ext_name) == len && strncmp(ext_name, name, len) == 0)
+                       return &obj->externs[i];
+       }
+       return NULL;
+}
+
 static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val,
                              char value)
 {
@@ -8029,8 +8043,13 @@ static int kallsyms_cb(unsigned long long sym_addr, char sym_type,
        struct bpf_object *obj = ctx;
        const struct btf_type *t;
        struct extern_desc *ext;
+       char *res;
 
-       ext = find_extern_by_name(obj, sym_name);
+       res = strstr(sym_name, ".llvm.");
+       if (sym_type == 'd' && res)
+               ext = find_extern_by_name_with_len(obj, sym_name, res - sym_name);
+       else
+               ext = find_extern_by_name(obj, sym_name);
        if (!ext || ext->type != EXT_KSYM)
                return 0;