[PATCH dwarves v1] btf_encoder: handle .BTF_ids section endianness when cross-compiling

[Eduard Zingerman <eddyz87@xxxxxxxxx>]

btf_encoder__tag_kfuncs() reads .BTF_ids section to identify a set of
kfuncs present in the ELF being processed. This section consists of
records of the following shape:

  struct btf_id_and_flag {
      uint32_t id;
      uint32_t flags;
  };

When endianness of binary operated by pahole differs from the
host endianness these fields require byte swap before using.

At the moment such byte swap does not happen and kfuncs are not marked
with decl tags when e.g. s390 kernel is compiled on x86.
To reproduces the bug:
- follow instructions from [0] to build an s390 vmlinux;
- execute:
  pahole --btf_features_strict=decl_tag_kfuncs,decl_tag \
         --btf_encode_detached=test.btf vmlinux
- observe no kfuncs generated:
  bpftool btf dump test.btf format c | grep __ksym

This commit fixes the issue by adding an endianness conversion step
for .BTF_ids section data before main processing step, modifying the
Elf_Data object in-place.
The choice is such in order to:
- minimize changes;
- keep using Elf_Data, as it provides fields {d_size,d_off} used
  by kfunc processing routines;
- avoid sprinkling bswap_32 at each 'struct btf_id_and_flag' field
  access in fear of forgetting to add new ones when code is modified.

[0] https://docs.kernel.org/bpf/s390.html

Cc: Alan Maguire <alan.maguire@xxxxxxxxxx>
Cc: Daniel Xu <dxu@xxxxxxxxx>
Cc: Kumar Kartikeya Dwivedi <memxor@xxxxxxxxx>
Cc: Vadim Fedorenko <vadfed@xxxxxxxx>
Fixes: 72e88f29c6f7 ("pahole: Inject kfunc decl tags into BTF")
Signed-off-by: Eduard Zingerman <eddyz87@xxxxxxxxx>
---
 btf_encoder.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 lib/bpf       |  2 +-
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/btf_encoder.c b/btf_encoder.c
index e1adddf..3bdb73b 100644
--- a/btf_encoder.c
+++ b/btf_encoder.c
@@ -33,6 +33,7 @@
 #include <stdint.h>
 #include <search.h> /* for tsearch(), tfind() and tdestroy() */
 #include <pthread.h>
+#include <byteswap.h>
 
 #define BTF_IDS_SECTION		".BTF_ids"
 #define BTF_ID_FUNC_PFX		"__BTF_ID__func__"
@@ -1847,11 +1848,47 @@ static int btf_encoder__tag_kfunc(struct btf_encoder *encoder, struct gobuffer *
 	return 0;
 }
 
+/* If byte order of 'elf' differs from current byte order, convert the data->d_buf.
+ * ELF file is opened in a readonly mode, so data->d_buf cannot be modified in place.
+ * Instead, allocate a new buffer if modification is necessary.
+ */
+static int convert_idlist_endianness(Elf *elf, Elf_Data *data, bool *copied)
+{
+	int byteorder, i;
+	char *elf_ident;
+	uint32_t *tmp;
+
+	*copied = false;
+	elf_ident = elf_getident(elf, NULL);
+	if (elf_ident == NULL) {
+		fprintf(stderr, "Cannot get ELF identification from header\n");
+		return -EINVAL;
+	}
+	byteorder = elf_ident[EI_DATA];
+	if ((BYTE_ORDER == LITTLE_ENDIAN && byteorder == ELFDATA2LSB)
+	    || (BYTE_ORDER == BIG_ENDIAN && byteorder == ELFDATA2MSB))
+		return 0;
+	tmp = malloc(data->d_size);
+	if (tmp == NULL) {
+		fprintf(stderr, "Cannot allocate %lu bytes of memory\n", data->d_size);
+		return -ENOMEM;
+	}
+	memcpy(tmp, data->d_buf, data->d_size);
+	data->d_buf = tmp;
+	*copied = true;
+
+	/* .BTF_ids sections consist of u32 objects */
+	for (i = 0; i < data->d_size / sizeof(uint32_t); i++)
+		tmp[i] = bswap_32(tmp[i]);
+	return 0;
+}
+
 static int btf_encoder__tag_kfuncs(struct btf_encoder *encoder)
 {
 	const char *filename = encoder->source_filename;
 	struct gobuffer btf_kfunc_ranges = {};
 	struct gobuffer btf_funcs = {};
+	bool free_idlist = false;
 	Elf_Data *symbols = NULL;
 	Elf_Data *idlist = NULL;
 	Elf_Scn *symscn = NULL;
@@ -1919,6 +1956,9 @@ static int btf_encoder__tag_kfuncs(struct btf_encoder *encoder)
 			idlist_shndx = i;
 			idlist_addr = shdr.sh_addr;
 			idlist = data;
+			err = convert_idlist_endianness(elf, idlist, &free_idlist);
+			if (err < 0)
+				goto out;
 		}
 	}
 
@@ -2031,6 +2071,8 @@ static int btf_encoder__tag_kfuncs(struct btf_encoder *encoder)
 out:
 	__gobuffer__delete(&btf_funcs);
 	__gobuffer__delete(&btf_kfunc_ranges);
+	if (free_idlist)
+		free(idlist->d_buf);
 	if (elf)
 		elf_end(elf);
 	if (fd != -1)
diff --git a/lib/bpf b/lib/bpf
index 09b9e83..caa17bd 160000
--- a/lib/bpf
+++ b/lib/bpf
@@ -1 +1 @@
-Subproject commit 09b9e83102eb8ab9e540d36b4559c55f3bcdb95d
+Subproject commit caa17bdcbfc58e68eaf4d017c058e6577606bf56
-- 
2.47.0