Merge branch 'tools-resolve_btfids-fix-cross-compilation-to-non-host-endianness'

Viktor Malik says:

====================
tools/resolve_btfids: fix cross-compilation to non-host endianness

The .BTF_ids section is pre-filled with zeroed BTF ID entries during the
build and afterwards patched by resolve_btfids with correct values.
Since resolve_btfids always writes in host-native endianness, it relies
on libelf to do the translation when the target ELF is cross-compiled to
a different endianness (this was introduced in commit 61e8aeda9398
("bpf: Fix libelf endian handling in resolv_btfids")).

Unfortunately, the translation will corrupt the flags fields of SET8
entries because these were written during vmlinux compilation and are in
the correct endianness already. This will lead to numerous selftests
failures such as:

    $ sudo ./test_verifier 502 502
    #502/p sleepable fentry accept FAIL
    Failed to load prog 'Invalid argument'!
    bpf_fentry_test1 is not sleepable
    verification time 34 usec
    stack depth 0
    processed 0 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0
    Summary: 0 PASSED, 0 SKIPPED, 1 FAILED

Since it's not possible to instruct libelf to translate just certain
values, let's manually bswap the flags (both global and entry flags) in
resolve_btfids when needed, so that libelf then translates everything
correctly.

The first patch of the series refactors resolve_btfids by using types
from btf_ids.h instead of accessing the BTF ID data using magic offsets.
Acked-by: Jiri Olsa <jolsa@kernel.org>
---
Changes in v4:
- remove unnecessary vars and pointer casts (suggested by Daniel Xu)

Changes in v3:
- add byte swap of global 'flags' field in btf_id_set8 (suggested by
  Jiri Olsa)
- cleaner refactoring of sets_patch (suggested by Jiri Olsa)
- add compile-time assertion that IDs are at the beginning of pairs
  struct in btf_id_set8 (suggested by Daniel Borkmann)

Changes in v2:
- use type defs from btf_ids.h (suggested by Andrii Nakryiko)
====================

Link: https://lore.kernel.org/r/cover.1707223196.git.vmalik@redhat.com
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

tools/bpf/resolve_btfids/main.c

@@ -70,6 +70,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <linux/btf_ids.h>
 #include <linux/rbtree.h>
 #include <linux/zalloc.h>
 #include <linux/err.h>
@@ -78,7 +79,7 @@
 #include <subcmd/parse-options.h>
 
 #define BTF_IDS_SECTION	".BTF_ids"
-#define BTF_ID		"__BTF_ID__"
+#define BTF_ID_PREFIX	"__BTF_ID__"
 
 #define BTF_STRUCT	"struct"
 #define BTF_UNION	"union"
@@ -89,6 +90,14 @@
 
 #define ADDR_CNT	100
 
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+# define ELFDATANATIVE	ELFDATA2LSB
+#elif __BYTE_ORDER == __BIG_ENDIAN
+# define ELFDATANATIVE	ELFDATA2MSB
+#else
+# error "Unknown machine endianness!"
+#endif
+
 struct btf_id {
 	struct rb_node	 rb_node;
 	char		*name;
@@ -116,6 +125,7 @@ struct object {
 		int		 idlist_shndx;
 		size_t		 strtabidx;
 		unsigned long	 idlist_addr;
+		int		 encoding;
 	} efile;
 
 	struct rb_root	sets;
@@ -161,7 +171,7 @@ static int eprintf(int level, int var, const char *fmt, ...)
 
 static bool is_btf_id(const char *name)
 {
-	return name && !strncmp(name, BTF_ID, sizeof(BTF_ID) - 1);
+	return name && !strncmp(name, BTF_ID_PREFIX, sizeof(BTF_ID_PREFIX) - 1);
 }
 
 static struct btf_id *btf_id__find(struct rb_root *root, const char *name)
@@ -319,6 +329,7 @@ static int elf_collect(struct object *obj)
 {
 	Elf_Scn *scn = NULL;
 	size_t shdrstrndx;
+	GElf_Ehdr ehdr;
 	int idx = 0;
 	Elf *elf;
 	int fd;
@@ -350,6 +361,13 @@ static int elf_collect(struct object *obj)
 		return -1;
 	}
 
+	if (gelf_getehdr(obj->efile.elf, &ehdr) == NULL) {
+		pr_err("FAILED cannot get ELF header: %s\n",
+			elf_errmsg(-1));
+		return -1;
+	}
+	obj->efile.encoding = ehdr.e_ident[EI_DATA];
+
 	/*
 	 * Scan all the elf sections and look for save data
 	 * from .BTF_ids section and symbols.
@@ -441,7 +459,7 @@ static int symbols_collect(struct object *obj)
 		 * __BTF_ID__TYPE__vfs_truncate__0
 		 * prefix =  ^
 		 */
-		prefix = name + sizeof(BTF_ID) - 1;
+		prefix = name + sizeof(BTF_ID_PREFIX) - 1;
 
 		/* struct */
 		if (!strncmp(prefix, BTF_STRUCT, sizeof(BTF_STRUCT) - 1)) {
@@ -649,19 +667,18 @@ static int cmp_id(const void *pa, const void *pb)
 static int sets_patch(struct object *obj)
 {
 	Elf_Data *data = obj->efile.idlist;
-	int *ptr = data->d_buf;
 	struct rb_node *next;
 
 	next = rb_first(&obj->sets);
 	while (next) {
-		unsigned long addr, idx;
+		struct btf_id_set8 *set8;
+		struct btf_id_set *set;
+		unsigned long addr, off;
 		struct btf_id *id;
-		int *base;
-		int cnt;
 
 		id   = rb_entry(next, struct btf_id, rb_node);
 		addr = id->addr[0];
-		idx  = addr - obj->efile.idlist_addr;
+		off = addr - obj->efile.idlist_addr;
 
 		/* sets are unique */
 		if (id->addr_cnt != 1) {
@@ -670,14 +687,39 @@ static int sets_patch(struct object *obj)
 			return -1;
 		}
 
-		idx = idx / sizeof(int);
-		base = &ptr[idx] + (id->is_set8 ? 2 : 1);
-		cnt = ptr[idx];
+		if (id->is_set) {
+			set = data->d_buf + off;
+			qsort(set->ids, set->cnt, sizeof(set->ids[0]), cmp_id);
+		} else {
+			set8 = data->d_buf + off;
+			/*
+			 * Make sure id is at the beginning of the pairs
+			 * struct, otherwise the below qsort would not work.
+			 */
+			BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
+			qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
+
+			/*
+			 * When ELF endianness does not match endianness of the
+			 * host, libelf will do the translation when updating
+			 * the ELF. This, however, corrupts SET8 flags which are
+			 * already in the target endianness. So, let's bswap
+			 * them to the host endianness and libelf will then
+			 * correctly translate everything.
+			 */
+			if (obj->efile.encoding != ELFDATANATIVE) {
+				int i;
+
+				set8->flags = bswap_32(set8->flags);
+				for (i = 0; i < set8->cnt; i++) {
+					set8->pairs[i].flags =
+						bswap_32(set8->pairs[i].flags);
+				}
+			}
+		}
 
 		pr_debug("sorting  addr %5lu: cnt %6d [%s]\n",
-			 (idx + 1) * sizeof(int), cnt, id->name);
-
-		qsort(base, cnt, id->is_set8 ? sizeof(uint64_t) : sizeof(int), cmp_id);
+			 off, id->is_set ? set->cnt : set8->cnt, id->name);
 
 		next = rb_next(next);
 	}

tools/include/linux/btf_ids.h

@@ -8,6 +8,15 @@ struct btf_id_set {
 	u32 ids[];
 };
 
+struct btf_id_set8 {
+	u32 cnt;
+	u32 flags;
+	struct {
+		u32 id;
+		u32 flags;
+	} pairs[];
+};
+
 #ifdef CONFIG_DEBUG_INFO_BTF
 
 #include <linux/compiler.h> /* for __PASTE */