bpftool: __bpf_fastcall for kfuncs marked with special decl_tag

Generate __attribute__((bpf_fastcall)) for kfuncs marked with
"bpf_fastcall" decl tag. E.g. for the following BTF:

    $ bpftool btf dump file vmlinux
    ...
    [A] FUNC 'bpf_rdonly_cast' type_id=...
    ...
    [B] DECL_TAG 'bpf_kfunc' type_id=A component_idx=-1
    [C] DECL_TAG 'bpf_fastcall' type_id=A component_idx=-1

Generate the following vmlinux.h:

    #ifndef __VMLINUX_H__
    #define __VMLINUX_H__
    ...
    #ifndef __bpf_fastcall
    #if __has_attribute(bpf_fastcall)
    #define __bpf_fastcall __attribute__((bpf_fastcall))
    #else
    #define __bpf_fastcall
    #endif
    #endif
    ...
    __bpf_fastcall extern void *bpf_rdonly_cast(...) ...;

The "bpf_fastcall" / "bpf_kfunc" tags pair would generated by pahole
when constructing vmlinux BTF.

While at it, sort printed kfuncs by name for better vmlinux.h
stability.

Signed-off-by: Eduard Zingerman <[email protected]>
Signed-off-by: Andrii Nakryiko <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: eddyz87

src/btf.c

@@ -1,11 +1,15 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2019 Facebook */
 
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
 #include <errno.h>
 #include <fcntl.h>
 #include <linux/err.h>
 #include <stdbool.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <linux/btf.h>
@@ -21,6 +25,7 @@
 #include "main.h"
 
 #define KFUNC_DECL_TAG		"bpf_kfunc"
+#define FASTCALL_DECL_TAG	"bpf_fastcall"
 
 static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_UNKN]		= "UNKNOWN",
@@ -464,47 +469,113 @@ static int dump_btf_raw(const struct btf *btf,
 	return 0;
 }
 
+struct ptr_array {
+	__u32 cnt;
+	__u32 cap;
+	const void **elems;
+};
+
+static int ptr_array_push(const void *ptr, struct ptr_array *arr)
+{
+	__u32 new_cap;
+	void *tmp;
+
+	if (arr->cnt == arr->cap) {
+		new_cap = (arr->cap ?: 16) * 2;
+		tmp = realloc(arr->elems, sizeof(*arr->elems) * new_cap);
+		if (!tmp)
+			return -ENOMEM;
+		arr->elems = tmp;
+		arr->cap = new_cap;
+	}
+	arr->elems[arr->cnt++] = ptr;
+	return 0;
+}
+
+static void ptr_array_free(struct ptr_array *arr)
+{
+	free(arr->elems);
+}
+
+static int cmp_kfuncs(const void *pa, const void *pb, void *ctx)
+{
+	struct btf *btf = ctx;
+	const struct btf_type *a = *(void **)pa;
+	const struct btf_type *b = *(void **)pb;
+
+	return strcmp(btf__str_by_offset(btf, a->name_off),
+		      btf__str_by_offset(btf, b->name_off));
+}
+
 static int dump_btf_kfuncs(struct btf_dump *d, const struct btf *btf)
 {
 	LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts);
-	int cnt = btf__type_cnt(btf);
-	int i;
+	__u32 cnt = btf__type_cnt(btf), i, j;
+	struct ptr_array fastcalls = {};
+	struct ptr_array kfuncs = {};
+	int err = 0;
 
 	printf("\n/* BPF kfuncs */\n");
 	printf("#ifndef BPF_NO_KFUNC_PROTOTYPES\n");
 
 	for (i = 1; i < cnt; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
+		const struct btf_type *ft;
 		const char *name;
-		int err;
 
 		if (!btf_is_decl_tag(t))
 			continue;
 
 		if (btf_decl_tag(t)->component_idx != -1)
 			continue;
 
-		name = btf__name_by_offset(btf, t->name_off);
-		if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG)))
+		ft = btf__type_by_id(btf, t->type);
+		if (!btf_is_func(ft))
 			continue;
 
-		t = btf__type_by_id(btf, t->type);
-		if (!btf_is_func(t))
-			continue;
+		name = btf__name_by_offset(btf, t->name_off);
+		if (strncmp(name, KFUNC_DECL_TAG, sizeof(KFUNC_DECL_TAG)) == 0) {
+			err = ptr_array_push(ft, &kfuncs);
+			if (err)
+				goto out;
+		}
+
+		if (strncmp(name, FASTCALL_DECL_TAG, sizeof(FASTCALL_DECL_TAG)) == 0) {
+			err = ptr_array_push(ft, &fastcalls);
+			if (err)
+				goto out;
+		}
+	}
+
+	/* Sort kfuncs by name for improved vmlinux.h stability  */
+	qsort_r(kfuncs.elems, kfuncs.cnt, sizeof(*kfuncs.elems), cmp_kfuncs, (void *)btf);
+	for (i = 0; i < kfuncs.cnt; i++) {
+		const struct btf_type *t = kfuncs.elems[i];
 
 		printf("extern ");
 
+		/* Assume small amount of fastcall kfuncs */
+		for (j = 0; j < fastcalls.cnt; j++) {
+			if (fastcalls.elems[j] == t) {
+				printf("__bpf_fastcall ");
+				break;
+			}
+		}
+
 		opts.field_name = btf__name_by_offset(btf, t->name_off);
 		err = btf_dump__emit_type_decl(d, t->type, &opts);
 		if (err)
-			return err;
+			goto out;
 
 		printf(" __weak __ksym;\n");
 	}
 
 	printf("#endif\n\n");
 
-	return 0;
+out:
+	ptr_array_free(&fastcalls);
+	ptr_array_free(&kfuncs);
+	return err;
 }
 
 static void __printf(2, 0) btf_dump_printf(void *ctx,
@@ -718,6 +789,13 @@ static int dump_btf_c(const struct btf *btf,
 	printf("#ifndef __weak\n");
 	printf("#define __weak __attribute__((weak))\n");
 	printf("#endif\n\n");
+	printf("#ifndef __bpf_fastcall\n");
+	printf("#if __has_attribute(bpf_fastcall)\n");
+	printf("#define __bpf_fastcall __attribute__((bpf_fastcall))\n");
+	printf("#else\n");
+	printf("#define __bpf_fastcall\n");
+	printf("#endif\n");
+	printf("#endif\n\n");
 
 	if (root_type_cnt) {
 		for (i = 0; i < root_type_cnt; i++) {