Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 79 files changed, 5275 insertions(+), 600 deletions(-).

The main changes are:

1) Basic BTF validation in libbpf, from Andrii Nakryiko.

2) bpf_assert(), bpf_throw(), exceptions in bpf progs, from Kumar Kartikeya Dwivedi.

3) next_thread cleanups, from Oleg Nesterov.

4) Add mcpu=v4 support to arm32, from Puranjay Mohan.

5) Add support for __percpu pointers in bpf progs, from Yonghong Song.

6) Fix bpf tailcall interaction with bpf trampoline, from Leon Hwang.

7) Raise irq_work in bpf_mem_alloc while irqs are disabled to improve refill probabablity, from Hou Tao.

Please consider pulling these changes from:

  git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git

Thanks a lot!

Also thanks to reporters, reviewers and testers of commits in this pull-request:

Alan Maguire, Andrey Konovalov, Dave Marchevsky, "Eric W. Biederman",
Jiri Olsa, Maciej Fijalkowski, Quentin Monnet, Russell King (Oracle),
Song Liu, Stanislav Fomichev, Yonghong Song
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 303 insertions, 24 deletions

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index bbab9ad9dc5a..77ceea575dc7 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -181,6 +181,7 @@ enum libbpf_tristate {
 #define __ksym __attribute__((section(".ksyms")))
 #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted")))
 #define __kptr __attribute__((btf_type_tag("kptr")))
+#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr")))
 
 #define bpf_ksym_exists(sym) ({									\
 	_Static_assert(!__builtin_constant_p(!!sym), #sym " should be marked as __weak");	\
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 8484b563b53d..ee95fd379d4d 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -448,6 +448,165 @@ static int btf_parse_type_sec(struct btf *btf)
 	return 0;
 }
 
+static int btf_validate_str(const struct btf *btf, __u32 str_off, const char *what, __u32 type_id)
+{
+	const char *s;
+
+	s = btf__str_by_offset(btf, str_off);
+	if (!s) {
+		pr_warn("btf: type [%u]: invalid %s (string offset %u)\n", type_id, what, str_off);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_validate_id(const struct btf *btf, __u32 id, __u32 ctx_id)
+{
+	const struct btf_type *t;
+
+	t = btf__type_by_id(btf, id);
+	if (!t) {
+		pr_warn("btf: type [%u]: invalid referenced type ID %u\n", ctx_id, id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_validate_type(const struct btf *btf, const struct btf_type *t, __u32 id)
+{
+	__u32 kind = btf_kind(t);
+	int err, i, n;
+
+	err = btf_validate_str(btf, t->name_off, "type name", id);
+	if (err)
+		return err;
+
+	switch (kind) {
+	case BTF_KIND_UNKN:
+	case BTF_KIND_INT:
+	case BTF_KIND_FWD:
+	case BTF_KIND_FLOAT:
+		break;
+	case BTF_KIND_PTR:
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+	case BTF_KIND_VAR:
+	case BTF_KIND_DECL_TAG:
+	case BTF_KIND_TYPE_TAG:
+		err = btf_validate_id(btf, t->type, id);
+		if (err)
+			return err;
+		break;
+	case BTF_KIND_ARRAY: {
+		const struct btf_array *a = btf_array(t);
+
+		err = btf_validate_id(btf, a->type, id);
+		err = err ?: btf_validate_id(btf, a->index_type, id);
+		if (err)
+			return err;
+		break;
+	}
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION: {
+		const struct btf_member *m = btf_members(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "field name", id);
+			err = err ?: btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_ENUM: {
+		const struct btf_enum *m = btf_enum(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "enum name", id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_ENUM64: {
+		const struct btf_enum64 *m = btf_enum64(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "enum name", id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_FUNC: {
+		const struct btf_type *ft;
+
+		err = btf_validate_id(btf, t->type, id);
+		if (err)
+			return err;
+		ft = btf__type_by_id(btf, t->type);
+		if (btf_kind(ft) != BTF_KIND_FUNC_PROTO) {
+			pr_warn("btf: type [%u]: referenced type [%u] is not FUNC_PROTO\n", id, t->type);
+			return -EINVAL;
+		}
+		break;
+	}
+	case BTF_KIND_FUNC_PROTO: {
+		const struct btf_param *m = btf_params(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_str(btf, m->name_off, "param name", id);
+			err = err ?: btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	case BTF_KIND_DATASEC: {
+		const struct btf_var_secinfo *m = btf_var_secinfos(t);
+
+		n = btf_vlen(t);
+		for (i = 0; i < n; i++, m++) {
+			err = btf_validate_id(btf, m->type, id);
+			if (err)
+				return err;
+		}
+		break;
+	}
+	default:
+		pr_warn("btf: type [%u]: unrecognized kind %u\n", id, kind);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Validate basic sanity of BTF. It's intentionally less thorough than
+ * kernel's validation and validates only properties of BTF that libbpf relies
+ * on to be correct (e.g., valid type IDs, valid string offsets, etc)
+ */
+static int btf_sanity_check(const struct btf *btf)
+{
+	const struct btf_type *t;
+	__u32 i, n = btf__type_cnt(btf);
+	int err;
+
+	for (i = 1; i < n; i++) {
+		t = btf_type_by_id(btf, i);
+		err = btf_validate_type(btf, t, i);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
 __u32 btf__type_cnt(const struct btf *btf)
 {
 	return btf->start_id + btf->nr_types;
@@ -902,6 +1061,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	err = btf_parse_str_sec(btf);
 	err = err ?: btf_parse_type_sec(btf);
+	err = err ?: btf_sanity_check(btf);
 	if (err)
 		goto done;
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 96ff1aa4bf6a..3a6108e3238b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -436,9 +436,11 @@ struct bpf_program {
 	int fd;
 	bool autoload;
 	bool autoattach;
+	bool sym_global;
 	bool mark_btf_static;
 	enum bpf_prog_type type;
 	enum bpf_attach_type expected_attach_type;
+	int exception_cb_idx;
 
 	int prog_ifindex;
 	__u32 attach_btf_obj_fd;
@@ -765,6 +767,7 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog,
 
 	prog->type = BPF_PROG_TYPE_UNSPEC;
 	prog->fd = -1;
+	prog->exception_cb_idx = -1;
 
 	/* libbpf's convention for SEC("?abc...") is that it's just like
 	 * SEC("abc...") but the corresponding bpf_program starts out with
@@ -871,14 +874,16 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		if (err)
 			return err;
 
+		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL)
+			prog->sym_global = true;
+
 		/* if function is a global/weak symbol, but has restricted
 		 * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC
 		 * as static to enable more permissive BPF verification mode
 		 * with more outside context available to BPF verifier
 		 */
-		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL
-		    && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
-			|| ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
+		if (prog->sym_global && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+		    || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -3142,6 +3147,86 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		}
 	}
 
+	if (!kernel_supports(obj, FEAT_BTF_DECL_TAG))
+		goto skip_exception_cb;
+	for (i = 0; i < obj->nr_programs; i++) {
+		struct bpf_program *prog = &obj->programs[i];
+		int j, k, n;
+
+		if (prog_is_subprog(obj, prog))
+			continue;
+		n = btf__type_cnt(obj->btf);
+		for (j = 1; j < n; j++) {
+			const char *str = "exception_callback:", *name;
+			size_t len = strlen(str);
+			struct btf_type *t;
+
+			t = btf_type_by_id(obj->btf, j);
+			if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
+				continue;
+
+			name = btf__str_by_offset(obj->btf, t->name_off);
+			if (strncmp(name, str, len))
+				continue;
+
+			t = btf_type_by_id(obj->btf, t->type);
+			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+				pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
+					prog->name);
+				return -EINVAL;
+			}
+			if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)))
+				continue;
+			/* Multiple callbacks are specified for the same prog,
+			 * the verifier will eventually return an error for this
+			 * case, hence simply skip appending a subprog.
+			 */
+			if (prog->exception_cb_idx >= 0) {
+				prog->exception_cb_idx = -1;
+				break;
+			}
+
+			name += len;
+			if (str_is_empty(name)) {
+				pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
+					prog->name);
+				return -EINVAL;
+			}
+
+			for (k = 0; k < obj->nr_programs; k++) {
+				struct bpf_program *subprog = &obj->programs[k];
+
+				if (!prog_is_subprog(obj, subprog))
+					continue;
+				if (strcmp(name, subprog->name))
+					continue;
+				/* Enforce non-hidden, as from verifier point of
+				 * view it expects global functions, whereas the
+				 * mark_btf_static fixes up linkage as static.
+				 */
+				if (!subprog->sym_global || subprog->mark_btf_static) {
+					pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
+						prog->name, subprog->name);
+					return -EINVAL;
+				}
+				/* Let's see if we already saw a static exception callback with the same name */
+				if (prog->exception_cb_idx >= 0) {
+					pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
+					        prog->name, subprog->name);
+					return -EINVAL;
+				}
+				prog->exception_cb_idx = k;
+				break;
+			}
+
+			if (prog->exception_cb_idx >= 0)
+				continue;
+			pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
+			return -ENOENT;
+		}
+	}
+skip_exception_cb:
+
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -6235,13 +6320,45 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 }
 
 static int
+bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog,
+				struct bpf_program *subprog)
+{
+       struct bpf_insn *insns;
+       size_t new_cnt;
+       int err;
+
+       subprog->sub_insn_off = main_prog->insns_cnt;
+
+       new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
+       insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
+       if (!insns) {
+               pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
+               return -ENOMEM;
+       }
+       main_prog->insns = insns;
+       main_prog->insns_cnt = new_cnt;
+
+       memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
+              subprog->insns_cnt * sizeof(*insns));
+
+       pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
+                main_prog->name, subprog->insns_cnt, subprog->name);
+
+       /* The subprog insns are now appended. Append its relos too. */
+       err = append_subprog_relos(main_prog, subprog);
+       if (err)
+               return err;
+       return 0;
+}
+
+static int
 bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		       struct bpf_program *prog)
 {
-	size_t sub_insn_idx, insn_idx, new_cnt;
+	size_t sub_insn_idx, insn_idx;
 	struct bpf_program *subprog;
-	struct bpf_insn *insns, *insn;
 	struct reloc_desc *relo;
+	struct bpf_insn *insn;
 	int err;
 
 	err = reloc_prog_func_and_line_info(obj, main_prog, prog);
@@ -6316,25 +6433,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog,
 		 *   and relocate.
 		 */
 		if (subprog->sub_insn_off == 0) {
-			subprog->sub_insn_off = main_prog->insns_cnt;
-
-			new_cnt = main_prog->insns_cnt + subprog->insns_cnt;
-			insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns));
-			if (!insns) {
-				pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name);
-				return -ENOMEM;
-			}
-			main_prog->insns = insns;
-			main_prog->insns_cnt = new_cnt;
-
-			memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns,
-			       subprog->insns_cnt * sizeof(*insns));
-
-			pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n",
-				 main_prog->name, subprog->insns_cnt, subprog->name);
-
-			/* The subprog insns are now appended. Append its relos too. */
-			err = append_subprog_relos(main_prog, subprog);
+			err = bpf_object__append_subprog_code(obj, main_prog, subprog);
 			if (err)
 				return err;
 			err = bpf_object__reloc_code(obj, main_prog, subprog);
@@ -6568,6 +6667,25 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 				prog->name, err);
 			return err;
 		}
+
+		/* Now, also append exception callback if it has not been done already. */
+		if (prog->exception_cb_idx >= 0) {
+			struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx];
+
+			/* Calling exception callback directly is disallowed, which the
+			 * verifier will reject later. In case it was processed already,
+			 * we can skip this step, otherwise for all other valid cases we
+			 * have to append exception callback now.
+			 */
+			if (subprog->sub_insn_off == 0) {
+				err = bpf_object__append_subprog_code(obj, prog, subprog);
+				if (err)
+					return err;
+				err = bpf_object__reloc_code(obj, prog, subprog);
+				if (err)
+					return err;
+			}
+		}
 	}
 	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {