Merge branch 'link_query-bpf_iter'

Yonghong Song says:

====================
"link" has been an important concept for bpf ecosystem to connect
bpf program with other properties. Currently, the information related
information can be queried from userspace through bpf command
BPF_LINK_GET_NEXT_ID, BPF_LINK_GET_FD_BY_ID and BPF_OBJ_GET_INFO_BY_FD.
The information is also available by "cating" /proc/<pid>/fdinfo/<link_fd>.
Raw_tracepoint, tracing, cgroup, netns and xdp links are already
supported in the kernel and bpftool.

This patch added support for bpf iterator. Patch #1 added generic support
for link querying interface. Patch #2 implemented callback functions
for map element bpf iterators. Patch #3 added bpftool support.

Changelogs:
  v3 -> v4:
    . return target specific link_info even if target_name buffer
      is empty. (Andrii)
  v2 -> v3:
    . remove extra '\t' when fdinfo prints map_id to make parsing
      consistent. (Andrii)
  v1 -> v2:
    . fix checkpatch.pl warnings. (Jakub)
====================

Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -1218,12 +1218,18 @@ typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
 					union bpf_iter_link_info *linfo,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
+typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
+					struct seq_file *seq);
+typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
+					 struct bpf_link_info *info);
 
 #define BPF_ITER_CTX_ARG_MAX 2
 struct bpf_iter_reg {
 	const char *target;
 	bpf_iter_attach_target_t attach_target;
 	bpf_iter_detach_target_t detach_target;
+	bpf_iter_show_fdinfo_t show_fdinfo;
+	bpf_iter_fill_link_info_t fill_link_info;
 	u32 ctx_arg_info_size;
 	struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
 	const struct bpf_iter_seq_info *seq_info;
@@ -1250,6 +1256,10 @@ int bpf_iter_new_fd(struct bpf_link *link);
 bool bpf_link_is_iter(struct bpf_link *link);
 struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
 int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
+void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
+			      struct seq_file *seq);
+int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
+				struct bpf_link_info *info);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);

include/uapi/linux/bpf.h

@@ -4071,6 +4071,13 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct {
+			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
+			__u32 target_name_len;	   /* in/out: target_name buffer len */
+			union {
+				__u32 map_id;
+			} map;
+		} iter;
 		struct  {
 			__u32 netns_ino;
 			__u32 attach_type;

kernel/bpf/bpf_iter.c

@@ -377,10 +377,68 @@ out_unlock:
 	return ret;
 }
 
+static void bpf_iter_link_show_fdinfo(const struct bpf_link *link,
+				      struct seq_file *seq)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	bpf_iter_show_fdinfo_t show_fdinfo;
+
+	seq_printf(seq,
+		   "target_name:\t%s\n",
+		   iter_link->tinfo->reg_info->target);
+
+	show_fdinfo = iter_link->tinfo->reg_info->show_fdinfo;
+	if (show_fdinfo)
+		show_fdinfo(&iter_link->aux, seq);
+}
+
+static int bpf_iter_link_fill_link_info(const struct bpf_link *link,
+					struct bpf_link_info *info)
+{
+	struct bpf_iter_link *iter_link =
+		container_of(link, struct bpf_iter_link, link);
+	char __user *ubuf = u64_to_user_ptr(info->iter.target_name);
+	bpf_iter_fill_link_info_t fill_link_info;
+	u32 ulen = info->iter.target_name_len;
+	const char *target_name;
+	u32 target_len;
+
+	if (!ulen ^ !ubuf)
+		return -EINVAL;
+
+	target_name = iter_link->tinfo->reg_info->target;
+	target_len =  strlen(target_name);
+	info->iter.target_name_len = target_len + 1;
+
+	if (ubuf) {
+		if (ulen >= target_len + 1) {
+			if (copy_to_user(ubuf, target_name, target_len + 1))
+				return -EFAULT;
+		} else {
+			char zero = '\0';
+
+			if (copy_to_user(ubuf, target_name, ulen - 1))
+				return -EFAULT;
+			if (put_user(zero, ubuf + ulen - 1))
+				return -EFAULT;
+			return -ENOSPC;
+		}
+	}
+
+	fill_link_info = iter_link->tinfo->reg_info->fill_link_info;
+	if (fill_link_info)
+		return fill_link_info(&iter_link->aux, info);
+
+	return 0;
+}
+
 static const struct bpf_link_ops bpf_iter_link_lops = {
 	.release = bpf_iter_link_release,
 	.dealloc = bpf_iter_link_dealloc,
 	.update_prog = bpf_iter_link_replace,
+	.show_fdinfo = bpf_iter_link_show_fdinfo,
+	.fill_link_info = bpf_iter_link_fill_link_info,
 };
 
 bool bpf_link_is_iter(struct bpf_link *link)

kernel/bpf/map_iter.c

@@ -149,6 +149,19 @@ static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux)
 	bpf_map_put_with_uref(aux->map);
 }
 
+void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
+			      struct seq_file *seq)
+{
+	seq_printf(seq, "map_id:\t%u\n", aux->map->id);
+}
+
+int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
+				struct bpf_link_info *info)
+{
+	info->iter.map.map_id = aux->map->id;
+	return 0;
+}
+
 DEFINE_BPF_ITER_FUNC(bpf_map_elem, struct bpf_iter_meta *meta,
 		     struct bpf_map *map, void *key, void *value)
 
@@ -156,6 +169,8 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = {
 	.target			= "bpf_map_elem",
 	.attach_target		= bpf_iter_attach_map,
 	.detach_target		= bpf_iter_detach_map,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_map_elem, key),

net/core/bpf_sk_storage.c

@@ -1437,6 +1437,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
 	.target			= "bpf_sk_storage_map",
 	.attach_target		= bpf_iter_attach_map,
 	.detach_target		= bpf_iter_detach_map,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),

tools/bpf/bpftool/link.c

@@ -77,6 +77,22 @@ static void show_link_attach_type_json(__u32 attach_type, json_writer_t *wtr)
 		jsonw_uint_field(wtr, "attach_type", attach_type);
 }
 
+static bool is_iter_map_target(const char *target_name)
+{
+	return strcmp(target_name, "bpf_map_elem") == 0 ||
+	       strcmp(target_name, "bpf_sk_storage_map") == 0;
+}
+
+static void show_iter_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	const char *target_name = u64_to_ptr(info->iter.target_name);
+
+	jsonw_string_field(wtr, "target_name", target_name);
+
+	if (is_iter_map_target(target_name))
+		jsonw_uint_field(wtr, "map_id", info->iter.map.map_id);
+}
+
 static int get_prog_info(int prog_id, struct bpf_prog_info *info)
 {
 	__u32 len = sizeof(*info);
@@ -128,6 +144,9 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 				   info->cgroup.cgroup_id);
 		show_link_attach_type_json(info->cgroup.attach_type, json_wtr);
 		break;
+	case BPF_LINK_TYPE_ITER:
+		show_iter_json(info, json_wtr);
+		break;
 	case BPF_LINK_TYPE_NETNS:
 		jsonw_uint_field(json_wtr, "netns_ino",
 				 info->netns.netns_ino);
@@ -175,6 +194,16 @@ static void show_link_attach_type_plain(__u32 attach_type)
 		printf("attach_type %u  ", attach_type);
 }
 
+static void show_iter_plain(struct bpf_link_info *info)
+{
+	const char *target_name = u64_to_ptr(info->iter.target_name);
+
+	printf("target_name %s  ", target_name);
+
+	if (is_iter_map_target(target_name))
+		printf("map_id %u  ", info->iter.map.map_id);
+}
+
 static int show_link_close_plain(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -204,6 +233,9 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		printf("\n\tcgroup_id %zu  ", (size_t)info->cgroup.cgroup_id);
 		show_link_attach_type_plain(info->cgroup.attach_type);
 		break;
+	case BPF_LINK_TYPE_ITER:
+		show_iter_plain(info);
+		break;
 	case BPF_LINK_TYPE_NETNS:
 		printf("\n\tnetns_ino %u  ", info->netns.netns_ino);
 		show_link_attach_type_plain(info->netns.attach_type);
@@ -231,7 +263,7 @@ static int do_show_link(int fd)
 {
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
-	char raw_tp_name[256];
+	char buf[256];
 	int err;
 
 	memset(&info, 0, sizeof(info));
@@ -245,8 +277,14 @@ again:
 	}
 	if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT &&
 	    !info.raw_tracepoint.tp_name) {
-		info.raw_tracepoint.tp_name = (unsigned long)&raw_tp_name;
-		info.raw_tracepoint.tp_name_len = sizeof(raw_tp_name);
+		info.raw_tracepoint.tp_name = (unsigned long)&buf;
+		info.raw_tracepoint.tp_name_len = sizeof(buf);
+		goto again;
+	}
+	if (info.type == BPF_LINK_TYPE_ITER &&
+	    !info.iter.target_name) {
+		info.iter.target_name = (unsigned long)&buf;
+		info.iter.target_name_len = sizeof(buf);
 		goto again;
 	}
 

tools/include/uapi/linux/bpf.h

@@ -4071,6 +4071,13 @@ struct bpf_link_info {
 			__u64 cgroup_id;
 			__u32 attach_type;
 		} cgroup;
+		struct {
+			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
+			__u32 target_name_len;	   /* in/out: target_name buffer len */
+			union {
+				__u32 map_id;
+			} map;
+		} iter;
 		struct  {
 			__u32 netns_ino;
 			__u32 attach_type;