Allow storage of flexible metadata information for eBPF programs

.travis.yml

@@ -0,0 +1,33 @@
+sudo: required
+language: bash
+dist: bionic
+services:
+    - docker
+
+env:
+    global:
+        - PROJECT_NAME='libbpf'
+        - AUTHOR_EMAIL="$(git log -1 --pretty=\"%aE\")"
+        - REPO_ROOT="$TRAVIS_BUILD_DIR"
+        - CI_ROOT="$REPO_ROOT/travis-ci"
+        - VMTEST_ROOT="$CI_ROOT/vmtest"
+
+addons:
+    apt:
+        packages:
+            - qemu-kvm
+            - zstd
+            - binutils-dev
+            - elfutils
+            - libcap-dev
+            - libelf-dev
+            - libdw-dev
+            - python3-docutils
+
+jobs:
+    include:
+        - stage: Builds & Tests
+          name: Kernel LATEST + selftests
+          language: bash
+          env: KERNEL=LATEST
+          script:  $CI_ROOT/vmtest/run_vmtest.sh || travis_terminate 1

drivers/net/ethernet/netronome/nfp/bpf/offload.c

@@ -111,34 +111,40 @@ static int
 nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 		    struct bpf_prog *prog)
 {
-	int i, cnt, err;
+	int i, cnt, err = 0;
+
+	mutex_lock(&prog->aux->used_maps_mutex);
 
 	/* Quickly count the maps we will have to remember */
 	cnt = 0;
 	for (i = 0; i < prog->aux->used_map_cnt; i++)
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i]))
 			cnt++;
 	if (!cnt)
-		return 0;
+		goto out;
 
 	nfp_prog->map_records = kmalloc_array(cnt,
 					      sizeof(nfp_prog->map_records[0]),
 					      GFP_KERNEL);
-	if (!nfp_prog->map_records)
-		return -ENOMEM;
+	if (!nfp_prog->map_records) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	for (i = 0; i < prog->aux->used_map_cnt; i++)
 		if (bpf_map_offload_neutral(prog->aux->used_maps[i])) {
 			err = nfp_map_ptr_record(bpf, nfp_prog,
 						 prog->aux->used_maps[i]);
 			if (err) {
 				nfp_map_ptrs_forget(bpf, nfp_prog);
-				return err;
+				goto out;
 			}
 		}
 	WARN_ON(cnt != nfp_prog->map_records_cnt);
 
-	return 0;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return err;
 }
 
 static int

include/linux/bpf.h

@@ -751,6 +751,7 @@ struct bpf_prog_aux {
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
 	struct bpf_map **used_maps;
+	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */

include/uapi/linux/bpf.h

@@ -124,6 +124,7 @@ enum bpf_cmd {
 	BPF_ENABLE_STATS,
 	BPF_ITER_CREATE,
 	BPF_LINK_DETACH,
+	BPF_PROG_BIND_MAP,
 };
 
 enum bpf_map_type {
@@ -658,6 +659,12 @@ union bpf_attr {
 		__u32		flags;
 	} iter_create;
 
+	struct { /* struct used by BPF_PROG_BIND_MAP command */
+		__u32		prog_fd;
+		__u32		map_fd;
+		__u32		flags;		/* extra flags */
+	} prog_bind_map;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF

kernel/bpf/core.c

@@ -98,6 +98,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	fp->jit_requested = ebpf_jit_enabled();
 
 	INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode);
+	mutex_init(&fp->aux->used_maps_mutex);
 
 	return fp;
 }
@@ -253,6 +254,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 void __bpf_prog_free(struct bpf_prog *fp)
 {
 	if (fp->aux) {
+		mutex_destroy(&fp->aux->used_maps_mutex);
 		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
@@ -1747,8 +1749,9 @@ bool bpf_prog_array_compatible(struct bpf_array *array,
 static int bpf_check_tail_call(const struct bpf_prog *fp)
 {
 	struct bpf_prog_aux *aux = fp->aux;
-	int i;
+	int i, ret = 0;
 
+	mutex_lock(&aux->used_maps_mutex);
 	for (i = 0; i < aux->used_map_cnt; i++) {
 		struct bpf_map *map = aux->used_maps[i];
 		struct bpf_array *array;
@@ -1757,11 +1760,15 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 			continue;
 
 		array = container_of(map, struct bpf_array, map);
-		if (!bpf_prog_array_compatible(array, fp))
-			return -EINVAL;
+		if (!bpf_prog_array_compatible(array, fp)) {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
-	return 0;
+out:
+	mutex_unlock(&aux->used_maps_mutex);
+	return ret;
 }
 
 static void bpf_prog_select_func(struct bpf_prog *fp)

kernel/bpf/syscall.c

@@ -3162,21 +3162,25 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	const struct bpf_map *map;
 	int i;
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
 		map = prog->aux->used_maps[i];
 		if (map == (void *)addr) {
 			*type = BPF_PSEUDO_MAP_FD;
-			return map;
+			goto out;
 		}
 		if (!map->ops->map_direct_value_meta)
 			continue;
 		if (!map->ops->map_direct_value_meta(map, addr, off)) {
 			*type = BPF_PSEUDO_MAP_VALUE;
-			return map;
+			goto out;
 		}
 	}
+	map = NULL;
 
-	return NULL;
+out:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+	return map;
 }
 
 static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
@@ -3294,6 +3298,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	memcpy(info.tag, prog->tag, sizeof(prog->tag));
 	memcpy(info.name, prog->aux->name, sizeof(prog->aux->name));
 
+	mutex_lock(&prog->aux->used_maps_mutex);
 	ulen = info.nr_map_ids;
 	info.nr_map_ids = prog->aux->used_map_cnt;
 	ulen = min_t(u32, info.nr_map_ids, ulen);
@@ -3303,9 +3308,12 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 
 		for (i = 0; i < ulen; i++)
 			if (put_user(prog->aux->used_maps[i]->id,
-				     &user_map_ids[i]))
+				     &user_map_ids[i])) {
+				mutex_unlock(&prog->aux->used_maps_mutex);
 				return -EFAULT;
+			}
 	}
+	mutex_unlock(&prog->aux->used_maps_mutex);
 
 	err = set_info_rec_size(&info);
 	if (err)
@@ -4153,6 +4161,66 @@ static int bpf_iter_create(union bpf_attr *attr)
 	return err;
 }
 
+#define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags
+
+static int bpf_prog_bind_map(union bpf_attr *attr)
+{
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct bpf_map **used_maps_old, **used_maps_new;
+	int i, ret = 0;
+
+	if (CHECK_ATTR(BPF_PROG_BIND_MAP))
+		return -EINVAL;
+
+	if (attr->prog_bind_map.flags)
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->prog_bind_map.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	map = bpf_map_get(attr->prog_bind_map.map_fd);
+	if (IS_ERR(map)) {
+		ret = PTR_ERR(map);
+		goto out_prog_put;
+	}
+
+	mutex_lock(&prog->aux->used_maps_mutex);
+
+	used_maps_old = prog->aux->used_maps;
+
+	for (i = 0; i < prog->aux->used_map_cnt; i++)
+		if (used_maps_old[i] == map)
+			goto out_unlock;
+
+	used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1,
+				      sizeof(used_maps_new[0]),
+				      GFP_KERNEL);
+	if (!used_maps_new) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(used_maps_new, used_maps_old,
+	       sizeof(used_maps_old[0]) * prog->aux->used_map_cnt);
+	used_maps_new[prog->aux->used_map_cnt] = map;
+
+	prog->aux->used_map_cnt++;
+	prog->aux->used_maps = used_maps_new;
+
+	kfree(used_maps_old);
+
+out_unlock:
+	mutex_unlock(&prog->aux->used_maps_mutex);
+
+	if (ret)
+		bpf_map_put(map);
+out_prog_put:
+	bpf_prog_put(prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr;
@@ -4286,6 +4354,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_LINK_DETACH:
 		err = link_detach(&attr);
 		break;
+	case BPF_PROG_BIND_MAP:
+		err = bpf_prog_bind_map(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;

net/core/dev.c

@@ -5441,15 +5441,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	if (new) {
 		u32 i;
 
+		mutex_lock(&new->aux->used_maps_mutex);
+
 		/* generic XDP does not work with DEVMAPs that can
 		 * have a bpf_prog installed on an entry
 		 */
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]))
-				return -EINVAL;
-			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
+			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
+				mutex_unlock(&new->aux->used_maps_mutex);
 				return -EINVAL;
+			}
 		}
+
+		mutex_unlock(&new->aux->used_maps_mutex);
 	}
 
 	switch (xdp->command) {

tools/bpf/bpftool/json_writer.c

@@ -119,6 +119,12 @@ void jsonw_pretty(json_writer_t *self, bool on)
 	self->pretty = on;
 }
 
+void jsonw_reset(json_writer_t *self)
+{
+	assert(self->depth == 0);
+	self->sep = '\0';
+}
+
 /* Basic blocks */
 static void jsonw_begin(json_writer_t *self, int c)
 {

tools/bpf/bpftool/json_writer.h

@@ -27,6 +27,9 @@ void jsonw_destroy(json_writer_t **self_p);
 /* Cause output to have pretty whitespace */
 void jsonw_pretty(json_writer_t *self, bool on);
 
+/* Reset separator to create new JSON */
+void jsonw_reset(json_writer_t *self);
+
 /* Add property name */
 void jsonw_name(json_writer_t *self, const char *name);