summaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/arraymap.c23
-rw-r--r--kernel/bpf/bpf_iter.c8
-rw-r--r--kernel/bpf/bpf_struct_ops.c26
-rw-r--r--kernel/bpf/btf.c34
-rw-r--r--kernel/bpf/cgroup.c36
-rw-r--r--kernel/bpf/cgroup_iter.c65
-rw-r--r--kernel/bpf/core.c23
-rw-r--r--kernel/bpf/cpumap.c10
-rw-r--r--kernel/bpf/cpumask.c6
-rw-r--r--kernel/bpf/devmap.c10
-rw-r--r--kernel/bpf/helpers.c130
-rw-r--r--kernel/bpf/inode.c5
-rw-r--r--kernel/bpf/map_iter.c6
-rw-r--r--kernel/bpf/memalloc.c33
-rw-r--r--kernel/bpf/offload.c18
-rw-r--r--kernel/bpf/ringbuf.c3
-rw-r--r--kernel/bpf/stackmap.c2
-rw-r--r--kernel/bpf/syscall.c77
-rw-r--r--kernel/bpf/task_iter.c286
-rw-r--r--kernel/bpf/tcx.c4
-rw-r--r--kernel/bpf/verifier.c836
21 files changed, 1356 insertions, 285 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 9bfad7e969..c9843dde69 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -871,7 +871,7 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
return 0;
}
-static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *old_ptr;
@@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
}
if (old_ptr) {
- map->ops->map_fd_put_ptr(map, old_ptr, true);
+ map->ops->map_fd_put_ptr(map, old_ptr, need_defer);
return 0;
} else {
return -ENOENT;
}
}
+static long fd_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+ return __fd_array_map_delete_elem(map, key, true);
+}
+
static void *prog_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
@@ -925,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
}
/* decrement refcnt of all bpf_progs that are stored in this map */
-static void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
for (i = 0; i < array->map.max_entries; i++)
- fd_array_map_delete_elem(map, &i);
+ __fd_array_map_delete_elem(map, &i, need_defer);
}
static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
@@ -1072,7 +1077,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_array_aux,
work)->map;
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, true);
bpf_map_put(map);
}
@@ -1222,7 +1227,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
for (i = 0; i < array->map.max_entries; i++) {
ee = READ_ONCE(array->ptrs[i]);
if (ee && ee->map_file == map_file)
- fd_array_map_delete_elem(map, &i);
+ __fd_array_map_delete_elem(map, &i, true);
}
rcu_read_unlock();
}
@@ -1230,7 +1235,7 @@ static void perf_event_fd_array_release(struct bpf_map *map,
static void perf_event_fd_array_map_free(struct bpf_map *map)
{
if (map->map_flags & BPF_F_PRESERVE_ELEMS)
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
@@ -1266,7 +1271,7 @@ static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_de
static void cgroup_fd_array_free(struct bpf_map *map)
{
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
@@ -1311,7 +1316,7 @@ static void array_of_map_free(struct bpf_map *map)
* is protected by fdget/fdput.
*/
bpf_map_meta_free(map->inner_map_meta);
- bpf_fd_array_map_clear(map);
+ bpf_fd_array_map_clear(map, false);
fd_array_map_free(map);
}
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 96856f130c..0fae791641 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -782,9 +782,7 @@ struct bpf_iter_num_kern {
int end; /* final value, exclusive */
} __aligned(8);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
{
@@ -793,8 +791,6 @@ __bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
BUILD_BUG_ON(sizeof(struct bpf_iter_num_kern) != sizeof(struct bpf_iter_num));
BUILD_BUG_ON(__alignof__(struct bpf_iter_num_kern) != __alignof__(struct bpf_iter_num));
- BTF_TYPE_EMIT(struct btf_iter_num);
-
/* start == end is legit, it's an empty range and we'll just get NULL
* on first (and any subsequent) bpf_iter_num_next() call
*/
@@ -845,4 +841,4 @@ __bpf_kfunc void bpf_iter_num_destroy(struct bpf_iter_num *it)
s->cur = s->end = 0;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index fdc3e8705a..db6176fb64 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -615,7 +615,10 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map)
if (st_map->links)
bpf_struct_ops_map_put_progs(st_map);
bpf_map_area_free(st_map->links);
- bpf_jit_free_exec(st_map->image);
+ if (st_map->image) {
+ bpf_jit_free_exec(st_map->image);
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ }
bpf_map_area_free(st_map->uvalue);
bpf_map_area_free(st_map);
}
@@ -657,6 +660,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
struct bpf_struct_ops_map *st_map;
const struct btf_type *t, *vt;
struct bpf_map *map;
+ int ret;
st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
if (!st_ops)
@@ -681,12 +685,27 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
st_map->st_ops = st_ops;
map = &st_map->map;
+ ret = bpf_jit_charge_modmem(PAGE_SIZE);
+ if (ret) {
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(ret);
+ }
+
+ st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
+ if (!st_map->image) {
+ /* __bpf_struct_ops_map_free() uses st_map->image as flag
+ * for "charged or not". In this case, we need to unchange
+ * here.
+ */
+ bpf_jit_uncharge_modmem(PAGE_SIZE);
+ __bpf_struct_ops_map_free(map);
+ return ERR_PTR(-ENOMEM);
+ }
st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE);
st_map->links =
bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *),
NUMA_NO_NODE);
- st_map->image = bpf_jit_alloc_exec(PAGE_SIZE);
- if (!st_map->uvalue || !st_map->links || !st_map->image) {
+ if (!st_map->uvalue || !st_map->links) {
__bpf_struct_ops_map_free(map);
return ERR_PTR(-ENOMEM);
}
@@ -907,4 +926,3 @@ err_out:
kfree(link);
return err;
}
-
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a31704a6bb..15d71d2986 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3293,6 +3293,8 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
type = BPF_KPTR_UNREF;
else if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off)))
type = BPF_KPTR_REF;
+ else if (!strcmp("percpu_kptr", __btf_name_by_offset(btf, t->name_off)))
+ type = BPF_KPTR_PERCPU;
else
return -EINVAL;
@@ -3308,10 +3310,10 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t,
return BTF_FIELD_FOUND;
}
-static const char *btf_find_decl_tag_value(const struct btf *btf,
- const struct btf_type *pt,
- int comp_idx, const char *tag_key)
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+ int comp_idx, const char *tag_key)
{
+ const char *value = NULL;
int i;
for (i = 1; i < btf_nr_types(btf); i++) {
@@ -3325,9 +3327,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf,
continue;
if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len))
continue;
- return __btf_name_by_offset(btf, t->name_off) + len;
+ /* Prevent duplicate entries for same type */
+ if (value)
+ return ERR_PTR(-EEXIST);
+ value = __btf_name_by_offset(btf, t->name_off) + len;
}
- return NULL;
+ if (!value)
+ return ERR_PTR(-ENOENT);
+ return value;
}
static int
@@ -3345,7 +3352,7 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
if (t->size != sz)
return BTF_FIELD_IGNORE;
value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:");
- if (!value_type)
+ if (IS_ERR(value_type))
return -EINVAL;
node_field_name = strstr(value_type, ":");
if (!node_field_name)
@@ -3457,6 +3464,7 @@ static int btf_find_struct_field(const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, member_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3523,6 +3531,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_find_kptr(btf, var_type, off, sz,
idx < info_cnt ? &info[idx] : &tmp);
if (ret < 0)
@@ -3783,6 +3792,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]);
if (ret < 0)
goto end;
@@ -6949,7 +6959,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
* (either PTR_TO_CTX or SCALAR_VALUE).
*/
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
- struct bpf_reg_state *regs)
+ struct bpf_reg_state *regs, bool is_ex_cb)
{
struct bpf_verifier_log *log = &env->log;
struct bpf_prog *prog = env->prog;
@@ -7006,7 +7016,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
tname, nargs, MAX_BPF_FUNC_REG_ARGS);
return -EINVAL;
}
- /* check that function returns int */
+ /* check that function returns int, exception cb also requires this */
t = btf_type_by_id(btf, t->type);
while (btf_type_is_modifier(t))
t = btf_type_by_id(btf, t->type);
@@ -7055,6 +7065,14 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
i, btf_type_str(t), tname);
return -EINVAL;
}
+ /* We have already ensured that the callback returns an integer, just
+ * like all global subprogs. We need to determine it only has a single
+ * scalar argument.
+ */
+ if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) {
+ bpf_log(log, "exception cb only supports single integer argument\n");
+ return -EINVAL;
+ }
return 0;
}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac37bd53ae..491d20038c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
* @flags: Pointer to u32 which contains higher bits of BPF program
* return value (OR'ed together).
*
- * socket is expected to be of type INET or INET6.
+ * socket is expected to be of type INET, INET6 or UNIX.
*
* This function will return %-EPERM if an attached program is found and
* returned value != 1 during execution. In all other cases, 0 is returned.
@@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
/* Check socket family since not all sockets represent network
* endpoint (e.g. AF_UNIX).
*/
- if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)
+ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 &&
+ sk->sk_family != AF_UNIX)
return 0;
if (!ctx.uaddr) {
@@ -1799,7 +1800,7 @@ static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
}
int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
- int *optname, char __user *optval,
+ int *optname, sockptr_t optval,
int *optlen, char **kernel_optval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1822,7 +1823,8 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
ctx.optlen = *optlen;
- if (copy_from_user(ctx.optval, optval, min(*optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(*optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1889,8 +1891,8 @@ out:
}
int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
- int optname, char __user *optval,
- int __user *optlen, int max_optlen,
+ int optname, sockptr_t optval,
+ sockptr_t optlen, int max_optlen,
int retval)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
@@ -1917,8 +1919,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
* one that kernel returned as well to let
* BPF programs inspect the value.
*/
-
- if (get_user(ctx.optlen, optlen)) {
+ if (copy_from_sockptr(&ctx.optlen, optlen,
+ sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1929,8 +1931,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
orig_optlen = ctx.optlen;
- if (copy_from_user(ctx.optval, optval,
- min(ctx.optlen, max_optlen)) != 0) {
+ if (copy_from_sockptr(ctx.optval, optval,
+ min(ctx.optlen, max_optlen))) {
ret = -EFAULT;
goto out;
}
@@ -1944,7 +1946,8 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
if (ret < 0)
goto out;
- if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+ if (!sockptr_is_null(optval) &&
+ (ctx.optlen > max_optlen || ctx.optlen < 0)) {
if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
ctx.optlen, max_optlen);
@@ -1956,11 +1959,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
}
if (ctx.optlen != 0) {
- if (optval && copy_to_user(optval, ctx.optval, ctx.optlen)) {
+ if (!sockptr_is_null(optval) &&
+ copy_to_sockptr(optval, ctx.optval, ctx.optlen)) {
ret = -EFAULT;
goto out;
}
- if (put_user(ctx.optlen, optlen)) {
+ if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) {
ret = -EFAULT;
goto out;
}
@@ -2533,10 +2537,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_get_retval_proto;
@@ -2548,10 +2555,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
return NULL;
default:
return &bpf_set_retval_proto;
diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c
index 810378f04f..f04a468cf6 100644
--- a/kernel/bpf/cgroup_iter.c
+++ b/kernel/bpf/cgroup_iter.c
@@ -282,7 +282,7 @@ static struct bpf_iter_reg bpf_cgroup_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__cgroup, cgroup),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &cgroup_iter_seq_info,
};
@@ -294,3 +294,66 @@ static int __init bpf_cgroup_iter_init(void)
}
late_initcall(bpf_cgroup_iter_init);
+
+struct bpf_iter_css {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_kern {
+ struct cgroup_subsys_state *start;
+ struct cgroup_subsys_state *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
+ struct cgroup_subsys_state *start, unsigned int flags)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css));
+
+ kit->start = NULL;
+ switch (flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->start = start;
+ kit->pos = NULL;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it)
+{
+ struct bpf_iter_css_kern *kit = (void *)it;
+
+ if (!kit->start)
+ return NULL;
+
+ switch (kit->flags) {
+ case BPF_CGROUP_ITER_DESCENDANTS_PRE:
+ kit->pos = css_next_descendant_pre(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_DESCENDANTS_POST:
+ kit->pos = css_next_descendant_post(kit->pos, kit->start);
+ break;
+ case BPF_CGROUP_ITER_ANCESTORS_UP:
+ kit->pos = kit->pos ? kit->pos->parent : kit->start;
+ }
+
+ return kit->pos;
+}
+
+__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it)
+{
+}
+
+__bpf_kfunc_end_defs();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5d1efe5200..fe254ae035 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -212,7 +212,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
const struct bpf_line_info *linfo;
void **jited_linfo;
- if (!prog->aux->jited_linfo)
+ if (!prog->aux->jited_linfo || prog->aux->func_idx > prog->aux->func_cnt)
/* Userspace did not provide linfo */
return;
@@ -543,7 +543,7 @@ static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
{
int i;
- for (i = 0; i < fp->aux->func_cnt; i++)
+ for (i = 0; i < fp->aux->real_func_cnt; i++)
bpf_prog_kallsyms_del(fp->aux->func[i]);
}
@@ -593,7 +593,7 @@ bpf_prog_ksym_set_name(struct bpf_prog *prog)
sym = bin2hex(sym, prog->tag, sizeof(prog->tag));
/* prog->aux->name will be ignored if full btf name is available */
- if (prog->aux->func_info_cnt) {
+ if (prog->aux->func_info_cnt && prog->aux->func_idx < prog->aux->func_info_cnt) {
type = btf_type_by_id(prog->aux->btf,
prog->aux->func_info[prog->aux->func_idx].type_id);
func_name = btf_name_by_offset(prog->aux->btf, type->name_off);
@@ -741,7 +741,7 @@ bool is_bpf_text_address(unsigned long addr)
return ret;
}
-static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
{
struct bpf_ksym *ksym = bpf_ksym_find(addr);
@@ -1216,7 +1216,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
if (!extra_pass)
addr = NULL;
else if (prog->aux->func &&
- off >= 0 && off < prog->aux->func_cnt)
+ off >= 0 && off < prog->aux->real_func_cnt)
addr = (u8 *)prog->aux->func[off]->bpf_func;
else
return -EINVAL;
@@ -2729,7 +2729,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
- for (i = 0; i < aux->func_cnt; i++) {
+ for (i = 0; i < aux->real_func_cnt; i++) {
/* We can just unlink the subprog poke descriptor table as
* it was originally linked to the main program and is also
* released along with it.
@@ -2737,7 +2737,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
}
- if (aux->func_cnt) {
+ if (aux->real_func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
} else {
@@ -2922,6 +2922,15 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len)
return -ENOTSUPP;
}
+bool __weak bpf_jit_supports_exceptions(void)
+{
+ return false;
+}
+
+void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+}
+
#ifdef CONFIG_BPF_SYSCALL
static int __init bpf_global_ma_init(void)
{
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e42a1bdb7f..8a0bb80fe4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -764,6 +764,16 @@ void __cpu_map_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool cpu_map_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&cpu_map_flush_list)))
+ return false;
+ __cpu_map_flush();
+ return true;
+}
+#endif
+
static int __init cpu_map_init(void)
{
int cpu;
diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c
index 6983af8e09..e01c741e54 100644
--- a/kernel/bpf/cpumask.c
+++ b/kernel/bpf/cpumask.c
@@ -34,9 +34,7 @@ static bool cpu_valid(u32 cpu)
return cpu < nr_cpu_ids;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
/**
* bpf_cpumask_create() - Create a mutable BPF cpumask.
@@ -407,7 +405,7 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
return cpumask_any_and_distribute(src1, src2);
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(cpumask_kfunc_btf_ids)
BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 4d42f6ed6c..a936c704d4 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -418,6 +418,16 @@ void __dev_flush(void)
}
}
+#ifdef CONFIG_DEBUG_NET
+bool dev_check_flush(void)
+{
+ if (list_empty(this_cpu_ptr(&dev_flush_list)))
+ return false;
+ __dev_flush();
+ return true;
+}
+#endif
+
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 607be04db7..ce4729ef1a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -22,6 +22,7 @@
#include <linux/security.h>
#include <linux/btf_ids.h>
#include <linux/bpf_mem_alloc.h>
+#include <linux/kasan.h>
#include "../../lib/kstrtox.h"
@@ -31,12 +32,13 @@
*
* Different map implementations will rely on rcu in map methods
* lookup/update/delete, therefore eBPF programs must run under rcu lock
- * if program is allowed to access maps, so check rcu_read_lock_held in
- * all three functions.
+ * if program is allowed to access maps, so check rcu_read_lock_held() or
+ * rcu_read_lock_trace_held() in all three functions.
*/
BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return (unsigned long) map->ops->map_lookup_elem(map, key);
}
@@ -52,7 +54,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
void *, value, u64, flags)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return map->ops->map_update_elem(map, key, value, flags);
}
@@ -69,7 +72,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return map->ops->map_delete_elem(map, key);
}
@@ -1097,6 +1101,7 @@ struct bpf_hrtimer {
struct bpf_prog *prog;
void __rcu *callback_fn;
void *value;
+ struct rcu_head rcu;
};
/* the actual struct hidden inside uapi struct bpf_timer */
@@ -1278,7 +1283,7 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
if (in_nmi())
return -EOPNOTSUPP;
- if (flags > BPF_F_TIMER_ABS)
+ if (flags & ~(BPF_F_TIMER_ABS | BPF_F_TIMER_CPU_PIN))
return -EINVAL;
__bpf_spin_lock_irqsave(&timer->lock);
t = timer->timer;
@@ -1292,6 +1297,9 @@ BPF_CALL_3(bpf_timer_start, struct bpf_timer_kern *, timer, u64, nsecs, u64, fla
else
mode = HRTIMER_MODE_REL_SOFT;
+ if (flags & BPF_F_TIMER_CPU_PIN)
+ mode |= HRTIMER_MODE_PINNED;
+
hrtimer_start(&t->timer, ns_to_ktime(nsecs), mode);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
@@ -1325,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer)
if (in_nmi())
return -EOPNOTSUPP;
+ rcu_read_lock();
__bpf_spin_lock_irqsave(&timer->lock);
t = timer->timer;
if (!t) {
@@ -1346,6 +1355,7 @@ out:
* if it was running.
*/
ret = ret ?: hrtimer_cancel(&t->timer);
+ rcu_read_unlock();
return ret;
}
@@ -1400,7 +1410,7 @@ out:
*/
if (this_cpu_read(hrtimer_running) != t)
hrtimer_cancel(&t->timer);
- kfree(t);
+ kfree_rcu(t, rcu);
}
BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
@@ -1814,8 +1824,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
}
}
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock)
{
@@ -1847,7 +1855,7 @@ unlock:
* bpf_list_head which needs to be freed.
*/
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
@@ -1886,14 +1894,12 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
migrate_disable();
- __bpf_obj_drop_impl(obj, field->graph_root.value_rec);
+ __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
migrate_enable();
}
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
{
@@ -1909,9 +1915,19 @@ __bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
return p;
}
+__bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign)
+{
+ u64 size = local_type_id__k;
+
+ /* The verifier has ensured that meta__ign must be NULL */
+ return bpf_mem_alloc(&bpf_global_percpu_ma, size);
+}
+
/* Must be called under migrate_disable(), as required by bpf_mem_free */
-void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
+void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu)
{
+ struct bpf_mem_alloc *ma;
+
if (rec && rec->refcount_off >= 0 &&
!refcount_dec_and_test((refcount_t *)(p + rec->refcount_off))) {
/* Object is refcounted and refcount_dec didn't result in 0
@@ -1923,10 +1939,14 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec)
if (rec)
bpf_obj_free_fields(rec, p);
+ if (percpu)
+ ma = &bpf_global_percpu_ma;
+ else
+ ma = &bpf_global_ma;
if (rec && rec->refcount_off >= 0)
- bpf_mem_free_rcu(&bpf_global_ma, p);
+ bpf_mem_free_rcu(ma, p);
else
- bpf_mem_free(&bpf_global_ma, p);
+ bpf_mem_free(ma, p);
}
__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
@@ -1934,7 +1954,13 @@ __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign)
struct btf_struct_meta *meta = meta__ign;
void *p = p__alloc;
- __bpf_obj_drop_impl(p, meta ? meta->record : NULL);
+ __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false);
+}
+
+__bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign)
+{
+ /* The verifier has ensured that meta__ign must be NULL */
+ bpf_mem_free_rcu(&bpf_global_percpu_ma, p__alloc);
}
__bpf_kfunc void *bpf_refcount_acquire_impl(void *p__refcounted_kptr, void *meta__ign)
@@ -1972,7 +1998,7 @@ static int __bpf_list_add(struct bpf_list_node_kern *node,
*/
if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
@@ -2071,7 +2097,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root,
*/
if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) {
/* Only called from BPF prog, no need to migrate_disable */
- __bpf_obj_drop_impl((void *)n - off, rec);
+ __bpf_obj_drop_impl((void *)n - off, rec, false);
return -EINVAL;
}
@@ -2447,15 +2473,60 @@ __bpf_kfunc void bpf_rcu_read_unlock(void)
rcu_read_unlock();
}
-__diag_pop();
+struct bpf_throw_ctx {
+ struct bpf_prog_aux *aux;
+ u64 sp;
+ u64 bp;
+ int cnt;
+};
+
+static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+ struct bpf_throw_ctx *ctx = cookie;
+ struct bpf_prog *prog;
+
+ if (!is_bpf_text_address(ip))
+ return !ctx->cnt;
+ prog = bpf_prog_ksym_find(ip);
+ ctx->cnt++;
+ if (bpf_is_subprog(prog))
+ return true;
+ ctx->aux = prog->aux;
+ ctx->sp = sp;
+ ctx->bp = bp;
+ return false;
+}
+
+__bpf_kfunc void bpf_throw(u64 cookie)
+{
+ struct bpf_throw_ctx ctx = {};
+
+ arch_bpf_stack_walk(bpf_stack_walker, &ctx);
+ WARN_ON_ONCE(!ctx.aux);
+ if (ctx.aux)
+ WARN_ON_ONCE(!ctx.aux->exception_boundary);
+ WARN_ON_ONCE(!ctx.bp);
+ WARN_ON_ONCE(!ctx.cnt);
+ /* Prevent KASAN false positives for CONFIG_KASAN_STACK by unpoisoning
+ * deeper stack depths than ctx.sp as we do not return from bpf_throw,
+ * which skips compiler generated instrumentation to do the same.
+ */
+ kasan_unpoison_task_stack_below((void *)(long)ctx.sp);
+ ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0);
+ WARN(1, "A call to BPF exception callback should never return\n");
+}
+
+__bpf_kfunc_end_defs();
BTF_SET8_START(generic_btf_ids)
#ifdef CONFIG_KEXEC_CORE
BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
#endif
BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_percpu_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_obj_drop_impl, KF_RELEASE)
-BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_percpu_obj_drop_impl, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_refcount_acquire_impl, KF_ACQUIRE | KF_RET_NULL | KF_RCU)
BTF_ID_FLAGS(func, bpf_list_push_front_impl)
BTF_ID_FLAGS(func, bpf_list_push_back_impl)
BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
@@ -2474,6 +2545,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_throw)
BTF_SET8_END(generic_btf_ids)
static const struct btf_kfunc_id_set generic_kfunc_set = {
@@ -2500,6 +2572,20 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW)
BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
+BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_dynptr_adjust)
BTF_ID_FLAGS(func, bpf_dynptr_is_null)
BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 99d0625b6c..1aafb2ff2e 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -118,8 +118,7 @@ static struct inode *bpf_get_inode(struct super_block *sb,
return ERR_PTR(-ENOSPC);
inode->i_ino = get_next_ino();
- inode->i_atime = inode_set_ctime_current(inode);
- inode->i_mtime = inode->i_atime;
+ simple_inode_init_ts(inode);
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
@@ -147,7 +146,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode,
d_instantiate(dentry, inode);
dget(dentry);
- dir->i_mtime = inode_set_ctime_current(dir);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
}
static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir,
diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c
index 6fc9dae9ed..6abd7c5df4 100644
--- a/kernel/bpf/map_iter.c
+++ b/kernel/bpf/map_iter.c
@@ -193,9 +193,7 @@ static int __init bpf_map_iter_init(void)
late_initcall(bpf_map_iter_init);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
{
@@ -213,7 +211,7 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
return ret;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(bpf_map_iter_kfunc_ids)
BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 85f9501ff6..aa0fbf000a 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -340,6 +340,7 @@ static void free_bulk(struct bpf_mem_cache *c)
int cnt;
WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
do {
inc_active(c, &flags);
@@ -365,6 +366,9 @@ static void __free_by_rcu(struct rcu_head *head)
struct bpf_mem_cache *tgt = c->tgt;
struct llist_node *llnode;
+ WARN_ON_ONCE(tgt->unit_size != c->unit_size);
+ WARN_ON_ONCE(tgt->percpu_size != c->percpu_size);
+
llnode = llist_del_all(&c->waiting_for_gp);
if (!llnode)
goto out;
@@ -501,6 +505,9 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
struct obj_cgroup *objcg = NULL;
int cpu, i, unit_size, percpu_size = 0;
+ /* room for llist_node and per-cpu pointer */
+ if (percpu)
+ percpu_size = LLIST_NODE_SZ + sizeof(void *);
ma->percpu = percpu;
if (size) {
@@ -508,10 +515,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
if (!pc)
return -ENOMEM;
- if (percpu)
- /* room for llist_node and per-cpu pointer */
- percpu_size = LLIST_NODE_SZ + sizeof(void *);
- else
+ if (!percpu)
size += LLIST_NODE_SZ; /* room for llist_node */
unit_size = size;
@@ -532,10 +536,6 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
return 0;
}
- /* size == 0 && percpu is an invalid combination */
- if (WARN_ON_ONCE(percpu))
- return -EINVAL;
-
pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
if (!pcc)
return -ENOMEM;
@@ -548,6 +548,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
c = &cc->cache[i];
c->unit_size = sizes[i];
c->objcg = objcg;
+ c->percpu_size = percpu_size;
c->tgt = c;
init_refill_work(c);
@@ -742,12 +743,17 @@ static void notrace *unit_alloc(struct bpf_mem_cache *c)
}
}
local_dec(&c->active);
- local_irq_restore(flags);
WARN_ON(cnt < 0);
if (cnt < c->low_watermark)
irq_work_raise(c);
+ /* Enable IRQ after the enqueue of irq work completes, so irq work
+ * will run after IRQ is enabled and free_llist may be refilled by
+ * irq work before other task preempts current task.
+ */
+ local_irq_restore(flags);
+
return llnode;
}
@@ -783,11 +789,16 @@ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
llist_add(llnode, &c->free_llist_extra);
}
local_dec(&c->active);
- local_irq_restore(flags);
if (cnt > c->high_watermark)
/* free few objects from current cpu into global kmalloc pool */
irq_work_raise(c);
+ /* Enable IRQ after irq_work_raise() completes, otherwise when current
+ * task is preempted by task which does unit_alloc(), unit_alloc() may
+ * return NULL unexpectedly because irq work is already pending but can
+ * not been triggered and free_llist can not be refilled timely.
+ */
+ local_irq_restore(flags);
}
static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr)
@@ -805,10 +816,10 @@ static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr)
llist_add(llnode, &c->free_llist_extra_rcu);
}
local_dec(&c->active);
- local_irq_restore(flags);
if (!atomic_read(&c->call_rcu_in_progress))
irq_work_raise(c);
+ local_irq_restore(flags);
}
/* Called from BPF program or from sys_bpf syscall.
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 87d6693d82..1a4fec330e 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -234,7 +234,14 @@ int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr)
attr->prog_type != BPF_PROG_TYPE_XDP)
return -EINVAL;
- if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY)
+ if (attr->prog_flags & ~(BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_XDP_HAS_FRAGS))
+ return -EINVAL;
+
+ /* Frags are allowed only if program is dev-bound-only, but not
+ * if it is requesting bpf offload.
+ */
+ if (attr->prog_flags & BPF_F_XDP_HAS_FRAGS &&
+ !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY))
return -EINVAL;
if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS &&
@@ -847,10 +854,11 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
if (!ops)
goto out;
- if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP))
- p = ops->xmo_rx_timestamp;
- else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
- p = ops->xmo_rx_hash;
+#define XDP_METADATA_KFUNC(name, _, __, xmo) \
+ if (func_id == bpf_xdp_metadata_kfunc_id(name)) p = ops->xmo;
+ XDP_METADATA_KFUNC_xxx
+#undef XDP_METADATA_KFUNC
+
out:
up_read(&bpf_devs_lock);
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index f045fde632..0ee653a936 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -770,8 +770,7 @@ schedule_work_return:
/* Prevent the clearing of the busy-bit from being reordered before the
* storing of any rb consumer or producer positions.
*/
- smp_mb__before_atomic();
- atomic_set(&rb->busy, 0);
+ atomic_set_release(&rb->busy, 0);
if (flags & BPF_RB_FORCE_WAKEUP)
irq_work_queue(&rb->work);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 36775c4bc3..dff7ba5397 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -28,7 +28,7 @@ struct bpf_stack_map {
void *elems;
struct pcpu_freelist freelist;
u32 n_buckets;
- struct stack_map_bucket *buckets[];
+ struct stack_map_bucket *buckets[] __counted_by(n_buckets);
};
static inline bool stack_map_use_build_id(struct bpf_map *map)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f61c53237c..349d735b4e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -35,8 +35,9 @@
#include <linux/rcupdate_trace.h>
#include <linux/memcontrol.h>
#include <linux/trace_events.h>
-#include <net/netfilter/nf_bpf_link.h>
+#include <net/netfilter/nf_bpf_link.h>
+#include <net/netkit.h>
#include <net/tcx.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -514,6 +515,7 @@ void btf_record_free(struct btf_record *rec)
switch (rec->fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (rec->fields[i].kptr.module)
module_put(rec->fields[i].kptr.module);
btf_put(rec->fields[i].kptr.btf);
@@ -560,6 +562,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
switch (fields[i].type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
btf_get(fields[i].kptr.btf);
if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) {
ret = -ENXIO;
@@ -624,8 +627,6 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj)
bpf_timer_cancel_and_free(obj + rec->timer_off);
}
-extern void __bpf_obj_drop_impl(void *p, const struct btf_record *rec);
-
void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
{
const struct btf_field *fields;
@@ -650,6 +651,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
WRITE_ONCE(*(u64 *)field_ptr, 0);
break;
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0);
if (!xchgd_field)
break;
@@ -659,8 +661,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
field->kptr.btf_id);
migrate_disable();
__bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ?
- pointee_struct_meta->record :
- NULL);
+ pointee_struct_meta->record : NULL,
+ fields[i].type == BPF_KPTR_PERCPU);
migrate_enable();
} else {
field->kptr.dtor(xchgd_field);
@@ -1071,6 +1073,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
case BPF_REFCOUNT:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
@@ -1699,6 +1702,9 @@ int generic_map_delete_batch(struct bpf_map *map,
if (!max_count)
return 0;
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
@@ -1756,6 +1762,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
if (!max_count)
return 0;
+ if (put_user(0, &uattr->batch.count))
+ return -EFAULT;
+
key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN);
if (!key)
return -ENOMEM;
@@ -2468,14 +2477,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return 0;
default:
return -EINVAL;
@@ -2771,7 +2785,7 @@ free_used_maps:
* period before we can tear down JIT memory since symbols
* are already exposed under kallsyms.
*/
- __bpf_prog_put_noref(prog, prog->aux->func_cnt);
+ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt);
return err;
free_prog_sec:
free_uid(prog->aux->user);
@@ -3405,7 +3419,7 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
static int bpf_perf_link_fill_common(const struct perf_event *event,
char __user *uname, u32 ulen,
u64 *probe_offset, u64 *probe_addr,
- u32 *fd_type)
+ u32 *fd_type, unsigned long *missed)
{
const char *buf;
u32 prog_id;
@@ -3416,7 +3430,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
return -EINVAL;
err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf,
- probe_offset, probe_addr);
+ probe_offset, probe_addr, missed);
if (err)
return err;
if (!uname)
@@ -3439,6 +3453,7 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
struct bpf_link_info *info)
{
+ unsigned long missed;
char __user *uname;
u64 addr, offset;
u32 ulen, type;
@@ -3447,7 +3462,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
ulen = info->perf_event.kprobe.name_len;
err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
- &type);
+ &type, &missed);
if (err)
return err;
if (type == BPF_FD_TYPE_KRETPROBE)
@@ -3456,6 +3471,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
info->perf_event.type = BPF_PERF_EVENT_KPROBE;
info->perf_event.kprobe.offset = offset;
+ info->perf_event.kprobe.missed = missed;
if (!kallsyms_show_value(current_cred()))
addr = 0;
info->perf_event.kprobe.addr = addr;
@@ -3475,7 +3491,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
ulen = info->perf_event.uprobe.name_len;
err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
- &type);
+ &type, NULL);
if (err)
return err;
@@ -3511,7 +3527,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
ulen = info->perf_event.tracepoint.name_len;
info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
- return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL);
+ return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL);
}
static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
@@ -3707,14 +3723,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
case BPF_CGROUP_INET6_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
return BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
case BPF_CGROUP_SOCK_OPS:
return BPF_PROG_TYPE_SOCK_OPS;
@@ -3751,6 +3772,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
return BPF_PROG_TYPE_LSM;
case BPF_TCX_INGRESS:
case BPF_TCX_EGRESS:
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
return BPF_PROG_TYPE_SCHED_CLS;
default:
return BPF_PROG_TYPE_UNSPEC;
@@ -3802,7 +3825,9 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
return 0;
case BPF_PROG_TYPE_SCHED_CLS:
if (attach_type != BPF_TCX_INGRESS &&
- attach_type != BPF_TCX_EGRESS)
+ attach_type != BPF_TCX_EGRESS &&
+ attach_type != BPF_NETKIT_PRIMARY &&
+ attach_type != BPF_NETKIT_PEER)
return -EINVAL;
return 0;
default:
@@ -3885,7 +3910,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ret = cgroup_bpf_prog_attach(attr, ptype, prog);
break;
case BPF_PROG_TYPE_SCHED_CLS:
- ret = tcx_prog_attach(attr, prog);
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_attach(attr, prog);
+ else
+ ret = netkit_prog_attach(attr, prog);
break;
default:
ret = -EINVAL;
@@ -3946,7 +3975,11 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ret = cgroup_bpf_prog_detach(attr, ptype);
break;
case BPF_PROG_TYPE_SCHED_CLS:
- ret = tcx_prog_detach(attr, prog);
+ if (attr->attach_type == BPF_TCX_INGRESS ||
+ attr->attach_type == BPF_TCX_EGRESS)
+ ret = tcx_prog_detach(attr, prog);
+ else
+ ret = netkit_prog_detach(attr, prog);
break;
default:
ret = -EINVAL;
@@ -3980,14 +4013,19 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_INET6_POST_BIND:
case BPF_CGROUP_INET4_CONNECT:
case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
case BPF_CGROUP_INET4_GETPEERNAME:
case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
case BPF_CGROUP_INET4_GETSOCKNAME:
case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
case BPF_CGROUP_UDP4_SENDMSG:
case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
case BPF_CGROUP_UDP4_RECVMSG:
case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
case BPF_CGROUP_SYSCTL:
@@ -4008,6 +4046,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_TCX_INGRESS:
case BPF_TCX_EGRESS:
return tcx_prog_query(attr, uattr);
+ case BPF_NETKIT_PRIMARY:
+ case BPF_NETKIT_PEER:
+ return netkit_prog_query(attr, uattr);
default:
return -EINVAL;
}
@@ -4853,7 +4894,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr,
err = bpf_get_perf_event_info(event, &prog_id, &fd_type,
&buf, &probe_offset,
- &probe_addr);
+ &probe_addr, NULL);
if (!err)
err = bpf_task_fd_query_copy(attr, uattr, prog_id,
fd_type, buf,
@@ -4989,7 +5030,11 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
ret = bpf_xdp_link_attach(attr, prog);
break;
case BPF_PROG_TYPE_SCHED_CLS:
- ret = tcx_link_attach(attr, prog);
+ if (attr->link_create.attach_type == BPF_TCX_INGRESS ||
+ attr->link_create.attach_type == BPF_TCX_EGRESS)
+ ret = tcx_link_attach(attr, prog);
+ else
+ ret = netkit_link_attach(attr, prog);
break;
case BPF_PROG_TYPE_NETFILTER:
ret = bpf_nf_link_attach(attr, prog);
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index c4ab9d6cdb..26082b9789 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -7,7 +7,9 @@
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
+#include <linux/bpf_mem_alloc.h>
#include <linux/btf_ids.h>
+#include <linux/mm_types.h>
#include "mmap_unlock_work.h"
static const char * const iter_task_type_names[] = {
@@ -35,16 +37,13 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
u32 *tid,
bool skip_if_dup_files)
{
- struct task_struct *task, *next_task;
+ struct task_struct *task;
struct pid *pid;
- u32 saved_tid;
+ u32 next_tid;
if (!*tid) {
/* The first time, the iterator calls this function. */
pid = find_pid_ns(common->pid, common->ns);
- if (!pid)
- return NULL;
-
task = get_pid_task(pid, PIDTYPE_TGID);
if (!task)
return NULL;
@@ -66,44 +65,27 @@ static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_comm
return task;
}
- pid = find_pid_ns(common->pid_visiting, common->ns);
- if (!pid)
- return NULL;
-
- task = get_pid_task(pid, PIDTYPE_PID);
+ task = find_task_by_pid_ns(common->pid_visiting, common->ns);
if (!task)
return NULL;
retry:
- if (!pid_alive(task)) {
- put_task_struct(task);
- return NULL;
- }
+ task = next_thread(task);
- next_task = next_thread(task);
- put_task_struct(task);
- if (!next_task)
- return NULL;
-
- saved_tid = *tid;
- *tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns);
- if (!*tid || *tid == common->pid) {
+ next_tid = __task_pid_nr_ns(task, PIDTYPE_PID, common->ns);
+ if (!next_tid || next_tid == common->pid) {
/* Run out of tasks of a process. The tasks of a
* thread_group are linked as circular linked list.
*/
- *tid = saved_tid;
return NULL;
}
- get_task_struct(next_task);
- common->pid_visiting = *tid;
-
- if (skip_if_dup_files && task->files == task->group_leader->files) {
- task = next_task;
+ if (skip_if_dup_files && task->files == task->group_leader->files)
goto retry;
- }
- return next_task;
+ *tid = common->pid_visiting = next_tid;
+ get_task_struct(task);
+ return task;
}
static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
@@ -308,11 +290,9 @@ again:
rcu_read_lock();
for (;; curr_fd++) {
struct file *f;
- f = task_lookup_next_fd_rcu(curr_task, &curr_fd);
+ f = task_lookup_next_fdget_rcu(curr_task, &curr_fd);
if (!f)
break;
- if (!get_file_rcu(f))
- continue;
/* set info->fd */
info->fd = curr_fd;
@@ -724,7 +704,7 @@ static struct bpf_iter_reg task_reg_info = {
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &task_seq_info,
.fill_link_info = bpf_iter_fill_link_info,
@@ -823,6 +803,244 @@ const struct bpf_func_proto bpf_find_vma_proto = {
.arg5_type = ARG_ANYTHING,
};
+struct bpf_iter_task_vma_kern_data {
+ struct task_struct *task;
+ struct mm_struct *mm;
+ struct mmap_unlock_irq_work *work;
+ struct vma_iterator vmi;
+};
+
+struct bpf_iter_task_vma {
+ /* opaque iterator state; having __u64 here allows to preserve correct
+ * alignment requirements in vmlinux.h, generated from BTF
+ */
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+/* Non-opaque version of bpf_iter_task_vma */
+struct bpf_iter_task_vma_kern {
+ struct bpf_iter_task_vma_kern_data *data;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
+ struct task_struct *task, u64 addr)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+ bool irq_work_busy = false;
+ int err;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_vma_kern) != sizeof(struct bpf_iter_task_vma));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_vma_kern) != __alignof__(struct bpf_iter_task_vma));
+
+ /* is_iter_reg_valid_uninit guarantees that kit hasn't been initialized
+ * before, so non-NULL kit->data doesn't point to previously
+ * bpf_mem_alloc'd bpf_iter_task_vma_kern_data
+ */
+ kit->data = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_iter_task_vma_kern_data));
+ if (!kit->data)
+ return -ENOMEM;
+
+ kit->data->task = get_task_struct(task);
+ kit->data->mm = task->mm;
+ if (!kit->data->mm) {
+ err = -ENOENT;
+ goto err_cleanup_iter;
+ }
+
+ /* kit->data->work == NULL is valid after bpf_mmap_unlock_get_irq_work */
+ irq_work_busy = bpf_mmap_unlock_get_irq_work(&kit->data->work);
+ if (irq_work_busy || !mmap_read_trylock(kit->data->mm)) {
+ err = -EBUSY;
+ goto err_cleanup_iter;
+ }
+
+ vma_iter_init(&kit->data->vmi, kit->data->mm, addr);
+ return 0;
+
+err_cleanup_iter:
+ if (kit->data->task)
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ /* NULL kit->data signals failed bpf_iter_task_vma initialization */
+ kit->data = NULL;
+ return err;
+}
+
+__bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (!kit->data) /* bpf_iter_task_vma_new failed */
+ return NULL;
+ return vma_next(&kit->data->vmi);
+}
+
+__bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
+{
+ struct bpf_iter_task_vma_kern *kit = (void *)it;
+
+ if (kit->data) {
+ bpf_mmap_unlock_mm(kit->data->work, kit->data->mm);
+ put_task_struct(kit->data->task);
+ bpf_mem_free(&bpf_global_ma, kit->data);
+ }
+}
+
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
+
+struct bpf_iter_css_task {
+ __u64 __opaque[1];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_css_task_kern {
+ struct css_task_iter *css_it;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+ struct cgroup_subsys_state *css, unsigned int flags)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) !=
+ __alignof__(struct bpf_iter_css_task));
+ kit->css_it = NULL;
+ switch (flags) {
+ case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED:
+ case CSS_TASK_ITER_PROCS:
+ case 0:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter));
+ if (!kit->css_it)
+ return -ENOMEM;
+ css_task_iter_start(css, flags, kit->css_it);
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return NULL;
+ return css_task_iter_next(kit->css_it);
+}
+
+__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it)
+{
+ struct bpf_iter_css_task_kern *kit = (void *)it;
+
+ if (!kit->css_it)
+ return;
+ css_task_iter_end(kit->css_it);
+ bpf_mem_free(&bpf_global_ma, kit->css_it);
+}
+
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
+
+struct bpf_iter_task {
+ __u64 __opaque[3];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_task_kern {
+ struct task_struct *task;
+ struct task_struct *pos;
+ unsigned int flags;
+} __attribute__((aligned(8)));
+
+enum {
+ /* all process in the system */
+ BPF_TASK_ITER_ALL_PROCS,
+ /* all threads in the system */
+ BPF_TASK_ITER_ALL_THREADS,
+ /* all threads of a specific process */
+ BPF_TASK_ITER_PROC_THREADS
+};
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
+ struct task_struct *task__nullable, unsigned int flags)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+
+ BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task));
+ BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) !=
+ __alignof__(struct bpf_iter_task));
+
+ kit->task = kit->pos = NULL;
+ switch (flags) {
+ case BPF_TASK_ITER_ALL_THREADS:
+ case BPF_TASK_ITER_ALL_PROCS:
+ break;
+ case BPF_TASK_ITER_PROC_THREADS:
+ if (!task__nullable)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (flags == BPF_TASK_ITER_PROC_THREADS)
+ kit->task = task__nullable;
+ else
+ kit->task = &init_task;
+ kit->pos = kit->task;
+ kit->flags = flags;
+ return 0;
+}
+
+__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it)
+{
+ struct bpf_iter_task_kern *kit = (void *)it;
+ struct task_struct *pos;
+ unsigned int flags;
+
+ flags = kit->flags;
+ pos = kit->pos;
+
+ if (!pos)
+ return pos;
+
+ if (flags == BPF_TASK_ITER_ALL_PROCS)
+ goto get_next_task;
+
+ kit->pos = next_thread(kit->pos);
+ if (kit->pos == kit->task) {
+ if (flags == BPF_TASK_ITER_PROC_THREADS) {
+ kit->pos = NULL;
+ return pos;
+ }
+ } else
+ return pos;
+
+get_next_task:
+ kit->pos = next_task(kit->pos);
+ kit->task = kit->pos;
+ if (kit->pos == &init_task)
+ kit->pos = NULL;
+
+ return pos;
+}
+
+__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it)
+{
+}
+
+__bpf_kfunc_end_defs();
+
DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
static void do_mmap_read_unlock(struct irq_work *entry)
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
index 1338a13a8b..2e4885e778 100644
--- a/kernel/bpf/tcx.c
+++ b/kernel/bpf/tcx.c
@@ -250,7 +250,7 @@ static void tcx_link_dealloc(struct bpf_link *link)
static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
{
- const struct tcx_link *tcx = tcx_link_const(link);
+ const struct tcx_link *tcx = tcx_link(link);
u32 ifindex = 0;
rtnl_lock();
@@ -267,7 +267,7 @@ static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq)
static int tcx_link_fill_info(const struct bpf_link *link,
struct bpf_link_info *info)
{
- const struct tcx_link *tcx = tcx_link_const(link);
+ const struct tcx_link *tcx = tcx_link(link);
u32 ifindex = 0;
rtnl_lock();
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a7901ed358..e215413c79 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
#include <linux/poison.h>
#include <linux/module.h>
#include <linux/cpumask.h>
+#include <linux/bpf_mem_alloc.h>
#include <net/xdp.h>
#include "disasm.h"
@@ -41,6 +42,9 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+struct bpf_mem_alloc bpf_global_percpu_ma;
+static bool bpf_global_percpu_ma_set;
+
/* bpf_check() is a static code analyzer that walks eBPF program
* instruction by instruction and updates register/stack state.
* All paths of conditional branches are analyzed until 'bpf_exit' insn.
@@ -304,7 +308,7 @@ struct bpf_kfunc_call_arg_meta {
/* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling,
* generally to pass info about user-defined local kptr types to later
* verification logic
- * bpf_obj_drop
+ * bpf_obj_drop/bpf_percpu_obj_drop
* Record the local kptr type to be drop'd
* bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type)
* Record the local kptr type to be refcount_incr'd and use
@@ -336,6 +340,7 @@ struct bpf_kfunc_call_arg_meta {
struct btf *btf_vmlinux;
static DEFINE_MUTEX(bpf_verifier_lock);
+static DEFINE_MUTEX(bpf_percpu_ma_lock);
static const struct bpf_line_info *
find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
@@ -543,6 +548,7 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
}
static bool is_sync_callback_calling_kfunc(u32 btf_id);
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn);
static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
{
@@ -1183,7 +1189,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg
static void __mark_reg_known_zero(struct bpf_reg_state *reg);
+static bool in_rcu_cs(struct bpf_verifier_env *env);
+
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta);
+
static int mark_stack_slots_iter(struct bpf_verifier_env *env,
+ struct bpf_kfunc_call_arg_meta *meta,
struct bpf_reg_state *reg, int insn_idx,
struct btf *btf, u32 btf_id, int nr_slots)
{
@@ -1204,6 +1215,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env,
__mark_reg_known_zero(st);
st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
+ if (is_kfunc_rcu_protected(meta)) {
+ if (in_rcu_cs(env))
+ st->type |= MEM_RCU;
+ else
+ st->type |= PTR_UNTRUSTED;
+ }
st->live |= REG_LIVE_WRITTEN;
st->ref_obj_id = i == 0 ? id : 0;
st->iter.btf = btf;
@@ -1278,7 +1295,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env,
return true;
}
-static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
struct btf *btf, u32 btf_id, int nr_slots)
{
struct bpf_func_state *state = func(env, reg);
@@ -1286,26 +1303,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_
spi = iter_get_spi(env, reg, nr_slots);
if (spi < 0)
- return false;
+ return -EINVAL;
for (i = 0; i < nr_slots; i++) {
struct bpf_stack_state *slot = &state->stack[spi - i];
struct bpf_reg_state *st = &slot->spilled_ptr;
+ if (st->type & PTR_UNTRUSTED)
+ return -EPROTO;
/* only main (first) slot has ref_obj_id set */
if (i == 0 && !st->ref_obj_id)
- return false;
+ return -EINVAL;
if (i != 0 && st->ref_obj_id)
- return false;
+ return -EINVAL;
if (st->iter.btf != btf || st->iter.btf_id != btf_id)
- return false;
+ return -EINVAL;
for (j = 0; j < BPF_REG_SIZE; j++)
if (slot->slot_type[j] != STACK_ITER)
- return false;
+ return -EINVAL;
}
- return true;
+ return 0;
}
/* Check if given stack slot is "special":
@@ -1352,6 +1371,50 @@ static void scrub_spilled_slot(u8 *stype)
*stype = STACK_MISC;
}
+static void print_scalar_ranges(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ const char **sep)
+{
+ struct {
+ const char *name;
+ u64 val;
+ bool omit;
+ } minmaxs[] = {
+ {"smin", reg->smin_value, reg->smin_value == S64_MIN},
+ {"smax", reg->smax_value, reg->smax_value == S64_MAX},
+ {"umin", reg->umin_value, reg->umin_value == 0},
+ {"umax", reg->umax_value, reg->umax_value == U64_MAX},
+ {"smin32", (s64)reg->s32_min_value, reg->s32_min_value == S32_MIN},
+ {"smax32", (s64)reg->s32_max_value, reg->s32_max_value == S32_MAX},
+ {"umin32", reg->u32_min_value, reg->u32_min_value == 0},
+ {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX},
+ }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)];
+ bool neg1, neg2;
+
+ for (m1 = &minmaxs[0]; m1 < mend; m1++) {
+ if (m1->omit)
+ continue;
+
+ neg1 = m1->name[0] == 's' && (s64)m1->val < 0;
+
+ verbose(env, "%s%s=", *sep, m1->name);
+ *sep = ",";
+
+ for (m2 = m1 + 2; m2 < mend; m2 += 2) {
+ if (m2->omit || m2->val != m1->val)
+ continue;
+ /* don't mix negatives with positives */
+ neg2 = m2->name[0] == 's' && (s64)m2->val < 0;
+ if (neg2 != neg1)
+ continue;
+ m2->omit = true;
+ verbose(env, "%s=", m2->name);
+ }
+
+ verbose(env, m1->name[0] == 's' ? "%lld" : "%llu", m1->val);
+ }
+}
+
static void print_verifier_state(struct bpf_verifier_env *env,
const struct bpf_func_state *state,
bool print_all)
@@ -1415,34 +1478,13 @@ static void print_verifier_state(struct bpf_verifier_env *env,
*/
verbose_a("imm=%llx", reg->var_off.value);
} else {
- if (reg->smin_value != reg->umin_value &&
- reg->smin_value != S64_MIN)
- verbose_a("smin=%lld", (long long)reg->smin_value);
- if (reg->smax_value != reg->umax_value &&
- reg->smax_value != S64_MAX)
- verbose_a("smax=%lld", (long long)reg->smax_value);
- if (reg->umin_value != 0)
- verbose_a("umin=%llu", (unsigned long long)reg->umin_value);
- if (reg->umax_value != U64_MAX)
- verbose_a("umax=%llu", (unsigned long long)reg->umax_value);
+ print_scalar_ranges(env, reg, &sep);
if (!tnum_is_unknown(reg->var_off)) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose_a("var_off=%s", tn_buf);
}
- if (reg->s32_min_value != reg->smin_value &&
- reg->s32_min_value != S32_MIN)
- verbose_a("s32_min=%d", (int)(reg->s32_min_value));
- if (reg->s32_max_value != reg->smax_value &&
- reg->s32_max_value != S32_MAX)
- verbose_a("s32_max=%d", (int)(reg->s32_max_value));
- if (reg->u32_min_value != reg->umin_value &&
- reg->u32_min_value != U32_MIN)
- verbose_a("u32_min=%d", (int)(reg->u32_min_value));
- if (reg->u32_max_value != reg->umax_value &&
- reg->u32_max_value != U32_MAX)
- verbose_a("u32_max=%d", (int)(reg->u32_max_value));
}
#undef verbose_a
@@ -1768,7 +1810,9 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
return -ENOMEM;
dst_state->jmp_history_cnt = src->jmp_history_cnt;
- /* if dst has more stack frames then src frame, free them */
+ /* if dst has more stack frames then src frame, free them, this is also
+ * necessary in case of exceptional exits using bpf_throw.
+ */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
@@ -2669,6 +2713,68 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
return env->subprog_cnt - 1;
}
+static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ struct btf *btf = aux->btf;
+ const struct btf_type *t;
+ u32 main_btf_id, id;
+ const char *name;
+ int ret, i;
+
+ /* Non-zero func_info_cnt implies valid btf */
+ if (!aux->func_info_cnt)
+ return 0;
+ main_btf_id = aux->func_info[0].type_id;
+
+ t = btf_type_by_id(btf, main_btf_id);
+ if (!t) {
+ verbose(env, "invalid btf id for main subprog in func_info\n");
+ return -EINVAL;
+ }
+
+ name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:");
+ if (IS_ERR(name)) {
+ ret = PTR_ERR(name);
+ /* If there is no tag present, there is no exception callback */
+ if (ret == -ENOENT)
+ ret = 0;
+ else if (ret == -EEXIST)
+ verbose(env, "multiple exception callback tags for main subprog\n");
+ return ret;
+ }
+
+ ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC);
+ if (ret < 0) {
+ verbose(env, "exception callback '%s' could not be found in BTF\n", name);
+ return ret;
+ }
+ id = ret;
+ t = btf_type_by_id(btf, id);
+ if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+ verbose(env, "exception callback '%s' must have global linkage\n", name);
+ return -EINVAL;
+ }
+ ret = 0;
+ for (i = 0; i < aux->func_info_cnt; i++) {
+ if (aux->func_info[i].type_id != id)
+ continue;
+ ret = aux->func_info[i].insn_off;
+ /* Further func_info and subprog checks will also happen
+ * later, so assume this is the right insn_off for now.
+ */
+ if (!ret) {
+ verbose(env, "invalid exception callback insn_off in func_info: 0\n");
+ ret = -EINVAL;
+ }
+ }
+ if (!ret) {
+ verbose(env, "exception callback type id not found in func_info\n");
+ ret = -EINVAL;
+ }
+ return ret;
+}
+
#define MAX_KFUNC_DESCS 256
#define MAX_KFUNC_BTFS 256
@@ -3008,8 +3114,8 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
{
struct bpf_subprog_info *subprog = env->subprog_info;
+ int i, ret, insn_cnt = env->prog->len, ex_cb_insn;
struct bpf_insn *insn = env->prog->insnsi;
- int i, ret, insn_cnt = env->prog->len;
/* Add entry function. */
ret = add_subprog(env, 0);
@@ -3035,6 +3141,26 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
return ret;
}
+ ret = bpf_find_exception_callback_insn_off(env);
+ if (ret < 0)
+ return ret;
+ ex_cb_insn = ret;
+
+ /* If ex_cb_insn > 0, this means that the main program has a subprog
+ * marked using BTF decl tag to serve as the exception callback.
+ */
+ if (ex_cb_insn) {
+ ret = add_subprog(env, ex_cb_insn);
+ if (ret < 0)
+ return ret;
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (env->subprog_info[i].start != ex_cb_insn)
+ continue;
+ env->exception_callback_subprog = i;
+ break;
+ }
+ }
+
/* Add a fake 'exit' subprog which could simplify subprog iteration
* logic. 'subprog_cnt' should not be increased.
*/
@@ -3083,7 +3209,7 @@ next:
if (i == subprog_end - 1) {
/* to avoid fall-through from one subprog into another
* the last insn of the subprog should be either exit
- * or unconditional jump back
+ * or unconditional jump back or bpf_throw call
*/
if (code != (BPF_JMP | BPF_EXIT) &&
code != (BPF_JMP32 | BPF_JA) &&
@@ -3244,7 +3370,7 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (class == BPF_LDX) {
if (t != SRC_OP)
- return BPF_SIZE(code) == BPF_DW;
+ return BPF_SIZE(code) == BPF_DW || BPF_MODE(code) == BPF_MEMSX;
/* LDX source must be ptr. */
return true;
}
@@ -5243,6 +5369,8 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
perm_flags |= PTR_UNTRUSTED;
} else {
perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
+ if (kptr_field->type == BPF_KPTR_PERCPU)
+ perm_flags |= MEM_PERCPU;
}
if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
@@ -5286,7 +5414,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
*/
if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off,
kptr_field->kptr.btf, kptr_field->kptr.btf_id,
- kptr_field->type == BPF_KPTR_REF))
+ kptr_field->type != BPF_KPTR_UNREF))
goto bad_type;
return 0;
bad_type:
@@ -5314,7 +5442,9 @@ static bool in_rcu_cs(struct bpf_verifier_env *env)
/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
BTF_SET_START(rcu_protected_types)
BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
+#endif
BTF_ID(struct, bpf_cpumask)
BTF_ID(struct, task_struct)
BTF_SET_END(rcu_protected_types)
@@ -5330,7 +5460,18 @@ static bool rcu_safe_kptr(const struct btf_field *field)
{
const struct btf_field_kptr *kptr = &field->kptr;
- return field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id);
+ return field->type == BPF_KPTR_PERCPU ||
+ (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id));
+}
+
+static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
+{
+ if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
+ if (kptr_field->type != BPF_KPTR_PERCPU)
+ return PTR_MAYBE_NULL | MEM_RCU;
+ return PTR_MAYBE_NULL | MEM_RCU | MEM_PERCPU;
+ }
+ return PTR_MAYBE_NULL | PTR_UNTRUSTED;
}
static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
@@ -5356,7 +5497,8 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
/* We only allow loading referenced kptr, since it will be marked as
* untrusted, similar to unreferenced kptr.
*/
- if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) {
+ if (class != BPF_LDX &&
+ (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) {
verbose(env, "store to referenced kptr disallowed\n");
return -EACCES;
}
@@ -5367,10 +5509,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno,
* value from map as PTR_TO_BTF_ID, with the correct type.
*/
mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf,
- kptr_field->kptr.btf_id,
- rcu_safe_kptr(kptr_field) && in_rcu_cs(env) ?
- PTR_MAYBE_NULL | MEM_RCU :
- PTR_MAYBE_NULL | PTR_UNTRUSTED);
+ kptr_field->kptr.btf_id, btf_ld_kptr_type(env, kptr_field));
/* For mark_ptr_or_null_reg */
val_reg->id = ++env->id_gen;
} else if (class == BPF_STX) {
@@ -5424,6 +5563,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
switch (field->type) {
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
+ case BPF_KPTR_PERCPU:
if (src != ACCESS_DIRECT) {
verbose(env, "kptr cannot be accessed indirectly by helper\n");
return -EACCES;
@@ -5877,6 +6017,27 @@ continue_func:
for (; i < subprog_end; i++) {
int next_insn, sidx;
+ if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off) {
+ bool err = false;
+
+ if (!is_bpf_throw_kfunc(insn + i))
+ continue;
+ if (subprog[idx].is_cb)
+ err = true;
+ for (int c = 0; c < frame && !err; c++) {
+ if (subprog[ret_prog[c]].is_cb) {
+ err = true;
+ break;
+ }
+ }
+ if (!err)
+ continue;
+ verbose(env,
+ "bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n",
+ i, idx);
+ return -EINVAL;
+ }
+
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
/* remember insn and function to return to */
@@ -5899,6 +6060,10 @@ continue_func:
/* async callbacks don't increase bpf prog stack size unless called directly */
if (!bpf_pseudo_call(insn + i))
continue;
+ if (subprog[sidx].is_exception_cb) {
+ verbose(env, "insn %d cannot call exception cb directly\n", i);
+ return -EINVAL;
+ }
}
i = next_insn;
idx = sidx;
@@ -5920,8 +6085,13 @@ continue_func:
* tail call counter throughout bpf2bpf calls combined with tailcalls
*/
if (tail_call_reachable)
- for (j = 0; j < frame; j++)
+ for (j = 0; j < frame; j++) {
+ if (subprog[ret_prog[j]].is_exception_cb) {
+ verbose(env, "cannot tail call within exception cb\n");
+ return -EINVAL;
+ }
subprog[ret_prog[j]].tail_call_reachable = true;
+ }
if (subprog[0].tail_call_reachable)
env->prog->aux->tail_call_reachable = true;
@@ -6437,7 +6607,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
}
if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) &&
- !reg->ref_obj_id) {
+ !(reg->type & MEM_RCU) && !reg->ref_obj_id) {
verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n");
return -EFAULT;
}
@@ -7542,7 +7712,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
return -EACCES;
}
- if (kptr_field->type != BPF_KPTR_REF) {
+ if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) {
verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
return -EACCES;
}
@@ -7713,15 +7883,24 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
return err;
}
- err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots);
+ err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
if (err)
return err;
} else {
/* iter_next() or iter_destroy() expect initialized iter state*/
- if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) {
+ err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots);
+ switch (err) {
+ case 0:
+ break;
+ case -EINVAL:
verbose(env, "expected an initialized iter_%s as arg #%d\n",
iter_type_str(meta->btf, btf_id), regno);
- return -EINVAL;
+ return err;
+ case -EPROTO:
+ verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
+ return err;
+ default:
+ return err;
}
spi = iter_get_spi(env, reg, nr_slots);
@@ -8087,6 +8266,7 @@ static const struct bpf_reg_types btf_ptr_types = {
static const struct bpf_reg_types percpu_btf_ptr_types = {
.types = {
PTR_TO_BTF_ID | MEM_PERCPU,
+ PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU,
PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED,
}
};
@@ -8165,8 +8345,10 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
if (base_type(arg_type) == ARG_PTR_TO_MEM)
type &= ~DYNPTR_TYPE_FLAG_MASK;
- if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type))
+ if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type)) {
type &= ~MEM_ALLOC;
+ type &= ~MEM_PERCPU;
+ }
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
expected = compatible->types[i];
@@ -8249,6 +8431,7 @@ found:
break;
}
case PTR_TO_BTF_ID | MEM_ALLOC:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_ALLOC:
if (meta->func_id != BPF_FUNC_spin_lock && meta->func_id != BPF_FUNC_spin_unlock &&
meta->func_id != BPF_FUNC_kptr_xchg) {
verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n");
@@ -8260,6 +8443,7 @@ found:
}
break;
case PTR_TO_BTF_ID | MEM_PERCPU:
+ case PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU:
case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED:
/* Handled by helper specific checks */
break;
@@ -9254,6 +9438,7 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins
* interested in validating only BPF helpers that can call subprogs as
* callbacks
*/
+ env->subprog_info[subprog].is_cb = true;
if (bpf_pseudo_kfunc_call(insn) &&
!is_sync_callback_calling_kfunc(insn->imm)) {
verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n",
@@ -9674,7 +9859,8 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
verbose(env, "to caller at %d:\n", *insn_idx);
print_verifier_state(env, caller, true);
}
- /* clear everything in the callee */
+ /* clear everything in the callee. In case of exceptional exits using
+ * bpf_throw, this will be done by copy_verifier_state for extra frames. */
free_func_state(callee);
state->frame[state->curframe--] = NULL;
@@ -9816,17 +10002,17 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
}
-static int check_reference_leak(struct bpf_verifier_env *env)
+static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit)
{
struct bpf_func_state *state = cur_func(env);
bool refs_lingering = false;
int i;
- if (state->frameno && !state->in_callback_fn)
+ if (!exception_exit && state->frameno && !state->in_callback_fn)
return 0;
for (i = 0; i < state->acquired_refs; i++) {
- if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
+ if (!exception_exit && state->in_callback_fn && state->refs[i].callback_ref != state->frameno)
continue;
verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
state->refs[i].id, state->refs[i].insn_idx);
@@ -9933,6 +10119,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
int *insn_idx_p)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+ bool returns_cpu_specific_alloc_ptr = false;
const struct bpf_func_proto *fn = NULL;
enum bpf_return_type ret_type;
enum bpf_type_flag ret_flag;
@@ -10043,6 +10230,26 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EFAULT;
}
err = unmark_stack_slots_dynptr(env, &regs[meta.release_regno]);
+ } else if (func_id == BPF_FUNC_kptr_xchg && meta.ref_obj_id) {
+ u32 ref_obj_id = meta.ref_obj_id;
+ bool in_rcu = in_rcu_cs(env);
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ err = release_reference_state(cur_func(env), ref_obj_id);
+ if (!err) {
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg->ref_obj_id == ref_obj_id) {
+ if (in_rcu && (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) {
+ reg->ref_obj_id = 0;
+ reg->type &= ~MEM_ALLOC;
+ reg->type |= MEM_RCU;
+ } else {
+ mark_reg_invalid(env, reg);
+ }
+ }
+ }));
+ }
} else if (meta.ref_obj_id) {
err = release_reference(env, meta.ref_obj_id);
} else if (register_is_null(&regs[meta.release_regno])) {
@@ -10060,7 +10267,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
switch (func_id) {
case BPF_FUNC_tail_call:
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "tail_call would lead to reference leak\n");
return err;
@@ -10184,6 +10391,23 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
break;
}
+ case BPF_FUNC_per_cpu_ptr:
+ case BPF_FUNC_this_cpu_ptr:
+ {
+ struct bpf_reg_state *reg = &regs[BPF_REG_1];
+ const struct btf_type *type;
+
+ if (reg->type & MEM_RCU) {
+ type = btf_type_by_id(reg->btf, reg->btf_id);
+ if (!type || !btf_type_is_struct(type)) {
+ verbose(env, "Helper has invalid btf/btf_id in R1\n");
+ return -EFAULT;
+ }
+ returns_cpu_specific_alloc_ptr = true;
+ env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true;
+ }
+ break;
+ }
case BPF_FUNC_user_ringbuf_drain:
err = push_callback_call(env, insn, insn_idx, meta.subprogno,
set_user_ringbuf_callback_state);
@@ -10273,14 +10497,18 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
regs[BPF_REG_0].mem_size = tsize;
} else {
- /* MEM_RDONLY may be carried from ret_flag, but it
- * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
- * it will confuse the check of PTR_TO_BTF_ID in
- * check_mem_access().
- */
- ret_flag &= ~MEM_RDONLY;
+ if (returns_cpu_specific_alloc_ptr) {
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU;
+ } else {
+ /* MEM_RDONLY may be carried from ret_flag, but it
+ * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
+ * it will confuse the check of PTR_TO_BTF_ID in
+ * check_mem_access().
+ */
+ ret_flag &= ~MEM_RDONLY;
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
+ }
- regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
regs[BPF_REG_0].btf = meta.ret_btf;
regs[BPF_REG_0].btf_id = meta.ret_btf_id;
}
@@ -10296,8 +10524,11 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (func_id == BPF_FUNC_kptr_xchg) {
ret_btf = meta.kptr_field->kptr.btf;
ret_btf_id = meta.kptr_field->kptr.btf_id;
- if (!btf_is_kernel(ret_btf))
+ if (!btf_is_kernel(ret_btf)) {
regs[BPF_REG_0].type |= MEM_ALLOC;
+ if (meta.kptr_field->type == BPF_KPTR_PERCPU)
+ regs[BPF_REG_0].type |= MEM_PERCPU;
+ }
} else {
if (fn->ret_btf_id == BPF_PTR_POISON) {
verbose(env, "verifier internal error:");
@@ -10444,6 +10675,11 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta)
return meta->kfunc_flags & KF_RCU;
}
+static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta)
+{
+ return meta->kfunc_flags & KF_RCU_PROTECTED;
+}
+
static bool __kfunc_param_match_suffix(const struct btf *btf,
const struct btf_param *arg,
const char *suffix)
@@ -10518,6 +10754,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf
return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr");
}
+static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__nullable");
+}
+
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
const struct btf_param *arg,
const char *name)
@@ -10660,6 +10901,7 @@ enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CALLBACK,
KF_ARG_PTR_TO_RB_ROOT,
KF_ARG_PTR_TO_RB_NODE,
+ KF_ARG_PTR_TO_NULL,
};
enum special_kfunc_type {
@@ -10682,6 +10924,10 @@ enum special_kfunc_type {
KF_bpf_dynptr_slice,
KF_bpf_dynptr_slice_rdwr,
KF_bpf_dynptr_clone,
+ KF_bpf_percpu_obj_new_impl,
+ KF_bpf_percpu_obj_drop_impl,
+ KF_bpf_throw,
+ KF_bpf_iter_css_task_new,
};
BTF_SET_START(special_kfunc_set)
@@ -10702,6 +10948,12 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#endif
BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
@@ -10724,6 +10976,14 @@ BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
+BTF_ID(func, bpf_percpu_obj_new_impl)
+BTF_ID(func, bpf_percpu_obj_drop_impl)
+BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
+BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
{
@@ -10804,6 +11064,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
if (is_kfunc_arg_callback(env, meta->btf, &args[argno]))
return KF_ARG_PTR_TO_CALLBACK;
+ if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg))
+ return KF_ARG_PTR_TO_NULL;
if (argno + 1 < nargs &&
(is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], &regs[regno + 1]) ||
@@ -11041,6 +11303,12 @@ static bool is_sync_callback_calling_kfunc(u32 btf_id)
return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
}
+static bool is_bpf_throw_kfunc(struct bpf_insn *insn)
+{
+ return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
+ insn->imm == special_kfunc_list[KF_bpf_throw];
+}
+
static bool is_rbtree_lock_required_kfunc(u32 btf_id)
{
return is_bpf_rbtree_api_kfunc(btf_id);
@@ -11248,6 +11516,28 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
&meta->arg_rbtree_root.field);
}
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
+static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
+{
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+ switch (prog_type) {
+ case BPF_PROG_TYPE_LSM:
+ return true;
+ case BPF_PROG_TYPE_TRACING:
+ if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+ return true;
+ fallthrough;
+ default:
+ return env->prog->aux->sleepable;
+ }
+}
+
static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta,
int insn_idx)
{
@@ -11334,7 +11624,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
- (register_is_null(reg) || type_may_be_null(reg->type))) {
+ (register_is_null(reg) || type_may_be_null(reg->type)) &&
+ !is_kfunc_arg_nullable(meta->btf, &args[i])) {
verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
return -EACCES;
}
@@ -11359,6 +11650,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
return kf_arg_type;
switch (kf_arg_type) {
+ case KF_ARG_PTR_TO_NULL:
+ continue;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
case KF_ARG_PTR_TO_BTF_ID:
if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))
@@ -11418,7 +11711,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
break;
case KF_ARG_PTR_TO_ALLOC_BTF_ID:
- if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) {
+ if (meta->func_id != special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
+ verbose(env, "arg#%d expected for bpf_percpu_obj_drop_impl()\n", i);
+ return -EINVAL;
+ }
+ } else {
verbose(env, "arg#%d expected pointer to allocated object\n", i);
return -EINVAL;
}
@@ -11426,8 +11729,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "allocated object must be referenced\n");
return -EINVAL;
}
- if (meta->btf == btf_vmlinux &&
- meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta->btf == btf_vmlinux) {
meta->arg_btf = reg->btf;
meta->arg_btf_id = reg->btf_id;
}
@@ -11489,6 +11791,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
}
case KF_ARG_PTR_TO_ITER:
+ if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
+ if (!check_css_task_iter_allowlist(env)) {
+ verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
+ return -EINVAL;
+ }
+ }
ret = process_iter_arg(env, regno, insn_idx, meta);
if (ret < 0)
return ret;
@@ -11700,6 +12008,8 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
return 0;
}
+static int check_return_code(struct bpf_verifier_env *env, int regno);
+
static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
@@ -11761,6 +12071,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (env->cur_state->active_rcu_lock) {
struct bpf_func_state *state;
struct bpf_reg_state *reg;
+ u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER);
if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
@@ -11771,7 +12082,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
return -EINVAL;
} else if (rcu_unlock) {
- bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({
if (reg->type & MEM_RCU) {
reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL);
reg->type |= PTR_UNTRUSTED;
@@ -11822,6 +12133,24 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
+ if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
+ if (!bpf_jit_supports_exceptions()) {
+ verbose(env, "JIT does not support calling kfunc %s#%d\n",
+ func_name, meta.func_id);
+ return -ENOTSUPP;
+ }
+ env->seen_exception = true;
+
+ /* In the case of the default callback, the cookie value passed
+ * to bpf_throw becomes the return value of the program.
+ */
+ if (!env->exception_callback_subprog) {
+ err = check_return_code(env, BPF_REG_1);
+ if (err < 0)
+ return err;
+ }
+ }
+
for (i = 0; i < CALLER_SAVED_REGS; i++)
mark_reg_not_init(env, regs, caller_saved[i]);
@@ -11832,6 +12161,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* Only exception is bpf_obj_new_impl */
if (meta.btf != btf_vmlinux ||
(meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl] &&
+ meta.func_id != special_kfunc_list[KF_bpf_percpu_obj_new_impl] &&
meta.func_id != special_kfunc_list[KF_bpf_refcount_acquire_impl])) {
verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
return -EINVAL;
@@ -11845,13 +12175,29 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ struct btf_struct_meta *struct_meta;
struct btf *ret_btf;
u32 ret_btf_id;
- if (unlikely(!bpf_global_ma_set))
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
return -ENOMEM;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!bpf_global_percpu_ma_set) {
+ mutex_lock(&bpf_percpu_ma_lock);
+ if (!bpf_global_percpu_ma_set) {
+ err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
+ if (!err)
+ bpf_global_percpu_ma_set = true;
+ }
+ mutex_unlock(&bpf_percpu_ma_lock);
+ if (err)
+ return err;
+ }
+ }
+
if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
return -EINVAL;
@@ -11862,24 +12208,38 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* This may be NULL due to user not supplying a BTF */
if (!ret_btf) {
- verbose(env, "bpf_obj_new requires prog BTF\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
return -EINVAL;
}
ret_t = btf_type_by_id(ret_btf, ret_btf_id);
if (!ret_t || !__btf_type_is_struct(ret_t)) {
- verbose(env, "bpf_obj_new type ID argument must be of a struct\n");
+ verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
return -EINVAL;
}
+ struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+ if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
+ return -EINVAL;
+ }
+
+ if (struct_meta) {
+ verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
+ return -EINVAL;
+ }
+ }
+
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
regs[BPF_REG_0].btf = ret_btf;
regs[BPF_REG_0].btf_id = ret_btf_id;
+ if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl])
+ regs[BPF_REG_0].type |= MEM_PERCPU;
insn_aux->obj_new_size = ret_t->size;
- insn_aux->kptr_struct_meta =
- btf_find_struct_meta(ret_btf, ret_btf_id);
+ insn_aux->kptr_struct_meta = struct_meta;
} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
@@ -12016,7 +12376,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
regs[BPF_REG_0].id = ++env->id_gen;
} else if (btf_type_is_void(t)) {
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
- if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
+ if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl]) {
insn_aux->kptr_struct_meta =
btf_find_struct_meta(meta.arg_btf,
meta.arg_btf_id);
@@ -13816,12 +14177,16 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
return !!tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 0;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(subreg))
return !tnum_equals_const(subreg, val);
else if (val < reg->u32_min_value || val > reg->u32_max_value)
return 1;
+ else if (sval < reg->s32_min_value || sval > reg->s32_max_value)
+ return 1;
break;
case BPF_JSET:
if ((~subreg.mask & subreg.value) & val)
@@ -13893,12 +14258,16 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
return !!tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 0;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 0;
break;
case BPF_JNE:
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
else if (val < reg->umin_value || val > reg->umax_value)
return 1;
+ else if (sval < reg->smin_value || sval > reg->smax_value)
+ return 1;
break;
case BPF_JSET:
if ((~reg->var_off.mask & reg->var_off.value) & val)
@@ -14854,7 +15223,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
* gen_ld_abs() may terminate the program at runtime, leading to
* reference leak.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, false);
if (err) {
verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
return err;
@@ -14903,7 +15272,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
-static int check_return_code(struct bpf_verifier_env *env)
+static int check_return_code(struct bpf_verifier_env *env, int regno)
{
struct tnum enforce_attach_type_range = tnum_unknown;
const struct bpf_prog *prog = env->prog;
@@ -14915,7 +15284,7 @@ static int check_return_code(struct bpf_verifier_env *env)
const bool is_subprog = frame->subprogno;
/* LSM and struct_ops func-ptr's return type could be "void" */
- if (!is_subprog) {
+ if (!is_subprog || frame->in_exception_callback_fn) {
switch (prog_type) {
case BPF_PROG_TYPE_LSM:
if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -14937,22 +15306,22 @@ static int check_return_code(struct bpf_verifier_env *env)
* of bpf_exit, which means that program wrote
* something into it earlier
*/
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ err = check_reg_arg(env, regno, SRC_OP);
if (err)
return err;
- if (is_pointer_value(env, BPF_REG_0)) {
- verbose(env, "R0 leaks addr as return value\n");
+ if (is_pointer_value(env, regno)) {
+ verbose(env, "R%d leaks addr as return value\n", regno);
return -EACCES;
}
- reg = cur_regs(env) + BPF_REG_0;
+ reg = cur_regs(env) + regno;
if (frame->in_async_callback_fn) {
/* enforce return zero from async callbacks like timer */
if (reg->type != SCALAR_VALUE) {
- verbose(env, "In async callback the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "In async callback the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -14963,10 +15332,10 @@ static int check_return_code(struct bpf_verifier_env *env)
return 0;
}
- if (is_subprog) {
+ if (is_subprog && !frame->in_exception_callback_fn) {
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
return 0;
@@ -14976,10 +15345,13 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME ||
env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
- env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME)
range = tnum_range(1, 1);
if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND ||
env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND)
@@ -15048,8 +15420,8 @@ static int check_return_code(struct bpf_verifier_env *env)
}
if (reg->type != SCALAR_VALUE) {
- verbose(env, "At program exit the register R0 is not a known value (%s)\n",
- reg_type_str(env, reg->type));
+ verbose(env, "At program exit the register R%d is not a known value (%s)\n",
+ regno, reg_type_str(env, reg->type));
return -EINVAL;
}
@@ -15325,8 +15697,8 @@ static int check_cfg(struct bpf_verifier_env *env)
{
int insn_cnt = env->prog->len;
int *insn_stack, *insn_state;
- int ret = 0;
- int i;
+ int ex_insn_beg, i, ret = 0;
+ bool ex_done = false;
insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
@@ -15342,6 +15714,7 @@ static int check_cfg(struct bpf_verifier_env *env)
insn_stack[0] = 0; /* 0 is the first instruction */
env->cfg.cur_stack = 1;
+walk_cfg:
while (env->cfg.cur_stack > 0) {
int t = insn_stack[env->cfg.cur_stack - 1];
@@ -15368,6 +15741,16 @@ static int check_cfg(struct bpf_verifier_env *env)
goto err_free;
}
+ if (env->exception_callback_subprog && !ex_done) {
+ ex_insn_beg = env->subprog_info[env->exception_callback_subprog].start;
+
+ insn_state[ex_insn_beg] = DISCOVERED;
+ insn_stack[0] = ex_insn_beg;
+ env->cfg.cur_stack = 1;
+ ex_done = true;
+ goto walk_cfg;
+ }
+
for (i = 0; i < insn_cnt; i++) {
struct bpf_insn *insn = &env->prog->insnsi[i];
@@ -15415,20 +15798,18 @@ static int check_abnormal_return(struct bpf_verifier_env *env)
#define MIN_BPF_FUNCINFO_SIZE 8
#define MAX_FUNCINFO_REC_SIZE 252
-static int check_btf_func(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_func_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
- const struct btf_type *type, *func_proto, *ret_type;
- u32 i, nfuncs, urec_size, min_size;
u32 krec_size = sizeof(struct bpf_func_info);
+ const struct btf_type *type, *func_proto;
+ u32 i, nfuncs, urec_size, min_size;
struct bpf_func_info *krecord;
- struct bpf_func_info_aux *info_aux = NULL;
struct bpf_prog *prog;
const struct btf *btf;
- bpfptr_t urecord;
u32 prev_offset = 0;
- bool scalar_return;
+ bpfptr_t urecord;
int ret = -ENOMEM;
nfuncs = attr->func_info_cnt;
@@ -15438,11 +15819,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
return 0;
}
- if (nfuncs != env->subprog_cnt) {
- verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
- return -EINVAL;
- }
-
urec_size = attr->func_info_rec_size;
if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
urec_size > MAX_FUNCINFO_REC_SIZE ||
@@ -15460,9 +15836,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
- info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
- if (!info_aux)
- goto err_free;
for (i = 0; i < nfuncs; i++) {
ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
@@ -15501,11 +15874,6 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- if (env->subprog_info[i].start != krecord[i].insn_off) {
- verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
- goto err_free;
- }
-
/* check type_id */
type = btf_type_by_id(btf, krecord[i].type_id);
if (!type || !btf_type_is_func(type)) {
@@ -15513,12 +15881,77 @@ static int check_btf_func(struct bpf_verifier_env *env,
krecord[i].type_id);
goto err_free;
}
- info_aux[i].linkage = BTF_INFO_VLEN(type->info);
func_proto = btf_type_by_id(btf, type->type);
if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
/* btf_func_check() already verified it during BTF load */
goto err_free;
+
+ prev_offset = krecord[i].insn_off;
+ bpfptr_add(&urecord, urec_size);
+ }
+
+ prog->aux->func_info = krecord;
+ prog->aux->func_info_cnt = nfuncs;
+ return 0;
+
+err_free:
+ kvfree(krecord);
+ return ret;
+}
+
+static int check_btf_func(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ const struct btf_type *type, *func_proto, *ret_type;
+ u32 i, nfuncs, urec_size;
+ struct bpf_func_info *krecord;
+ struct bpf_func_info_aux *info_aux = NULL;
+ struct bpf_prog *prog;
+ const struct btf *btf;
+ bpfptr_t urecord;
+ bool scalar_return;
+ int ret = -ENOMEM;
+
+ nfuncs = attr->func_info_cnt;
+ if (!nfuncs) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+ if (nfuncs != env->subprog_cnt) {
+ verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
+ return -EINVAL;
+ }
+
+ urec_size = attr->func_info_rec_size;
+
+ prog = env->prog;
+ btf = prog->aux->btf;
+
+ urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
+
+ krecord = prog->aux->func_info;
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+ if (!info_aux)
+ return -ENOMEM;
+
+ for (i = 0; i < nfuncs; i++) {
+ /* check insn_off */
+ ret = -EINVAL;
+
+ if (env->subprog_info[i].start != krecord[i].insn_off) {
+ verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
+ goto err_free;
+ }
+
+ /* Already checked type_id */
+ type = btf_type_by_id(btf, krecord[i].type_id);
+ info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+ /* Already checked func_proto */
+ func_proto = btf_type_by_id(btf, type->type);
+
ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
scalar_return =
btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type);
@@ -15531,17 +15964,13 @@ static int check_btf_func(struct bpf_verifier_env *env,
goto err_free;
}
- prev_offset = krecord[i].insn_off;
bpfptr_add(&urecord, urec_size);
}
- prog->aux->func_info = krecord;
- prog->aux->func_info_cnt = nfuncs;
prog->aux->func_info_aux = info_aux;
return 0;
err_free:
- kvfree(krecord);
kfree(info_aux);
return ret;
}
@@ -15554,7 +15983,8 @@ static void adjust_btf_func(struct bpf_verifier_env *env)
if (!aux->func_info)
return;
- for (i = 0; i < env->subprog_cnt; i++)
+ /* func_info is not available for hidden subprogs */
+ for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++)
aux->func_info[i].insn_off = env->subprog_info[i].start;
}
@@ -15758,9 +16188,9 @@ static int check_core_relo(struct bpf_verifier_env *env,
return err;
}
-static int check_btf_info(struct bpf_verifier_env *env,
- const union bpf_attr *attr,
- bpfptr_t uattr)
+static int check_btf_info_early(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
{
struct btf *btf;
int err;
@@ -15780,6 +16210,24 @@ static int check_btf_info(struct bpf_verifier_env *env,
}
env->prog->aux->btf = btf;
+ err = check_btf_func_early(env, attr, uattr);
+ if (err)
+ return err;
+ return 0;
+}
+
+static int check_btf_info(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ bpfptr_t uattr)
+{
+ int err;
+
+ if (!attr->func_info_cnt && !attr->line_info_cnt) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+
err = check_btf_func(env, attr, uattr);
if (err)
return err;
@@ -16964,6 +17412,7 @@ static int do_check(struct bpf_verifier_env *env)
int prev_insn_idx = -1;
for (;;) {
+ bool exception_exit = false;
struct bpf_insn *insn;
u8 class;
int err;
@@ -17178,12 +17627,17 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
}
- if (insn->src_reg == BPF_PSEUDO_CALL)
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
err = check_func_call(env, insn, &env->insn_idx);
- else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
+ } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
err = check_kfunc_call(env, insn, &env->insn_idx);
- else
+ if (!err && is_bpf_throw_kfunc(insn)) {
+ exception_exit = true;
+ goto process_bpf_exit_full;
+ }
+ } else {
err = check_helper_call(env, insn, &env->insn_idx);
+ }
if (err)
return err;
@@ -17213,7 +17667,7 @@ static int do_check(struct bpf_verifier_env *env)
verbose(env, "BPF_EXIT uses reserved fields\n");
return -EINVAL;
}
-
+process_bpf_exit_full:
if (env->cur_state->active_lock.ptr &&
!in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_spin_unlock is missing\n");
@@ -17232,10 +17686,23 @@ static int do_check(struct bpf_verifier_env *env)
* function, for which reference_state must
* match caller reference state when it exits.
*/
- err = check_reference_leak(env);
+ err = check_reference_leak(env, exception_exit);
if (err)
return err;
+ /* The side effect of the prepare_func_exit
+ * which is being skipped is that it frees
+ * bpf_func_state. Typically, process_bpf_exit
+ * will only be hit with outermost exit.
+ * copy_verifier_state in pop_stack will handle
+ * freeing of any extra bpf_func_state left over
+ * from not processing all nested function
+ * exits. We also skip return code checks as
+ * they are not needed for exceptional exits.
+ */
+ if (exception_exit)
+ goto process_bpf_exit;
+
if (state->curframe) {
/* exit from nested function */
err = prepare_func_exit(env, &env->insn_idx);
@@ -17245,7 +17712,7 @@ static int do_check(struct bpf_verifier_env *env)
continue;
}
- err = check_return_code(env);
+ err = check_return_code(env, BPF_REG_0);
if (err)
return err;
process_bpf_exit:
@@ -18538,6 +19005,9 @@ static int jit_subprogs(struct bpf_verifier_env *env)
}
func[i]->aux->num_exentries = num_exentries;
func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
+ func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb;
+ if (!i)
+ func[i]->aux->exception_boundary = env->seen_exception;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -18577,7 +19047,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* the call instruction, as an index for this list
*/
func[i]->aux->func = func;
- func[i]->aux->func_cnt = env->subprog_cnt;
+ func[i]->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ func[i]->aux->real_func_cnt = env->subprog_cnt;
}
for (i = 0; i < env->subprog_cnt; i++) {
old_bpf_func = func[i]->bpf_func;
@@ -18623,7 +19094,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
prog->aux->extable = func[0]->aux->extable;
prog->aux->num_exentries = func[0]->aux->num_exentries;
prog->aux->func = func;
- prog->aux->func_cnt = env->subprog_cnt;
+ prog->aux->func_cnt = env->subprog_cnt - env->hidden_subprog_cnt;
+ prog->aux->real_func_cnt = env->subprog_cnt;
+ prog->aux->bpf_exception_cb = (void *)func[env->exception_callback_subprog]->bpf_func;
+ prog->aux->exception_boundary = func[0]->aux->exception_boundary;
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
@@ -18790,21 +19264,35 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
insn->imm = BPF_CALL_IMM(desc->addr);
if (insn->off)
return 0;
- if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
+ if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size;
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size);
insn_buf[1] = addr[0];
insn_buf[2] = addr[1];
insn_buf[3] = *insn;
*cnt = 4;
} else if (desc->func_id == special_kfunc_list[KF_bpf_obj_drop_impl] ||
+ desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
+ if (desc->func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl] && kptr_struct_meta) {
+ verbose(env, "verifier internal error: NULL kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
!kptr_struct_meta) {
verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
@@ -18845,6 +19333,33 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return 0;
}
+/* The function requires that first instruction in 'patch' is insnsi[prog->len - 1] */
+static int add_hidden_subprog(struct bpf_verifier_env *env, struct bpf_insn *patch, int len)
+{
+ struct bpf_subprog_info *info = env->subprog_info;
+ int cnt = env->subprog_cnt;
+ struct bpf_prog *prog;
+
+ /* We only reserve one slot for hidden subprogs in subprog_info. */
+ if (env->hidden_subprog_cnt) {
+ verbose(env, "verifier internal error: only one hidden subprog supported\n");
+ return -EFAULT;
+ }
+ /* We're not patching any existing instruction, just appending the new
+ * ones for the hidden subprog. Hence all of the adjustment operations
+ * in bpf_patch_insn_data are no-ops.
+ */
+ prog = bpf_patch_insn_data(env, env->prog->len - 1, patch, len);
+ if (!prog)
+ return -ENOMEM;
+ env->prog = prog;
+ info[cnt + 1].start = info[cnt].start;
+ info[cnt].start = prog->len - len + 1;
+ env->subprog_cnt++;
+ env->hidden_subprog_cnt++;
+ return 0;
+}
+
/* Do various post-verification rewrites in a single program pass.
* These rewrites simplify JIT and interpreter implementations.
*/
@@ -18863,6 +19378,26 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
struct bpf_map *map_ptr;
int i, ret, cnt, delta = 0;
+ if (env->seen_exception && !env->exception_callback_subprog) {
+ struct bpf_insn patch[] = {
+ env->prog->insnsi[insn_cnt - 1],
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ };
+
+ ret = add_hidden_subprog(env, patch, ARRAY_SIZE(patch));
+ if (ret < 0)
+ return ret;
+ prog = env->prog;
+ insn = prog->insnsi;
+
+ env->exception_callback_subprog = env->subprog_cnt - 1;
+ /* Don't update insn_cnt, as add_hidden_subprog always appends insns */
+ env->subprog_info[env->exception_callback_subprog].is_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_async_cb = true;
+ env->subprog_info[env->exception_callback_subprog].is_exception_cb = true;
+ }
+
for (i = 0; i < insn_cnt; i++, insn++) {
/* Make divide-by-zero exceptions impossible. */
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
@@ -19132,6 +19667,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_call_imm;
}
+ /* bpf_per_cpu_ptr() and bpf_this_cpu_ptr() */
+ if (env->insn_aux_data[i + delta].call_with_percpu_alloc_ptr) {
+ /* patch with 'r1 = *(u64 *)(r1 + 0)' since for percpu data,
+ * bpf_mem_alloc() returns a ptr to the percpu data ptr.
+ */
+ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+ insn_buf[1] = *insn;
+ cnt = 2;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ goto patch_call_imm;
+ }
+
/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
* and other inlining handlers are currently limited to 64 bit
* only.
@@ -19541,7 +20095,7 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state;
@@ -19572,7 +20126,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs = state->frame[state->curframe]->regs;
if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
- ret = btf_prepare_func_args(env, subprog, regs);
+ ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb);
if (ret)
goto out;
for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
@@ -19588,6 +20142,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
regs[i].id = ++env->id_gen;
}
}
+ if (is_ex_cb) {
+ state->frame[0]->in_exception_callback_fn = true;
+ env->subprog_info[subprog].is_cb = true;
+ env->subprog_info[subprog].is_async_cb = true;
+ env->subprog_info[subprog].is_exception_cb = true;
+ }
} else {
/* 1st arg to a function */
regs[BPF_REG_1].type = PTR_TO_CTX;
@@ -19652,7 +20212,7 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
continue;
env->insn_idx = env->subprog_info[i].start;
WARN_ON_ONCE(env->insn_idx == 0);
- ret = do_check_common(env, i);
+ ret = do_check_common(env, i, env->exception_callback_subprog == i);
if (ret) {
return ret;
} else if (env->log.level & BPF_LOG_LEVEL) {
@@ -19669,7 +20229,7 @@ static int do_check_main(struct bpf_verifier_env *env)
int ret;
env->insn_idx = 0;
- ret = do_check_common(env, 0);
+ ret = do_check_common(env, 0, false);
if (!ret)
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return ret;
@@ -19838,6 +20398,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
bpf_log(log, "Subprog %s doesn't exist\n", tname);
return -EINVAL;
}
+ if (aux->func && aux->func[subprog]->aux->exception_cb) {
+ bpf_log(log,
+ "%s programs cannot attach to exception callback\n",
+ prog_extension ? "Extension" : "FENTRY/FEXIT");
+ return -EINVAL;
+ }
conservative = aux->func_info_aux[subprog].unreliable;
if (prog_extension) {
if (conservative) {
@@ -20265,6 +20831,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (!env->explored_states)
goto skip_full_check;
+ ret = check_btf_info_early(env, attr, uattr);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = add_subprog_and_kfunc(env);
if (ret < 0)
goto skip_full_check;
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-20 23:11:15 +0000