aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c53
-rw-r--r--kernel/bpf/btf.c419
-rw-r--r--kernel/bpf/cgroup.c370
-rw-r--r--kernel/bpf/core.c14
-rw-r--r--kernel/bpf/cpumap.c53
-rw-r--r--kernel/bpf/disasm.c5
-rw-r--r--kernel/bpf/hashtab.c6
-rw-r--r--kernel/bpf/helpers.c131
-rw-r--r--kernel/bpf/local_storage.c6
-rw-r--r--kernel/bpf/lpm_trie.c3
-rw-r--r--kernel/bpf/queue_stack_maps.c6
-rw-r--r--kernel/bpf/syscall.c164
-rw-r--r--kernel/bpf/verifier.c618
-rw-r--r--kernel/sysctl.c6
-rw-r--r--kernel/taskstats.c33
-rw-r--r--kernel/time/time.c10
-rw-r--r--kernel/trace/bpf_trace.c30
17 files changed, 1694 insertions, 233 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c72e0d8e1e65..584636c9e2eb 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -22,7 +22,7 @@
#include "map_in_map.h"
#define ARRAY_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
static void bpf_array_free_percpu(struct bpf_array *array)
{
@@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr)
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0 ||
attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags) ||
(percpu && numa_node != NUMA_NO_NODE))
return -EINVAL;
@@ -160,6 +161,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
return array->value + array->elem_size * (index & array->index_mask);
}
+static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
+ u32 off)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+ if (map->max_entries != 1)
+ return -ENOTSUPP;
+ if (off >= map->value_size)
+ return -EINVAL;
+
+ *imm = (unsigned long)array->value;
+ return 0;
+}
+
+static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
+ u32 *off)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u64 base = (unsigned long)array->value;
+ u64 range = array->elem_size;
+
+ if (map->max_entries != 1)
+ return -ENOTSUPP;
+ if (imm < base || imm >= base + range)
+ return -ENOENT;
+
+ *off = imm - base;
+ return 0;
+}
+
/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
@@ -360,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
return;
}
- seq_printf(m, "%u: ", *(u32 *)key);
+ if (map->btf_key_type_id)
+ seq_printf(m, "%u: ", *(u32 *)key);
btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
seq_puts(m, "\n");
@@ -397,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map,
{
u32 int_data;
+ /* One exception for keyless BTF: .bss/.data/.rodata map */
+ if (btf_type_is_void(key_type)) {
+ if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+ map->max_entries != 1)
+ return -EINVAL;
+
+ if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
+ return -EINVAL;
+
+ return 0;
+ }
+
if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
@@ -419,6 +463,8 @@ const struct bpf_map_ops array_map_ops = {
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
.map_gen_lookup = array_map_gen_lookup,
+ .map_direct_value_addr = array_map_direct_value_addr,
+ .map_direct_value_meta = array_map_direct_value_meta,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
};
@@ -440,6 +486,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr)
/* only file descriptors can be stored in this type of map */
if (attr->value_size != sizeof(u32))
return -EINVAL;
+ /* Program read-only/write-only not supported for special maps yet. */
+ if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
+ return -EINVAL;
return array_map_alloc_check(attr);
}
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index bd3921b1514b..cad09858a5f2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -185,6 +185,16 @@
i < btf_type_vlen(struct_type); \
i++, member++)
+#define for_each_vsi(i, struct_type, member) \
+ for (i = 0, member = btf_type_var_secinfo(struct_type); \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
+#define for_each_vsi_from(i, from, struct_type, member) \
+ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \
+ i < btf_type_vlen(struct_type); \
+ i++, member++)
+
static DEFINE_IDR(btf_idr);
static DEFINE_SPINLOCK(btf_idr_lock);
@@ -262,6 +272,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
[BTF_KIND_RESTRICT] = "RESTRICT",
[BTF_KIND_FUNC] = "FUNC",
[BTF_KIND_FUNC_PROTO] = "FUNC_PROTO",
+ [BTF_KIND_VAR] = "VAR",
+ [BTF_KIND_DATASEC] = "DATASEC",
};
struct btf_kind_operations {
@@ -314,7 +326,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
return false;
}
-static bool btf_type_is_void(const struct btf_type *t)
+bool btf_type_is_void(const struct btf_type *t)
{
return t == &btf_void;
}
@@ -375,13 +387,36 @@ static bool btf_type_is_int(const struct btf_type *t)
return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
}
+static bool btf_type_is_var(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+static bool btf_type_is_datasec(const struct btf_type *t)
+{
+ return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
+}
+
+/* Types that act only as a source, not sink or intermediate
+ * type when resolving.
+ */
+static bool btf_type_is_resolve_source_only(const struct btf_type *t)
+{
+ return btf_type_is_var(t) ||
+ btf_type_is_datasec(t);
+}
+
/* What types need to be resolved?
*
* btf_type_is_modifier() is an obvious one.
*
* btf_type_is_struct() because its member refers to
* another type (through member->type).
-
+ *
+ * btf_type_is_var() because the variable refers to
+ * another type. btf_type_is_datasec() holds multiple
+ * btf_type_is_var() types that need resolving.
+ *
* btf_type_is_array() because its element (array->type)
* refers to another type. Array can be thought of a
* special case of struct while array just has the same
@@ -390,9 +425,11 @@ static bool btf_type_is_int(const struct btf_type *t)
static bool btf_type_needs_resolve(const struct btf_type *t)
{
return btf_type_is_modifier(t) ||
- btf_type_is_ptr(t) ||
- btf_type_is_struct(t) ||
- btf_type_is_array(t);
+ btf_type_is_ptr(t) ||
+ btf_type_is_struct(t) ||
+ btf_type_is_array(t) ||
+ btf_type_is_var(t) ||
+ btf_type_is_datasec(t);
}
/* t->size can be used */
@@ -403,6 +440,7 @@ static bool btf_type_has_size(const struct btf_type *t)
case BTF_KIND_STRUCT:
case BTF_KIND_UNION:
case BTF_KIND_ENUM:
+ case BTF_KIND_DATASEC:
return true;
}
@@ -467,6 +505,16 @@ static const struct btf_enum *btf_type_enum(const struct btf_type *t)
return (const struct btf_enum *)(t + 1);
}
+static const struct btf_var *btf_type_var(const struct btf_type *t)
+{
+ return (const struct btf_var *)(t + 1);
+}
+
+static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t)
+{
+ return (const struct btf_var_secinfo *)(t + 1);
+}
+
static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
{
return kind_ops[BTF_INFO_KIND(t->info)];
@@ -478,23 +526,31 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
offset < btf->hdr.str_len;
}
-/* Only C-style identifier is permitted. This can be relaxed if
- * necessary.
- */
-static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
+{
+ if ((first ? !isalpha(c) :
+ !isalnum(c)) &&
+ c != '_' &&
+ ((c == '.' && !dot_ok) ||
+ c != '.'))
+ return false;
+ return true;
+}
+
+static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
{
/* offset must be valid */
const char *src = &btf->strings[offset];
const char *src_limit;
- if (!isalpha(*src) && *src != '_')
+ if (!__btf_name_char_ok(*src, true, dot_ok))
return false;
/* set a limit on identifier length */
src_limit = src + KSYM_NAME_LEN;
src++;
while (*src && src < src_limit) {
- if (!isalnum(*src) && *src != '_')
+ if (!__btf_name_char_ok(*src, false, dot_ok))
return false;
src++;
}
@@ -502,6 +558,19 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
return !*src;
}
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+ return __btf_name_valid(btf, offset, false);
+}
+
+static bool btf_name_valid_section(const struct btf *btf, u32 offset)
+{
+ return __btf_name_valid(btf, offset, true);
+}
+
static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!offset)
@@ -697,6 +766,32 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
__btf_verifier_log(log, "\n");
}
+__printf(4, 5)
+static void btf_verifier_log_vsi(struct btf_verifier_env *env,
+ const struct btf_type *datasec_type,
+ const struct btf_var_secinfo *vsi,
+ const char *fmt, ...)
+{
+ struct bpf_verifier_log *log = &env->log;
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+ if (env->phase != CHECK_META)
+ btf_verifier_log_type(env, datasec_type, NULL);
+
+ __btf_verifier_log(log, "\t type_id=%u offset=%u size=%u",
+ vsi->type, vsi->offset, vsi->size);
+ if (fmt && *fmt) {
+ __btf_verifier_log(log, " ");
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+ }
+
+ __btf_verifier_log(log, "\n");
+}
+
static void btf_verifier_log_hdr(struct btf_verifier_env *env,
u32 btf_data_size)
{
@@ -974,7 +1069,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
} else if (btf_type_is_ptr(size_type)) {
size = sizeof(void *);
} else {
- if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+ if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) &&
+ !btf_type_is_var(size_type)))
return NULL;
size = btf->resolved_sizes[size_type_id];
@@ -1509,7 +1605,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
u32 next_type_size = 0;
next_type = btf_type_by_id(btf, next_type_id);
- if (!next_type) {
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
@@ -1542,6 +1638,53 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
return 0;
}
+static int btf_var_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_type *next_type;
+ const struct btf_type *t = v->t;
+ u32 next_type_id = t->type;
+ struct btf *btf = env->btf;
+ u32 next_type_size;
+
+ next_type = btf_type_by_id(btf, next_type_id);
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, next_type) &&
+ !env_type_is_resolved(env, next_type_id))
+ return env_stack_push(env, next_type, next_type_id);
+
+ if (btf_type_is_modifier(next_type)) {
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id;
+
+ resolved_type_id = next_type_id;
+ resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+ if (btf_type_is_ptr(resolved_type) &&
+ !env_type_is_resolve_sink(env, resolved_type) &&
+ !env_type_is_resolved(env, resolved_type_id))
+ return env_stack_push(env, resolved_type,
+ resolved_type_id);
+ }
+
+ /* We must resolve to something concrete at this point, no
+ * forward types or similar that would resolve to size of
+ * zero is allowed.
+ */
+ if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+ btf_verifier_log_type(env, v->t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+ return 0;
+}
+
static int btf_ptr_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
@@ -1551,7 +1694,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
struct btf *btf = env->btf;
next_type = btf_type_by_id(btf, next_type_id);
- if (!next_type) {
+ if (!next_type || btf_type_is_resolve_source_only(next_type)) {
btf_verifier_log_type(env, v->t, "Invalid type_id");
return -EINVAL;
}
@@ -1609,6 +1752,15 @@ static void btf_modifier_seq_show(const struct btf *btf,
btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
}
+static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
+ u32 type_id, void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ t = btf_type_id_resolve(btf, &type_id);
+
+ btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
@@ -1776,7 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->index_type */
index_type_id = array->index_type;
index_type = btf_type_by_id(btf, index_type_id);
- if (btf_type_nosize_or_null(index_type)) {
+ if (btf_type_is_resolve_source_only(index_type) ||
+ btf_type_nosize_or_null(index_type)) {
btf_verifier_log_type(env, v->t, "Invalid index");
return -EINVAL;
}
@@ -1795,7 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->type */
elem_type_id = array->type;
elem_type = btf_type_by_id(btf, elem_type_id);
- if (btf_type_nosize_or_null(elem_type)) {
+ if (btf_type_is_resolve_source_only(elem_type) ||
+ btf_type_nosize_or_null(elem_type)) {
btf_verifier_log_type(env, v->t,
"Invalid elem");
return -EINVAL;
@@ -2016,7 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
const struct btf_type *member_type = btf_type_by_id(env->btf,
member_type_id);
- if (btf_type_nosize_or_null(member_type)) {
+ if (btf_type_is_resolve_source_only(member_type) ||
+ btf_type_nosize_or_null(member_type)) {
btf_verifier_log_member(env, v->t, member,
"Invalid member");
return -EINVAL;
@@ -2411,6 +2566,222 @@ static struct btf_kind_operations func_ops = {
.seq_show = btf_df_seq_show,
};
+static s32 btf_var_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_var *var;
+ u32 meta_needed = sizeof(*var);
+
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen != 0");
+ return -EINVAL;
+ }
+
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
+ if (!t->name_off ||
+ !__btf_name_valid(env->btf, t->name_off, true)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ /* A var cannot be in type void */
+ if (!t->type || !BTF_TYPE_ID_VALID(t->type)) {
+ btf_verifier_log_type(env, t, "Invalid type_id");
+ return -EINVAL;
+ }
+
+ var = btf_type_var(t);
+ if (var->linkage != BTF_VAR_STATIC &&
+ var->linkage != BTF_VAR_GLOBAL_ALLOCATED) {
+ btf_verifier_log_type(env, t, "Linkage not supported");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ return meta_needed;
+}
+
+static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t)
+{
+ const struct btf_var *var = btf_type_var(t);
+
+ btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage);
+}
+
+static const struct btf_kind_operations var_ops = {
+ .check_meta = btf_var_check_meta,
+ .resolve = btf_var_resolve,
+ .check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
+ .log_details = btf_var_log,
+ .seq_show = btf_var_seq_show,
+};
+
+static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
+ const struct btf_type *t,
+ u32 meta_left)
+{
+ const struct btf_var_secinfo *vsi;
+ u64 last_vsi_end_off = 0, sum = 0;
+ u32 i, meta_needed;
+
+ meta_needed = btf_type_vlen(t) * sizeof(*vsi);
+ if (meta_left < meta_needed) {
+ btf_verifier_log_basic(env, t,
+ "meta_left:%u meta_needed:%u",
+ meta_left, meta_needed);
+ return -EINVAL;
+ }
+
+ if (!btf_type_vlen(t)) {
+ btf_verifier_log_type(env, t, "vlen == 0");
+ return -EINVAL;
+ }
+
+ if (!t->size) {
+ btf_verifier_log_type(env, t, "size == 0");
+ return -EINVAL;
+ }
+
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
+ if (!t->name_off ||
+ !btf_name_valid_section(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_type(env, t, NULL);
+
+ for_each_vsi(i, t, vsi) {
+ /* A var cannot be in type void */
+ if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid type_id");
+ return -EINVAL;
+ }
+
+ if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid offset");
+ return -EINVAL;
+ }
+
+ if (!vsi->size || vsi->size > t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid size");
+ return -EINVAL;
+ }
+
+ last_vsi_end_off = vsi->offset + vsi->size;
+ if (last_vsi_end_off > t->size) {
+ btf_verifier_log_vsi(env, t, vsi,
+ "Invalid offset+size");
+ return -EINVAL;
+ }
+
+ btf_verifier_log_vsi(env, t, vsi, NULL);
+ sum += vsi->size;
+ }
+
+ if (t->size < sum) {
+ btf_verifier_log_type(env, t, "Invalid btf_info size");
+ return -EINVAL;
+ }
+
+ return meta_needed;
+}
+
+static int btf_datasec_resolve(struct btf_verifier_env *env,
+ const struct resolve_vertex *v)
+{
+ const struct btf_var_secinfo *vsi;
+ struct btf *btf = env->btf;
+ u16 i;
+
+ for_each_vsi_from(i, v->next_member, v->t, vsi) {
+ u32 var_type_id = vsi->type, type_id, type_size = 0;
+ const struct btf_type *var_type = btf_type_by_id(env->btf,
+ var_type_id);
+ if (!var_type || !btf_type_is_var(var_type)) {
+ btf_verifier_log_vsi(env, v->t, vsi,
+ "Not a VAR kind member");
+ return -EINVAL;
+ }
+
+ if (!env_type_is_resolve_sink(env, var_type) &&
+ !env_type_is_resolved(env, var_type_id)) {
+ env_stack_set_next_member(env, i + 1);
+ return env_stack_push(env, var_type, var_type_id);
+ }
+
+ type_id = var_type->type;
+ if (!btf_type_id_size(btf, &type_id, &type_size)) {
+ btf_verifier_log_vsi(env, v->t, vsi, "Invalid type");
+ return -EINVAL;
+ }
+
+ if (vsi->size < type_size) {
+ btf_verifier_log_vsi(env, v->t, vsi, "Invalid size");
+ return -EINVAL;
+ }
+ }
+
+ env_stack_pop_resolved(env, 0, 0);
+ return 0;
+}
+
+static void btf_datasec_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_datasec_seq_show(const struct btf *btf,
+ const struct btf_type *t, u32 type_id,
+ void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ const struct btf_var_secinfo *vsi;
+ const struct btf_type *var;
+ u32 i;
+
+ seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+ for_each_vsi(i, t, vsi) {
+ var = btf_type_by_id(btf, vsi->type);
+ if (i)
+ seq_puts(m, ",");
+ btf_type_ops(var)->seq_show(btf, var, vsi->type,
+ data + vsi->offset, bits_offset, m);
+ }
+ seq_puts(m, "}");
+}
+
+static const struct btf_kind_operations datasec_ops = {
+ .check_meta = btf_datasec_check_meta,
+ .resolve = btf_datasec_resolve,
+ .check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
+ .log_details = btf_datasec_log,
+ .seq_show = btf_datasec_seq_show,
+};
+
static int btf_func_proto_check(struct btf_verifier_env *env,
const struct btf_type *t)
{
@@ -2542,6 +2913,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
[BTF_KIND_RESTRICT] = &modifier_ops,
[BTF_KIND_FUNC] = &func_ops,
[BTF_KIND_FUNC_PROTO] = &func_proto_ops,
+ [BTF_KIND_VAR] = &var_ops,
+ [BTF_KIND_DATASEC] = &datasec_ops,
};
static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -2622,13 +2995,17 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
if (!env_type_is_resolved(env, type_id))
return false;
- if (btf_type_is_struct(t))
+ if (btf_type_is_struct(t) || btf_type_is_datasec(t))
return !btf->resolved_ids[type_id] &&
- !btf->resolved_sizes[type_id];
+ !btf->resolved_sizes[type_id];
- if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+ if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
+ btf_type_is_var(t)) {
t = btf_type_id_resolve(btf, &type_id);
- return t && !btf_type_is_modifier(t);
+ return t &&
+ !btf_type_is_modifier(t) &&
+ !btf_type_is_var(t) &&
+ !btf_type_is_datasec(t);
}
if (btf_type_is_array(t)) {
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 4e807973aa80..fcde0f7b2585 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -11,7 +11,10 @@
#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
+#include <linux/filter.h>
#include <linux/slab.h>
+#include <linux/sysctl.h>
+#include <linux/string.h>
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <net/sock.h>
@@ -701,7 +704,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
static const struct bpf_func_proto *
-cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
switch (func_id) {
case BPF_FUNC_map_lookup_elem:
@@ -710,6 +713,12 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_update_elem_proto;
case BPF_FUNC_map_delete_elem:
return &bpf_map_delete_elem_proto;
+ case BPF_FUNC_map_push_elem:
+ return &bpf_map_push_elem_proto;
+ case BPF_FUNC_map_pop_elem:
+ return &bpf_map_pop_elem_proto;
+ case BPF_FUNC_map_peek_elem:
+ return &bpf_map_peek_elem_proto;
case BPF_FUNC_get_current_uid_gid:
return &bpf_get_current_uid_gid_proto;
case BPF_FUNC_get_local_storage:
@@ -725,6 +734,12 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
}
}
+static const struct bpf_func_proto *
+cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ return cgroup_base_func_proto(func_id, prog);
+}
+
static bool cgroup_dev_is_valid_access(int off, int size,
enum bpf_access_type type,
const struct bpf_prog *prog,
@@ -762,3 +777,356 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
.get_func_proto = cgroup_dev_func_proto,
.is_valid_access = cgroup_dev_is_valid_access,
};
+
+/**
+ * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl
+ *
+ * @head: sysctl table header
+ * @table: sysctl table
+ * @write: sysctl is being read (= 0) or written (= 1)
+ * @buf: pointer to buffer passed by user space
+ * @pcount: value-result argument: value is size of buffer pointed to by @buf,
+ * result is size of @new_buf if program set new value, initial value
+ * otherwise
+ * @ppos: value-result argument: value is position at which read from or write
+ * to sysctl is happening, result is new position if program overrode it,
+ * initial value otherwise
+ * @new_buf: pointer to pointer to new buffer that will be allocated if program
+ * overrides new value provided by user space on sysctl write
+ * NOTE: it's caller responsibility to free *new_buf if it was set
+ * @type: type of program to be executed
+ *
+ * Program is run when sysctl is being accessed, either read or written, and
+ * can allow or deny such access.
+ *
+ * This function will return %-EPERM if an attached program is found and
+ * returned value != 1 during execution. In all other cases 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+ struct ctl_table *table, int write,
+ void __user *buf, size_t *pcount,
+ loff_t *ppos, void **new_buf,
+ enum bpf_attach_type type)
+{
+ struct bpf_sysctl_kern ctx = {
+ .head = head,
+ .table = table,
+ .write = write,
+ .ppos = ppos,
+ .cur_val = NULL,
+ .cur_len = PAGE_SIZE,
+ .new_val = NULL,
+ .new_len = 0,
+ .new_updated = 0,
+ };
+ struct cgroup *cgrp;
+ int ret;
+
+ ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
+ if (ctx.cur_val) {
+ mm_segment_t old_fs;
+ loff_t pos = 0;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ if (table->proc_handler(table, 0, (void __user *)ctx.cur_val,
+ &ctx.cur_len, &pos)) {
+ /* Let BPF program decide how to proceed. */
+ ctx.cur_len = 0;
+ }
+ set_fs(old_fs);
+ } else {
+ /* Let BPF program decide how to proceed. */
+ ctx.cur_len = 0;
+ }
+
+ if (write && buf && *pcount) {
+ /* BPF program should be able to override new value with a
+ * buffer bigger than provided by user.
+ */
+ ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
+ ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount);
+ if (!ctx.new_val ||
+ copy_from_user(ctx.new_val, buf, ctx.new_len))
+ /* Let BPF program decide how to proceed. */
+ ctx.new_len = 0;
+ }
+
+ rcu_read_lock();
+ cgrp = task_dfl_cgroup(current);
+ ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
+ rcu_read_unlock();
+
+ kfree(ctx.cur_val);
+
+ if (ret == 1 && ctx.new_updated) {
+ *new_buf = ctx.new_val;
+ *pcount = ctx.new_len;
+ } else {
+ kfree(ctx.new_val);
+ }
+
+ return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
+
+static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
+ size_t *lenp)
+{
+ ssize_t tmp_ret = 0, ret;
+
+ if (dir->header.parent) {
+ tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp);
+ if (tmp_ret < 0)
+ return tmp_ret;
+ }
+
+ ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp);
+ if (ret < 0)
+ return ret;
+ *bufp += ret;
+ *lenp -= ret;
+ ret += tmp_ret;
+
+ /* Avoid leading slash. */
+ if (!ret)
+ return ret;
+
+ tmp_ret = strscpy(*bufp, "/", *lenp);
+ if (tmp_ret < 0)
+ return tmp_ret;
+ *bufp += tmp_ret;
+ *lenp -= tmp_ret;
+
+ return ret + tmp_ret;
+}
+
+BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf,
+ size_t, buf_len, u64, flags)
+{
+ ssize_t tmp_ret = 0, ret;
+
+ if (!buf)
+ return -EINVAL;
+
+ if (!(flags & BPF_F_SYSCTL_BASE_NAME)) {
+ if (!ctx->head)
+ return -EINVAL;
+ tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len);
+ if (tmp_ret < 0)
+ return tmp_ret;
+ }
+
+ ret = strscpy(buf, ctx->table->procname, buf_len);
+
+ return ret < 0 ? ret : tmp_ret + ret;
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
+ .func = bpf_sysctl_get_name,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+static int copy_sysctl_value(char *dst, size_t dst_len, char *src,
+ size_t src_len)
+{
+ if (!dst)
+ return -EINVAL;
+
+ if (!dst_len)
+ return -E2BIG;
+
+ if (!src || !src_len) {
+ memset(dst, 0, dst_len);
+ return -EINVAL;
+ }
+
+ memcpy(dst, src, min(dst_len, src_len));
+
+ if (dst_len > src_len) {
+ memset(dst + src_len, '\0', dst_len - src_len);
+ return src_len;
+ }
+
+ dst[dst_len - 1] = '\0';
+
+ return -E2BIG;
+}
+
+BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx,
+ char *, buf, size_t, buf_len)
+{
+ return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
+ .func = bpf_sysctl_get_current_value,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf,
+ size_t, buf_len)
+{
+ if (!ctx->write) {
+ if (buf && buf_len)
+ memset(buf, '\0', buf_len);
+ return -EINVAL;
+ }
+ return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = {
+ .func = bpf_sysctl_get_new_value,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx,
+ const char *, buf, size_t, buf_len)
+{
+ if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len)
+ return -EINVAL;
+
+ if (buf_len > PAGE_SIZE - 1)
+ return -E2BIG;
+
+ memcpy(ctx->new_val, buf, buf_len);
+ ctx->new_len = buf_len;
+ ctx->new_updated = 1;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
+ .func = bpf_sysctl_set_new_value,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+};
+
+static const struct bpf_func_proto *
+sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_strtol:
+ return &bpf_strtol_proto;
+ case BPF_FUNC_strtoul:
+ return &bpf_strtoul_proto;
+ case BPF_FUNC_sysctl_get_name:
+ return &bpf_sysctl_get_name_proto;
+ case BPF_FUNC_sysctl_get_current_value:
+ return &bpf_sysctl_get_current_value_proto;
+ case BPF_FUNC_sysctl_get_new_value:
+ return &bpf_sysctl_get_new_value_proto;
+ case BPF_FUNC_sysctl_set_new_value:
+ return &bpf_sysctl_set_new_value_proto;
+ default:
+ return cgroup_base_func_proto(func_id, prog);
+ }
+}
+
+static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ const int size_default = sizeof(__u32);
+
+ if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size)
+ return false;
+
+ switch (off) {
+ case offsetof(struct bpf_sysctl, write):
+ if (type != BPF_READ)
+ return false;
+ bpf_ctx_record_field_size(info, size_default);
+ return bpf_ctx_narrow_access_ok(off, size, size_default);
+ case offsetof(struct bpf_sysctl, file_pos):
+ if (type == BPF_READ) {
+ bpf_ctx_record_field_size(info, size_default);
+ return bpf_ctx_narrow_access_ok(off, size, size_default);
+ } else {
+ return size == size_default;
+ }
+ default:
+ return false;
+ }
+}
+
+static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
+ const struct bpf_insn *si,
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog, u32 *target_size)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ switch (si->off) {
+ case offsetof(struct bpf_sysctl, write):
+ *insn++ = BPF_LDX_MEM(
+ BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+ bpf_target_off(struct bpf_sysctl_kern, write,
+ FIELD_SIZEOF(struct bpf_sysctl_kern,
+ write),
+ target_size));
+ break;
+ case offsetof(struct bpf_sysctl, file_pos):
+ /* ppos is a pointer so it should be accessed via indirect
+ * loads and stores. Also for stores additional temporary
+ * register is used since neither src_reg nor dst_reg can be
+ * overridden.
+ */
+ if (type == BPF_WRITE) {
+ int treg = BPF_REG_9;
+
+ if (si->src_reg == treg || si->dst_reg == treg)
+ --treg;
+ if (si->src_reg == treg || si->dst_reg == treg)
+ --treg;
+ *insn++ = BPF_STX_MEM(
+ BPF_DW, si->dst_reg, treg,
+ offsetof(struct bpf_sysctl_kern, tmp_reg));
+ *insn++ = BPF_LDX_MEM(
+ BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+ treg, si->dst_reg,
+ offsetof(struct bpf_sysctl_kern, ppos));
+ *insn++ = BPF_STX_MEM(
+ BPF_SIZEOF(u32), treg, si->src_reg, 0);
+ *insn++ = BPF_LDX_MEM(
+ BPF_DW, treg, si->dst_reg,
+ offsetof(struct bpf_sysctl_kern, tmp_reg));
+ } else {
+ *insn++ = BPF_LDX_MEM(
+ BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sysctl_kern, ppos));
+ *insn++ = BPF_LDX_MEM(
+ BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0);
+ }
+ *target_size = sizeof(u32);
+ break;
+ }
+
+ return insn - insn_buf;
+}
+
+const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
+ .get_func_proto = sysctl_func_proto,
+ .is_valid_access = sysctl_is_valid_access,
+ .convert_ctx_access = sysctl_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_sysctl_prog_ops = {
+};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c605397c79f0..3ba56e73c90e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
dst[i] = fp->insnsi[i];
if (!was_ld_map &&
dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
- dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+ (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
+ dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
was_ld_map = true;
dst[i].imm = 0;
} else if (was_ld_map &&
@@ -438,6 +439,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
const u32 cnt_max = S16_MAX;
struct bpf_prog *prog_adj;
+ int err;
/* Since our patchlet doesn't expand the image, we're done. */
if (insn_delta == 0) {
@@ -453,8 +455,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
* we afterwards may not fail anymore.
*/
if (insn_adj_cnt > cnt_max &&
- bpf_adj_branches(prog, off, off + 1, off + len, true))
- return NULL;
+ (err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
+ return ERR_PTR(err);
/* Several new instructions need to be inserted. Make room
* for them. Likely, there's no need for a new allocation as
@@ -463,7 +465,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
GFP_USER);
if (!prog_adj)
- return NULL;
+ return ERR_PTR(-ENOMEM);
prog_adj->len = insn_adj_cnt;
@@ -1095,13 +1097,13 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
continue;
tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
- if (!tmp) {
+ if (IS_ERR(tmp)) {
/* Patching may have repointed aux->prog during
* realloc from the original one, so we need to
* fix it up here on error.
*/
bpf_jit_prog_release_other(prog, clone);
- return ERR_PTR(-ENOMEM);
+ return tmp;
}
clone = tmp;
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 3c18260403dd..cf727d77c6c6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -160,12 +160,12 @@ static void cpu_map_kthread_stop(struct work_struct *work)
}
static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
- struct xdp_frame *xdpf)
+ struct xdp_frame *xdpf,
+ struct sk_buff *skb)
{
unsigned int hard_start_headroom;
unsigned int frame_size;
void *pkt_data_start;
- struct sk_buff *skb;
/* Part of headroom was reserved to xdpf */
hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom;
@@ -191,8 +191,8 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
pkt_data_start = xdpf->data - hard_start_headroom;
- skb = build_skb(pkt_data_start, frame_size);
- if (!skb)
+ skb = build_skb_around(skb, pkt_data_start, frame_size);
+ if (unlikely(!skb))
return NULL;
skb_reserve(skb, hard_start_headroom);
@@ -240,6 +240,8 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
}
}
+#define CPUMAP_BATCH 8
+
static int cpu_map_kthread_run(void *data)
{
struct bpf_cpu_map_entry *rcpu = data;
@@ -252,8 +254,11 @@ static int cpu_map_kthread_run(void *data)
* kthread_stop signal until queue is empty.
*/
while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
- unsigned int processed = 0, drops = 0, sched = 0;
- struct xdp_frame *xdpf;
+ unsigned int drops = 0, sched = 0;
+ void *frames[CPUMAP_BATCH];
+ void *skbs[CPUMAP_BATCH];
+ gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
+ int i, n, m;
/* Release CPU reschedule checks */
if (__ptr_ring_empty(rcpu->queue)) {
@@ -269,18 +274,38 @@ static int cpu_map_kthread_run(void *data)
sched = cond_resched();
}
- /* Process packets in rcpu->queue */
- local_bh_disable();
/*
* The bpf_cpu_map_entry is single consumer, with this
* kthread CPU pinned. Lockless access to ptr_ring
* consume side valid as no-resize allowed of queue.
*/
- while ((xdpf = __ptr_ring_consume(rcpu->queue))) {
- struct sk_buff *skb;
+ n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
+
+ for (i = 0; i < n; i++) {
+ void *f = frames[i];
+ struct page *page = virt_to_page(f);
+
+ /* Bring struct page memory area to curr CPU. Read by
+ * build_skb_around via page_is_pfmemalloc(), and when
+ * freed written by page_frag_free call.
+ */
+ prefetchw(page);
+ }
+
+ m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs);
+ if (unlikely(m == 0)) {
+ for (i = 0; i < n; i++)
+ skbs[i] = NULL; /* effect: xdp_return_frame */
+ drops = n;
+ }
+
+ local_bh_disable();
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ struct sk_buff *skb = skbs[i];
int ret;
- skb = cpu_map_build_skb(rcpu, xdpf);
+ skb = cpu_map_build_skb(rcpu, xdpf, skb);
if (!skb) {
xdp_return_frame(xdpf);
continue;
@@ -290,13 +315,9 @@ static int cpu_map_kthread_run(void *data)
ret = netif_receive_skb_core(skb);
if (ret == NET_RX_DROP)
drops++;
-
- /* Limit BH-disable period */
- if (++processed == 8)
- break;
}
/* Feedback loop via tracepoint */
- trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+ trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
local_bh_enable(); /* resched point, may call do_softirq() */
}
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index de73f55e42fd..d9ce383c0f9c 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
* part of the ldimm64 insn is accessible.
*/
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
- bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+ bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD ||
+ insn->src_reg == BPF_PSEUDO_MAP_VALUE;
char tmp[64];
- if (map_ptr && !allow_ptr_leaks)
+ if (is_ptr && !allow_ptr_leaks)
imm = 0;
verbose(cbs->private_data, "(%02x) r%d = %s\n",
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fed15cf94dca..192d32e77db3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -23,7 +23,7 @@
#define HTAB_CREATE_FLAG_MASK \
(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
+ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
struct bucket {
struct hlist_nulls_head head;
@@ -262,8 +262,8 @@ static int htab_map_alloc_check(union bpf_attr *attr)
/* Guard against local DoS, and discourage production use. */
return -EPERM;
- if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
- /* reserved bits should not be used */
+ if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (!lru && percpu_lru)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a411fc17d265..4266ffde07ca 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -18,6 +18,9 @@
#include <linux/sched.h>
#include <linux/uidgid.h>
#include <linux/filter.h>
+#include <linux/ctype.h>
+
+#include "../../lib/kstrtox.h"
/* If kernel subsystem is allowing eBPF programs to call this function,
* inside its own verifier_ops->get_func_proto() callback it should return
@@ -363,4 +366,132 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
.arg2_type = ARG_ANYTHING,
};
#endif
+
+#define BPF_STRTOX_BASE_MASK 0x1F
+
+static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags,
+ unsigned long long *res, bool *is_negative)
+{
+ unsigned int base = flags & BPF_STRTOX_BASE_MASK;
+ const char *cur_buf = buf;
+ size_t cur_len = buf_len;
+ unsigned int consumed;
+ size_t val_len;
+ char str[64];
+
+ if (!buf || !buf_len || !res || !is_negative)
+ return -EINVAL;
+
+ if (base != 0 && base != 8 && base != 10 && base != 16)
+ return -EINVAL;
+
+ if (flags & ~BPF_STRTOX_BASE_MASK)
+ return -EINVAL;
+
+ while (cur_buf < buf + buf_len && isspace(*cur_buf))
+ ++cur_buf;
+
+ *is_negative = (cur_buf < buf + buf_len && *cur_buf == '-');
+ if (*is_negative)
+ ++cur_buf;
+
+ consumed = cur_buf - buf;
+ cur_len -= consumed;
+ if (!cur_len)
+ return -EINVAL;
+
+ cur_len = min(cur_len, sizeof(str) - 1);
+ memcpy(str, cur_buf, cur_len);
+ str[cur_len] = '\0';
+ cur_buf = str;
+
+ cur_buf = _parse_integer_fixup_radix(cur_buf, &base);
+ val_len = _parse_integer(cur_buf, base, res);
+
+ if (val_len & KSTRTOX_OVERFLOW)
+ return -ERANGE;
+
+ if (val_len == 0)
+ return -EINVAL;
+
+ cur_buf += val_len;
+ consumed += cur_buf - str;
+
+ return consumed;
+}
+
+static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
+ long long *res)
+{
+ unsigned long long _res;
+ bool is_negative;
+ int err;
+
+ err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+ if (err < 0)
+ return err;
+ if (is_negative) {
+ if ((long long)-_res > 0)
+ return -ERANGE;
+ *res = -_res;
+ } else {
+ if ((long long)_res < 0)
+ return -ERANGE;
+ *res = _res;
+ }
+ return err;
+}
+
+BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
+ long *, res)
+{
+ long long _res;
+ int err;
+
+ err = __bpf_strtoll(buf, buf_len, flags, &_res);
+ if (err < 0)
+ return err;
+ if (_res != (long)_res)
+ return -ERANGE;
+ *res = _res;
+ return err;
+}
+
+const struct bpf_func_proto bpf_strtol_proto = {
+ .func = bpf_strtol,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
+ unsigned long *, res)
+{
+ unsigned long long _res;
+ bool is_negative;
+ int err;
+
+ err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+ if (err < 0)
+ return err;
+ if (is_negative)
+ return -EINVAL;
+ if (_res != (unsigned long)_res)
+ return -ERANGE;
+ *res = _res;
+ return err;
+}
+
+const struct bpf_func_proto bpf_strtoul_proto = {
+ .func = bpf_strtoul,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_LONG,
+};
#endif
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 6b572e2de7fb..980e8f1f6cb5 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -14,7 +14,7 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO
#ifdef CONFIG_CGROUP_BPF
#define LOCAL_STORAGE_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_cgroup_storage_map {
struct bpf_map map;
@@ -282,8 +282,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
if (attr->value_size > PAGE_SIZE)
return ERR_PTR(-E2BIG);
- if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
- /* reserved bits should not be used */
+ if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return ERR_PTR(-EINVAL);
if (attr->max_entries)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 93a5cbbde421..e61630c2e50b 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -538,7 +538,7 @@ out:
#define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \
- BPF_F_RDONLY | BPF_F_WRONLY)
+ BPF_F_ACCESS_MASK)
static struct bpf_map *trie_alloc(union bpf_attr *attr)
{
@@ -553,6 +553,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
if (attr->max_entries == 0 ||
!(attr->map_flags & BPF_F_NO_PREALLOC) ||
attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags) ||
attr->key_size < LPM_KEY_SIZE_MIN ||
attr->key_size > LPM_KEY_SIZE_MAX ||
attr->value_size < LPM_VAL_SIZE_MIN ||
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index b384ea9f3254..0b140d236889 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -11,8 +11,7 @@
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
- (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
-
+ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
struct bpf_queue_stack {
struct bpf_map map;
@@ -52,7 +51,8 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr)
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 0 ||
attr->value_size == 0 ||
- attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+ attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
+ !bpf_map_flags_access_ok(attr->map_flags))
return -EINVAL;
if (attr->value_size > KMALLOC_MAX_SIZE)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index afca36f53c49..ad3ccf82f31d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -166,13 +166,25 @@ void bpf_map_area_free(void *area)
kvfree(area);
}
+static u32 bpf_map_flags_retain_permanent(u32 flags)
+{
+ /* Some map creation flags are not tied to the map object but
+ * rather to the map fd instead, so they have no meaning upon
+ * map object inspection since multiple file descriptors with
+ * different (access) properties can exist here. Thus, given
+ * this has zero meaning for the map itself, lets clear these
+ * from here.
+ */
+ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY);
+}
+
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
{
map->map_type = attr->map_type;
map->key_size = attr->key_size;
map->value_size = attr->value_size;
map->max_entries = attr->max_entries;
- map->map_flags = attr->map_flags;
+ map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
map->numa_node = bpf_map_attr_numa_node(attr);
}
@@ -343,6 +355,18 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
return 0;
}
+static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
+{
+ fmode_t mode = f.file->f_mode;
+
+ /* Our file permissions may have been overridden by global
+ * map permissions facing syscall side.
+ */
+ if (READ_ONCE(map->frozen))
+ mode &= ~FMODE_CAN_WRITE;
+ return mode;
+}
+
#ifdef CONFIG_PROC_FS
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
@@ -364,14 +388,16 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
"memlock:\t%llu\n"
- "map_id:\t%u\n",
+ "map_id:\t%u\n"
+ "frozen:\t%u\n",
map->map_type,
map->key_size,
map->value_size,
map->max_entries,
map->map_flags,
map->pages * 1ULL << PAGE_SHIFT,
- map->id);
+ map->id,
+ READ_ONCE(map->frozen));
if (owner_prog_type) {
seq_printf(m, "owner_prog_type:\t%u\n",
@@ -448,10 +474,10 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
const char *end = src + BPF_OBJ_NAME_LEN;
memset(dst, 0, BPF_OBJ_NAME_LEN);
-
- /* Copy all isalnum() and '_' char */
+ /* Copy all isalnum(), '_' and '.' chars. */
while (src < end && *src) {
- if (!isalnum(*src) && *src != '_')
+ if (!isalnum(*src) &&
+ *src != '_' && *src != '.')
return -EINVAL;
*dst++ = *src++;
}
@@ -478,9 +504,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
u32 key_size, value_size;
int ret = 0;
- key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
- if (!key_type || key_size != map->key_size)
- return -EINVAL;
+ /* Some maps allow key to be unspecified. */
+ if (btf_key_id) {
+ key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+ if (!key_type || key_size != map->key_size)
+ return -EINVAL;
+ } else {
+ key_type = btf_type_by_id(btf, 0);
+ if (!map->ops->map_check_btf)
+ return -EINVAL;
+ }
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
if (!value_type || value_size != map->value_size)
@@ -489,9 +522,12 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
map->spin_lock_off = btf_find_spin_lock(btf, value_type);
if (map_value_has_spin_lock(map)) {
+ if (map->map_flags & BPF_F_RDONLY_PROG)
+ return -EACCES;
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY &&
- map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_SK_STORAGE)
return -ENOTSUPP;
if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
map->value_size) {
@@ -545,7 +581,7 @@ static int map_create(union bpf_attr *attr)
if (attr->btf_key_type_id || attr->btf_value_type_id) {
struct btf *btf;
- if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
+ if (!attr->btf_value_type_id) {
err = -EINVAL;
goto free_map_nouncharge;
}
@@ -713,8 +749,7 @@ static int map_lookup_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
@@ -843,8 +878,7 @@ static int map_update_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -955,8 +989,7 @@ static int map_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -1007,8 +1040,7 @@ static int map_get_next_key(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_READ)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
@@ -1075,8 +1107,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -1118,6 +1149,36 @@ err_put:
return err;
}
+#define BPF_MAP_FREEZE_LAST_FIELD map_fd
+
+static int map_freeze(const union bpf_attr *attr)
+{
+ int err = 0, ufd = attr->map_fd;
+ struct bpf_map *map;
+ struct fd f;
+
+ if (CHECK_ATTR(BPF_MAP_FREEZE))
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+ if (READ_ONCE(map->frozen)) {
+ err = -EBUSY;
+ goto err_put;
+ }
+ if (!capable(CAP_SYS_ADMIN)) {
+ err = -EPERM;
+ goto err_put;
+ }
+
+ WRITE_ONCE(map->frozen, true);
+err_put:
+ fdput(f);
+ return err;
+}
+
static const struct bpf_prog_ops * const bpf_prog_types[] = {
#define BPF_PROG_TYPE(_id, _name) \
[_id] = & _name ## _prog_ops,
@@ -1557,7 +1618,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license);
- if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+ if (attr->insn_cnt == 0 ||
+ attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
return -E2BIG;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
@@ -1728,12 +1790,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
}
raw_tp->btp = btp;
- prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
- BPF_PROG_TYPE_RAW_TRACEPOINT);
+ prog = bpf_prog_get(attr->raw_tracepoint.prog_fd);
if (IS_ERR(prog)) {
err = PTR_ERR(prog);
goto out_free_tp;
}
+ if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+ prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
+ err = -EINVAL;
+ goto out_put_prog;
+ }
err = bpf_probe_register(raw_tp->btp, prog);
if (err)
@@ -1827,6 +1893,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_FLOW_DISSECTOR:
ptype = BPF_PROG_TYPE_FLOW_DISSECTOR;
break;
+ case BPF_CGROUP_SYSCTL:
+ ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
+ break;
default:
return -EINVAL;
}
@@ -1905,6 +1974,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
return lirc_prog_detach(attr);
case BPF_FLOW_DISSECTOR:
return skb_flow_dissector_bpf_prog_detach(attr);
+ case BPF_CGROUP_SYSCTL:
+ ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
+ break;
default:
return -EINVAL;
}
@@ -1938,9 +2010,12 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_UDP6_SENDMSG:
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
+ case BPF_CGROUP_SYSCTL:
break;
case BPF_LIRC_MODE2:
return lirc_prog_query(attr, uattr);
+ case BPF_FLOW_DISSECTOR:
+ return skb_flow_dissector_prog_query(attr, uattr);
default:
return -EINVAL;
}
@@ -1948,7 +2023,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
return cgroup_bpf_prog_query(attr, uattr);
}
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
static int bpf_prog_test_run(const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -1961,6 +2036,14 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
if (CHECK_ATTR(BPF_PROG_TEST_RUN))
return -EINVAL;
+ if ((attr->test.ctx_size_in && !attr->test.ctx_in) ||
+ (!attr->test.ctx_size_in && attr->test.ctx_in))
+ return -EINVAL;
+
+ if ((attr->test.ctx_size_out && !attr->test.ctx_out) ||
+ (!attr->test.ctx_size_out && attr->test.ctx_out))
+ return -EINVAL;
+
prog = bpf_prog_get(attr->test.prog_fd);
if (IS_ERR(prog))
return PTR_ERR(prog);
@@ -2071,13 +2154,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
}
static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
- unsigned long addr)
+ unsigned long addr, u32 *off,
+ u32 *type)
{
+ const struct bpf_map *map;
int i;
- for (i = 0; i < prog->aux->used_map_cnt; i++)
- if (prog->aux->used_maps[i] == (void *)addr)
- return prog->aux->used_maps[i];
+ for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
+ map = prog->aux->used_maps[i];
+ if (map == (void *)addr) {
+ *type = BPF_PSEUDO_MAP_FD;
+ return map;
+ }
+ if (!map->ops->map_direct_value_meta)
+ continue;
+ if (!map->ops->map_direct_value_meta(map, addr, off)) {
+ *type = BPF_PSEUDO_MAP_VALUE;
+ return map;
+ }
+ }
+
return NULL;
}
@@ -2085,6 +2181,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
{
const struct bpf_map *map;
struct bpf_insn *insns;
+ u32 off, type;
u64 imm;
int i;
@@ -2112,11 +2209,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
continue;
imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
- map = bpf_map_from_imm(prog, imm);
+ map = bpf_map_from_imm(prog, imm, &off, &type);
if (map) {
- insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+ insns[i].src_reg = type;
insns[i].imm = map->id;
- insns[i + 1].imm = 0;
+ insns[i + 1].imm = off;
continue;
}
}
@@ -2706,6 +2803,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_MAP_GET_NEXT_KEY:
err = map_get_next_key(&attr);
break;
+ case BPF_MAP_FREEZE:
+ err = map_freeze(&attr);
+ break;
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr, uattr);
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 09d5d972c9ff..7b05e8938d5c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -176,7 +176,6 @@ struct bpf_verifier_stack_elem {
struct bpf_verifier_stack_elem *next;
};
-#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
#define BPF_COMPLEXITY_LIMIT_STATES 64
@@ -377,7 +376,8 @@ static bool is_release_function(enum bpf_func_id func_id)
static bool is_acquire_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_lookup_tcp ||
- func_id == BPF_FUNC_sk_lookup_udp;
+ func_id == BPF_FUNC_sk_lookup_udp ||
+ func_id == BPF_FUNC_skc_lookup_tcp;
}
static bool is_ptr_cast_function(enum bpf_func_id func_id)
@@ -405,6 +405,7 @@ static const char * const reg_type_str[] = {
[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
[PTR_TO_TCP_SOCK] = "tcp_sock",
[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
+ [PTR_TO_TP_BUFFER] = "tp_buffer",
};
static char slot_type_char[] = {
@@ -1091,7 +1092,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
*/
subprog[env->subprog_cnt].start = insn_cnt;
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, subprog[i].start);
@@ -1138,6 +1139,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
struct bpf_reg_state *parent)
{
bool writes = parent == state->parent; /* Observe write marks */
+ int cnt = 0;
while (parent) {
/* if read wasn't screened by an earlier write ... */
@@ -1149,12 +1151,25 @@ static int mark_reg_read(struct bpf_verifier_env *env,
parent->var_off.value, parent->off);
return -EFAULT;
}
+ if (parent->live & REG_LIVE_READ)
+ /* The parentage chain never changes and
+ * this parent was already marked as LIVE_READ.
+ * There is no need to keep walking the chain again and
+ * keep re-marking all parents as LIVE_READ.
+ * This case happens when the same register is read
+ * multiple times without writes into it in-between.
+ */
+ break;
/* ... then we depend on parent's value */
parent->live |= REG_LIVE_READ;
state = parent;
parent = state->parent;
writes = true;
+ cnt++;
}
+
+ if (env->longest_mark_read_walk < cnt)
+ env->longest_mark_read_walk = cnt;
return 0;
}
@@ -1163,30 +1178,32 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *regs = state->regs;
+ struct bpf_reg_state *reg, *regs = state->regs;
if (regno >= MAX_BPF_REG) {
verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
+ reg = &regs[regno];
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
- if (regs[regno].type == NOT_INIT) {
+ if (reg->type == NOT_INIT) {
verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
/* We don't need to worry about FP liveness because it's read-only */
- if (regno != BPF_REG_FP)
- return mark_reg_read(env, &regs[regno],
- regs[regno].parent);
+ if (regno == BPF_REG_FP)
+ return 0;
+
+ return mark_reg_read(env, reg, reg->parent);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose(env, "frame pointer is read only\n");
return -EACCES;
}
- regs[regno].live |= REG_LIVE_WRITTEN;
+ reg->live |= REG_LIVE_WRITTEN;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
@@ -1412,7 +1429,7 @@ static int check_stack_access(struct bpf_verifier_env *env,
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "variable stack access var_off=%s off=%d size=%d",
+ verbose(env, "variable stack access var_off=%s off=%d size=%d\n",
tn_buf, off, size);
return -EACCES;
}
@@ -1425,6 +1442,28 @@ static int check_stack_access(struct bpf_verifier_env *env,
return 0;
}
+static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, enum bpf_access_type type)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map = regs[regno].map_ptr;
+ u32 cap = bpf_map_flags_to_cap(map);
+
+ if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
+ verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+
+ if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
+ verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
/* check read/write into map element returned by bpf_map_lookup_elem() */
static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
int size, bool zero_size_allowed)
@@ -1454,7 +1493,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, state);
/* The minimum value is only important with signed
@@ -1955,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env,
return 0;
}
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ int regno, int off, int size)
+{
+ if (off < 0) {
+ verbose(env,
+ "R%d invalid tracepoint buffer access: off=%d, size=%d",
+ regno, off, size);
+ return -EACCES;
+ }
+ if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env,
+ "R%d invalid variable buffer offset: off=%d, var_off=%s",
+ regno, off, tn_buf);
+ return -EACCES;
+ }
+ if (off + size > env->prog->aux->max_tp_access)
+ env->prog->aux->max_tp_access = off + size;
+
+ return 0;
+}
+
+
/* truncate register to smaller size (in bytes)
* must be called with size < BPF_REG_SIZE
*/
@@ -2011,7 +2076,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
-
+ err = check_map_access_type(env, regno, off, size, t);
+ if (err)
+ return err;
err = check_map_access(env, regno, off, size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
@@ -2097,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
err = check_sock_access(env, insn_idx, regno, off, size, t);
if (!err && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_TP_BUFFER) {
+ err = check_tp_buffer_access(env, reg, regno, off, size);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
} else {
verbose(env, "R%d invalid mem access '%s'\n", regno,
reg_type_str[reg->type]);
@@ -2157,6 +2228,29 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}
+static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
+ int off, int access_size,
+ bool zero_size_allowed)
+{
+ struct bpf_reg_state *reg = reg_state(env, regno);
+
+ if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+ access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
+ regno, off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n",
+ regno, tn_buf, access_size);
+ }
+ return -EACCES;
+ }
+ return 0;
+}
+
/* when register 'regno' is passed into function that will read 'access_size'
* bytes from that pointer, make sure that it's within stack boundary
* and all elements of stack are initialized.
@@ -2169,7 +2263,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
{
struct bpf_reg_state *reg = reg_state(env, regno);
struct bpf_func_state *state = func(env, reg);
- int off, i, slot, spi;
+ int err, min_off, max_off, i, slot, spi;
if (reg->type != PTR_TO_STACK) {
/* Allow zero-byte read from NULL, regardless of pointer type */
@@ -2183,21 +2277,57 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
return -EACCES;
}
- /* Only allow fixed-offset stack reads */
- if (!tnum_is_const(reg->var_off)) {
- char tn_buf[48];
+ if (tnum_is_const(reg->var_off)) {
+ min_off = max_off = reg->var_off.value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err)
+ return err;
+ } else {
+ /* Variable offset is prohibited for unprivileged mode for
+ * simplicity since it requires corresponding support in
+ * Spectre masking for stack ALU.
+ * See also retrieve_ptr_limit().
+ */
+ if (!env->allow_ptr_leaks) {
+ char tn_buf[48];
- tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "invalid variable stack read R%d var_off=%s\n",
- regno, tn_buf);
- return -EACCES;
- }
- off = reg->off + reg->var_off.value;
- if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
- access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
- verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
- regno, off, access_size);
- return -EACCES;
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n",
+ regno, tn_buf);
+ return -EACCES;
+ }
+ /* Only initialized buffer on stack is allowed to be accessed
+ * with variable offset. With uninitialized buffer it's hard to
+ * guarantee that whole memory is marked as initialized on
+ * helper return since specific bounds are unknown what may
+ * cause uninitialized stack leaking.
+ */
+ if (meta && meta->raw_mode)
+ meta = NULL;
+
+ if (reg->smax_value >= BPF_MAX_VAR_OFF ||
+ reg->smax_value <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "R%d unbounded indirect variable offset stack access\n",
+ regno);
+ return -EACCES;
+ }
+ min_off = reg->smin_value + reg->off;
+ max_off = reg->smax_value + reg->off;
+ err = __check_stack_boundary(env, regno, min_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d min value is outside of stack bound\n",
+ regno);
+ return err;
+ }
+ err = __check_stack_boundary(env, regno, max_off, access_size,
+ zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d max value is outside of stack bound\n",
+ regno);
+ return err;
+ }
}
if (meta && meta->raw_mode) {
@@ -2206,10 +2336,10 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
return 0;
}
- for (i = 0; i < access_size; i++) {
+ for (i = min_off; i < max_off + access_size; i++) {
u8 *stype;
- slot = -(off + i) - 1;
+ slot = -i - 1;
spi = slot / BPF_REG_SIZE;
if (state->allocated_stack <= slot)
goto err;
@@ -2222,8 +2352,16 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
goto mark;
}
err:
- verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
- off, i, access_size);
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
+ min_off, i - min_off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n",
+ tn_buf, i - min_off, access_size);
+ }
return -EACCES;
mark:
/* reading any byte out of 8-byte 'spill_slot' will cause
@@ -2232,7 +2370,7 @@ mark:
mark_reg_read(env, &state->stack[spi].spilled_ptr,
state->stack[spi].spilled_ptr.parent);
}
- return update_stack_depth(env, state, off);
+ return update_stack_depth(env, state, min_off);
}
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
@@ -2247,6 +2385,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_VALUE:
+ if (check_map_access_type(env, regno, reg->off, access_size,
+ meta && meta->raw_mode ? BPF_WRITE :
+ BPF_READ))
+ return -EACCES;
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
default: /* scalar_value|ptr_to_stack or invalid ptr */
@@ -2353,6 +2495,22 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
type == ARG_CONST_SIZE_OR_ZERO;
}
+static bool arg_type_is_int_ptr(enum bpf_arg_type type)
+{
+ return type == ARG_PTR_TO_INT ||
+ type == ARG_PTR_TO_LONG;
+}
+
+static int int_ptr_type_to_size(enum bpf_arg_type type)
+{
+ if (type == ARG_PTR_TO_INT)
+ return sizeof(u32);
+ else if (type == ARG_PTR_TO_LONG)
+ return sizeof(u64);
+
+ return -EINVAL;
+}
+
static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
struct bpf_call_arg_meta *meta)
@@ -2385,10 +2543,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
if (arg_type == ARG_PTR_TO_MAP_KEY ||
arg_type == ARG_PTR_TO_MAP_VALUE ||
- arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+ arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
+ arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
expected_type = PTR_TO_STACK;
- if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
- type != expected_type)
+ if (register_is_null(reg) &&
+ arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL)
+ /* final test in check_stack_boundary() */;
+ else if (!type_is_pkt_pointer(type) &&
+ type != PTR_TO_MAP_VALUE &&
+ type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
arg_type == ARG_CONST_SIZE_OR_ZERO) {
@@ -2420,6 +2583,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
}
meta->ref_obj_id = reg->ref_obj_id;
}
+ } else if (arg_type == ARG_PTR_TO_SOCKET) {
+ expected_type = PTR_TO_SOCKET;
+ if (type != expected_type)
+ goto err_type;
} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
if (meta->func_id == BPF_FUNC_spin_lock) {
if (process_spin_lock(env, regno, true))
@@ -2445,6 +2612,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
type != expected_type)
goto err_type;
meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
+ } else if (arg_type_is_int_ptr(arg_type)) {
+ expected_type = PTR_TO_STACK;
+ if (!type_is_pkt_pointer(type) &&
+ type != PTR_TO_MAP_VALUE &&
+ type != expected_type)
+ goto err_type;
} else {
verbose(env, "unsupported arg_type %d\n", arg_type);
return -EFAULT;
@@ -2471,6 +2644,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
meta->map_ptr->key_size, false,
NULL);
} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
+ (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
+ !register_is_null(reg)) ||
arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
@@ -2526,6 +2701,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
err = check_helper_mem_access(env, regno - 1,
reg->umax_value,
zero_size_allowed, meta);
+ } else if (arg_type_is_int_ptr(arg_type)) {
+ int size = int_ptr_type_to_size(arg_type);
+
+ err = check_helper_mem_access(env, regno, size, false, meta);
+ if (err)
+ return err;
+ err = check_ptr_alignment(env, reg, 0, size, true);
}
return err;
@@ -2613,6 +2795,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
func_id != BPF_FUNC_map_push_elem)
goto error;
break;
+ case BPF_MAP_TYPE_SK_STORAGE:
+ if (func_id != BPF_FUNC_sk_storage_get &&
+ func_id != BPF_FUNC_sk_storage_delete)
+ goto error;
+ break;
default:
break;
}
@@ -2676,6 +2863,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
map->map_type != BPF_MAP_TYPE_STACK)
goto error;
break;
+ case BPF_FUNC_sk_storage_get:
+ case BPF_FUNC_sk_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+ goto error;
+ break;
default:
break;
}
@@ -2905,7 +3097,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
print_verifier_state(env, caller);
verbose(env, "callee:\n");
@@ -2945,7 +3137,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return err;
*insn_idx = callee->callsite + 1;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee);
verbose(env, "to caller at %d:\n", *insn_idx);
@@ -2979,6 +3171,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
int func_id, int insn_idx)
{
struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+ struct bpf_map *map = meta->map_ptr;
if (func_id != BPF_FUNC_tail_call &&
func_id != BPF_FUNC_map_lookup_elem &&
@@ -2989,11 +3182,24 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
func_id != BPF_FUNC_map_peek_elem)
return 0;
- if (meta->map_ptr == NULL) {
+ if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
+ /* In case of read-only, some additional restrictions
+ * need to be applied in order to prevent altering the
+ * state of the map from program side.
+ */
+ if ((map->map_flags & BPF_F_RDONLY_PROG) &&
+ (func_id == BPF_FUNC_map_delete_elem ||
+ func_id == BPF_FUNC_map_update_elem ||
+ func_id == BPF_FUNC_map_push_elem ||
+ func_id == BPF_FUNC_map_pop_elem)) {
+ verbose(env, "write into map forbidden\n");
+ return -EACCES;
+ }
+
if (!BPF_MAP_PTR(aux->map_state))
bpf_map_ptr_store(aux, meta->map_ptr,
meta->map_ptr->unpriv_array);
@@ -3157,19 +3363,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
- if (is_acquire_function(func_id)) {
- int id = acquire_reference_state(env, insn_idx);
-
- if (id < 0)
- return id;
- /* For mark_ptr_or_null_reg() */
- regs[BPF_REG_0].id = id;
- /* For release_reference() */
- regs[BPF_REG_0].ref_obj_id = id;
- } else {
- /* For mark_ptr_or_null_reg() */
- regs[BPF_REG_0].id = ++env->id_gen;
- }
+ regs[BPF_REG_0].id = ++env->id_gen;
+ } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
+ regs[BPF_REG_0].id = ++env->id_gen;
} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
@@ -3180,9 +3378,19 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
- if (is_ptr_cast_function(func_id))
+ if (is_ptr_cast_function(func_id)) {
/* For release_reference() */
regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+ } else if (is_acquire_function(func_id)) {
+ int id = acquire_reference_state(env, insn_idx);
+
+ if (id < 0)
+ return id;
+ /* For mark_ptr_or_null_reg() */
+ regs[BPF_REG_0].id = id;
+ /* For release_reference() */
+ regs[BPF_REG_0].ref_obj_id = id;
+ }
do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
@@ -3282,6 +3490,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
switch (ptr_reg->type) {
case PTR_TO_STACK:
+ /* Indirect variable offset stack access is prohibited in
+ * unprivileged mode so it's not handled here.
+ */
off = ptr_reg->off + ptr_reg->var_off.value;
if (mask_to_left)
*ptr_limit = MAX_BPF_STACK + off;
@@ -4982,23 +5193,17 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
insn->dst_reg);
return -EACCES;
}
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, this_branch->frame[this_branch->curframe]);
return 0;
}
-/* return the map pointer stored inside BPF_LD_IMM64 instruction */
-static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
-{
- u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
-
- return (struct bpf_map *) (unsigned long) imm64;
-}
-
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
+ struct bpf_insn_aux_data *aux = cur_aux(env);
struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_map *map;
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
@@ -5022,11 +5227,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
- /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
- BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+ map = env->used_maps[aux->map_index];
+ mark_reg_known_zero(env, regs, insn->dst_reg);
+ regs[insn->dst_reg].map_ptr = map;
+
+ if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+ regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+ regs[insn->dst_reg].off = aux->map_off;
+ if (map_value_has_spin_lock(map))
+ regs[insn->dst_reg].id = ++env->id_gen;
+ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+ } else {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
- regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
- regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
return 0;
}
@@ -5150,6 +5366,7 @@ static int check_return_code(struct bpf_verifier_env *env)
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
break;
default:
return 0;
@@ -5220,10 +5437,6 @@ enum {
#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
-static int *insn_stack; /* stack of insns to process */
-static int cur_stack; /* current stack index */
-static int *insn_state;
-
/* t, w, e - match pseudo-code above:
* t - index of current instruction
* w - next instruction
@@ -5231,6 +5444,9 @@ static int *insn_state;
*/
static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
{
+ int *insn_stack = env->cfg.insn_stack;
+ int *insn_state = env->cfg.insn_state;
+
if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
return 0;
@@ -5251,9 +5467,9 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
/* tree-edge */
insn_state[t] = DISCOVERED | e;
insn_state[w] = DISCOVERED;
- if (cur_stack >= env->prog->len)
+ if (env->cfg.cur_stack >= env->prog->len)
return -E2BIG;
- insn_stack[cur_stack++] = w;
+ insn_stack[env->cfg.cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
verbose_linfo(env, t, "%d: ", t);
@@ -5277,27 +5493,28 @@ static int check_cfg(struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi;
int insn_cnt = env->prog->len;
+ int *insn_stack, *insn_state;
int ret = 0;
int i, t;
- insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
- insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_stack) {
- kfree(insn_state);
+ kvfree(insn_state);
return -ENOMEM;
}
insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
insn_stack[0] = 0; /* 0 is the first instruction */
- cur_stack = 1;
+ env->cfg.cur_stack = 1;
peek_stack:
- if (cur_stack == 0)
+ if (env->cfg.cur_stack == 0)
goto check_state;
- t = insn_stack[cur_stack - 1];
+ t = insn_stack[env->cfg.cur_stack - 1];
if (BPF_CLASS(insns[t].code) == BPF_JMP ||
BPF_CLASS(insns[t].code) == BPF_JMP32) {
@@ -5366,7 +5583,7 @@ peek_stack:
mark_explored:
insn_state[t] = EXPLORED;
- if (cur_stack-- <= 0) {
+ if (env->cfg.cur_stack-- <= 0) {
verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
@@ -5384,8 +5601,9 @@ check_state:
ret = 0; /* cfg looks good */
err_free:
- kfree(insn_state);
- kfree(insn_stack);
+ kvfree(insn_state);
+ kvfree(insn_stack);
+ env->cfg.insn_state = env->cfg.insn_stack = NULL;
return ret;
}
@@ -6074,6 +6292,22 @@ static bool states_equal(struct bpf_verifier_env *env,
return true;
}
+static int propagate_liveness_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg,
+ struct bpf_reg_state *parent_reg)
+{
+ int err;
+
+ if (parent_reg->live & REG_LIVE_READ || !(reg->live & REG_LIVE_READ))
+ return 0;
+
+ err = mark_reg_read(env, reg, parent_reg);
+ if (err)
+ return err;
+
+ return 0;
+}
+
/* A write screens off any subsequent reads; but write marks come from the
* straight-line code between a state and its parent. When we arrive at an
* equivalent state (jump target or such) we didn't arrive by the straight-line
@@ -6085,8 +6319,9 @@ static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
struct bpf_verifier_state *vparent)
{
- int i, frame, err = 0;
+ struct bpf_reg_state *state_reg, *parent_reg;
struct bpf_func_state *state, *parent;
+ int i, frame, err = 0;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
@@ -6096,30 +6331,27 @@ static int propagate_liveness(struct bpf_verifier_env *env,
/* Propagate read liveness of registers... */
BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
for (frame = 0; frame <= vstate->curframe; frame++) {
+ parent = vparent->frame[frame];
+ state = vstate->frame[frame];
+ parent_reg = parent->regs;
+ state_reg = state->regs;
/* We don't need to worry about FP liveness, it's read-only */
for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) {
- if (vparent->frame[frame]->regs[i].live & REG_LIVE_READ)
- continue;
- if (vstate->frame[frame]->regs[i].live & REG_LIVE_READ) {
- err = mark_reg_read(env, &vstate->frame[frame]->regs[i],
- &vparent->frame[frame]->regs[i]);
- if (err)
- return err;
- }
+ err = propagate_liveness_reg(env, &state_reg[i],
+ &parent_reg[i]);
+ if (err)
+ return err;
}
- }
- /* ... and stack slots */
- for (frame = 0; frame <= vstate->curframe; frame++) {
- state = vstate->frame[frame];
- parent = vparent->frame[frame];
+ /* Propagate stack slots. */
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
i < parent->allocated_stack / BPF_REG_SIZE; i++) {
- if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
- continue;
- if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
- mark_reg_read(env, &state->stack[i].spilled_ptr,
- &parent->stack[i].spilled_ptr);
+ parent_reg = &parent->stack[i].spilled_ptr;
+ state_reg = &state->stack[i].spilled_ptr;
+ err = propagate_liveness_reg(env, state_reg,
+ parent_reg);
+ if (err)
+ return err;
}
}
return err;
@@ -6128,11 +6360,13 @@ static int propagate_liveness(struct bpf_verifier_env *env,
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
- struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state_list *sl, **pprev;
struct bpf_verifier_state *cur = env->cur_state, *new;
int i, j, err, states_cnt = 0;
- sl = env->explored_states[insn_idx];
+ pprev = &env->explored_states[insn_idx];
+ sl = *pprev;
+
if (!sl)
/* this 'insn_idx' instruction wasn't marked, so we will not
* be doing state search here
@@ -6143,6 +6377,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
while (sl != STATE_LIST_MARK) {
if (states_equal(env, &sl->state, cur)) {
+ sl->hit_cnt++;
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
@@ -6158,10 +6393,40 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return err;
return 1;
}
- sl = sl->next;
states_cnt++;
+ sl->miss_cnt++;
+ /* heuristic to determine whether this state is beneficial
+ * to keep checking from state equivalence point of view.
+ * Higher numbers increase max_states_per_insn and verification time,
+ * but do not meaningfully decrease insn_processed.
+ */
+ if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+ /* the state is unlikely to be useful. Remove it to
+ * speed up verification
+ */
+ *pprev = sl->next;
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ env->peak_states--;
+ } else {
+ /* cannot free this state, since parentage chain may
+ * walk it later. Add it for free_list instead to
+ * be freed at the end of verification
+ */
+ sl->next = env->free_list;
+ env->free_list = sl;
+ }
+ sl = *pprev;
+ continue;
+ }
+ pprev = &sl->next;
+ sl = *pprev;
}
+ if (env->max_states_per_insn < states_cnt)
+ env->max_states_per_insn = states_cnt;
+
if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
return 0;
@@ -6175,6 +6440,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
+ env->total_states++;
+ env->peak_states++;
/* add new state to the head of linked list */
new = &new_sl->state;
@@ -6259,8 +6526,7 @@ static int do_check(struct bpf_verifier_env *env)
struct bpf_verifier_state *state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
- int insn_cnt = env->prog->len, i;
- int insn_processed = 0;
+ int insn_cnt = env->prog->len;
bool do_print_state = false;
env->prev_linfo = NULL;
@@ -6295,10 +6561,10 @@ static int do_check(struct bpf_verifier_env *env)
insn = &insns[env->insn_idx];
class = BPF_CLASS(insn->code);
- if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+ if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
"BPF program is too large. Processed %d insn\n",
- insn_processed);
+ env->insn_processed);
return -E2BIG;
}
@@ -6307,7 +6573,7 @@ static int do_check(struct bpf_verifier_env *env)
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
if (do_print_state)
verbose(env, "\nfrom %d to %d%s: safe\n",
env->prev_insn_idx, env->insn_idx,
@@ -6325,8 +6591,9 @@ static int do_check(struct bpf_verifier_env *env)
if (need_resched())
cond_resched();
- if (env->log.level > 1 || (env->log.level && do_print_state)) {
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2 ||
+ (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
+ if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "%d:", env->insn_idx);
else
verbose(env, "\nfrom %d to %d%s:",
@@ -6337,7 +6604,7 @@ static int do_check(struct bpf_verifier_env *env)
do_print_state = false;
}
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
const struct bpf_insn_cbs cbs = {
.cb_print = verbose,
.private_data = env,
@@ -6602,16 +6869,6 @@ process_bpf_exit:
env->insn_idx++;
}
- verbose(env, "processed %d insns (limit %d), stack depth ",
- insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
- for (i = 0; i < env->subprog_cnt; i++) {
- u32 depth = env->subprog_info[i].stack_depth;
-
- verbose(env, "%d", depth);
- if (i + 1 < env->subprog_cnt)
- verbose(env, "+");
- }
- verbose(env, "\n");
env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
return 0;
}
@@ -6709,8 +6966,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
}
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+ struct bpf_insn_aux_data *aux;
struct bpf_map *map;
struct fd f;
+ u64 addr;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -6719,13 +6978,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
return -EINVAL;
}
- if (insn->src_reg == 0)
+ if (insn[0].src_reg == 0)
/* valid generic load 64-bit imm */
goto next_insn;
- if (insn[0].src_reg != BPF_PSEUDO_MAP_FD ||
- insn[1].imm != 0) {
- verbose(env, "unrecognized bpf_ld_imm64 insn\n");
+ /* In final convert_pseudo_ld_imm64() step, this is
+ * converted into regular 64-bit imm load insn.
+ */
+ if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
+ insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
+ (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
+ insn[1].imm != 0)) {
+ verbose(env,
+ "unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
@@ -6743,16 +7008,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
return err;
}
- /* store map pointer inside BPF_LD_IMM64 instruction */
- insn[0].imm = (u32) (unsigned long) map;
- insn[1].imm = ((u64) (unsigned long) map) >> 32;
+ aux = &env->insn_aux_data[i];
+ if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ addr = (unsigned long)map;
+ } else {
+ u32 off = insn[1].imm;
+
+ if (off >= BPF_MAX_VAR_OFF) {
+ verbose(env, "direct value offset of %u is not allowed\n", off);
+ fdput(f);
+ return -EINVAL;
+ }
+
+ if (!map->ops->map_direct_value_addr) {
+ verbose(env, "no direct value access support for this map type\n");
+ fdput(f);
+ return -EINVAL;
+ }
+
+ err = map->ops->map_direct_value_addr(map, &addr, off);
+ if (err) {
+ verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
+ map->value_size, off);
+ fdput(f);
+ return err;
+ }
+
+ aux->map_off = off;
+ addr += off;
+ }
+
+ insn[0].imm = (u32)addr;
+ insn[1].imm = addr >> 32;
/* check whether we recorded this map already */
- for (j = 0; j < env->used_map_cnt; j++)
+ for (j = 0; j < env->used_map_cnt; j++) {
if (env->used_maps[j] == map) {
+ aux->map_index = j;
fdput(f);
goto next_insn;
}
+ }
if (env->used_map_cnt >= MAX_USED_MAPS) {
fdput(f);
@@ -6769,6 +7065,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
fdput(f);
return PTR_ERR(map);
}
+
+ aux->map_index = env->used_map_cnt;
env->used_maps[env->used_map_cnt++] = map;
if (bpf_map_is_cgroup_storage(map) &&
@@ -6874,8 +7172,13 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
struct bpf_prog *new_prog;
new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
- if (!new_prog)
+ if (IS_ERR(new_prog)) {
+ if (PTR_ERR(new_prog) == -ERANGE)
+ verbose(env,
+ "insn %d cannot be patched due to 16-bit range\n",
+ env->insn_aux_data[off].orig_idx);
return NULL;
+ }
if (adjust_insn_aux_data(env, new_prog->len, off, len))
return NULL;
adjust_subprog_starts(env, off, len);
@@ -7413,9 +7716,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn->src_reg != BPF_PSEUDO_CALL)
continue;
subprog = insn->off;
- insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
- func[subprog]->bpf_func -
- __bpf_call_base;
+ insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
+ __bpf_call_base;
}
/* we use the aux data to keep a list of the start addresses
@@ -7817,6 +8119,14 @@ static void free_states(struct bpf_verifier_env *env)
struct bpf_verifier_state_list *sl, *sln;
int i;
+ sl = env->free_list;
+ while (sl) {
+ sln = sl->next;
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ sl = sln;
+ }
+
if (!env->explored_states)
return;
@@ -7832,12 +8142,37 @@ static void free_states(struct bpf_verifier_env *env)
}
}
- kfree(env->explored_states);
+ kvfree(env->explored_states);
+}
+
+static void print_verification_stats(struct bpf_verifier_env *env)
+{
+ int i;
+
+ if (env->log.level & BPF_LOG_STATS) {
+ verbose(env, "verification time %lld usec\n",
+ div_u64(env->verification_time, 1000));
+ verbose(env, "stack depth ");
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
+
+ verbose(env, "%d", depth);
+ if (i + 1 < env->subprog_cnt)
+ verbose(env, "+");
+ }
+ verbose(env, "\n");
+ }
+ verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
+ "total_states %d peak_states %d mark_read %d\n",
+ env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
+ env->max_states_per_insn, env->total_states,
+ env->peak_states, env->longest_mark_read_walk);
}
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
union bpf_attr __user *uattr)
{
+ u64 start_time = ktime_get_ns();
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
int i, len, ret = -EINVAL;
@@ -7865,9 +8200,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
+ is_priv = capable(CAP_SYS_ADMIN);
/* grab the mutex to protect few globals used by verifier */
- mutex_lock(&bpf_verifier_lock);
+ if (!is_priv)
+ mutex_lock(&bpf_verifier_lock);
if (attr->log_level || attr->log_buf || attr->log_size) {
/* user requested verbose verifier output
@@ -7879,8 +8216,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
ret = -EINVAL;
/* log attributes have to be sane */
- if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
- !log->level || !log->ubuf)
+ if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 ||
+ !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
goto err_unlock;
}
@@ -7890,7 +8227,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
- is_priv = capable(CAP_SYS_ADMIN);
env->allow_ptr_leaks = is_priv;
ret = replace_map_fd_with_map_ptr(env);
@@ -7903,7 +8239,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
goto skip_full_check;
}
- env->explored_states = kcalloc(env->prog->len,
+ env->explored_states = kvcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
ret = -ENOMEM;
@@ -7961,6 +8297,9 @@ skip_full_check:
if (ret == 0)
ret = fixup_call_args(env);
+ env->verification_time = ktime_get_ns() - start_time;
+ print_verification_stats(env);
+
if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
if (log->level && !log->ubuf) {
@@ -8000,7 +8339,8 @@ err_release_maps:
release_maps(env);
*prog = env->prog;
err_unlock:
- mutex_unlock(&bpf_verifier_lock);
+ if (!is_priv)
+ mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
err_free_env:
kfree(env);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c9ec050bcf46..599510a3355e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -3326,6 +3326,11 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
return -ENOSYS;
}
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
#endif /* CONFIG_PROC_SYSCTL */
@@ -3366,3 +3371,4 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
EXPORT_SYMBOL(proc_dostring);
EXPORT_SYMBOL(proc_doulongvec_minmax);
EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
+EXPORT_SYMBOL(proc_do_large_bitmap);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 4e62a4a8fa91..5f852b8f59f7 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -375,7 +375,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
? TASKSTATS_TYPE_AGGR_PID
: TASKSTATS_TYPE_AGGR_TGID;
- na = nla_nest_start(skb, aggr);
+ na = nla_nest_start_noflag(skb, aggr);
if (!na)
goto err;
@@ -649,17 +649,41 @@ err:
static const struct genl_ops taskstats_ops[] = {
{
.cmd = TASKSTATS_CMD_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = taskstats_user_cmd,
- .policy = taskstats_cmd_get_policy,
- .flags = GENL_ADMIN_PERM,
+ /* policy enforced later */
+ .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL,
},
{
.cmd = CGROUPSTATS_CMD_GET,
+ .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = cgroupstats_user_cmd,
- .policy = cgroupstats_cmd_get_policy,
+ /* policy enforced later */
+ .flags = GENL_CMD_CAP_HASPOL,
},
};
+static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
+ struct genl_info *info)
+{
+ const struct nla_policy *policy = NULL;
+
+ switch (ops->cmd) {
+ case TASKSTATS_CMD_GET:
+ policy = taskstats_cmd_get_policy;
+ break;
+ case CGROUPSTATS_CMD_GET:
+ policy = cgroupstats_cmd_get_policy;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return nlmsg_validate_deprecated(info->nlhdr, GENL_HDRLEN,
+ TASKSTATS_CMD_ATTR_MAX, policy,
+ info->extack);
+}
+
static struct genl_family family __ro_after_init = {
.name = TASKSTATS_GENL_NAME,
.version = TASKSTATS_GENL_VERSION,
@@ -667,6 +691,7 @@ static struct genl_family family __ro_after_init = {
.module = THIS_MODULE,
.ops = taskstats_ops,
.n_ops = ARRAY_SIZE(taskstats_ops),
+ .pre_doit = taskstats_pre_doit,
};
/* Needed early in initialization */
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 86656bbac232..7f7d6914ddd5 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -783,6 +783,16 @@ u64 jiffies64_to_nsecs(u64 j)
}
EXPORT_SYMBOL(jiffies64_to_nsecs);
+u64 jiffies64_to_msecs(const u64 j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+ return (MSEC_PER_SEC / HZ) * j;
+#else
+ return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_msecs);
+
/**
* nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
*
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 94b0e37d90ef..b496ffdf5f36 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -577,6 +577,12 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_map_update_elem_proto;
case BPF_FUNC_map_delete_elem:
return &bpf_map_delete_elem_proto;
+ case BPF_FUNC_map_push_elem:
+ return &bpf_map_push_elem_proto;
+ case BPF_FUNC_map_pop_elem:
+ return &bpf_map_pop_elem_proto;
+ case BPF_FUNC_map_peek_elem:
+ return &bpf_map_peek_elem_proto;
case BPF_FUNC_probe_read:
return &bpf_probe_read_proto;
case BPF_FUNC_ktime_get_ns:
@@ -917,6 +923,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
const struct bpf_prog_ops raw_tracepoint_prog_ops = {
};
+static bool raw_tp_writable_prog_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ if (off == 0) {
+ if (size != sizeof(u64) || type != BPF_READ)
+ return false;
+ info->reg_type = PTR_TO_TP_BUFFER;
+ }
+ return raw_tp_prog_is_valid_access(off, size, type, prog, info);
+}
+
+const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = {
+ .get_func_proto = raw_tp_prog_func_proto,
+ .is_valid_access = raw_tp_writable_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = {
+};
+
static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info)
@@ -1206,6 +1233,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64))
return -EINVAL;
+ if (prog->aux->max_tp_access > btp->writable_size)
+ return -EINVAL;
+
return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.