summaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-04-11 17:00:05 -0700
committerDavid S. Miller <davem@davemloft.net>2019-04-11 17:00:05 -0700
commitbb23581b9b38703257acabd520aa5ebf1db008af (patch)
tree9d9f7b7ccad9697dfd2eab3b1fda37056b0e47f6 /kernel/bpf
parent78f07adac86186b5ef0318b7faec377b6d31ea9f (diff)
parent947e8b595b82d3551750641445d0a97b8f29b536 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2019-04-12 The following pull-request contains BPF updates for your *net-next* tree. The main changes are: 1) Improve BPF verifier scalability for large programs through two optimizations: i) remove verifier states that are not useful in pruning, ii) stop walking parentage chain once first LIVE_READ is seen. Combined gives approx 20x speedup. Increase limits for accepting large programs under root, and add various stress tests, from Alexei. 2) Implement global data support in BPF. This enables static global variables for .data, .rodata and .bss sections to be properly handled which allows for more natural program development. This also opens up the possibility to optimize program workflow by compiling ELFs only once and later only rewriting section data before reload, from Daniel and with test cases and libbpf refactoring from Joe. 3) Add config option to generate BTF type info for vmlinux as part of the kernel build process. DWARF debug info is converted via pahole to BTF. Latter relies on libbpf and makes use of BTF deduplication algorithm which results in 100x savings compared to DWARF data. Resulting .BTF section is typically about 2MB in size, from Andrii. 4) Add BPF verifier support for stack access with variable offset from helpers and add various test cases along with it, from Andrey. 5) Extend bpf_skb_adjust_room() growth BPF helper to mark inner MAC header so that L2 encapsulation can be used for tc tunnels, from Alan. 6) Add support for input __sk_buff context in BPF_PROG_TEST_RUN so that users can define a subset of allowed __sk_buff fields that get fed into the test program, from Stanislav. 7) Add bpf fs multi-dimensional array tests for BTF test suite and fix up various UBSAN warnings in bpftool, from Yonghong. 8) Generate a pkg-config file for libbpf, from Luca. 9) Dump program's BTF id in bpftool, from Prashant. 10) libbpf fix to use smaller BPF log buffer size for AF_XDP's XDP program, from Magnus. 11) kallsyms related fixes for the case when symbols are not present in BPF selftests and samples, from Daniel ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/arraymap.c53
-rw-r--r--kernel/bpf/btf.c419
-rw-r--r--kernel/bpf/core.c14
-rw-r--r--kernel/bpf/disasm.c5
-rw-r--r--kernel/bpf/hashtab.c6
-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.c144
-rw-r--r--kernel/bpf/verifier.c397
10 files changed, 903 insertions, 150 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/core.c b/kernel/bpf/core.c
index ff09d32a8a1b..ace8c22c8b0e 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;
@@ -1096,13 +1098,13 @@ 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/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/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..d995eedfdd16 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 != '_')</