summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2018-12-20 17:31:36 -0800
committerDavid S. Miller <davem@davemloft.net>2018-12-20 17:31:36 -0800
commit339bbff2d6e005a5586adeffc3d69a0eea50a764 (patch)
treea5bedd1933215aa69acdb5dbbfcbafb29561fe3c /kernel
parente770454fabde2e0f8fb3e5039a2b6df8f128bc9b (diff)
parent1cf4a0ccc506b5c027afc5eaf3fddc83f96f31e7 (diff)
downloadlinux-339bbff2d6e005a5586adeffc3d69a0eea50a764.tar.bz2
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2018-12-21 The following pull-request contains BPF updates for your *net-next* tree. There is a merge conflict in test_verifier.c. Result looks as follows: [...] }, { "calls: cross frame pruning", .insns = { [...] .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, .errstr_unpriv = "function calls to other bpf functions are allowed for root only", .result_unpriv = REJECT, .errstr = "!read_ok", .result = REJECT, }, { "jset: functional", .insns = { [...] { "jset: unknown const compare not taken", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1), BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, .errstr_unpriv = "!read_ok", .result_unpriv = REJECT, .errstr = "!read_ok", .result = REJECT, }, [...] { "jset: range", .insns = { [...] }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, .result_unpriv = ACCEPT, .result = ACCEPT, }, The main changes are: 1) Various BTF related improvements in order to get line info working. Meaning, verifier will now annotate the corresponding BPF C code to the error log, from Martin and Yonghong. 2) Implement support for raw BPF tracepoints in modules, from Matt. 3) Add several improvements to verifier state logic, namely speeding up stacksafe check, optimizations for stack state equivalence test and safety checks for liveness analysis, from Alexei. 4) Teach verifier to make use of BPF_JSET instruction, add several test cases to kselftests and remove nfp specific JSET optimization now that verifier has awareness, from Jakub. 5) Improve BPF verifier's slot_type marking logic in order to allow more stack slot sharing, from Jiong. 6) Add sk_msg->size member for context access and add set of fixes and improvements to make sock_map with kTLS usable with openssl based applications, from John. 7) Several cleanups and documentation updates in bpftool as well as auto-mount of tracefs for "bpftool prog tracelog" command, from Quentin. 8) Include sub-program tags from now on in bpf_prog_info in order to have a reliable way for user space to get all tags of the program e.g. needed for kallsyms correlation, from Song. 9) Add BTF annotations for cgroup_local_storage BPF maps and implement bpf fs pretty print support, from Roman. 10) Fix bpftool in order to allow for cross-compilation, from Ivan. 11) Update of bpftool license to GPLv2-only + BSD-2-Clause in order to be compatible with libbfd and allow for Debian packaging, from Jakub. 12) Remove an obsolete prog->aux sanitation in dump and get rid of version check for prog load, from Daniel. 13) Fix a memory leak in libbpf's line info handling, from Prashant. 14) Fix cpumap's frame alignment for build_skb() so that skb_shared_info does not get unaligned, from Jesper. 15) Fix test_progs kselftest to work with older compilers which are less smart in optimizing (and thus throwing build error), from Stanislav. 16) Cleanup and simplify AF_XDP socket teardown, from Björn. 17) Fix sk lookup in BPF kselftest's test_sock_addr with regards to netns_id argument, from Andrey. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c1
-rw-r--r--kernel/bpf/btf.c393
-rw-r--r--kernel/bpf/cpumap.c2
-rw-r--r--kernel/bpf/local_storage.c84
-rw-r--r--kernel/bpf/lpm_trie.c1
-rw-r--r--kernel/bpf/syscall.c80
-rw-r--r--kernel/bpf/verifier.c241
-rw-r--r--kernel/module.c5
-rw-r--r--kernel/trace/bpf_trace.c99
9 files changed, 804 insertions, 102 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 24583da9ffd1..25632a75d630 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -382,6 +382,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
}
static int array_map_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index bf34933cc413..715f9fcf4712 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -164,7 +164,7 @@
#define BITS_ROUNDUP_BYTES(bits) \
(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
-#define BTF_INFO_MASK 0x0f00ffff
+#define BTF_INFO_MASK 0x8f00ffff
#define BTF_INT_MASK 0x0fffffff
#define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE)
#define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET)
@@ -274,6 +274,10 @@ struct btf_kind_operations {
const struct btf_type *struct_type,
const struct btf_member *member,
const struct btf_type *member_type);
+ int (*check_kflag_member)(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type);
void (*log_details)(struct btf_verifier_env *env,
const struct btf_type *t);
void (*seq_show)(const struct btf *btf, const struct btf_type *t,
@@ -419,6 +423,25 @@ static u16 btf_type_vlen(const struct btf_type *t)
return BTF_INFO_VLEN(t->info);
}
+static bool btf_type_kflag(const struct btf_type *t)
+{
+ return BTF_INFO_KFLAG(t->info);
+}
+
+static u32 btf_member_bit_offset(const struct btf_type *struct_type,
+ const struct btf_member *member)
+{
+ return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
+ : member->offset;
+}
+
+static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
+ const struct btf_member *member)
+{
+ return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
+ : 0;
+}
+
static u32 btf_type_int(const struct btf_type *t)
{
return *(u32 *)(t + 1);
@@ -474,7 +497,7 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
return !*src;
}
-const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!offset)
return "(anon)";
@@ -484,6 +507,14 @@ const char *btf_name_by_offset(const struct btf *btf, u32 offset)
return "(invalid-name-offset)";
}
+const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+{
+ if (offset < btf->hdr.str_len)
+ return &btf->strings[offset];
+
+ return NULL;
+}
+
const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
{
if (type_id > btf->nr_types)
@@ -514,6 +545,47 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
return true;
}
+/*
+ * Check that given struct member is a regular int with expected
+ * offset and size.
+ */
+bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
+ const struct btf_member *m,
+ u32 expected_offset, u32 expected_size)
+{
+ const struct btf_type *t;
+ u32 id, int_data;
+ u8 nr_bits;
+
+ id = m->type;
+ t = btf_type_id_size(btf, &id, NULL);
+ if (!t || !btf_type_is_int(t))
+ return false;
+
+ int_data = btf_type_int(t);
+ nr_bits = BTF_INT_BITS(int_data);
+ if (btf_type_kflag(s)) {
+ u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset);
+ u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset);
+
+ /* if kflag set, int should be a regular int and
+ * bit offset should be at byte boundary.
+ */
+ return !bitfield_size &&
+ BITS_ROUNDUP_BYTES(bit_offset) == expected_offset &&
+ BITS_ROUNDUP_BYTES(nr_bits) == expected_size;
+ }
+
+ if (BTF_INT_OFFSET(int_data) ||
+ BITS_PER_BYTE_MASKED(m->offset) ||
+ BITS_ROUNDUP_BYTES(m->offset) != expected_offset ||
+ BITS_PER_BYTE_MASKED(nr_bits) ||
+ BITS_ROUNDUP_BYTES(nr_bits) != expected_size)
+ return false;
+
+ return true;
+}
+
__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
const char *fmt, ...)
{
@@ -554,7 +626,7 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
__btf_verifier_log(log, "[%u] %s %s%s",
env->log_type_id,
btf_kind_str[kind],
- btf_name_by_offset(btf, t->name_off),
+ __btf_name_by_offset(btf, t->name_off),
log_details ? " " : "");
if (log_details)
@@ -597,9 +669,17 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
if (env->phase != CHECK_META)
btf_verifier_log_type(env, struct_type, NULL);
- __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
- btf_name_by_offset(btf, member->name_off),
- member->type, member->offset);
+ if (btf_type_kflag(struct_type))
+ __btf_verifier_log(log,
+ "\t%s type_id=%u bitfield_size=%u bits_offset=%u",
+ __btf_name_by_offset(btf, member->name_off),
+ member->type,
+ BTF_MEMBER_BITFIELD_SIZE(member->offset),
+ BTF_MEMBER_BIT_OFFSET(member->offset));
+ else
+ __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+ __btf_name_by_offset(btf, member->name_off),
+ member->type, member->offset);
if (fmt && *fmt) {
__btf_verifier_log(log, " ");
@@ -915,6 +995,38 @@ static int btf_df_check_member(struct btf_verifier_env *env,
return -EINVAL;
}
+static int btf_df_check_kflag_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ btf_verifier_log_basic(env, struct_type,
+ "Unsupported check_kflag_member");
+ return -EINVAL;
+}
+
+/* Used for ptr, array and struct/union type members.
+ * int, enum and modifier types have their specific callback functions.
+ */
+static int btf_generic_check_kflag_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member bitfield_size");
+ return -EINVAL;
+ }
+
+ /* bitfield size is 0, so member->offset represents bit offset only.
+ * It is safe to call non kflag check_member variants.
+ */
+ return btf_type_ops(member_type)->check_member(env, struct_type,
+ member,
+ member_type);
+}
+
static int btf_df_resolve(struct btf_verifier_env *env,
const struct resolve_vertex *v)
{
@@ -967,6 +1079,62 @@ static int btf_int_check_member(struct btf_verifier_env *env,
return 0;
}
+static int btf_int_check_kflag_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset;
+ u32 int_data = btf_type_int(member_type);
+ u32 struct_size = struct_type->size;
+ u32 nr_copy_bits;
+
+ /* a regular int type is required for the kflag int member */
+ if (!btf_type_int_is_regular(member_type)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member base type");
+ return -EINVAL;
+ }
+
+ /* check sanity of bitfield size */
+ nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+ struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+ nr_int_data_bits = BTF_INT_BITS(int_data);
+ if (!nr_bits) {
+ /* Not a bitfield member, member offset must be at byte
+ * boundary.
+ */
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member offset");
+ return -EINVAL;
+ }
+
+ nr_bits = nr_int_data_bits;
+ } else if (nr_bits > nr_int_data_bits) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member bitfield_size");
+ return -EINVAL;
+ }
+
+ bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+ nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off);
+ if (nr_copy_bits > BITS_PER_U64) {
+ btf_verifier_log_member(env, struct_type, member,
+ "nr_copy_bits exceeds 64");
+ return -EINVAL;
+ }
+
+ if (struct_size < bytes_offset ||
+ struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static s32 btf_int_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
@@ -986,6 +1154,11 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
int_data = btf_type_int(t);
if (int_data & ~BTF_INT_MASK) {
btf_verifier_log_basic(env, t, "Invalid int_data:%x",
@@ -1038,26 +1211,16 @@ static void btf_int_log(struct btf_verifier_env *env,
btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
}
-static void btf_int_bits_seq_show(const struct btf *btf,
- const struct btf_type *t,
- void *data, u8 bits_offset,
- struct seq_file *m)
+static void btf_bitfield_seq_show(void *data, u8 bits_offset,
+ u8 nr_bits, struct seq_file *m)
{
u16 left_shift_bits, right_shift_bits;
- u32 int_data = btf_type_int(t);
- u8 nr_bits = BTF_INT_BITS(int_data);
- u8 total_bits_offset;
u8 nr_copy_bytes;
u8 nr_copy_bits;
u64 print_num;
- /*
- * bits_offset is at most 7.
- * BTF_INT_OFFSET() cannot exceed 64 bits.
- */
- total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
- data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
- bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+ data += BITS_ROUNDDOWN_BYTES(bits_offset);
+ bits_offset = BITS_PER_BYTE_MASKED(bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
@@ -1077,6 +1240,24 @@ static void btf_int_bits_seq_show(const struct btf *btf,
seq_printf(m, "0x%llx", print_num);
}
+
+static void btf_int_bits_seq_show(const struct btf *btf,
+ const struct btf_type *t,
+ void *data, u8 bits_offset,
+ struct seq_file *m)
+{
+ u32 int_data = btf_type_int(t);
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
+ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+ btf_bitfield_seq_show(data, total_bits_offset, nr_bits, m);
+}
+
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 type_id, void *data, u8 bits_offset,
struct seq_file *m)
@@ -1126,6 +1307,7 @@ static const struct btf_kind_operations int_ops = {
.check_meta = btf_int_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_int_check_member,
+ .check_kflag_member = btf_int_check_kflag_member,
.log_details = btf_int_log,
.seq_show = btf_int_seq_show,
};
@@ -1155,6 +1337,31 @@ static int btf_modifier_check_member(struct btf_verifier_env *env,
resolved_type);
}
+static int btf_modifier_check_kflag_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ const struct btf_type *resolved_type;
+ u32 resolved_type_id = member->type;
+ struct btf_member resolved_member;
+ struct btf *btf = env->btf;
+
+ resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
+ if (!resolved_type) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member");
+ return -EINVAL;
+ }
+
+ resolved_member = *member;
+ resolved_member.type = resolved_type_id;
+
+ return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type,
+ &resolved_member,
+ resolved_type);
+}
+
static int btf_ptr_check_member(struct btf_verifier_env *env,
const struct btf_type *struct_type,
const struct btf_member *member,
@@ -1190,6 +1397,11 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
if (!BTF_TYPE_ID_VALID(t->type)) {
btf_verifier_log_type(env, t, "Invalid type_id");
return -EINVAL;
@@ -1343,6 +1555,7 @@ static struct btf_kind_operations modifier_ops = {
.check_meta = btf_ref_type_check_meta,
.resolve = btf_modifier_resolve,
.check_member = btf_modifier_check_member,
+ .check_kflag_member = btf_modifier_check_kflag_member,
.log_details = btf_ref_type_log,
.seq_show = btf_modifier_seq_show,
};
@@ -1351,6 +1564,7 @@ static struct btf_kind_operations ptr_ops = {
.check_meta = btf_ref_type_check_meta,
.resolve = btf_ptr_resolve,
.check_member = btf_ptr_check_member,
+ .check_kflag_member = btf_generic_check_kflag_member,
.log_details = btf_ref_type_log,
.seq_show = btf_ptr_seq_show,
};
@@ -1381,11 +1595,18 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
return 0;
}
+static void btf_fwd_type_log(struct btf_verifier_env *env,
+ const struct btf_type *t)
+{
+ btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct");
+}
+
static struct btf_kind_operations fwd_ops = {
.check_meta = btf_fwd_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_df_check_member,
- .log_details = btf_ref_type_log,
+ .check_kflag_member = btf_df_check_kflag_member,
+ .log_details = btf_fwd_type_log,
.seq_show = btf_df_seq_show,
};
@@ -1443,6 +1664,11 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
if (t->size) {
btf_verifier_log_type(env, t, "size != 0");
return -EINVAL;
@@ -1566,6 +1792,7 @@ static struct btf_kind_operations array_ops = {
.check_meta = btf_array_check_meta,
.resolve = btf_array_resolve,
.check_member = btf_array_check_member,
+ .check_kflag_member = btf_generic_check_kflag_member,
.log_details = btf_array_log,
.seq_show = btf_array_seq_show,
};
@@ -1604,6 +1831,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
+ u32 offset;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1645,7 +1873,8 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
- if (is_union && member->offset) {
+ offset = btf_member_bit_offset(t, member);
+ if (is_union && offset) {
btf_verifier_log_member(env, t, member,
"Invalid member bits_offset");
return -EINVAL;
@@ -1655,20 +1884,20 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
* ">" instead of ">=" because the last member could be
* "char a[0];"
*/
- if (last_offset > member->offset) {
+ if (last_offset > offset) {
btf_verifier_log_member(env, t, member,
"Invalid member bits_offset");
return -EINVAL;
}
- if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
+ if (BITS_ROUNDUP_BYTES(offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Member bits_offset exceeds its struct size");
return -EINVAL;
}
btf_verifier_log_member(env, t, member, NULL);
- last_offset = member->offset;
+ last_offset = offset;
}
return meta_needed;
@@ -1698,9 +1927,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
last_member_type = btf_type_by_id(env->btf,
last_member_type_id);
- err = btf_type_ops(last_member_type)->check_member(env, v->t,
- last_member,
- last_member_type);
+ if (btf_type_kflag(v->t))
+ err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t,
+ last_member,
+ last_member_type);
+ else
+ err = btf_type_ops(last_member_type)->check_member(env, v->t,
+ last_member,
+ last_member_type);
if (err)
return err;
}
@@ -1722,9 +1956,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
return env_stack_push(env, member_type, member_type_id);
}
- err = btf_type_ops(member_type)->check_member(env, v->t,
- member,
- member_type);
+ if (btf_type_kflag(v->t))
+ err = btf_type_ops(member_type)->check_kflag_member(env, v->t,
+ member,
+ member_type);
+ else
+ err = btf_type_ops(member_type)->check_member(env, v->t,
+ member,
+ member_type);
if (err)
return err;
}
@@ -1752,17 +1991,26 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
for_each_member(i, t, member) {
const struct btf_type *member_type = btf_type_by_id(btf,
member->type);
- u32 member_offset = member->offset;
- u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
- u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
const struct btf_kind_operations *ops;
+ u32 member_offset, bitfield_size;
+ u32 bytes_offset;
+ u8 bits8_offset;
if (i)
seq_puts(m, seq);
- ops = btf_type_ops(member_type);
- ops->seq_show(btf, member_type, member->type,
- data + bytes_offset, bits8_offset, m);
+ member_offset = btf_member_bit_offset(t, member);
+ bitfield_size = btf_member_bitfield_size(t, member);
+ if (bitfield_size) {
+ btf_bitfield_seq_show(data, member_offset,
+ bitfield_size, m);
+ } else {
+ bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+ bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+ ops = btf_type_ops(member_type);
+ ops->seq_show(btf, member_type, member->type,
+ data + bytes_offset, bits8_offset, m);
+ }
}
seq_puts(m, "}");
}
@@ -1771,6 +2019,7 @@ static struct btf_kind_operations struct_ops = {
.check_meta = btf_struct_check_meta,
.resolve = btf_struct_resolve,
.check_member = btf_struct_check_member,
+ .check_kflag_member = btf_generic_check_kflag_member,
.log_details = btf_struct_log,
.seq_show = btf_struct_seq_show,
};
@@ -1800,6 +2049,41 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
return 0;
}
+static int btf_enum_check_kflag_member(struct btf_verifier_env *env,
+ const struct btf_type *struct_type,
+ const struct btf_member *member,
+ const struct btf_type *member_type)
+{
+ u32 struct_bits_off, nr_bits, bytes_end, struct_size;
+ u32 int_bitsize = sizeof(int) * BITS_PER_BYTE;
+
+ struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+ nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+ if (!nr_bits) {
+ if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member is not byte aligned");
+ return -EINVAL;
+ }
+
+ nr_bits = int_bitsize;
+ } else if (nr_bits > int_bitsize) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Invalid member bitfield_size");
+ return -EINVAL;
+ }
+
+ struct_size = struct_type->size;
+ bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits);
+ if (struct_size < bytes_end) {
+ btf_verifier_log_member(env, struct_type, member,
+ "Member exceeds struct_size");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static s32 btf_enum_check_meta(struct btf_verifier_env *env,
const struct btf_type *t,
u32 meta_left)
@@ -1819,6 +2103,11 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
if (t->size != sizeof(int)) {
btf_verifier_log_type(env, t, "Expected size:%zu",
sizeof(int));
@@ -1850,7 +2139,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
btf_verifier_log(env, "\t%s val=%d\n",
- btf_name_by_offset(btf, enums[i].name_off),
+ __btf_name_by_offset(btf, enums[i].name_off),
enums[i].val);
}
@@ -1874,7 +2163,8 @@ static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
for (i = 0; i < nr_enums; i++) {
if (v == enums[i].val) {
seq_printf(m, "%s",
- btf_name_by_offset(btf, enums[i].name_off));
+ __btf_name_by_offset(btf,
+ enums[i].name_off));
return;
}
}
@@ -1886,6 +2176,7 @@ static struct btf_kind_operations enum_ops = {
.check_meta = btf_enum_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_enum_check_member,
+ .check_kflag_member = btf_enum_check_kflag_member,
.log_details = btf_enum_log,
.seq_show = btf_enum_seq_show,
};
@@ -1908,6 +2199,11 @@ static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
return meta_needed;
@@ -1932,20 +2228,20 @@ static void btf_func_proto_log(struct btf_verifier_env *env,
}
btf_verifier_log(env, "%u %s", args[0].type,
- btf_name_by_offset(env->btf,
- args[0].name_off));
+ __btf_name_by_offset(env->btf,
+ args[0].name_off));
for (i = 1; i < nr_args - 1; i++)
btf_verifier_log(env, ", %u %s", args[i].type,
- btf_name_by_offset(env->btf,
- args[i].name_off));
+ __btf_name_by_offset(env->btf,
+ args[i].name_off));
if (nr_args > 1) {
const struct btf_param *last_arg = &args[nr_args - 1];
if (last_arg->type)
btf_verifier_log(env, ", %u %s", last_arg->type,
- btf_name_by_offset(env->btf,
- last_arg->name_off));
+ __btf_name_by_offset(env->btf,
+ last_arg->name_off));
else
btf_verifier_log(env, ", vararg");
}
@@ -1967,6 +2263,7 @@ static struct btf_kind_operations func_proto_ops = {
* Hence, there is no btf_func_check_member().
*/
.check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
.log_details = btf_func_proto_log,
.seq_show = btf_df_seq_show,
};
@@ -1986,6 +2283,11 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_kflag(t)) {
+ btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
return 0;
@@ -1995,6 +2297,7 @@ static struct btf_kind_operations func_ops = {
.check_meta = btf_func_check_meta,
.resolve = btf_df_resolve,
.check_member = btf_df_check_member,
+ .check_kflag_member = btf_df_check_kflag_member,
.log_details = btf_ref_type_log,
.seq_show = btf_df_seq_show,
};
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 24aac0d0f412..8974b3755670 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -183,7 +183,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
* is not at a fixed memory location, with mixed length
* packets, which is bad for cache-line hotness.
*/
- frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom +
+ frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
pkt_data_start = xdpf->data - xdpf->headroom;
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index b65017dead44..07a34ef562a0 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -1,11 +1,13 @@
//SPDX-License-Identifier: GPL-2.0
#include <linux/bpf-cgroup.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/bug.h>
#include <linux/filter.h>
#include <linux/mm.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
+#include <uapi/linux/btf.h>
DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
@@ -308,6 +310,85 @@ static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
return -EINVAL;
}
+static int cgroup_storage_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
+ const struct btf_type *key_type,
+ const struct btf_type *value_type)
+{
+ struct btf_member *m;
+ u32 offset, size;
+
+ /* Key is expected to be of struct bpf_cgroup_storage_key type,
+ * which is:
+ * struct bpf_cgroup_storage_key {
+ * __u64 cgroup_inode_id;
+ * __u32 attach_type;
+ * };
+ */
+
+ /*
+ * Key_type must be a structure with two fields.
+ */
+ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
+ BTF_INFO_VLEN(key_type->info) != 2)
+ return -EINVAL;
+
+ /*
+ * The first field must be a 64 bit integer at 0 offset.
+ */
+ m = (struct btf_member *)(key_type + 1);
+ size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
+ if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
+ return -EINVAL;
+
+ /*
+ * The second field must be a 32 bit integer at 64 bit offset.
+ */
+ m++;
+ offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
+ size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
+ if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
+ return -EINVAL;
+
+ return 0;
+}
+
+static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
+ struct seq_file *m)
+{
+ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+ struct bpf_cgroup_storage_key *key = _key;
+ struct bpf_cgroup_storage *storage;
+ int cpu;
+
+ rcu_read_lock();
+ storage = cgroup_storage_lookup(map_to_storage(map), key, false);
+ if (!storage) {
+ rcu_read_unlock();
+ return;
+ }
+
+ btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+ stype = cgroup_storage_type(map);
+ if (stype == BPF_CGROUP_STORAGE_SHARED) {
+ seq_puts(m, ": ");
+ btf_type_seq_show(map->btf, map->btf_value_type_id,
+ &READ_ONCE(storage->buf)->data[0], m);
+ seq_puts(m, "\n");
+ } else {
+ seq_puts(m, ": {\n");
+ for_each_possible_cpu(cpu) {
+ seq_printf(m, "\tcpu%d: ", cpu);
+ btf_type_seq_show(map->btf, map->btf_value_type_id,
+ per_cpu_ptr(storage->percpu_buf, cpu),
+ m);
+ seq_puts(m, "\n");
+ }
+ seq_puts(m, "}\n");
+ }
+ rcu_read_unlock();
+}
+
const struct bpf_map_ops cgroup_storage_map_ops = {
.map_alloc = cgroup_storage_map_alloc,
.map_free = cgroup_storage_map_free,
@@ -315,7 +396,8 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
.map_lookup_elem = cgroup_storage_lookup_elem,
.map_update_elem = cgroup_storage_update_elem,
.map_delete_elem = cgroup_storage_delete_elem,
- .map_check_btf = map_check_no_btf,
+ .map_check_btf = cgroup_storage_check_btf,
+ .map_seq_show_elem = cgroup_storage_seq_show_elem,
};
int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index bfd4882e1106..abf1002080df 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -728,6 +728,7 @@ free_stack:
}
static int trie_check_btf(const struct bpf_map *map,
+ const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5745c7837621..0607db304def 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -456,6 +456,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
}
int map_check_no_btf(const struct bpf_map *map,
+ const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
@@ -478,7 +479,7 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
return -EINVAL;
if (map->ops->map_check_btf)
- ret = map->ops->map_check_btf(map, key_type, value_type);
+ ret = map->ops->map_check_btf(map, btf, key_type, value_type);
return ret;
}
@@ -1472,11 +1473,6 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
return -E2BIG;
-
- if (type == BPF_PROG_TYPE_KPROBE &&
- attr->kern_version != LINUX_VERSION_CODE)
- return -EINVAL;
-
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
!capable(CAP_SYS_ADMIN))
@@ -1608,6 +1604,7 @@ static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
bpf_prog_put(raw_tp->prog);
}
+ bpf_put_raw_tracepoint(raw_tp->btp);
kfree(raw_tp);
return 0;
}
@@ -1633,13 +1630,15 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
return -EFAULT;
tp_name[sizeof(tp_name) - 1] = 0;
- btp = bpf_find_raw_tracepoint(tp_name);
+ btp = bpf_get_raw_tracepoint(tp_name);
if (!btp)
return -ENOENT;
raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
- if (!raw_tp)
- return -ENOMEM;
+ if (!raw_tp) {
+ err = -ENOMEM;
+ goto out_put_btp;
+ }
raw_tp->btp = btp;
prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
@@ -1667,6 +1666,8 @@ out_put_prog:
bpf_prog_put(prog);
out_free_tp:
kfree(raw_tp);
+out_put_btp:
+ bpf_put_raw_tracepoint(btp);
return err;
}
@@ -2031,13 +2032,6 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
insns[i + 1].imm = 0;
continue;
}
-
- if (!bpf_dump_raw_ok() &&
- imm == (unsigned long)prog->aux) {
- insns[i].imm = 0;
- insns[i + 1].imm = 0;
- continue;
- }
}
return insns;
@@ -2271,33 +2265,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
ulen = info.nr_func_info;
info.nr_func_info = prog->aux->func_info_cnt;
if (info.nr_func_info && ulen) {
- if (bpf_dump_raw_ok()) {
- char __user *user_finfo;
+ char __user *user_finfo;
- user_finfo = u64_to_user_ptr(info.func_info);
- ulen = min_t(u32, info.nr_func_info, ulen);
- if (copy_to_user(user_finfo, prog->aux->func_info,
- info.func_info_rec_size * ulen))
- return -EFAULT;
- } else {
- info.func_info = 0;
- }
+ user_finfo = u64_to_user_ptr(info.func_info);
+ ulen = min_t(u32, info.nr_func_info, ulen);
+ if (copy_to_user(user_finfo, prog->aux->func_info,
+ info.func_info_rec_size * ulen))
+ return -EFAULT;
}
ulen = info.nr_line_info;
info.nr_line_info = prog->aux->nr_linfo;
if (info.nr_line_info && ulen) {
- if (bpf_dump_raw_ok()) {
- __u8 __user *user_linfo;
+ __u8 __user *user_linfo;
- user_linfo = u64_to_user_ptr(info.line_info);
- ulen = min_t(u32, info.nr_line_info, ulen);
- if (copy_to_user(user_linfo, prog->aux->linfo,
- info.line_info_rec_size * ulen))
- return -EFAULT;
- } else {
- info.line_info = 0;
- }
+ user_linfo = u64_to_user_ptr(info.line_info);
+ ulen = min_t(u32, info.nr_line_info, ulen);
+ if (copy_to_user(user_linfo, prog->aux->linfo,
+ info.line_info_rec_size * ulen))
+ return -EFAULT;
}
ulen = info.nr_jited_line_info;
@@ -2322,6 +2308,28 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
}
+ ulen = info.nr_prog_tags;
+ info.nr_prog_tags = prog->aux->func_cnt ? : 1;
+ if (ulen) {
+ __u8 __user (*user_prog_tags)[BPF_TAG_SIZE];
+ u32 i;
+
+ user_prog_tags = u64_to_user_ptr(info.prog_tags);
+ ulen = min_t(u32, info.nr_prog_tags, ulen);
+ if (prog->aux->func_cnt) {
+ for (i = 0; i < ulen; i++) {
+ if (copy_to_user(user_prog_tags[i],
+ prog->aux->func[i]->tag,
+ BPF_TAG_SIZE))
+ return -EFAULT;
+ }
+ } else {
+ if (copy_to_user(user_prog_tags[0],
+ prog->tag, BPF_TAG_SIZE))
+ return -EFAULT;
+ }
+ }
+
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 5b3c0a95244f..71d86e3024ae 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -26,6 +26,7 @@
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>
+#include <linux/ctype.h>
#include "disasm.h"
@@ -216,6 +217,27 @@ struct bpf_call_arg_meta {
static DEFINE_MUTEX(bpf_verifier_lock);
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+ const struct bpf_line_info *linfo;
+ const struct bpf_prog *prog;
+ u32 i, nr_linfo;
+
+ prog = env->prog;
+ nr_linfo = prog->aux->nr_linfo;
+
+ if (!nr_linfo || insn_off >= prog->len)
+ return NULL;
+
+ linfo = prog->aux->linfo;
+ for (i = 1; i < nr_linfo; i++)
+ if (insn_off < linfo[i].insn_off)
+ break;
+
+ return &linfo[i - 1];
+}
+
void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
va_list args)
{
@@ -266,6 +288,42 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
va_end(args);
}
+static const char *ltrim(const char *s)
+{
+ while (isspace(*s))
+ s++;
+
+ return s;
+}
+
+__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
+ u32 insn_off,
+ const char *prefix_fmt, ...)
+{
+ const struct bpf_line_info *linfo;
+
+ if (!bpf_verifier_log_needed(&env->log))
+ return;
+
+ linfo = find_linfo(env, insn_off);
+ if (!linfo || linfo == env->prev_linfo)
+ return;
+
+ if (prefix_fmt) {
+ va_list args;
+
+ va_start(args, prefix_fmt);
+ bpf_verifier_vlog(&env->log, prefix_fmt, args);
+ va_end(args);
+ }
+
+ verbose(env, "%s\n",
+ ltrim(btf_name_by_offset(env->prog->aux->btf,
+ linfo->line_off)));
+
+ env->prev_linfo = linfo;
+}
+
static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_PACKET ||
@@ -339,12 +397,14 @@ static char slot_type_char[] = {
static void print_liveness(struct bpf_verifier_env *env,
enum bpf_reg_liveness live)
{
- if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+ if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
verbose(env, "_");
if (live & REG_LIVE_READ)
verbose(env, "r");
if (live & REG_LIVE_WRITTEN)
verbose(env, "w");
+ if (live & REG_LIVE_DONE)
+ verbose(env, "D");
}
static struct bpf_func_state *func(struct bpf_verifier_env *env,
@@ -1074,6 +1134,12 @@ static int mark_reg_read(struct bpf_verifier_env *env,
/* if read wasn't screened by an earlier write ... */
if (writes && state->live & REG_LIVE_WRITTEN)
break;
+ if (parent->live & REG_LIVE_DONE) {
+ verbose(env, "verifier BUG type %s var_off %lld off %d\n",
+ reg_type_str[parent->type],
+ parent->var_off.value, parent->off);
+ return -EFAULT;
+ }
/* ... then we depend on parent's value */
parent->live |= REG_LIVE_READ;
state = parent;
@@ -1220,6 +1286,10 @@ static int check_stack_write(struct bpf_verifier_env *env,
/* regular write of data into stack destroys any spilled ptr */
state->stack[spi].spilled_ptr.type = NOT_INIT;
+ /* Mark slots as STACK_MISC if they belonged to spilled ptr. */
+ if (state->stack[spi].slot_type[0] == STACK_SPILL)
+ for (i = 0; i < BPF_REG_SIZE; i++)
+ state->stack[spi].slot_type[i] = STACK_MISC;
/* only mark the slot as written if all 8 bytes were written
* otherwise read propagation may incorrectly stop too soon
@@ -1237,6 +1307,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
register_is_null(&cur->regs[value_regno]))
type = STACK_ZERO;
+ /* Mark slots affected by this stack write. */
for (i = 0; i < size; i++)
state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
type;
@@ -3788,6 +3859,12 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
break;
+ case BPF_JSET:
+ if ((~reg->var_off.mask & reg->var_off.value) & val)
+ return 1;
+ if (!((reg->var_off.mask | reg->var_off.value) & val))
+ return 0;
+ break;
case BPF_JGT:
if (reg->umin_value > val)
return 1;
@@ -3872,6 +3949,13 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
*/
__mark_reg_known(false_reg, val);
break;
+ case BPF_JSET:
+ false_reg->var_off = tnum_and(false_reg->var_off,
+ tnum_const(~val));
+ if (is_power_of_2(val))
+ true_reg->var_off = tnum_or(true_reg->var_off,
+ tnum_const(val));
+ break;
case BPF_JGT:
false_reg->umax_value = min(false_reg->umax_value, val);
true_reg->umin_value = max(true_reg->umin_value, val + 1);
@@ -3944,6 +4028,13 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
*/
__mark_reg_known(false_reg, val);
break;
+ case BPF_JSET:
+ false_reg->var_off = tnum_and(false_reg->var_off,
+ tnum_const(~val));
+ if (is_power_of_2(val))
+ true_reg->var_off = tnum_or(true_reg->var_off,
+ tnum_const(val));
+ break;
case BPF_JGT:
true_reg->umax_value = min(true_reg->umax_value, val - 1);
false_reg->umin_value = max(false_reg->umin_value, val);
@@ -4561,6 +4652,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
return 0;
if (w < 0 || w >= env->prog->len) {
+ verbose_linfo(env, t, "%d: ", t);
verbose(env, "jump out of range from insn %d to %d\n", t, w);
return -EINVAL;
}
@@ -4578,6 +4670,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
insn_stack[cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
+ verbose_linfo(env, t, "%d: ", t);
+ verbose_linfo(env, w, "%d: ", w);
verbose(env, "back-edge from insn %d to %d\n", t, w);
return -EINVAL;
} else if (insn_state[w] == EXPLORED) {
@@ -4600,10 +4694,6 @@ static int check_cfg(struct bpf_verifier_env *env)
int ret = 0;
int i, t;
- ret = check_subprogs(env);
- if (ret < 0)
- return ret;
-
insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
@@ -4910,8 +5000,16 @@ static int check_btf_line(struct bpf_verifier_env *env,
goto err_free;
}
- if (!btf_name_offset_valid(btf, linfo[i].line_off) ||
- !btf_name_offset_valid(btf, linfo[i].file_name_off)) {
+ if (!prog->insnsi[linfo[i].insn_off].code) {
+ verbose(env,
+ "Invalid insn code at line_info[%u].insn_off\n",
+ i);
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ if (!btf_name_by_offset(btf, linfo[i].line_off) ||
+ !btf_name_by_offset(btf, linfo[i].file_name_off)) {
verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
err = -EINVAL;
goto err_free;
@@ -5021,6 +5119,102 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
return false;
}
+static void clean_func_state(struct bpf_verifier_env *env,
+ struct bpf_func_state *st)
+{
+ enum bpf_reg_liveness live;
+ int i, j;
+
+ for (i = 0; i < BPF_REG_FP; i++) {
+ live = st->regs[i].live;
+ /* liveness must not touch this register anymore */
+ st->regs[i].live |= REG_LIVE_DONE;
+ if (!(live & REG_LIVE_READ))
+ /* since the register is unused, clear its state
+ * to make further comparison simpler
+ */
+ __mark_reg_not_init(&st->regs[i]);
+ }
+
+ for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
+ live = st->stack[i].spilled_ptr.live;
+ /* liveness must not touch this stack slot anymore */
+ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
+ if (!(live & REG_LIVE_READ)) {
+ __mark_reg_not_init(&st->stack[i].spilled_ptr);
+ for (j = 0; j < BPF_REG_SIZE; j++)
+ st->stack[i].slot_type[j] = STACK_INVALID;
+ }
+ }
+}
+
+static void clean_verifier_state(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st)
+{
+ int i;
+
+ if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
+ /* all regs in this state in all frames were already marked */
+ return;
+
+ for (i = 0; i <= st->curframe; i++)
+ clean_func_state(env, st->frame[i]);
+}
+
+/* the parentage chains form a tree.
+ * the verifier states are added to state lists at given insn and
+ * pushed into state stack for future exploration.
+ * when the verifier reaches bpf_exit insn some of the verifer states
+ * stored in the state lists have their final liveness state already,
+ * but a lot of states will get revised from liveness point of view when
+ * the verifier explores other branches.
+ * Example:
+ * 1: r0 = 1
+ * 2: if r1 == 100 goto pc+1
+ * 3: r0 = 2
+ * 4: exit
+ * when the verifier reaches exit insn the register r0 in the state list of
+ * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch
+ * of insn 2 and goes exploring further. At the insn 4 it will walk the
+ * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ.
+ *
+ * Since the verifier pushes the branch states as it sees them while exploring
+ * the program the condition of walking the branch instruction for the second
+ * time means that all states below this branch were already explored and
+ * their final liveness markes are already propagated.
+ * Hence when the verifier completes the search of state list in is_state_visited()
+ * we can call this clean_live_states() function to mark all liveness states
+ * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
+ * will not be used.
+ * This function also clears the registers and stack for states that !READ
+ * to simplify state merging.
+ *
+ * Important note here that walking the same branch instruction in the callee
+ * doesn't meant that the states are DONE. The verifier has to compare
+ * the callsites
+ */
+static void clean_live_states(struct bpf_verifier_env *env, int insn,
+ struct bpf_verifier_state *cur)
+{
+ struct bpf_verifier_state_list *sl;
+ int i;
+
+ sl = env->explored_states[insn];
+ if (!sl)
+ return;
+
+ while (sl != STATE_LIST_MARK) {
+ if (sl->state.curframe != cur->curframe)
+ goto next;
+ for (i = 0; i <= cur->curframe; i++)
+ if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
+ goto next;
+ clean_verifier_state(env, &sl->state);
+next:
+ sl = sl->next;
+ }
+}
+
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
struct idpair *idmap)
@@ -5134,12 +5328,6 @@ static bool stacksafe(struct bpf_func_state *old,
{
int i, spi;
- /* if explored stack has more populated slots than current stack
- * such stacks are not equivalent
- */
- if (old->allocated_stack > cur->allocated_stack)
- return false;
-
/* walk slots of the explored stack and ignore any additional
* slots in the current stack, since explored(safe) state
* didn't use them
@@ -5147,12 +5335,21 @@ static bool stacksafe(struct bpf_func_state *old,
for (i = 0; i < old->allocated_stack; i++) {
spi = i / BPF_REG_SIZE;
- if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+ i += BPF_REG_SIZE - 1;
/* explored state didn't use this */
continue;
+ }
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
continue;
+
+ /* explored stack has more populated slots than current stack
+ * and these slots were used
+ */
+ if (i >= cur->allocated_stack)
+ return false;
+
/* if old state was safe with misc data in the stack
* it will be safe with zero-initialized stack.
* The opposite is not true
@@ -5336,6 +5533,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
*/
return 0;
+ clean_live_states(env, insn_idx, cur);
+
while (sl != STATE_LIST_MARK) {
if (states_equal(env, &sl->state, cur)) {
/* reached equivalent register/stack state,
@@ -5455,6 +5654,8 @@ static int do_check(struct bpf_verifier_env *env)
int insn_processed = 0;
bool do_print_state = false;
+ env->prev_linfo = NULL;
+
state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
if (!state)
return -ENOMEM;
@@ -5528,6 +5729,7 @@ static int do_check(struct bpf_verifier_env *env)
.private_data = env,
};
+ verbose_linfo(env, insn_idx, "; ");
verbose(env, "%d: ", insn_idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
@@ -6762,7 +6964,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
- ret = check_cfg(env);
+ ret = check_subprogs(env);
if (ret < 0)
goto skip_full_check;
@@ -6770,6 +6972,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (ret < 0)
goto skip_full_check;
+ ret = check_cfg(env);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = do_check(env);
if (env->cur_state) {
free_verifier_state(env->cur_state, true);
@@ -6784,10 +6990,11 @@ skip_full_check:
free_states(env);
if (ret == 0)
- sanitize_dead_code(env);
+ ret = check_max_stack_depth(env);
+ /* instruction rewrites happen after this point */
if (ret == 0)
- ret = check_max_stack_depth(env);
+ sanitize_dead_code(env);
if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
diff --git a/kernel/module.c b/kernel/module.c
index 49a405891587..06ec68f08387 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3093,6 +3093,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
sizeof(*mod->tracepoints_ptrs),
&mod->num_tracepoints);
#endif
+#ifdef CONFIG_BPF_EVENTS
+ mod->bpf_raw_events = section_objs(info, "__bpf_raw_tp_map",
+ sizeof(*mod->bpf_raw_events),
+ &mod->num_bpf_raw_events);
+#endif
#ifdef HAVE_JUMP_LABEL
mod->jump_entries = section_objs(info, "__jump_table",
sizeof(*mod->jump_entries),
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9864a35c8bb5..9ddb6fddb4e0 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -17,6 +17,43 @@
#include "trace_probe.h"
#include "trace.h"
+#ifdef CONFIG_MODULES
+struct bpf_trace_module {
+ struct module *module;
+ struct list_head list;
+};
+
+static LIST_HEAD(bpf_trace_modules);
+static DEFINE_MUTEX(bpf_module_mutex);
+
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+ struct bpf_raw_event_map *btp, *ret = NULL;
+ struct bpf_trace_module *btm;
+ unsigned int i;
+
+ mutex_lock(&bpf_module_mutex);
+ list_for_each_entry(btm, &bpf_trace_modules, list) {
+ for (i = 0; i < btm->module->num_bpf_raw_events; ++i) {
+ btp = &btm->module->bpf_raw_events[i];
+ if (!strcmp(btp->tp->name, name)) {
+ if (try_module_get(btm->module))
+ ret = btp;
+ goto out;
+ }
+ }
+ }
+out:
+ mutex_unlock(&bpf_module_mutex);
+ return ret;
+}
+#else
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+ return NULL;
+}
+#endif /* CONFIG_MODULES */
+
u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
@@ -1076,7 +1113,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
extern struct bpf_raw_event_map __start__bpf_raw_tp[];
extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
-struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
{
struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
@@ -1084,7 +1121,16 @@ struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
if (!strcmp(btp->tp->name, name))
return btp;
}
- return NULL;
+
+ return bpf_get_raw_tracepoint_module(name);
+}
+
+void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
+{
+ struct module *mod = __module_address((unsigned long)btp);
+
+ if (mod)
+ module_put(mod);
}
static __always_inline
@@ -1222,3 +1268,52 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
return err;
}
+
+#ifdef CONFIG_MODULES
+int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module)
+{
+ struct bpf_trace_module *btm, *tmp;
+ struct module *mod = module;
+
+ if (mod->num_bpf_raw_events == 0 ||
+ (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+ return 0;
+
+ mutex_lock(&bpf_module_mutex);
+
+ switch (op) {
+ case MODULE_STATE_COMING:
+ btm = kzalloc(sizeof(*btm), GFP_KERNEL);
+ if (btm) {
+ btm->module = module;
+ list_add(&btm->list, &bpf_trace_modules);
+ }
+ break;
+ case MODULE_STATE_GOING:
+ list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) {
+ if (btm->module == module) {
+ list_del(&btm->list);
+ kfree(btm);
+ break;
+ }
+ }
+ break;
+ }
+
+ mutex_unlock(&bpf_module_mutex);
+
+ return 0;
+}
+
+static struct notifier_block bpf_module_nb = {
+ .notifier_call = bpf_event_notify,
+};
+
+int __init bpf_event_init(void)
+{
+ register_module_notifier(&bpf_module_nb);
+ return 0;
+}
+
+fs_initcall(bpf_event_init);
+#endif /* CONFIG_MODULES */