summaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/btf.c82
-rw-r--r--kernel/bpf/core.c38
-rw-r--r--kernel/bpf/local_storage.c3
-rw-r--r--kernel/bpf/queue_stack_maps.c16
-rw-r--r--kernel/bpf/syscall.c35
-rw-r--r--kernel/bpf/verifier.c126
6 files changed, 254 insertions, 46 deletions
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index ee4c82667d65..4da543d6bea2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5,6 +5,7 @@
#include <uapi/linux/types.h>
#include <linux/seq_file.h>
#include <linux/compiler.h>
+#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>
@@ -426,6 +427,30 @@ 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)
+{
+ /* offset must be valid */
+ const char *src = &btf->strings[offset];
+ const char *src_limit;
+
+ if (!isalpha(*src) && *src != '_')
+ return false;
+
+ /* set a limit on identifier length */
+ src_limit = src + KSYM_NAME_LEN;
+ src++;
+ while (*src && src < src_limit) {
+ if (!isalnum(*src) && *src != '_')
+ return false;
+ src++;
+ }
+
+ return !*src;
+}
+
static const char *btf_name_by_offset(const struct btf *btf, u32 offset)
{
if (!offset)
@@ -1143,6 +1168,22 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* typedef type must have a valid name, and other ref types,
+ * volatile, const, restrict, should have a null name.
+ */
+ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ } else {
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+ }
+
btf_verifier_log_type(env, t, NULL);
return 0;
@@ -1300,6 +1341,13 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* fwd type must have a valid name */
+ if (!t->name_off ||
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
return 0;
@@ -1356,6 +1404,12 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* array type should not have a name */
+ if (t->name_off) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
if (btf_type_vlen(t)) {
btf_verifier_log_type(env, t, "vlen != 0");
return -EINVAL;
@@ -1532,6 +1586,13 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* struct type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
last_offset = 0;
@@ -1543,6 +1604,12 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* struct member either no name or a valid one */
+ if (member->name_off &&
+ !btf_name_valid_identifier(btf, member->name_off)) {
+ btf_verifier_log_member(env, t, member, "Invalid name");
+ return -EINVAL;
+ }
/* A member cannot be in type void */
if (!member->type || !BTF_TYPE_ID_VALID(member->type)) {
btf_verifier_log_member(env, t, member,
@@ -1730,6 +1797,13 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* enum type either no name or a valid one */
+ if (t->name_off &&
+ !btf_name_valid_identifier(env->btf, t->name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
btf_verifier_log_type(env, t, NULL);
for (i = 0; i < nr_enums; i++) {
@@ -1739,6 +1813,14 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /* enum member must have a valid name */
+ if (!enums[i].name_off ||
+ !btf_name_valid_identifier(btf, enums[i].name_off)) {
+ btf_verifier_log_type(env, t, "Invalid name");
+ return -EINVAL;
+ }
+
+
btf_verifier_log(env, "\t%s val=%d\n",
btf_name_by_offset(btf, enums[i].name_off),
enums[i].val);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6377225b2082..b1a3545d0ec8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -553,7 +553,6 @@ bool is_bpf_text_address(unsigned long addr)
int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *sym)
{
- unsigned long symbol_start, symbol_end;
struct bpf_prog_aux *aux;
unsigned int it = 0;
int ret = -ERANGE;
@@ -566,10 +565,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
if (it++ != symnum)
continue;
- bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end);
bpf_get_prog_name(aux->prog, sym);
- *value = symbol_start;
+ *value = (unsigned long)aux->prog->bpf_func;
*type = BPF_SYM_ELF_TYPE;
ret = 0;
@@ -674,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
bpf_prog_unlock_free(fp);
}
+int bpf_jit_get_func_addr(const struct bpf_prog *prog,
+ const struct bpf_insn *insn, bool extra_pass,
+ u64 *func_addr, bool *func_addr_fixed)
+{
+ s16 off = insn->off;
+ s32 imm = insn->imm;
+ u8 *addr;
+
+ *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
+ if (!*func_addr_fixed) {
+ /* Place-holder address till the last pass has collected
+ * all addresses for JITed subprograms in which case we
+ * can pick them up from prog->aux.
+ */
+ if (!extra_pass)
+ addr = NULL;
+ else if (prog->aux->func &&
+ off >= 0 && off < prog->aux->func_cnt)
+ addr = (u8 *)prog->aux->func[off]->bpf_func;
+ else
+ return -EINVAL;
+ } else {
+ /* Address of a BPF helper call. Since part of the core
+ * kernel, it's always at a fixed location. __bpf_call_base
+ * and the helper with imm relative to it are both in core
+ * kernel.
+ */
+ addr = (u8 *)__bpf_call_base + imm;
+ }
+
+ *func_addr = (unsigned long)addr;
+ return 0;
+}
+
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
struct bpf_insn *to_buff)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index c97a8f968638..bed9d48a7ae9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return -ENOENT;
new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
- map->value_size, __GFP_ZERO | GFP_USER,
+ map->value_size,
+ __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN,
map->numa_node);
if (!new)
return -ENOMEM;
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8bbd72d3a121..b384ea9f3254 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -7,6 +7,7 @@
#include <linux/bpf.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/capability.h>
#include "percpu_freelist.h"
#define QUEUE_STACK_CREATE_FLAG_MASK \
@@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
/* 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)
return -EINVAL;
@@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
{
int ret, numa_node = bpf_map_attr_numa_node(attr);
struct bpf_queue_stack *qs;
- u32 size, value_size;
- u64 queue_size, cost;
-
- size = attr->max_entries + 1;
- value_size = attr->value_size;
-
- queue_size = sizeof(*qs) + (u64) value_size * size;
+ u64 size, queue_size, cost;
- cost = queue_size;
+ size = (u64) attr->max_entries + 1;
+ cost = queue_size = sizeof(*qs) + size * attr->value_size;
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ccb93277aae2..cf5040fd5434 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
info.nr_jited_ksyms = 0;
+ info.nr_jited_func_lens = 0;
goto done;
}
@@ -2158,11 +2159,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
ulen = info.nr_jited_ksyms;
- info.nr_jited_ksyms = prog->aux->func_cnt;
+ info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
if (info.nr_jited_ksyms && ulen) {
if (bpf_dump_raw_ok()) {
+ unsigned long ksym_addr;
u64 __user *user_ksyms;
- ulong ksym_addr;
u32 i;
/* copy the address of the kernel symbol
@@ -2170,10 +2171,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
*/
ulen = min_t(u32, info.nr_jited_ksyms, ulen);
user_ksyms = u64_to_user_ptr(info.jited_ksyms);
- for (i = 0; i < ulen; i++) {
- ksym_addr = (ulong) prog->aux->func[i]->bpf_func;
- ksym_addr &= PAGE_MASK;
- if (put_user((u64) ksym_addr, &user_ksyms[i]))
+ if (prog->aux->func_cnt) {
+ for (i = 0; i < ulen; i++) {
+ ksym_addr = (unsigned long)
+ prog->aux->func[i]->bpf_func;
+ if (put_user((u64) ksym_addr,
+ &user_ksyms[i]))
+ return -EFAULT;
+ }
+ } else {
+ ksym_addr = (unsigned long) prog->bpf_func;
+ if (put_user((u64) ksym_addr, &user_ksyms[0]))
return -EFAULT;
}
} else {
@@ -2182,7 +2190,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
}
ulen = info.nr_jited_func_lens;
- info.nr_jited_func_lens = prog->aux->func_cnt;
+ info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
if (info.nr_jited_func_lens && ulen) {
if (bpf_dump_raw_ok()) {
u32 __user *user_lens;
@@ -2191,9 +2199,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
/* copy the JITed image lengths for each function */
ulen = min_t(u32, info.nr_jited_func_lens, ulen);
user_lens = u64_to_user_ptr(info.jited_func_lens);
- for (i = 0; i < ulen; i++) {
- func_len = prog->aux->func[i]->jited_len;
- if (put_user(func_len, &user_lens[i]))
+ if (prog->aux->func_cnt) {
+ for (i = 0; i < ulen; i++) {
+ func_len =
+ prog->aux->func[i]->jited_len;
+ if (put_user(func_len, &user_lens[i]))
+ return -EFAULT;
+ }
+ } else {
+ func_len = prog->jited_len;
+ if (put_user(func_len, &user_lens[0]))
return -EFAULT;
}
} else {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 171a2c88e77d..fc760d00a38c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -175,6 +175,7 @@ struct bpf_verifier_stack_elem {
#define BPF_COMPLEXITY_LIMIT_INSNS 131072
#define BPF_COMPLEXITY_LIMIT_STACK 1024
+#define BPF_COMPLEXITY_LIMIT_STATES 64
#define BPF_MAP_PTR_UNPRIV 1UL
#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
@@ -2852,10 +2853,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- else
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
@@ -2868,7 +2865,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
- regs[BPF_REG_0].id = ++env->id_gen;
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ } else {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ regs[BPF_REG_0].id = ++env->id_gen;
+ }
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
int id = acquire_reference_state(env, insn_idx);
if (id < 0)
@@ -3046,7 +3048,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->off = ptr_reg->off + smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. Note that off_reg->off
@@ -3076,10 +3078,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_SUB:
@@ -3108,7 +3111,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
dst_reg->var_off = ptr_reg->var_off;
dst_reg->id = ptr_reg->id;
dst_reg->off = ptr_reg->off - smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. If the subtrahend is known
@@ -3134,11 +3137,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_AND:
@@ -3748,6 +3752,79 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
}
}
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ * 1 - branch will be taken and "goto target" will be executed
+ * 0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+ if (__is_pointer_value(false, reg))
+ return -1;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ if (tnum_is_const(reg->var_off))
+ return !!tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JNE:
+ if (tnum_is_const(reg->var_off))
+ return !tnum_equals_const(reg->var_off, val);
+ break;
+ case BPF_JGT:
+ if (reg->umin_value > val)
+ return 1;
+ else if (reg->umax_value <= val)
+ return 0;
+ break;
+ case BPF_JSGT:
+ if (reg->smin_value > (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLT:
+ if (reg->umax_value < val)
+ return 1;
+ else if (reg->umin_value >= val)
+ return 0;
+ break;
+ case BPF_JSLT:
+ if (reg->smax_value < (s64)val)
+ return 1;
+ else if (reg->smin_value >= (s64)val)
+ return 0;
+ break;
+ case BPF_JGE:
+ if (reg->umin_value >= val)
+ return 1;
+ else if (reg->umax_value < val)
+ return 0;
+ break;
+ case BPF_JSGE:
+ if (reg->smin_value >= (s64)val)
+ return 1;
+ else if (reg->smax_value < (s64)val)
+ return 0;
+ break;
+ case BPF_JLE:
+ if (reg->umax_value <= val)
+ return 1;
+ else if (reg->umin_value > val)
+ return 0;
+ break;
+ case BPF_JSLE:
+ if (reg->smax_value <= (s64)val)
+ return 1;
+ else if (reg->smin_value > (s64)val)
+ return 0;
+ break;
+ }
+
+ return -1;
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
@@ -4149,21 +4226,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
dst_reg = &regs[insn->dst_reg];
- /* detect if R == 0 where R was initialized to zero earlier */
- if (BPF_SRC(insn->code) == BPF_K &&
- (opcode == BPF_JEQ || opcode == BPF_JNE) &&
- dst_reg->type == SCALAR_VALUE &&
- tnum_is_const(dst_reg->var_off)) {
- if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) ||
- (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) {
- /* if (imm == imm) goto pc+off;
- * only follow the goto, ignore fall-through
- */
+ if (BPF_SRC(insn->code) == BPF_K) {
+ int pred = is_branch_taken(dst_reg, insn->imm, opcode);
+
+ if (pred == 1) {
+ /* only follow the goto, ignore fall-through */
*insn_idx += insn->off;
return 0;
- } else {
- /* if (imm != imm) goto pc+off;
- * only follow fall-through branch, since
+ } else if (pred == 0) {
+ /* only follow fall-through branch, since
* that's where the program will go
*/
return 0;
@@ -4977,7 +5048,7 @@ 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 *cur = env->cur_state, *new;
- int i, j, err;
+ int i, j, err, states_cnt = 0;
sl = env->explored_states[insn_idx];
if (!sl)
@@ -5004,8 +5075,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
return 1;
}
sl = sl->next;
+ states_cnt++;
}
+ if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+ return 0;
+
/* there were no equivalent states, remember current one.
* technically the current state is not proven to be safe yet,
* but it will either reach outer most bpf_exit (which means it's safe)
@@ -5145,6 +5220,9 @@ static int do_check(struct bpf_verifier_env *env)
goto process_bpf_exit;
}
+ if (signal_pending(current))
+ return -EAGAIN;
+
if (need_resched())
cond_resched();
@@ -5647,7 +5725,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len
return;
/* NOTE: fake 'exit' subprog should be updated as well. */
for (i = 0; i <= env->subprog_cnt; i++) {
- if (env->subprog_info[i].start < off)
+ if (env->subprog_info[i].start <= off)
continue;
env->subprog_info[i].start += len - 1;
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-03-19 12:41:26 +0000