NoaSoftware
/
TencentOS-kernel
forked from TencentOS/TencentOS-kernel
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

bpf: Add bpf_for_each_map_elem() helper 

[upstream commit 69c087ba6225b574afb6e505b72cb75242a3d844]

The bpf_for_each_map_elem() helper is introduced which
iterates all map elements with a callback function. The
helper signature looks like
  long bpf_for_each_map_elem(map, callback_fn, callback_ctx, flags)
and for each map element, the callback_fn will be called. For example,
like hashmap, the callback signature may look like
  long callback_fn(map, key, val, callback_ctx)

There are two known use cases for this. One is from upstream ([1]) where
a for_each_map_elem helper may help implement a timeout mechanism
in a more generic way. Another is from our internal discussion
for a firewall use case where a map contains all the rules. The packet
data can be compared to all these rules to decide allow or deny
the packet.

For array maps, users can already use a bounded loop to traverse
elements. Using this helper can avoid using bounded loop. For other
type of maps (e.g., hash maps) where bounded loop is hard or
impossible to use, this helper provides a convenient way to
operate on all elements.

For callback_fn, besides map and map element, a callback_ctx,
allocated on caller stack, is also passed to the callback
function. This callback_ctx argument can provide additional
input and allow to write to caller stack for output.

If the callback_fn returns 0, the helper will iterate through next
element if available. If the callback_fn returns 1, the helper
will stop iterating and returns to the bpf program. Other return
values are not used for now.

Currently, this helper is only available with jit. It is possible
to make it work with interpreter with so effort but I leave it
as the future work.

[1]: https://lore.kernel.org/bpf/20210122205415.113822-1-xiyou.wangcong@gmail.com/

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210226204925.3884923-1-yhs@fb.com
This commit is contained in:
Yonghong Song 2021-02-26 12:49:25 -08:00 committed by Menglong Dong
parent 8a81a447b6
commit dfaec15bb0
8 changed files with 276 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
include/linux/bpf.h
View File

@ -39,6 +39,7 @@ struct bpf_local_storage_map;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
struct bpf_func_state;
typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
struct bpf_iter_aux_info *aux);
@ -103,6 +104,13 @@ struct bpf_map_ops {
void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
void *owner, u32 size);
struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee);
int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn,
void *callback_ctx, u64 flags);
/* BTF name and id of struct allocated by map_alloc */
const char * const map_btf_name;
int *map_btf_id;
@ -265,6 +273,9 @@ enum bpf_arg_type {
ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */
ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */
ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */
ARG_PTR_TO_FUNC, /* pointer to a bpf program function */
ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */
__BPF_ARG_TYPE_MAX,
};
/* type of values returned from helper functions */
@ -357,6 +368,8 @@ enum bpf_reg_type {
PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
PTR_TO_MEM, /* reg points to valid memory region */
PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */
PTR_TO_FUNC, /* reg points to a bpf program function */
PTR_TO_MAP_KEY, /* reg points to a map element key */
};
/* The information passed from prog-specific *_is_valid_access
@ -1622,6 +1635,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
const struct bpf_func_proto *bpf_tracing_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);

3
include/linux/bpf_verifier.h
View File

@ -57,6 +57,8 @@ struct bpf_reg_state {
/* Max size from any of the above. */
unsigned long raw;
u32 subprogno; /* for PTR_TO_FUNC */
};
/* Fixed part of pointer offset, pointer types only */
s32 off;
@ -191,6 +193,7 @@ struct bpf_func_state {
int acquired_refs;
struct bpf_reference_state *refs;
int allocated_stack;
bool in_callback_fn;
struct bpf_stack_state *stack;
};

9
include/uapi/linux/bpf.h
View File

@ -382,6 +382,15 @@ enum bpf_link_type {
* is struct/union.
*/
#define BPF_PSEUDO_BTF_ID 3
/* insn[0].src_reg: BPF_PSEUDO_FUNC
* insn[0].imm: insn offset to the func
* insn[1].imm: 0
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of the function
* verifier type: PTR_TO_FUNC.
*/
#define BPF_PSEUDO_FUNC 4
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function

16
kernel/bpf/bpf_iter.c
View File

@ -588,3 +588,19 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx)
*/
return ret == 0 ? 0 : -EAGAIN;
}
BPF_CALL_4(bpf_for_each_map_elem, struct bpf_map *, map, void *, callback_fn,
void *, callback_ctx, u64, flags)
{
return map->ops->map_for_each_callback(map, callback_fn, callback_ctx, flags);
}
const struct bpf_func_proto bpf_for_each_map_elem_proto = {
.func = bpf_for_each_map_elem,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_FUNC,
.arg3_type = ARG_PTR_TO_STACK_OR_NULL,
.arg4_type = ARG_ANYTHING,
};

208
kernel/bpf/verifier.c
View File

@ -231,6 +231,12 @@ static bool bpf_pseudo_call(const struct bpf_insn *insn)
insn->src_reg == BPF_PSEUDO_CALL;
}
static bool bpf_pseudo_func(const struct bpf_insn *insn)
{
return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
insn->src_reg == BPF_PSEUDO_FUNC;
}
struct bpf_call_arg_meta {
struct bpf_map *map_ptr;
bool raw_mode;
@ -242,6 +248,7 @@ struct bpf_call_arg_meta {
int ref_obj_id;
int func_id;
u32 btf_id;
u32 subprogno;
};
struct btf *btf_vmlinux;
@ -409,6 +416,7 @@ static bool reg_type_not_null(enum bpf_reg_type type)
return type == PTR_TO_SOCKET ||
type == PTR_TO_TCP_SOCK ||
type == PTR_TO_MAP_VALUE ||
type == PTR_TO_MAP_KEY ||
type == PTR_TO_SOCK_COMMON ||
type == PTR_TO_BTF_ID;
}
@ -520,6 +528,8 @@ static const char * const reg_type_str[] = {
[PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
[PTR_TO_RDWR_BUF] = "rdwr_buf",
[PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
[PTR_TO_FUNC] = "func",
[PTR_TO_MAP_KEY] = "map_key",
};
static char slot_type_char[] = {
@ -590,6 +600,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
if (type_is_pkt_pointer(t))
verbose(env, ",r=%d", reg->range);
else if (t == CONST_PTR_TO_MAP ||
t == PTR_TO_MAP_KEY ||
t == PTR_TO_MAP_VALUE ||
t == PTR_TO_MAP_VALUE_OR_NULL)
verbose(env, ",ks=%d,vs=%d",
@ -1269,6 +1280,19 @@ static int check_subprogs(struct bpf_verifier_env *env)
/* determine subprog starts. The end is one before the next starts */
for (i = 0; i < insn_cnt; i++) {
if (bpf_pseudo_func(insn + i)) {
if (!env->bpf_capable) {
verbose(env,
"function pointers are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
return -EPERM;
}
ret = add_subprog(env, i + insn[i].imm + 1);
if (ret < 0)
return ret;
/* remember subprog */
insn[i + 1].imm = ret;
continue;
}
if (!bpf_pseudo_call(insn + i))
continue;
if (!env->bpf_capable) {
@ -1994,6 +2018,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
case PTR_TO_RDONLY_BUF_OR_NULL:
case PTR_TO_RDWR_BUF:
case PTR_TO_RDWR_BUF_OR_NULL:
case PTR_TO_FUNC:
case PTR_TO_MAP_KEY:
return true;
default:
return false;
@ -2300,6 +2326,10 @@ static int __check_mem_access(struct bpf_verifier_env *env, int regno,
reg = &cur_regs(env)[regno];
switch (reg->type) {
case PTR_TO_MAP_KEY:
verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n",
mem_size, off, size);
break;
case PTR_TO_MAP_VALUE:
verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
mem_size, off, size);
@ -2699,6 +2729,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
case PTR_TO_FLOW_KEYS:
pointer_desc = "flow keys ";
break;
case PTR_TO_MAP_KEY:
pointer_desc = "key ";
break;
case PTR_TO_MAP_VALUE:
pointer_desc = "value ";
break;
@ -2798,7 +2831,7 @@ process_func:
continue_func:
subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
if (!bpf_pseudo_call(insn + i))
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
/* remember insn and function to return to */
ret_insn[frame] = i + 1;
@ -3121,7 +3154,19 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
/* for access checks, reg->off is just part of off */
off += reg->off;
if (reg->type == PTR_TO_MAP_VALUE) {
if (reg->type == PTR_TO_MAP_KEY) {
if (t == BPF_WRITE) {
verbose(env, "write to change key R%d not allowed\n", regno);
return -EACCES;
}
err = check_mem_region_access(env, regno, off, size,
reg->map_ptr->key_size, false);
if (err)
return err;
if (value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_MAP_VALUE) {
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
verbose(env, "R%d leaks addr into map\n", value_regno);
@ -3512,6 +3557,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
case PTR_TO_PACKET_META:
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_KEY:
return check_mem_region_access(env, regno, reg->off, access_size,
reg->map_ptr->key_size, false);
case PTR_TO_MAP_VALUE:
if (check_map_access_type(env, regno, reg->off, access_size,
meta && meta->raw_mode ? BPF_WRITE :
@ -3708,6 +3756,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
/* final test in check_stack_boundary() */;
else if (!type_is_pkt_pointer(type) &&
type != PTR_TO_MAP_VALUE &&
type != PTR_TO_MAP_KEY &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_CONST_SIZE ||
@ -3825,6 +3874,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
type != PTR_TO_MAP_VALUE &&
type != expected_type)
goto err_type;
} else if (arg_type == ARG_PTR_TO_FUNC) {
expected_type = PTR_TO_FUNC;
if (type != expected_type)
goto err_type;
} else if (arg_type == ARG_PTR_TO_STACK_OR_NULL) {
expected_type = PTR_TO_STACK;
if (type != expected_type)
goto err_type;
} else {
verbose(env, "unsupported arg_type %d\n", arg_type);
return -EFAULT;
@ -3833,6 +3890,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
if (arg_type == ARG_CONST_MAP_PTR) {
/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
meta->map_ptr = reg->map_ptr;
} else if (arg_type == ARG_PTR_TO_FUNC) {
meta->subprogno = reg->subprogno;
} else if (arg_type == ARG_PTR_TO_MAP_KEY) {
/* bpf_map_xxx(..., map_ptr, ..., key) call:
* check that [key, key + map->key_size) are within
@ -4414,6 +4473,35 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return __check_func_call(env, insn, insn_idx, subprog, set_callee_state);
}
static int set_map_elem_callback_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee,
int insn_idx)
{
struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx];
struct bpf_map *map;
int err;
if (bpf_map_ptr_poisoned(insn_aux)) {
verbose(env, "tail_call abusing map_ptr\n");
return -EINVAL;
}
map = BPF_MAP_PTR(insn_aux->map_ptr_state);
if (!map->ops->map_set_for_each_callback_args ||
!map->ops->map_for_each_callback) {
verbose(env, "callback function not allowed for map\n");
return -ENOTSUPP;
}
err = map->ops->map_set_for_each_callback_args(env, caller, callee);
if (err)
return err;
callee->in_callback_fn = true;
return 0;
}
static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
@ -4436,8 +4524,22 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
state->curframe--;
caller = state->frame[state->curframe];
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
if (callee->in_callback_fn) {
/* enforce R0 return value range [0, 1]. */
struct tnum range = tnum_range(0, 1);
if (r0->type != SCALAR_VALUE) {
verbose(env, "R0 not a scalar value\n");
return -EACCES;
}
if (!tnum_in(range, r0->var_off)) {
verbose_invalid_scalar(env, r0, &range, "callback return", "R0");
return -EINVAL;
}
} else {
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
}
/* Transfer references to the caller */
err = transfer_reference_state(caller, callee);
@ -4510,7 +4612,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
func_id != BPF_FUNC_map_delete_elem &&
func_id != BPF_FUNC_map_push_elem &&
func_id != BPF_FUNC_map_pop_elem &&
func_id != BPF_FUNC_map_peek_elem)
func_id != BPF_FUNC_map_peek_elem &&
func_id != BPF_FUNC_for_each_map_elem)
return 0;
if (map == NULL) {
@ -4591,15 +4694,18 @@ static int check_reference_leak(struct bpf_verifier_env *env)
return state->acquired_refs ? -EINVAL : 0;
}
static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx_p)
{
const struct bpf_func_proto *fn = NULL;
struct bpf_reg_state *regs;
struct bpf_call_arg_meta meta;
int insn_idx = *insn_idx_p;
bool changes_data;
int i, err;
int i, err, func_id;
/* find function prototype */
func_id = insn->imm;
if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
func_id);
@ -4695,6 +4801,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
return -EINVAL;
}
if (func_id == BPF_FUNC_for_each_map_elem) {
err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
set_map_elem_callback_state);
if (err < 0)
return -EINVAL;
}
/* reset caller saved regs */
for (i = 0; i < CALLER_SAVED_REGS; i++) {
mark_reg_not_init(env, regs, caller_saved[i]);
@ -4885,7 +4998,7 @@ enum {
static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
u32 *alu_limit, bool mask_to_left)
{
u32 max = 0, ptr_limit = 0;
u32 max = 0, ptr_limit = 0, off;
switch (ptr_reg->type) {
case PTR_TO_STACK:
@ -4903,6 +5016,19 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
ptr_reg->smin_value :
ptr_reg->umax_value) + ptr_reg->off;
break;
case PTR_TO_MAP_KEY:
/* Currently, this code is not exercised as the only use
* is bpf_for_each_map_elem() helper which requires
* bpf_capble. The code has been tested manually for
* future use.
*/
if (mask_to_left) {
ptr_limit = ptr_reg->umax_value + ptr_reg->off;
} else {
off = ptr_reg->smin_value + ptr_reg->off;
ptr_limit = ptr_reg->map_ptr->key_size - off;
}
return 0;
default:
return REASON_TYPE;
}
@ -5224,6 +5350,14 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
dst);
return -EACCES;
}
fallthrough;
default:
break;
}
@ -6905,6 +7039,24 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
return 0;
}
if (insn->src_reg == BPF_PSEUDO_FUNC) {
struct bpf_prog_aux *aux = env->prog->aux;
u32 subprogno = insn[1].imm;
if (!aux->func_info) {
verbose(env, "missing btf func_info\n");
return -EINVAL;
}
if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) {
verbose(env, "callback function not static\n");
return -EINVAL;
}
dst_reg->type = PTR_TO_FUNC;
dst_reg->subprogno = subprogno;
return 0;
}
map = env->used_maps[aux->map_index];
mark_reg_known_zero(env, regs, insn->dst_reg);
dst_reg->map_ptr = map;
@ -7269,6 +7421,9 @@ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env)
struct bpf_insn *insns = env->prog->insnsi;
int ret;
if (bpf_pseudo_func(insns + t))
return visit_func_call_insn(t, insn_cnt, insns, env, true);
/* All non-branch instructions have a single fall-through edge. */
if (BPF_CLASS(insns[t].code) != BPF_JMP &&
BPF_CLASS(insns[t].code) != BPF_JMP32)
@ -7844,6 +7999,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
*/
return false;
}
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
@ -8674,10 +8830,9 @@ static int do_check(struct bpf_verifier_env *env)
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else
err = check_helper_call(env, insn->imm, env->insn_idx);
err = check_helper_call(env, insn, &env->insn_idx);
if (err)
return err;
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
@ -8962,6 +9117,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
goto next_insn;
}
if (insn[0].src_reg == BPF_PSEUDO_FUNC) {
aux = &env->insn_aux_data[i];
aux->ptr_type = PTR_TO_FUNC;
goto next_insn;
}
/* In final convert_pseudo_ld_imm64() step, this is
* converted into regular 64-bit imm load insn.
*/
@ -9097,9 +9258,13 @@ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
int insn_cnt = env->prog->len;
int i;
for (i = 0; i < insn_cnt; i++, insn++)
if (insn->code == (BPF_LD | BPF_IMM | BPF_DW))
insn->src_reg = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
if (insn->code != (BPF_LD | BPF_IMM | BPF_DW))
continue;
if (insn->src_reg == BPF_PSEUDO_FUNC)
continue;
insn->src_reg = 0;
}
}
/* single env->prog->insni[off] instruction was replaced with the range
@ -9720,6 +9885,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
return 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (bpf_pseudo_func(insn)) {
env->insn_aux_data[i].call_imm = insn->imm;
/* subprog is encoded in insn[1].imm */
continue;
}
if (!bpf_pseudo_call(insn))
continue;
/* Upon error here we cannot fall back to interpreter but
@ -9802,6 +9973,12 @@ static int jit_subprogs(struct bpf_verifier_env *env)
for (i = 0; i < env->subprog_cnt; i++) {
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (bpf_pseudo_func(insn)) {
subprog = insn[1].imm;
insn[0].imm = (u32)(long)func[subprog]->bpf_func;
insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32;
continue;
}
if (!bpf_pseudo_call(insn))
continue;
subprog = insn->off;
@ -9847,6 +10024,11 @@ static int jit_subprogs(struct bpf_verifier_env *env)
* later look the same as if they were interpreted only.
*/
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
if (bpf_pseudo_func(insn)) {
insn[0].imm = env->insn_aux_data[i].call_imm;
insn[1].imm = find_subprog(env, i + insn[0].imm + 1);
continue;
}
if (!bpf_pseudo_call(insn))
continue;
insn->off = env->insn_aux_data[i].call_imm;

2
kernel/trace/bpf_trace.c
View File

@ -1057,6 +1057,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_ringbuf_discard_proto;
case BPF_FUNC_ringbuf_query:
return &bpf_ringbuf_query_proto;
case BPF_FUNC_for_each_map_elem:
return &bpf_for_each_map_elem_proto;
default:
return NULL;
}

2
net/core/filter.c
View File

@ -6140,6 +6140,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
return &bpf_ringbuf_discard_proto;
case BPF_FUNC_ringbuf_query:
return &bpf_ringbuf_query_proto;
case BPF_FUNC_for_each_map_elem:
return &bpf_for_each_map_elem_proto;
default:
break;
}

43
tools/include/uapi/linux/bpf.h
View File

@ -317,18 +317,45 @@ enum bpf_iter_link_info {
#define BPF_F_TEST_STATE_FREQ (1U << 3)
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* two extensions:
* the following extensions:
*
* insn[0].src_reg: BPF_PSEUDO_MAP_FD BPF_PSEUDO_MAP_VALUE
* insn[0].imm: map fd map fd
* insn[1].imm: 0 offset into value
* insn[0].off: 0 0
* insn[1].off: 0 0
* ldimm64 rewrite: address of map address of map[0]+offset
* verifier type: CONST_PTR_TO_MAP PTR_TO_MAP_VALUE
* insn[0].src_reg: BPF_PSEUDO_MAP_FD
* insn[0].imm: map fd
* insn[1].imm: 0
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of map
* verifier type: CONST_PTR_TO_MAP
*/
#define BPF_PSEUDO_MAP_FD 1
/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE
* insn[0].imm: map fd
* insn[1].imm: offset into value
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of map[0]+offset
* verifier type: PTR_TO_MAP_VALUE
*/
#define BPF_PSEUDO_MAP_VALUE 2
/* insn[0].src_reg: BPF_PSEUDO_BTF_ID
* insn[0].imm: kernel btd id of VAR
* insn[1].imm: 0
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of the kernel variable
* verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
* is struct/union.
*/
#define BPF_PSEUDO_BTF_ID 3
/* insn[0].src_reg: BPF_PSEUDO_FUNC
* insn[0].imm: insn offset to the func
* insn[1].imm: 0
* insn[0].off: 0
* insn[1].off: 0
* ldimm64 rewrite: address of the function
* verifier type: PTR_TO_FUNC.
*/
#define BPF_PSEUDO_FUNC 4
/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
* offset to another bpf function