summaryrefslogtreecommitdiff
path: root/kernel/bpf/helpers.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/helpers.c')
-rw-r--r--kernel/bpf/helpers.c1546
1 files changed, 1449 insertions, 97 deletions
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b5f0adae8293..c9fab9a356df 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -23,6 +23,11 @@
#include <linux/btf_ids.h>
#include <linux/bpf_mem_alloc.h>
#include <linux/kasan.h>
+#include <linux/bpf_verifier.h>
+#include <linux/uaccess.h>
+#include <linux/verification.h>
+#include <linux/task_work.h>
+#include <linux/irq_work.h>
#include "../../lib/kstrtox.h"
@@ -111,7 +116,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+ .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
};
BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
@@ -124,12 +129,13 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
- .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+ .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
};
BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
{
- WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+ !rcu_read_lock_bh_held());
return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu);
}
@@ -158,6 +164,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
.func = bpf_get_smp_processor_id,
.gpl_only = false,
.ret_type = RET_INTEGER,
+ .allow_fastcall = true,
};
BPF_CALL_0(bpf_get_numa_node_id)
@@ -517,16 +524,15 @@ static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
}
BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
- long *, res)
+ s64 *, res)
{
long long _res;
int err;
+ *res = 0;
err = __bpf_strtoll(buf, buf_len, flags, &_res);
if (err < 0)
return err;
- if (_res != (long)_res)
- return -ERANGE;
*res = _res;
return err;
}
@@ -538,23 +544,23 @@ const struct bpf_func_proto bpf_strtol_proto = {
.arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_LONG,
+ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
+ .arg4_size = sizeof(s64),
};
BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
- unsigned long *, res)
+ u64 *, res)
{
unsigned long long _res;
bool is_negative;
int err;
+ *res = 0;
err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
if (err < 0)
return err;
if (is_negative)
return -EINVAL;
- if (_res != (unsigned long)_res)
- return -ERANGE;
*res = _res;
return err;
}
@@ -566,7 +572,8 @@ const struct bpf_func_proto bpf_strtoul_proto = {
.arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
.arg2_type = ARG_CONST_SIZE,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_LONG,
+ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
+ .arg4_size = sizeof(u64),
};
BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
@@ -714,7 +721,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
if (cpu >= nr_cpu_ids)
return (unsigned long)NULL;
- return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu);
+ return (unsigned long)per_cpu_ptr((const void __percpu *)(const uintptr_t)ptr, cpu);
}
const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
@@ -727,7 +734,7 @@ const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
{
- return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr);
+ return (unsigned long)this_cpu_ptr((const void __percpu *)(const uintptr_t)percpu_ptr);
}
const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
@@ -760,30 +767,19 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
return -EINVAL;
}
-/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
- * arguments representation.
- */
-#define MAX_BPRINTF_BIN_ARGS 512
-
/* Support executing three nested bprintf helper calls on a given CPU */
#define MAX_BPRINTF_NEST_LEVEL 3
-struct bpf_bprintf_buffers {
- char bin_args[MAX_BPRINTF_BIN_ARGS];
- char buf[MAX_BPRINTF_BUF];
-};
static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
-static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
+int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs)
{
int nest_level;
- preempt_disable();
nest_level = this_cpu_inc_return(bpf_bprintf_nest_level);
if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) {
this_cpu_dec(bpf_bprintf_nest_level);
- preempt_enable();
return -EBUSY;
}
*bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]);
@@ -791,14 +787,18 @@ static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
return 0;
}
-void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
+void bpf_put_buffers(void)
{
- if (!data->bin_args && !data->buf)
- return;
if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
return;
this_cpu_dec(bpf_bprintf_nest_level);
- preempt_enable();
+}
+
+void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
+{
+ if (!data->bin_args && !data->buf)
+ return;
+ bpf_put_buffers();
}
/*
@@ -815,7 +815,7 @@ void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
* In argument preparation mode, if 0 is returned, safe temporary buffers are
* allocated and bpf_bprintf_cleanup should be called to free them after use.
*/
-int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
u32 num_args, struct bpf_bprintf_data *data)
{
bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
@@ -831,7 +831,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
return -EINVAL;
fmt_size = fmt_end - fmt;
- if (get_buffers && try_get_buffers(&buffers))
+ if (get_buffers && bpf_try_get_buffers(&buffers))
return -EBUSY;
if (data->get_bin_args) {
@@ -881,6 +881,13 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
if (fmt[i] == 'p') {
sizeof_cur_arg = sizeof(long);
+ if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
+ ispunct(fmt[i + 1])) {
+ if (tmp_buf)
+ cur_arg = raw_args[num_spec];
+ goto nocopy_fmt;
+ }
+
if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
fmt[i + 2] == 's') {
fmt_ptype = fmt[i + 1];
@@ -888,11 +895,9 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
goto fmt_str;
}
- if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
- ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
+ if (fmt[i + 1] == 'K' ||
fmt[i + 1] == 'x' || fmt[i + 1] == 's' ||
fmt[i + 1] == 'S') {
- /* just kernel pointers */
if (tmp_buf)
cur_arg = raw_args[num_spec];
i++;
@@ -1079,6 +1084,17 @@ const struct bpf_func_proto bpf_snprintf_proto = {
.arg5_type = ARG_CONST_SIZE_OR_ZERO,
};
+static void *map_key_from_value(struct bpf_map *map, void *value, u32 *arr_idx)
+{
+ if (map->map_type == BPF_MAP_TYPE_ARRAY) {
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+ *arr_idx = ((char *)value - array->value) / array->elem_size;
+ return arr_idx;
+ }
+ return (void *)value - round_up(map->key_size, 8);
+}
+
struct bpf_async_cb {
struct bpf_map *map;
struct bpf_prog *prog;
@@ -1161,15 +1177,8 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
* bpf_map_delete_elem() on the same timer.
*/
this_cpu_write(hrtimer_running, t);
- if (map->map_type == BPF_MAP_TYPE_ARRAY) {
- struct bpf_array *array = container_of(map, struct bpf_array, map);
- /* compute the key */
- idx = ((char *)value - array->value) / array->elem_size;
- key = &idx;
- } else { /* hash or lru */
- key = value - round_up(map->key_size, 8);
- }
+ key = map_key_from_value(map, value, &idx);
callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0);
/* The verifier checked that return value is zero. */
@@ -1195,15 +1204,7 @@ static void bpf_wq_work(struct work_struct *work)
if (!callback_fn)
return;
- if (map->map_type == BPF_MAP_TYPE_ARRAY) {
- struct bpf_array *array = container_of(map, struct bpf_array, map);
-
- /* compute the key */
- idx = ((char *)value - array->value) / array->elem_size;
- key = &idx;
- } else { /* hash or lru */
- key = value - round_up(map->key_size, 8);
- }
+ key = map_key_from_value(map, value, &idx);
rcu_read_lock_trace();
migrate_disable();
@@ -1269,8 +1270,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
goto out;
}
- /* allocate hrtimer via map_kmalloc to use memcg accounting */
- cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node);
+ /* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
+ * kmalloc_nolock() is available, avoid locking issues by using
+ * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
+ */
+ cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
if (!cb) {
ret = -ENOMEM;
goto out;
@@ -1283,8 +1287,7 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
atomic_set(&t->cancelling, 0);
INIT_WORK(&t->cb.delete_work, bpf_timer_delete_work);
- hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
- t->timer.function = bpf_timer_cb;
+ hrtimer_setup(&t->timer, bpf_timer_cb, clockid, HRTIMER_MODE_REL_SOFT);
cb->value = (void *)async - map->record->timer_off;
break;
case BPF_ASYNC_TYPE_WQ:
@@ -1592,10 +1595,24 @@ void bpf_timer_cancel_and_free(void *val)
* To avoid these issues, punt to workqueue context when we are in a
* timer callback.
*/
- if (this_cpu_read(hrtimer_running))
- queue_work(system_unbound_wq, &t->cb.delete_work);
- else
+ if (this_cpu_read(hrtimer_running)) {
+ queue_work(system_dfl_wq, &t->cb.delete_work);
+ return;
+ }
+
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ /* If the timer is running on other CPU, also use a kworker to
+ * wait for the completion of the timer instead of trying to
+ * acquire a sleepable lock in hrtimer_cancel() to wait for its
+ * completion.
+ */
+ if (hrtimer_try_to_cancel(&t->timer) >= 0)
+ kfree_rcu(t, cb.rcu);
+ else
+ queue_work(system_dfl_wq, &t->cb.delete_work);
+ } else {
bpf_timer_delete_work(&t->cb.delete_work);
+ }
}
/* This function is called by map_delete/update_elem for individual element and
@@ -1618,9 +1635,9 @@ void bpf_wq_cancel_and_free(void *val)
schedule_work(&work->delete_work);
}
-BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr)
+BPF_CALL_2(bpf_kptr_xchg, void *, dst, void *, ptr)
{
- unsigned long *kptr = map_value;
+ unsigned long *kptr = dst;
/* This helper may be inlined by verifier. */
return xchg(kptr, (unsigned long)ptr);
@@ -1635,7 +1652,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = {
.gpl_only = false,
.ret_type = RET_PTR_TO_BTF_ID_OR_NULL,
.ret_btf_id = BPF_PTR_POISON,
- .arg1_type = ARG_PTR_TO_KPTR,
+ .arg1_type = ARG_KPTR_XCHG_DEST,
.arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL | OBJ_RELEASE,
.arg2_btf_id = BPF_PTR_POISON,
};
@@ -1699,16 +1716,6 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
memset(ptr, 0, sizeof(*ptr));
}
-static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
-{
- u32 size = __bpf_dynptr_size(ptr);
-
- if (len > size || offset > size - len)
- return -E2BIG;
-
- return 0;
-}
-
BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr)
{
int err;
@@ -1741,11 +1748,11 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.arg3_type = ARG_ANYTHING,
- .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
+ .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE,
};
-BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
- u32, offset, u64, flags)
+static int __bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr_kern *src,
+ u32 offset, u64 flags)
{
enum bpf_dynptr_type type;
int err;
@@ -1772,12 +1779,21 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern
return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len);
case BPF_DYNPTR_TYPE_XDP:
return __bpf_xdp_load_bytes(src->data, src->offset + offset, dst, len);
+ case BPF_DYNPTR_TYPE_SKB_META:
+ memmove(dst, bpf_skb_meta_pointer(src->data, src->offset + offset), len);
+ return 0;
default:
WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type);
return -EFAULT;
}
}
+BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
+ u32, offset, u64, flags)
+{
+ return __bpf_dynptr_read(dst, len, src, offset, flags);
+}
+
static const struct bpf_func_proto bpf_dynptr_read_proto = {
.func = bpf_dynptr_read,
.gpl_only = false,
@@ -1789,8 +1805,8 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = {
.arg5_type = ARG_ANYTHING,
};
-BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
- u32, len, u64, flags)
+int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u32 offset, void *src,
+ u32 len, u64 flags)
{
enum bpf_dynptr_type type;
int err;
@@ -1822,12 +1838,23 @@ BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, v
if (flags)
return -EINVAL;
return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len);
+ case BPF_DYNPTR_TYPE_SKB_META:
+ if (flags)
+ return -EINVAL;
+ memmove(bpf_skb_meta_pointer(dst->data, dst->offset + offset), src, len);
+ return 0;
default:
WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type);
return -EFAULT;
}
}
+BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
+ u32, len, u64, flags)
+{
+ return __bpf_dynptr_write(dst, offset, src, len, flags);
+}
+
static const struct bpf_func_proto bpf_dynptr_write_proto = {
.func = bpf_dynptr_write,
.gpl_only = false,
@@ -1862,6 +1889,7 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3
return (unsigned long)(ptr->data + ptr->offset + offset);
case BPF_DYNPTR_TYPE_SKB:
case BPF_DYNPTR_TYPE_XDP:
+ case BPF_DYNPTR_TYPE_SKB_META:
/* skb and xdp dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */
return 0;
default:
@@ -1886,6 +1914,12 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
const struct bpf_func_proto bpf_probe_read_kernel_proto __weak;
const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak;
const struct bpf_func_proto bpf_task_pt_regs_proto __weak;
+const struct bpf_func_proto bpf_perf_event_read_proto __weak;
+const struct bpf_func_proto bpf_send_signal_proto __weak;
+const struct bpf_func_proto bpf_send_signal_thread_proto __weak;
+const struct bpf_func_proto bpf_get_task_stack_sleepable_proto __weak;
+const struct bpf_func_proto bpf_get_task_stack_proto __weak;
+const struct bpf_func_proto bpf_get_branch_snapshot_proto __weak;
const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
@@ -1939,6 +1973,8 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_current_pid_tgid_proto;
case BPF_FUNC_get_ns_current_pid_tgid:
return &bpf_get_ns_current_pid_tgid_proto;
+ case BPF_FUNC_get_current_uid_gid:
+ return &bpf_get_current_uid_gid_proto;
default:
break;
}
@@ -1996,7 +2032,21 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_current_cgroup_id_proto;
case BPF_FUNC_get_current_ancestor_cgroup_id:
return &bpf_get_current_ancestor_cgroup_id_proto;
+ case BPF_FUNC_current_task_under_cgroup:
+ return &bpf_current_task_under_cgroup_proto;
+#endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+ case BPF_FUNC_get_cgroup_classid:
+ return &bpf_get_cgroup_classid_curr_proto;
#endif
+ case BPF_FUNC_task_storage_get:
+ if (bpf_prog_check_recur(prog))
+ return &bpf_task_storage_get_recur_proto;
+ return &bpf_task_storage_get_proto;
+ case BPF_FUNC_task_storage_delete:
+ if (bpf_prog_check_recur(prog))
+ return &bpf_task_storage_delete_recur_proto;
+ return &bpf_task_storage_delete_proto;
default:
break;
}
@@ -2011,6 +2061,8 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_current_task_proto;
case BPF_FUNC_get_current_task_btf:
return &bpf_get_current_task_btf_proto;
+ case BPF_FUNC_get_current_comm:
+ return &bpf_get_current_comm_proto;
case BPF_FUNC_probe_read_user:
return &bpf_probe_read_user_proto;
case BPF_FUNC_probe_read_kernel:
@@ -2021,6 +2073,10 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_probe_read_kernel_str:
return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ?
NULL : &bpf_probe_read_kernel_str_proto;
+ case BPF_FUNC_copy_from_user:
+ return &bpf_copy_from_user_proto;
+ case BPF_FUNC_copy_from_user_task:
+ return &bpf_copy_from_user_task_proto;
case BPF_FUNC_snprintf_btf:
return &bpf_snprintf_btf_proto;
case BPF_FUNC_snprintf:
@@ -2029,10 +2085,26 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_task_pt_regs_proto;
case BPF_FUNC_trace_vprintk:
return bpf_get_trace_vprintk_proto();
+ case BPF_FUNC_perf_event_read_value:
+ return bpf_get_perf_event_read_value_proto();
+ case BPF_FUNC_perf_event_read:
+ return &bpf_perf_event_read_proto;
+ case BPF_FUNC_send_signal:
+ return &bpf_send_signal_proto;
+ case BPF_FUNC_send_signal_thread:
+ return &bpf_send_signal_thread_proto;
+ case BPF_FUNC_get_task_stack:
+ return prog->sleepable ? &bpf_get_task_stack_sleepable_proto
+ : &bpf_get_task_stack_proto;
+ case BPF_FUNC_get_branch_snapshot:
+ return &bpf_get_branch_snapshot_proto;
+ case BPF_FUNC_find_vma:
+ return &bpf_find_vma_proto;
default:
return NULL;
}
}
+EXPORT_SYMBOL_GPL(bpf_base_func_proto);
void bpf_list_head_free(const struct btf_field *field, void *list_head,
struct bpf_spin_lock *spin_lock)
@@ -2064,9 +2136,7 @@ unlock:
/* The contained type can also have resources, including a
* bpf_list_head which needs to be freed.
*/
- migrate_disable();
__bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
- migrate_enable();
}
}
@@ -2103,9 +2173,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
obj -= field->graph_root.node_offset;
- migrate_disable();
__bpf_obj_drop_impl(obj, field->graph_root.value_rec, false);
- migrate_enable();
}
}
@@ -2268,6 +2336,26 @@ __bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head)
return __bpf_list_del(head, true);
}
+__bpf_kfunc struct bpf_list_node *bpf_list_front(struct bpf_list_head *head)
+{
+ struct list_head *h = (struct list_head *)head;
+
+ if (list_empty(h) || unlikely(!h->next))
+ return NULL;
+
+ return (struct bpf_list_node *)h->next;
+}
+
+__bpf_kfunc struct bpf_list_node *bpf_list_back(struct bpf_list_head *head)
+{
+ struct list_head *h = (struct list_head *)head;
+
+ if (list_empty(h) || unlikely(!h->next))
+ return NULL;
+
+ return (struct bpf_list_node *)h->prev;
+}
+
__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
struct bpf_rb_node *node)
{
@@ -2341,6 +2429,33 @@ __bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root)
return (struct bpf_rb_node *)rb_first_cached(r);
}
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_root(struct bpf_rb_root *root)
+{
+ struct rb_root_cached *r = (struct rb_root_cached *)root;
+
+ return (struct bpf_rb_node *)r->rb_root.rb_node;
+}
+
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_left(struct bpf_rb_root *root, struct bpf_rb_node *node)
+{
+ struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
+
+ if (READ_ONCE(node_internal->owner) != root)
+ return NULL;
+
+ return (struct bpf_rb_node *)node_internal->rb_node.rb_left;
+}
+
+__bpf_kfunc struct bpf_rb_node *bpf_rbtree_right(struct bpf_rb_root *root, struct bpf_rb_node *node)
+{
+ struct bpf_rb_node_kern *node_internal = (struct bpf_rb_node_kern *)node;
+
+ if (READ_ONCE(node_internal->owner) != root)
+ return NULL;
+
+ return (struct bpf_rb_node *)node_internal->rb_node.rb_right;
+}
+
/**
* bpf_task_acquire - Acquire a reference to a task. A task acquired by this
* kfunc which is not stored in a map as a kptr, must be released by calling
@@ -2430,7 +2545,7 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid)
{
struct cgroup *cgrp;
- cgrp = cgroup_get_from_id(cgid);
+ cgrp = __cgroup_get_from_id(cgid);
if (IS_ERR(cgrp))
return NULL;
return cgrp;
@@ -2457,6 +2572,29 @@ __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task,
return ret;
}
+BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ struct cgroup *cgrp;
+
+ if (unlikely(idx >= array->map.max_entries))
+ return -E2BIG;
+
+ cgrp = READ_ONCE(array->ptrs[idx]);
+ if (unlikely(!cgrp))
+ return -EAGAIN;
+
+ return task_under_cgroup_hierarchy(current, cgrp);
+}
+
+const struct bpf_func_proto bpf_current_task_under_cgroup_proto = {
+ .func = bpf_current_task_under_cgroup,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_ANYTHING,
+};
+
/**
* bpf_task_get_cgroup1 - Acquires the associated cgroup of a task within a
* specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its
@@ -2497,6 +2635,25 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
}
/**
+ * bpf_task_from_vpid - Find a struct task_struct from its vpid by looking it up
+ * in the pid namespace of the current task. If a task is returned, it must
+ * either be stored in a map, or released with bpf_task_release().
+ * @vpid: The vpid of the task being looked up.
+ */
+__bpf_kfunc struct task_struct *bpf_task_from_vpid(s32 vpid)
+{
+ struct task_struct *p;
+
+ rcu_read_lock();
+ p = find_task_by_vpid(vpid);
+ if (p)
+ p = bpf_task_acquire(p);
+ rcu_read_unlock();
+
+ return p;
+}
+
+/**
* bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data.
* @p: The dynptr whose data slice to retrieve
* @offset: Offset into the dynptr
@@ -2561,6 +2718,8 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr *p, u32 offset,
bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false);
return buffer__opt;
}
+ case BPF_DYNPTR_TYPE_SKB_META:
+ return bpf_skb_meta_pointer(ptr->data, ptr->offset + offset);
default:
WARN_ONCE(true, "unknown dynptr type %d\n", type);
return NULL;
@@ -2704,6 +2863,107 @@ __bpf_kfunc int bpf_dynptr_clone(const struct bpf_dynptr *p,
return 0;
}
+/**
+ * bpf_dynptr_copy() - Copy data from one dynptr to another.
+ * @dst_ptr: Destination dynptr - where data should be copied to
+ * @dst_off: Offset into the destination dynptr
+ * @src_ptr: Source dynptr - where data should be copied from
+ * @src_off: Offset into the source dynptr
+ * @size: Length of the data to copy from source to destination
+ *
+ * Copies data from source dynptr to destination dynptr.
+ * Returns 0 on success; negative error, otherwise.
+ */
+__bpf_kfunc int bpf_dynptr_copy(struct bpf_dynptr *dst_ptr, u32 dst_off,
+ struct bpf_dynptr *src_ptr, u32 src_off, u32 size)
+{
+ struct bpf_dynptr_kern *dst = (struct bpf_dynptr_kern *)dst_ptr;
+ struct bpf_dynptr_kern *src = (struct bpf_dynptr_kern *)src_ptr;
+ void *src_slice, *dst_slice;
+ char buf[256];
+ u32 off;
+
+ src_slice = bpf_dynptr_slice(src_ptr, src_off, NULL, size);
+ dst_slice = bpf_dynptr_slice_rdwr(dst_ptr, dst_off, NULL, size);
+
+ if (src_slice && dst_slice) {
+ memmove(dst_slice, src_slice, size);
+ return 0;
+ }
+
+ if (src_slice)
+ return __bpf_dynptr_write(dst, dst_off, src_slice, size, 0);
+
+ if (dst_slice)
+ return __bpf_dynptr_read(dst_slice, size, src, src_off, 0);
+
+ if (bpf_dynptr_check_off_len(dst, dst_off, size) ||
+ bpf_dynptr_check_off_len(src, src_off, size))
+ return -E2BIG;
+
+ off = 0;
+ while (off < size) {
+ u32 chunk_sz = min_t(u32, sizeof(buf), size - off);
+ int err;
+
+ err = __bpf_dynptr_read(buf, chunk_sz, src, src_off + off, 0);
+ if (err)
+ return err;
+ err = __bpf_dynptr_write(dst, dst_off + off, buf, chunk_sz, 0);
+ if (err)
+ return err;
+
+ off += chunk_sz;
+ }
+ return 0;
+}
+
+/**
+ * bpf_dynptr_memset() - Fill dynptr memory with a constant byte.
+ * @p: Destination dynptr - where data will be filled
+ * @offset: Offset into the dynptr to start filling from
+ * @size: Number of bytes to fill
+ * @val: Constant byte to fill the memory with
+ *
+ * Fills the @size bytes of the memory area pointed to by @p
+ * at @offset with the constant byte @val.
+ * Returns 0 on success; negative error, otherwise.
+ */
+ __bpf_kfunc int bpf_dynptr_memset(struct bpf_dynptr *p, u32 offset, u32 size, u8 val)
+ {
+ struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)p;
+ u32 chunk_sz, write_off;
+ char buf[256];
+ void* slice;
+ int err;
+
+ slice = bpf_dynptr_slice_rdwr(p, offset, NULL, size);
+ if (likely(slice)) {
+ memset(slice, val, size);
+ return 0;
+ }
+
+ if (__bpf_dynptr_is_rdonly(ptr))
+ return -EINVAL;
+
+ err = bpf_dynptr_check_off_len(ptr, offset, size);
+ if (err)
+ return err;
+
+ /* Non-linear data under the dynptr, write from a local buffer */
+ chunk_sz = min_t(u32, sizeof(buf), size);
+ memset(buf, val, chunk_sz);
+
+ for (write_off = 0; write_off < size; write_off += chunk_sz) {
+ chunk_sz = min_t(u32, sizeof(buf), size - write_off);
+ err = __bpf_dynptr_write(ptr, offset + write_off, buf, chunk_sz, 0);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
__bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj)
{
return obj;
@@ -2736,9 +2996,16 @@ static bool bpf_stack_walker(void *cookie, u64 ip, u64 sp, u64 bp)
struct bpf_throw_ctx *ctx = cookie;
struct bpf_prog *prog;
- if (!is_bpf_text_address(ip))
- return !ctx->cnt;
+ /*
+ * The RCU read lock is held to safely traverse the latch tree, but we
+ * don't need its protection when accessing the prog, since it has an
+ * active stack frame on the current stack trace, and won't disappear.
+ */
+ rcu_read_lock();
prog = bpf_prog_ksym_find(ip);
+ rcu_read_unlock();
+ if (!prog)
+ return !ctx->cnt;
ctx->cnt++;
if (bpf_is_subprog(prog))
return true;
@@ -2801,9 +3068,9 @@ __bpf_kfunc int bpf_wq_start(struct bpf_wq *wq, unsigned int flags)
__bpf_kfunc int bpf_wq_set_callback_impl(struct bpf_wq *wq,
int (callback_fn)(void *map, int *key, void *value),
unsigned int flags,
- void *aux__ign)
+ void *aux__prog)
{
- struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__ign;
+ struct bpf_prog_aux *aux = (struct bpf_prog_aux *)aux__prog;
struct bpf_async_kern *async = (struct bpf_async_kern *)wq;
if (flags)
@@ -2826,21 +3093,47 @@ struct bpf_iter_bits {
__u64 __opaque[2];
} __aligned(8);
+#define BITS_ITER_NR_WORDS_MAX 511
+
struct bpf_iter_bits_kern {
union {
- unsigned long *bits;
- unsigned long bits_copy;
+ __u64 *bits;
+ __u64 bits_copy;
};
- u32 nr_bits;
+ int nr_bits;
int bit;
} __aligned(8);
+/* On 64-bit hosts, unsigned long and u64 have the same size, so passing
+ * a u64 pointer and an unsigned long pointer to find_next_bit() will
+ * return the same result, as both point to the same 8-byte area.
+ *
+ * For 32-bit little-endian hosts, using a u64 pointer or unsigned long
+ * pointer also makes no difference. This is because the first iterated
+ * unsigned long is composed of bits 0-31 of the u64 and the second unsigned
+ * long is composed of bits 32-63 of the u64.
+ *
+ * However, for 32-bit big-endian hosts, this is not the case. The first
+ * iterated unsigned long will be bits 32-63 of the u64, so swap these two
+ * ulong values within the u64.
+ */
+static void swap_ulong_in_u64(u64 *bits, unsigned int nr)
+{
+#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+ unsigned int i;
+
+ for (i = 0; i < nr; i++)
+ bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32);
+#endif
+}
+
/**
* bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area
* @it: The new bpf_iter_bits to be created
* @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over
* @nr_words: The size of the specified memory area, measured in 8-byte units.
- * Due to the limitation of memalloc, it can't be greater than 512.
+ * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be
+ * further reduced by the BPF memory allocator implementation.
*
* This function initializes a new bpf_iter_bits structure for iterating over
* a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It
@@ -2867,6 +3160,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
if (!unsafe_ptr__ign || !nr_words)
return -EINVAL;
+ if (nr_words > BITS_ITER_NR_WORDS_MAX)
+ return -E2BIG;
/* Optimization for u64 mask */
if (nr_bits == 64) {
@@ -2874,10 +3169,15 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
if (err)
return -EFAULT;
+ swap_ulong_in_u64(&kit->bits_copy, nr_words);
+
kit->nr_bits = nr_bits;
return 0;
}
+ if (bpf_mem_alloc_check_size(false, nr_bytes))
+ return -E2BIG;
+
/* Fallback to memalloc */
kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes);
if (!kit->bits)
@@ -2889,6 +3189,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
return err;
}
+ swap_ulong_in_u64(kit->bits, nr_words);
+
kit->nr_bits = nr_bits;
return 0;
}
@@ -2905,17 +3207,16 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w
__bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it)
{
struct bpf_iter_bits_kern *kit = (void *)it;
- u32 nr_bits = kit->nr_bits;
- const unsigned long *bits;
- int bit;
+ int bit = kit->bit, nr_bits = kit->nr_bits;
+ const void *bits;
- if (nr_bits == 0)
+ if (!nr_bits || bit >= nr_bits)
return NULL;
bits = nr_bits == 64 ? &kit->bits_copy : kit->bits;
- bit = find_next_bit(bits, nr_bits, kit->bit + 1);
+ bit = find_next_bit(bits, nr_bits, bit + 1);
if (bit >= nr_bits) {
- kit->nr_bits = 0;
+ kit->bit = bit;
return NULL;
}
@@ -2938,8 +3239,997 @@ __bpf_kfunc void bpf_iter_bits_destroy(struct bpf_iter_bits *it)
bpf_mem_free(&bpf_global_ma, kit->bits);
}
+/**
+ * bpf_copy_from_user_str() - Copy a string from an unsafe user address
+ * @dst: Destination address, in kernel space. This buffer must be
+ * at least @dst__sz bytes long.
+ * @dst__sz: Maximum number of bytes to copy, includes the trailing NUL.
+ * @unsafe_ptr__ign: Source address, in user space.
+ * @flags: The only supported flag is BPF_F_PAD_ZEROS
+ *
+ * Copies a NUL-terminated string from userspace to BPF space. If user string is
+ * too long this will still ensure zero termination in the dst buffer unless
+ * buffer size is 0.
+ *
+ * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst to 0 on success and
+ * memset all of @dst on failure.
+ */
+__bpf_kfunc int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void __user *unsafe_ptr__ign, u64 flags)
+{
+ int ret;
+
+ if (unlikely(flags & ~BPF_F_PAD_ZEROS))
+ return -EINVAL;
+
+ if (unlikely(!dst__sz))
+ return 0;
+
+ ret = strncpy_from_user(dst, unsafe_ptr__ign, dst__sz - 1);
+ if (ret < 0) {
+ if (flags & BPF_F_PAD_ZEROS)
+ memset((char *)dst, 0, dst__sz);
+
+ return ret;
+ }
+
+ if (flags & BPF_F_PAD_ZEROS)
+ memset((char *)dst + ret, 0, dst__sz - ret);
+ else
+ ((char *)dst)[ret] = '\0';
+
+ return ret + 1;
+}
+
+/**
+ * bpf_copy_from_user_task_str() - Copy a string from an task's address space
+ * @dst: Destination address, in kernel space. This buffer must be
+ * at least @dst__sz bytes long.
+ * @dst__sz: Maximum number of bytes to copy, includes the trailing NUL.
+ * @unsafe_ptr__ign: Source address in the task's address space.
+ * @tsk: The task whose address space will be used
+ * @flags: The only supported flag is BPF_F_PAD_ZEROS
+ *
+ * Copies a NUL terminated string from a task's address space to @dst__sz
+ * buffer. If user string is too long this will still ensure zero termination
+ * in the @dst__sz buffer unless buffer size is 0.
+ *
+ * If BPF_F_PAD_ZEROS flag is set, memset the tail of @dst__sz to 0 on success
+ * and memset all of @dst__sz on failure.
+ *
+ * Return: The number of copied bytes on success including the NUL terminator.
+ * A negative error code on failure.
+ */
+__bpf_kfunc int bpf_copy_from_user_task_str(void *dst, u32 dst__sz,
+ const void __user *unsafe_ptr__ign,
+ struct task_struct *tsk, u64 flags)
+{
+ int ret;
+
+ if (unlikely(flags & ~BPF_F_PAD_ZEROS))
+ return -EINVAL;
+
+ if (unlikely(dst__sz == 0))
+ return 0;
+
+ ret = copy_remote_vm_str(tsk, (unsigned long)unsafe_ptr__ign, dst, dst__sz, 0);
+ if (ret < 0) {
+ if (flags & BPF_F_PAD_ZEROS)
+ memset(dst, 0, dst__sz);
+ return ret;
+ }
+
+ if (flags & BPF_F_PAD_ZEROS)
+ memset(dst + ret, 0, dst__sz - ret);
+
+ return ret + 1;
+}
+
+/* Keep unsinged long in prototype so that kfunc is usable when emitted to
+ * vmlinux.h in BPF programs directly, but note that while in BPF prog, the
+ * unsigned long always points to 8-byte region on stack, the kernel may only
+ * read and write the 4-bytes on 32-bit.
+ */
+__bpf_kfunc void bpf_local_irq_save(unsigned long *flags__irq_flag)
+{
+ local_irq_save(*flags__irq_flag);
+}
+
+__bpf_kfunc void bpf_local_irq_restore(unsigned long *flags__irq_flag)
+{
+ local_irq_restore(*flags__irq_flag);
+}
+
+__bpf_kfunc void __bpf_trap(void)
+{
+}
+
+/*
+ * Kfuncs for string operations.
+ *
+ * Since strings are not necessarily %NUL-terminated, we cannot directly call
+ * in-kernel implementations. Instead, we open-code the implementations using
+ * __get_kernel_nofault instead of plain dereference to make them safe.
+ */
+
+static int __bpf_strcasecmp(const char *s1, const char *s2, bool ignore_case)
+{
+ char c1, c2;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s1, 1) ||
+ !copy_from_kernel_nofault_allowed(s2, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c1, s1, char, err_out);
+ __get_kernel_nofault(&c2, s2, char, err_out);
+ if (ignore_case) {
+ c1 = tolower(c1);
+ c2 = tolower(c2);
+ }
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (c1 == '\0')
+ return 0;
+ s1++;
+ s2++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strcmp - Compare two strings
+ * @s1__ign: One string
+ * @s2__ign: Another string
+ *
+ * Return:
+ * * %0 - Strings are equal
+ * * %-1 - @s1__ign is smaller
+ * * %1 - @s2__ign is smaller
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of strings is too large
+ * * %-ERANGE - One of strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcmp(const char *s1__ign, const char *s2__ign)
+{
+ return __bpf_strcasecmp(s1__ign, s2__ign, false);
+}
+
+/**
+ * bpf_strcasecmp - Compare two strings, ignoring the case of the characters
+ * @s1__ign: One string
+ * @s2__ign: Another string
+ *
+ * Return:
+ * * %0 - Strings are equal
+ * * %-1 - @s1__ign is smaller
+ * * %1 - @s2__ign is smaller
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of strings is too large
+ * * %-ERANGE - One of strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcasecmp(const char *s1__ign, const char *s2__ign)
+{
+ return __bpf_strcasecmp(s1__ign, s2__ign, true);
+}
+
+/**
+ * bpf_strnchr - Find a character in a length limited string
+ * @s__ign: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in the first @count characters of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnchr(const char *s__ign, size_t count, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ return i;
+ if (sc == '\0')
+ return -ENOENT;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : -ENOENT;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strchr - Find the first occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - The index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchr(const char *s__ign, char c)
+{
+ return bpf_strnchr(s__ign, XATTR_SIZE_MAX, c);
+}
+
+/**
+ * bpf_strchrnul - Find and return a character in a string, or end of string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign or index of
+ * the null byte at the end of @s__ign when @c is not found
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchrnul(const char *s__ign, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == '\0' || sc == c)
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strrchr - Find the last occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the last occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strrchr(const char *s__ign, int c)
+{
+ char sc;
+ int i, last = -ENOENT;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ last = i;
+ if (sc == '\0')
+ return last;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnlen - Calculate the length of a length-limited string
+ * @s__ign: The string
+ * @count: The maximum number of characters to count
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnlen(const char *s__ign, size_t count)
+{
+ char c;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c, s__ign, char, err_out);
+ if (c == '\0')
+ return i;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : i;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strlen - Calculate the length of a string
+ * @s__ign: The string
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strlen(const char *s__ign)
+{
+ return bpf_strnlen(s__ign, XATTR_SIZE_MAX);
+}
+
+/**
+ * bpf_strspn - Calculate the length of the initial substring of @s__ign which
+ * only contains letters in @accept__ign
+ * @s__ign: The string to be searched
+ * @accept__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which only
+ * contains letters from @accept__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strspn(const char *s__ign, const char *accept__ign)
+{
+ char cs, ca;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(accept__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&ca, accept__ign + j, char, err_out);
+ if (cs == ca || ca == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (ca == '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strcspn - Calculate the length of the initial substring of @s__ign which
+ * does not contain letters in @reject__ign
+ * @s__ign: The string to be searched
+ * @reject__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which does not
+ * contain letters from @reject__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcspn(const char *s__ign, const char *reject__ign)
+{
+ char cs, cr;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(reject__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&cr, reject__ign + j, char, err_out);
+ if (cs == cr || cr == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (cr != '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnstr - Find the first substring in a length-limited string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ * @len: the maximum number of characters to search
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within the first @len characters of @s1__ign
+ * * %-ENOENT - @s2__ign not found in the first @len characters of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len)
+{
+ char c1, c2;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s1__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(s2__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&c2, s2__ign + j, char, err_out);
+ if (c2 == '\0')
+ return i;
+ /*
+ * We allow reading an extra byte from s2 (note the
+ * `i + j <= len` above) to cover the case when s2 is
+ * a suffix of the first len chars of s1.
+ */
+ if (i + j == len)
+ break;
+ __get_kernel_nofault(&c1, s1__ign + j, char, err_out);
+ if (c1 == '\0')
+ return -ENOENT;
+ if (c1 != c2)
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (i + j == len)
+ return -ENOENT;
+ s1__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strstr - Find the first substring in a string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within @s1__ign
+ * * %-ENOENT - @s2__ign is not a substring of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strstr(const char *s1__ign, const char *s2__ign)
+{
+ return bpf_strnstr(s1__ign, s2__ign, XATTR_SIZE_MAX);
+}
+#ifdef CONFIG_KEYS
+/**
+ * bpf_lookup_user_key - lookup a key by its serial
+ * @serial: key handle serial number
+ * @flags: lookup-specific flags
+ *
+ * Search a key with a given *serial* and the provided *flags*.
+ * If found, increment the reference count of the key by one, and
+ * return it in the bpf_key structure.
+ *
+ * The bpf_key structure must be passed to bpf_key_put() when done
+ * with it, so that the key reference count is decremented and the
+ * bpf_key structure is freed.
+ *
+ * Permission checks are deferred to the time the key is used by
+ * one of the available key-specific kfuncs.
+ *
+ * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested
+ * special keyring (e.g. session keyring), if it doesn't yet exist.
+ * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting
+ * for the key construction, and to retrieve uninstantiated keys (keys
+ * without data attached to them).
+ *
+ * Return: a bpf_key pointer with a valid key pointer if the key is found, a
+ * NULL pointer otherwise.
+ */
+__bpf_kfunc struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags)
+{
+ key_ref_t key_ref;
+ struct bpf_key *bkey;
+
+ if (flags & ~KEY_LOOKUP_ALL)
+ return NULL;
+
+ /*
+ * Permission check is deferred until the key is used, as the
+ * intent of the caller is unknown here.
+ */
+ key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK);
+ if (IS_ERR(key_ref))
+ return NULL;
+
+ bkey = kmalloc(sizeof(*bkey), GFP_KERNEL);
+ if (!bkey) {
+ key_put(key_ref_to_ptr(key_ref));
+ return NULL;
+ }
+
+ bkey->key = key_ref_to_ptr(key_ref);
+ bkey->has_ref = true;
+
+ return bkey;
+}
+
+/**
+ * bpf_lookup_system_key - lookup a key by a system-defined ID
+ * @id: key ID
+ *
+ * Obtain a bpf_key structure with a key pointer set to the passed key ID.
+ * The key pointer is marked as invalid, to prevent bpf_key_put() from
+ * attempting to decrement the key reference count on that pointer. The key
+ * pointer set in such way is currently understood only by
+ * verify_pkcs7_signature().
+ *
+ * Set *id* to one of the values defined in include/linux/verification.h:
+ * 0 for the primary keyring (immutable keyring of system keys);
+ * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring
+ * (where keys can be added only if they are vouched for by existing keys
+ * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform
+ * keyring (primarily used by the integrity subsystem to verify a kexec'ed
+ * kerned image and, possibly, the initramfs signature).
+ *
+ * Return: a bpf_key pointer with an invalid key pointer set from the
+ * pre-determined ID on success, a NULL pointer otherwise
+ */
+__bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id)
+{
+ struct bpf_key *bkey;
+
+ if (system_keyring_id_check(id) < 0)
+ return NULL;
+
+ bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC);
+ if (!bkey)
+ return NULL;
+
+ bkey->key = (struct key *)(unsigned long)id;
+ bkey->has_ref = false;
+
+ return bkey;
+}
+
+/**
+ * bpf_key_put - decrement key reference count if key is valid and free bpf_key
+ * @bkey: bpf_key structure
+ *
+ * Decrement the reference count of the key inside *bkey*, if the pointer
+ * is valid, and free *bkey*.
+ */
+__bpf_kfunc void bpf_key_put(struct bpf_key *bkey)
+{
+ if (bkey->has_ref)
+ key_put(bkey->key);
+
+ kfree(bkey);
+}
+
+/**
+ * bpf_verify_pkcs7_signature - verify a PKCS#7 signature
+ * @data_p: data to verify
+ * @sig_p: signature of the data
+ * @trusted_keyring: keyring with keys trusted for signature verification
+ *
+ * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr*
+ * with keys in a keyring referenced by *trusted_keyring*.
+ *
+ * Return: 0 on success, a negative value on error.
+ */
+__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p,
+ struct bpf_dynptr *sig_p,
+ struct bpf_key *trusted_keyring)
+{
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+ struct bpf_dynptr_kern *data_ptr = (struct bpf_dynptr_kern *)data_p;
+ struct bpf_dynptr_kern *sig_ptr = (struct bpf_dynptr_kern *)sig_p;
+ const void *data, *sig;
+ u32 data_len, sig_len;
+ int ret;
+
+ if (trusted_keyring->has_ref) {
+ /*
+ * Do the permission check deferred in bpf_lookup_user_key().
+ * See bpf_lookup_user_key() for more details.
+ *
+ * A call to key_task_permission() here would be redundant, as
+ * it is already done by keyring_search() called by
+ * find_asymmetric_key().
+ */
+ ret = key_validate(trusted_keyring->key);
+ if (ret < 0)
+ return ret;
+ }
+
+ data_len = __bpf_dynptr_size(data_ptr);
+ data = __bpf_dynptr_data(data_ptr, data_len);
+ sig_len = __bpf_dynptr_size(sig_ptr);
+ sig = __bpf_dynptr_data(sig_ptr, sig_len);
+
+ return verify_pkcs7_signature(data, data_len, sig, sig_len,
+ trusted_keyring->key,
+ VERIFYING_BPF_SIGNATURE, NULL,
+ NULL);
+#else
+ return -EOPNOTSUPP;
+#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
+}
+#endif /* CONFIG_KEYS */
+
+typedef int (*bpf_task_work_callback_t)(struct bpf_map *map, void *key, void *value);
+
+enum bpf_task_work_state {
+ /* bpf_task_work is ready to be used */
+ BPF_TW_STANDBY = 0,
+ /* irq work scheduling in progress */
+ BPF_TW_PENDING,
+ /* task work scheduling in progress */
+ BPF_TW_SCHEDULING,
+ /* task work is scheduled successfully */
+ BPF_TW_SCHEDULED,
+ /* callback is running */
+ BPF_TW_RUNNING,
+ /* associated BPF map value is deleted */
+ BPF_TW_FREED,
+};
+
+struct bpf_task_work_ctx {
+ enum bpf_task_work_state state;
+ refcount_t refcnt;
+ struct callback_head work;
+ struct irq_work irq_work;
+ /* bpf_prog that schedules task work */
+ struct bpf_prog *prog;
+ /* task for which callback is scheduled */
+ struct task_struct *task;
+ /* the map and map value associated with this context */
+ struct bpf_map *map;
+ void *map_val;
+ enum task_work_notify_mode mode;
+ bpf_task_work_callback_t callback_fn;
+ struct rcu_head rcu;
+} __aligned(8);
+
+/* Actual type for struct bpf_task_work */
+struct bpf_task_work_kern {
+ struct bpf_task_work_ctx *ctx;
+};
+
+static void bpf_task_work_ctx_reset(struct bpf_task_work_ctx *ctx)
+{
+ if (ctx->prog) {
+ bpf_prog_put(ctx->prog);
+ ctx->prog = NULL;
+ }
+ if (ctx->task) {
+ bpf_task_release(ctx->task);
+ ctx->task = NULL;
+ }
+}
+
+static bool bpf_task_work_ctx_tryget(struct bpf_task_work_ctx *ctx)
+{
+ return refcount_inc_not_zero(&ctx->refcnt);
+}
+
+static void bpf_task_work_ctx_put(struct bpf_task_work_ctx *ctx)
+{
+ if (!refcount_dec_and_test(&ctx->refcnt))
+ return;
+
+ bpf_task_work_ctx_reset(ctx);
+
+ /* bpf_mem_free expects migration to be disabled */
+ migrate_disable();
+ bpf_mem_free(&bpf_global_ma, ctx);
+ migrate_enable();
+}
+
+static void bpf_task_work_cancel(struct bpf_task_work_ctx *ctx)
+{
+ /*
+ * Scheduled task_work callback holds ctx ref, so if we successfully
+ * cancelled, we put that ref on callback's behalf. If we couldn't
+ * cancel, callback will inevitably run or has already completed
+ * running, and it would have taken care of its ctx ref itself.
+ */
+ if (task_work_cancel(ctx->task, &ctx->work))
+ bpf_task_work_ctx_put(ctx);
+}
+
+static void bpf_task_work_callback(struct callback_head *cb)
+{
+ struct bpf_task_work_ctx *ctx = container_of(cb, struct bpf_task_work_ctx, work);
+ enum bpf_task_work_state state;
+ u32 idx;
+ void *key;
+
+ /* Read lock is needed to protect ctx and map key/value access */
+ guard(rcu_tasks_trace)();
+ /*
+ * This callback may start running before bpf_task_work_irq() switched to
+ * SCHEDULED state, so handle both transition variants SCHEDULING|SCHEDULED -> RUNNING.
+ */
+ state = cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_RUNNING);
+ if (state == BPF_TW_SCHEDULED)
+ state = cmpxchg(&ctx->state, BPF_TW_SCHEDULED, BPF_TW_RUNNING);
+ if (state == BPF_TW_FREED) {
+ bpf_task_work_ctx_put(ctx);
+ return;
+ }
+
+ key = (void *)map_key_from_value(ctx->map, ctx->map_val, &idx);
+
+ migrate_disable();
+ ctx->callback_fn(ctx->map, key, ctx->map_val);
+ migrate_enable();
+
+ bpf_task_work_ctx_reset(ctx);
+ (void)cmpxchg(&ctx->state, BPF_TW_RUNNING, BPF_TW_STANDBY);
+
+ bpf_task_work_ctx_put(ctx);
+}
+
+static void bpf_task_work_irq(struct irq_work *irq_work)
+{
+ struct bpf_task_work_ctx *ctx = container_of(irq_work, struct bpf_task_work_ctx, irq_work);
+ enum bpf_task_work_state state;
+ int err;
+
+ guard(rcu_tasks_trace)();
+
+ if (cmpxchg(&ctx->state, BPF_TW_PENDING, BPF_TW_SCHEDULING) != BPF_TW_PENDING) {
+ bpf_task_work_ctx_put(ctx);
+ return;
+ }
+
+ err = task_work_add(ctx->task, &ctx->work, ctx->mode);
+ if (err) {
+ bpf_task_work_ctx_reset(ctx);
+ /*
+ * try to switch back to STANDBY for another task_work reuse, but we might have
+ * gone to FREED already, which is fine as we already cleaned up after ourselves
+ */
+ (void)cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_STANDBY);
+ bpf_task_work_ctx_put(ctx);
+ return;
+ }
+
+ /*
+ * It's technically possible for just scheduled task_work callback to
+ * complete running by now, going SCHEDULING -> RUNNING and then
+ * dropping its ctx refcount. Instead of capturing extra ref just to
+ * protected below ctx->state access, we rely on RCU protection to
+ * perform below SCHEDULING -> SCHEDULED attempt.
+ */
+ state = cmpxchg(&ctx->state, BPF_TW_SCHEDULING, BPF_TW_SCHEDULED);
+ if (state == BPF_TW_FREED)
+ bpf_task_work_cancel(ctx); /* clean up if we switched into FREED state */
+}
+
+static struct bpf_task_work_ctx *bpf_task_work_fetch_ctx(struct bpf_task_work *tw,
+ struct bpf_map *map)
+{
+ struct bpf_task_work_kern *twk = (void *)tw;
+ struct bpf_task_work_ctx *ctx, *old_ctx;
+
+ ctx = READ_ONCE(twk->ctx);
+ if (ctx)
+ return ctx;
+
+ ctx = bpf_mem_alloc(&bpf_global_ma, sizeof(struct bpf_task_work_ctx));
+ if (!ctx)
+ return ERR_PTR(-ENOMEM);
+
+ memset(ctx, 0, sizeof(*ctx));
+ refcount_set(&ctx->refcnt, 1); /* map's own ref */
+ ctx->state = BPF_TW_STANDBY;
+
+ old_ctx = cmpxchg(&twk->ctx, NULL, ctx);
+ if (old_ctx) {
+ /*
+ * tw->ctx is set by concurrent BPF program, release allocated
+ * memory and try to reuse already set context.
+ */
+ bpf_mem_free(&bpf_global_ma, ctx);
+ return old_ctx;
+ }
+
+ return ctx; /* Success */
+}
+
+static struct bpf_task_work_ctx *bpf_task_work_acquire_ctx(struct bpf_task_work *tw,
+ struct bpf_map *map)
+{
+ struct bpf_task_work_ctx *ctx;
+
+ ctx = bpf_task_work_fetch_ctx(tw, map);
+ if (IS_ERR(ctx))
+ return ctx;
+
+ /* try to get ref for task_work callback to hold */
+ if (!bpf_task_work_ctx_tryget(ctx))
+ return ERR_PTR(-EBUSY);
+
+ if (cmpxchg(&ctx->state, BPF_TW_STANDBY, BPF_TW_PENDING) != BPF_TW_STANDBY) {
+ /* lost acquiring race or map_release_uref() stole it from us, put ref and bail */
+ bpf_task_work_ctx_put(ctx);
+ return ERR_PTR(-EBUSY);
+ }
+
+ /*
+ * If no process or bpffs is holding a reference to the map, no new callbacks should be
+ * scheduled. This does not address any race or correctness issue, but rather is a policy
+ * choice: dropping user references should stop everything.
+ */
+ if (!atomic64_read(&map->usercnt)) {
+ /* drop ref we just got for task_work callback itself */
+ bpf_task_work_ctx_put(ctx);
+ /* transfer map's ref into cancel_and_free() */
+ bpf_task_work_cancel_and_free(tw);
+ return ERR_PTR(-EBUSY);
+ }
+
+ return ctx;
+}
+
+static int bpf_task_work_schedule(struct task_struct *task, struct bpf_task_work *tw,
+ struct bpf_map *map, bpf_task_work_callback_t callback_fn,
+ struct bpf_prog_aux *aux, enum task_work_notify_mode mode)
+{
+ struct bpf_prog *prog;
+ struct bpf_task_work_ctx *ctx;
+ int err;
+
+ BTF_TYPE_EMIT(struct bpf_task_work);
+
+ prog = bpf_prog_inc_not_zero(aux->prog);
+ if (IS_ERR(prog))
+ return -EBADF;
+ task = bpf_task_acquire(task);
+ if (!task) {
+ err = -EBADF;
+ goto release_prog;
+ }
+
+ ctx = bpf_task_work_acquire_ctx(tw, map);
+ if (IS_ERR(ctx)) {
+ err = PTR_ERR(ctx);
+ goto release_all;
+ }
+
+ ctx->task = task;
+ ctx->callback_fn = callback_fn;
+ ctx->prog = prog;
+ ctx->mode = mode;
+ ctx->map = map;
+ ctx->map_val = (void *)tw - map->record->task_work_off;
+ init_task_work(&ctx->work, bpf_task_work_callback);
+ init_irq_work(&ctx->irq_work, bpf_task_work_irq);
+
+ irq_work_queue(&ctx->irq_work);
+ return 0;
+
+release_all:
+ bpf_task_release(task);
+release_prog:
+ bpf_prog_put(prog);
+ return err;
+}
+
+/**
+ * bpf_task_work_schedule_signal - Schedule BPF callback using task_work_add with TWA_SIGNAL mode
+ * @task: Task struct for which callback should be scheduled
+ * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping
+ * @map__map: bpf_map that embeds struct bpf_task_work in the values
+ * @callback: pointer to BPF subprogram to call
+ * @aux__prog: user should pass NULL
+ *
+ * Return: 0 if task work has been scheduled successfully, negative error code otherwise
+ */
+__bpf_kfunc int bpf_task_work_schedule_signal(struct task_struct *task, struct bpf_task_work *tw,
+ void *map__map, bpf_task_work_callback_t callback,
+ void *aux__prog)
+{
+ return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_SIGNAL);
+}
+
+/**
+ * bpf_task_work_schedule_resume - Schedule BPF callback using task_work_add with TWA_RESUME mode
+ * @task: Task struct for which callback should be scheduled
+ * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping
+ * @map__map: bpf_map that embeds struct bpf_task_work in the values
+ * @callback: pointer to BPF subprogram to call
+ * @aux__prog: user should pass NULL
+ *
+ * Return: 0 if task work has been scheduled successfully, negative error code otherwise
+ */
+__bpf_kfunc int bpf_task_work_schedule_resume(struct task_struct *task, struct bpf_task_work *tw,
+ void *map__map, bpf_task_work_callback_t callback,
+ void *aux__prog)
+{
+ return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_RESUME);
+}
+
__bpf_kfunc_end_defs();
+static void bpf_task_work_cancel_scheduled(struct irq_work *irq_work)
+{
+ struct bpf_task_work_ctx *ctx = container_of(irq_work, struct bpf_task_work_ctx, irq_work);
+
+ bpf_task_work_cancel(ctx); /* this might put task_work callback's ref */
+ bpf_task_work_ctx_put(ctx); /* and here we put map's own ref that was transferred to us */
+}
+
+void bpf_task_work_cancel_and_free(void *val)
+{
+ struct bpf_task_work_kern *twk = val;
+ struct bpf_task_work_ctx *ctx;
+ enum bpf_task_work_state state;
+
+ ctx = xchg(&twk->ctx, NULL);
+ if (!ctx)
+ return;
+
+ state = xchg(&ctx->state, BPF_TW_FREED);
+ if (state == BPF_TW_SCHEDULED) {
+ /* run in irq_work to avoid locks in NMI */
+ init_irq_work(&ctx->irq_work, bpf_task_work_cancel_scheduled);
+ irq_work_queue(&ctx->irq_work);
+ return;
+ }
+
+ bpf_task_work_ctx_put(ctx); /* put bpf map's ref */
+}
+
BTF_KFUNCS_START(generic_btf_ids)
#ifdef CONFIG_CRASH_DUMP
BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
@@ -2953,11 +4243,16 @@ BTF_ID_FLAGS(func, bpf_list_push_front_impl)
BTF_ID_FLAGS(func, bpf_list_push_back_impl)
BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_list_front, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_list_back, KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE)
BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_rbtree_add_impl)
BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_root, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_left, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_rbtree_right, KF_RET_NULL)
#ifdef CONFIG_CGROUPS
BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
@@ -2968,7 +4263,19 @@ BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU)
BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL)
#endif
BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_task_from_vpid, KF_ACQUIRE | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_throw)
+#ifdef CONFIG_BPF_EVENTS
+BTF_ID_FLAGS(func, bpf_send_signal_task, KF_TRUSTED_ARGS)
+#endif
+#ifdef CONFIG_KEYS
+BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE)
+#ifdef CONFIG_SYSTEM_DATA_VERIFICATION
+BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE)
+#endif
+#endif
BTF_KFUNCS_END(generic_btf_ids)
static const struct btf_kfunc_id_set generic_kfunc_set = {
@@ -2986,8 +4293,8 @@ BTF_ID(func, bpf_cgroup_release_dtor)
#endif
BTF_KFUNCS_START(common_btf_ids)
-BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx)
-BTF_ID_FLAGS(func, bpf_rdonly_cast)
+BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx, KF_FASTCALL)
+BTF_ID_FLAGS(func, bpf_rdonly_cast, KF_FASTCALL)
BTF_ID_FLAGS(func, bpf_rcu_read_lock)
BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
BTF_ID_FLAGS(func, bpf_dynptr_slice, KF_RET_NULL)
@@ -3014,7 +4321,11 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null)
BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
BTF_ID_FLAGS(func, bpf_dynptr_size)
BTF_ID_FLAGS(func, bpf_dynptr_clone)
+BTF_ID_FLAGS(func, bpf_dynptr_copy)
+BTF_ID_FLAGS(func, bpf_dynptr_memset)
+#ifdef CONFIG_NET
BTF_ID_FLAGS(func, bpf_modify_return_test_tp)
+#endif
BTF_ID_FLAGS(func, bpf_wq_init)
BTF_ID_FLAGS(func, bpf_wq_set_callback_impl)
BTF_ID_FLAGS(func, bpf_wq_start)
@@ -3023,6 +4334,46 @@ BTF_ID_FLAGS(func, bpf_preempt_enable)
BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW)
BTF_ID_FLAGS(func, bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_bits_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_get_kmem_cache)
+BTF_ID_FLAGS(func, bpf_iter_kmem_cache_new, KF_ITER_NEW | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_kmem_cache_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_kmem_cache_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_local_irq_save)
+BTF_ID_FLAGS(func, bpf_local_irq_restore)
+BTF_ID_FLAGS(func, bpf_probe_read_user_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_user_str_dynptr)
+BTF_ID_FLAGS(func, bpf_probe_read_kernel_str_dynptr)
+BTF_ID_FLAGS(func, bpf_copy_from_user_dynptr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_str_dynptr, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_copy_from_user_task_str_dynptr, KF_SLEEPABLE | KF_TRUSTED_ARGS)
+#ifdef CONFIG_DMA_SHARED_BUFFER
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_new, KF_ITER_NEW | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
+#endif
+BTF_ID_FLAGS(func, __bpf_trap)
+BTF_ID_FLAGS(func, bpf_strcmp);
+BTF_ID_FLAGS(func, bpf_strcasecmp);
+BTF_ID_FLAGS(func, bpf_strchr);
+BTF_ID_FLAGS(func, bpf_strchrnul);
+BTF_ID_FLAGS(func, bpf_strnchr);
+BTF_ID_FLAGS(func, bpf_strrchr);
+BTF_ID_FLAGS(func, bpf_strlen);
+BTF_ID_FLAGS(func, bpf_strnlen);
+BTF_ID_FLAGS(func, bpf_strspn);
+BTF_ID_FLAGS(func, bpf_strcspn);
+BTF_ID_FLAGS(func, bpf_strstr);
+BTF_ID_FLAGS(func, bpf_strnstr);
+#if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS)
+BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)
+#endif
+BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_task_work_schedule_signal, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_task_work_schedule_resume, KF_TRUSTED_ARGS)
BTF_KFUNCS_END(common_btf_ids)
static const struct btf_kfunc_id_set common_kfunc_set = {
@@ -3051,6 +4402,7 @@ static int __init kfunc_init(void)
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set);
ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &generic_kfunc_set);
+ ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &generic_kfunc_set);
ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors,
ARRAY_SIZE(generic_dtors),
THIS_MODULE);