summaryrefslogtreecommitdiff
path: root/kernel/bpf/syscall.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/syscall.c')
-rw-r--r--kernel/bpf/syscall.c134
1 files changed, 73 insertions, 61 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64131f88c553..adc83cb82f37 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -181,7 +181,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
int err;
/* Need to create a kthread, thus must support schedule */
- if (bpf_map_is_dev_bound(map)) {
+ if (bpf_map_is_offloaded(map)) {
return bpf_map_offload_update_elem(map, key, value, flags);
} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
@@ -238,7 +238,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
void *ptr;
int err;
- if (bpf_map_is_dev_bound(map))
+ if (bpf_map_is_offloaded(map))
return bpf_map_offload_lookup_elem(map, key, value);
bpf_disable_instrumentation();
@@ -309,7 +309,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
* __GFP_RETRY_MAYFAIL to avoid such situations.
*/
- const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT;
+ gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO);
unsigned int flags = 0;
unsigned long align = 1;
void *area;
@@ -390,7 +390,7 @@ static int bpf_map_alloc_id(struct bpf_map *map)
return id > 0 ? 0 : id;
}
-void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
+void bpf_map_free_id(struct bpf_map *map)
{
unsigned long flags;
@@ -402,18 +402,12 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
if (!map->id)
return;
- if (do_idr_lock)
- spin_lock_irqsave(&map_idr_lock, flags);
- else
- __acquire(&map_idr_lock);
+ spin_lock_irqsave(&map_idr_lock, flags);
idr_remove(&map_idr, map->id);
map->id = 0;
- if (do_idr_lock)
- spin_unlock_irqrestore(&map_idr_lock, flags);
- else
- __release(&map_idr_lock);
+ spin_unlock_irqrestore(&map_idr_lock, flags);
}
#ifdef CONFIG_MEMCG_KMEM
@@ -424,7 +418,8 @@ static void bpf_map_save_memcg(struct bpf_map *map)
* So we have to check map->objcg for being NULL each time it's
* being used.
*/
- map->objcg = get_obj_cgroup_from_current();
+ if (memcg_bpf_enabled())
+ map->objcg = get_obj_cgroup_from_current();
}
static void bpf_map_release_memcg(struct bpf_map *map)
@@ -470,6 +465,21 @@ void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
return ptr;
}
+void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size,
+ gfp_t flags)
+{
+ struct mem_cgroup *memcg, *old_memcg;
+ void *ptr;
+
+ memcg = bpf_map_get_memcg(map);
+ old_memcg = set_active_memcg(memcg);
+ ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT);
+ set_active_memcg(old_memcg);
+ mem_cgroup_put(memcg);
+
+ return ptr;
+}
+
void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
size_t align, gfp_t flags)
{
@@ -527,9 +537,6 @@ void btf_record_free(struct btf_record *rec)
return;
for (i = 0; i < rec->cnt; i++) {
switch (rec->fields[i].type) {
- case BPF_SPIN_LOCK:
- case BPF_TIMER:
- break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
if (rec->fields[i].kptr.module)
@@ -538,7 +545,11 @@ void btf_record_free(struct btf_record *rec)
break;
case BPF_LIST_HEAD:
case BPF_LIST_NODE:
- /* Nothing to release for bpf_list_head */
+ case BPF_RB_ROOT:
+ case BPF_RB_NODE:
+ case BPF_SPIN_LOCK:
+ case BPF_TIMER:
+ /* Nothing to release */
break;
default:
WARN_ON_ONCE(1);
@@ -571,9 +582,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
new_rec->cnt = 0;
for (i = 0; i < rec->cnt; i++) {
switch (fields[i].type) {
- case BPF_SPIN_LOCK:
- case BPF_TIMER:
- break;
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
btf_get(fields[i].kptr.btf);
@@ -584,7 +592,11 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
break;
case BPF_LIST_HEAD:
case BPF_LIST_NODE:
- /* Nothing to acquire for bpf_list_head */
+ case BPF_RB_ROOT:
+ case BPF_RB_NODE:
+ case BPF_SPIN_LOCK:
+ case BPF_TIMER:
+ /* Nothing to acquire */
break;
default:
ret = -EFAULT;
@@ -664,7 +676,13 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
continue;
bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off);
break;
+ case BPF_RB_ROOT:
+ if (WARN_ON_ONCE(rec->spin_lock_off < 0))
+ continue;
+ bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off);
+ break;
case BPF_LIST_NODE:
+ case BPF_RB_NODE:
break;
default:
WARN_ON_ONCE(1);
@@ -706,13 +724,13 @@ static void bpf_map_put_uref(struct bpf_map *map)
}
/* decrement map refcnt and schedule it for freeing via workqueue
- * (unrelying map implementation ops->map_free() might sleep)
+ * (underlying map implementation ops->map_free() might sleep)
*/
-static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
+void bpf_map_put(struct bpf_map *map)
{
if (atomic64_dec_and_test(&map->refcnt)) {
/* bpf_map_free_id() must be called first */
- bpf_map_free_id(map, do_idr_lock);
+ bpf_map_free_id(map);
btf_put(map->btf);
INIT_WORK(&map->work, bpf_map_free_deferred);
/* Avoid spawning kworkers, since they all might contend
@@ -721,11 +739,6 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
queue_work(system_unbound_wq, &map->work);
}
}
-
-void bpf_map_put(struct bpf_map *map)
-{
- __bpf_map_put(map, true);
-}
EXPORT_SYMBOL_GPL(bpf_map_put);
void bpf_map_put_with_uref(struct bpf_map *map)
@@ -882,10 +895,10 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
/* set default open/close callbacks */
vma->vm_ops = &bpf_map_default_vmops;
vma->vm_private_data = map;
- vma->vm_flags &= ~VM_MAYEXEC;
+ vm_flags_clear(vma, VM_MAYEXEC);
if (!(vma->vm_flags & VM_WRITE))
/* disallow re-mapping with PROT_WRITE */
- vma->vm_flags &= ~VM_MAYWRITE;
+ vm_flags_clear(vma, VM_MAYWRITE);
err = map->ops->map_mmap(map, vma);
if (err)
@@ -1005,7 +1018,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
return -EINVAL;
map->record = btf_parse_fields(btf, value_type,
- BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD,
+ BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
+ BPF_RB_ROOT,
map->value_size);
if (!IS_ERR_OR_NULL(map->record)) {
int i;
@@ -1053,6 +1067,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
}
break;
case BPF_LIST_HEAD:
+ case BPF_RB_ROOT:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_LRU_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY) {
@@ -1483,7 +1498,7 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
goto err_put;
}
- if (bpf_map_is_dev_bound(map)) {
+ if (bpf_map_is_offloaded(map)) {
err = bpf_map_offload_delete_elem(map, key);
goto out;
} else if (IS_FD_PROG_ARRAY(map) ||
@@ -1547,7 +1562,7 @@ static int map_get_next_key(union bpf_attr *attr)
if (!next_key)
goto free_key;
- if (bpf_map_is_dev_bound(map)) {
+ if (bpf_map_is_offloaded(map)) {
err = bpf_map_offload_get_next_key(map, key, next_key);
goto out;
}
@@ -1605,7 +1620,7 @@ int generic_map_delete_batch(struct bpf_map *map,
map->key_size))
break;
- if (bpf_map_is_dev_bound(map)) {
+ if (bpf_map_is_offloaded(map)) {
err = bpf_map_offload_delete_elem(map, key);
break;
}
@@ -1851,7 +1866,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
- if (!bpf_map_is_dev_bound(map)) {
+ if (!bpf_map_is_offloaded(map)) {
bpf_disable_instrumentation();
rcu_read_lock();
err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags);
@@ -1944,7 +1959,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
if (!ops)
return -EINVAL;
- if (!bpf_prog_is_dev_bound(prog->aux))
+ if (!bpf_prog_is_offloaded(prog->aux))
prog->aux->ops = ops;
else
prog->aux->ops = &bpf_offload_prog_ops;
@@ -1972,7 +1987,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
return;
if (audit_enabled == AUDIT_OFF)
return;
- if (op == BPF_AUDIT_LOAD)
+ if (!in_irq() && !irqs_disabled())
ctx = audit_context();
ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
if (unlikely(!ab))
@@ -2001,7 +2016,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
return id > 0 ? 0 : id;
}
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog)
{
unsigned long flags;
@@ -2013,18 +2028,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
if (!prog->aux->id)
return;
- if (do_idr_lock)
- spin_lock_irqsave(&prog_idr_lock, flags);
- else
- __acquire(&prog_idr_lock);
-
+ spin_lock_irqsave(&prog_idr_lock, flags);
idr_remove(&prog_idr, prog->aux->id);
prog->aux->id = 0;
-
- if (do_idr_lock)
- spin_unlock_irqrestore(&prog_idr_lock, flags);
- else
- __release(&prog_idr_lock);
+ spin_unlock_irqrestore(&prog_idr_lock, flags);
}
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
@@ -2067,17 +2074,15 @@ static void bpf_prog_put_deferred(struct work_struct *work)
prog = aux->prog;
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
+ bpf_prog_free_id(prog);
__bpf_prog_put_noref(prog, true);
}
-static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+static void __bpf_prog_put(struct bpf_prog *prog)
{
struct bpf_prog_aux *aux = prog->aux;
if (atomic64_dec_and_test(&aux->refcnt)) {
- /* bpf_prog_free_id() must be called first */
- bpf_prog_free_id(prog, do_idr_lock);
-
if (in_irq() || irqs_disabled()) {
INIT_WORK(&aux->work, bpf_prog_put_deferred);
schedule_work(&aux->work);
@@ -2089,7 +2094,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
void bpf_prog_put(struct bpf_prog *prog)
{
- __bpf_prog_put(prog, true);
+ __bpf_prog_put(prog);
}
EXPORT_SYMBOL_GPL(bpf_prog_put);
@@ -2255,7 +2260,7 @@ bool bpf_prog_get_ok(struct bpf_prog *prog,
if (prog->type != *attach_type)
return false;
- if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv)
+ if (bpf_prog_is_offloaded(prog->aux) && !attach_drv)
return false;
return true;
@@ -2491,7 +2496,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
BPF_F_TEST_STATE_FREQ |
BPF_F_SLEEPABLE |
BPF_F_TEST_RND_HI32 |
- BPF_F_XDP_HAS_FRAGS))
+ BPF_F_XDP_HAS_FRAGS |
+ BPF_F_XDP_DEV_BOUND_ONLY))
return -EINVAL;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -2575,7 +2581,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
prog->aux->attach_btf = attach_btf;
prog->aux->attach_btf_id = attr->attach_btf_id;
prog->aux->dst_prog = dst_prog;
- prog->aux->offload_requested = !!attr->prog_ifindex;
+ prog->aux->dev_bound = !!attr->prog_ifindex;
prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
@@ -2599,7 +2605,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
prog->gpl_compatible = is_gpl ? 1 : 0;
if (bpf_prog_is_dev_bound(prog->aux)) {
- err = bpf_prog_offload_init(prog, attr);
+ err = bpf_prog_dev_bound_init(prog, attr);
+ if (err)
+ goto free_prog_sec;
+ }
+
+ if (type == BPF_PROG_TYPE_EXT && dst_prog &&
+ bpf_prog_is_dev_bound(dst_prog->aux)) {
+ err = bpf_prog_dev_bound_inherit(prog, dst_prog);
if (err)
goto free_prog_sec;
}
@@ -3997,7 +4010,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
return -EFAULT;
}
- if (bpf_prog_is_dev_bound(prog->aux)) {
+ if (bpf_prog_is_offloaded(prog->aux)) {
err = bpf_prog_offload_info_fill(&info, prog);
if (err)
return err;
@@ -4225,7 +4238,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
}
info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id;
- if (bpf_map_is_dev_bound(map)) {
+ if (bpf_map_is_offloaded(map)) {
err = bpf_map_offload_info_fill(&info, map);
if (err)
return err;
@@ -5319,7 +5332,6 @@ static struct ctl_table bpf_syscall_table[] = {
{
.procname = "bpf_stats_enabled",
.data = &bpf_stats_enabled_key.key,
- .maxlen = sizeof(bpf_stats_enabled_key),
.mode = 0644,
.proc_handler = bpf_stats_handler,
},
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-09 05:38:15 +0000