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.c1135
1 files changed, 797 insertions, 338 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 869265852d51..4ff82144f885 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
+#include <crypto/sha2.h>
#include <linux/bpf.h>
#include <linux/bpf-cgroup.h>
#include <linux/bpf_trace.h>
@@ -35,6 +36,10 @@
#include <linux/rcupdate_trace.h>
#include <linux/memcontrol.h>
#include <linux/trace_events.h>
+#include <linux/tracepoint.h>
+#include <linux/overflow.h>
+#include <linux/cookie.h>
+#include <linux/verification.h>
#include <net/netfilter/nf_bpf_link.h>
#include <net/netkit.h>
@@ -51,6 +56,7 @@
#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY)
DEFINE_PER_CPU(int, bpf_prog_active);
+DEFINE_COOKIE(bpf_map_cookie);
static DEFINE_IDR(prog_idr);
static DEFINE_SPINLOCK(prog_idr_lock);
static DEFINE_IDR(map_idr);
@@ -152,7 +158,90 @@ static void maybe_wait_bpf_programs(struct bpf_map *map)
*/
if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
- synchronize_rcu();
+ synchronize_rcu_expedited();
+}
+
+static void unpin_uptr_kaddr(void *kaddr)
+{
+ if (kaddr)
+ unpin_user_page(virt_to_page(kaddr));
+}
+
+static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj)
+{
+ const struct btf_field *field;
+ void **uptr_addr;
+ int i;
+
+ for (i = 0, field = rec->fields; i < cnt; i++, field++) {
+ if (field->type != BPF_UPTR)
+ continue;
+
+ uptr_addr = obj + field->offset;
+ unpin_uptr_kaddr(*uptr_addr);
+ }
+}
+
+static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj)
+{
+ if (!btf_record_has_field(rec, BPF_UPTR))
+ return;
+
+ __bpf_obj_unpin_uptrs(rec, rec->cnt, obj);
+}
+
+static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj)
+{
+ const struct btf_field *field;
+ const struct btf_type *t;
+ unsigned long start, end;
+ struct page *page;
+ void **uptr_addr;
+ int i, err;
+
+ if (!btf_record_has_field(rec, BPF_UPTR))
+ return 0;
+
+ for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) {
+ if (field->type != BPF_UPTR)
+ continue;
+
+ uptr_addr = obj + field->offset;
+ start = *(unsigned long *)uptr_addr;
+ if (!start)
+ continue;
+
+ t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id);
+ /* t->size was checked for zero before */
+ if (check_add_overflow(start, t->size - 1, &end)) {
+ err = -EFAULT;
+ goto unpin_all;
+ }
+
+ /* The uptr's struct cannot span across two pages */
+ if ((start & PAGE_MASK) != (end & PAGE_MASK)) {
+ err = -EOPNOTSUPP;
+ goto unpin_all;
+ }
+
+ err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page);
+ if (err != 1)
+ goto unpin_all;
+
+ if (PageHighMem(page)) {
+ err = -EOPNOTSUPP;
+ unpin_user_page(page);
+ goto unpin_all;
+ }
+
+ *uptr_addr = page_address(page) + offset_in_page(start);
+ }
+
+ return 0;
+
+unpin_all:
+ __bpf_obj_unpin_uptrs(rec, i, obj);
+ return err;
}
static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
@@ -199,9 +288,14 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
err = map->ops->map_push_elem(map, value, flags);
} else {
- rcu_read_lock();
- err = map->ops->map_update_elem(map, key, value, flags);
- rcu_read_unlock();
+ err = bpf_obj_pin_uptrs(map->record, value);
+ if (!err) {
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value, flags);
+ rcu_read_unlock();
+ if (err)
+ bpf_obj_unpin_uptrs(map->record, value);
+ }
}
bpf_enable_instrumentation();
@@ -226,7 +320,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
- err = bpf_stackmap_copy(map, key, value);
+ err = bpf_stackmap_extract(map, key, value, false);
} else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) {
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
@@ -385,7 +479,7 @@ void bpf_map_free_id(struct bpf_map *map)
spin_unlock_irqrestore(&map_idr_lock, flags);
}
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
static void bpf_map_save_memcg(struct bpf_map *map)
{
/* Currently if a map is created by a process belonging to the root
@@ -426,6 +520,21 @@ void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
return ptr;
}
+void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags,
+ int node)
+{
+ struct mem_cgroup *memcg, *old_memcg;
+ void *ptr;
+
+ memcg = bpf_map_get_memcg(map);
+ old_memcg = set_active_memcg(memcg);
+ ptr = kmalloc_nolock(size, flags | __GFP_ACCOUNT, node);
+ set_active_memcg(old_memcg);
+ mem_cgroup_put(memcg);
+
+ return ptr;
+}
+
void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
{
struct mem_cgroup *memcg, *old_memcg;
@@ -480,32 +589,49 @@ static void bpf_map_release_memcg(struct bpf_map *map)
}
#endif
-int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+static bool can_alloc_pages(void)
+{
+ return preempt_count() == 0 && !irqs_disabled() &&
+ !IS_ENABLED(CONFIG_PREEMPT_RT);
+}
+
+static struct page *__bpf_alloc_page(int nid)
+{
+ if (!can_alloc_pages())
+ return alloc_pages_nolock(__GFP_ACCOUNT, nid, 0);
+
+ return alloc_pages_node(nid,
+ GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT
+ | __GFP_NOWARN,
+ 0);
+}
+
+int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
unsigned long nr_pages, struct page **pages)
{
unsigned long i, j;
struct page *pg;
int ret = 0;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg, *old_memcg;
memcg = bpf_map_get_memcg(map);
old_memcg = set_active_memcg(memcg);
#endif
for (i = 0; i < nr_pages; i++) {
- pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0);
+ pg = __bpf_alloc_page(nid);
if (pg) {
pages[i] = pg;
continue;
}
for (j = 0; j < i; j++)
- __free_page(pages[j]);
+ free_pages_nolock(pages[j], 0);
ret = -ENOMEM;
break;
}
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
set_active_memcg(old_memcg);
mem_cgroup_put(memcg);
#endif
@@ -548,18 +674,22 @@ void btf_record_free(struct btf_record *rec)
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
+ case BPF_UPTR:
if (rec->fields[i].kptr.module)
module_put(rec->fields[i].kptr.module);
- btf_put(rec->fields[i].kptr.btf);
+ if (btf_is_kernel(rec->fields[i].kptr.btf))
+ btf_put(rec->fields[i].kptr.btf);
break;
case BPF_LIST_HEAD:
case BPF_LIST_NODE:
case BPF_RB_ROOT:
case BPF_RB_NODE:
case BPF_SPIN_LOCK:
+ case BPF_RES_SPIN_LOCK:
case BPF_TIMER:
case BPF_REFCOUNT:
case BPF_WORKQUEUE:
+ case BPF_TASK_WORK:
/* Nothing to release */
break;
default:
@@ -584,7 +714,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
if (IS_ERR_OR_NULL(rec))
return NULL;
- size = offsetof(struct btf_record, fields[rec->cnt]);
+ size = struct_size(rec, fields, rec->cnt);
new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN);
if (!new_rec)
return ERR_PTR(-ENOMEM);
@@ -596,7 +726,9 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
case BPF_KPTR_UNREF:
case BPF_KPTR_REF:
case BPF_KPTR_PERCPU:
- btf_get(fields[i].kptr.btf);
+ case BPF_UPTR:
+ if (btf_is_kernel(fields[i].kptr.btf))
+ btf_get(fields[i].kptr.btf);
if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) {
ret = -ENXIO;
goto free;
@@ -607,9 +739,11 @@ struct btf_record *btf_record_dup(const struct btf_record *rec)
case BPF_RB_ROOT:
case BPF_RB_NODE:
case BPF_SPIN_LOCK:
+ case BPF_RES_SPIN_LOCK:
case BPF_TIMER:
case BPF_REFCOUNT:
case BPF_WORKQUEUE:
+ case BPF_TASK_WORK:
/* Nothing to acquire */
break;
default:
@@ -636,7 +770,7 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r
return false;
if (rec_a->cnt != rec_b->cnt)
return false;
- size = offsetof(struct btf_record, fields[rec_a->cnt]);
+ size = struct_size(rec_a, fields, rec_a->cnt);
/* btf_parse_fields uses kzalloc to allocate a btf_record, so unused
* members are zeroed out. So memcmp is safe to do without worrying
* about padding/unused fields.
@@ -668,6 +802,13 @@ void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj)
bpf_wq_cancel_and_free(obj + rec->wq_off);
}
+void bpf_obj_free_task_work(const struct btf_record *rec, void *obj)
+{
+ if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TASK_WORK)))
+ return;
+ bpf_task_work_cancel_and_free(obj + rec->task_work_off);
+}
+
void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
{
const struct btf_field *fields;
@@ -684,6 +825,7 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
switch (fields[i].type) {
case BPF_SPIN_LOCK:
+ case BPF_RES_SPIN_LOCK:
break;
case BPF_TIMER:
bpf_timer_cancel_and_free(field_ptr);
@@ -691,6 +833,9 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
case BPF_WORKQUEUE:
bpf_wq_cancel_and_free(field_ptr);
break;
+ case BPF_TASK_WORK:
+ bpf_task_work_cancel_and_free(field_ptr);
+ break;
case BPF_KPTR_UNREF:
WRITE_ONCE(*(u64 *)field_ptr, 0);
break;
@@ -703,15 +848,17 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
if (!btf_is_kernel(field->kptr.btf)) {
pointee_struct_meta = btf_find_struct_meta(field->kptr.btf,
field->kptr.btf_id);
- migrate_disable();
__bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ?
pointee_struct_meta->record : NULL,
fields[i].type == BPF_KPTR_PERCPU);
- migrate_enable();
} else {
field->kptr.dtor(xchgd_field);
}
break;
+ case BPF_UPTR:
+ /* The caller ensured that no one is using the uptr */
+ unpin_uptr_kaddr(*(void **)field_ptr);
+ break;
case BPF_LIST_HEAD:
if (WARN_ON_ONCE(rec->spin_lock_off < 0))
continue;
@@ -733,17 +880,20 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj)
}
}
-/* called from workqueue */
-static void bpf_map_free_deferred(struct work_struct *work)
+static void bpf_map_free(struct bpf_map *map)
{
- struct bpf_map *map = container_of(work, struct bpf_map, work);
struct btf_record *rec = map->record;
struct btf *btf = map->btf;
- security_bpf_map_free(map);
- bpf_map_release_memcg(map);
- /* implementation dependent freeing */
+ /* implementation dependent freeing. Disabling migration to simplify
+ * the free of values or special fields allocated from bpf memory
+ * allocator.
+ */
+ kfree(map->excl_prog_sha);
+ migrate_disable();
map->ops->map_free(map);
+ migrate_enable();
+
/* Delay freeing of btf_record for maps, as map_free
* callback usually needs access to them. It is better to do it here
* than require each callback to do the free itself manually.
@@ -760,6 +910,17 @@ static void bpf_map_free_deferred(struct work_struct *work)
btf_put(btf);
}
+/* called from workqueue */
+static void bpf_map_free_deferred(struct work_struct *work)
+{
+ struct bpf_map *map = container_of(work, struct bpf_map, work);
+
+ security_bpf_map_free(map);
+ bpf_map_release_memcg(map);
+ bpf_map_owner_free(map);
+ bpf_map_free(map);
+}
+
static void bpf_map_put_uref(struct bpf_map *map)
{
if (atomic64_dec_and_test(&map->usercnt)) {
@@ -774,7 +935,7 @@ static void bpf_map_free_in_work(struct bpf_map *map)
/* Avoid spawning kworkers, since they all might contend
* for the same mutex like slab_mutex.
*/
- queue_work(system_unbound_wq, &map->work);
+ queue_work(system_dfl_wq, &map->work);
}
static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
@@ -829,7 +990,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
{
- fmode_t mode = f.file->f_mode;
+ fmode_t mode = fd_file(f)->f_mode;
/* Our file permissions may have been overridden by global
* map permissions facing syscall side.
@@ -851,12 +1012,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
struct bpf_map *map = filp->private_data;
u32 type = 0, jited = 0;
- if (map_type_contains_progs(map)) {
- spin_lock(&map->owner.lock);
- type = map->owner.type;
- jited = map->owner.jited;
- spin_unlock(&map->owner.lock);
+ spin_lock(&map->owner_lock);
+ if (map->owner) {
+ type = map->owner->type;
+ jited = map->owner->jited;
}
+ spin_unlock(&map->owner_lock);
seq_printf(m,
"map_type:\t%u\n"
@@ -928,7 +1089,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = {
static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct bpf_map *map = filp->private_data;
- int err;
+ int err = 0;
if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record))
return -ENOTSUPP;
@@ -952,24 +1113,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
err = -EACCES;
goto out;
}
+ bpf_map_write_active_inc(map);
}
+out:
+ mutex_unlock(&map->freeze_mutex);
+ if (err)
+ return err;
/* set default open/close callbacks */
vma->vm_ops = &bpf_map_default_vmops;
vma->vm_private_data = map;
vm_flags_clear(vma, VM_MAYEXEC);
+ /* If mapping is read-only, then disallow potentially re-mapping with
+ * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing
+ * means that as far as BPF map's memory-mapped VMAs are concerned,
+ * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set,
+ * both should be set, so we can forget about VM_MAYWRITE and always
+ * check just VM_WRITE
+ */
if (!(vma->vm_flags & VM_WRITE))
- /* disallow re-mapping with PROT_WRITE */
vm_flags_clear(vma, VM_MAYWRITE);
err = map->ops->map_mmap(map, vma);
- if (err)
- goto out;
+ if (err) {
+ if (vma->vm_flags & VM_WRITE)
+ bpf_map_write_active_dec(map);
+ }
- if (vma->vm_flags & VM_MAYWRITE)
- bpf_map_write_active_inc(map);
-out:
- mutex_unlock(&map->freeze_mutex);
return err;
}
@@ -992,7 +1162,7 @@ static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr
if (map->ops->map_get_unmapped_area)
return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags);
#ifdef CONFIG_MMU
- return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags);
+ return mm_get_unmapped_area(filp, addr, len, pgoff, flags);
#else
return addr;
#endif
@@ -1064,6 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size)
return src - orig_src;
}
+EXPORT_SYMBOL_GPL(bpf_obj_name_cpy);
int map_check_no_btf(const struct bpf_map *map,
const struct btf *btf,
@@ -1096,8 +1267,9 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
return -EINVAL;
map->record = btf_parse_fields(btf, value_type,
- BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
- BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE,
+ BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD |
+ BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR |
+ BPF_TASK_WORK,
map->value_size);
if (!IS_ERR_OR_NULL(map->record)) {
int i;
@@ -1115,6 +1287,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
case 0:
continue;
case BPF_SPIN_LOCK:
+ case BPF_RES_SPIN_LOCK:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY &&
map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
@@ -1128,6 +1301,7 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
break;
case BPF_TIMER:
case BPF_WORKQUEUE:
+ case BPF_TASK_WORK:
if (map->map_type != BPF_MAP_TYPE_HASH &&
map->map_type != BPF_MAP_TYPE_LRU_HASH &&
map->map_type != BPF_MAP_TYPE_ARRAY) {
@@ -1153,6 +1327,12 @@ static int map_check_btf(struct bpf_map *map, struct bpf_token *token,
goto free_map_tab;
}
break;
+ case BPF_UPTR:
+ if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) {
+ ret = -EOPNOTSUPP;
+ goto free_map_tab;
+ }
+ break;
case BPF_LIST_HEAD:
case BPF_RB_ROOT:
if (map->map_type != BPF_MAP_TYPE_HASH &&
@@ -1191,9 +1371,9 @@ static bool bpf_net_capable(void)
return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN);
}
-#define BPF_MAP_CREATE_LAST_FIELD map_token_fd
+#define BPF_MAP_CREATE_LAST_FIELD excl_prog_hash_size
/* called via syscall */
-static int map_create(union bpf_attr *attr)
+static int map_create(union bpf_attr *attr, bpfptr_t uattr)
{
const struct bpf_map_ops *ops;
struct bpf_token *token = NULL;
@@ -1314,6 +1494,7 @@ static int map_create(union bpf_attr *attr)
case BPF_MAP_TYPE_STRUCT_OPS:
case BPF_MAP_TYPE_CPUMAP:
case BPF_MAP_TYPE_ARENA:
+ case BPF_MAP_TYPE_INSN_ARRAY:
if (!bpf_token_capable(token, CAP_BPF))
goto put_token;
break;
@@ -1343,10 +1524,14 @@ static int map_create(union bpf_attr *attr)
if (err < 0)
goto free_map;
+ preempt_disable();
+ map->cookie = gen_cookie_next(&bpf_map_cookie);
+ preempt_enable();
+
atomic64_set(&map->refcnt, 1);
atomic64_set(&map->usercnt, 1);
mutex_init(&map->freeze_mutex);
- spin_lock_init(&map->owner.lock);
+ spin_lock_init(&map->owner_lock);
if (attr->btf_key_type_id || attr->btf_value_type_id ||
/* Even the map's value is a kernel's struct,
@@ -1383,7 +1568,30 @@ static int map_create(union bpf_attr *attr)
attr->btf_vmlinux_value_type_id;
}
- err = security_bpf_map_create(map, attr, token);
+ if (attr->excl_prog_hash) {
+ bpfptr_t uprog_hash = make_bpfptr(attr->excl_prog_hash, uattr.is_kernel);
+
+ if (attr->excl_prog_hash_size != SHA256_DIGEST_SIZE) {
+ err = -EINVAL;
+ goto free_map;
+ }
+
+ map->excl_prog_sha = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
+ if (!map->excl_prog_sha) {
+ err = -ENOMEM;
+ goto free_map;
+ }
+
+ if (copy_from_bpfptr(map->excl_prog_sha, uprog_hash, SHA256_DIGEST_SIZE)) {
+ err = -EFAULT;
+ goto free_map;
+ }
+ } else if (attr->excl_prog_hash_size) {
+ err = -EINVAL;
+ goto free_map;
+ }
+
+ err = security_bpf_map_create(map, attr, token, uattr.is_kernel);
if (err)
goto free_map_sec;
@@ -1411,28 +1619,12 @@ static int map_create(union bpf_attr *attr)
free_map_sec:
security_bpf_map_free(map);
free_map:
- btf_put(map->btf);
- map->ops->map_free(map);
+ bpf_map_free(map);
put_token:
bpf_token_put(token);
return err;
}
-/* if error is returned, fd is released.
- * On success caller should complete fd access with matching fdput()
- */
-struct bpf_map *__bpf_map_get(struct fd f)
-{
- if (!f.file)
- return ERR_PTR(-EBADF);
- if (f.file->f_op != &bpf_map_fops) {
- fdput(f);
- return ERR_PTR(-EINVAL);
- }
-
- return f.file->private_data;
-}
-
void bpf_map_inc(struct bpf_map *map)
{
atomic64_inc(&map->refcnt);
@@ -1448,31 +1640,23 @@ EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref);
struct bpf_map *bpf_map_get(u32 ufd)
{
- struct fd f = fdget(ufd);
- struct bpf_map *map;
-
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return map;
+ CLASS(fd, f)(ufd);
+ struct bpf_map *map = __bpf_map_get(f);
- bpf_map_inc(map);
- fdput(f);
+ if (!IS_ERR(map))
+ bpf_map_inc(map);
return map;
}
-EXPORT_SYMBOL(bpf_map_get);
+EXPORT_SYMBOL_NS(bpf_map_get, "BPF_INTERNAL");
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
- struct fd f = fdget(ufd);
- struct bpf_map *map;
-
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return map;
+ CLASS(fd, f)(ufd);
+ struct bpf_map *map = __bpf_map_get(f);
- bpf_map_inc_with_uref(map);
- fdput(f);
+ if (!IS_ERR(map))
+ bpf_map_inc_with_uref(map);
return map;
}
@@ -1495,15 +1679,13 @@ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref)
struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map)
{
- spin_lock_bh(&map_idr_lock);
- map = __bpf_map_inc_not_zero(map, false);
- spin_unlock_bh(&map_idr_lock);
-
- return map;
+ lockdep_assert(rcu_read_lock_held());
+ return __bpf_map_inc_not_zero(map, false);
}
EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero);
-int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+int __weak bpf_stackmap_extract(struct bpf_map *map, void *key, void *value,
+ bool delete)
{
return -ENOTSUPP;
}
@@ -1537,39 +1719,28 @@ static int map_lookup_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *uvalue = u64_to_user_ptr(attr->value);
- int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
u32 value_size;
- struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
- if (attr->flags & ~BPF_F_LOCK)
- return -EINVAL;
-
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
- if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
- err = -EPERM;
- goto err_put;
- }
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
+ return -EPERM;
- if ((attr->flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
- err = -EINVAL;
- goto err_put;
- }
+ err = bpf_map_check_op_flags(map, attr->flags, BPF_F_LOCK);
+ if (err)
+ return err;
key = __bpf_copy_key(ukey, map->key_size);
- if (IS_ERR(key)) {
- err = PTR_ERR(key);
- goto err_put;
- }
+ if (IS_ERR(key))
+ return PTR_ERR(key);
value_size = bpf_map_value_size(map);
@@ -1600,8 +1771,6 @@ free_value:
kvfree(value);
free_key:
kvfree(key);
-err_put:
- fdput(f);
return err;
}
@@ -1612,17 +1781,15 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
{
bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel);
- int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
u32 value_size;
- struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
@@ -1632,11 +1799,9 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
goto err_put;
}
- if ((attr->flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
- err = -EINVAL;
+ err = bpf_map_check_op_flags(map, attr->flags, ~0);
+ if (err)
goto err_put;
- }
key = ___bpf_copy_key(ukey, map->key_size);
if (IS_ERR(key)) {
@@ -1651,7 +1816,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
goto free_key;
}
- err = bpf_map_update_value(map, f.file, key, value, attr->flags);
+ err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags);
if (!err)
maybe_wait_bpf_programs(map);
@@ -1660,7 +1825,6 @@ free_key:
kvfree(key);
err_put:
bpf_map_write_active_dec(map);
- fdput(f);
return err;
}
@@ -1669,16 +1833,14 @@ err_put:
static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr)
{
bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel);
- int ufd = attr->map_fd;
struct bpf_map *map;
- struct fd f;
void *key;
int err;
if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
@@ -1715,7 +1877,6 @@ out:
kvfree(key);
err_put:
bpf_map_write_active_dec(map);
- fdput(f);
return err;
}
@@ -1726,30 +1887,24 @@ static int map_get_next_key(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *unext_key = u64_to_user_ptr(attr->next_key);
- int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *next_key;
- struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
- if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
- err = -EPERM;
- goto err_put;
- }
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ))
+ return -EPERM;
if (ukey) {
key = __bpf_copy_key(ukey, map->key_size);
- if (IS_ERR(key)) {
- err = PTR_ERR(key);
- goto err_put;
- }
+ if (IS_ERR(key))
+ return PTR_ERR(key);
} else {
key = NULL;
}
@@ -1781,8 +1936,6 @@ free_next_key:
kvfree(next_key);
free_key:
kvfree(key);
-err_put:
- fdput(f);
return err;
}
@@ -1852,13 +2005,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
void *key, *value;
int err = 0;
- if (attr->batch.elem_flags & ~BPF_F_LOCK)
- return -EINVAL;
-
- if ((attr->batch.elem_flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
- return -EINVAL;
- }
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
@@ -1903,8 +2052,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file,
return err;
}
-#define MAP_LOOKUP_RETRIES 3
-
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
@@ -1914,15 +2061,12 @@ int generic_map_lookup_batch(struct bpf_map *map,
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
void *buf, *buf_prevkey, *prev_key, *key, *value;
- int err, retry = MAP_LOOKUP_RETRIES;
u32 value_size, cp, max_count;
+ int err;
- if (attr->batch.elem_flags & ~BPF_F_LOCK)
- return -EINVAL;
-
- if ((attr->batch.elem_flags & BPF_F_LOCK) &&
- !btf_record_has_field(map->record, BPF_SPIN_LOCK))
- return -EINVAL;
+ err = bpf_map_check_op_flags(map, attr->batch.elem_flags, BPF_F_LOCK);
+ if (err)
+ return err;
value_size = bpf_map_value_size(map);
@@ -1961,14 +2105,8 @@ int generic_map_lookup_batch(struct bpf_map *map,
err = bpf_map_copy_value(map, key, value,
attr->batch.elem_flags);
- if (err == -ENOENT) {
- if (retry) {
- retry--;
- continue;
- }
- err = -EINTR;
- break;
- }
+ if (err == -ENOENT)
+ goto next_key;
if (err)
goto free_buf;
@@ -1983,12 +2121,12 @@ int generic_map_lookup_batch(struct bpf_map *map,
goto free_buf;
}
+ cp++;
+next_key:
if (!prev_key)
prev_key = buf_prevkey;
swap(prev_key, key);
- retry = MAP_LOOKUP_RETRIES;
- cp++;
cond_resched();
}
@@ -2011,11 +2149,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *uvalue = u64_to_user_ptr(attr->value);
- int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
u32 value_size;
- struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM))
@@ -2024,7 +2160,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
if (attr->flags & ~BPF_F_LOCK)
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
@@ -2068,7 +2204,8 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
} else if (map->map_type == BPF_MAP_TYPE_HASH ||
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) {
+ map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
if (!bpf_map_is_offloaded(map)) {
bpf_disable_instrumentation();
rcu_read_lock();
@@ -2094,7 +2231,6 @@ free_key:
kvfree(key);
err_put:
bpf_map_write_active_dec(map);
- fdput(f);
return err;
}
@@ -2102,27 +2238,22 @@ err_put:
static int map_freeze(const union bpf_attr *attr)
{
- int err = 0, ufd = attr->map_fd;
+ int err = 0;
struct bpf_map *map;
- struct fd f;
if (CHECK_ATTR(BPF_MAP_FREEZE))
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->map_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
- if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) {
- fdput(f);
+ if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record))
return -ENOTSUPP;
- }
- if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
- fdput(f);
+ if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE))
return -EPERM;
- }
mutex_lock(&map->freeze_mutex);
if (bpf_map_write_active(map)) {
@@ -2137,7 +2268,6 @@ static int map_freeze(const union bpf_attr *attr)
WRITE_ONCE(map->frozen, true);
err_put:
mutex_unlock(&map->freeze_mutex);
- fdput(f);
return err;
}
@@ -2191,7 +2321,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
return;
if (audit_enabled == AUDIT_OFF)
return;
- if (!in_irq() && !irqs_disabled())
+ if (!in_hardirq() && !irqs_disabled())
ctx = audit_context();
ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
if (unlikely(!ab))
@@ -2257,6 +2387,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
kvfree(prog->aux->jited_linfo);
kvfree(prog->aux->linfo);
kfree(prog->aux->kfunc_tab);
+ kfree(prog->aux->ctx_arg_info);
if (prog->aux->attach_btf)
btf_put(prog->aux->attach_btf);
@@ -2288,7 +2419,7 @@ static void __bpf_prog_put(struct bpf_prog *prog)
struct bpf_prog_aux *aux = prog->aux;
if (atomic64_dec_and_test(&aux->refcnt)) {
- if (in_irq() || irqs_disabled()) {
+ if (in_hardirq() || irqs_disabled()) {
INIT_WORK(&aux->work, bpf_prog_put_deferred);
schedule_work(&aux->work);
} else {
@@ -2322,6 +2453,9 @@ void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog)
struct bpf_prog_stats *stats;
unsigned int flags;
+ if (unlikely(!prog->stats))
+ return;
+
stats = this_cpu_ptr(prog->stats);
flags = u64_stats_update_begin_irqsave(&stats->syncp);
u64_stats_inc(&stats->misses);
@@ -2407,18 +2541,6 @@ int bpf_prog_new_fd(struct bpf_prog *prog)
O_RDWR | O_CLOEXEC);
}
-static struct bpf_prog *____bpf_prog_get(struct fd f)
-{
- if (!f.file)
- return ERR_PTR(-EBADF);
- if (f.file->f_op != &bpf_prog_fops) {
- fdput(f);
- return ERR_PTR(-EINVAL);
- }
-
- return f.file->private_data;
-}
-
void bpf_prog_add(struct bpf_prog *prog, int i)
{
atomic64_add(i, &prog->aux->refcnt);
@@ -2474,20 +2596,19 @@ bool bpf_prog_get_ok(struct bpf_prog *prog,
static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type,
bool attach_drv)
{
- struct fd f = fdget(ufd);
+ CLASS(fd, f)(ufd);
struct bpf_prog *prog;
- prog = ____bpf_prog_get(f);
- if (IS_ERR(prog))
- return prog;
- if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) {
- prog = ERR_PTR(-EINVAL);
- goto out;
- }
+ if (fd_empty(f))
+ return ERR_PTR(-EBADF);
+ if (fd_file(f)->f_op != &bpf_prog_fops)
+ return ERR_PTR(-EINVAL);
+
+ prog = fd_file(f)->private_data;
+ if (!bpf_prog_get_ok(prog, attach_type, attach_drv))
+ return ERR_PTR(-EINVAL);
bpf_prog_inc(prog);
-out:
- fdput(f);
return prog;
}
@@ -2690,8 +2811,61 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
}
}
+static int bpf_prog_verify_signature(struct bpf_prog *prog, union bpf_attr *attr,
+ bool is_kernel)
+{
+ bpfptr_t usig = make_bpfptr(attr->signature, is_kernel);
+ struct bpf_dynptr_kern sig_ptr, insns_ptr;
+ struct bpf_key *key = NULL;
+ void *sig;
+ int err = 0;
+
+ if (system_keyring_id_check(attr->keyring_id) == 0)
+ key = bpf_lookup_system_key(attr->keyring_id);
+ else
+ key = bpf_lookup_user_key(attr->keyring_id, 0);
+
+ if (!key)
+ return -EINVAL;
+
+ sig = kvmemdup_bpfptr(usig, attr->signature_size);
+ if (IS_ERR(sig)) {
+ bpf_key_put(key);
+ return -ENOMEM;
+ }
+
+ bpf_dynptr_init(&sig_ptr, sig, BPF_DYNPTR_TYPE_LOCAL, 0,
+ attr->signature_size);
+ bpf_dynptr_init(&insns_ptr, prog->insnsi, BPF_DYNPTR_TYPE_LOCAL, 0,
+ prog->len * sizeof(struct bpf_insn));
+
+ err = bpf_verify_pkcs7_signature((struct bpf_dynptr *)&insns_ptr,
+ (struct bpf_dynptr *)&sig_ptr, key);
+
+ bpf_key_put(key);
+ kvfree(sig);
+ return err;
+}
+
+static int bpf_prog_mark_insn_arrays_ready(struct bpf_prog *prog)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < prog->aux->used_map_cnt; i++) {
+ if (prog->aux->used_maps[i]->map_type != BPF_MAP_TYPE_INSN_ARRAY)
+ continue;
+
+ err = bpf_insn_array_ready(prog->aux->used_maps[i]);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd
+#define BPF_PROG_LOAD_LAST_FIELD keyring_id
static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
{
@@ -2855,6 +3029,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
/* eBPF programs must be GPL compatible to use GPL-ed functions */
prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0;
+ if (attr->signature) {
+ err = bpf_prog_verify_signature(prog, attr, uattr.is_kernel);
+ if (err)
+ goto free_prog;
+ }
+
prog->orig_prog = NULL;
prog->jited = 0;
@@ -2900,7 +3080,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (err < 0)
goto free_prog;
- err = security_bpf_prog_load(prog, attr, token);
+ err = security_bpf_prog_load(prog, attr, token, uattr.is_kernel);
if (err)
goto free_prog_sec;
@@ -2913,6 +3093,10 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
if (err < 0)
goto free_used_maps;
+ err = bpf_prog_mark_insn_arrays_ready(prog);
+ if (err < 0)
+ goto free_used_maps;
+
err = bpf_prog_alloc_id(prog);
if (err)
goto free_used_maps;
@@ -2995,15 +3179,33 @@ static int bpf_obj_get(const union bpf_attr *attr)
attr->file_flags);
}
-void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
- const struct bpf_link_ops *ops, struct bpf_prog *prog)
+/* bpf_link_init_sleepable() allows to specify whether BPF link itself has
+ * "sleepable" semantics, which normally would mean that BPF link's attach
+ * hook can dereference link or link's underlying program for some time after
+ * detachment due to RCU Tasks Trace-based lifetime protection scheme.
+ * BPF program itself can be non-sleepable, yet, because it's transitively
+ * reachable through BPF link, its freeing has to be delayed until after RCU
+ * Tasks Trace GP.
+ */
+void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type, bool sleepable)
{
WARN_ON(ops->dealloc && ops->dealloc_deferred);
atomic64_set(&link->refcnt, 1);
link->type = type;
+ link->sleepable = sleepable;
link->id = 0;
link->ops = ops;
link->prog = prog;
+ link->attach_type = attach_type;
+}
+
+void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
+ const struct bpf_link_ops *ops, struct bpf_prog *prog,
+ enum bpf_attach_type attach_type)
+{
+ bpf_link_init_sleepable(link, type, ops, prog, attach_type, false);
}
static void bpf_link_free_id(int id)
@@ -3038,12 +3240,24 @@ void bpf_link_inc(struct bpf_link *link)
atomic64_inc(&link->refcnt);
}
+static void bpf_link_dealloc(struct bpf_link *link)
+{
+ /* now that we know that bpf_link itself can't be reached, put underlying BPF program */
+ if (link->prog)
+ bpf_prog_put(link->prog);
+
+ /* free bpf_link and its containing memory */
+ if (link->ops->dealloc_deferred)
+ link->ops->dealloc_deferred(link);
+ else
+ link->ops->dealloc(link);
+}
+
static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
{
struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
- /* free bpf_link and its containing memory */
- link->ops->dealloc_deferred(link);
+ bpf_link_dealloc(link);
}
static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
@@ -3058,26 +3272,27 @@ static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
static void bpf_link_free(struct bpf_link *link)
{
const struct bpf_link_ops *ops = link->ops;
- bool sleepable = false;
bpf_link_free_id(link->id);
- if (link->prog) {
- sleepable = link->prog->sleepable;
- /* detach BPF program, clean up used resources */
+ /* detach BPF program, clean up used resources */
+ if (link->prog)
ops->release(link);
- bpf_prog_put(link->prog);
- }
if (ops->dealloc_deferred) {
- /* schedule BPF link deallocation; if underlying BPF program
- * is sleepable, we need to first wait for RCU tasks trace
- * sync, then go through "classic" RCU grace period
+ /* Schedule BPF link deallocation, which will only then
+ * trigger putting BPF program refcount.
+ * If underlying BPF program is sleepable or BPF link's target
+ * attach hookpoint is sleepable or otherwise requires RCU GPs
+ * to ensure link and its underlying BPF program is not
+ * reachable anymore, we need to first wait for RCU tasks
+ * trace sync, and then go through "classic" RCU grace period
*/
- if (sleepable)
+ if (link->sleepable || (link->prog && link->prog->sleepable))
call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
else
call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
- } else if (ops->dealloc)
- ops->dealloc(link);
+ } else if (ops->dealloc) {
+ bpf_link_dealloc(link);
+ }
}
static void bpf_link_put_deferred(struct work_struct *work)
@@ -3131,13 +3346,24 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_link *link = filp->private_data;
const struct bpf_prog *prog = link->prog;
+ enum bpf_link_type type = link->type;
char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
- seq_printf(m,
- "link_type:\t%s\n"
- "link_id:\t%u\n",
- bpf_link_type_strs[link->type],
- link->id);
+ if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) {
+ if (link->type == BPF_LINK_TYPE_KPROBE_MULTI)
+ seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ?
+ "kretprobe_multi" : "kprobe_multi");
+ else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI)
+ seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ?
+ "uretprobe_multi" : "uprobe_multi");
+ else
+ seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]);
+ } else {
+ WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type);
+ seq_printf(m, "link_type:\t<%u>\n", type);
+ }
+ seq_printf(m, "link_id:\t%u\n", link->id);
+
if (prog) {
bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
@@ -3256,23 +3482,19 @@ int bpf_link_new_fd(struct bpf_link *link)
struct bpf_link *bpf_link_get_from_fd(u32 ufd)
{
- struct fd f = fdget(ufd);
+ CLASS(fd, f)(ufd);
struct bpf_link *link;
- if (!f.file)
+ if (fd_empty(f))
return ERR_PTR(-EBADF);
- if (f.file->f_op != &bpf_link_fops && f.file->f_op != &bpf_link_fops_poll) {
- fdput(f);
+ if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll)
return ERR_PTR(-EINVAL);
- }
- link = f.file->private_data;
+ link = fd_file(f)->private_data;
bpf_link_inc(link);
- fdput(f);
-
return link;
}
-EXPORT_SYMBOL(bpf_link_get_from_fd);
+EXPORT_SYMBOL_NS(bpf_link_get_from_fd, "BPF_INTERNAL");
static void bpf_tracing_link_release(struct bpf_link *link)
{
@@ -3280,7 +3502,8 @@ static void bpf_tracing_link_release(struct bpf_link *link)
container_of(link, struct bpf_tracing_link, link.link);
WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link,
- tr_link->trampoline));
+ tr_link->trampoline,
+ tr_link->tgt_prog));
bpf_trampoline_put(tr_link->trampoline);
@@ -3309,10 +3532,12 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
seq_printf(seq,
"attach_type:\t%d\n"
"target_obj_id:\t%u\n"
- "target_btf_id:\t%u\n",
- tr_link->attach_type,
+ "target_btf_id:\t%u\n"
+ "cookie:\t%llu\n",
+ link->attach_type,
target_obj_id,
- target_btf_id);
+ target_btf_id,
+ tr_link->link.cookie);
}
static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
@@ -3321,7 +3546,8 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
struct bpf_tracing_link *tr_link =
container_of(link, struct bpf_tracing_link, link.link);
- info->tracing.attach_type = tr_link->attach_type;
+ info->tracing.attach_type = link->attach_type;
+ info->tracing.cookie = tr_link->link.cookie;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
&info->tracing.target_obj_id,
&info->tracing.target_btf_id);
@@ -3339,7 +3565,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
static int bpf_tracing_prog_attach(struct bpf_prog *prog,
int tgt_prog_fd,
u32 btf_id,
- u64 bpf_cookie)
+ u64 bpf_cookie,
+ enum bpf_attach_type attach_type)
{
struct bpf_link_primer link_primer;
struct bpf_prog *tgt_prog = NULL;
@@ -3407,8 +3634,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
goto out_put_prog;
}
bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
- &bpf_tracing_link_lops, prog);
- link->attach_type = prog->expected_attach_type;
+ &bpf_tracing_link_lops, prog, attach_type);
+
link->link.cookie = bpf_cookie;
mutex_lock(&prog->aux->dst_mutex);
@@ -3420,7 +3647,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
* in prog->aux
*
* - if prog->aux->dst_trampoline is NULL, the program has already been
- * attached to a target and its initial target was cleared (below)
+ * attached to a target and its initial target was cleared (below)
*
* - if tgt_prog != NULL, the caller specified tgt_prog_fd +
* target_btf_id using the link_create API.
@@ -3495,7 +3722,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
if (err)
goto out_unlock;
- err = bpf_trampoline_link_prog(&link->link, tr);
+ err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog);
if (err) {
bpf_link_cleanup(&link_primer);
link = NULL;
@@ -3557,8 +3784,10 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
container_of(link, struct bpf_raw_tp_link, link);
seq_printf(seq,
- "tp_name:\t%s\n",
- raw_tp_link->btp->tp->name);
+ "tp_name:\t%s\n"
+ "cookie:\t%llu\n",
+ raw_tp_link->btp->tp->name,
+ raw_tp_link->cookie);
}
static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
@@ -3594,6 +3823,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
return -EINVAL;
info->raw_tracepoint.tp_name_len = tp_len + 1;
+ info->raw_tracepoint.cookie = raw_tp_link->cookie;
if (!ubuf)
return 0;
@@ -3631,15 +3861,16 @@ static void bpf_perf_link_dealloc(struct bpf_link *link)
}
static int bpf_perf_link_fill_common(const struct perf_event *event,
- char __user *uname, u32 ulen,
+ char __user *uname, u32 *ulenp,
u64 *probe_offset, u64 *probe_addr,
u32 *fd_type, unsigned long *missed)
{
const char *buf;
- u32 prog_id;
+ u32 prog_id, ulen;
size_t len;
int err;
+ ulen = *ulenp;
if (!ulen ^ !uname)
return -EINVAL;
@@ -3647,10 +3878,17 @@ static int bpf_perf_link_fill_common(const struct perf_event *event,
probe_offset, probe_addr, missed);
if (err)
return err;
+
+ if (buf) {
+ len = strlen(buf);
+ *ulenp = len + 1;
+ } else {
+ *ulenp = 1;
+ }
if (!uname)
return 0;
+
if (buf) {
- len = strlen(buf);
err = bpf_copy_to_user(uname, buf, ulen, len);
if (err)
return err;
@@ -3675,7 +3913,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
uname = u64_to_user_ptr(info->perf_event.kprobe.func_name);
ulen = info->perf_event.kprobe.name_len;
- err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+ err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr,
&type, &missed);
if (err)
return err;
@@ -3683,7 +3921,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
info->perf_event.type = BPF_PERF_EVENT_KRETPROBE;
else
info->perf_event.type = BPF_PERF_EVENT_KPROBE;
-
+ info->perf_event.kprobe.name_len = ulen;
info->perf_event.kprobe.offset = offset;
info->perf_event.kprobe.missed = missed;
if (!kallsyms_show_value(current_cred()))
@@ -3692,20 +3930,46 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
info->perf_event.kprobe.cookie = event->bpf_cookie;
return 0;
}
+
+static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, addr;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &addr, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "missed:\t%lu\n"
+ "addr:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, missed, addr,
+ type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe",
+ event->bpf_cookie);
+}
#endif
#ifdef CONFIG_UPROBE_EVENTS
static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
struct bpf_link_info *info)
{
+ u64 ref_ctr_offset, offset;
char __user *uname;
- u64 addr, offset;
u32 ulen, type;
int err;
uname = u64_to_user_ptr(info->perf_event.uprobe.file_name);
ulen = info->perf_event.uprobe.name_len;
- err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr,
+ err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &ref_ctr_offset,
&type, NULL);
if (err)
return err;
@@ -3714,10 +3978,37 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
info->perf_event.type = BPF_PERF_EVENT_URETPROBE;
else
info->perf_event.type = BPF_PERF_EVENT_UPROBE;
+ info->perf_event.uprobe.name_len = ulen;
info->perf_event.uprobe.offset = offset;
info->perf_event.uprobe.cookie = event->bpf_cookie;
+ info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset;
return 0;
}
+
+static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, ref_ctr_offset;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &ref_ctr_offset, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "ref_ctr_offset:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, ref_ctr_offset,
+ type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe",
+ event->bpf_cookie);
+}
#endif
static int bpf_perf_link_fill_probe(const struct perf_event *event,
@@ -3739,12 +4030,18 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event,
{
char __user *uname;
u32 ulen;
+ int err;
uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name);
ulen = info->perf_event.tracepoint.name_len;
+ err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL);
+ if (err)
+ return err;
+
info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT;
+ info->perf_event.tracepoint.name_len = ulen;
info->perf_event.tracepoint.cookie = event->bpf_cookie;
- return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL);
+ return 0;
}
static int bpf_perf_link_fill_perf_event(const struct perf_event *event,
@@ -3780,10 +4077,79 @@ static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
}
}
+static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ seq_printf(seq,
+ "type:\t%u\n"
+ "config:\t%llu\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ event->attr.type, event->attr.config,
+ "event", event->bpf_cookie);
+}
+
+static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ int err;
+ const char *name;
+ u32 prog_id;
+
+ err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL,
+ NULL, NULL);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "tp_name:\t%s\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, "tracepoint", event->bpf_cookie);
+}
+
+static void bpf_probe_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+ return bpf_perf_link_fdinfo_kprobe(event, seq);
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+ return bpf_perf_link_fdinfo_uprobe(event, seq);
+#endif
+}
+
+static void bpf_perf_link_show_fdinfo(const struct bpf_link *link,
+ struct seq_file *seq)
+{
+ struct bpf_perf_link *perf_link;
+ const struct perf_event *event;
+
+ perf_link = container_of(link, struct bpf_perf_link, link);
+ event = perf_get_event(perf_link->perf_file);
+ if (IS_ERR(event))
+ return;
+
+ switch (event->prog->type) {
+ case BPF_PROG_TYPE_PERF_EVENT:
+ return bpf_perf_event_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_TRACEPOINT:
+ return bpf_tracepoint_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_KPROBE:
+ return bpf_probe_link_show_fdinfo(event, seq);
+ default:
+ return;
+ }
+}
+
static const struct bpf_link_ops bpf_perf_link_lops = {
.release = bpf_perf_link_release,
.dealloc = bpf_perf_link_dealloc,
.fill_link_info = bpf_perf_link_fill_link_info,
+ .show_fdinfo = bpf_perf_link_show_fdinfo,
};
static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -3806,7 +4172,8 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
err = -ENOMEM;
goto out_put_file;
}
- bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog);
+ bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog,
+ attr->link_create.attach_type);
link->perf_file = perf_file;
err = bpf_link_prime(&link->link, &link_primer);
@@ -3838,7 +4205,8 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
#endif /* CONFIG_PERF_EVENTS */
static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
- const char __user *user_tp_name, u64 cookie)
+ const char __user *user_tp_name, u64 cookie,
+ enum bpf_attach_type attach_type)
{
struct bpf_link_primer link_primer;
struct bpf_raw_tp_link *link;
@@ -3861,7 +4229,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
tp_name = prog->aux->attach_func_name;
break;
}
- return bpf_tracing_prog_attach(prog, 0, 0, 0);
+ return bpf_tracing_prog_attach(prog, 0, 0, 0, attach_type);
case BPF_PROG_TYPE_RAW_TRACEPOINT:
case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0)
@@ -3882,8 +4250,9 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
err = -ENOMEM;
goto out_put_btp;
}
- bpf_link_init(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
- &bpf_raw_tp_link_lops, prog);
+ bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
+ &bpf_raw_tp_link_lops, prog, attach_type,
+ tracepoint_is_faultable(btp->tp));
link->btp = btp;
link->cookie = cookie;
@@ -3924,7 +4293,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
tp_name = u64_to_user_ptr(attr->raw_tracepoint.name);
cookie = attr->raw_tracepoint.cookie;
- fd = bpf_raw_tp_link_attach(prog, tp_name, cookie);
+ fd = bpf_raw_tp_link_attach(prog, tp_name, cookie, prog->expected_attach_type);
if (fd < 0)
bpf_prog_put(prog);
return fd;
@@ -4049,10 +4418,14 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI &&
attach_type != BPF_TRACE_UPROBE_MULTI)
return -EINVAL;
+ if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION &&
+ attach_type != BPF_TRACE_UPROBE_SESSION)
+ return -EINVAL;
if (attach_type != BPF_PERF_EVENT &&
attach_type != BPF_TRACE_KPROBE_MULTI &&
attach_type != BPF_TRACE_KPROBE_SESSION &&
- attach_type != BPF_TRACE_UPROBE_MULTI)
+ attach_type != BPF_TRACE_UPROBE_MULTI &&
+ attach_type != BPF_TRACE_UPROBE_SESSION)
return -EINVAL;
return 0;
case BPF_PROG_TYPE_SCHED_CLS:
@@ -4070,12 +4443,32 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
}
}
+static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype,
+ bool check_atype)
+{
+ switch (ptype) {
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ return true;
+ case BPF_PROG_TYPE_LSM:
+ return check_atype ? atype == BPF_LSM_CGROUP : true;
+ default:
+ return false;
+ }
+}
+
#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
#define BPF_F_ATTACH_MASK_BASE \
(BPF_F_ALLOW_OVERRIDE | \
BPF_F_ALLOW_MULTI | \
- BPF_F_REPLACE)
+ BPF_F_REPLACE | \
+ BPF_F_PREORDER)
#define BPF_F_ATTACH_MASK_MPROG \
(BPF_F_REPLACE | \
@@ -4099,6 +4492,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (bpf_mprog_supported(ptype)) {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
return -EINVAL;
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG))
+ return -EINVAL;
} else {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
return -EINVAL;
@@ -4116,6 +4512,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
+ if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) {
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+ goto out;
+ }
+
switch (ptype) {
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
@@ -4127,20 +4528,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_PROG_TYPE_FLOW_DISSECTOR:
ret = netns_bpf_prog_attach(attr, prog);
break;
- case BPF_PROG_TYPE_CGROUP_DEVICE:
- case BPF_PROG_TYPE_CGROUP_SKB:
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- case BPF_PROG_TYPE_CGROUP_SYSCTL:
- case BPF_PROG_TYPE_SOCK_OPS:
- case BPF_PROG_TYPE_LSM:
- if (ptype == BPF_PROG_TYPE_LSM &&
- prog->expected_attach_type != BPF_LSM_CGROUP)
- ret = -EINVAL;
- else
- ret = cgroup_bpf_prog_attach(attr, ptype, prog);
- break;
case BPF_PROG_TYPE_SCHED_CLS:
if (attr->attach_type == BPF_TCX_INGRESS ||
attr->attach_type == BPF_TCX_EGRESS)
@@ -4151,7 +4538,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
default:
ret = -EINVAL;
}
-
+out:
if (ret)
bpf_prog_put(prog);
return ret;
@@ -4179,6 +4566,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
}
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags || attr->relative_fd)
+ return -EINVAL;
} else if (attr->attach_flags ||
attr->relative_fd ||
attr->expected_revision) {
@@ -4639,6 +5029,8 @@ static int bpf_prog_get_info_by_fd(struct file *file,
info.recursion_misses = stats.misses;
info.verified_insns = prog->aux->verified_insns;
+ if (prog->aux->btf)
+ info.btf_id = btf_obj_id(prog->aux->btf);
if (!bpf_capable()) {
info.jited_prog_len = 0;
@@ -4657,19 +5049,19 @@ static int bpf_prog_get_info_by_fd(struct file *file,
struct bpf_insn *insns_sanitized;
bool fault;
- if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
+ if (!prog->blinded || bpf_dump_raw_ok(file->f_cred)) {
+ insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
+ if (!insns_sanitized)
+ return -ENOMEM;
+ uinsns = u64_to_user_ptr(info.xlated_prog_insns);
+ ulen = min_t(u32, info.xlated_prog_len, ulen);
+ fault = copy_to_user(uinsns, insns_sanitized, ulen);
+ kfree(insns_sanitized);
+ if (fault)
+ return -EFAULT;
+ } else {
info.xlated_prog_insns = 0;
- goto done;
}
- insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
- if (!insns_sanitized)
- return -ENOMEM;
- uinsns = u64_to_user_ptr(info.xlated_prog_insns);
- ulen = min_t(u32, info.xlated_prog_len, ulen);
- fault = copy_to_user(uinsns, insns_sanitized, ulen);
- kfree(insns_sanitized);
- if (fault)
- return -EFAULT;
}
if (bpf_prog_is_offloaded(prog->aux)) {
@@ -4785,8 +5177,6 @@ static int bpf_prog_get_info_by_fd(struct file *file,
}
}
- if (prog->aux->btf)
- info.btf_id = btf_obj_id(prog->aux->btf);
info.attach_btf_id = prog->aux->attach_btf_id;
if (attach_btf)
info.attach_btf_obj_id = btf_obj_id(attach_btf);
@@ -4884,6 +5274,9 @@ static int bpf_map_get_info_by_fd(struct file *file,
info_len = min_t(u32, sizeof(info), info_len);
memset(&info, 0, sizeof(info));
+ if (copy_from_user(&info, uinfo, info_len))
+ return -EFAULT;
+
info.type = map->map_type;
info.id = map->id;
info.key_size = map->key_size;
@@ -4908,6 +5301,25 @@ static int bpf_map_get_info_by_fd(struct file *file,
return err;
}
+ if (info.hash) {
+ char __user *uhash = u64_to_user_ptr(info.hash);
+
+ if (!map->ops->map_get_hash)
+ return -EINVAL;
+
+ if (info.hash_size != SHA256_DIGEST_SIZE)
+ return -EINVAL;
+
+ err = map->ops->map_get_hash(map, SHA256_DIGEST_SIZE, map->sha);
+ if (err != 0)
+ return err;
+
+ if (copy_to_user(uhash, map->sha, SHA256_DIGEST_SIZE) != 0)
+ return -EFAULT;
+ } else if (info.hash_size) {
+ return -EINVAL;
+ }
+
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
return -EFAULT;
@@ -4969,38 +5381,48 @@ static int bpf_link_get_info_by_fd(struct file *file,
}
+static int token_get_info_by_fd(struct file *file,
+ struct bpf_token *token,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+ u32 info_len = attr->info.info_len;
+ int err;
+
+ err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len);
+ if (err)
+ return err;
+ return bpf_token_get_info_by_fd(token, attr, uattr);
+}
+
#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- int ufd = attr->info.bpf_fd;
- struct fd f;
- int err;
-
if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD))
return -EINVAL;
- f = fdget(ufd);
- if (!f.file)
+ CLASS(fd, f)(attr->info.bpf_fd);
+ if (fd_empty(f))
return -EBADFD;
- if (f.file->f_op == &bpf_prog_fops)
- err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
+ if (fd_file(f)->f_op == &bpf_prog_fops)
+ return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr,
uattr);
- else if (f.file->f_op == &bpf_map_fops)
- err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
+ else if (fd_file(f)->f_op == &bpf_map_fops)
+ return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr,
uattr);
- else if (f.file->f_op == &btf_fops)
- err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
- else if (f.file->f_op == &bpf_link_fops || f.file->f_op == &bpf_link_fops_poll)
- err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
+ else if (fd_file(f)->f_op == &btf_fops)
+ return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr);
+ else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll)
+ return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data,
attr, uattr);
- else
- err = -EINVAL;
-
- fdput(f);
- return err;
+ else if (fd_file(f)->f_op == &bpf_token_fops)
+ return token_get_info_by_fd(fd_file(f), fd_file(f)->private_data,
+ attr, uattr);
+ return -EINVAL;
}
#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd
@@ -5035,15 +5457,34 @@ static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_
return btf_new_fd(attr, uattr, uattr_size);
}
-#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id
+#define BPF_BTF_GET_FD_BY_ID_LAST_FIELD fd_by_id_token_fd
static int bpf_btf_get_fd_by_id(const union bpf_attr *attr)
{
+ struct bpf_token *token = NULL;
+
if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID))
return -EINVAL;
- if (!capable(CAP_SYS_ADMIN))
+ if (attr->open_flags & ~BPF_F_TOKEN_FD)
+ return -EINVAL;
+
+ if (attr->open_flags & BPF_F_TOKEN_FD) {
+ token = bpf_token_get_from_fd(attr->fd_by_id_token_fd);
+ if (IS_ERR(token))
+ return PTR_ERR(token);
+ if (!bpf_token_allow_cmd(token, BPF_BTF_GET_FD_BY_ID)) {
+ bpf_token_put(token);
+ token = NULL;
+ }
+ }
+
+ if (!bpf_token_capable(token, CAP_SYS_ADMIN)) {
+ bpf_token_put(token);
return -EPERM;
+ }
+
+ bpf_token_put(token);
return btf_get_fd_by_id(attr->btf_id);
}
@@ -5068,21 +5509,10 @@ static int bpf_task_fd_query_copy(const union bpf_attr *attr,
if (put_user(zero, ubuf))
return -EFAULT;
- } else if (input_len >= len + 1) {
- /* ubuf can hold the string with NULL terminator */
- if (copy_to_user(ubuf, buf, len + 1))
- return -EFAULT;
} else {
- /* ubuf cannot hold the string with NULL terminator,
- * do a partial copy with NULL terminator.
- */
- char zero = '\0';
-
- err = -ENOSPC;
- if (copy_to_user(ubuf, buf, input_len - 1))
- return -EFAULT;
- if (put_user(zero, ubuf + input_len - 1))
- return -EFAULT;
+ err = bpf_copy_to_user(ubuf, buf, input_len, len);
+ if (err == -EFAULT)
+ return err;
}
}
@@ -5188,14 +5618,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
struct bpf_map *map;
- int err, ufd;
- struct fd f;
+ int err;
if (CHECK_ATTR(BPF_MAP_BATCH))
return -EINVAL;
- ufd = attr->batch.map_fd;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->batch.map_fd);
+
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
@@ -5215,7 +5644,7 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH)
BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr);
else if (cmd == BPF_MAP_UPDATE_BATCH)
- BPF_DO_BATCH(map->ops->map_update_batch, map, f.file, attr, uattr);
+ BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr);
else
BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr);
err_put:
@@ -5223,7 +5652,6 @@ err_put:
maybe_wait_bpf_programs(map);
bpf_map_write_active_dec(map);
}
- fdput(f);
return err;
}
@@ -5262,7 +5690,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
ret = bpf_tracing_prog_attach(prog,
attr->link_create.target_fd,
attr->link_create.target_btf_id,
- attr->link_create.tracing.cookie);
+ attr->link_create.tracing.cookie,
+ attr->link_create.attach_type);
break;
case BPF_PROG_TYPE_LSM:
case BPF_PROG_TYPE_TRACING:
@@ -5271,7 +5700,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
goto out;
}
if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
- ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie);
+ ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie,
+ attr->link_create.attach_type);
else if (prog->expected_attach_type == BPF_TRACE_ITER)
ret = bpf_iter_link_attach(attr, uattr, prog);
else if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -5280,7 +5710,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
ret = bpf_tracing_prog_attach(prog,
attr->link_create.target_fd,
attr->link_create.target_btf_id,
- attr->link_create.tracing.cookie);
+ attr->link_create.tracing.cookie,
+ attr->link_create.attach_type);
break;
case BPF_PROG_TYPE_FLOW_DISSECTOR:
case BPF_PROG_TYPE_SK_LOOKUP:
@@ -5315,7 +5746,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI ||
attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION)
ret = bpf_kprobe_multi_link_attach(attr, prog);
- else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI)
+ else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI ||
+ attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION)
ret = bpf_uprobe_multi_link_attach(attr, prog);
break;
default:
@@ -5668,7 +6100,29 @@ static int token_create(union bpf_attr *attr)
return bpf_token_create(attr);
}
-static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
+#define BPF_PROG_STREAM_READ_BY_FD_LAST_FIELD prog_stream_read.prog_fd
+
+static int prog_stream_read(union bpf_attr *attr)
+{
+ char __user *buf = u64_to_user_ptr(attr->prog_stream_read.stream_buf);
+ u32 len = attr->prog_stream_read.stream_buf_len;
+ struct bpf_prog *prog;
+ int ret;
+
+ if (CHECK_ATTR(BPF_PROG_STREAM_READ_BY_FD))
+ return -EINVAL;
+
+ prog = bpf_prog_get(attr->prog_stream_read.prog_fd);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ ret = bpf_prog_stream_read(prog, attr->prog_stream_read.stream_id, buf, len);
+ bpf_prog_put(prog);
+
+ return ret;
+}
+
+static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size)
{
union bpf_attr attr;
int err;
@@ -5683,13 +6137,13 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
if (copy_from_bpfptr(&attr, uattr, size) != 0)
return -EFAULT;
- err = security_bpf(cmd, &attr, size);
+ err = security_bpf(cmd, &attr, size, uattr.is_kernel);
if (err < 0)
return err;
switch (cmd) {
case BPF_MAP_CREATE:
- err = map_create(&attr);
+ err = map_create(&attr, uattr);
break;
case BPF_MAP_LOOKUP_ELEM:
err = map_lookup_elem(&attr);
@@ -5804,6 +6258,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size)
case BPF_TOKEN_CREATE:
err = token_create(&attr);
break;
+ case BPF_PROG_STREAM_READ_BY_FD:
+ err = prog_stream_read(&attr);
+ break;
default:
err = -EINVAL;
break;
@@ -5896,7 +6353,7 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
return ____bpf_sys_bpf(cmd, attr, size);
}
}
-EXPORT_SYMBOL(kern_sys_bpf);
+EXPORT_SYMBOL_NS(kern_sys_bpf, "BPF_INTERNAL");
static const struct bpf_func_proto bpf_sys_bpf_proto = {
.func = bpf_sys_bpf,
@@ -5932,6 +6389,7 @@ static const struct bpf_func_proto bpf_sys_close_proto = {
BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res)
{
+ *res = 0;
if (flags)
return -EINVAL;
@@ -5952,7 +6410,8 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = {
.arg1_type = ARG_PTR_TO_MEM,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
.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),
};
static const struct bpf_func_proto *
@@ -5983,7 +6442,7 @@ const struct bpf_prog_ops bpf_syscall_prog_ops = {
};
#ifdef CONFIG_SYSCTL
-static int bpf_stats_handler(struct ctl_table *table, int write,
+static int bpf_stats_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct static_key *key = (struct static_key *)table->data;
@@ -6018,7 +6477,7 @@ void __weak unpriv_ebpf_notify(int new_state)
{
}
-static int bpf_unpriv_handler(struct ctl_table *table, int write,
+static int bpf_unpriv_handler(const struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int ret, unpriv_enable = *(int *)table->data;
@@ -6042,7 +6501,7 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write,
return ret;
}
-static struct ctl_table bpf_syscall_table[] = {
+static const struct ctl_table bpf_syscall_table[] = {
{
.procname = "unprivileged_bpf_disabled",
.data = &sysctl_unprivileged_bpf_disabled,
generated by cgit (git 2.34.1) at 2025-12-22 05:27:30 +0000