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.c145
1 files changed, 109 insertions, 36 deletions
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e50c0bfdb7d..1033ee8c0caf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
return map;
}
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+ atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+ atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+ return atomic64_read(&map->writecnt) != 0;
+}
+
static u32 bpf_map_value_size(const struct bpf_map *map)
{
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -199,7 +214,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key,
err = bpf_fd_reuseport_array_update_elem(map, key, value,
flags);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
+ map->map_type == BPF_MAP_TYPE_STACK ||
+ map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
err = map->ops->map_push_elem(map, value, flags);
} else {
rcu_read_lock();
@@ -238,7 +254,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value,
} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
- map->map_type == BPF_MAP_TYPE_STACK) {
+ map->map_type == BPF_MAP_TYPE_STACK ||
+ map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
err = map->ops->map_peek_elem(map, value);
} else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
/* struct_ops map requires directly updating "value" */
@@ -348,6 +365,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
map->max_entries = attr->max_entries;
map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
map->numa_node = bpf_map_attr_numa_node(attr);
+ map->map_extra = attr->map_extra;
}
static int bpf_map_alloc_id(struct bpf_map *map)
@@ -543,8 +561,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
- type = array->aux->type;
- jited = array->aux->jited;
+ spin_lock(&array->aux->owner.lock);
+ type = array->aux->owner.type;
+ jited = array->aux->owner.jited;
+ spin_unlock(&array->aux->owner.lock);
}
seq_printf(m,
@@ -553,6 +573,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
"value_size:\t%u\n"
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
+ "map_extra:\t%#llx\n"
"memlock:\t%lu\n"
"map_id:\t%u\n"
"frozen:\t%u\n",
@@ -561,6 +582,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
map->value_size,
map->max_entries,
map->map_flags,
+ (unsigned long long)map->map_extra,
bpf_map_memory_footprint(map),
map->id,
READ_ONCE(map->frozen));
@@ -594,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt++;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_inc(map);
}
/* called for all unmapped memory region (including initial) */
@@ -606,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_MAYWRITE) {
- mutex_lock(&map->freeze_mutex);
- map->writecnt--;
- mutex_unlock(&map->freeze_mutex);
- }
+ if (vma->vm_flags & VM_MAYWRITE)
+ bpf_map_write_active_dec(map);
}
static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -661,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
goto out;
if (vma->vm_flags & VM_MAYWRITE)
- map->writecnt++;
+ bpf_map_write_active_inc(map);
out:
mutex_unlock(&map->freeze_mutex);
return err;
@@ -810,7 +826,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
return ret;
}
-#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id
+#define BPF_MAP_CREATE_LAST_FIELD map_extra
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
@@ -831,6 +847,10 @@ static int map_create(union bpf_attr *attr)
return -EINVAL;
}
+ if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
+ attr->map_extra != 0)
+ return -EINVAL;
+
f_flags = bpf_get_file_flag(attr->map_flags);
if (f_flags < 0)
return f_flags;
@@ -1080,6 +1100,14 @@ static int map_lookup_elem(union bpf_attr *attr)
if (!value)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) {
+ if (copy_from_user(value, uvalue, value_size))
+ err = -EFAULT;
+ else
+ err = bpf_map_copy_value(map, key, value, attr->flags);
+ goto free_value;
+ }
+
err = bpf_map_copy_value(map, key, value, attr->flags);
if (err)
goto free_value;
@@ -1120,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1155,6 +1184,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1177,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
@@ -1207,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr)
out:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1337,12 +1369,11 @@ int generic_map_update_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);
u32 value_size, cp, max_count;
- int ufd = attr->map_fd;
+ int ufd = attr->batch.map_fd;
void *key, *value;
struct fd f;
int err = 0;
- f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -1367,6 +1398,7 @@ int generic_map_update_batch(struct bpf_map *map,
return -ENOMEM;
}
+ f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
@@ -1386,6 +1418,7 @@ int generic_map_update_batch(struct bpf_map *map,
kvfree(value);
kvfree(key);
+ fdput(f);
return err;
}
@@ -1513,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
+ bpf_map_write_active_inc(map);
if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
@@ -1577,6 +1611,7 @@ free_value:
free_key:
kvfree(key);
err_put:
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -1604,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr)
}
mutex_lock(&map->freeze_mutex);
-
- if (map->writecnt) {
+ if (bpf_map_write_active(map)) {
err = -EBUSY;
goto err_put;
}
@@ -1804,8 +1838,14 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
return 0;
}
+struct bpf_prog_kstats {
+ u64 nsecs;
+ u64 cnt;
+ u64 misses;
+};
+
static void bpf_prog_get_stats(const struct bpf_prog *prog,
- struct bpf_prog_stats *stats)
+ struct bpf_prog_kstats *stats)
{
u64 nsecs = 0, cnt = 0, misses = 0;
int cpu;
@@ -1818,9 +1858,9 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog,
st = per_cpu_ptr(prog->stats, cpu);
do {
start = u64_stats_fetch_begin_irq(&st->syncp);
- tnsecs = st->nsecs;
- tcnt = st->cnt;
- tmisses = st->misses;
+ tnsecs = u64_stats_read(&st->nsecs);
+ tcnt = u64_stats_read(&st->cnt);
+ tmisses = u64_stats_read(&st->misses);
} while (u64_stats_fetch_retry_irq(&st->syncp, start));
nsecs += tnsecs;
cnt += tcnt;
@@ -1836,7 +1876,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
- struct bpf_prog_stats stats;
+ struct bpf_prog_kstats stats;
bpf_prog_get_stats(prog, &stats);
bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
@@ -1848,7 +1888,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
"prog_id:\t%u\n"
"run_time_ns:\t%llu\n"
"run_cnt:\t%llu\n"
- "recursion_misses:\t%llu\n",
+ "recursion_misses:\t%llu\n"
+ "verified_insns:\t%u\n",
prog->type,
prog->jited,
prog_tag,
@@ -1856,7 +1897,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
prog->aux->id,
stats.nsecs,
stats.cnt,
- stats.misses);
+ stats.misses,
+ prog->aux->verified_insns);
}
#endif
@@ -3575,7 +3617,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
struct bpf_prog_info info;
u32 info_len = attr->info.info_len;
- struct bpf_prog_stats stats;
+ struct bpf_prog_kstats stats;
char __user *uinsns;
u32 ulen;
int err;
@@ -3625,6 +3667,8 @@ static int bpf_prog_get_info_by_fd(struct file *file,
info.run_cnt = stats.cnt;
info.recursion_misses = stats.misses;
+ info.verified_insns = prog->aux->verified_insns;
+
if (!bpf_capable()) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
@@ -3871,6 +3915,7 @@ static int bpf_map_get_info_by_fd(struct file *file,
info.value_size = map->value_size;
info.max_entries = map->max_entries;
info.map_flags = map->map_flags;
+ info.map_extra = map->map_extra;
memcpy(info.name, map->name, sizeof(map->name));
if (map->btf) {
@@ -4140,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
union bpf_attr __user *uattr,
int cmd)
{
+ bool has_read = cmd == BPF_MAP_LOOKUP_BATCH ||
+ 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;
@@ -4152,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
-
- if ((cmd == BPF_MAP_LOOKUP_BATCH ||
- cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+ if (has_write)
+ bpf_map_write_active_inc(map);
+ if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
err = -EPERM;
goto err_put;
}
-
- if (cmd != BPF_MAP_LOOKUP_BATCH &&
- !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+ if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
err = -EPERM;
goto err_put;
}
@@ -4174,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
BPF_DO_BATCH(map->ops->map_update_batch);
else
BPF_DO_BATCH(map->ops->map_delete_batch);
-
err_put:
+ if (has_write)
+ bpf_map_write_active_dec(map);
fdput(f);
return err;
}
@@ -4753,6 +4799,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = {
.arg1_type = ARG_ANYTHING,
};
+BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res)
+{
+ if (flags)
+ return -EINVAL;
+
+ if (name_sz <= 1 || name[name_sz - 1])
+ return -EINVAL;
+
+ if (!bpf_dump_raw_ok(current_cred()))
+ return -EPERM;
+
+ *res = kallsyms_lookup_name(name);
+ return *res ? 0 : -ENOENT;
+}
+
+const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = {
+ .func = bpf_kallsyms_lookup_name,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_PTR_TO_LONG,
+};
+
static const struct bpf_func_proto *
syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
@@ -4763,6 +4834,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_btf_find_by_name_kind_proto;
case BPF_FUNC_sys_close:
return &bpf_sys_close_proto;
+ case BPF_FUNC_kallsyms_lookup_name:
+ return &bpf_kallsyms_lookup_name_proto;
default:
return tracing_prog_func_proto(func_id, prog);
}