mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Alexei Starovoitov](/assets/img/avatar_default.png)
Introduce BPF_F_LOCK flag for map_lookup and map_update syscall commands and for map_update() helper function. In all these cases take a lock of existing element (which was provided in BTF description) before copying (in or out) the rest of map value. Implementation details that are part of uapi: Array: The array map takes the element lock for lookup/update. Hash: hash map also takes the lock for lookup/update and tries to avoid the bucket lock. If old element exists it takes the element lock and updates the element in place. If element doesn't exist it allocates new one and inserts into hash table while holding the bucket lock. In rare case the hashmap has to take both the bucket lock and the element lock to update old value in place. Cgroup local storage: It is similar to array. update in place and lookup are done with lock taken. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
366 lines
8.7 KiB
C
366 lines
8.7 KiB
C
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*/
|
|
#include <linux/bpf.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/random.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/uidgid.h>
|
|
#include <linux/filter.h>
|
|
|
|
/* If kernel subsystem is allowing eBPF programs to call this function,
|
|
* inside its own verifier_ops->get_func_proto() callback it should return
|
|
* bpf_map_lookup_elem_proto, so that verifier can properly check the arguments
|
|
*
|
|
* Different map implementations will rely on rcu in map methods
|
|
* lookup/update/delete, therefore eBPF programs must run under rcu lock
|
|
* if program is allowed to access maps, so check rcu_read_lock_held in
|
|
* all three functions.
|
|
*/
|
|
BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
|
|
{
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
return (unsigned long) map->ops->map_lookup_elem(map, key);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_lookup_elem_proto = {
|
|
.func = bpf_map_lookup_elem,
|
|
.gpl_only = false,
|
|
.pkt_access = true,
|
|
.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_MAP_KEY,
|
|
};
|
|
|
|
BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
|
|
void *, value, u64, flags)
|
|
{
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
return map->ops->map_update_elem(map, key, value, flags);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_update_elem_proto = {
|
|
.func = bpf_map_update_elem,
|
|
.gpl_only = false,
|
|
.pkt_access = true,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_MAP_KEY,
|
|
.arg3_type = ARG_PTR_TO_MAP_VALUE,
|
|
.arg4_type = ARG_ANYTHING,
|
|
};
|
|
|
|
BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
|
|
{
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
return map->ops->map_delete_elem(map, key);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_delete_elem_proto = {
|
|
.func = bpf_map_delete_elem,
|
|
.gpl_only = false,
|
|
.pkt_access = true,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_MAP_KEY,
|
|
};
|
|
|
|
BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags)
|
|
{
|
|
return map->ops->map_push_elem(map, value, flags);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_push_elem_proto = {
|
|
.func = bpf_map_push_elem,
|
|
.gpl_only = false,
|
|
.pkt_access = true,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_MAP_VALUE,
|
|
.arg3_type = ARG_ANYTHING,
|
|
};
|
|
|
|
BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
|
|
{
|
|
return map->ops->map_pop_elem(map, value);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_pop_elem_proto = {
|
|
.func = bpf_map_pop_elem,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
|
|
};
|
|
|
|
BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
|
|
{
|
|
return map->ops->map_peek_elem(map, value);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_map_peek_elem_proto = {
|
|
.func = bpf_map_pop_elem,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
|
|
};
|
|
|
|
const struct bpf_func_proto bpf_get_prandom_u32_proto = {
|
|
.func = bpf_user_rnd_u32,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_0(bpf_get_smp_processor_id)
|
|
{
|
|
return smp_processor_id();
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
|
|
.func = bpf_get_smp_processor_id,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_0(bpf_get_numa_node_id)
|
|
{
|
|
return numa_node_id();
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_numa_node_id_proto = {
|
|
.func = bpf_get_numa_node_id,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_0(bpf_ktime_get_ns)
|
|
{
|
|
/* NMI safe access to clock monotonic */
|
|
return ktime_get_mono_fast_ns();
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_ktime_get_ns_proto = {
|
|
.func = bpf_ktime_get_ns,
|
|
.gpl_only = true,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_0(bpf_get_current_pid_tgid)
|
|
{
|
|
struct task_struct *task = current;
|
|
|
|
if (unlikely(!task))
|
|
return -EINVAL;
|
|
|
|
return (u64) task->tgid << 32 | task->pid;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_current_pid_tgid_proto = {
|
|
.func = bpf_get_current_pid_tgid,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_0(bpf_get_current_uid_gid)
|
|
{
|
|
struct task_struct *task = current;
|
|
kuid_t uid;
|
|
kgid_t gid;
|
|
|
|
if (unlikely(!task))
|
|
return -EINVAL;
|
|
|
|
current_uid_gid(&uid, &gid);
|
|
return (u64) from_kgid(&init_user_ns, gid) << 32 |
|
|
from_kuid(&init_user_ns, uid);
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_current_uid_gid_proto = {
|
|
.func = bpf_get_current_uid_gid,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
BPF_CALL_2(bpf_get_current_comm, char *, buf, u32, size)
|
|
{
|
|
struct task_struct *task = current;
|
|
|
|
if (unlikely(!task))
|
|
goto err_clear;
|
|
|
|
strncpy(buf, task->comm, size);
|
|
|
|
/* Verifier guarantees that size > 0. For task->comm exceeding
|
|
* size, guarantee that buf is %NUL-terminated. Unconditionally
|
|
* done here to save the size test.
|
|
*/
|
|
buf[size - 1] = 0;
|
|
return 0;
|
|
err_clear:
|
|
memset(buf, 0, size);
|
|
return -EINVAL;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_current_comm_proto = {
|
|
.func = bpf_get_current_comm,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
|
|
.arg2_type = ARG_CONST_SIZE,
|
|
};
|
|
|
|
#if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK)
|
|
|
|
static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
|
|
{
|
|
arch_spinlock_t *l = (void *)lock;
|
|
union {
|
|
__u32 val;
|
|
arch_spinlock_t lock;
|
|
} u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED };
|
|
|
|
compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0");
|
|
BUILD_BUG_ON(sizeof(*l) != sizeof(__u32));
|
|
BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32));
|
|
arch_spin_lock(l);
|
|
}
|
|
|
|
static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
|
|
{
|
|
arch_spinlock_t *l = (void *)lock;
|
|
|
|
arch_spin_unlock(l);
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void __bpf_spin_lock(struct bpf_spin_lock *lock)
|
|
{
|
|
atomic_t *l = (void *)lock;
|
|
|
|
BUILD_BUG_ON(sizeof(*l) != sizeof(*lock));
|
|
do {
|
|
atomic_cond_read_relaxed(l, !VAL);
|
|
} while (atomic_xchg(l, 1));
|
|
}
|
|
|
|
static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock)
|
|
{
|
|
atomic_t *l = (void *)lock;
|
|
|
|
atomic_set_release(l, 0);
|
|
}
|
|
|
|
#endif
|
|
|
|
static DEFINE_PER_CPU(unsigned long, irqsave_flags);
|
|
|
|
notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock)
|
|
{
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
__bpf_spin_lock(lock);
|
|
__this_cpu_write(irqsave_flags, flags);
|
|
return 0;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_spin_lock_proto = {
|
|
.func = bpf_spin_lock,
|
|
.gpl_only = false,
|
|
.ret_type = RET_VOID,
|
|
.arg1_type = ARG_PTR_TO_SPIN_LOCK,
|
|
};
|
|
|
|
notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock)
|
|
{
|
|
unsigned long flags;
|
|
|
|
flags = __this_cpu_read(irqsave_flags);
|
|
__bpf_spin_unlock(lock);
|
|
local_irq_restore(flags);
|
|
return 0;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_spin_unlock_proto = {
|
|
.func = bpf_spin_unlock,
|
|
.gpl_only = false,
|
|
.ret_type = RET_VOID,
|
|
.arg1_type = ARG_PTR_TO_SPIN_LOCK,
|
|
};
|
|
|
|
void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
|
|
bool lock_src)
|
|
{
|
|
struct bpf_spin_lock *lock;
|
|
|
|
if (lock_src)
|
|
lock = src + map->spin_lock_off;
|
|
else
|
|
lock = dst + map->spin_lock_off;
|
|
preempt_disable();
|
|
____bpf_spin_lock(lock);
|
|
copy_map_value(map, dst, src);
|
|
____bpf_spin_unlock(lock);
|
|
preempt_enable();
|
|
}
|
|
|
|
#ifdef CONFIG_CGROUPS
|
|
BPF_CALL_0(bpf_get_current_cgroup_id)
|
|
{
|
|
struct cgroup *cgrp = task_dfl_cgroup(current);
|
|
|
|
return cgrp->kn->id.id;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
|
|
.func = bpf_get_current_cgroup_id,
|
|
.gpl_only = false,
|
|
.ret_type = RET_INTEGER,
|
|
};
|
|
|
|
#ifdef CONFIG_CGROUP_BPF
|
|
DECLARE_PER_CPU(struct bpf_cgroup_storage*,
|
|
bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
|
|
|
|
BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
|
|
{
|
|
/* flags argument is not used now,
|
|
* but provides an ability to extend the API.
|
|
* verifier checks that its value is correct.
|
|
*/
|
|
enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
|
|
struct bpf_cgroup_storage *storage;
|
|
void *ptr;
|
|
|
|
storage = this_cpu_read(bpf_cgroup_storage[stype]);
|
|
|
|
if (stype == BPF_CGROUP_STORAGE_SHARED)
|
|
ptr = &READ_ONCE(storage->buf)->data[0];
|
|
else
|
|
ptr = this_cpu_ptr(storage->percpu_buf);
|
|
|
|
return (unsigned long)ptr;
|
|
}
|
|
|
|
const struct bpf_func_proto bpf_get_local_storage_proto = {
|
|
.func = bpf_get_local_storage,
|
|
.gpl_only = false,
|
|
.ret_type = RET_PTR_TO_MAP_VALUE,
|
|
.arg1_type = ARG_CONST_MAP_PTR,
|
|
.arg2_type = ARG_ANYTHING,
|
|
};
|
|
#endif
|
|
#endif
|