linux_dsm_epyc7002/kernel/bpf/helpers.c
Alexei Starovoitov d83525ca62 bpf: introduce bpf_spin_lock
Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let
bpf program serialize access to other variables.

Example:
struct hash_elem {
    int cnt;
    struct bpf_spin_lock lock;
};
struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key);
if (val) {
    bpf_spin_lock(&val->lock);
    val->cnt++;
    bpf_spin_unlock(&val->lock);
}

Restrictions and safety checks:
- bpf_spin_lock is only allowed inside HASH and ARRAY maps.
- BTF description of the map is mandatory for safety analysis.
- bpf program can take one bpf_spin_lock at a time, since two or more can
  cause dead locks.
- only one 'struct bpf_spin_lock' is allowed per map element.
  It drastically simplifies implementation yet allows bpf program to use
  any number of bpf_spin_locks.
- when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed.
- bpf program must bpf_spin_unlock() before return.
- bpf program can access 'struct bpf_spin_lock' only via
  bpf_spin_lock()/bpf_spin_unlock() helpers.
- load/store into 'struct bpf_spin_lock lock;' field is not allowed.
- to use bpf_spin_lock() helper the BTF description of map value must be
  a struct and have 'struct bpf_spin_lock anyname;' field at the top level.
  Nested lock inside another struct is not allowed.
- syscall map_lookup doesn't copy bpf_spin_lock field to user space.
- syscall map_update and program map_update do not update bpf_spin_lock field.
- bpf_spin_lock cannot be on the stack or inside networking packet.
  bpf_spin_lock can only be inside HASH or ARRAY map value.
- bpf_spin_lock is available to root only and to all program types.
- bpf_spin_lock is not allowed in inner maps of map-in-map.
- ld_abs is not allowed inside spin_lock-ed region.
- tracing progs and socket filter progs cannot use bpf_spin_lock due to
  insufficient preemption checks

Implementation details:
- cgroup-bpf class of programs can nest with xdp/tc programs.
  Hence bpf_spin_lock is equivalent to spin_lock_irqsave.
  Other solutions to avoid nested bpf_spin_lock are possible.
  Like making sure that all networking progs run with softirq disabled.
  spin_lock_irqsave is the simplest and doesn't add overhead to the
  programs that don't use it.
- arch_spinlock_t is used when its implemented as queued_spin_lock
- archs can force their own arch_spinlock_t
- on architectures where queued_spin_lock is not available and
  sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used.
- presence of bpf_spin_lock inside map value could have been indicated via
  extra flag during map_create, but specifying it via BTF is cleaner.
  It provides introspection for map key/value and reduces user mistakes.

Next steps:
- allow bpf_spin_lock in other map types (like cgroup local storage)
- introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper
  to request kernel to grab bpf_spin_lock before rewriting the value.
  That will serialize access to map elements.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 20:55:38 +01:00

351 lines
8.4 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,
};
#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