linux/kernel/bpf/bpf_inode_storage.c

285 lines
7.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2019 Facebook
* Copyright 2020 Google LLC.
*/
#include <linux/rculist.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/bpf.h>
#include <linux/bpf_local_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
#include <linux/bpf_lsm.h>
#include <linux/btf_ids.h>
#include <linux/fdtable.h>
bpf: Allow bpf_local_storage to be used by sleepable programs Other maps like hashmaps are already available to sleepable programs. Sleepable BPF programs run under trace RCU. Allow task, sk and inode storage to be used from sleepable programs. This allows sleepable and non-sleepable programs to provide shareable annotations on kernel objects. Sleepable programs run in trace RCU where as non-sleepable programs run in a normal RCU critical section i.e. __bpf_prog_enter{_sleepable} and __bpf_prog_exit{_sleepable}) (rcu_read_lock or rcu_read_lock_trace). In order to make the local storage maps accessible to both sleepable and non-sleepable programs, one needs to call both call_rcu_tasks_trace and call_rcu to wait for both trace and classical RCU grace periods to expire before freeing memory. Paul's work on call_rcu_tasks_trace allows us to have per CPU queueing for call_rcu_tasks_trace. This behaviour can be achieved by setting rcupdate.rcu_task_enqueue_lim=<num_cpus> boot parameter. In light of these new performance changes and to keep the local storage code simple, avoid adding a new flag for sleepable maps / local storage to select the RCU synchronization (trace / classical). Also, update the dereferencing of the pointers to use rcu_derference_check (with either the trace or normal RCU locks held) with a common bpf_rcu_lock_held helper method. Signed-off-by: KP Singh <kpsingh@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20211224152916.1550677-2-kpsingh@kernel.org
2021-12-24 18:29:15 +03:00
#include <linux/rcupdate_trace.h>
DEFINE_BPF_STORAGE_CACHE(inode_cache);
static struct bpf_local_storage __rcu **
inode_storage_ptr(void *owner)
{
struct inode *inode = owner;
struct bpf_storage_blob *bsb;
bsb = bpf_inode(inode);
if (!bsb)
return NULL;
return &bsb->storage;
}
static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode,
struct bpf_map *map,
bool cacheit_lockit)
{
struct bpf_local_storage *inode_storage;
struct bpf_local_storage_map *smap;
struct bpf_storage_blob *bsb;
bsb = bpf_inode(inode);
if (!bsb)
return NULL;
bpf: Allow bpf_local_storage to be used by sleepable programs Other maps like hashmaps are already available to sleepable programs. Sleepable BPF programs run under trace RCU. Allow task, sk and inode storage to be used from sleepable programs. This allows sleepable and non-sleepable programs to provide shareable annotations on kernel objects. Sleepable programs run in trace RCU where as non-sleepable programs run in a normal RCU critical section i.e. __bpf_prog_enter{_sleepable} and __bpf_prog_exit{_sleepable}) (rcu_read_lock or rcu_read_lock_trace). In order to make the local storage maps accessible to both sleepable and non-sleepable programs, one needs to call both call_rcu_tasks_trace and call_rcu to wait for both trace and classical RCU grace periods to expire before freeing memory. Paul's work on call_rcu_tasks_trace allows us to have per CPU queueing for call_rcu_tasks_trace. This behaviour can be achieved by setting rcupdate.rcu_task_enqueue_lim=<num_cpus> boot parameter. In light of these new performance changes and to keep the local storage code simple, avoid adding a new flag for sleepable maps / local storage to select the RCU synchronization (trace / classical). Also, update the dereferencing of the pointers to use rcu_derference_check (with either the trace or normal RCU locks held) with a common bpf_rcu_lock_held helper method. Signed-off-by: KP Singh <kpsingh@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20211224152916.1550677-2-kpsingh@kernel.org
2021-12-24 18:29:15 +03:00
inode_storage =
rcu_dereference_check(bsb->storage, bpf_rcu_lock_held());
if (!inode_storage)
return NULL;
smap = (struct bpf_local_storage_map *)map;
return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit);
}
void bpf_inode_storage_free(struct inode *inode)
{
struct bpf_local_storage_elem *selem;
struct bpf_local_storage *local_storage;
bool free_inode_storage = false;
struct bpf_storage_blob *bsb;
struct hlist_node *n;
bsb = bpf_inode(inode);
if (!bsb)
return;
rcu_read_lock();
local_storage = rcu_dereference(bsb->storage);
if (!local_storage) {
rcu_read_unlock();
return;
}
/* Neither the bpf_prog nor the bpf-map's syscall
* could be modifying the local_storage->list now.
* Thus, no elem can be added-to or deleted-from the
* local_storage->list by the bpf_prog or by the bpf-map's syscall.
*
* It is racing with bpf_local_storage_map_free() alone
* when unlinking elem from the local_storage->list and
* the map's bucket->list.
*/
raw_spin_lock_bh(&local_storage->lock);
hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) {
/* Always unlink from map before unlinking from
* local_storage.
*/
bpf_selem_unlink_map(selem);
free_inode_storage = bpf_selem_unlink_storage_nolock(
local_storage, selem, false);
}
raw_spin_unlock_bh(&local_storage->lock);
rcu_read_unlock();
/* free_inoode_storage should always be true as long as
* local_storage->list was non-empty.
*/
if (free_inode_storage)
kfree_rcu(local_storage, rcu);
}
static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_local_storage_data *sdata;
struct file *f;
int fd;
fd = *(int *)key;
f = fget_raw(fd);
if (!f)
return ERR_PTR(-EBADF);
sdata = inode_storage_lookup(f->f_inode, map, true);
fput(f);
return sdata ? sdata->data : NULL;
}
static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags)
{
struct bpf_local_storage_data *sdata;
struct file *f;
int fd;
fd = *(int *)key;
f = fget_raw(fd);
if (!f)
return -EBADF;
if (!inode_storage_ptr(f->f_inode)) {
fput(f);
return -EBADF;
}
sdata = bpf_local_storage_update(f->f_inode,
(struct bpf_local_storage_map *)map,
value, map_flags, GFP_ATOMIC);
fput(f);
return PTR_ERR_OR_ZERO(sdata);
}
static int inode_storage_delete(struct inode *inode, struct bpf_map *map)
{
struct bpf_local_storage_data *sdata;
sdata = inode_storage_lookup(inode, map, false);
if (!sdata)
return -ENOENT;
bpf_selem_unlink(SELEM(sdata));
return 0;
}
static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key)
{
struct file *f;
int fd, err;
fd = *(int *)key;
f = fget_raw(fd);
if (!f)
return -EBADF;
err = inode_storage_delete(f->f_inode, map);
fput(f);
return err;
}
/* *gfp_flags* is a hidden argument provided by the verifier */
BPF_CALL_5(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode,
void *, value, u64, flags, gfp_t, gfp_flags)
{
struct bpf_local_storage_data *sdata;
bpf: Allow bpf_local_storage to be used by sleepable programs Other maps like hashmaps are already available to sleepable programs. Sleepable BPF programs run under trace RCU. Allow task, sk and inode storage to be used from sleepable programs. This allows sleepable and non-sleepable programs to provide shareable annotations on kernel objects. Sleepable programs run in trace RCU where as non-sleepable programs run in a normal RCU critical section i.e. __bpf_prog_enter{_sleepable} and __bpf_prog_exit{_sleepable}) (rcu_read_lock or rcu_read_lock_trace). In order to make the local storage maps accessible to both sleepable and non-sleepable programs, one needs to call both call_rcu_tasks_trace and call_rcu to wait for both trace and classical RCU grace periods to expire before freeing memory. Paul's work on call_rcu_tasks_trace allows us to have per CPU queueing for call_rcu_tasks_trace. This behaviour can be achieved by setting rcupdate.rcu_task_enqueue_lim=<num_cpus> boot parameter. In light of these new performance changes and to keep the local storage code simple, avoid adding a new flag for sleepable maps / local storage to select the RCU synchronization (trace / classical). Also, update the dereferencing of the pointers to use rcu_derference_check (with either the trace or normal RCU locks held) with a common bpf_rcu_lock_held helper method. Signed-off-by: KP Singh <kpsingh@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20211224152916.1550677-2-kpsingh@kernel.org
2021-12-24 18:29:15 +03:00
WARN_ON_ONCE(!bpf_rcu_lock_held());
if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
return (unsigned long)NULL;
/* explicitly check that the inode_storage_ptr is not
* NULL as inode_storage_lookup returns NULL in this case and
* bpf_local_storage_update expects the owner to have a
* valid storage pointer.
*/
if (!inode || !inode_storage_ptr(inode))
return (unsigned long)NULL;
sdata = inode_storage_lookup(inode, map, true);
if (sdata)
return (unsigned long)sdata->data;
/* This helper must only called from where the inode is guaranteed
* to have a refcount and cannot be freed.
*/
if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) {
sdata = bpf_local_storage_update(
inode, (struct bpf_local_storage_map *)map, value,
BPF_NOEXIST, gfp_flags);
return IS_ERR(sdata) ? (unsigned long)NULL :
(unsigned long)sdata->data;
}
return (unsigned long)NULL;
}
BPF_CALL_2(bpf_inode_storage_delete,
struct bpf_map *, map, struct inode *, inode)
{
bpf: Allow bpf_local_storage to be used by sleepable programs Other maps like hashmaps are already available to sleepable programs. Sleepable BPF programs run under trace RCU. Allow task, sk and inode storage to be used from sleepable programs. This allows sleepable and non-sleepable programs to provide shareable annotations on kernel objects. Sleepable programs run in trace RCU where as non-sleepable programs run in a normal RCU critical section i.e. __bpf_prog_enter{_sleepable} and __bpf_prog_exit{_sleepable}) (rcu_read_lock or rcu_read_lock_trace). In order to make the local storage maps accessible to both sleepable and non-sleepable programs, one needs to call both call_rcu_tasks_trace and call_rcu to wait for both trace and classical RCU grace periods to expire before freeing memory. Paul's work on call_rcu_tasks_trace allows us to have per CPU queueing for call_rcu_tasks_trace. This behaviour can be achieved by setting rcupdate.rcu_task_enqueue_lim=<num_cpus> boot parameter. In light of these new performance changes and to keep the local storage code simple, avoid adding a new flag for sleepable maps / local storage to select the RCU synchronization (trace / classical). Also, update the dereferencing of the pointers to use rcu_derference_check (with either the trace or normal RCU locks held) with a common bpf_rcu_lock_held helper method. Signed-off-by: KP Singh <kpsingh@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20211224152916.1550677-2-kpsingh@kernel.org
2021-12-24 18:29:15 +03:00
WARN_ON_ONCE(!bpf_rcu_lock_held());
if (!inode)
return -EINVAL;
/* This helper must only called from where the inode is guaranteed
* to have a refcount and cannot be freed.
*/
return inode_storage_delete(inode, map);
}
static int notsupp_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
return -ENOTSUPP;
}
static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr)
{
struct bpf_local_storage_map *smap;
smap = bpf_local_storage_map_alloc(attr);
if (IS_ERR(smap))
return ERR_CAST(smap);
smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache);
return &smap->map;
}
static void inode_storage_map_free(struct bpf_map *map)
{
struct bpf_local_storage_map *smap;
smap = (struct bpf_local_storage_map *)map;
bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx);
bpf_local_storage_map_free(smap, NULL);
}
static int inode_storage_map_btf_id;
const struct bpf_map_ops inode_storage_map_ops = {
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 04:18:06 +03:00
.map_meta_equal = bpf_map_meta_equal,
.map_alloc_check = bpf_local_storage_map_alloc_check,
.map_alloc = inode_storage_map_alloc,
.map_free = inode_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_inode_storage_lookup_elem,
.map_update_elem = bpf_fd_inode_storage_update_elem,
.map_delete_elem = bpf_fd_inode_storage_delete_elem,
.map_check_btf = bpf_local_storage_map_check_btf,
.map_btf_name = "bpf_local_storage_map",
.map_btf_id = &inode_storage_map_btf_id,
.map_owner_storage_ptr = inode_storage_ptr,
};
BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode)
const struct bpf_func_proto bpf_inode_storage_get_proto = {
.func = bpf_inode_storage_get,
.gpl_only = false,
.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_BTF_ID,
.arg2_btf_id = &bpf_inode_storage_btf_ids[0],
.arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
.arg4_type = ARG_ANYTHING,
};
const struct bpf_func_proto bpf_inode_storage_delete_proto = {
.func = bpf_inode_storage_delete,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_CONST_MAP_PTR,
.arg2_type = ARG_PTR_TO_BTF_ID,
.arg2_btf_id = &bpf_inode_storage_btf_ids[0],
};