openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'bpf-xdp-redirect' 

Björn Töpel says:

====================
This two patch series contain two optimizations for the
bpf_redirect_map() helper and the xdp_do_redirect() function.

The bpf_redirect_map() optimization is about avoiding the map lookup
dispatching. Instead of having a switch-statement and selecting the
correct lookup function, we let bpf_redirect_map() be a map operation,
where each map has its own bpf_redirect_map() implementation. This way
the run-time lookup is avoided.

The xdp_do_redirect() patch restructures the code, so that the map
pointer indirection can be avoided.

Performance-wise I got 4% improvement for XSKMAP
(sample:xdpsock/rx-drop), and 8% (sample:xdp_redirect_map) on my
machine.

v5->v6:  Removed REDIR enum, and instead use map_id and map_type. (Daniel)
         Applied Daniel's fixups on patch 1. (Daniel)
v4->v5:  Renamed map operation to map_redirect. (Daniel)
v3->v4:  Made bpf_redirect_map() a map operation. (Daniel)
v2->v3:  Fix build when CONFIG_NET is not set. (lkp)
v1->v2:  Removed warning when CONFIG_BPF_SYSCALL was not set. (lkp)
         Cleaned up case-clause in xdp_do_generic_redirect_map(). (Toke)
         Re-added comment. (Toke)
rfc->v1: Use map_id, and remove bpf_clear_redirect_map(). (Toke)
         Get rid of the macro and use __always_inline. (Jesper)
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit is contained in:
Daniel Borkmann 2021-03-10 01:06:34 +01:00
parent 11d39cfeec ee75aef23a
commit 32f91529e2
9 changed files with 194 additions and 207 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
include/linux/bpf.h
View File

@ -118,6 +118,9 @@ struct bpf_map_ops {
void *owner, u32 size);
struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
/* Misc helpers.*/
int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags);
/* map_meta_equal must be implemented for maps that can be
* used as an inner map. It is a runtime check to ensure
* an inner map can be inserted to an outer map.
@ -1450,9 +1453,9 @@ struct btf *bpf_get_btf_vmlinux(void);
/* Map specifics */
struct xdp_buff;
struct sk_buff;
struct bpf_dtab_netdev;
struct bpf_cpu_map_entry;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
void __dev_flush(void);
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx);
@ -1462,7 +1465,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
bool dev_map_can_have_prog(struct bpf_map *map);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_flush(void);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx);
@ -1593,17 +1595,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
return -EOPNOTSUPP;
}
static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline bool dev_map_can_have_prog(struct bpf_map *map)
{
return false;
@ -1615,6 +1606,7 @@ static inline void __dev_flush(void)
struct xdp_buff;
struct bpf_dtab_netdev;
struct bpf_cpu_map_entry;
static inline
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
@ -1639,12 +1631,6 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
return 0;
}
static inline
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
return NULL;
}
static inline void __cpu_map_flush(void)
{
}

31
include/linux/filter.h
View File

@ -646,7 +646,8 @@ struct bpf_redirect_info {
u32 flags;
u32 tgt_index;
void *tgt_value;
struct bpf_map *map;
u32 map_id;
enum bpf_map_type map_type;
u32 kern_flags;
struct bpf_nh_params nh;
};
@ -1472,4 +1473,32 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
}
#endif /* IS_ENABLED(CONFIG_IPV6) */
static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
void *lookup_elem(struct bpf_map *map, u32 key))
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
/* Lower bits of the flags are used as return code on lookup failure */
if (unlikely(flags > XDP_TX))
return XDP_ABORTED;
ri->tgt_value = lookup_elem(map, ifindex);
if (unlikely(!ri->tgt_value)) {
/* If the lookup fails we want to clear out the state in the
* redirect_info struct completely, so that if an eBPF program
* performs multiple lookups, the last one always takes
* precedence.
*/
ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
return flags;
}
ri->tgt_index = ifindex;
ri->map_id = map->id;
ri->map_type = map->map_type;
return XDP_REDIRECT;
}
#endif /* __LINUX_FILTER_H__ */

19
include/net/xdp_sock.h
View File

@ -80,19 +80,6 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
void __xsk_map_flush(void);
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
struct xsk_map *m = container_of(map, struct xsk_map, map);
struct xdp_sock *xs;
if (key >= map->max_entries)
return NULL;
xs = READ_ONCE(m->xsk_map[key]);
return xs;
}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@ -109,12 +96,6 @@ static inline void __xsk_map_flush(void)
{
}
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */

58
include/trace/events/xdp.h
View File

@ -86,19 +86,15 @@ struct _bpf_dtab_netdev {
};
#endif /* __DEVMAP_OBJ_TYPE */
#define devmap_ifindex(tgt, map) \
(((map->map_type == BPF_MAP_TYPE_DEVMAP || \
map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
DECLARE_EVENT_CLASS(xdp_redirect_template,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
const struct bpf_map *map, u32 index),
enum bpf_map_type map_type,
u32 map_id, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index),
TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index),
TP_STRUCT__entry(
__field(int, prog_id)
@ -111,14 +107,22 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
),
TP_fast_assign(
u32 ifindex = 0, map_index = index;
if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex;
} else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
ifindex = index;
map_index = 0;
}
__entry->prog_id = xdp->aux->id;
__entry->act = XDP_REDIRECT;
__entry->ifindex = dev->ifindex;
__entry->err = err;
__entry->to_ifindex = map ? devmap_ifindex(tgt, map) :
index;
__entry->map_id = map ? map->id : 0;
__entry->map_index = map ? index : 0;
__entry->to_ifindex = ifindex;
__entry->map_id = map_id;
__entry->map_index = map_index;
),
TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
@ -133,45 +137,49 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
enum bpf_map_type map_type,
u32 map_id, u32 index),
TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
enum bpf_map_type map_type,
u32 map_id, u32 index),
TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
#define _trace_xdp_redirect(dev, xdp, to) \
trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to)
trace_xdp_redirect(dev, xdp, NULL, 0, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
#define _trace_xdp_redirect_err(dev, xdp, to, err) \
trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to)
trace_xdp_redirect_err(dev, xdp, NULL, err, BPF_MAP_TYPE_UNSPEC, INT_MAX, to)
#define _trace_xdp_redirect_map(dev, xdp, to, map, index) \
trace_xdp_redirect(dev, xdp, to, 0, map, index)
#define _trace_xdp_redirect_map(dev, xdp, to, map_type, map_id, index) \
trace_xdp_redirect(dev, xdp, to, 0, map_type, map_id, index)
#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err) \
trace_xdp_redirect_err(dev, xdp, to, err, map, index)
#define _trace_xdp_redirect_map_err(dev, xdp, to, map_type, map_id, index, err) \
trace_xdp_redirect_err(dev, xdp, to, err, map_type, map_id, index)
/* not used anymore, but kept around so as not to break old programs */
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
enum bpf_map_type map_type,
u32 map_id, u32 index),
TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
const void *tgt, int err,
const struct bpf_map *map, u32 index),
TP_ARGS(dev, xdp, tgt, err, map, index)
enum bpf_map_type map_type,
u32 map_id, u32 index),
TP_ARGS(dev, xdp, tgt, err, map_type, map_id, index)
);
TRACE_EVENT(xdp_cpumap_kthread,

9
kernel/bpf/cpumap.c
View File

@ -543,7 +543,6 @@ static void cpu_map_free(struct bpf_map *map)
* complete.
*/
bpf_clear_redirect_map(map);
synchronize_rcu();
/* For cpu_map the remote CPUs can still be using the entries
@ -563,7 +562,7 @@ static void cpu_map_free(struct bpf_map *map)
kfree(cmap);
}
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
struct bpf_cpu_map_entry *rcpu;
@ -600,6 +599,11 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
return 0;
}
static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem);
}
static int cpu_map_btf_id;
const struct bpf_map_ops cpu_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
@ -612,6 +616,7 @@ const struct bpf_map_ops cpu_map_ops = {
.map_check_btf = map_check_no_btf,
.map_btf_name = "bpf_cpu_map",
.map_btf_id = &cpu_map_btf_id,
.map_redirect = cpu_map_redirect,
};
static void bq_flush_to_queue(struct xdp_bulk_queue *bq)

17
kernel/bpf/devmap.c
View File

@ -197,7 +197,6 @@ static void dev_map_free(struct bpf_map *map)
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
bpf_clear_redirect_map(map);
synchronize_rcu();
/* Make sure prior __dev_map_entry_free() have completed. */
@ -258,7 +257,7 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
return 0;
}
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct hlist_head *head = dev_map_index_hash(dtab, key);
@ -392,7 +391,7 @@ void __dev_flush(void)
* update happens in parallel here a dev_put wont happen until after reading the
* ifindex.
*/
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *obj;
@ -735,6 +734,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
map, key, value, map_flags);
}
static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem);
}
static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem);
}
static int dev_map_btf_id;
const struct bpf_map_ops dev_map_ops = {
.map_meta_equal = bpf_map_meta_equal,
@ -747,6 +756,7 @@ const struct bpf_map_ops dev_map_ops = {
.map_check_btf = map_check_no_btf,
.map_btf_name = "bpf_dtab",
.map_btf_id = &dev_map_btf_id,
.map_redirect = dev_map_redirect,
};
static int dev_map_hash_map_btf_id;
@ -761,6 +771,7 @@ const struct bpf_map_ops dev_map_hash_ops = {
.map_check_btf = map_check_no_btf,
.map_btf_name = "bpf_dtab",
.map_btf_id = &dev_map_hash_map_btf_id,
.map_redirect = dev_hash_map_redirect,
};
static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,

13
kernel/bpf/verifier.c
View File

@ -5582,7 +5582,8 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
func_id != BPF_FUNC_map_push_elem &&
func_id != BPF_FUNC_map_pop_elem &&
func_id != BPF_FUNC_map_peek_elem &&
func_id != BPF_FUNC_for_each_map_elem)
func_id != BPF_FUNC_for_each_map_elem &&
func_id != BPF_FUNC_redirect_map)
return 0;
if (map == NULL) {
@ -12017,7 +12018,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
insn->imm == BPF_FUNC_map_delete_elem ||
insn->imm == BPF_FUNC_map_push_elem ||
insn->imm == BPF_FUNC_map_pop_elem ||
insn->imm == BPF_FUNC_map_peek_elem)) {
insn->imm == BPF_FUNC_map_peek_elem ||
insn->imm == BPF_FUNC_redirect_map)) {
aux = &env->insn_aux_data[i + delta];
if (bpf_map_ptr_poisoned(aux))
goto patch_call_imm;
@ -12059,6 +12061,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
(int (*)(struct bpf_map *map, void *value))NULL));
BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
(int (*)(struct bpf_map *map, void *value))NULL));
BUILD_BUG_ON(!__same_type(ops->map_redirect,
(int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
patch_map_ops_generic:
switch (insn->imm) {
case BPF_FUNC_map_lookup_elem:
@ -12085,6 +12090,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
__bpf_call_base;
continue;
case BPF_FUNC_redirect_map:
insn->imm = BPF_CAST_CALL(ops->map_redirect) -
__bpf_call_base;
continue;
}
goto patch_call_imm;

181
net/core/filter.c
View File

@ -3918,23 +3918,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
.arg2_type = ARG_ANYTHING,
};
static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
struct bpf_map *map, struct xdp_buff *xdp)
{
switch (map->map_type) {
case BPF_MAP_TYPE_DEVMAP:
case BPF_MAP_TYPE_DEVMAP_HASH:
return dev_map_enqueue(fwd, xdp, dev_rx);
case BPF_MAP_TYPE_CPUMAP:
return cpu_map_enqueue(fwd, xdp, dev_rx);
case BPF_MAP_TYPE_XSKMAP:
return __xsk_map_redirect(fwd, xdp);
default:
return -EBADRQC;
}
return 0;
}
void xdp_do_flush(void)
{
__dev_flush();
@ -3943,71 +3926,52 @@ void xdp_do_flush(void)
}
EXPORT_SYMBOL_GPL(xdp_do_flush);
static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
{
switch (map->map_type) {
case BPF_MAP_TYPE_DEVMAP:
return __dev_map_lookup_elem(map, index);
case BPF_MAP_TYPE_DEVMAP_HASH:
return __dev_map_hash_lookup_elem(map, index);
case BPF_MAP_TYPE_CPUMAP:
return __cpu_map_lookup_elem(map, index);
case BPF_MAP_TYPE_XSKMAP:
return __xsk_map_lookup_elem(map, index);
default:
return NULL;
}
}
void bpf_clear_redirect_map(struct bpf_map *map)
{
struct bpf_redirect_info *ri;
int cpu;
for_each_possible_cpu(cpu) {
ri = per_cpu_ptr(&bpf_redirect_info, cpu);
/* Avoid polluting remote cacheline due to writes if
* not needed. Once we pass this test, we need the
* cmpxchg() to make sure it hasn't been changed in
* the meantime by remote CPU.
*/
if (unlikely(READ_ONCE(ri->map) == map))
cmpxchg(&ri->map, map, NULL);
}
}
int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct bpf_map *map = READ_ONCE(ri->map);
u32 index = ri->tgt_index;
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
int err;
ri->tgt_index = 0;
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
if (unlikely(!map)) {
fwd = dev_get_by_index_rcu(dev_net(dev), index);
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
err = dev_map_enqueue(fwd, xdp, dev);
break;
case BPF_MAP_TYPE_CPUMAP:
err = cpu_map_enqueue(fwd, xdp, dev);
break;
case BPF_MAP_TYPE_XSKMAP:
err = __xsk_map_redirect(fwd, xdp);
break;
case BPF_MAP_TYPE_UNSPEC:
if (map_id == INT_MAX) {
fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
break;
}
err = dev_xdp_enqueue(fwd, xdp, dev);
} else {
err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
break;
}
fallthrough;
default:
err = -EBADRQC;
}
if (unlikely(err))
goto err;
_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
_trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
return 0;
err:
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
@ -4016,41 +3980,36 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
struct bpf_prog *xdp_prog,
struct bpf_map *map)
void *fwd,
enum bpf_map_type map_type, u32 map_id)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
u32 index = ri->tgt_index;
void *fwd = ri->tgt_value;
int err = 0;
int err;
ri->tgt_index = 0;
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
struct bpf_dtab_netdev *dst = fwd;
err = dev_map_generic_redirect(dst, skb, xdp_prog);
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
err = dev_map_generic_redirect(fwd, skb, xdp_prog);
if (unlikely(err))
goto err;
} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
struct xdp_sock *xs = fwd;
err = xsk_generic_rcv(xs, xdp);
break;
case BPF_MAP_TYPE_XSKMAP:
err = xsk_generic_rcv(fwd, xdp);
if (err)
goto err;
consume_skb(skb);
} else {
break;
default:
/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
err = -EBADRQC;
goto err;
}
_trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
_trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
return 0;
err:
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
return err;
}
@ -4058,16 +4017,16 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct bpf_map *map = READ_ONCE(ri->map);
u32 index = ri->tgt_index;
struct net_device *fwd;
int err = 0;
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
int err;
if (map)
return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog,
map);
ri->tgt_index = 0;
fwd = dev_get_by_index_rcu(dev_net(dev), index);
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
@ -4078,11 +4037,14 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
goto err;
skb->dev = fwd;
_trace_xdp_redirect(dev, xdp_prog, index);
_trace_xdp_redirect(dev, xdp_prog, ri->tgt_index);
generic_xdp_tx(skb, xdp_prog);
return 0;
}
return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id);
err:
_trace_xdp_redirect_err(dev, xdp_prog, index, err);
_trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err);
return err;
}
@ -4093,10 +4055,12 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
if (unlikely(flags))
return XDP_ABORTED;
ri->flags = flags;
/* NB! Map type UNSPEC and map_id == INT_MAX (never generated
* by map_idr) is used for ifindex based XDP redirect.
*/
ri->tgt_index = ifindex;
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
ri->map_id = INT_MAX;
ri->map_type = BPF_MAP_TYPE_UNSPEC;
return XDP_REDIRECT;
}
@ -4112,28 +4076,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
/* Lower bits of the flags are used as return code on lookup failure */
if (unlikely(flags > XDP_TX))
return XDP_ABORTED;
ri->tgt_value = __xdp_map_lookup_elem(map, ifindex);
if (unlikely(!ri->tgt_value)) {
/* If the lookup fails we want to clear out the state in the
* redirect_info struct completely, so that if an eBPF program
* performs multiple lookups, the last one always takes
* precedence.
*/
WRITE_ONCE(ri->map, NULL);
return flags;
}
ri->flags = flags;
ri->tgt_index = ifindex;
WRITE_ONCE(ri->map, map);
return XDP_REDIRECT;
return map->ops->map_redirect(map, ifindex, flags);
}
static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {

17
net/xdp/xskmap.c
View File

@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
{
struct xsk_map *m = container_of(map, struct xsk_map, map);
bpf_clear_redirect_map(map);
synchronize_net();
bpf_map_area_free(m);
}
@ -125,6 +124,16 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
return insn - insn_buf;
}
static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
{
struct xsk_map *m = container_of(map, struct xsk_map, map);
if (key >= map->max_entries)
return NULL;
return READ_ONCE(m->xsk_map[key]);
}
static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
{
WARN_ON_ONCE(!rcu_read_lock_held());
@ -215,6 +224,11 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
return 0;
}
static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
}
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
struct xdp_sock **map_entry)
{
@ -247,4 +261,5 @@ const struct bpf_map_ops xsk_map_ops = {
.map_check_btf = map_check_no_btf,
.map_btf_name = "xsk_map",
.map_btf_id = &xsk_map_btf_id,
.map_redirect = xsk_map_redirect,
};