* [PATCH bpf-next v3 1/3] xdp: Move devmap bulk queue into struct net_device
2020-01-16 15:14 [PATCH bpf-next v3 0/3] xdp: Introduce bulking for non-map XDP_REDIRECT Toke Høiland-Jørgensen
@ 2020-01-16 15:14 ` Toke Høiland-Jørgensen
2020-01-16 15:14 ` [PATCH bpf-next v3 2/3] xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Toke Høiland-Jørgensen
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Toke Høiland-Jørgensen @ 2020-01-16 15:14 UTC (permalink / raw)
To: netdev
Cc: bpf, Daniel Borkmann, Alexei Starovoitov, David Miller,
Jesper Dangaard Brouer, Björn Töpel, John Fastabend,
Maciej Fijalkowski
From: Toke Høiland-Jørgensen <toke@redhat.com>
Commit 96360004b862 ("xdp: Make devmap flush_list common for all map
instances"), changed devmap flushing to be a global operation instead of a
per-map operation. However, the queue structure used for bulking was still
allocated as part of the containing map.
This patch moves the devmap bulk queue into struct net_device. The
motivation for this is reusing it for the non-map variant of XDP_REDIRECT,
which will be changed in a subsequent commit. To avoid other fields of
struct net_device moving to different cache lines, we also move a couple of
other members around.
We defer the actual allocation of the bulk queue structure until the
NETDEV_REGISTER notification devmap.c. This makes it possible to check for
ndo_xdp_xmit support before allocating the structure, which is not possible
at the time struct net_device is allocated. However, we keep the freeing in
free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER.
Because of this change, we lose the reference back to the map that
originated the redirect, so change the tracepoint to always return 0 as the
map ID and index. Otherwise no functional change is intended with this
patch.
After this patch, the relevant part of struct net_device looks like this,
according to pahole:
/* --- cacheline 14 boundary (896 bytes) --- */
struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */
unsigned int num_tx_queues; /* 904 4 */
unsigned int real_num_tx_queues; /* 908 4 */
struct Qdisc * qdisc; /* 912 8 */
unsigned int tx_queue_len; /* 920 4 */
spinlock_t tx_global_lock; /* 924 4 */
struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */
struct xps_dev_maps * xps_cpus_map; /* 936 8 */
struct xps_dev_maps * xps_rxqs_map; /* 944 8 */
struct mini_Qdisc * miniq_egress; /* 952 8 */
/* --- cacheline 15 boundary (960 bytes) --- */
struct hlist_head qdisc_hash[16]; /* 960 128 */
/* --- cacheline 17 boundary (1088 bytes) --- */
struct timer_list watchdog_timer; /* 1088 40 */
/* XXX last struct has 4 bytes of padding */
int watchdog_timeo; /* 1128 4 */
/* XXX 4 bytes hole, try to pack */
struct list_head todo_list; /* 1136 16 */
/* --- cacheline 18 boundary (1152 bytes) --- */
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
include/linux/netdevice.h | 13 ++++++---
include/trace/events/xdp.h | 2 +
kernel/bpf/devmap.c | 63 +++++++++++++++++++-------------------------
net/core/dev.c | 2 +
4 files changed, 38 insertions(+), 42 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2741aa35bec6..5ec3537fbdb1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -876,6 +876,7 @@ enum bpf_netdev_command {
struct bpf_prog_offload_ops;
struct netlink_ext_ack;
struct xdp_umem;
+struct xdp_dev_bulk_queue;
struct netdev_bpf {
enum bpf_netdev_command command;
@@ -1986,12 +1987,10 @@ struct net_device {
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
struct Qdisc *qdisc;
-#ifdef CONFIG_NET_SCHED
- DECLARE_HASHTABLE (qdisc_hash, 4);
-#endif
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
- int watchdog_timeo;
+
+ struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS
struct xps_dev_maps __rcu *xps_cpus_map;
@@ -2001,11 +2000,15 @@ struct net_device {
struct mini_Qdisc __rcu *miniq_egress;
#endif
+#ifdef CONFIG_NET_SCHED
+ DECLARE_HASHTABLE (qdisc_hash, 4);
+#endif
/* These may be needed for future network-power-down code. */
struct timer_list watchdog_timer;
+ int watchdog_timeo;
- int __percpu *pcpu_refcnt;
struct list_head todo_list;
+ int __percpu *pcpu_refcnt;
struct list_head link_watch_list;
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index a7378bcd9928..72bad13d4a3c 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -278,7 +278,7 @@ TRACE_EVENT(xdp_devmap_xmit,
),
TP_fast_assign(
- __entry->map_id = map->id;
+ __entry->map_id = map ? map->id : 0;
__entry->act = XDP_REDIRECT;
__entry->map_index = map_index;
__entry->drops = drops;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index da9c832fc5c8..030d125c3839 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -53,13 +53,11 @@
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
#define DEV_MAP_BULK_SIZE 16
-struct bpf_dtab_netdev;
-
-struct xdp_bulk_queue {
+struct xdp_dev_bulk_queue {
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
struct list_head flush_node;
+ struct net_device *dev;
struct net_device *dev_rx;
- struct bpf_dtab_netdev *obj;
unsigned int count;
};
@@ -67,9 +65,8 @@ struct bpf_dtab_netdev {
struct net_device *dev; /* must be first member, due to tracepoint */
struct hlist_node index_hlist;
struct bpf_dtab *dtab;
- struct xdp_bulk_queue __percpu *bulkq;
struct rcu_head rcu;
- unsigned int idx; /* keep track of map index for tracepoint */
+ unsigned int idx;
};
struct bpf_dtab {
@@ -219,7 +216,6 @@ static void dev_map_free(struct bpf_map *map)
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
hlist_del_rcu(&dev->index_hlist);
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -234,7 +230,6 @@ static void dev_map_free(struct bpf_map *map)
if (!dev)
continue;
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -320,10 +315,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
return -ENOENT;
}
-static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
+static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
- struct bpf_dtab_netdev *obj = bq->obj;
- struct net_device *dev = obj->dev;
+ struct net_device *dev = bq->dev;
int sent = 0, drops = 0, err = 0;
int i;
@@ -346,8 +340,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
out:
bq->count = 0;
- trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
- sent, drops, bq->dev_rx, dev, err);
+ trace_xdp_devmap_xmit(NULL, 0, sent, drops, bq->dev_rx, dev, err);
bq->dev_rx = NULL;
__list_del_clearprev(&bq->flush_node);
return 0;
@@ -374,7 +367,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
void __dev_map_flush(void)
{
struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
- struct xdp_bulk_queue *bq, *tmp;
+ struct xdp_dev_bulk_queue *bq, *tmp;
rcu_read_lock();
list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
@@ -401,12 +394,12 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
-static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
+static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
{
struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
- struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
+ struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
bq_xmit_all(bq, 0);
@@ -444,7 +437,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
- return bq_enqueue(dst, xdpf, dev_rx);
+ return bq_enqueue(dev, xdpf, dev_rx);
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -483,7 +476,6 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
struct bpf_dtab_netdev *dev;
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
- free_percpu(dev->bulkq);
dev_put(dev->dev);
kfree(dev);
}
@@ -538,30 +530,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
u32 ifindex,
unsigned int idx)
{
- gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
struct bpf_dtab_netdev *dev;
- struct xdp_bulk_queue *bq;
- int cpu;
- dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
+ dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
+ dtab->map.numa_node);
if (!dev)
return ERR_PTR(-ENOMEM);
- dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
- sizeof(void *), gfp);
- if (!dev->bulkq) {
- kfree(dev);
- return ERR_PTR(-ENOMEM);
- }
-
- for_each_possible_cpu(cpu) {
- bq = per_cpu_ptr(dev->bulkq, cpu);
- bq->obj = dev;
- }
-
dev->dev = dev_get_by_index(net, ifindex);
if (!dev->dev) {
- free_percpu(dev->bulkq);
kfree(dev);
return ERR_PTR(-EINVAL);
}
@@ -721,9 +698,23 @@ static int dev_map_notification(struct notifier_block *notifier,
{
struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
struct bpf_dtab *dtab;
- int i;
+ int i, cpu;
switch (event) {
+ case NETDEV_REGISTER:
+ if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
+ break;
+
+ /* will be freed in free_netdev() */
+ netdev->xdp_bulkq =
+ __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
+ sizeof(void *), GFP_ATOMIC);
+ if (!netdev->xdp_bulkq)
+ return NOTIFY_BAD;
+
+ for_each_possible_cpu(cpu)
+ per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
+ break;
case NETDEV_UNREGISTER:
/* This rcu_read_lock/unlock pair is needed because
* dev_map_list is an RCU list AND to ensure a delete
diff --git a/net/core/dev.c b/net/core/dev.c
index d99f88c58636..e7802a41ae7f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9847,6 +9847,8 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
+ free_percpu(dev->xdp_bulkq);
+ dev->xdp_bulkq = NULL;
netdev_unregister_lockdep_key(dev);
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH bpf-next v3 2/3] xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths
2020-01-16 15:14 [PATCH bpf-next v3 0/3] xdp: Introduce bulking for non-map XDP_REDIRECT Toke Høiland-Jørgensen
2020-01-16 15:14 ` [PATCH bpf-next v3 1/3] xdp: Move devmap bulk queue into struct net_device Toke Høiland-Jørgensen
@ 2020-01-16 15:14 ` Toke Høiland-Jørgensen
2020-01-16 15:14 ` [PATCH bpf-next v3 3/3] devmap: Adjust tracepoint for map-less queue flush Toke Høiland-Jørgensen
2020-01-17 4:06 ` [PATCH bpf-next v3 0/3] xdp: Introduce bulking for non-map XDP_REDIRECT Alexei Starovoitov
3 siblings, 0 replies; 5+ messages in thread
From: Toke Høiland-Jørgensen @ 2020-01-16 15:14 UTC (permalink / raw)
To: netdev
Cc: bpf, Daniel Borkmann, Alexei Starovoitov, David Miller,
Jesper Dangaard Brouer, Björn Töpel, John Fastabend,
Maciej Fijalkowski
From: Toke Høiland-Jørgensen <toke@redhat.com>
Since the bulk queue used by XDP_REDIRECT now lives in struct net_device,
we can re-use the bulking for the non-map version of the bpf_redirect()
helper. This is a simple matter of having xdp_do_redirect_slow() queue the
frame on the bulk queue instead of sending it out with __bpf_tx_xdp().
Unfortunately we can't make the bpf_redirect() helper return an error if
the ifindex doesn't exit (as bpf_redirect_map() does), because we don't
have a reference to the network namespace of the ingress device at the time
the helper is called. So we have to leave it as-is and keep the device
lookup in xdp_do_redirect_slow().
Since this leaves less reason to have the non-map redirect code in a
separate function, so we get rid of the xdp_do_redirect_slow() function
entirely. This does lose us the tracepoint disambiguation, but fortunately
the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint
entry structures. This means both can contain a map index, so we can just
amend the tracepoint definitions so we always emit the xdp_redirect(_err)
tracepoints, but with the map ID only populated if a map is present. This
means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep
the definitions around in case someone is still listening for them.
With this change, the performance of the xdp_redirect sample program goes
from 5Mpps to 8.4Mpps (a 68% increase).
Since the flush functions are no longer map-specific, rename the flush()
functions to drop _map from their names. One of the renamed functions is
the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To
keep from having to update all drivers, use a #define to keep the old name
working, and only update the virtual drivers in this patch.
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
---
drivers/net/tun.c | 4 +-
drivers/net/veth.c | 2 -
drivers/net/virtio_net.c | 2 -
include/linux/bpf.h | 13 +++++-
include/linux/filter.h | 10 +++-
include/trace/events/xdp.h | 101 +++++++++++++++++++-------------------------
kernel/bpf/devmap.c | 32 ++++++++++----
net/core/filter.c | 90 ++++++++-------------------------------
8 files changed, 108 insertions(+), 146 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 683d371e6e82..3a5a6c655dda 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1718,7 +1718,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
if (err < 0)
goto err_xdp;
if (err == XDP_REDIRECT)
- xdp_do_flush_map();
+ xdp_do_flush();
if (err != XDP_PASS)
goto out;
@@ -2549,7 +2549,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
}
if (flush)
- xdp_do_flush_map();
+ xdp_do_flush();
rcu_read_unlock();
local_bh_enable();
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a552df37a347..1c89017beebb 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -769,7 +769,7 @@ static int veth_poll(struct napi_struct *napi, int budget)
if (xdp_xmit & VETH_XDP_TX)
veth_xdp_flush(rq->dev, &bq);
if (xdp_xmit & VETH_XDP_REDIR)
- xdp_do_flush_map();
+ xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4d7d5434cc5d..c458cd313281 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1432,7 +1432,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
virtqueue_napi_complete(napi, rq->vq, received);
if (xdp_xmit & VIRTIO_XDP_REDIR)
- xdp_do_flush_map();
+ xdp_do_flush();
if (xdp_xmit & VIRTIO_XDP_TX) {
sq = virtnet_xdp_sq(vi);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3517e32149a4..8e3b8f4ad183 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1056,7 +1056,9 @@ struct sk_buff;
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_map_flush(void);
+void __dev_flush(void);
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -1169,13 +1171,20 @@ static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map
return NULL;
}
-static inline void __dev_map_flush(void)
+static inline void __dev_flush(void)
{
}
struct xdp_buff;
struct bpf_dtab_netdev;
+static inline
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return 0;
+}
+
static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a366a0b64a57..f349e2c0884c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -918,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
return 0;
}
-/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
+/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the
* same cpu context. Further for best results no more than a single map
* for the do_redirect/do_flush pair should be used. This limitation is
* because we only track one map and force a flush when the map changes.
@@ -929,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
int xdp_do_redirect(struct net_device *dev,
struct xdp_buff *xdp,
struct bpf_prog *prog);
-void xdp_do_flush_map(void);
+void xdp_do_flush(void);
+
+/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as
+ * it is no longer only flushing maps. Keep this define for compatibility
+ * until all drivers are updated - do not use xdp_do_flush_map() in new code!
+ */
+#define xdp_do_flush_map xdp_do_flush
void bpf_warn_invalid_xdp_action(u32 act);
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 72bad13d4a3c..b680973687b4 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -79,14 +79,26 @@ TRACE_EVENT(xdp_bulk_tx,
__entry->sent, __entry->drops, __entry->err)
);
+#ifndef __DEVMAP_OBJ_TYPE
+#define __DEVMAP_OBJ_TYPE
+struct _bpf_dtab_netdev {
+ struct net_device *dev;
+};
+#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,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
+ TP_ARGS(dev, xdp, tgt, err, map, index),
TP_STRUCT__entry(
__field(int, prog_id)
@@ -103,90 +115,65 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
__entry->act = XDP_REDIRECT;
__entry->ifindex = dev->ifindex;
__entry->err = err;
- __entry->to_ifindex = to_ifindex;
+ __entry->to_ifindex = map ? devmap_ifindex(tgt, map) :
+ index;
__entry->map_id = map ? map->id : 0;
- __entry->map_index = map_index;
+ __entry->map_index = map ? index : 0;
),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d",
+ TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
+ " map_id=%d map_index=%d",
__entry->prog_id,
__print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
__entry->ifindex, __entry->to_ifindex,
- __entry->err)
+ __entry->err, __entry->map_id, __entry->map_index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
#define _trace_xdp_redirect(dev, xdp, to) \
- trace_xdp_redirect(dev, xdp, to, 0, NULL, 0);
+ trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to);
#define _trace_xdp_redirect_err(dev, xdp, to, err) \
- trace_xdp_redirect_err(dev, xdp, to, err, NULL, 0);
+ trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, 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_err(dev, xdp, to, map, index, err) \
+ trace_xdp_redirect_err(dev, xdp, to, err, map, index);
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map,
+/* 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,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
- " map_id=%d map_index=%d",
- __entry->prog_id,
- __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
- __entry->ifindex, __entry->to_ifindex,
- __entry->err,
- __entry->map_id, __entry->map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
+DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
TP_PROTO(const struct net_device *dev,
const struct bpf_prog *xdp,
- int to_ifindex, int err,
- const struct bpf_map *map, u32 map_index),
- TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
- TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
- " map_id=%d map_index=%d",
- __entry->prog_id,
- __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
- __entry->ifindex, __entry->to_ifindex,
- __entry->err,
- __entry->map_id, __entry->map_index)
+ const void *tgt, int err,
+ const struct bpf_map *map, u32 index),
+ TP_ARGS(dev, xdp, tgt, err, map, index)
);
-#ifndef __DEVMAP_OBJ_TYPE
-#define __DEVMAP_OBJ_TYPE
-struct _bpf_dtab_netdev {
- struct net_device *dev;
-};
-#endif /* __DEVMAP_OBJ_TYPE */
-
-#define devmap_ifindex(fwd, map) \
- ((map->map_type == BPF_MAP_TYPE_DEVMAP || \
- map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ? \
- ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)
-
-#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
- trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
- 0, map, idx)
-
-#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
- trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
- err, map, idx)
-
TRACE_EVENT(xdp_cpumap_kthread,
TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 030d125c3839..d5311009953f 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -81,7 +81,7 @@ struct bpf_dtab {
u32 n_buckets;
};
-static DEFINE_PER_CPU(struct list_head, dev_map_flush_list);
+static DEFINE_PER_CPU(struct list_head, dev_flush_list);
static DEFINE_SPINLOCK(dev_map_lock);
static LIST_HEAD(dev_map_list);
@@ -357,16 +357,16 @@ static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
goto out;
}
-/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
+/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
* from the driver before returning from its napi->poll() routine. The poll()
* routine is called either from busy_poll context or net_rx_action signaled
* from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
* net device can be torn down. On devmap tear down we ensure the flush list
* is empty before completing to ensure all flush operations have completed.
*/
-void __dev_map_flush(void)
+void __dev_flush(void)
{
- struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
+ struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
rcu_read_lock();
@@ -396,9 +396,8 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
*/
static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
struct net_device *dev_rx)
-
{
- struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
+ struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
@@ -419,10 +418,9 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
return 0;
}
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
{
- struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
int err;
@@ -440,6 +438,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return bq_enqueue(dev, xdpf, dev_rx);
}
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return __xdp_enqueue(dev, xdp, dev_rx);
+}
+
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct net_device *dev = dst->dev;
+
+ return __xdp_enqueue(dev, xdp, dev_rx);
+}
+
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
@@ -762,7 +774,7 @@ static int __init dev_map_init(void)
register_netdevice_notifier(&dev_map_notifier);
for_each_possible_cpu(cpu)
- INIT_LIST_HEAD(&per_cpu(dev_map_flush_list, cpu));
+ INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
return 0;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index d6f58dc4e1c4..17de6747d9e3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3458,58 +3458,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
.arg2_type = ARG_ANYTHING,
};
-static int __bpf_tx_xdp(struct net_device *dev,
- struct bpf_map *map,
- struct xdp_buff *xdp,
- u32 index)
-{
- struct xdp_frame *xdpf;
- int err, sent;
-
- if (!dev->netdev_ops->ndo_xdp_xmit) {
- return -EOPNOTSUPP;
- }
-
- err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
- if (unlikely(err))
- return err;
-
- xdpf = convert_to_xdp_frame(xdp);
- if (unlikely(!xdpf))
- return -EOVERFLOW;
-
- sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH);
- if (sent <= 0)
- return sent;
- return 0;
-}
-
-static noinline int
-xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri)
-{
- struct net_device *fwd;
- u32 index = ri->tgt_index;
- int err;
-
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
- ri->tgt_index = 0;
- if (unlikely(!fwd)) {
- err = -EINVAL;
- goto err;
- }
-
- err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
- if (unlikely(err))
- goto err;
-
- _trace_xdp_redirect(dev, xdp_prog, index);
- return 0;
-err:
- _trace_xdp_redirect_err(dev, xdp_prog, index, err);
- return err;
-}
-
static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
struct bpf_map *map, struct xdp_buff *xdp)
{
@@ -3527,13 +3475,13 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
return 0;
}
-void xdp_do_flush_map(void)
+void xdp_do_flush(void)
{
- __dev_map_flush();
+ __dev_flush();
__cpu_map_flush();
__xsk_map_flush();
}
-EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+EXPORT_SYMBOL_GPL(xdp_do_flush);
static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
{
@@ -3568,10 +3516,11 @@ void bpf_clear_redirect_map(struct bpf_map *map)
}
}
-static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog, struct bpf_map *map,
- struct bpf_redirect_info *ri)
+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;
void *fwd = ri->tgt_value;
int err;
@@ -3580,7 +3529,18 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
ri->tgt_value = NULL;
WRITE_ONCE(ri->map, NULL);
- err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+ if (unlikely(!map)) {
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = dev_xdp_enqueue(fwd, xdp, dev);
+ } else {
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+ }
+
if (unlikely(err))
goto err;
@@ -3590,18 +3550,6 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
return err;
}
-
-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);
-
- if (likely(map))
- return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
-
- return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri);
-}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
static int xdp_do_generic_redirect_map(struct net_device *dev,
^ permalink raw reply related [flat|nested] 5+ messages in thread