* [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
2021-05-13 7:04 [PATCH RESEND v11 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-05-13 7:04 ` Hangbin Liu
2021-05-13 22:23 ` John Fastabend
2021-05-14 6:49 ` Jesper Dangaard Brouer
2021-05-13 7:04 ` [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
` (2 subsequent siblings)
3 siblings, 2 replies; 10+ messages in thread
From: Hangbin Liu @ 2021-05-13 7:04 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
From: Jesper Dangaard Brouer <brouer@redhat.com>
This changes the devmap XDP program support to run the program when the
bulk queue is flushed instead of before the frame is enqueued. This has
a couple of benefits:
- It "sorts" the packets by destination devmap entry, and then runs the
same BPF program on all the packets in sequence. This ensures that we
keep the XDP program and destination device properties hot in I-cache.
- It makes the multicast implementation simpler because it can just
enqueue packets using bq_enqueue() without having to deal with the
devmap program at all.
The drawback is that if the devmap program drops the packet, the enqueue
step is redundant. However, arguably this is mostly visible in a
micro-benchmark, and with more mixed traffic the I-cache benefit should
win out. The performance impact of just this patch is as follows:
Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface,
which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send
pkts via pktgen cmd:
./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
There are about +/- 0.1M deviation for native testing, the performance
improved for the base-case, but some drop back with xdp devmap prog attached.
Version | Test | Generic | Native | Native + 2nd xdp_prog
5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M
5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M
5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M
5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M
When bq_xmit_all() is called from bq_enqueue(), another packet will
always be enqueued immediately after, so clearing dev_rx, xdp_prog and
flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(),
and only check them once in bq_enqueue() since they are all modified
together.
This change also has the side effect of extending the lifetime of the
RCU-protected xdp_prog that lives inside the devmap entries: Instead of
just living for the duration of the XDP program invocation, the
reference now lives all the way until the bq is flushed. This is safe
because the bq flush happens at the end of the NAPI poll loop, so
everything happens between a local_bh_disable()/local_bh_enable() pair.
However, this is by no means obvious from looking at the call sites; in
particular, some drivers have an additional rcu_read_lock() around only
the XDP program invocation, which only confuses matters further.
Cleaning this up will be done in a separate patch series.
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v9: update commit description based on Toke and Martin's suggestion
v4-v8: no update
v3: rebase the code based on Lorenzo's "Move drop error path to devmap
for XDP_REDIRECT"
v2: no update
---
kernel/bpf/devmap.c | 127 ++++++++++++++++++++++++++------------------
1 file changed, 76 insertions(+), 51 deletions(-)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index aa516472ce46..3980fb3bfb09 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -57,6 +57,7 @@ struct xdp_dev_bulk_queue {
struct list_head flush_node;
struct net_device *dev;
struct net_device *dev_rx;
+ struct bpf_prog *xdp_prog;
unsigned int count;
};
@@ -326,22 +327,71 @@ bool dev_map_can_have_prog(struct bpf_map *map)
return false;
}
+static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
+ struct xdp_frame **frames, int n,
+ struct net_device *dev)
+{
+ struct xdp_txq_info txq = { .dev = dev };
+ struct xdp_buff xdp;
+ int i, nframes = 0;
+
+ for (i = 0; i < n; i++) {
+ struct xdp_frame *xdpf = frames[i];
+ u32 act;
+ int err;
+
+ xdp_convert_frame_to_buff(xdpf, &xdp);
+ xdp.txq = &txq;
+
+ act = bpf_prog_run_xdp(xdp_prog, &xdp);
+ switch (act) {
+ case XDP_PASS:
+ err = xdp_update_frame_from_buff(&xdp, xdpf);
+ if (unlikely(err < 0))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ frames[nframes++] = xdpf;
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ fallthrough;
+ case XDP_ABORTED:
+ trace_xdp_exception(dev, xdp_prog, act);
+ fallthrough;
+ case XDP_DROP:
+ xdp_return_frame_rx_napi(xdpf);
+ break;
+ }
+ }
+ return nframes; /* sent frames count */
+}
+
static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
{
struct net_device *dev = bq->dev;
- int sent = 0, err = 0;
+ int sent = 0, drops = 0, err = 0;
+ unsigned int cnt = bq->count;
+ int to_send = cnt;
int i;
- if (unlikely(!bq->count))
+ if (unlikely(!cnt))
return;
- for (i = 0; i < bq->count; i++) {
+ for (i = 0; i < cnt; i++) {
struct xdp_frame *xdpf = bq->q[i];
prefetch(xdpf);
}
- sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags);
+ if (bq->xdp_prog) {
+ to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
+ if (!to_send)
+ goto out;
+
+ drops = cnt - to_send;
+ }
+
+ sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
if (sent < 0) {
/* If ndo_xdp_xmit fails with an errno, no frames have
* been xmit'ed.
@@ -353,13 +403,13 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
/* If not all frames have been transmitted, it is our
* responsibility to free them
*/
- for (i = sent; unlikely(i < bq->count); i++)
+ for (i = sent; unlikely(i < to_send); i++)
xdp_return_frame_rx_napi(bq->q[i]);
- trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, bq->count - sent, err);
- bq->dev_rx = NULL;
+out:
+ drops = cnt - sent;
bq->count = 0;
- __list_del_clearprev(&bq->flush_node);
+ trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
}
/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
@@ -377,8 +427,12 @@ void __dev_flush(void)
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq, *tmp;
- list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+ list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
bq_xmit_all(bq, XDP_XMIT_FLUSH);
+ bq->dev_rx = NULL;
+ bq->xdp_prog = NULL;
+ __list_del_clearprev(&bq->flush_node);
+ }
}
/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
@@ -401,7 +455,7 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
* Thus, safe percpu variable access.
*/
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
- struct net_device *dev_rx)
+ struct net_device *dev_rx, struct bpf_prog *xdp_prog)
{
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
@@ -412,18 +466,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
* from net_device drivers NAPI func end.
+ *
+ * Do the same with xdp_prog and flush_list since these fields
+ * are only ever modified together.
*/
- if (!bq->dev_rx)
+ if (!bq->dev_rx) {
bq->dev_rx = dev_rx;
+ bq->xdp_prog = xdp_prog;
+ list_add(&bq->flush_node, flush_list);
+ }
bq->q[bq->count++] = xdpf;
-
- if (!bq->flush_node.prev)
- list_add(&bq->flush_node, flush_list);
}
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
- struct net_device *dev_rx)
+ struct net_device *dev_rx,
+ struct bpf_prog *xdp_prog)
{
struct xdp_frame *xdpf;
int err;
@@ -439,42 +497,14 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
if (unlikely(!xdpf))
return -EOVERFLOW;
- bq_enqueue(dev, xdpf, dev_rx);
+ bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
return 0;
}
-static struct xdp_buff *dev_map_run_prog(struct net_device *dev,
- struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog)
-{
- struct xdp_txq_info txq = { .dev = dev };
- u32 act;
-
- xdp_set_data_meta_invalid(xdp);
- xdp->txq = &txq;
-
- act = bpf_prog_run_xdp(xdp_prog, xdp);
- switch (act) {
- case XDP_PASS:
- return xdp;
- case XDP_DROP:
- break;
- default:
- bpf_warn_invalid_xdp_action(act);
- fallthrough;
- case XDP_ABORTED:
- trace_xdp_exception(dev, xdp_prog, act);
- break;
- }
-
- xdp_return_buff(xdp);
- return NULL;
-}
-
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
- return __xdp_enqueue(dev, xdp, dev_rx);
+ return __xdp_enqueue(dev, xdp, dev_rx, NULL);
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
@@ -482,12 +512,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
- if (dst->xdp_prog) {
- xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog);
- if (!xdp)
- return 0;
- }
- return __xdp_enqueue(dev, xdp, dev_rx);
+ return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
}
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
--
2.26.3
^ permalink raw reply related [flat|nested] 10+ messages in thread* RE: [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
2021-05-13 7:04 ` [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
@ 2021-05-13 22:23 ` John Fastabend
2021-05-14 6:49 ` Jesper Dangaard Brouer
1 sibling, 0 replies; 10+ messages in thread
From: John Fastabend @ 2021-05-13 22:23 UTC (permalink / raw)
To: Hangbin Liu, bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
Hangbin Liu wrote:
> From: Jesper Dangaard Brouer <brouer@redhat.com>
>
> This changes the devmap XDP program support to run the program when the
> bulk queue is flushed instead of before the frame is enqueued. This has
> a couple of benefits:
>
> - It "sorts" the packets by destination devmap entry, and then runs the
> same BPF program on all the packets in sequence. This ensures that we
> keep the XDP program and destination device properties hot in I-cache.
>
> - It makes the multicast implementation simpler because it can just
> enqueue packets using bq_enqueue() without having to deal with the
> devmap program at all.
>
> The drawback is that if the devmap program drops the packet, the enqueue
> step is redundant. However, arguably this is mostly visible in a
> micro-benchmark, and with more mixed traffic the I-cache benefit should
> win out. The performance impact of just this patch is as follows:
>
> Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface,
> which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send
> pkts via pktgen cmd:
> ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>
> There are about +/- 0.1M deviation for native testing, the performance
> improved for the base-case, but some drop back with xdp devmap prog attached.
>
> Version | Test | Generic | Native | Native + 2nd xdp_prog
> 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M
> 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M
> 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M
> 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M
>
> When bq_xmit_all() is called from bq_enqueue(), another packet will
> always be enqueued immediately after, so clearing dev_rx, xdp_prog and
> flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(),
> and only check them once in bq_enqueue() since they are all modified
> together.
>
> This change also has the side effect of extending the lifetime of the
> RCU-protected xdp_prog that lives inside the devmap entries: Instead of
> just living for the duration of the XDP program invocation, the
> reference now lives all the way until the bq is flushed. This is safe
> because the bq flush happens at the end of the NAPI poll loop, so
> everything happens between a local_bh_disable()/local_bh_enable() pair.
> However, this is by no means obvious from looking at the call sites; in
> particular, some drivers have an additional rcu_read_lock() around only
> the XDP program invocation, which only confuses matters further.
> Cleaning this up will be done in a separate patch series.
>
> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
>
Acked-by: John Fastabend <john.fastabend@gmail.com>
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue
2021-05-13 7:04 ` [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
2021-05-13 22:23 ` John Fastabend
@ 2021-05-14 6:49 ` Jesper Dangaard Brouer
1 sibling, 0 replies; 10+ messages in thread
From: Jesper Dangaard Brouer @ 2021-05-14 6:49 UTC (permalink / raw)
To: Hangbin Liu
Cc: bpf, netdev, Toke Høiland-Jørgensen, Jiri Benc,
Eelco Chaudron, ast, Daniel Borkmann, Lorenzo Bianconi,
David Ahern, Andrii Nakryiko, Alexei Starovoitov, John Fastabend,
Maciej Fijalkowski, Björn Töpel, Martin KaFai Lau,
brouer
On Thu, 13 May 2021 15:04:44 +0800
Hangbin Liu <liuhangbin@gmail.com> wrote:
> From: Jesper Dangaard Brouer <brouer@redhat.com>
>
> This changes the devmap XDP program support to run the program when the
> bulk queue is flushed instead of before the frame is enqueued. This has
> a couple of benefits:
>
> - It "sorts" the packets by destination devmap entry, and then runs the
> same BPF program on all the packets in sequence. This ensures that we
> keep the XDP program and destination device properties hot in I-cache.
>
> - It makes the multicast implementation simpler because it can just
> enqueue packets using bq_enqueue() without having to deal with the
> devmap program at all.
>
> The drawback is that if the devmap program drops the packet, the enqueue
> step is redundant. However, arguably this is mostly visible in a
> micro-benchmark, and with more mixed traffic the I-cache benefit should
> win out. The performance impact of just this patch is as follows:
>
> Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface,
> which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send
> pkts via pktgen cmd:
> ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64
>
> There are about +/- 0.1M deviation for native testing, the performance
> improved for the base-case, but some drop back with xdp devmap prog attached.
>
> Version | Test | Generic | Native | Native + 2nd xdp_prog
> 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M
> 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M
> 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M
> 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M
>
> When bq_xmit_all() is called from bq_enqueue(), another packet will
> always be enqueued immediately after, so clearing dev_rx, xdp_prog and
> flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(),
> and only check them once in bq_enqueue() since they are all modified
> together.
>
> This change also has the side effect of extending the lifetime of the
> RCU-protected xdp_prog that lives inside the devmap entries: Instead of
> just living for the duration of the XDP program invocation, the
> reference now lives all the way until the bq is flushed. This is safe
> because the bq flush happens at the end of the NAPI poll loop, so
> everything happens between a local_bh_disable()/local_bh_enable() pair.
> However, this is by no means obvious from looking at the call sites; in
> particular, some drivers have an additional rcu_read_lock() around only
> the XDP program invocation, which only confuses matters further.
> Cleaning this up will be done in a separate patch series.
>
> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
For the sake of good order
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-05-13 7:04 [PATCH RESEND v11 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-05-13 7:04 ` [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
@ 2021-05-13 7:04 ` Hangbin Liu
2021-05-13 20:01 ` John Fastabend
2021-05-18 20:36 ` Daniel Borkmann
2021-05-13 7:04 ` [PATCH RESEND v11 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test Hangbin Liu
2021-05-13 7:04 ` [PATCH RESEND v11 4/4] selftests/bpf: add xdp_redirect_multi test Hangbin Liu
3 siblings, 2 replies; 10+ messages in thread
From: Hangbin Liu @ 2021-05-13 7:04 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
extend xdp_redirect_map for broadcast support.
With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces
in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be
excluded when do broadcasting.
When getting the devices in dev hash map via dev_map_hash_get_next_key(),
there is a possibility that we fall back to the first key when a device
was removed. This will duplicate packets on some interfaces. So just walk
the whole buckets to avoid this issue. For dev array map, we also walk the
whole map to find valid interfaces.
Function bpf_clear_redirect_map() was removed in
commit ee75aef23afe ("bpf, xdp: Restructure redirect actions").
Add it back as we need to use ri->map again.
With test topology:
+-------------------+ +-------------------+
| Host A (i40e 10G) | ---------- | eno1(i40e 10G) |
+-------------------+ | |
| Host B |
+-------------------+ | |
| Host C (i40e 10G) | ---------- | eno2(i40e 10G) |
+-------------------+ | |
| +------+ |
| veth0 -- | Peer | |
| veth1 -- | | |
| veth2 -- | NS | |
| +------+ |
+-------------------+
On Host A:
# pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64
On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory):
Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing.
All the veth peers in the NS have a XDP_DROP program loaded. The
forward_map max_entries in xdp_redirect_map_multi is modify to 4.
Testing the performance impact on the regular xdp_redirect path with and
without patch (to check impact of additional check for broadcast mode):
5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M
5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M
5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M
Testing the performance when cloning packets with the redirect_map_multi
test, using a redirect map size of 4, filled with 1-3 devices:
5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M
5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M
5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v11:
a) Use unlikely() when checking if this is for broadcast redirecting.
b) Fix the tracepoint NULL pointer issue Jesper found
c) Remove BPF_F_REDIR_MASK and just use OR flags to make the reader more
clear about what's going on
d) Add the performace number with multi veth interfaces in commit
description.
v10:
Remind by Jesper: revert xchg() and use READ/WRITE_ONCE when read/write map
pointer as xchg call can be expensive, since this is an atomic operation.
v9: no update
v8:
use hlist_for_each_entry_rcu() when loop the devmap hash ojbs
v7:
no need to free xdpf in dev_map_enqueue_clone() if xdpf_clone failed.
Also return -EOVERFLOW if xdp_convert_buff_to_frame() failed the same
as other caller did.
v6:
Fix a skb leak in the error path for generic XDP
v5:
a) use xchg() instead of READ/WRITE_ONCE and no need to clear ri->flags
in xdp_do_redirect()
b) Do not use get_next_key() as we may restart looping from the first key
when remove/update a dev in hash map. Just walk the map directly to
get all the devices and ignore the new added/deleted objects.
c) Loop all the array map instead stop at the first hole.
v4:
a) add a new argument flag_mask to __bpf_xdp_redirect_map() filter out
invalid map.
b) __bpf_xdp_redirect_map() sets the map pointer if the broadcast flag
is set and clears it if the flag isn't set
c) xdp_do_redirect() does the READ_ONCE/WRITE_ONCE on ri->map to check
if we should enqueue multi
v3:
a) Rebase the code on Björn's "bpf, xdp: Restructure redirect actions".
- Add struct bpf_map *map back to struct bpf_redirect_info as we need
it for multicast.
- Add bpf_clear_redirect_map() back for devmap.c
- Add devmap_lookup_elem() as we need it in general path.
b) remove tmp_key in devmap_get_next_obj()
v2: Fix flag renaming issue in v1
---
include/linux/bpf.h | 20 ++++
include/linux/filter.h | 18 +++-
include/net/xdp.h | 1 +
include/trace/events/xdp.h | 6 +-
include/uapi/linux/bpf.h | 16 ++-
kernel/bpf/cpumap.c | 3 +-
kernel/bpf/devmap.c | 183 ++++++++++++++++++++++++++++++++-
net/core/filter.c | 37 ++++++-
net/core/xdp.c | 29 ++++++
net/xdp/xskmap.c | 3 +-
tools/include/uapi/linux/bpf.h | 16 ++-
11 files changed, 317 insertions(+), 15 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 02b02cb29ce2..f6bd89712128 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1499,8 +1499,13 @@ 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_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress);
bool dev_map_can_have_prog(struct bpf_map *map);
void __cpu_map_flush(void);
@@ -1668,6 +1673,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return 0;
}
+static inline
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
+{
+ return 0;
+}
+
struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
@@ -1677,6 +1689,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
return 0;
}
+static inline
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress)
+{
+ return 0;
+}
+
static inline void __cpu_map_flush(void)
{
}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9a09547bc7ba..e4885b42d754 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -646,6 +646,7 @@ 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;
@@ -1464,17 +1465,18 @@ 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,
+static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex,
+ u64 flags, u64 flag_mask,
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))
+ if (unlikely(flags & ~(BPF_F_ACTION_MASK | flag_mask)))
return XDP_ABORTED;
ri->tgt_value = lookup_elem(map, ifindex);
- if (unlikely(!ri->tgt_value)) {
+ if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) {
/* 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
@@ -1482,13 +1484,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
*/
ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
ri->map_type = BPF_MAP_TYPE_UNSPEC;
- return flags;
+ return flags & BPF_F_ACTION_MASK;
}
ri->tgt_index = ifindex;
ri->map_id = map->id;
ri->map_type = map->map_type;
+ if (flags & BPF_F_BROADCAST) {
+ WRITE_ONCE(ri->map, map);
+ ri->flags = flags;
+ } else {
+ WRITE_ONCE(ri->map, NULL);
+ ri->flags = 0;
+ }
+
return XDP_REDIRECT;
}
diff --git a/include/net/xdp.h b/include/net/xdp.h
index a5bc214a49d9..5533f0ab2afc 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
struct net_device *dev);
int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
static inline
void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index fcad3645a70b..c40fc97f9417 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
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;
+ /* Just leave to_ifindex to 0 if do broadcast redirect,
+ * as tgt will be NULL.
+ */
+ if (tgt)
+ 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;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ec6d85a81744..78d1ec401b3a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2534,8 +2534,12 @@ union bpf_attr {
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
* one of the XDP program return codes up to **XDP_TX**, as chosen
- * by the caller. Any higher bits in the *flags* argument must be
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -5080,6 +5084,14 @@ enum {
BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
};
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
+#define BPF_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 5dd3e866599a..a1a0c4e791c6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -601,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
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);
+ return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+ __cpu_map_lookup_elem);
}
static int cpu_map_btf_id;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 3980fb3bfb09..5262a62355a1 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -198,6 +198,7 @@ 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. */
@@ -515,6 +516,99 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
}
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
+ int exclude_ifindex)
+{
+ if (!obj || obj->dev->ifindex == exclude_ifindex ||
+ !obj->dev->netdev_ops->ndo_xdp_xmit)
+ return false;
+
+ if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
+ return false;
+
+ return true;
+}
+
+static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
+ struct net_device *dev_rx,
+ struct xdp_frame *xdpf)
+{
+ struct xdp_frame *nxdpf;
+
+ nxdpf = xdpf_clone(xdpf);
+ if (!nxdpf)
+ return -ENOMEM;
+
+ bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
+
+ return 0;
+}
+
+int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
+ struct bpf_map *map, bool exclude_ingress)
+{
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct xdp_frame *xdpf;
+ unsigned int i;
+ int err;
+
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+ return -EOVERFLOW;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_rcu(dst, head, index_hlist,
+ lockdep_is_held(&dtab->index_lock)) {
+ if (!is_valid_dst(dst, xdp, exclude_ifindex))
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
+ }
+
+ /* consume the last copy of the frame */
+ if (last_dst)
+ bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
+ else
+ xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
+
+ return 0;
+}
+
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
@@ -529,6 +623,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
return 0;
}
+static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
+ struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct sk_buff *nskb;
+ int err;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ return -ENOMEM;
+
+ err = dev_map_generic_redirect(dst, nskb, xdp_prog);
+ if (unlikely(err)) {
+ consume_skb(nskb);
+ return err;
+ }
+
+ return 0;
+}
+
+int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog, struct bpf_map *map,
+ bool exclude_ingress)
+{
+ struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
+ int exclude_ifindex = exclude_ingress ? dev->ifindex : 0;
+ struct bpf_dtab_netdev *dst, *last_dst = NULL;
+ struct hlist_head *head;
+ struct hlist_node *next;
+ unsigned int i;
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ for (i = 0; i < map->max_entries; i++) {
+ dst = READ_ONCE(dtab->netdev_map[i]);
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ } else { /* BPF_MAP_TYPE_DEVMAP_HASH */
+ for (i = 0; i < dtab->n_buckets; i++) {
+ head = dev_map_index_hash(dtab, i);
+ hlist_for_each_entry_safe(dst, next, head, index_hlist) {
+ if (!dst || dst->dev->ifindex == exclude_ifindex)
+ continue;
+
+ /* we only need n-1 clones; last_dst enqueued below */
+ if (!last_dst) {
+ last_dst = dst;
+ continue;
+ }
+
+ err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
+ if (err)
+ return err;
+
+ last_dst = dst;
+ }
+ }
+ }
+
+ /* consume the first skb and return */
+ if (last_dst)
+ return dev_map_generic_redirect(last_dst, skb, xdp_prog);
+
+ /* dtab is empty */
+ consume_skb(skb);
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -755,12 +930,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
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);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __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);
+ return __bpf_xdp_redirect_map(map, ifindex, flags,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
+ __dev_map_hash_lookup_elem);
}
static int dev_map_btf_id;
diff --git a/net/core/filter.c b/net/core/filter.c
index cae56d08a670..04848de3e058 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3926,6 +3926,23 @@ void xdp_do_flush(void)
}
EXPORT_SYMBOL_GPL(xdp_do_flush);
+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)
{
@@ -3933,6 +3950,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
+ struct bpf_map *map;
int err;
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
@@ -3942,7 +3960,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_enqueue(fwd, xdp, dev);
+ map = READ_ONCE(ri->map);
+ if (unlikely(map)) {
+ WRITE_ONCE(ri->map, NULL);
+ err = dev_map_enqueue_multi(xdp, dev, map,
+ ri->flags & BPF_F_EXCLUDE_INGRESS);
+ } else {
+ err = dev_map_enqueue(fwd, xdp, dev);
+ }
break;
case BPF_MAP_TYPE_CPUMAP:
err = cpu_map_enqueue(fwd, xdp, dev);
@@ -3984,13 +4009,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
enum bpf_map_type map_type, u32 map_id)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ struct bpf_map *map;
int err;
switch (map_type) {
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+ map = READ_ONCE(ri->map);
+ if (unlikely(map)) {
+ WRITE_ONCE(ri->map, NULL);
+ err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
+ ri->flags & BPF_F_EXCLUDE_INGRESS);
+ } else {
+ err = dev_map_generic_redirect(fwd, skb, xdp_prog);
+ }
if (unlikely(err))
goto err;
break;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 858276e72c68..b33f4c4b6d65 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -584,3 +584,32 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
return __xdp_build_skb_from_frame(xdpf, skb, dev);
}
EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
+
+struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
+{
+ unsigned int headroom, totalsize;
+ struct xdp_frame *nxdpf;
+ struct page *page;
+ void *addr;
+
+ headroom = xdpf->headroom + sizeof(*xdpf);
+ totalsize = headroom + xdpf->len;
+
+ if (unlikely(totalsize > PAGE_SIZE))
+ return NULL;
+ page = dev_alloc_page();
+ if (!page)
+ return NULL;
+ addr = page_to_virt(page);
+
+ memcpy(addr, xdpf, totalsize);
+
+ nxdpf = addr;
+ nxdpf->data = addr + headroom;
+ nxdpf->frame_sz = PAGE_SIZE;
+ nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
+ nxdpf->mem.id = 0;
+
+ return nxdpf;
+}
+EXPORT_SYMBOL_GPL(xdpf_clone);
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 67b4ce504852..9df75ea4a567 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
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);
+ return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+ __xsk_map_lookup_elem);
}
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ec6d85a81744..78d1ec401b3a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2534,8 +2534,12 @@ union bpf_attr {
* The lower two bits of *flags* are used as the return code if
* the map lookup fails. This is so that the return value can be
* one of the XDP program return codes up to **XDP_TX**, as chosen
- * by the caller. Any higher bits in the *flags* argument must be
- * unset.
+ * by the caller. The higher bits of *flags* can be set to
+ * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
+ *
+ * With BPF_F_BROADCAST the packet will be broadcasted to all the
+ * interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress
+ * interface will be excluded when do broadcasting.
*
* See also **bpf_redirect**\ (), which only supports redirecting
* to an ifindex, but doesn't require a map to do so.
@@ -5080,6 +5084,14 @@ enum {
BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
};
+/* Flags for bpf_redirect_map helper */
+enum {
+ BPF_F_BROADCAST = (1ULL << 3),
+ BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
+};
+
+#define BPF_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
+
#define __bpf_md_ptr(type, name) \
union { \
type name; \
--
2.26.3
^ permalink raw reply related [flat|nested] 10+ messages in thread* RE: [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-05-13 7:04 ` [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-05-13 20:01 ` John Fastabend
2021-05-14 6:21 ` Jesper Dangaard Brouer
2021-05-18 20:36 ` Daniel Borkmann
1 sibling, 1 reply; 10+ messages in thread
From: John Fastabend @ 2021-05-13 20:01 UTC (permalink / raw)
To: Hangbin Liu, bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
Hangbin Liu wrote:
> This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
> extend xdp_redirect_map for broadcast support.
>
> With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces
> in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be
> excluded when do broadcasting.
>
> When getting the devices in dev hash map via dev_map_hash_get_next_key(),
> there is a possibility that we fall back to the first key when a device
> was removed. This will duplicate packets on some interfaces. So just walk
> the whole buckets to avoid this issue. For dev array map, we also walk the
> whole map to find valid interfaces.
>
> Function bpf_clear_redirect_map() was removed in
> commit ee75aef23afe ("bpf, xdp: Restructure redirect actions").
> Add it back as we need to use ri->map again.
>
> With test topology:
> +-------------------+ +-------------------+
> | Host A (i40e 10G) | ---------- | eno1(i40e 10G) |
> +-------------------+ | |
> | Host B |
> +-------------------+ | |
> | Host C (i40e 10G) | ---------- | eno2(i40e 10G) |
> +-------------------+ | |
> | +------+ |
> | veth0 -- | Peer | |
> | veth1 -- | | |
> | veth2 -- | NS | |
> | +------+ |
> +-------------------+
>
> On Host A:
> # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64
>
> On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory):
> Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing.
> All the veth peers in the NS have a XDP_DROP program loaded. The
> forward_map max_entries in xdp_redirect_map_multi is modify to 4.
>
> Testing the performance impact on the regular xdp_redirect path with and
> without patch (to check impact of additional check for broadcast mode):
>
> 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M
> 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M
> 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
> 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M
>
> Testing the performance when cloning packets with the redirect_map_multi
> test, using a redirect map size of 4, filled with 1-3 devices:
>
> 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M
> 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M
> 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M
>
> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
> Acked-by: Martin KaFai Lau <kafai@fb.com>
> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
[...]
LGTM thanks for sticking with it.
Acked-by: John Fastabend <john.fastabend@gmail.com>
^ permalink raw reply [flat|nested] 10+ messages in thread* Re: [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-05-13 20:01 ` John Fastabend
@ 2021-05-14 6:21 ` Jesper Dangaard Brouer
0 siblings, 0 replies; 10+ messages in thread
From: Jesper Dangaard Brouer @ 2021-05-14 6:21 UTC (permalink / raw)
To: John Fastabend
Cc: Hangbin Liu, bpf, netdev, Toke Høiland-Jørgensen,
Jiri Benc, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, Maciej Fijalkowski, Björn Töpel,
Martin KaFai Lau, brouer
On Thu, 13 May 2021 13:01:16 -0700
John Fastabend <john.fastabend@gmail.com> wrote:
> Hangbin Liu wrote:
> > This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
> > extend xdp_redirect_map for broadcast support.
> >
> > With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces
> > in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be
> > excluded when do broadcasting.
> >
> > When getting the devices in dev hash map via dev_map_hash_get_next_key(),
> > there is a possibility that we fall back to the first key when a device
> > was removed. This will duplicate packets on some interfaces. So just walk
> > the whole buckets to avoid this issue. For dev array map, we also walk the
> > whole map to find valid interfaces.
> >
> > Function bpf_clear_redirect_map() was removed in
> > commit ee75aef23afe ("bpf, xdp: Restructure redirect actions").
> > Add it back as we need to use ri->map again.
> >
> > With test topology:
> > +-------------------+ +-------------------+
> > | Host A (i40e 10G) | ---------- | eno1(i40e 10G) |
> > +-------------------+ | |
> > | Host B |
> > +-------------------+ | |
> > | Host C (i40e 10G) | ---------- | eno2(i40e 10G) |
> > +-------------------+ | |
> > | +------+ |
> > | veth0 -- | Peer | |
> > | veth1 -- | | |
> > | veth2 -- | NS | |
> > | +------+ |
> > +-------------------+
> >
> > On Host A:
> > # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64
> >
> > On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory):
> > Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing.
> > All the veth peers in the NS have a XDP_DROP program loaded. The
> > forward_map max_entries in xdp_redirect_map_multi is modify to 4.
> >
> > Testing the performance impact on the regular xdp_redirect path with and
> > without patch (to check impact of additional check for broadcast mode):
> >
> > 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M
> > 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M
> > 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M
> > 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M
> >
> > Testing the performance when cloning packets with the redirect_map_multi
> > test, using a redirect map size of 4, filled with 1-3 devices:
> >
> > 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M
> > 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M
> > 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M
> >
> > Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
> > Acked-by: Martin KaFai Lau <kafai@fb.com>
> > Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
>
> [...]
>
> LGTM thanks for sticking with it.
+1
> Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support
2021-05-13 7:04 ` [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-05-13 20:01 ` John Fastabend
@ 2021-05-18 20:36 ` Daniel Borkmann
1 sibling, 0 replies; 10+ messages in thread
From: Daniel Borkmann @ 2021-05-18 20:36 UTC (permalink / raw)
To: Hangbin Liu, bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Lorenzo Bianconi,
David Ahern, Andrii Nakryiko, Alexei Starovoitov, John Fastabend,
Maciej Fijalkowski, Björn Töpel, Martin KaFai Lau
On 5/13/21 9:04 AM, Hangbin Liu wrote:
> This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to
> extend xdp_redirect_map for broadcast support.
Just few minor bits, other than that it's good to go, imho:
> -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags,
> +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex,
> + u64 flags, u64 flag_mask,
nit: const u64 flag_mask
> 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))
> + if (unlikely(flags & ~(BPF_F_ACTION_MASK | flag_mask)))
> return XDP_ABORTED;
>
> ri->tgt_value = lookup_elem(map, ifindex);
> - if (unlikely(!ri->tgt_value)) {
> + if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) {
> /* 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
> @@ -1482,13 +1484,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind
> */
> ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */
> ri->map_type = BPF_MAP_TYPE_UNSPEC;
> - return flags;
> + return flags & BPF_F_ACTION_MASK;
> }
>
> ri->tgt_index = ifindex;
> ri->map_id = map->id;
> ri->map_type = map->map_type;
>
> + if (flags & BPF_F_BROADCAST) {
> + WRITE_ONCE(ri->map, map);
> + ri->flags = flags;
> + } else {
> + WRITE_ONCE(ri->map, NULL);
> + ri->flags = 0;
> + }
> +
> return XDP_REDIRECT;
> }
>
[...]
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index ec6d85a81744..78d1ec401b3a 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2534,8 +2534,12 @@ union bpf_attr {
> * The lower two bits of *flags* are used as the return code if
> * the map lookup fails. This is so that the return value can be
> * one of the XDP program return codes up to **XDP_TX**, as chosen
> - * by the caller. Any higher bits in the *flags* argument must be
> - * unset.
> + * by the caller. The higher bits of *flags* can be set to
> + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below.
> + *
> + * With BPF_F_BROADCAST the packet will be broadcasted to all the
> + * interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress
nit: in the map, with
> + * interface will be excluded when do broadcasting.
> *
> * See also **bpf_redirect**\ (), which only supports redirecting
> * to an ifindex, but doesn't require a map to do so.
> @@ -5080,6 +5084,14 @@ enum {
> BPF_F_BPRM_SECUREEXEC = (1ULL << 0),
> };
>
> +/* Flags for bpf_redirect_map helper */
> +enum {
> + BPF_F_BROADCAST = (1ULL << 3),
> + BPF_F_EXCLUDE_INGRESS = (1ULL << 4),
> +};
> +
> +#define BPF_F_ACTION_MASK (XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX)
Why do we need to expose BPF_F_ACTION_MASK into the uapi header here?
My understanding is that this is only needed kernel-internal (and therefore
the mask itself has no meaning for a user)?
> #define __bpf_md_ptr(type, name) \
> union { \
> type name; \
> diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
> index 5dd3e866599a..a1a0c4e791c6 100644
> --- a/kernel/bpf/cpumap.c
> +++ b/kernel/bpf/cpumap.c
> @@ -601,7 +601,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
>
> 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);
> + return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
> + __cpu_map_lookup_elem);
> }
>
> static int cpu_map_btf_id;
> diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> index 3980fb3bfb09..5262a62355a1 100644
> --- a/kernel/bpf/devmap.c
> +++ b/kernel/bpf/devmap.c
> @@ -198,6 +198,7 @@ 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. */
> @@ -515,6 +516,99 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
> return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
> }
>
> +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
> + int exclude_ifindex)
> +{
> + if (!obj || obj->dev->ifindex == exclude_ifindex ||
> + !obj->dev->netdev_ops->ndo_xdp_xmit)
> + return false;
> +
> + if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
> + return false;
> +
> + return true;
> +}
> +
> +static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
> + struct net_device *dev_rx,
> + struct xdp_frame *xdpf)
> +{
> + struct xdp_frame *nxdpf;
> +
> + nxdpf = xdpf_clone(xdpf);
> + if (!nxdpf)
> + return -ENOMEM;
> +
> + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
> +
> + return 0;
> +}
> +
[...]
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index 858276e72c68..b33f4c4b6d65 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -584,3 +584,32 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
> return __xdp_build_skb_from_frame(xdpf, skb, dev);
> }
> EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame);
> +
> +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf)
> +{
> + unsigned int headroom, totalsize;
> + struct xdp_frame *nxdpf;
> + struct page *page;
> + void *addr;
> +
> + headroom = xdpf->headroom + sizeof(*xdpf);
> + totalsize = headroom + xdpf->len;
> +
> + if (unlikely(totalsize > PAGE_SIZE))
> + return NULL;
> + page = dev_alloc_page();
> + if (!page)
> + return NULL;
> + addr = page_to_virt(page);
> +
> + memcpy(addr, xdpf, totalsize);
> +
> + nxdpf = addr;
> + nxdpf->data = addr + headroom;
> + nxdpf->frame_sz = PAGE_SIZE;
> + nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
> + nxdpf->mem.id = 0;
> +
> + return nxdpf;
> +}
> +EXPORT_SYMBOL_GPL(xdpf_clone);
This doesn't have a module user, why it needs to be exported?
> diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
> index 67b4ce504852..9df75ea4a567 100644
> --- a/net/xdp/xskmap.c
> +++ b/net/xdp/xskmap.c
> @@ -226,7 +226,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
>
> 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);
> + return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
> + __xsk_map_lookup_elem);
> }
>
> void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
Thanks,
Daniel
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH RESEND v11 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test
2021-05-13 7:04 [PATCH RESEND v11 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
2021-05-13 7:04 ` [PATCH RESEND v11 1/4] bpf: run devmap xdp_prog on flush instead of bulk enqueue Hangbin Liu
2021-05-13 7:04 ` [PATCH RESEND v11 2/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
@ 2021-05-13 7:04 ` Hangbin Liu
2021-05-13 7:04 ` [PATCH RESEND v11 4/4] selftests/bpf: add xdp_redirect_multi test Hangbin Liu
3 siblings, 0 replies; 10+ messages in thread
From: Hangbin Liu @ 2021-05-13 7:04 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
This is a sample for xdp redirect broadcast. In the sample we could forward
all packets between given interfaces. There is also an option -X that could
enable 2nd xdp_prog on egress interface.
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
samples/bpf/Makefile | 3 +
samples/bpf/xdp_redirect_map_multi_kern.c | 88 +++++++
samples/bpf/xdp_redirect_map_multi_user.c | 302 ++++++++++++++++++++++
3 files changed, 393 insertions(+)
create mode 100644 samples/bpf/xdp_redirect_map_multi_kern.c
create mode 100644 samples/bpf/xdp_redirect_map_multi_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 45ceca4e2c70..520434ea966f 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -41,6 +41,7 @@ tprogs-y += test_map_in_map
tprogs-y += per_socket_stats_example
tprogs-y += xdp_redirect
tprogs-y += xdp_redirect_map
+tprogs-y += xdp_redirect_map_multi
tprogs-y += xdp_redirect_cpu
tprogs-y += xdp_monitor
tprogs-y += xdp_rxq_info
@@ -99,6 +100,7 @@ test_map_in_map-objs := test_map_in_map_user.o
per_socket_stats_example-objs := cookie_uid_helper_example.o
xdp_redirect-objs := xdp_redirect_user.o
xdp_redirect_map-objs := xdp_redirect_map_user.o
+xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o
xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o
xdp_monitor-objs := xdp_monitor_user.o
xdp_rxq_info-objs := xdp_rxq_info_user.o
@@ -160,6 +162,7 @@ always-y += tcp_tos_reflect_kern.o
always-y += tcp_dumpstats_kern.o
always-y += xdp_redirect_kern.o
always-y += xdp_redirect_map_kern.o
+always-y += xdp_redirect_map_multi_kern.o
always-y += xdp_redirect_cpu_kern.o
always-y += xdp_monitor_kern.o
always-y += xdp_rxq_info_kern.o
diff --git a/samples/bpf/xdp_redirect_map_multi_kern.c b/samples/bpf/xdp_redirect_map_multi_kern.c
new file mode 100644
index 000000000000..71aa23d1cb2b
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_kern.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 32);
+} forward_map_general SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 32);
+} forward_map_native SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __type(key, u32);
+ __type(value, long);
+ __uint(max_entries, 1);
+} rxcnt SEC(".maps");
+
+/* map to store egress interfaces mac addresses, set the
+ * max_entries to 1 and extend it in user sapce prog.
+ */
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, u32);
+ __type(value, __be64);
+ __uint(max_entries, 1);
+} mac_map SEC(".maps");
+
+static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map)
+{
+ long *value;
+ u32 key = 0;
+
+ /* count packet in global counter */
+ value = bpf_map_lookup_elem(&rxcnt, &key);
+ if (value)
+ *value += 1;
+
+ return bpf_redirect_map(forward_map, key,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+SEC("xdp_redirect_general")
+int xdp_redirect_map_general(struct xdp_md *ctx)
+{
+ return xdp_redirect_map(ctx, &forward_map_general);
+}
+
+SEC("xdp_redirect_native")
+int xdp_redirect_map_native(struct xdp_md *ctx)
+{
+ return xdp_redirect_map(ctx, &forward_map_native);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ u32 key = ctx->egress_ifindex;
+ struct ethhdr *eth = data;
+ __be64 *mac;
+ u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ mac = bpf_map_lookup_elem(&mac_map, &key);
+ if (mac)
+ __builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c
new file mode 100644
index 000000000000..84cdbbed20b7
--- /dev/null
+++ b/samples/bpf/xdp_redirect_map_multi_user.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+static int rxcnt_map_fd;
+
+static void int_exit(int sig)
+{
+ __u32 prog_id = 0;
+ int i;
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id)
+ bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+ }
+
+ exit(0);
+}
+
+static void poll_stats(int interval)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ __u64 values[nr_cpus], prev[nr_cpus];
+
+ memset(prev, 0, sizeof(prev));
+
+ while (1) {
+ __u64 sum = 0;
+ __u32 key = 0;
+ int i;
+
+ sleep(interval);
+ assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ sum += (values[i] - prev[i]);
+ if (sum)
+ printf("Forwarding %10llu pkt/s\n", sum / interval);
+ memcpy(prev, values, sizeof(values));
+ }
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+ char ifname[IF_NAMESIZE];
+ struct ifreq ifr;
+ int fd, ret = -1;
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0)
+ return ret;
+
+ if (!if_indextoname(ifindex, ifname))
+ goto err_out;
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+ goto err_out;
+
+ memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+ ret = 0;
+
+err_out:
+ close(fd);
+ return ret;
+}
+
+static int update_mac_map(struct bpf_object *obj)
+{
+ int i, ret = -1, mac_map_fd;
+ unsigned char mac_addr[6];
+ unsigned int ifindex;
+
+ mac_map_fd = bpf_object__find_map_fd_by_name(obj, "mac_map");
+ if (mac_map_fd < 0) {
+ printf("find mac map fd failed\n");
+ return ret;
+ }
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ ret = get_mac_addr(ifindex, mac_addr);
+ if (ret < 0) {
+ printf("get interface %d mac failed\n", ifindex);
+ return ret;
+ }
+
+ ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0);
+ if (ret) {
+ perror("bpf_update_elem mac_map_fd");
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+ "OPTS:\n"
+ " -S use skb-mode\n"
+ " -N enforce native mode\n"
+ " -F force loading prog\n"
+ " -X load xdp program on egress\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ int i, ret, opt, forward_map_fd, max_ifindex = 0;
+ struct bpf_program *ingress_prog, *egress_prog;
+ int ingress_prog_fd, egress_prog_fd = 0;
+ struct bpf_devmap_val devmap_val;
+ bool attach_egress_prog = false;
+ char ifname[IF_NAMESIZE];
+ struct bpf_map *mac_map;
+ struct bpf_object *obj;
+ unsigned int ifindex;
+ char filename[256];
+
+ while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+ switch (opt) {
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'N':
+ /* default, set below */
+ break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ case 'X':
+ attach_egress_prog = true;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ } else if (attach_egress_prog) {
+ printf("Load xdp program on egress with SKB mode not supported yet\n");
+ return 1;
+ }
+
+ if (optind == argc) {
+ printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+ return 1;
+ }
+
+ printf("Get interfaces");
+ for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+ ifaces[i] = if_nametoindex(argv[optind + i]);
+ if (!ifaces[i])
+ ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+ if (!if_indextoname(ifaces[i], ifname)) {
+ perror("Invalid interface name or i");
+ return 1;
+ }
+
+ /* Find the largest index number */
+ if (ifaces[i] > max_ifindex)
+ max_ifindex = ifaces[i];
+
+ printf(" %d", ifaces[i]);
+ }
+ printf("\n");
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ obj = bpf_object__open(filename);
+ if (libbpf_get_error(obj)) {
+ printf("ERROR: opening BPF object file failed\n");
+ obj = NULL;
+ goto err_out;
+ }
+
+ /* Reset the map size to max ifindex + 1 */
+ if (attach_egress_prog) {
+ mac_map = bpf_object__find_map_by_name(obj, "mac_map");
+ ret = bpf_map__resize(mac_map, max_ifindex + 1);
+ if (ret < 0) {
+ printf("ERROR: reset mac map size failed\n");
+ goto err_out;
+ }
+ }
+
+ /* load BPF program */
+ if (bpf_object__load(obj)) {
+ printf("ERROR: loading BPF object file failed\n");
+ goto err_out;
+ }
+
+ if (xdp_flags & XDP_FLAGS_SKB_MODE) {
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general");
+ forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_general");
+ } else {
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native");
+ forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_native");
+ }
+ if (!ingress_prog || forward_map_fd < 0) {
+ printf("finding ingress_prog/forward_map in obj file failed\n");
+ goto err_out;
+ }
+
+ ingress_prog_fd = bpf_program__fd(ingress_prog);
+ if (ingress_prog_fd < 0) {
+ printf("find ingress_prog fd failed\n");
+ goto err_out;
+ }
+
+ rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
+ if (rxcnt_map_fd < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ goto err_out;
+ }
+
+ if (attach_egress_prog) {
+ /* Update mac_map with all egress interfaces' mac addr */
+ if (update_mac_map(obj) < 0) {
+ printf("Error: update mac map failed");
+ goto err_out;
+ }
+
+ /* Find egress prog fd */
+ egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+ if (!egress_prog) {
+ printf("finding egress_prog in obj file failed\n");
+ goto err_out;
+ }
+ egress_prog_fd = bpf_program__fd(egress_prog);
+ if (egress_prog_fd < 0) {
+ printf("find egress_prog fd failed\n");
+ goto err_out;
+ }
+ }
+
+ /* Remove attached program when program is interrupted or killed */
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+
+ /* Init forward multicast groups */
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ /* bind prog_fd to each interface */
+ ret = bpf_set_link_xdp_fd(ifindex, ingress_prog_fd, xdp_flags);
+ if (ret) {
+ printf("Set xdp fd failed on %d\n", ifindex);
+ goto err_out;
+ }
+
+ /* Add all the interfaces to forward group and attach
+ * egress devmap programe if exist
+ */
+ devmap_val.ifindex = ifindex;
+ devmap_val.bpf_prog.fd = egress_prog_fd;
+ ret = bpf_map_update_elem(forward_map_fd, &ifindex, &devmap_val, 0);
+ if (ret) {
+ perror("bpf_map_update_elem forward_map");
+ goto err_out;
+ }
+ }
+
+ poll_stats(2);
+
+ return 0;
+
+err_out:
+ return 1;
+}
--
2.26.3
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH RESEND v11 4/4] selftests/bpf: add xdp_redirect_multi test
2021-05-13 7:04 [PATCH RESEND v11 0/4] xdp: extend xdp_redirect_map with broadcast support Hangbin Liu
` (2 preceding siblings ...)
2021-05-13 7:04 ` [PATCH RESEND v11 3/4] sample/bpf: add xdp_redirect_map_multi for redirect_map broadcast test Hangbin Liu
@ 2021-05-13 7:04 ` Hangbin Liu
3 siblings, 0 replies; 10+ messages in thread
From: Hangbin Liu @ 2021-05-13 7:04 UTC (permalink / raw)
To: bpf
Cc: netdev, Toke Høiland-Jørgensen, Jiri Benc,
Jesper Dangaard Brouer, Eelco Chaudron, ast, Daniel Borkmann,
Lorenzo Bianconi, David Ahern, Andrii Nakryiko,
Alexei Starovoitov, John Fastabend, Maciej Fijalkowski,
Björn Töpel, Martin KaFai Lau, Hangbin Liu
Add a bpf selftest for new helper xdp_redirect_map_multi(). In this
test there are 3 forward groups and 1 exclude group. The test will
redirect each interface's packets to all the interfaces in the forward
group, and exclude the interface in exclude map.
Two maps (DEVMAP, DEVMAP_HASH) and two xdp modes (generic, drive) will
be tested. XDP egress program will also be tested by setting pkt src MAC
to egress interface's MAC address.
For more test details, you can find it in the test script. Here is
the test result.
]# time ./test_xdp_redirect_multi.sh
Pass: xdpgeneric arp(F_BROADCAST) ns1-1
Pass: xdpgeneric arp(F_BROADCAST) ns1-2
Pass: xdpgeneric arp(F_BROADCAST) ns1-3
Pass: xdpgeneric IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1
Pass: xdpgeneric IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2
Pass: xdpgeneric IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3
Pass: xdpgeneric IPv6 (no flags) ns1-1
Pass: xdpgeneric IPv6 (no flags) ns1-2
Pass: xdpdrv arp(F_BROADCAST) ns1-1
Pass: xdpdrv arp(F_BROADCAST) ns1-2
Pass: xdpdrv arp(F_BROADCAST) ns1-3
Pass: xdpdrv IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1
Pass: xdpdrv IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2
Pass: xdpdrv IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3
Pass: xdpdrv IPv6 (no flags) ns1-1
Pass: xdpdrv IPv6 (no flags) ns1-2
Pass: xdpegress mac ns1-2
Pass: xdpegress mac ns1-3
Summary: PASS 18, FAIL 0
real 1m18.321s
user 0m0.123s
sys 0m0.350s
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v11: remove some sleeps to reduce the testing time. Re-struct the test
and make clear what flags we are testing.
v2-v10: no update
v2: add a IPv6 test to validates that single redirect still works
after multicast redirect.
---
tools/testing/selftests/bpf/Makefile | 3 +-
.../bpf/progs/xdp_redirect_multi_kern.c | 94 ++++++++
.../selftests/bpf/test_xdp_redirect_multi.sh | 204 ++++++++++++++++
.../selftests/bpf/xdp_redirect_multi.c | 226 ++++++++++++++++++
4 files changed, 526 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
create mode 100644 tools/testing/selftests/bpf/xdp_redirect_multi.c
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 511259c2c6c5..17a2c14c8459 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -54,6 +54,7 @@ TEST_FILES = xsk_prereqs.sh \
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
+ test_xdp_redirect_multi.sh \
test_xdp_meta.sh \
test_xdp_veth.sh \
test_offload.py \
@@ -84,7 +85,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xdpxceiver
+ xdpxceiver xdp_redirect_multi
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
new file mode 100644
index 000000000000..880debcbcd65
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KBUILD_MODNAME "foo"
+#include <string.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+/* One map use devmap, another one use devmap_hash for testing */
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(int));
+ __uint(max_entries, 1024);
+} map_all SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP_HASH);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 128);
+} map_egress SEC(".maps");
+
+/* map to store egress interfaces mac addresses */
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u32);
+ __type(value, __be64);
+ __uint(max_entries, 128);
+} mac_map SEC(".maps");
+
+SEC("xdp_redirect_map_multi")
+int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ int if_index = ctx->ingress_ifindex;
+ struct ethhdr *eth = data;
+ __u16 h_proto;
+ __u64 nh_off;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ h_proto = eth->h_proto;
+
+ /* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */
+ if (h_proto == bpf_htons(ETH_P_IP))
+ return bpf_redirect_map(&map_all, 0,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+ /* Using IPv6 for none flag testing */
+ else if (h_proto == bpf_htons(ETH_P_IPV6))
+ return bpf_redirect_map(&map_all, if_index, 0);
+ /* All others for BPF_F_BROADCAST testing */
+ else
+ return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST);
+}
+
+/* The following 2 progs are for 2nd devmap prog testing */
+SEC("xdp_redirect_map_ingress")
+int xdp_redirect_map_all_prog(struct xdp_md *ctx)
+{
+ return bpf_redirect_map(&map_egress, 0,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_devmap_prog(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ __u32 key = ctx->egress_ifindex;
+ struct ethhdr *eth = data;
+ __u64 nh_off;
+ __be64 *mac;
+
+ nh_off = sizeof(*eth);
+ if (data + nh_off > data_end)
+ return XDP_DROP;
+
+ mac = bpf_map_lookup_elem(&mac_map, &key);
+ if (mac)
+ __builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
new file mode 100755
index 000000000000..1538373157e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
@@ -0,0 +1,204 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test topology:
+# - - - - - - - - - - - - - - - - - - - - - - - - -
+# | veth1 veth2 veth3 | ... init net
+# - -| - - - - - - | - - - - - - | - -
+# --------- --------- ---------
+# | veth0 | | veth0 | | veth0 | ...
+# --------- --------- ---------
+# ns1 ns2 ns3
+#
+# Test modules:
+# XDP modes: generic, native, native + egress_prog
+#
+# Test cases:
+# ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive
+# the redirects.
+# ns1 -> gw: ns1, ns2, ns3, should receive the arp request
+# IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress
+# interface should not receive the redirects.
+# ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects.
+# IPv6: Testing none flag, all the pkts should be redirected back
+# ping test: ns1 -> ns2 (block), echo requests will be redirect back
+# egress_prog:
+# all src mac should be egress interface's mac
+
+# netns numbers
+NUM=3
+IFACES=""
+DRV_MODE="xdpgeneric xdpdrv xdpegress"
+PASS=0
+FAIL=0
+
+test_pass()
+{
+ echo "Pass: $@"
+ PASS=$((PASS + 1))
+}
+
+test_fail()
+{
+ echo "fail: $@"
+ FAIL=$((FAIL + 1))
+}
+
+clean_up()
+{
+ for i in $(seq $NUM); do
+ ip link del veth$i 2> /dev/null
+ ip netns del ns$i 2> /dev/null
+ done
+}
+
+# Kselftest framework requirement - SKIP code is 4.
+check_env()
+{
+ ip link set dev lo xdpgeneric off &>/dev/null
+ if [ $? -ne 0 ];then
+ echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
+ exit 4
+ fi
+
+ which tcpdump &>/dev/null
+ if [ $? -ne 0 ];then
+ echo "selftests: [SKIP] Could not run test without tcpdump"
+ exit 4
+ fi
+}
+
+setup_ns()
+{
+ local mode=$1
+ IFACES=""
+
+ if [ "$mode" = "xdpegress" ]; then
+ mode="xdpdrv"
+ fi
+
+ for i in $(seq $NUM); do
+ ip netns add ns$i
+ ip link add veth$i type veth peer name veth0 netns ns$i
+ ip link set veth$i up
+ ip -n ns$i link set veth0 up
+
+ ip -n ns$i addr add 192.0.2.$i/24 dev veth0
+ ip -n ns$i addr add 2001:db8::$i/64 dev veth0
+ # Add a neigh entry for IPv4 ping test
+ ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0
+ ip -n ns$i link set veth0 $mode obj \
+ xdp_dummy.o sec xdp_dummy &> /dev/null || \
+ { test_fail "Unable to load dummy xdp" && exit 1; }
+ IFACES="$IFACES veth$i"
+ veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}')
+ done
+}
+
+do_egress_tests()
+{
+ local mode=$1
+
+ # mac test
+ ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log &
+ ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log &
+ sleep 0.5
+ ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
+ sleep 0.5
+ pkill -9 tcpdump
+
+ # mac check
+ grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \
+ test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
+ grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \
+ test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
+}
+
+do_ping_tests()
+{
+ local mode=$1
+
+ # ping6 test: echo request should be redirect back to itself, not others
+ ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
+
+ ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ns1-1_${mode}.log &
+ ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ns1-2_${mode}.log &
+ ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ns1-3_${mode}.log &
+ sleep 0.5
+ # ARP test
+ ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
+ # IPv4 test
+ ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null
+ # IPv6 test
+ ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null
+ sleep 0.5
+ pkill -9 tcpdump
+
+ # All netns should receive the redirect arp requests
+ [ $(grep -c "who-has 192.0.2.254" ns1-1_${mode}.log) -gt 4 ] && \
+ test_pass "$mode arp(F_BROADCAST) ns1-1" || \
+ test_fail "$mode arp(F_BROADCAST) ns1-1"
+ [ $(grep -c "who-has 192.0.2.254" ns1-2_${mode}.log) -le 4 ] && \
+ test_pass "$mode arp(F_BROADCAST) ns1-2" || \
+ test_fail "$mode arp(F_BROADCAST) ns1-2"
+ [ $(grep -c "who-has 192.0.2.254" ns1-3_${mode}.log) -le 4 ] && \
+ test_pass "$mode arp(F_BROADCAST) ns1-3" || \
+ test_fail "$mode arp(F_BROADCAST) ns1-3"
+
+ # ns1 should not receive the redirect echo request, others should
+ [ $(grep -c "ICMP echo request" ns1-1_${mode}.log) -eq 4 ] && \
+ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \
+ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1"
+ [ $(grep -c "ICMP echo request" ns1-2_${mode}.log) -eq 4 ] && \
+ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \
+ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2"
+ [ $(grep -c "ICMP echo request" ns1-3_${mode}.log) -eq 4 ] && \
+ test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \
+ test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3"
+
+ # ns1 should receive the echo request, ns2 should not
+ [ $(grep -c "ICMP6, echo request" ns1-1_${mode}.log) -eq 4 ] && \
+ test_pass "$mode IPv6 (no flags) ns1-1" || \
+ test_fail "$mode IPv6 (no flags) ns1-1"
+ [ $(grep -c "ICMP6, echo request" ns1-2_${mode}.log) -eq 0 ] && \
+ test_pass "$mode IPv6 (no flags) ns1-2" || \
+ test_fail "$mode IPv6 (no flags) ns1-2"
+}
+
+do_tests()
+{
+ local mode=$1
+ local drv_p
+
+ case ${mode} in
+ xdpdrv) drv_p="-N";;
+ xdpegress) drv_p="-X";;
+ xdpgeneric) drv_p="-S";;
+ esac
+
+ ./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log &
+ xdp_pid=$!
+ sleep 1
+
+ if [ "$mode" = "xdpegress" ]; then
+ do_egress_tests $mode
+ else
+ do_ping_tests $mode
+ fi
+
+ kill $xdp_pid
+}
+
+trap clean_up 0 2 3 6 9
+
+check_env
+rm -f xdp_redirect_*.log ns*.log mac_ns*.log
+
+for mode in ${DRV_MODE}; do
+ setup_ns $mode
+ do_tests $mode
+ clean_up
+done
+
+echo "Summary: PASS $PASS, FAIL $FAIL"
+[ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
new file mode 100644
index 000000000000..3696a8f32c23
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <net/if.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define MAX_IFACE_NUM 32
+#define MAX_INDEX_NUM 1024
+
+static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int ifaces[MAX_IFACE_NUM] = {};
+
+static void int_exit(int sig)
+{
+ __u32 prog_id = 0;
+ int i;
+
+ for (i = 0; ifaces[i] > 0; i++) {
+ if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(1);
+ }
+ if (prog_id)
+ bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags);
+ }
+
+ exit(0);
+}
+
+static int get_mac_addr(unsigned int ifindex, void *mac_addr)
+{
+ char ifname[IF_NAMESIZE];
+ struct ifreq ifr;
+ int fd, ret = -1;
+
+ fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (fd < 0)
+ return ret;
+
+ if (!if_indextoname(ifindex, ifname))
+ goto err_out;
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+ goto err_out;
+
+ memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+ ret = 0;
+
+err_out:
+ close(fd);
+ return ret;
+}
+
+static void usage(const char *prog)
+{
+ fprintf(stderr,
+ "usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
+ "OPTS:\n"
+ " -S use skb-mode\n"
+ " -N enforce native mode\n"
+ " -F force loading prog\n"
+ " -X load xdp program on egress\n",
+ prog);
+}
+
+int main(int argc, char **argv)
+{
+ int prog_fd, group_all, mac_map;
+ struct bpf_program *ingress_prog, *egress_prog;
+ struct bpf_prog_load_attr prog_load_attr = {
+ .prog_type = BPF_PROG_TYPE_UNSPEC,
+ };
+ int i, ret, opt, egress_prog_fd = 0;
+ struct bpf_devmap_val devmap_val;
+ bool attach_egress_prog = false;
+ unsigned char mac_addr[6];
+ char ifname[IF_NAMESIZE];
+ struct bpf_object *obj;
+ unsigned int ifindex;
+ char filename[256];
+
+ while ((opt = getopt(argc, argv, "SNFX")) != -1) {
+ switch (opt) {
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'N':
+ /* default, set below */
+ break;
+ case 'F':
+ xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
+ break;
+ case 'X':
+ attach_egress_prog = true;
+ break;
+ default:
+ usage(basename(argv[0]));
+ return 1;
+ }
+ }
+
+ if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ } else if (attach_egress_prog) {
+ printf("Load xdp program on egress with SKB mode not supported yet\n");
+ goto err_out;
+ }
+
+ if (optind == argc) {
+ printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
+ goto err_out;
+ }
+
+ printf("Get interfaces");
+ for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
+ ifaces[i] = if_nametoindex(argv[optind + i]);
+ if (!ifaces[i])
+ ifaces[i] = strtoul(argv[optind + i], NULL, 0);
+ if (!if_indextoname(ifaces[i], ifname)) {
+ perror("Invalid interface name or i");
+ goto err_out;
+ }
+ if (ifaces[i] > MAX_INDEX_NUM) {
+ printf("Interface index to large\n");
+ goto err_out;
+ }
+ printf(" %d", ifaces[i]);
+ }
+ printf("\n");
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+ prog_load_attr.file = filename;
+
+ if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+ goto err_out;
+
+ if (attach_egress_prog)
+ group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
+ else
+ group_all = bpf_object__find_map_fd_by_name(obj, "map_all");
+ mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map");
+
+ if (group_all < 0 || mac_map < 0) {
+ printf("bpf_object__find_map_fd_by_name failed\n");
+ goto err_out;
+ }
+
+ if (attach_egress_prog) {
+ /* Find ingress/egress prog for 2nd xdp prog */
+ ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog");
+ egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
+ if (!ingress_prog || !egress_prog) {
+ printf("finding ingress/egress_prog in obj file failed\n");
+ goto err_out;
+ }
+ prog_fd = bpf_program__fd(ingress_prog);
+ egress_prog_fd = bpf_program__fd(egress_prog);
+ if (prog_fd < 0 || egress_prog_fd < 0) {
+ printf("find egress_prog fd failed\n");
+ goto err_out;
+ }
+ }
+
+ signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
+
+ /* Init forward multicast groups and exclude group */
+ for (i = 0; ifaces[i] > 0; i++) {
+ ifindex = ifaces[i];
+
+ if (attach_egress_prog) {
+ ret = get_mac_addr(ifindex, mac_addr);
+ if (ret < 0) {
+ printf("get interface %d mac failed\n", ifindex);
+ goto err_out;
+ }
+ ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0);
+ if (ret) {
+ perror("bpf_update_elem mac_map failed\n");
+ goto err_out;
+ }
+ }
+
+ /* Add all the interfaces to group all */
+ devmap_val.ifindex = ifindex;
+ devmap_val.bpf_prog.fd = egress_prog_fd;
+ ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0);
+ if (ret) {
+ perror("bpf_map_update_elem");
+ goto err_out;
+ }
+
+ /* bind prog_fd to each interface */
+ ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags);
+ if (ret) {
+ printf("Set xdp fd failed on %d\n", ifindex);
+ goto err_out;
+ }
+ }
+
+ /* sleep some time for testing */
+ sleep(999);
+
+ return 0;
+
+err_out:
+ return 1;
+}
--
2.26.3
^ permalink raw reply related [flat|nested] 10+ messages in thread