* Re: [net PATCH v3 3/5] virtio_net: factor out xdp handler for readability
From: John Fastabend @ 2017-01-13 19:56 UTC (permalink / raw)
To: Jason Wang, mst; +Cc: john.r.fastabend, netdev, alexei.starovoitov, daniel
In-Reply-To: <da246cbb-710c-275f-489c-251ea898a389@redhat.com>
On 17-01-12 11:40 PM, Jason Wang wrote:
>
>
> On 2017年01月13日 10:51, John Fastabend wrote:
>> At this point the do_xdp_prog is mostly if/else branches handling
>> the different modes of virtio_net. So remove it and handle running
>> the program in the per mode handlers.
>>
>> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
>> ---
>> drivers/net/virtio_net.c | 76 +++++++++++++++++-----------------------------
>> 1 file changed, 28 insertions(+), 48 deletions(-)
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 43cb2e0..ec54644 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -388,49 +388,6 @@ static void virtnet_xdp_xmit(struct virtnet_info *vi,
>> virtqueue_kick(sq->vq);
>> }
>>
>
> [...]
>
>> /* This happens when rx buffer size is underestimated */
>> @@ -598,8 +570,10 @@ static struct sk_buff *receive_mergeable(struct
>> net_device *dev,
>> if (unlikely(hdr->hdr.gso_type))
>> goto err_xdp;
>> - act = do_xdp_prog(vi, rq, xdp_prog,
>> - page_address(xdp_page) + offset, len);
>> + data = page_address(xdp_page) + offset;
>> + xdp.data = data + desc_room;
>> + xdp.data_end = xdp.data + (len - vi->hdr_len);
>
> It looks desc_room is always vi->hdr_len.
>
Seems to be the case I'll just use vi->hdr_len and remove the variable.
Thanks.
>> + act = bpf_prog_run_xdp(xdp_prog, &xdp);
>> switch (act) {
>> case XDP_PASS:
>> /* We can only create skb based on xdp_page. */
>> @@ -613,13 +587,19 @@ static struct sk_buff *receive_mergeable(struct
>> net_device *dev,
>> }
>> break;
>> case XDP_TX:
>> + qp = vi->curr_queue_pairs -
>> + vi->xdp_queue_pairs +
>> + smp_processor_id();
>> + virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp, data);
>> ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
>> if (unlikely(xdp_page != page))
>> goto err_xdp;
>> rcu_read_unlock();
>> goto xdp_xmit;
>> - case XDP_DROP:
>> default:
>> + bpf_warn_invalid_xdp_action(act);
>> + case XDP_ABORTED:
>> + case XDP_DROP:
>> if (unlikely(xdp_page != page))
>> __free_pages(xdp_page, 0);
>> ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
>>
>
^ permalink raw reply
* Re: [net PATCH 5/5] virtio_net: XDP support for adjust_head
From: John Fastabend @ 2017-01-13 19:53 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: jasowang, john.r.fastabend, netdev, alexei.starovoitov, daniel
In-Reply-To: <20170113191451-mutt-send-email-mst@kernel.org>
On 17-01-13 09:23 AM, Michael S. Tsirkin wrote:
> On Thu, Jan 12, 2017 at 01:45:19PM -0800, John Fastabend wrote:
>> Add support for XDP adjust head by allocating a 256B header region
>> that XDP programs can grow into. This is only enabled when a XDP
>> program is loaded.
>>
>> In order to ensure that we do not have to unwind queue headroom push
>> queue setup below bpf_prog_add. It reads better to do a prog ref
>> unwind vs another queue setup call.
>>
>> At the moment this code must do a full reset to ensure old buffers
>> without headroom on program add or with headroom on program removal
>> are not used incorrectly in the datapath. Ideally we would only
>> have to disable/enable the RX queues being updated but there is no
>> API to do this at the moment in virtio so use the big hammer. In
>> practice it is likely not that big of a problem as this will only
>> happen when XDP is enabled/disabled changing programs does not
>> require the reset. There is some risk that the driver may either
>> have an allocation failure or for some reason fail to correctly
>> negotiate with the underlying backend in this case the driver will
>> be left uninitialized. I have not seen this ever happen on my test
>> systems and for what its worth this same failure case can occur
>> from probe and other contexts in virtio framework.
>>
>> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
>> ---
[...]
>>
>> +#define VIRTIO_XDP_HEADROOM 256
>> +
>> +static int init_vqs(struct virtnet_info *vi);
>> +static void remove_vq_common(struct virtnet_info *vi, bool lock);
>> +
>> +/* Reset virtio device with RTNL held this is very similar to the
>> + * freeze()/restore() logic except we need to ensure locking. It is
>> + * possible that this routine may fail and leave the driver in a
>> + * failed state. However assuming the driver negotiated correctly
>> + * at probe time we _should_ be able to (re)negotiate driver again.
>> + */
>> +static int virtnet_xdp_reset(struct virtnet_info *vi)
>> +{
>> + struct virtio_device *vdev = vi->vdev;
>> + unsigned int status;
>> + int i, ret;
>> +
>> + /* Disable and unwind rings */
>> + virtio_config_disable(vdev);
>> + vdev->failed = vdev->config->get_status(vdev) & VIRTIO_CONFIG_S_FAILED;
>> +
>> + netif_device_detach(vi->dev);
>
> After this point, netif_device_present
> will return false, and then we have a bunch of code
> that does
> if (!netif_device_present(dev))
> return -ENODEV;
>
>
> so we need to audit this code to make sure it's
> all called under rtnl, correct?
>
Correct. In the XDP case it is.
> We don't want it to fail because of timing.
>
> Maybe add an assert there.
>
I can add an assert here to ensure it doesn't ever get
refactored out or something.
>
>> + cancel_delayed_work_sync(&vi->refill);
>> + if (netif_running(vi->dev)) {
>> + for (i = 0; i < vi->max_queue_pairs; i++)
>> + napi_disable(&vi->rq[i].napi);
>> + }
>> +
>> + remove_vq_common(vi, false);
>> +
>> + /* Do a reset per virtio spec recommendation */
>> + vdev->config->reset(vdev);
>> +
>> + /* Acknowledge that we've seen the device. */
>> + status = vdev->config->get_status(vdev);
>> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_ACKNOWLEDGE);
>> +
>> + /* Notify driver is up and finalize features per specification. The
>> + * error code from finalize features is checked here but should not
>> + * fail because we assume features were previously synced successfully.
>> + */
>> + status = vdev->config->get_status(vdev);
>> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER);
>> + ret = virtio_finalize_features(vdev);
>
> I'd rather we put all this in virtio core, maybe call it virtio_reset or
> something.
At first I started to do this but decided it was easier to open code it I
was on the fence though so if we think it would be cleaner then I will
do it.
The trick is needs to be broken down into two pieces, something like the
following,
virtio_reset() {
do_generic_down_part -> pci pieces
vdev->config->down() -> do down part of device specifics
do_generic_up_part
vdev->config->up() -> do up part of device specifics
do_finalize_part
}
Alternatively we could reuse the freeze/restore device callbacks but those
make assumptions about locking. So we could pass a context through but per
Stephen's comment that gets a bit fragile. And sparse doesn't like it either
apparently. I think making it an explicit down/up reset callback might
make it clean and reusable for any other devices.
Any thoughts? My preference outside of open coding it is the new down_reset
and up_reset callbacks.
>
>> + if (ret) {
>> + netdev_warn(vi->dev, "virtio_finalize_features failed during reset aborting\n");
>> + goto err;
>> + }
>> +
>> + ret = init_vqs(vi);
>> + if (ret) {
>> + netdev_warn(vi->dev, "init_vqs failed during reset aborting\n");
>> + goto err;
>> + }
>> + virtio_device_ready(vi->vdev);
>> +
>> + if (netif_running(vi->dev)) {
>> + for (i = 0; i < vi->curr_queue_pairs; i++)
>> + if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
>> + schedule_delayed_work(&vi->refill, 0);
>> +
>> + for (i = 0; i < vi->max_queue_pairs; i++)
>> + virtnet_napi_enable(&vi->rq[i]);
>> + }
>> + netif_device_attach(vi->dev);
>> + /* Finally, tell the device we're all set */
>> + status = vdev->config->get_status(vdev);
>> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_DRIVER_OK);
>> + virtio_config_enable(vdev);
>> +
>> + return 0;
>> +err:
>> + status = vdev->config->get_status(vdev);
>> + vdev->config->set_status(vdev, status | VIRTIO_CONFIG_S_FAILED);
>
> And maybe virtio_fail ?
>
Sure.
Thanks,
John
^ permalink raw reply
* Re: Commit 1fe8e0... (include more headers in if_tunnel.h) breaks my user-space build.
From: Ben Greear @ 2017-01-13 19:50 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev, mikko.rapeli
In-Reply-To: <20170113114158.6e5c3461@xeon-e3>
On 01/13/2017 11:41 AM, Stephen Hemminger wrote:
> On Fri, 13 Jan 2017 11:12:32 -0800
> Ben Greear <greearb@candelatech.com> wrote:
>
>> I am including netinet/ip.h, and also linux/if_tunnel.h, and the linux/ip.h conflicts with
>> netinet/ip.h.
>>
>> Maybe my build environment is screwed up, but maybe also it would be better to
>> just let the user include appropriate headers before including if_tunnel.h
>> and revert this patch?
>>
>>
>> include/uapi/linux/if_tunnel.h: include linux/if.h, linux/ip.h and linux/in6.h
>>
>> Fixes userspace compilation errors like:
>>
>> error: field ‘iph’ has incomplete type
>> error: field ‘prefix’ has incomplete type
>>
>> Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
>> Signed-off-by: David S. Miller <davem@davemloft.net>
>>
>> Thanks,
>> Ben
>>
>
> What I ended up doing for iproute2 was including all headers used by the source
> based on sanitized kernel headers. Basically
> $ git grep '^#include <linux/' | \
> awk -F: '{print $2}' | \
> sed -e 's/^#include <//' -e 's/>.*$//' | \
> sort -u >linux.headers
> $ for f in $(cat linux.headers)
> do cp ~/kernel/net-next/usr/include/$f include/$f
> done
>
> You can't take only some of the headers, once you decide to diverge from glibc provided
> headers, you got to take them all.
>
I do grab a copy of the linux kernel headers and compile against that, but netinet/ip.h is
coming from the OS. Do you mean I should not include netinet/ip.h and instead use linux/ip.h?
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: Commit 1fe8e0... (include more headers in if_tunnel.h) breaks my user-space build.
From: Stephen Hemminger @ 2017-01-13 19:41 UTC (permalink / raw)
To: Ben Greear; +Cc: netdev, mikko.rapeli
In-Reply-To: <f1cede01-3fa4-130a-fa2d-7cbdfe3648b3@candelatech.com>
On Fri, 13 Jan 2017 11:12:32 -0800
Ben Greear <greearb@candelatech.com> wrote:
> I am including netinet/ip.h, and also linux/if_tunnel.h, and the linux/ip.h conflicts with
> netinet/ip.h.
>
> Maybe my build environment is screwed up, but maybe also it would be better to
> just let the user include appropriate headers before including if_tunnel.h
> and revert this patch?
>
>
> include/uapi/linux/if_tunnel.h: include linux/if.h, linux/ip.h and linux/in6.h
>
> Fixes userspace compilation errors like:
>
> error: field ‘iph’ has incomplete type
> error: field ‘prefix’ has incomplete type
>
> Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
> Signed-off-by: David S. Miller <davem@davemloft.net>
>
> Thanks,
> Ben
>
What I ended up doing for iproute2 was including all headers used by the source
based on sanitized kernel headers. Basically
$ git grep '^#include <linux/' | \
awk -F: '{print $2}' | \
sed -e 's/^#include <//' -e 's/>.*$//' | \
sort -u >linux.headers
$ for f in $(cat linux.headers)
do cp ~/kernel/net-next/usr/include/$f include/$f
done
You can't take only some of the headers, once you decide to diverge from glibc provided
headers, you got to take them all.
^ permalink raw reply
* Re: Commit 1fe8e0... (include more headers in if_tunnel.h) breaks my user-space build.
From: Ben Greear @ 2017-01-13 19:21 UTC (permalink / raw)
To: netdev, mikko.rapeli
In-Reply-To: <f1cede01-3fa4-130a-fa2d-7cbdfe3648b3@candelatech.com>
On 01/13/2017 11:12 AM, Ben Greear wrote:
> I am including netinet/ip.h, and also linux/if_tunnel.h, and the linux/ip.h conflicts with
> netinet/ip.h.
>
> Maybe my build environment is screwed up, but maybe also it would be better to
> just let the user include appropriate headers before including if_tunnel.h
> and revert this patch?
>
>
> include/uapi/linux/if_tunnel.h: include linux/if.h, linux/ip.h and linux/in6.h
>
> Fixes userspace compilation errors like:
>
> error: field ‘iph’ has incomplete type
> error: field ‘prefix’ has incomplete type
>
> Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
> Signed-off-by: David S. Miller <davem@davemloft.net>
>
> Thanks,
> Ben
>
I forgot the full commit ID, my abbreviation was not sufficient to be unique it seems:
1fe8e0f074c77aa41aaa579345a9e675acbebfa9
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Commit 1fe8e0... (include more headers in if_tunnel.h) breaks my user-space build.
From: Ben Greear @ 2017-01-13 19:12 UTC (permalink / raw)
To: netdev, mikko.rapeli
I am including netinet/ip.h, and also linux/if_tunnel.h, and the linux/ip.h conflicts with
netinet/ip.h.
Maybe my build environment is screwed up, but maybe also it would be better to
just let the user include appropriate headers before including if_tunnel.h
and revert this patch?
include/uapi/linux/if_tunnel.h: include linux/if.h, linux/ip.h and linux/in6.h
Fixes userspace compilation errors like:
error: field ‘iph’ has incomplete type
error: field ‘prefix’ has incomplete type
Signed-off-by: Mikko Rapeli <mikko.rapeli@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* [PATCHv3 net-next 7/7] sctp: implement sender-side procedures for SSN Reset Request Parameter
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to implement sender-side procedures for the Outgoing
and Incoming SSN Reset Request Parameter described in rfc6525 section
5.1.2 and 5.1.3.
It is also add sockopt SCTP_RESET_STREAMS in rfc6525 section 6.3.2
for users.
Note that the new asoc member strreset_outstanding is to make sure
only one reconf request chunk on the fly as rfc6525 section 5.1.1
demands.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/sctp.h | 6 ++++
include/net/sctp/structs.h | 1 +
include/uapi/linux/sctp.h | 11 +++++++
net/sctp/outqueue.c | 33 +++++++++++++------
net/sctp/socket.c | 29 +++++++++++++++++
net/sctp/stream.c | 79 ++++++++++++++++++++++++++++++++++++++++++++++
6 files changed, 149 insertions(+), 10 deletions(-)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index bc0e049..3cfd365b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -194,6 +194,12 @@ void sctp_remaddr_proc_exit(struct net *net);
int sctp_offload_init(void);
/*
+ * sctp/stream.c
+ */
+int sctp_send_reset_streams(struct sctp_association *asoc,
+ struct sctp_reset_streams *params);
+
+/*
* Module global variables
*/
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index d99b76e..231fa9ac 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1875,6 +1875,7 @@ struct sctp_association {
reconf_enable:1;
__u8 strreset_enable;
+ __u8 strreset_outstanding; /* request param count on the fly */
__u32 strreset_outseq; /* Update after receiving response */
__u32 strreset_inseq; /* Update after receiving request */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 867be0f..03c27ce 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -116,6 +116,7 @@ typedef __s32 sctp_assoc_t;
#define SCTP_DEFAULT_PRINFO 114
#define SCTP_PR_ASSOC_STATUS 115
#define SCTP_ENABLE_STREAM_RESET 118
+#define SCTP_RESET_STREAMS 119
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
@@ -145,6 +146,9 @@ typedef __s32 sctp_assoc_t;
#define SCTP_ENABLE_CHANGE_ASSOC_REQ 0x04
#define SCTP_ENABLE_STRRESET_MASK 0x07
+#define SCTP_STREAM_RESET_INCOMING 0x01
+#define SCTP_STREAM_RESET_OUTGOING 0x02
+
/* These are bit fields for msghdr->msg_flags. See section 5.1. */
/* On user space Linux, these live in <bits/socket.h> as an enum. */
enum sctp_msg_flags {
@@ -1015,4 +1019,11 @@ struct sctp_info {
__u32 __reserved3;
};
+struct sctp_reset_streams {
+ sctp_assoc_t srs_assoc_id;
+ uint16_t srs_flags;
+ uint16_t srs_number_streams; /* 0 == ALL */
+ uint16_t srs_stream_list[]; /* list if srs_num_streams is not 0 */
+};
+
#endif /* _UAPI_SCTP_H */
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 34efaa4..65abe22 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -915,22 +915,28 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
case SCTP_CID_ECN_ECNE:
case SCTP_CID_ASCONF:
case SCTP_CID_FWD_TSN:
+ case SCTP_CID_RECONF:
status = sctp_packet_transmit_chunk(packet, chunk,
one_packet, gfp);
if (status != SCTP_XMIT_OK) {
/* put the chunk back */
list_add(&chunk->list, &q->control_chunk_list);
- } else {
- asoc->stats.octrlchunks++;
- /* PR-SCTP C5) If a FORWARD TSN is sent, the
- * sender MUST assure that at least one T3-rtx
- * timer is running.
- */
- if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) {
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
- }
+ break;
+ }
+
+ asoc->stats.octrlchunks++;
+ /* PR-SCTP C5) If a FORWARD TSN is sent, the
+ * sender MUST assure that at least one T3-rtx
+ * timer is running.
+ */
+ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) {
+ sctp_transport_reset_t3_rtx(transport);
+ transport->last_time_sent = jiffies;
}
+
+ if (chunk == asoc->strreset_chunk)
+ sctp_transport_reset_reconf_timer(transport);
+
break;
default:
@@ -1016,6 +1022,8 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
/* Finally, transmit new packets. */
while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
+ __u32 sid = ntohs(chunk->subh.data_hdr->stream);
+
/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
* stream identifier.
*/
@@ -1038,6 +1046,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
continue;
}
+ if (asoc->stream->out[sid].state == SCTP_STREAM_CLOSED) {
+ sctp_outq_head_data(q, chunk);
+ goto sctp_flush_out;
+ }
+
/* If there is a specified transport, use it.
* Otherwise, we want to use the active path.
*/
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ae07db4..e072bf7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3787,6 +3787,32 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk,
return retval;
}
+static int sctp_setsockopt_reset_streams(struct sock *sk,
+ char __user *optval,
+ unsigned int optlen)
+{
+ struct sctp_reset_streams *params;
+ struct sctp_association *asoc;
+ int retval = -EINVAL;
+
+ if (optlen < sizeof(struct sctp_reset_streams))
+ return -EINVAL;
+
+ params = memdup_user(optval, optlen);
+ if (IS_ERR(params))
+ return PTR_ERR(params);
+
+ asoc = sctp_id2assoc(sk, params->srs_assoc_id);
+ if (!asoc)
+ goto out;
+
+ retval = sctp_send_reset_streams(asoc, params);
+
+out:
+ kfree(params);
+ return retval;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -3956,6 +3982,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_ENABLE_STREAM_RESET:
retval = sctp_setsockopt_enable_strreset(sk, optval, optlen);
break;
+ case SCTP_RESET_STREAMS:
+ retval = sctp_setsockopt_reset_streams(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f86de43..13d5e07 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -33,6 +33,7 @@
*/
#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp)
{
@@ -83,3 +84,81 @@ void sctp_stream_clear(struct sctp_stream *stream)
for (i = 0; i < stream->incnt; i++)
stream->in[i].ssn = 0;
}
+
+static int sctp_send_reconf(struct sctp_association *asoc,
+ struct sctp_chunk *chunk)
+{
+ struct net *net = sock_net(asoc->base.sk);
+ int retval = 0;
+
+ retval = sctp_primitive_RECONF(net, asoc, chunk);
+ if (retval)
+ sctp_chunk_free(chunk);
+
+ return retval;
+}
+
+int sctp_send_reset_streams(struct sctp_association *asoc,
+ struct sctp_reset_streams *params)
+{
+ struct sctp_stream *stream = asoc->stream;
+ __u16 i, str_nums, *str_list;
+ struct sctp_chunk *chunk;
+ int retval = -EINVAL;
+ bool out, in;
+
+ if (!asoc->peer.reconf_capable ||
+ !(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ)) {
+ retval = -ENOPROTOOPT;
+ goto out;
+ }
+
+ if (asoc->strreset_outstanding) {
+ retval = -EINPROGRESS;
+ goto out;
+ }
+
+ out = params->srs_flags & SCTP_STREAM_RESET_OUTGOING;
+ in = params->srs_flags & SCTP_STREAM_RESET_INCOMING;
+ if (!out && !in)
+ goto out;
+
+ str_nums = params->srs_number_streams;
+ str_list = params->srs_stream_list;
+ if (out && str_nums)
+ for (i = 0; i < str_nums; i++)
+ if (str_list[i] >= stream->outcnt)
+ goto out;
+
+ if (in && str_nums)
+ for (i = 0; i < str_nums; i++)
+ if (str_list[i] >= stream->incnt)
+ goto out;
+
+ chunk = sctp_make_strreset_req(asoc, str_nums, str_list, out, in);
+ if (!chunk)
+ goto out;
+
+ if (out) {
+ if (str_nums)
+ for (i = 0; i < str_nums; i++)
+ stream->out[str_list[i]].state =
+ SCTP_STREAM_CLOSED;
+ else
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_CLOSED;
+ }
+
+ asoc->strreset_outstanding = out + in;
+ asoc->strreset_chunk = chunk;
+ sctp_chunk_hold(asoc->strreset_chunk);
+
+ retval = sctp_send_reconf(asoc, chunk);
+ if (retval) {
+ sctp_chunk_put(asoc->strreset_chunk);
+ asoc->strreset_chunk = NULL;
+ }
+
+out:
+ return retval;
+}
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 6/7] sctp: add sockopt SCTP_ENABLE_STREAM_RESET
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to add sockopt SCTP_ENABLE_STREAM_RESET to get/set
strreset_enable to indicate which reconf request type it supports,
which is described in rfc6525 section 6.3.1.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/structs.h | 4 +++
include/uapi/linux/sctp.h | 7 ++++
net/sctp/associola.c | 1 +
net/sctp/socket.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 96 insertions(+)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ee037ef..d99b76e 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1257,6 +1257,8 @@ struct sctp_endpoint {
__u8 auth_enable:1,
prsctp_enable:1,
reconf_enable:1;
+
+ __u8 strreset_enable;
};
/* Recover the outter endpoint structure. */
@@ -1872,6 +1874,8 @@ struct sctp_association {
prsctp_enable:1,
reconf_enable:1;
+ __u8 strreset_enable;
+
__u32 strreset_outseq; /* Update after receiving response */
__u32 strreset_inseq; /* Update after receiving request */
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index a406adc..867be0f 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -115,6 +115,7 @@ typedef __s32 sctp_assoc_t;
#define SCTP_PR_SUPPORTED 113
#define SCTP_DEFAULT_PRINFO 114
#define SCTP_PR_ASSOC_STATUS 115
+#define SCTP_ENABLE_STREAM_RESET 118
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
@@ -138,6 +139,12 @@ typedef __s32 sctp_assoc_t;
#define SCTP_PR_RTX_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_RTX)
#define SCTP_PR_PRIO_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_PRIO)
+/* For enable stream reset */
+#define SCTP_ENABLE_RESET_STREAM_REQ 0x01
+#define SCTP_ENABLE_RESET_ASSOC_REQ 0x02
+#define SCTP_ENABLE_CHANGE_ASSOC_REQ 0x04
+#define SCTP_ENABLE_STRRESET_MASK 0x07
+
/* These are bit fields for msghdr->msg_flags. See section 5.1. */
/* On user space Linux, these live in <bits/socket.h> as an enum. */
enum sctp_msg_flags {
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 68b99ad..e50dc6d 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -271,6 +271,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
asoc->active_key_id = ep->active_key_id;
asoc->prsctp_enable = ep->prsctp_enable;
asoc->reconf_enable = ep->reconf_enable;
+ asoc->strreset_enable = ep->strreset_enable;
/* Save the hmacs and chunks list into this association */
if (ep->auth_hmacs_list)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 318c678..ae07db4 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3751,6 +3751,42 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk,
return retval;
}
+static int sctp_setsockopt_enable_strreset(struct sock *sk,
+ char __user *optval,
+ unsigned int optlen)
+{
+ struct sctp_assoc_value params;
+ struct sctp_association *asoc;
+ int retval = -EINVAL;
+
+ if (optlen != sizeof(params))
+ goto out;
+
+ if (copy_from_user(¶ms, optval, optlen)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ if (params.assoc_value & (~SCTP_ENABLE_STRRESET_MASK))
+ goto out;
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (asoc) {
+ asoc->strreset_enable = params.assoc_value;
+ } else if (!params.assoc_id) {
+ struct sctp_sock *sp = sctp_sk(sk);
+
+ sp->ep->strreset_enable = params.assoc_value;
+ } else {
+ goto out;
+ }
+
+ retval = 0;
+
+out:
+ return retval;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -3917,6 +3953,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_DEFAULT_PRINFO:
retval = sctp_setsockopt_default_prinfo(sk, optval, optlen);
break;
+ case SCTP_ENABLE_STREAM_RESET:
+ retval = sctp_setsockopt_enable_strreset(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -6401,6 +6440,47 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
return retval;
}
+static int sctp_getsockopt_enable_strreset(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ struct sctp_assoc_value params;
+ struct sctp_association *asoc;
+ int retval = -EFAULT;
+
+ if (len < sizeof(params)) {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ len = sizeof(params);
+ if (copy_from_user(¶ms, optval, len))
+ goto out;
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (asoc) {
+ params.assoc_value = asoc->strreset_enable;
+ } else if (!params.assoc_id) {
+ struct sctp_sock *sp = sctp_sk(sk);
+
+ params.assoc_value = sp->ep->strreset_enable;
+ } else {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ if (put_user(len, optlen))
+ goto out;
+
+ if (copy_to_user(optval, ¶ms, len))
+ goto out;
+
+ retval = 0;
+
+out:
+ return retval;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -6568,6 +6648,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
retval = sctp_getsockopt_pr_assocstatus(sk, len, optval,
optlen);
break;
+ case SCTP_ENABLE_STREAM_RESET:
+ retval = sctp_getsockopt_enable_strreset(sk, len, optval,
+ optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 5/7] sctp: add reconf_enable in asoc ep and netns
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to add reconf_enable field in all of asoc ep and netns
to indicate if they support stream reset.
When initializing, asoc reconf_enable get the default value from ep
reconf_enable which is from netns netns reconf_enable by default.
It is also to add reconf_capable in asoc peer part to know if peer
supports reconf_enable, the value is set if ext params have reconf
chunk support when processing init chunk, just as rfc6525 section
5.1.1 demands.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/netns/sctp.h | 3 +++
include/net/sctp/structs.h | 7 +++++--
net/sctp/associola.c | 1 +
net/sctp/endpointola.c | 1 +
net/sctp/protocol.c | 3 +++
net/sctp/sm_make_chunk.c | 15 +++++++++++++++
6 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index c501d67..b7871d0 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -118,6 +118,9 @@ struct netns_sctp {
/* Flag to indicate if PR-SCTP is enabled. */
int prsctp_enable;
+ /* Flag to indicate if PR-CONFIG is enabled. */
+ int reconf_enable;
+
/* Flag to idicate if SCTP-AUTH is enabled */
int auth_enable;
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 463b4d6..ee037ef 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1255,7 +1255,8 @@ struct sctp_endpoint {
struct list_head endpoint_shared_keys;
__u16 active_key_id;
__u8 auth_enable:1,
- prsctp_enable:1;
+ prsctp_enable:1,
+ reconf_enable:1;
};
/* Recover the outter endpoint structure. */
@@ -1508,6 +1509,7 @@ struct sctp_association {
hostname_address:1, /* Peer understands DNS addresses? */
asconf_capable:1, /* Does peer support ADDIP? */
prsctp_capable:1, /* Can peer do PR-SCTP? */
+ reconf_capable:1, /* Can peer do RE-CONFIG? */
auth_capable:1; /* Is peer doing SCTP-AUTH? */
/* sack_needed : This flag indicates if the next received
@@ -1867,7 +1869,8 @@ struct sctp_association {
__u8 need_ecne:1, /* Need to send an ECNE Chunk? */
temp:1, /* Is it a temporary association? */
- prsctp_enable:1;
+ prsctp_enable:1,
+ reconf_enable:1;
__u32 strreset_outseq; /* Update after receiving response */
__u32 strreset_inseq; /* Update after receiving request */
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index fc33540..68b99ad 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -270,6 +270,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
asoc->active_key_id = ep->active_key_id;
asoc->prsctp_enable = ep->prsctp_enable;
+ asoc->reconf_enable = ep->reconf_enable;
/* Save the hmacs and chunks list into this association */
if (ep->auth_hmacs_list)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 410ddc1..8c58923 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -164,6 +164,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
ep->auth_hmacs_list = auth_hmacs;
ep->auth_chunk_list = auth_chunks;
ep->prsctp_enable = net->sctp.prsctp_enable;
+ ep->reconf_enable = net->sctp.reconf_enable;
return ep;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index f9c3c37..8227bbb 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1258,6 +1258,9 @@ static int __net_init sctp_defaults_init(struct net *net)
/* Enable PR-SCTP by default. */
net->sctp.prsctp_enable = 1;
+ /* Disable RECONF by default. */
+ net->sctp.reconf_enable = 0;
+
/* Disable AUTH by default. */
net->sctp.auth_enable = 0;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 172385c..c4a0a9c 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -270,6 +270,11 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
num_ext += 2;
}
+ if (asoc->reconf_enable) {
+ extensions[num_ext] = SCTP_CID_RECONF;
+ num_ext += 1;
+ }
+
if (sp->adaptation_ind)
chunksize += sizeof(aiparam);
@@ -434,6 +439,11 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
num_ext += 2;
}
+ if (asoc->peer.reconf_capable) {
+ extensions[num_ext] = SCTP_CID_RECONF;
+ num_ext += 1;
+ }
+
if (sp->adaptation_ind)
chunksize += sizeof(aiparam);
@@ -2012,6 +2022,11 @@ static void sctp_process_ext_param(struct sctp_association *asoc,
for (i = 0; i < num_ext; i++) {
switch (param.ext->chunks[i]) {
+ case SCTP_CID_RECONF:
+ if (asoc->reconf_enable &&
+ !asoc->peer.reconf_capable)
+ asoc->peer.reconf_capable = 1;
+ break;
case SCTP_CID_FWD_TSN:
if (asoc->prsctp_enable && !asoc->peer.prsctp_capable)
asoc->peer.prsctp_capable = 1;
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 4/7] sctp: add stream reconf primitive
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to add a primitive based on sctp primitive frame for
sending stream reconf request. It works as the other primitives,
and create a SCTP_CMD_REPLY command to send the request chunk out.
sctp_primitive_RECONF would be the api to send a reconf request
chunk.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/constants.h | 3 ++-
include/net/sctp/sctp.h | 2 ++
include/net/sctp/sm.h | 1 +
net/sctp/primitive.c | 3 +++
net/sctp/sm_statefuns.c | 13 +++++++++++++
net/sctp/sm_statetable.c | 20 ++++++++++++++++++++
6 files changed, 41 insertions(+), 1 deletion(-)
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 8307c86..3567c97 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -114,9 +114,10 @@ typedef enum {
SCTP_PRIMITIVE_SEND,
SCTP_PRIMITIVE_REQUESTHEARTBEAT,
SCTP_PRIMITIVE_ASCONF,
+ SCTP_PRIMITIVE_RECONF,
} sctp_event_primitive_t;
-#define SCTP_EVENT_PRIMITIVE_MAX SCTP_PRIMITIVE_ASCONF
+#define SCTP_EVENT_PRIMITIVE_MAX SCTP_PRIMITIVE_RECONF
#define SCTP_NUM_PRIMITIVE_TYPES (SCTP_EVENT_PRIMITIVE_MAX + 1)
/* We define here a utility type for manipulating subtypes.
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 598d938..bc0e049 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -141,6 +141,8 @@ int sctp_primitive_ABORT(struct net *, struct sctp_association *, void *arg);
int sctp_primitive_SEND(struct net *, struct sctp_association *, void *arg);
int sctp_primitive_REQUESTHEARTBEAT(struct net *, struct sctp_association *, void *arg);
int sctp_primitive_ASCONF(struct net *, struct sctp_association *, void *arg);
+int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc,
+ void *arg);
/*
* sctp/input.c
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index d2d9e28..430ed13 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -157,6 +157,7 @@ sctp_state_fn_t sctp_sf_error_shutdown;
sctp_state_fn_t sctp_sf_ignore_primitive;
sctp_state_fn_t sctp_sf_do_prm_requestheartbeat;
sctp_state_fn_t sctp_sf_do_prm_asconf;
+sctp_state_fn_t sctp_sf_do_prm_reconf;
/* Prototypes for other event state functions. */
sctp_state_fn_t sctp_sf_do_no_pending_tsn;
diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c
index ab8d9f9..f0553a0 100644
--- a/net/sctp/primitive.c
+++ b/net/sctp/primitive.c
@@ -211,3 +211,6 @@ DECLARE_PRIMITIVE(REQUESTHEARTBEAT);
*/
DECLARE_PRIMITIVE(ASCONF);
+
+/* RE-CONFIG 5.1 */
+DECLARE_PRIMITIVE(RECONF);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 2ae186a..782e579 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -5185,6 +5185,19 @@ sctp_disposition_t sctp_sf_do_prm_asconf(struct net *net,
return SCTP_DISPOSITION_CONSUME;
}
+/* RE-CONFIG Section 5.1 RECONF Chunk Procedures */
+sctp_disposition_t sctp_sf_do_prm_reconf(struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const sctp_subtype_t type,
+ void *arg, sctp_cmd_seq_t *commands)
+{
+ struct sctp_chunk *chunk = arg;
+
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(chunk));
+ return SCTP_DISPOSITION_CONSUME;
+}
+
/*
* Ignore the primitive event
*
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index 3da521a..b5438b4 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -643,6 +643,25 @@ chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = {
TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \
} /* TYPE_SCTP_PRIMITIVE_ASCONF */
+#define TYPE_SCTP_PRIMITIVE_RECONF { \
+ /* SCTP_STATE_CLOSED */ \
+ TYPE_SCTP_FUNC(sctp_sf_error_closed), \
+ /* SCTP_STATE_COOKIE_WAIT */ \
+ TYPE_SCTP_FUNC(sctp_sf_error_closed), \
+ /* SCTP_STATE_COOKIE_ECHOED */ \
+ TYPE_SCTP_FUNC(sctp_sf_error_closed), \
+ /* SCTP_STATE_ESTABLISHED */ \
+ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \
+ /* SCTP_STATE_SHUTDOWN_PENDING */ \
+ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \
+ /* SCTP_STATE_SHUTDOWN_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \
+ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \
+ TYPE_SCTP_FUNC(sctp_sf_do_prm_reconf), \
+ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_error_shutdown), \
+} /* TYPE_SCTP_PRIMITIVE_RECONF */
+
/* The primary index for this table is the primitive type.
* The secondary index for this table is the state.
*/
@@ -653,6 +672,7 @@ static const sctp_sm_table_entry_t primitive_event_table[SCTP_NUM_PRIMITIVE_TYPE
TYPE_SCTP_PRIMITIVE_SEND,
TYPE_SCTP_PRIMITIVE_REQUESTHEARTBEAT,
TYPE_SCTP_PRIMITIVE_ASCONF,
+ TYPE_SCTP_PRIMITIVE_RECONF,
};
#define TYPE_SCTP_OTHER_NO_PENDING_TSN { \
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 3/7] sctp: add stream reconf timer
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to add a per transport timer based on sctp timer frame
for stream reconf chunk retransmission. It would start after sending
a reconf request chunk, and stop after receiving the response chunk.
If the timer expires, besides retransmitting the reconf request chunk,
it would also do the same thing with data RTO timer. like to increase
the appropriate error counts, and perform threshold management, possibly
destroying the asoc if sctp retransmission thresholds are exceeded, just
as section 5.1.1 describes.
This patch is also to add asoc strreset_chunk, it is used to save the
reconf request chunk, so that it can be retransmitted, and to check if
the response is really for this request by comparing the information
inside with the response chunk as well.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/constants.h | 1 +
include/net/sctp/sm.h | 2 ++
include/net/sctp/structs.h | 6 ++++++
net/sctp/associola.c | 9 +++++++++
net/sctp/sm_sideeffect.c | 32 ++++++++++++++++++++++++++++++++
net/sctp/sm_statefuns.c | 28 ++++++++++++++++++++++++++++
net/sctp/sm_statetable.c | 20 ++++++++++++++++++++
net/sctp/transport.c | 17 +++++++++++++++--
8 files changed, 113 insertions(+), 2 deletions(-)
diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 5b847e4..8307c86 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -90,6 +90,7 @@ typedef enum {
SCTP_EVENT_TIMEOUT_T4_RTO,
SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD,
SCTP_EVENT_TIMEOUT_HEARTBEAT,
+ SCTP_EVENT_TIMEOUT_RECONF,
SCTP_EVENT_TIMEOUT_SACK,
SCTP_EVENT_TIMEOUT_AUTOCLOSE,
} sctp_event_timeout_t;
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 3462cb0..d2d9e28 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -167,6 +167,7 @@ sctp_state_fn_t sctp_sf_cookie_wait_icmp_abort;
/* Prototypes for timeout event state functions. */
sctp_state_fn_t sctp_sf_do_6_3_3_rtx;
+sctp_state_fn_t sctp_sf_send_reconf;
sctp_state_fn_t sctp_sf_do_6_2_sack;
sctp_state_fn_t sctp_sf_autoclose_timer_expire;
@@ -278,6 +279,7 @@ int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype,
/* 2nd level prototypes */
void sctp_generate_t3_rtx_event(unsigned long peer);
void sctp_generate_heartbeat_event(unsigned long peer);
+void sctp_generate_reconf_event(unsigned long peer);
void sctp_generate_proto_unreach_event(unsigned long peer);
void sctp_ootb_pkt_free(struct sctp_packet *);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 3dc983e..463b4d6 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -877,6 +877,9 @@ struct sctp_transport {
/* Timer to handle ICMP proto unreachable envets */
struct timer_list proto_unreach_timer;
+ /* Timer to handler reconf chunk rtx */
+ struct timer_list reconf_timer;
+
/* Since we're using per-destination retransmission timers
* (see above), we're also using per-destination "transmitted"
* queues. This probably ought to be a private struct
@@ -935,6 +938,7 @@ void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk);
void sctp_transport_free(struct sctp_transport *);
void sctp_transport_reset_t3_rtx(struct sctp_transport *);
void sctp_transport_reset_hb_timer(struct sctp_transport *);
+void sctp_transport_reset_reconf_timer(struct sctp_transport *transport);
int sctp_transport_hold(struct sctp_transport *);
void sctp_transport_put(struct sctp_transport *);
void sctp_transport_update_rto(struct sctp_transport *, __u32);
@@ -1868,6 +1872,8 @@ struct sctp_association {
__u32 strreset_outseq; /* Update after receiving response */
__u32 strreset_inseq; /* Update after receiving request */
+ struct sctp_chunk *strreset_chunk; /* save request chunk */
+
struct sctp_priv_assoc_stats stats;
int sent_cnt_removable;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 42ece6f..fc33540 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -362,6 +362,9 @@ void sctp_association_free(struct sctp_association *asoc)
/* Free stream information. */
sctp_stream_free(asoc->stream);
+ if (asoc->strreset_chunk)
+ sctp_chunk_free(asoc->strreset_chunk);
+
/* Clean up the bound address list. */
sctp_bind_addr_free(&asoc->base.bind_addr);
@@ -520,6 +523,12 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
if (asoc->peer.last_data_from == peer)
asoc->peer.last_data_from = transport;
+ if (asoc->strreset_chunk &&
+ asoc->strreset_chunk->transport == peer) {
+ asoc->strreset_chunk->transport = transport;
+ sctp_transport_reset_reconf_timer(transport);
+ }
+
/* If we remove the transport an INIT was last sent to, set it to
* NULL. Combined with the update of the retran path above, this
* will cause the next INIT to be sent to the next available
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index c345bf1..a455271 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -436,6 +436,37 @@ void sctp_generate_proto_unreach_event(unsigned long data)
sctp_association_put(asoc);
}
+ /* Handle the timeout of the RE-CONFIG timer. */
+void sctp_generate_reconf_event(unsigned long data)
+{
+ struct sctp_transport *transport = (struct sctp_transport *)data;
+ struct sctp_association *asoc = transport->asoc;
+ struct sock *sk = asoc->base.sk;
+ struct net *net = sock_net(sk);
+ int error = 0;
+
+ bh_lock_sock(sk);
+ if (sock_owned_by_user(sk)) {
+ pr_debug("%s: sock is busy\n", __func__);
+
+ /* Try again later. */
+ if (!mod_timer(&transport->reconf_timer, jiffies + (HZ / 20)))
+ sctp_transport_hold(transport);
+ goto out_unlock;
+ }
+
+ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT,
+ SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF),
+ asoc->state, asoc->ep, asoc,
+ transport, GFP_ATOMIC);
+
+ if (error)
+ sk->sk_err = -error;
+
+out_unlock:
+ bh_unlock_sock(sk);
+ sctp_transport_put(transport);
+}
/* Inject a SACK Timeout event into the state machine. */
static void sctp_generate_sack_event(unsigned long data)
@@ -453,6 +484,7 @@ sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = {
sctp_generate_t4_rto_event,
sctp_generate_t5_shutdown_guard_event,
NULL,
+ NULL,
sctp_generate_sack_event,
sctp_generate_autoclose_event,
};
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 0ceded3..2ae186a 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1021,6 +1021,34 @@ sctp_disposition_t sctp_sf_sendbeat_8_3(struct net *net,
return SCTP_DISPOSITION_CONSUME;
}
+/* resend asoc strreset_chunk. */
+sctp_disposition_t sctp_sf_send_reconf(struct net *net,
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const sctp_subtype_t type, void *arg,
+ sctp_cmd_seq_t *commands)
+{
+ struct sctp_transport *transport = arg;
+
+ if (asoc->overall_error_count >= asoc->max_retrans) {
+ sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR,
+ SCTP_ERROR(ETIMEDOUT));
+ /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */
+ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED,
+ SCTP_PERR(SCTP_ERROR_NO_ERROR));
+ SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS);
+ SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB);
+ return SCTP_DISPOSITION_DELETE_TCB;
+ }
+
+ sctp_chunk_hold(asoc->strreset_chunk);
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY,
+ SCTP_CHUNK(asoc->strreset_chunk));
+ sctp_add_cmd_sf(commands, SCTP_CMD_STRIKE, SCTP_TRANSPORT(transport));
+
+ return SCTP_DISPOSITION_CONSUME;
+}
+
/*
* Process an heartbeat request.
*
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index a987d54..3da521a 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -888,6 +888,25 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_
TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
}
+#define TYPE_SCTP_EVENT_TIMEOUT_RECONF { \
+ /* SCTP_STATE_CLOSED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_COOKIE_WAIT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_COOKIE_ECHOED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_ESTABLISHED */ \
+ TYPE_SCTP_FUNC(sctp_sf_send_reconf), \
+ /* SCTP_STATE_SHUTDOWN_PENDING */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+ /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
+ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \
+}
+
static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = {
TYPE_SCTP_EVENT_TIMEOUT_NONE,
TYPE_SCTP_EVENT_TIMEOUT_T1_COOKIE,
@@ -897,6 +916,7 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][S
TYPE_SCTP_EVENT_TIMEOUT_T4_RTO,
TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD,
TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT,
+ TYPE_SCTP_EVENT_TIMEOUT_RECONF,
TYPE_SCTP_EVENT_TIMEOUT_SACK,
TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE,
};
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index a1652ab..baa1ac0 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -88,9 +88,11 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
INIT_LIST_HEAD(&peer->transports);
setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event,
- (unsigned long)peer);
+ (unsigned long)peer);
setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
- (unsigned long)peer);
+ (unsigned long)peer);
+ setup_timer(&peer->reconf_timer, sctp_generate_reconf_event,
+ (unsigned long)peer);
setup_timer(&peer->proto_unreach_timer,
sctp_generate_proto_unreach_event, (unsigned long)peer);
@@ -144,6 +146,9 @@ void sctp_transport_free(struct sctp_transport *transport)
if (del_timer(&transport->T3_rtx_timer))
sctp_transport_put(transport);
+ if (del_timer(&transport->reconf_timer))
+ sctp_transport_put(transport);
+
/* Delete the ICMP proto unreachable timer if it's active. */
if (del_timer(&transport->proto_unreach_timer))
sctp_association_put(transport->asoc);
@@ -211,6 +216,14 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport)
sctp_transport_hold(transport);
}
+void sctp_transport_reset_reconf_timer(struct sctp_transport *transport)
+{
+ if (!timer_pending(&transport->reconf_timer))
+ if (!mod_timer(&transport->reconf_timer,
+ jiffies + transport->rto))
+ sctp_transport_hold(transport);
+}
+
/* This transport has been assigned to an association.
* Initialize fields from the association or from the sock itself.
* Register the reference count in the association.
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 2/7] sctp: add support for generating stream reconf ssn reset request chunk
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to add asoc strreset_outseq and strreset_inseq for
saving the reconf request sequence, initialize them when create
assoc and process init, and also to define Incoming and Outgoing
SSN Reset Request Parameter described in rfc6525 section 4.1 and
4.2, As they can be in one same chunk as section rfc6525 3.1-3
describes, it makes them in one function.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/linux/sctp.h | 26 ++++++++++++++
include/net/sctp/sm.h | 5 ++-
include/net/sctp/structs.h | 3 ++
net/sctp/associola.c | 1 +
net/sctp/sm_make_chunk.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 122 insertions(+), 1 deletion(-)
diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index cdc3b05..d5da19c 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -200,6 +200,13 @@ typedef enum {
SCTP_PARAM_SUCCESS_REPORT = cpu_to_be16(0xc005),
SCTP_PARAM_ADAPTATION_LAYER_IND = cpu_to_be16(0xc006),
+ /* RE-CONFIG. Section 4 */
+ SCTP_PARAM_RESET_OUT_REQUEST = cpu_to_be16(0x000d),
+ SCTP_PARAM_RESET_IN_REQUEST = cpu_to_be16(0x000e),
+ SCTP_PARAM_RESET_TSN_REQUEST = cpu_to_be16(0x000f),
+ SCTP_PARAM_RESET_RESPONSE = cpu_to_be16(0x0010),
+ SCTP_PARAM_RESET_ADD_OUT_STREAMS = cpu_to_be16(0x0011),
+ SCTP_PARAM_RESET_ADD_IN_STREAMS = cpu_to_be16(0x0012),
} sctp_param_t; /* enum */
@@ -716,4 +723,23 @@ struct sctp_reconf_chunk {
__u8 params[0];
} __packed;
+struct sctp_strreset_req {
+ sctp_paramhdr_t param_hdr;
+ __u32 request_seq;
+} __packed;
+
+struct sctp_strreset_outreq {
+ sctp_paramhdr_t param_hdr;
+ __u32 request_seq;
+ __u32 response_seq;
+ __u32 send_reset_at_tsn;
+ __u16 list_of_streams[0];
+} __packed;
+
+struct sctp_strreset_inreq {
+ sctp_paramhdr_t param_hdr;
+ __u32 request_seq;
+ __u16 list_of_streams[0];
+} __packed;
+
#endif /* __LINUX_SCTP_H__ */
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index ca6c971..3462cb0 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -259,7 +259,10 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc,
__u32 new_cum_tsn, size_t nstreams,
struct sctp_fwdtsn_skip *skiplist);
struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc);
-
+struct sctp_chunk *sctp_make_strreset_req(
+ const struct sctp_association *asoc,
+ __u16 stream_num, __u16 *stream_list,
+ bool out, bool in);
void sctp_chunk_assign_tsn(struct sctp_chunk *);
void sctp_chunk_assign_ssn(struct sctp_chunk *);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 4741ec2..3dc983e 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1865,6 +1865,9 @@ struct sctp_association {
temp:1, /* Is it a temporary association? */
prsctp_enable:1;
+ __u32 strreset_outseq; /* Update after receiving response */
+ __u32 strreset_inseq; /* Update after receiving request */
+
struct sctp_priv_assoc_stats stats;
int sent_cnt_removable;
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 36294f7..42ece6f 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -207,6 +207,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
* association to the same value as the initial TSN.
*/
asoc->addip_serial = asoc->c.initial_tsn;
+ asoc->strreset_outseq = asoc->c.initial_tsn;
INIT_LIST_HEAD(&asoc->addip_chunk_list);
INIT_LIST_HEAD(&asoc->asconf_ack_list);
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index fd58097..172385c 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1844,6 +1844,7 @@ struct sctp_association *sctp_unpack_cookie(
retval->next_tsn = retval->c.initial_tsn;
retval->ctsn_ack_point = retval->next_tsn - 1;
retval->addip_serial = retval->c.initial_tsn;
+ retval->strreset_outseq = retval->c.initial_tsn;
retval->adv_peer_ack_point = retval->ctsn_ack_point;
retval->peer.prsctp_capable = retval->c.prsctp_capable;
retval->peer.adaptation_ind = retval->c.adaptation_ind;
@@ -2387,6 +2388,8 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
asoc->peer.i.initial_tsn =
ntohl(peer_init->init_hdr.initial_tsn);
+ asoc->strreset_inseq = asoc->peer.i.initial_tsn;
+
/* Apply the upper bounds for output streams based on peer's
* number of inbound streams.
*/
@@ -3559,3 +3562,88 @@ static struct sctp_chunk *sctp_make_reconf(
return retval;
}
+
+/* RE-CONFIG 4.1 (STREAM OUT RESET)
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Parameter Type = 13 | Parameter Length = 16 + 2 * N |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Re-configuration Request Sequence Number |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Re-configuration Response Sequence Number |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Sender's Last Assigned TSN |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Stream Number 1 (optional) | Stream Number 2 (optional) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * / ...... /
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Stream Number N-1 (optional) | Stream Number N (optional) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * RE-CONFIG 4.2 (STREAM IN RESET)
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Parameter Type = 14 | Parameter Length = 8 + 2 * N |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Re-configuration Request Sequence Number |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Stream Number 1 (optional) | Stream Number 2 (optional) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * / ...... /
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Stream Number N-1 (optional) | Stream Number N (optional) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+struct sctp_chunk *sctp_make_strreset_req(
+ const struct sctp_association *asoc,
+ __u16 stream_num, __u16 *stream_list,
+ bool out, bool in)
+{
+ struct sctp_strreset_outreq outreq;
+ __u16 stream_len = stream_num * 2;
+ struct sctp_strreset_inreq inreq;
+ struct sctp_chunk *retval;
+ __u16 outlen, inlen, i;
+
+ outlen = (sizeof(outreq) + stream_len) * out;
+ inlen = (sizeof(inreq) + stream_len) * in;
+
+ retval = sctp_make_reconf(asoc, outlen + inlen);
+ if (!retval)
+ return NULL;
+
+ for (i = 0; i < stream_num; i++)
+ stream_list[i] = htons(stream_list[i]);
+
+ if (outlen) {
+ outreq.param_hdr.type = SCTP_PARAM_RESET_OUT_REQUEST;
+ outreq.param_hdr.length = htons(outlen);
+ outreq.request_seq = htonl(asoc->strreset_outseq);
+ outreq.response_seq = htonl(asoc->strreset_inseq - 1);
+ outreq.send_reset_at_tsn = htonl(asoc->next_tsn - 1);
+
+ sctp_addto_chunk(retval, sizeof(outreq), &outreq);
+
+ if (stream_len)
+ sctp_addto_chunk(retval, stream_len, stream_list);
+ }
+
+ if (inlen) {
+ inreq.param_hdr.type = SCTP_PARAM_RESET_IN_REQUEST;
+ inreq.param_hdr.length = htons(inlen);
+ inreq.request_seq = htonl(asoc->strreset_outseq + out);
+
+ sctp_addto_chunk(retval, sizeof(inreq), &inreq);
+
+ if (stream_len)
+ sctp_addto_chunk(retval, stream_len, stream_list);
+ }
+
+ for (i = 0; i < stream_num; i++)
+ stream_list[i] = ntohs(stream_list[i]);
+
+ return retval;
+}
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 1/7] sctp: add a common helper function to generate stream reconf chunk
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
In-Reply-To: <cover.1484334002.git.lucien.xin@gmail.com>
This patch is to define a common api used to alloc memory and initialize
reconf chunk header that described in rfc6525 section 3.1.
All reconf chunks will be generated by calling this helper function.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/linux/sctp.h | 6 ++++++
net/sctp/sm_make_chunk.c | 33 +++++++++++++++++++++++++++++++++
2 files changed, 39 insertions(+)
diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index fcb4c36..cdc3b05 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -108,6 +108,7 @@ typedef enum {
/* Use hex, as defined in ADDIP sec. 3.1 */
SCTP_CID_ASCONF = 0xC1,
SCTP_CID_ASCONF_ACK = 0x80,
+ SCTP_CID_RECONF = 0x82,
} sctp_cid_t; /* enum */
@@ -710,4 +711,9 @@ struct sctp_infox {
struct sctp_association *asoc;
};
+struct sctp_reconf_chunk {
+ sctp_chunkhdr_t chunk_hdr;
+ __u8 params[0];
+} __packed;
+
#endif /* __LINUX_SCTP_H__ */
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index a15d824..fd58097 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -3526,3 +3526,36 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc,
return retval;
}
+
+/* RE-CONFIG 3.1 (RE-CONFIG chunk)
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Type = 130 | Chunk Flags | Chunk Length |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * \ \
+ * / Re-configuration Parameter /
+ * \ \
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * \ \
+ * / Re-configuration Parameter (optional) /
+ * \ \
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+static struct sctp_chunk *sctp_make_reconf(
+ const struct sctp_association *asoc,
+ int length)
+{
+ struct sctp_reconf_chunk *reconf;
+ struct sctp_chunk *retval;
+
+ retval = sctp_make_control(asoc, SCTP_CID_RECONF, 0, length,
+ GFP_ATOMIC);
+ if (!retval)
+ return NULL;
+
+ reconf = (struct sctp_reconf_chunk *)retval->chunk_hdr;
+ retval->param_hdr.v = reconf->params;
+
+ return retval;
+}
--
2.1.0
^ permalink raw reply related
* [PATCHv3 net-next 0/7] sctp: add sender-side procedures for stream reconf ssn reset request chunk
From: Xin Long @ 2017-01-13 19:15 UTC (permalink / raw)
To: network dev, linux-sctp
Cc: Marcelo Ricardo Leitner, Neil Horman, Vlad Yasevich, davem
Patch 7/7 is to implement sender-side procedures for the Outgoing
and Incoming SSN Reset Request Parameter described in rfc6525
section 5.1.2 and 5.1.3
Patches 1-6/7 are ahead of it to define some apis and asoc members
for it.
Note that with this patchset, asoc->reconf_enable has no chance yet to
be set, until the patch "sctp: add get and set sockopt for reconf_enable"
is applied in the future. As we can not just enable it when sctp is not
capable of processing reconf chunk yet.
v1->v2:
- put these into a smaller group.
- rename some temporary variables in the codes.
- rename the titles of the commits and improve some changelogs.
v2->v3:
- re-split the patchset and make sure it has no dead codes for review.
Xin Long (7):
sctp: add a common helper function to generate stream reconf chunk
sctp: add support for generating stream reconf ssn reset request chunk
sctp: add stream reconf timer
sctp: add stream reconf primitive
sctp: add reconf_enable in asoc ep and netns
sctp: add sockopt SCTP_ENABLE_STREAM_RESET
sctp: implement sender-side procedures for SSN Reset Request Parameter
include/linux/sctp.h | 32 ++++++++++
include/net/netns/sctp.h | 3 +
include/net/sctp/constants.h | 4 +-
include/net/sctp/sctp.h | 8 +++
include/net/sctp/sm.h | 8 ++-
include/net/sctp/structs.h | 21 ++++++-
include/uapi/linux/sctp.h | 18 ++++++
net/sctp/associola.c | 12 ++++
net/sctp/endpointola.c | 1 +
net/sctp/outqueue.c | 33 +++++++----
net/sctp/primitive.c | 3 +
net/sctp/protocol.c | 3 +
net/sctp/sm_make_chunk.c | 136 +++++++++++++++++++++++++++++++++++++++++++
net/sctp/sm_sideeffect.c | 32 ++++++++++
net/sctp/sm_statefuns.c | 41 +++++++++++++
net/sctp/sm_statetable.c | 40 +++++++++++++
net/sctp/socket.c | 113 +++++++++++++++++++++++++++++++++++
net/sctp/stream.c | 79 +++++++++++++++++++++++++
net/sctp/transport.c | 17 +++++-
19 files changed, 588 insertions(+), 16 deletions(-)
--
2.1.0
^ permalink raw reply
* Re: [PATCH][V2] flow dissector: check if arp_eth is null rather than arp
From: Eric Dumazet @ 2017-01-13 19:02 UTC (permalink / raw)
To: Colin King
Cc: David S . Miller, Alexander Duyck, Jiri Pirko, Tom Herbert,
Eric Dumazet, Hadar Hen Zion, Simon Horman, Gao Feng, Amir Vadai,
netdev, linux-kernel
In-Reply-To: <20170113184820.823-1-colin.king@canonical.com>
On Fri, 2017-01-13 at 18:48 +0000, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> arp is being checked instead of arp_eth to see if the call to
> __skb_header_pointer failed. Fix this by checking arp_eth is
> null instead of arp. Also fix to use length hlen rather than
> hlen - sizeof(_arp); thanks to Eric Dumazet for spotting
> this latter issue.
>
> CoverityScan CID#1396428 ("Logically dead code") on 2nd
> arp comparison (which should be arp_eth instead).
>
> Fixes: commit 55733350e5e8b70c5 ("flow disector: ARP support")
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
> ---
Acked-by: Eric Dumazet <edumazet@google.com>
Thanks !
^ permalink raw reply
* Re: [PATCH net-next] mii_bus: increase MII_BUS_ID_SIZE to 61
From: Florian Fainelli @ 2017-01-13 18:59 UTC (permalink / raw)
To: Andrew Lunn, Volodymyr Bendiuga
Cc: netdev, volodymyr.bendiuga, Magnus Öberg
In-Reply-To: <20170113163108.GN10203@lunn.ch>
On 01/13/2017 08:31 AM, Andrew Lunn wrote:
> On Fri, Jan 13, 2017 at 04:19:12PM +0100, Volodymyr Bendiuga wrote:
>> From: Volodymyr Bendiuga <volodymyr.bendiuga@westermo.se>
>>
>> Some bus names are pretty long and do not fit into 20 chars.
>>
>> Signed-off-by: Volodymyr Bendiuga <volodymyr.bendiuga@westermo.se>
>> Signed-off-by: Magnus Öberg <magnus.oberg@westermo.se>
>> ---
>> include/linux/phy.h | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/include/linux/phy.h b/include/linux/phy.h
>> index feb8a98..b67f94d 100644
>> --- a/include/linux/phy.h
>> +++ b/include/linux/phy.h
>> @@ -162,7 +162,7 @@ static inline const char *phy_modes(phy_interface_t interface)
>> * Need to be a little smaller than phydev->dev.bus_id to leave room
>> * for the ":%02x"
>> */
>> -#define MII_BUS_ID_SIZE (20 - 3)
>> +#define MII_BUS_ID_SIZE (64 - 3)
>
> Hi Volodymyr
>
> Humm, i assume you looked at the comment? What is the size of phydev->dev.bus_id?
> Is 61 still a little smaller?
Also it seems like you missed this one:
/* A Structure for boards to register fixups with the PHY Lib */
struct phy_fixup {
struct list_head list;
char bus_id[20];
^================
u32 phy_uid;
u32 phy_uid_mask;
int (*run)(struct phy_device *phydev);
};
Did you really run into naming conflicts where increasing the bus ID
size became the only solution here?
--
Florian
^ permalink raw reply
* [PATCH][V2] flow dissector: check if arp_eth is null rather than arp
From: Colin King @ 2017-01-13 18:48 UTC (permalink / raw)
To: David S . Miller, Alexander Duyck, Jiri Pirko, Tom Herbert,
Eric Dumazet, Hadar Hen Zion, Simon Horman, Gao Feng, Amir Vadai,
netdev
Cc: linux-kernel
From: Colin Ian King <colin.king@canonical.com>
arp is being checked instead of arp_eth to see if the call to
__skb_header_pointer failed. Fix this by checking arp_eth is
null instead of arp. Also fix to use length hlen rather than
hlen - sizeof(_arp); thanks to Eric Dumazet for spotting
this latter issue.
CoverityScan CID#1396428 ("Logically dead code") on 2nd
arp comparison (which should be arp_eth instead).
Fixes: commit 55733350e5e8b70c5 ("flow disector: ARP support")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
---
net/core/flow_dissector.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e3dffc7..c35aae1 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -407,9 +407,9 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
sizeof(_arp_eth), data,
- hlen - sizeof(_arp),
+ hlen,
&_arp_eth);
- if (!arp)
+ if (!arp_eth)
goto out_bad;
if (dissector_uses_key(flow_dissector,
--
2.10.2
^ permalink raw reply related
* Re: [PATCH] flow disector: check if arp_eth is null rather than arp
From: Eric Dumazet @ 2017-01-13 18:36 UTC (permalink / raw)
To: Colin Ian King
Cc: David S . Miller, Alexander Duyck, Jiri Pirko, Tom Herbert,
Eric Dumazet, Simon Horman, Hadar Hen Zion, Gao Feng, Amir Vadai,
netdev, linux-kernel
In-Reply-To: <7b26e04c-b3f1-a82f-8f18-d93207388a28@canonical.com>
On Fri, 2017-01-13 at 18:25 +0000, Colin Ian King wrote:
> On 13/01/17 18:24, Eric Dumazet wrote:
> > It looks that we try very hard to add critical bugs in flow dissector.
> >
> > This is embarrassing really.
> >
> > I am questioning if the __skb_header_pointer() is correct
> >
> > Why using hlen - sizeof(_arp) ?
> >
> > arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
> > sizeof(_arp_eth), data,
> > hlen - sizeof(_arp),
> > &_arp_eth);
> >
>
> Yep, the sizeof maybe dubious too, I overlooked that one; if somebody
> can clarify that then I'll send a V2 if it needs fixing up too.
I am pretty sure we should use hlen instead of (hlen - sizeof(_arp))
A V2 would be nice ;)
^ permalink raw reply
* Re: [PATCH] flow disector: check if arp_eth is null rather than arp
From: Eric Dumazet @ 2017-01-13 18:24 UTC (permalink / raw)
To: Colin King
Cc: David S . Miller, Alexander Duyck, Jiri Pirko, Tom Herbert,
Eric Dumazet, Simon Horman, Hadar Hen Zion, Gao Feng, Amir Vadai,
netdev, linux-kernel
In-Reply-To: <20170113133428.20130-1-colin.king@canonical.com>
On Fri, 2017-01-13 at 13:34 +0000, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> arp is being checked instead of arp_eth to see if the call to
> __skb_header_pointer failed. Fix this by checking arp_eth is
> null instead of arp.
>
> CoverityScan CID#1396428 ("Logically dead code") on 2nd
> arp comparison (which should be arp_eth instead).
>
> Fixes: commit 55733350e5e8b70c5 ("flow disector: ARP support")
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
> ---
> net/core/flow_dissector.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
> index e3dffc7..fec48e9 100644
> --- a/net/core/flow_dissector.c
> +++ b/net/core/flow_dissector.c
> @@ -409,7 +409,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
> sizeof(_arp_eth), data,
> hlen - sizeof(_arp),
> &_arp_eth);
> - if (!arp)
> + if (!arp_eth)
> goto out_bad;
>
> if (dissector_uses_key(flow_dissector,
It looks that we try very hard to add critical bugs in flow dissector.
This is embarrassing really.
I am questioning if the __skb_header_pointer() is correct
Why using hlen - sizeof(_arp) ?
arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
sizeof(_arp_eth), data,
hlen - sizeof(_arp),
&_arp_eth);
^ permalink raw reply
* Re: [Patch net] atm: remove an unnecessary loop
From: Cong Wang @ 2017-01-13 18:20 UTC (permalink / raw)
To: David Miller
Cc: Francois Romieu, Linux Kernel Network Developers, Michal Hocko,
Chas Williams, Andrey Konovalov
In-Reply-To: <20170113.121001.2197905484527884236.davem@davemloft.net>
On Fri, Jan 13, 2017 at 9:10 AM, David Miller <davem@davemloft.net> wrote:
> From: Francois Romieu <romieu@fr.zoreil.com>
> Date: Fri, 13 Jan 2017 01:07:00 +0100
>
>> Were alloc_skb moved one level up in the call stack, there would be
>> no need to use the new wait api in the subsequent page, thus easing
>> pre 3.19 longterm kernel maintenance (at least those on korg page).
>>
>> But it tastes a tad bit too masochistic.
>
> Lack of error handling of allocation failure is always a huge red
> flag. We even long ago tried to do something like this for TCP FIN
> handling.
>
> It's dumb, it doesn't work.
>
> Therefore I agree that the correct fix is to move the SKB allocation
> up one level to vcc_sendmsg() and make it handle errors properly.
If you can justify API is not broken by doing that, I am more than happy
to do it, as I already stated in the latter patch:
"Of course, the logic itself is suspicious, other sendmsg()
could handle skb allocation failure very well, not sure
why ATM has to wait for a successful one here. But probably
it is too late to change since the errno and behavior is
visible to user-space. So just leave the logic as it is."
For some reason, no one reads that patch. :-/
^ permalink raw reply
* Re: [PATCH] flow disector: check if arp_eth is null rather than arp
From: Colin Ian King @ 2017-01-13 18:25 UTC (permalink / raw)
To: Eric Dumazet
Cc: David S . Miller, Alexander Duyck, Jiri Pirko, Tom Herbert,
Eric Dumazet, Simon Horman, Hadar Hen Zion, Gao Feng, Amir Vadai,
netdev, linux-kernel
In-Reply-To: <1484331851.13165.46.camel@edumazet-glaptop3.roam.corp.google.com>
On 13/01/17 18:24, Eric Dumazet wrote:
> On Fri, 2017-01-13 at 13:34 +0000, Colin King wrote:
>> From: Colin Ian King <colin.king@canonical.com>
>>
>> arp is being checked instead of arp_eth to see if the call to
>> __skb_header_pointer failed. Fix this by checking arp_eth is
>> null instead of arp.
>>
>> CoverityScan CID#1396428 ("Logically dead code") on 2nd
>> arp comparison (which should be arp_eth instead).
>>
>> Fixes: commit 55733350e5e8b70c5 ("flow disector: ARP support")
>> Signed-off-by: Colin Ian King <colin.king@canonical.com>
>> ---
>> net/core/flow_dissector.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
>> index e3dffc7..fec48e9 100644
>> --- a/net/core/flow_dissector.c
>> +++ b/net/core/flow_dissector.c
>> @@ -409,7 +409,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
>> sizeof(_arp_eth), data,
>> hlen - sizeof(_arp),
>> &_arp_eth);
>> - if (!arp)
>> + if (!arp_eth)
>> goto out_bad;
>>
>> if (dissector_uses_key(flow_dissector,
>
> It looks that we try very hard to add critical bugs in flow dissector.
>
> This is embarrassing really.
>
> I am questioning if the __skb_header_pointer() is correct
>
> Why using hlen - sizeof(_arp) ?
>
> arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp),
> sizeof(_arp_eth), data,
> hlen - sizeof(_arp),
> &_arp_eth);
>
Yep, the sizeof maybe dubious too, I overlooked that one; if somebody
can clarify that then I'll send a V2 if it needs fixing up too.
Colin
^ permalink raw reply
* Re: [Patch net] atm: remove an unnecessary loop
From: Cong Wang @ 2017-01-13 18:18 UTC (permalink / raw)
To: Francois Romieu
Cc: Linux Kernel Network Developers, Michal Hocko, Chas Williams,
Andrey Konovalov
In-Reply-To: <20170113132346.GA19220@electric-eye.fr.zoreil.com>
On Fri, Jan 13, 2017 at 5:23 AM, Francois Romieu <romieu@fr.zoreil.com> wrote:
> Cong Wang <xiyou.wangcong@gmail.com> :
> [...]
>> alloc_skb(GFP_KERNEL) itself is sleeping, so the new wait api is still
>> needed.
>
> The task state change warning is the symptom.
>
> The deeply nested alloc_skb is the problem.
>
> Diagnosis: nesting is wrong. It makes zero sense. Fix it and the
> implicit task state change problem automagically goes away.
>
> alloc_skb() does not need to be in the "while" loop.
This is exactly what I describe in my changelog, don't know
why you want to repeat it...
>
> alloc_skb() does not need to be in the {prepare_to_wait/add_wait_queue ...
> finish_wait/remove_wait_queue} block.
>
If you ever read the followup patch of this one, you will find:
"
Of course, the logic itself is suspicious, other sendmsg()
could handle skb allocation failure very well, not sure
why ATM has to wait for a successful one here. But probably
it is too late to change since the errno and behavior is
visible to user-space. So just leave the logic as it is.
"
> alloc_tx() is not correctly named: given its original content, it deserves
> to be called something like:
Please don't expect me to fix many things in one patch, let's
fix each of them separately, agreed?
>
> "wait_for_decent_tx_drain_and_alloc_by_hand_coz_i_dont_trust_the_mm_subsystem_and_i_dont_know_what_i_want"
>
> I claim that:
> - alloc_tx() should only perform the "wait_for_decent_tx_drain" part
> - alloc_skb() ought to be done directly in vcc_sendmsg
> - alloc_skb() failure can be handled gracefully in vcc_sendmsg
> - alloc_skb() may use a (m->msg_flags & MSG_DONTWAIT) dependant
> GFP_{KERNEL / ATOMIC} flag
> - most of it can be done in a longterm maintenance pain minimizing
> way. Call it a side-effect: I don't claim that it *must* be done
> this way.
Never disagree, but again, please ensure there is no API brokeness
as I mentioned in the followup patch which you missed. Apparently
my ATM knowledge is not enough to justify the API/ABI.
Thanks.
^ permalink raw reply
* Re: [RFC PATCH] tcp: accept RST for rcv_nxt - 1 after receiving a FIN
From: Eric Dumazet @ 2017-01-13 18:17 UTC (permalink / raw)
To: Jason Baron; +Cc: netdev
In-Reply-To: <10070e29-2278-8df4-4abb-61a16895dfa4@akamai.com>
On Fri, 2017-01-13 at 12:28 -0500, Jason Baron wrote:
> i,
>
> (Re-sending - seems like my reply was lost)
>
> I wanted to define this condition as narrowly as I could. I'm ok
> dropping it -
> I'm not sure its going to make much difference in practice. So to that end,
> dropping this extra check makes sense.
>
> I posted this as RFC because RFC 5961, I don't think says anything about
> accepting rcv_nxt - 1 in this case, so I was wondering what people
> thought...
This seems a reasonable trade-off to me
( to the rescue : RFC 1122 1.2.2 )
^ permalink raw reply
* [PATCH net-next 2/2] mpls: Packet stats
From: Robert Shearman @ 2017-01-13 18:14 UTC (permalink / raw)
To: davem; +Cc: netdev, roopa, David Ahern, ebiederm, Robert Shearman
In-Reply-To: <1484331253-5908-1-git-send-email-rshearma@brocade.com>
Having MPLS packet stats is useful for observing network operation and
for diagnosing network problems. In the absence of anything better,
RFC2863 and RFC3813 are used for guidance for which stats to expose
and the semantics of them. In particular rx_noroutes maps to in
unknown protos in RFC2863. The stats are exposed to userspace via
AF_MPLS attributes embedded in the IFLA_STATS_AF_SPEC attribute of
RTM_GETSTATS messages.
All the introduced fields are 64-bit, even error ones, to ensure no
overflow with long uptimes. Per-CPU counters are used to avoid
cache-line contention on the commonly used fields. The other fields
have also been made per-CPU for code to avoid performance problems in
error conditions on the assumption that on some platforms the cost of
atomic operations could be more expensive than sending the packet
(which is what would be done in the success case). If that's not the
case, we could instead not use per-CPU counters for these fields.
Only unicast and non-fragment are exposed at the moment, but other
counters can be exposed in the future either by adding to the end of
struct mpls_link_stats or by additional netlink attributes in the
AF_MPLS IFLA_STATS_AF_SPEC nested attribute.
Signed-off-by: Robert Shearman <rshearma@brocade.com>
---
include/uapi/linux/mpls.h | 30 ++++++++
net/mpls/af_mpls.c | 179 ++++++++++++++++++++++++++++++++++++++++------
net/mpls/internal.h | 58 ++++++++++++++-
net/mpls/mpls_iptunnel.c | 11 ++-
4 files changed, 250 insertions(+), 28 deletions(-)
diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
index 24a6cb1aec86..77a19dfe3990 100644
--- a/include/uapi/linux/mpls.h
+++ b/include/uapi/linux/mpls.h
@@ -43,4 +43,34 @@ struct mpls_label {
#define MPLS_LABEL_FIRST_UNRESERVED 16 /* RFC3032 */
+/* These are embedded into IFLA_STATS_AF_SPEC:
+ * [IFLA_STATS_AF_SPEC]
+ * -> [AF_MPLS]
+ * -> [MPLS_STATS_xxx]
+ *
+ * Attributes:
+ * [MPLS_STATS_LINK] = {
+ * struct mpls_link_stats
+ * }
+ */
+enum {
+ MPLS_STATS_UNSPEC, /* also used as 64bit pad attribute */
+ MPLS_STATS_LINK,
+ __MPLS_STATS_MAX,
+};
+
+#define MPLS_STATS_MAX (__MPLS_STATS_MAX - 1)
+
+struct mpls_link_stats {
+ __u64 rx_packets; /* total packets received */
+ __u64 tx_packets; /* total packets transmitted */
+ __u64 rx_bytes; /* total bytes received */
+ __u64 tx_bytes; /* total bytes transmitted */
+ __u64 rx_errors; /* bad packets received */
+ __u64 tx_errors; /* packet transmit problems */
+ __u64 rx_dropped; /* packet dropped on receive */
+ __u64 tx_dropped; /* packet dropped on transmit */
+ __u64 rx_noroute; /* no route for packet dest */
+};
+
#endif /* _UAPI_MPLS_H */
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 15fe97644ffe..fb20941cdda2 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -8,6 +8,7 @@
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/vmalloc.h>
+#include <linux/percpu.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
@@ -17,8 +18,8 @@
#include <net/netns/generic.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
-#include <net/addrconf.h>
#endif
+#include <net/addrconf.h>
#include <net/nexthop.h>
#include "internal.h"
@@ -48,11 +49,6 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
return rt;
}
-static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
-{
- return rcu_dereference_rtnl(dev->mpls_ptr);
-}
-
bool mpls_output_possible(const struct net_device *dev)
{
return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
@@ -98,6 +94,29 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
}
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
+void mpls_stats_inc_outucastpkts(struct net_device *dev,
+ const struct sk_buff *skb)
+{
+ struct mpls_dev *mdev;
+ struct inet6_dev *in6dev;
+
+ if (skb->protocol == htons(ETH_P_MPLS_UC)) {
+ mdev = mpls_dev_get(dev);
+ if (mdev)
+ MPLS_INC_STATS_LEN(mdev, skb->len,
+ tx_packets,
+ tx_bytes);
+ } else if (skb->protocol == htons(ETH_P_IP)) {
+ IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ in6dev = __in6_dev_get(dev);
+ if (in6dev)
+ IP6_UPD_PO_STATS(dev_net(dev), in6dev,
+ IPSTATS_MIB_OUT, skb->len);
+ }
+}
+EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts);
+
static u32 mpls_multipath_hash(struct mpls_route *rt,
struct sk_buff *skb, bool bos)
{
@@ -253,6 +272,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct mpls_nh *nh;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
+ struct mpls_dev *out_mdev;
struct mpls_dev *mdev;
unsigned int hh_len;
unsigned int new_header_size;
@@ -262,17 +282,25 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
/* Careful this entire function runs inside of an rcu critical section */
mdev = mpls_dev_get(dev);
- if (!mdev || !mdev->input_enabled)
+ if (!mdev)
goto drop;
- if (skb->pkt_type != PACKET_HOST)
+ MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets,
+ rx_bytes);
+
+ if (!mdev->input_enabled) {
+ MPLS_INC_STATS(mdev, rx_dropped);
goto drop;
+ }
+
+ if (skb->pkt_type != PACKET_HOST)
+ goto err;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
- goto drop;
+ goto err;
if (!pskb_may_pull(skb, sizeof(*hdr)))
- goto drop;
+ goto err;
/* Read and decode the label */
hdr = mpls_hdr(skb);
@@ -285,33 +313,35 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
skb_orphan(skb);
rt = mpls_route_input_rcu(net, dec.label);
- if (!rt)
+ if (!rt) {
+ MPLS_INC_STATS(mdev, rx_noroute);
goto drop;
+ }
nh = mpls_select_multipath(rt, skb, dec.bos);
if (!nh)
- goto drop;
-
- /* Find the output device */
- out_dev = rcu_dereference(nh->nh_dev);
- if (!mpls_output_possible(out_dev))
- goto drop;
+ goto err;
if (skb_warn_if_lro(skb))
- goto drop;
+ goto err;
skb_forward_csum(skb);
/* Verify ttl is valid */
if (dec.ttl <= 1)
- goto drop;
+ goto err;
dec.ttl -= 1;
+ /* Find the output device */
+ out_dev = rcu_dereference(nh->nh_dev);
+ if (!mpls_output_possible(out_dev))
+ goto tx_err;
+
/* Verify the destination can hold the packet */
new_header_size = mpls_nh_header_size(nh);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
- goto drop;
+ goto tx_err;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
@@ -319,7 +349,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
- goto drop;
+ goto tx_err;
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
@@ -327,7 +357,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
if (!mpls_egress(rt, skb, dec))
- goto drop;
+ goto err;
} else {
bool bos;
int i;
@@ -343,6 +373,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
}
}
+ mpls_stats_inc_outucastpkts(out_dev, skb);
+
/* If via wasn't specified then send out using device address */
if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC)
err = neigh_xmit(NEIGH_LINK_TABLE, out_dev,
@@ -355,6 +387,13 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
__func__, err);
return 0;
+tx_err:
+ out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
+ if (out_mdev)
+ MPLS_INC_STATS(out_mdev, tx_errors);
+ goto drop;
+err:
+ MPLS_INC_STATS(mdev, rx_errors);
drop:
kfree_skb(skb);
return NET_RX_DROP;
@@ -853,6 +892,70 @@ static int mpls_route_del(struct mpls_route_config *cfg)
return err;
}
+static void mpls_get_stats(struct mpls_dev *mdev,
+ struct mpls_link_stats *stats)
+{
+ struct mpls_pcpu_stats *p;
+ int i;
+
+ memset(stats, 0, sizeof(*stats));
+
+ for_each_possible_cpu(i) {
+ struct mpls_link_stats local;
+ unsigned int start;
+
+ p = per_cpu_ptr(mdev->stats, i);
+ do {
+ start = u64_stats_fetch_begin(&p->syncp);
+ local = p->stats;
+ } while (u64_stats_fetch_retry(&p->syncp, start));
+
+ stats->rx_packets += local.rx_packets;
+ stats->rx_bytes += local.rx_bytes;
+ stats->tx_packets += local.tx_packets;
+ stats->tx_bytes += local.tx_bytes;
+ stats->rx_errors += local.rx_errors;
+ stats->tx_errors += local.tx_errors;
+ stats->rx_dropped += local.rx_dropped;
+ stats->tx_dropped += local.tx_dropped;
+ stats->rx_noroute += local.rx_noroute;
+ }
+}
+
+static int mpls_fill_stats_af(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ struct mpls_link_stats *stats;
+ struct mpls_dev *mdev;
+ struct nlattr *nla;
+
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return -ENODATA;
+
+ nla = nla_reserve_64bit(skb, MPLS_STATS_LINK,
+ sizeof(struct mpls_link_stats),
+ MPLS_STATS_UNSPEC);
+ if (!nla)
+ return -EMSGSIZE;
+
+ stats = nla_data(nla);
+ mpls_get_stats(mdev, stats);
+
+ return 0;
+}
+
+static size_t mpls_get_stats_af_size(const struct net_device *dev)
+{
+ struct mpls_dev *mdev;
+
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return 0;
+
+ return nla_total_size_64bit(sizeof(struct mpls_link_stats));
+}
+
#define MPLS_PERDEV_SYSCTL_OFFSET(field) \
(&((struct mpls_dev *)0)->field)
@@ -911,6 +1014,7 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
{
struct mpls_dev *mdev;
int err = -ENOMEM;
+ int i;
ASSERT_RTNL();
@@ -918,6 +1022,17 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
if (!mdev)
return ERR_PTR(err);
+ mdev->stats = alloc_percpu(struct mpls_pcpu_stats);
+ if (!mdev->stats)
+ goto free;
+
+ for_each_possible_cpu(i) {
+ struct mpls_pcpu_stats *mpls_stats;
+
+ mpls_stats = per_cpu_ptr(mdev->stats, i);
+ u64_stats_init(&mpls_stats->syncp);
+ }
+
err = mpls_dev_sysctl_register(dev, mdev);
if (err)
goto free;
@@ -927,10 +1042,19 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev)
return mdev;
free:
+ free_percpu(mdev->stats);
kfree(mdev);
return ERR_PTR(err);
}
+static void mpls_dev_destroy_rcu(struct rcu_head *head)
+{
+ struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu);
+
+ free_percpu(mdev->stats);
+ kfree(mdev);
+}
+
static void mpls_ifdown(struct net_device *dev, int event)
{
struct mpls_route __rcu **platform_label;
@@ -1045,7 +1169,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
if (mdev) {
mpls_dev_sysctl_unregister(mdev);
RCU_INIT_POINTER(dev->mpls_ptr, NULL);
- kfree_rcu(mdev, rcu);
+ call_rcu(&mdev->rcu, mpls_dev_destroy_rcu);
}
break;
case NETDEV_CHANGENAME:
@@ -1706,6 +1830,12 @@ static struct pernet_operations mpls_net_ops = {
.exit = mpls_net_exit,
};
+static struct rtnl_af_ops mpls_af_ops __read_mostly = {
+ .family = AF_MPLS,
+ .fill_stats_af = mpls_fill_stats_af,
+ .get_stats_af_size = mpls_get_stats_af_size,
+};
+
static int __init mpls_init(void)
{
int err;
@@ -1722,6 +1852,8 @@ static int __init mpls_init(void)
dev_add_pack(&mpls_packet_type);
+ rtnl_af_register(&mpls_af_ops);
+
rtnl_register(PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, NULL);
rtnl_register(PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, NULL);
rtnl_register(PF_MPLS, RTM_GETROUTE, NULL, mpls_dump_routes, NULL);
@@ -1738,6 +1870,7 @@ module_init(mpls_init);
static void __exit mpls_exit(void)
{
rtnl_unregister_all(PF_MPLS);
+ rtnl_af_unregister(&mpls_af_ops);
dev_remove_pack(&mpls_packet_type);
unregister_netdevice_notifier(&mpls_dev_notifier);
unregister_pernet_subsys(&mpls_net_ops);
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index bdfef6c3271a..d97243034605 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -9,13 +9,58 @@ struct mpls_entry_decoded {
u8 bos;
};
+struct mpls_pcpu_stats {
+ struct mpls_link_stats stats;
+ struct u64_stats_sync syncp;
+};
+
struct mpls_dev {
- int input_enabled;
+ int input_enabled;
- struct ctl_table_header *sysctl;
- struct rcu_head rcu;
+ struct mpls_pcpu_stats __percpu *stats;
+
+ struct ctl_table_header *sysctl;
+ struct rcu_head rcu;
};
+#if BITS_PER_LONG == 32
+
+#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \
+ do { \
+ __typeof__(*(mdev)->stats) *ptr = \
+ raw_cpu_ptr((mdev)->stats); \
+ local_bh_disable(); \
+ u64_stats_update_begin(&ptr->syncp); \
+ ptr->stats.pkts_field++; \
+ ptr->stats.bytes_field += (len); \
+ u64_stats_update_end(&ptr->syncp); \
+ local_bh_enable(); \
+ } while (0)
+
+#define MPLS_INC_STATS(mdev, field) \
+ do { \
+ __typeof__(*(mdev)->stats) *ptr = \
+ raw_cpu_ptr((mdev)->stats); \
+ local_bh_disable(); \
+ u64_stats_update_begin(&ptr->syncp); \
+ ptr->stats.field++; \
+ u64_stats_update_end(&ptr->syncp); \
+ local_bh_enable(); \
+ } while (0)
+
+#else
+
+#define MPLS_INC_STATS_LEN(mdev, len, pkts_field, bytes_field) \
+ do { \
+ this_cpu_inc((mdev)->stats->stats.pkts_field); \
+ this_cpu_add((mdev)->stats->stats.bytes_field, (len)); \
+ } while (0)
+
+#define MPLS_INC_STATS(mdev, field) \
+ this_cpu_inc((mdev)->stats->stats.field)
+
+#endif
+
struct sk_buff;
#define LABEL_NOT_SPECIFIED (1 << 20)
@@ -114,6 +159,11 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr *
return result;
}
+static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
+{
+ return rcu_dereference_rtnl(dev->mpls_ptr);
+}
+
int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels,
const u32 label[]);
int nla_get_labels(const struct nlattr *nla, u32 max_labels, u8 *labels,
@@ -123,5 +173,7 @@ int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
bool mpls_output_possible(const struct net_device *dev);
unsigned int mpls_dev_mtu(const struct net_device *dev);
bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu);
+void mpls_stats_inc_outucastpkts(struct net_device *dev,
+ const struct sk_buff *skb);
#endif /* MPLS_INTERNAL_H */
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2f7ccd934416..02531284bc49 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -48,11 +48,15 @@ static int mpls_xmit(struct sk_buff *skb)
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = NULL;
struct rt6_info *rt6 = NULL;
+ struct mpls_dev *out_mdev;
int err = 0;
bool bos;
int i;
unsigned int ttl;
+ /* Find the output device */
+ out_dev = dst->dev;
+
/* Obtain the ttl */
if (dst->ops->family == AF_INET) {
ttl = ip_hdr(skb)->ttl;
@@ -66,8 +70,6 @@ static int mpls_xmit(struct sk_buff *skb)
skb_orphan(skb);
- /* Find the output device */
- out_dev = dst->dev;
if (!mpls_output_possible(out_dev) ||
!dst->lwtstate || skb_warn_if_lro(skb))
goto drop;
@@ -109,6 +111,8 @@ static int mpls_xmit(struct sk_buff *skb)
bos = false;
}
+ mpls_stats_inc_outucastpkts(out_dev, skb);
+
if (rt)
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
skb);
@@ -122,6 +126,9 @@ static int mpls_xmit(struct sk_buff *skb)
return LWTUNNEL_XMIT_DONE;
drop:
+ out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
+ if (out_mdev)
+ MPLS_INC_STATS(out_mdev, tx_errors);
kfree_skb(skb);
return -EINVAL;
}
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 1/2] net: AF-specific RTM_GETSTATS attributes
From: Robert Shearman @ 2017-01-13 18:14 UTC (permalink / raw)
To: davem; +Cc: netdev, roopa, David Ahern, ebiederm, Robert Shearman
In-Reply-To: <1484331253-5908-1-git-send-email-rshearma@brocade.com>
Add the functionality for including address-family-specific per-link
stats in RTM_GETSTATS messages. This is done through adding a new
IFLA_STATS_AF_SPEC attribute under which address family attributes are
nested and then the AF-specific attributes can be further nested. This
follows the model of IFLA_AF_SPEC on RTM_*LINK messages and it has the
advantage of presenting an easily extended hierarchy. The rtnl_af_ops
structure is extended to provide AFs with the opportunity to fill and
provide the size of their stats attributes.
One alternative would have been to provide AFs with the ability to add
attributes directly into the RTM_GETSTATS message without a nested
hierarchy. I discounted this approach as it increases the rate at
which the 32 attribute number space is used up and it makes
implementation a little more tricky for stats dump resuming (at the
moment the order in which attributes are added to the message has to
match the numeric order of the attributes).
Another alternative would have been to register per-AF RTM_GETSTATS
handlers. I discounted this approach as I perceived a common use-case
to be getting all the stats for an interface and this approach would
necessitate multiple requests/dumps to retrieve them all.
Signed-off-by: Robert Shearman <rshearma@brocade.com>
---
include/net/rtnetlink.h | 4 ++++
include/uapi/linux/if_link.h | 1 +
net/core/rtnetlink.c | 50 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 55 insertions(+)
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 4113916cc1bb..106de5f7bf06 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -139,6 +139,10 @@ struct rtnl_af_ops {
const struct nlattr *attr);
int (*set_link_af)(struct net_device *dev,
const struct nlattr *attr);
+
+ int (*fill_stats_af)(struct sk_buff *skb,
+ const struct net_device *dev);
+ size_t (*get_stats_af_size)(const struct net_device *dev);
};
void __rtnl_af_unregister(struct rtnl_af_ops *ops);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 6b13e591abc9..184b16ed2b84 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -847,6 +847,7 @@ enum {
IFLA_STATS_LINK_XSTATS,
IFLA_STATS_LINK_XSTATS_SLAVE,
IFLA_STATS_LINK_OFFLOAD_XSTATS,
+ IFLA_STATS_AF_SPEC,
__IFLA_STATS_MAX,
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 18b5aae99bec..4edc1bd7a735 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3829,6 +3829,39 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
*idxattr = 0;
}
+ if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, *idxattr)) {
+ struct rtnl_af_ops *af_ops;
+
+ *idxattr = IFLA_STATS_AF_SPEC;
+ attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC);
+ if (!attr)
+ goto nla_put_failure;
+
+ list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ if (af_ops->fill_stats_af) {
+ struct nlattr *af;
+ int err;
+
+ af = nla_nest_start(skb, af_ops->family);
+ if (!af)
+ goto nla_put_failure;
+
+ err = af_ops->fill_stats_af(skb, dev);
+
+ if (err == -ENODATA)
+ nla_nest_cancel(skb, af);
+ else if (err < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(skb, af);
+ }
+ }
+
+ nla_nest_end(skb, attr);
+
+ *idxattr = 0;
+ }
+
nlmsg_end(skb, nlh);
return 0;
@@ -3885,6 +3918,23 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev,
if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS, 0))
size += rtnl_get_offload_stats_size(dev);
+ if (stats_attr_valid(filter_mask, IFLA_STATS_AF_SPEC, 0)) {
+ struct rtnl_af_ops *af_ops;
+
+ /* for IFLA_STATS_AF_SPEC */
+ size += nla_total_size(0);
+
+ list_for_each_entry(af_ops, &rtnl_af_ops, list) {
+ if (af_ops->get_stats_af_size) {
+ size += nla_total_size(
+ af_ops->get_stats_af_size(dev));
+
+ /* for AF_* */
+ size += nla_total_size(0);
+ }
+ }
+ }
+
return size;
}
--
2.1.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox