* Re: [PATCH 1/4] dt-bindings: net: ravb: Document optional reset-gpios property
From: Sergei Shtylyov @ 2017-09-28 20:07 UTC (permalink / raw)
To: Geert Uytterhoeven, David S . Miller, Simon Horman, Magnus Damm
Cc: Andrew Lunn, Florian Fainelli, Niklas Söderlund, netdev,
linux-renesas-soc, devicetree
In-Reply-To: <1506614014-4398-2-git-send-email-geert+renesas@glider.be>
Hello!
On 09/28/2017 06:53 PM, Geert Uytterhoeven wrote:
> The optional "reset-gpios" property (part of the generic MDIO bus
> properties) lets us describe the GPIO used for resetting the Ethernet
> PHY.
>
> Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
> ---
> Documentation/devicetree/bindings/net/renesas,ravb.txt | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
> index c902261893b913f5..4a6ec1ba32d0bf16 100644
> --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
> +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
> @@ -52,6 +52,7 @@ Optional properties:
> AVB_LINK signal.
> - renesas,ether-link-active-low: boolean, specify when the AVB_LINK signal is
> active-low instead of normal active-high.
> +- reset-gpios: see mdio.txt in the same directory.
Sigh, I can only repeat that was a terrible prop name choice -- when
applied to a MAC node... what reset does it mean? MAC?
MBR, Sergei
^ permalink raw reply
* [PATCH net-next 00/10] Introduce SCTP Stream Schedulers
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
This patchset introduces the SCTP Stream Schedulers are defined by
https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
It provides 3 schedulers at the moment: FCFS, Priority and Round Robin.
The other 3, Round Robin per packet, Fair Capacity and Weighted Fair
Capacity will be added later. More specifically, WFQ is required by
WebRTC Datachannels.
The draft also defines the idata chunk, allowing a usermsg to be
interrupted by another piece of idata from another stream. This patchset
*doesn't* include it. It will be posted later by Xin Long. Its
integration with this patchset is very simple and it basically only
requires a tweak in sctp_sched_dequeue_done(), to ignore datamsg
boundaries.
The first 5 patches are a preparation for the next ones. The most
relevant patches are the 4th and 6th ones. More details are available on
each patch.
Marcelo Ricardo Leitner (10):
sctp: silence warns on sctp_stream_init allocations
sctp: factor out stream->out allocation
sctp: factor out stream->in allocation
sctp: introduce struct sctp_stream_out_ext
sctp: introduce sctp_chunk_stream_no
sctp: introduce stream scheduler foundations
sctp: add sockopt to get/set stream scheduler
sctp: add sockopt to get/set stream scheduler parameters
sctp: introduce priority based stream scheduler
sctp: introduce round robin stream scheduler
include/net/sctp/stream_sched.h | 72 +++++++++
include/net/sctp/structs.h | 63 +++++++-
include/uapi/linux/sctp.h | 16 ++
net/sctp/Makefile | 3 +-
net/sctp/chunk.c | 6 +-
net/sctp/outqueue.c | 63 ++++----
net/sctp/sm_sideeffect.c | 3 +
net/sctp/socket.c | 179 ++++++++++++++++++++-
net/sctp/stream.c | 196 +++++++++++++++++++----
net/sctp/stream_sched.c | 275 +++++++++++++++++++++++++++++++
net/sctp/stream_sched_prio.c | 347 ++++++++++++++++++++++++++++++++++++++++
net/sctp/stream_sched_rr.c | 201 +++++++++++++++++++++++
12 files changed, 1347 insertions(+), 77 deletions(-)
create mode 100644 include/net/sctp/stream_sched.h
create mode 100644 net/sctp/stream_sched.c
create mode 100644 net/sctp/stream_sched_prio.c
create mode 100644 net/sctp/stream_sched_rr.c
--
2.13.5
^ permalink raw reply
* [PATCH net-next 01/10] sctp: silence warns on sctp_stream_init allocations
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
As SCTP supports up to 65535 streams, that can lead to very large
allocations in sctp_stream_init(). As Xin Long noticed, systems with
small amounts of memory are more prone to not have enough memory and
dump warnings on dmesg initiated by user actions. Thus, silence them.
Also, if the reallocation of stream->out is not necessary, skip it and
keep the memory we already have.
Reported-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/stream.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 63ea1550371493ec8863627c7a43f46a22f4a4c9..1afa9555808390d5fc736727422d9700a3855613 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -40,9 +40,14 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
{
int i;
+ gfp |= __GFP_NOWARN;
+
/* Initial stream->out size may be very big, so free it and alloc
- * a new one with new outcnt to save memory.
+ * a new one with new outcnt to save memory if needed.
*/
+ if (outcnt == stream->outcnt)
+ goto in;
+
kfree(stream->out);
stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp);
@@ -53,6 +58,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
for (i = 0; i < stream->outcnt; i++)
stream->out[i].state = SCTP_STREAM_OPEN;
+in:
if (!incnt)
return 0;
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 02/10] sctp: factor out stream->out allocation
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
There is 1 place allocating it and 2 other reallocating. Move such
procedures to a common function.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/stream.c | 52 ++++++++++++++++++++++++++++++++--------------------
1 file changed, 32 insertions(+), 20 deletions(-)
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 1afa9555808390d5fc736727422d9700a3855613..6d0e997d301f89e165367106c02e82f8a6c3a877 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -35,6 +35,30 @@
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
+ gfp_t gfp)
+{
+ struct sctp_stream_out *out;
+
+ out = kmalloc_array(outcnt, sizeof(*out), gfp);
+ if (!out)
+ return -ENOMEM;
+
+ if (stream->out) {
+ memcpy(out, stream->out, min(outcnt, stream->outcnt) *
+ sizeof(*out));
+ kfree(stream->out);
+ }
+
+ if (outcnt > stream->outcnt)
+ memset(out + stream->outcnt, 0,
+ (outcnt - stream->outcnt) * sizeof(*out));
+
+ stream->out = out;
+
+ return 0;
+}
+
int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
gfp_t gfp)
{
@@ -48,11 +72,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
if (outcnt == stream->outcnt)
goto in;
- kfree(stream->out);
-
- stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp);
- if (!stream->out)
- return -ENOMEM;
+ i = sctp_stream_alloc_out(stream, outcnt, gfp);
+ if (i)
+ return i;
stream->outcnt = outcnt;
for (i = 0; i < stream->outcnt; i++)
@@ -276,15 +298,9 @@ int sctp_send_add_streams(struct sctp_association *asoc,
}
if (out) {
- struct sctp_stream_out *streamout;
-
- streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
- GFP_KERNEL);
- if (!streamout)
+ retval = sctp_stream_alloc_out(stream, outcnt, GFP_KERNEL);
+ if (retval)
goto out;
-
- memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
- stream->out = streamout;
}
chunk = sctp_make_strreset_addstrm(asoc, out, in);
@@ -682,10 +698,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
struct sctp_strreset_addstrm *addstrm = param.v;
struct sctp_stream *stream = &asoc->stream;
__u32 result = SCTP_STRRESET_DENIED;
- struct sctp_stream_out *streamout;
struct sctp_chunk *chunk = NULL;
__u32 request_seq, outcnt;
__u16 out, i;
+ int ret;
request_seq = ntohl(addstrm->request_seq);
if (TSN_lt(asoc->strreset_inseq, request_seq) ||
@@ -714,14 +730,10 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in(
if (!out || outcnt > SCTP_MAX_STREAM)
goto out;
- streamout = krealloc(stream->out, outcnt * sizeof(*streamout),
- GFP_ATOMIC);
- if (!streamout)
+ ret = sctp_stream_alloc_out(stream, outcnt, GFP_ATOMIC);
+ if (ret)
goto out;
- memset(streamout + stream->outcnt, 0, out * sizeof(*streamout));
- stream->out = streamout;
-
chunk = sctp_make_strreset_addstrm(asoc, out, 0);
if (!chunk)
goto out;
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 03/10] sctp: factor out stream->in allocation
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
Same idea as previous patch.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/stream.c | 36 ++++++++++++++++++++++++++++--------
1 file changed, 28 insertions(+), 8 deletions(-)
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6d0e997d301f89e165367106c02e82f8a6c3a877..952437d656cc71ad1c133a736c539eff9a8d80c2 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -59,6 +59,31 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
return 0;
}
+static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
+ gfp_t gfp)
+{
+ struct sctp_stream_in *in;
+
+ in = kmalloc_array(incnt, sizeof(*stream->in), gfp);
+
+ if (!in)
+ return -ENOMEM;
+
+ if (stream->in) {
+ memcpy(in, stream->in, min(incnt, stream->incnt) *
+ sizeof(*in));
+ kfree(stream->in);
+ }
+
+ if (incnt > stream->incnt)
+ memset(in + stream->incnt, 0,
+ (incnt - stream->incnt) * sizeof(*in));
+
+ stream->in = in;
+
+ return 0;
+}
+
int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
gfp_t gfp)
{
@@ -84,8 +109,8 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
if (!incnt)
return 0;
- stream->in = kcalloc(incnt, sizeof(*stream->in), gfp);
- if (!stream->in) {
+ i = sctp_stream_alloc_in(stream, incnt, gfp);
+ if (i) {
kfree(stream->out);
stream->out = NULL;
return -ENOMEM;
@@ -623,7 +648,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
struct sctp_strreset_addstrm *addstrm = param.v;
struct sctp_stream *stream = &asoc->stream;
__u32 result = SCTP_STRRESET_DENIED;
- struct sctp_stream_in *streamin;
__u32 request_seq, incnt;
__u16 in, i;
@@ -670,13 +694,9 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out(
if (!in || incnt > SCTP_MAX_STREAM)
goto out;
- streamin = krealloc(stream->in, incnt * sizeof(*streamin),
- GFP_ATOMIC);
- if (!streamin)
+ if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC))
goto out;
- memset(streamin + stream->incnt, 0, in * sizeof(*streamin));
- stream->in = streamin;
stream->incnt = incnt;
result = SCTP_STRRESET_PERFORMED;
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 04/10] sctp: introduce struct sctp_stream_out_ext
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
With the stream schedulers, sctp_stream_out will become too big to be
allocated by kmalloc and as we need to allocate with BH disabled, we
cannot use __vmalloc in sctp_stream_init().
This patch moves out the stats from sctp_stream_out to
sctp_stream_out_ext, which will be allocated only when the application
tries to sendmsg something on it.
Just the introduction of sctp_stream_out_ext would already fix the issue
described above by splitting the allocation in two. Moving the stats
to it also reduces the pressure on the allocator as we will ask for less
memory atomically when creating the socket and we will use GFP_KERNEL
later.
Then, for stream schedulers, we will just use sctp_stream_out_ext.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/net/sctp/structs.h | 10 ++++++++--
net/sctp/chunk.c | 6 +++---
net/sctp/outqueue.c | 4 ++--
net/sctp/socket.c | 27 +++++++++++++++++++++------
net/sctp/stream.c | 16 ++++++++++++++++
5 files changed, 50 insertions(+), 13 deletions(-)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0477945de1a3cf5c27348e99d9a30e02c491d1de..9b2b30b3ba4dfd10c24c3e06ed80779180a06baf 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -84,6 +84,7 @@ struct sctp_ulpq;
struct sctp_ep_common;
struct crypto_shash;
struct sctp_stream;
+struct sctp_stream_out;
#include <net/sctp/tsnmap.h>
@@ -380,6 +381,7 @@ struct sctp_sender_hb_info {
int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
gfp_t gfp);
+int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid);
void sctp_stream_free(struct sctp_stream *stream);
void sctp_stream_clear(struct sctp_stream *stream);
void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new);
@@ -1315,11 +1317,15 @@ struct sctp_inithdr_host {
__u32 initial_tsn;
};
+struct sctp_stream_out_ext {
+ __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
+ __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+};
+
struct sctp_stream_out {
__u16 ssn;
__u8 state;
- __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
- __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+ struct sctp_stream_out_ext *ext;
};
struct sctp_stream_in {
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 3afac275ee82dbec825dd71378dffe69a53718a7..7b261afc47b9d709fdd780a93aaba874f35d79be 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -311,10 +311,10 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
if (chunk->sent_count) {
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
- streamout->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
+ streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
} else {
chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
- streamout->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
+ streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++;
}
return 1;
} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
@@ -323,7 +323,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
- streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
+ streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
return 1;
} else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) &&
chunk->msg->expires_at &&
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 2966ff400755fe93e3658e09d3bb44b9d7d19d2e..746b07b7937d8730824b9e09917d947aa7863ec6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -366,7 +366,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
streamout = &asoc->stream.out[chk->sinfo.sinfo_stream];
asoc->sent_cnt_removable--;
asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
- streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
+ streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
if (!chk->tsn_gap_acked) {
if (chk->transport)
@@ -404,7 +404,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
struct sctp_stream_out *streamout =
&asoc->stream.out[chk->sinfo.sinfo_stream];
- streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
+ streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
}
msg_len -= SCTP_DATA_SNDSIZE(chk) +
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d4730ada7f3233367be7a0e3bb10e286a25602c8..d207734326b085e60625e4333f74221481114892 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1927,6 +1927,13 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len)
goto out_free;
}
+ /* Allocate sctp_stream_out_ext if not already done */
+ if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) {
+ err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
+ if (err)
+ goto out_free;
+ }
+
if (sctp_wspace(asoc) < msg_len)
sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));
@@ -6645,7 +6652,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
char __user *optval,
int __user *optlen)
{
- struct sctp_stream_out *streamout;
+ struct sctp_stream_out_ext *streamoute;
struct sctp_association *asoc;
struct sctp_prstatus params;
int retval = -EINVAL;
@@ -6668,21 +6675,29 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
if (!asoc || params.sprstat_sid >= asoc->stream.outcnt)
goto out;
- streamout = &asoc->stream.out[params.sprstat_sid];
+ streamoute = asoc->stream.out[params.sprstat_sid].ext;
+ if (!streamoute) {
+ /* Not allocated yet, means all stats are 0 */
+ params.sprstat_abandoned_unsent = 0;
+ params.sprstat_abandoned_sent = 0;
+ retval = 0;
+ goto out;
+ }
+
if (policy == SCTP_PR_SCTP_NONE) {
params.sprstat_abandoned_unsent = 0;
params.sprstat_abandoned_sent = 0;
for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
params.sprstat_abandoned_unsent +=
- streamout->abandoned_unsent[policy];
+ streamoute->abandoned_unsent[policy];
params.sprstat_abandoned_sent +=
- streamout->abandoned_sent[policy];
+ streamoute->abandoned_sent[policy];
}
} else {
params.sprstat_abandoned_unsent =
- streamout->abandoned_unsent[__SCTP_PR_INDEX(policy)];
+ streamoute->abandoned_unsent[__SCTP_PR_INDEX(policy)];
params.sprstat_abandoned_sent =
- streamout->abandoned_sent[__SCTP_PR_INDEX(policy)];
+ streamoute->abandoned_sent[__SCTP_PR_INDEX(policy)];
}
if (put_user(len, optlen) || copy_to_user(optval, ¶ms, len)) {
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 952437d656cc71ad1c133a736c539eff9a8d80c2..055ca25bbc91bf932db8048c72a1b11cc2214942 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -121,8 +121,24 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
return 0;
}
+int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
+{
+ struct sctp_stream_out_ext *soute;
+
+ soute = kzalloc(sizeof(*soute), GFP_KERNEL);
+ if (!soute)
+ return -ENOMEM;
+ stream->out[sid].ext = soute;
+
+ return 0;
+}
+
void sctp_stream_free(struct sctp_stream *stream)
{
+ int i;
+
+ for (i = 0; i < stream->outcnt; i++)
+ kfree(stream->out[i].ext);
kfree(stream->out);
kfree(stream->in);
}
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 05/10] sctp: introduce sctp_chunk_stream_no
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
Add a helper to fetch the stream number from a given chunk.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/net/sctp/structs.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 9b2b30b3ba4dfd10c24c3e06ed80779180a06baf..c48f7999fe9b80c5b5e41910a3608059b94140a7 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -642,6 +642,11 @@ void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *,
union sctp_addr *);
const union sctp_addr *sctp_source(const struct sctp_chunk *chunk);
+static inline __u16 sctp_chunk_stream_no(struct sctp_chunk *ch)
+{
+ return ntohs(ch->subh.data_hdr->stream);
+}
+
enum {
SCTP_ADDR_NEW, /* new address added to assoc/ep */
SCTP_ADDR_SRC, /* address can be used as source */
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 06/10] sctp: introduce stream scheduler foundations
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
This patch introduces the hooks necessary to do stream scheduling, as
per RFC Draft ndata. It also introduces the first scheduler, which is
what we do today but now factored out: first come first served (FCFS).
With stream scheduling now we have to track which chunk was enqueued on
which stream and be able to select another other than the in front of
the main outqueue. So we introduce a list on sctp_stream_out_ext
structure for this purpose.
We reuse sctp_chunk->transmitted_list space for the list above, as the
chunk cannot belong to the two lists at the same time. By using the
union in there, we can have distinct names for these moments.
sctp_sched_ops are the operations expected to be implemented by each
scheduler. The dequeueing is a bit particular to this implementation but
it is to match how we dequeue packets today. We first dequeue and then
check if it fits the packet and if not, we requeue it at head. Thus why
we don't have a peek operation but have dequeue_done instead, which is
called once the chunk can be safely considered as transmitted.
The check removed from sctp_outq_flush is now performed by
sctp_stream_outq_migrate, which is only called during assoc setup.
(sctp_sendmsg() also checks for it)
The only operation that is foreseen but not yet added here is a way to
signalize that a new packet is starting or that the packet is done, for
round robin scheduler per packet, but is intentionally left to the
patch that actually implements it.
Support for IDATA chunks, also described in this RFC, with user message
interleaving is straightforward as it just requires the schedulers to
probe for the feature and ignore datamsg boundaries when dequeueing.
See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/net/sctp/stream_sched.h | 72 +++++++++++
include/net/sctp/structs.h | 15 ++-
include/uapi/linux/sctp.h | 6 +
net/sctp/Makefile | 2 +-
net/sctp/outqueue.c | 59 +++++----
net/sctp/sm_sideeffect.c | 3 +
net/sctp/stream.c | 88 +++++++++++--
net/sctp/stream_sched.c | 270 ++++++++++++++++++++++++++++++++++++++++
8 files changed, 477 insertions(+), 38 deletions(-)
create mode 100644 include/net/sctp/stream_sched.h
create mode 100644 net/sctp/stream_sched.c
diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h
new file mode 100644
index 0000000000000000000000000000000000000000..c676550a4c7dd0ea27ac0e14437d0a2b451ef499
--- /dev/null
+++ b/include/net/sctp/stream_sched.h
@@ -0,0 +1,72 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * These are definitions used by the stream schedulers, defined in RFC
+ * draft ndata (https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-11)
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ * ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresses:
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#ifndef __sctp_stream_sched_h__
+#define __sctp_stream_sched_h__
+
+struct sctp_sched_ops {
+ /* Property handling for a given stream */
+ int (*set)(struct sctp_stream *stream, __u16 sid, __u16 value,
+ gfp_t gfp);
+ int (*get)(struct sctp_stream *stream, __u16 sid, __u16 *value);
+
+ /* Init the specific scheduler */
+ int (*init)(struct sctp_stream *stream);
+ /* Init a stream */
+ int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+ /* Frees the entire thing */
+ void (*free)(struct sctp_stream *stream);
+
+ /* Enqueue a chunk */
+ void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg);
+ /* Dequeue a chunk */
+ struct sctp_chunk *(*dequeue)(struct sctp_outq *q);
+ /* Called only if the chunk fit the packet */
+ void (*dequeue_done)(struct sctp_outq *q, struct sctp_chunk *chunk);
+ /* Sched all chunks already enqueued */
+ void (*sched_all)(struct sctp_stream *steam);
+ /* Unched all chunks already enqueued */
+ void (*unsched_all)(struct sctp_stream *steam);
+};
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+ enum sctp_sched_type sched);
+int sctp_sched_get_sched(struct sctp_association *asoc);
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+ __u16 value, gfp_t gfp);
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+ __u16 *value);
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch);
+
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch);
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp);
+struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream);
+
+#endif /* __sctp_stream_sched_h__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index c48f7999fe9b80c5b5e41910a3608059b94140a7..3c22a30fd71b4ef87419a77cf69b00807a5986bb 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -84,7 +84,6 @@ struct sctp_ulpq;
struct sctp_ep_common;
struct crypto_shash;
struct sctp_stream;
-struct sctp_stream_out;
#include <net/sctp/tsnmap.h>
@@ -531,8 +530,12 @@ struct sctp_chunk {
/* How many times this chunk have been sent, for prsctp RTX policy */
int sent_count;
- /* This is our link to the per-transport transmitted list. */
- struct list_head transmitted_list;
+ union {
+ /* This is our link to the per-transport transmitted list. */
+ struct list_head transmitted_list;
+ /* List in specific stream outq */
+ struct list_head stream_list;
+ };
/* This field is used by chunks that hold fragmented data.
* For the first fragment this is the list that holds the rest of
@@ -1019,6 +1022,9 @@ struct sctp_outq {
/* Data pending that has never been transmitted. */
struct list_head out_chunk_list;
+ /* Stream scheduler being used */
+ struct sctp_sched_ops *sched;
+
unsigned int out_qlen; /* Total length of queued data chunks. */
/* Error of send failed, may used in SCTP_SEND_FAILED event. */
@@ -1325,6 +1331,7 @@ struct sctp_inithdr_host {
struct sctp_stream_out_ext {
__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
+ struct list_head outq; /* chunks enqueued by this stream */
};
struct sctp_stream_out {
@@ -1342,6 +1349,8 @@ struct sctp_stream {
struct sctp_stream_in *in;
__u16 outcnt;
__u16 incnt;
+ /* Current stream being sent, if any */
+ struct sctp_stream_out *out_curr;
};
#define SCTP_STREAM_CLOSED 0x00
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 6217ff8500a1d818fd1002fbd6f81c0c11974665..4487e7625ddbd48be1868a8292a807ecd0a314bc 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -1088,4 +1088,10 @@ struct sctp_add_streams {
uint16_t sas_outstrms;
};
+/* SCTP Stream schedulers */
+enum sctp_sched_type {
+ SCTP_SS_FCFS,
+ SCTP_SS_MAX = SCTP_SS_FCFS
+};
+
#endif /* _UAPI_SCTP_H */
diff --git a/net/sctp/Makefile b/net/sctp/Makefile
index 70f1b570bab9764d692f1c2e605d76d056cda2cd..0f6e6d1d69fd336b4a99f896851b0120f9a0d1e0 100644
--- a/net/sctp/Makefile
+++ b/net/sctp/Makefile
@@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
inqueue.o outqueue.o ulpqueue.o \
tsnmap.o bind_addr.o socket.o primitive.o \
output.o input.o debug.o stream.o auth.o \
- offload.o
+ offload.o stream_sched.o
sctp_probe-y := probe.o
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 746b07b7937d8730824b9e09917d947aa7863ec6..4db012aa25f7a042f063bc17b56270effebc6cc6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -50,6 +50,7 @@
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
/* Declare internal functions here. */
static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn);
@@ -72,32 +73,38 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp);
/* Add data to the front of the queue. */
static inline void sctp_outq_head_data(struct sctp_outq *q,
- struct sctp_chunk *ch)
+ struct sctp_chunk *ch)
{
+ struct sctp_stream_out_ext *oute;
+ __u16 stream;
+
list_add(&ch->list, &q->out_chunk_list);
q->out_qlen += ch->skb->len;
+
+ stream = sctp_chunk_stream_no(ch);
+ oute = q->asoc->stream.out[stream].ext;
+ list_add(&ch->stream_list, &oute->outq);
}
/* Take data from the front of the queue. */
static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q)
{
- struct sctp_chunk *ch = NULL;
-
- if (!list_empty(&q->out_chunk_list)) {
- struct list_head *entry = q->out_chunk_list.next;
-
- ch = list_entry(entry, struct sctp_chunk, list);
- list_del_init(entry);
- q->out_qlen -= ch->skb->len;
- }
- return ch;
+ return q->sched->dequeue(q);
}
+
/* Add data chunk to the end of the queue. */
static inline void sctp_outq_tail_data(struct sctp_outq *q,
struct sctp_chunk *ch)
{
+ struct sctp_stream_out_ext *oute;
+ __u16 stream;
+
list_add_tail(&ch->list, &q->out_chunk_list);
q->out_qlen += ch->skb->len;
+
+ stream = sctp_chunk_stream_no(ch);
+ oute = q->asoc->stream.out[stream].ext;
+ list_add_tail(&ch->stream_list, &oute->outq);
}
/*
@@ -207,6 +214,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
INIT_LIST_HEAD(&q->retransmit);
INIT_LIST_HEAD(&q->sacked);
INIT_LIST_HEAD(&q->abandoned);
+ sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
}
/* Free the outqueue structure and any related pending chunks.
@@ -258,6 +266,7 @@ static void __sctp_outq_teardown(struct sctp_outq *q)
/* Throw away any leftover data chunks. */
while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
+ sctp_sched_dequeue_done(q, chunk);
/* Mark as send failure. */
sctp_chunk_fail(chunk, q->error);
@@ -391,13 +400,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
struct sctp_outq *q = &asoc->outqueue;
struct sctp_chunk *chk, *temp;
+ q->sched->unsched_all(&asoc->stream);
+
list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) {
if (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) ||
chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)
continue;
- list_del_init(&chk->list);
- q->out_qlen -= chk->skb->len;
+ sctp_sched_dequeue_common(q, chk);
asoc->sent_cnt_removable--;
asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) {
@@ -415,6 +425,8 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
break;
}
+ q->sched->sched_all(&asoc->stream);
+
return msg_len;
}
@@ -1033,22 +1045,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
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.
- */
- if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) {
-
- /* Mark as failed send. */
- sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
- if (asoc->peer.prsctp_capable &&
- SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags))
- asoc->sent_cnt_removable--;
- sctp_chunk_free(chunk);
- continue;
- }
-
/* Has this chunk expired? */
if (sctp_chunk_abandoned(chunk)) {
+ sctp_sched_dequeue_done(q, chunk);
sctp_chunk_fail(chunk, 0);
sctp_chunk_free(chunk);
continue;
@@ -1070,6 +1069,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
new_transport = asoc->peer.active_path;
if (new_transport->state == SCTP_UNCONFIRMED) {
WARN_ONCE(1, "Attempt to send packet on unconfirmed path.");
+ sctp_sched_dequeue_done(q, chunk);
sctp_chunk_fail(chunk, 0);
sctp_chunk_free(chunk);
continue;
@@ -1133,6 +1133,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
else
asoc->stats.oodchunks++;
+ /* Only now it's safe to consider this
+ * chunk as sent, sched-wise.
+ */
+ sctp_sched_dequeue_done(q, chunk);
+
break;
default:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index e6a2974e020e1a4232d94e6c2933eebff5f8acb4..402bfbb888cda53248dd192d3756a2f4db1d2a7f 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -50,6 +50,7 @@
#include <net/sock.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
static int sctp_cmd_interpreter(enum sctp_event event_type,
union sctp_subtype subtype,
@@ -1089,6 +1090,8 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
list_for_each_entry(chunk, &msg->chunks, frag_list)
sctp_outq_tail(&asoc->outqueue, chunk, gfp);
+
+ asoc->outqueue.sched->enqueue(&asoc->outqueue, msg);
}
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 055ca25bbc91bf932db8048c72a1b11cc2214942..5ea33a2c453b4272c5c22fa61e8e8bec06001f8b 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -32,8 +32,61 @@
* Xin Long <lucien.xin@gmail.com>
*/
+#include <linux/list.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Migrates chunks from stream queues to new stream queues if needed,
+ * but not across associations. Also, removes those chunks to streams
+ * higher than the new max.
+ */
+static void sctp_stream_outq_migrate(struct sctp_stream *stream,
+ struct sctp_stream *new, __u16 outcnt)
+{
+ struct sctp_association *asoc;
+ struct sctp_chunk *ch, *temp;
+ struct sctp_outq *outq;
+ int i;
+
+ asoc = container_of(stream, struct sctp_association, stream);
+ outq = &asoc->outqueue;
+
+ list_for_each_entry_safe(ch, temp, &outq->out_chunk_list, list) {
+ __u16 sid = sctp_chunk_stream_no(ch);
+
+ if (sid < outcnt)
+ continue;
+
+ sctp_sched_dequeue_common(outq, ch);
+ /* No need to call dequeue_done here because
+ * the chunks are not scheduled by now.
+ */
+
+ /* Mark as failed send. */
+ sctp_chunk_fail(ch, SCTP_ERROR_INV_STRM);
+ if (asoc->peer.prsctp_capable &&
+ SCTP_PR_PRIO_ENABLED(ch->sinfo.sinfo_flags))
+ asoc->sent_cnt_removable--;
+
+ sctp_chunk_free(ch);
+ }
+
+ if (new) {
+ /* Here we actually move the old ext stuff into the new
+ * buffer, because we want to keep it. Then
+ * sctp_stream_update will swap ->out pointers.
+ */
+ for (i = 0; i < outcnt; i++) {
+ kfree(new->out[i].ext);
+ new->out[i].ext = stream->out[i].ext;
+ stream->out[i].ext = NULL;
+ }
+ }
+
+ for (i = outcnt; i < stream->outcnt; i++)
+ kfree(stream->out[i].ext);
+}
static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
gfp_t gfp)
@@ -87,7 +140,8 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
gfp_t gfp)
{
- int i;
+ struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+ int i, ret = 0;
gfp |= __GFP_NOWARN;
@@ -97,6 +151,11 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
if (outcnt == stream->outcnt)
goto in;
+ /* Filter out chunks queued on streams that won't exist anymore */
+ sched->unsched_all(stream);
+ sctp_stream_outq_migrate(stream, NULL, outcnt);
+ sched->sched_all(stream);
+
i = sctp_stream_alloc_out(stream, outcnt, gfp);
if (i)
return i;
@@ -105,20 +164,27 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
for (i = 0; i < stream->outcnt; i++)
stream->out[i].state = SCTP_STREAM_OPEN;
+ sched->init(stream);
+
in:
if (!incnt)
- return 0;
+ goto out;
i = sctp_stream_alloc_in(stream, incnt, gfp);
if (i) {
- kfree(stream->out);
- stream->out = NULL;
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto free;
}
stream->incnt = incnt;
+ goto out;
- return 0;
+free:
+ sched->free(stream);
+ kfree(stream->out);
+ stream->out = NULL;
+out:
+ return ret;
}
int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
@@ -130,13 +196,15 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
return -ENOMEM;
stream->out[sid].ext = soute;
- return 0;
+ return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
}
void sctp_stream_free(struct sctp_stream *stream)
{
+ struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
int i;
+ sched->free(stream);
for (i = 0; i < stream->outcnt; i++)
kfree(stream->out[i].ext);
kfree(stream->out);
@@ -156,6 +224,10 @@ void sctp_stream_clear(struct sctp_stream *stream)
void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
{
+ struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+
+ sched->unsched_all(stream);
+ sctp_stream_outq_migrate(stream, new, new->outcnt);
sctp_stream_free(stream);
stream->out = new->out;
@@ -163,6 +235,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
stream->outcnt = new->outcnt;
stream->incnt = new->incnt;
+ sched->sched_all(stream);
+
new->out = NULL;
new->in = NULL;
}
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
new file mode 100644
index 0000000000000000000000000000000000000000..40a9a9de2b98a56786a4c8585f5ad514be9189af
--- /dev/null
+++ b/net/sctp/stream_sched.c
@@ -0,0 +1,270 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ * ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* First Come First Serve (a.k.a. FIFO)
+ * RFC DRAFT ndata Section 3.1
+ */
+static int sctp_sched_fcfs_set(struct sctp_stream *stream, __u16 sid,
+ __u16 value, gfp_t gfp)
+{
+ return 0;
+}
+
+static int sctp_sched_fcfs_get(struct sctp_stream *stream, __u16 sid,
+ __u16 *value)
+{
+ *value = 0;
+ return 0;
+}
+
+static int sctp_sched_fcfs_init(struct sctp_stream *stream)
+{
+ return 0;
+}
+
+static int sctp_sched_fcfs_init_sid(struct sctp_stream *stream, __u16 sid,
+ gfp_t gfp)
+{
+ return 0;
+}
+
+static void sctp_sched_fcfs_free(struct sctp_stream *stream)
+{
+}
+
+static void sctp_sched_fcfs_enqueue(struct sctp_outq *q,
+ struct sctp_datamsg *msg)
+{
+}
+
+static struct sctp_chunk *sctp_sched_fcfs_dequeue(struct sctp_outq *q)
+{
+ struct sctp_stream *stream = &q->asoc->stream;
+ struct sctp_chunk *ch = NULL;
+ struct list_head *entry;
+
+ if (list_empty(&q->out_chunk_list))
+ goto out;
+
+ if (stream->out_curr) {
+ ch = list_entry(stream->out_curr->ext->outq.next,
+ struct sctp_chunk, stream_list);
+ } else {
+ entry = q->out_chunk_list.next;
+ ch = list_entry(entry, struct sctp_chunk, list);
+ }
+
+ sctp_sched_dequeue_common(q, ch);
+
+out:
+ return ch;
+}
+
+static void sctp_sched_fcfs_dequeue_done(struct sctp_outq *q,
+ struct sctp_chunk *chunk)
+{
+}
+
+static void sctp_sched_fcfs_sched_all(struct sctp_stream *stream)
+{
+}
+
+static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream)
+{
+}
+
+static struct sctp_sched_ops sctp_sched_fcfs = {
+ .set = sctp_sched_fcfs_set,
+ .get = sctp_sched_fcfs_get,
+ .init = sctp_sched_fcfs_init,
+ .init_sid = sctp_sched_fcfs_init_sid,
+ .free = sctp_sched_fcfs_free,
+ .enqueue = sctp_sched_fcfs_enqueue,
+ .dequeue = sctp_sched_fcfs_dequeue,
+ .dequeue_done = sctp_sched_fcfs_dequeue_done,
+ .sched_all = sctp_sched_fcfs_sched_all,
+ .unsched_all = sctp_sched_fcfs_unsched_all,
+};
+
+/* API to other parts of the stack */
+
+struct sctp_sched_ops *sctp_sched_ops[] = {
+ &sctp_sched_fcfs,
+};
+
+int sctp_sched_set_sched(struct sctp_association *asoc,
+ enum sctp_sched_type sched)
+{
+ struct sctp_sched_ops *n = sctp_sched_ops[sched];
+ struct sctp_sched_ops *old = asoc->outqueue.sched;
+ struct sctp_datamsg *msg = NULL;
+ struct sctp_chunk *ch;
+ int i, ret = 0;
+
+ if (old == n)
+ return ret;
+
+ if (sched > SCTP_SS_MAX)
+ return -EINVAL;
+
+ if (old) {
+ old->free(&asoc->stream);
+
+ /* Give the next scheduler a clean slate. */
+ for (i = 0; i < asoc->stream.outcnt; i++) {
+ void *p = asoc->stream.out[i].ext;
+
+ if (!p)
+ continue;
+
+ p += offsetofend(struct sctp_stream_out_ext, outq);
+ memset(p, 0, sizeof(struct sctp_stream_out_ext) -
+ offsetofend(struct sctp_stream_out_ext, outq));
+ }
+ }
+
+ asoc->outqueue.sched = n;
+ n->init(&asoc->stream);
+ for (i = 0; i < asoc->stream.outcnt; i++) {
+ if (!asoc->stream.out[i].ext)
+ continue;
+
+ ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+ if (ret)
+ goto err;
+ }
+
+ /* We have to requeue all chunks already queued. */
+ list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+ if (ch->msg == msg)
+ continue;
+ msg = ch->msg;
+ n->enqueue(&asoc->outqueue, msg);
+ }
+
+ return ret;
+
+err:
+ n->free(&asoc->stream);
+ asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */
+
+ return ret;
+}
+
+int sctp_sched_get_sched(struct sctp_association *asoc)
+{
+ int i;
+
+ for (i = 0; i <= SCTP_SS_MAX; i++)
+ if (asoc->outqueue.sched == sctp_sched_ops[i])
+ return i;
+
+ return 0;
+}
+
+int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
+ __u16 value, gfp_t gfp)
+{
+ if (sid >= asoc->stream.outcnt)
+ return -EINVAL;
+
+ if (!asoc->stream.out[sid].ext) {
+ int ret;
+
+ ret = sctp_stream_init_ext(&asoc->stream, sid);
+ if (ret)
+ return ret;
+ }
+
+ return asoc->outqueue.sched->set(&asoc->stream, sid, value, gfp);
+}
+
+int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
+ __u16 *value)
+{
+ if (sid >= asoc->stream.outcnt)
+ return -EINVAL;
+
+ if (!asoc->stream.out[sid].ext)
+ return 0;
+
+ return asoc->outqueue.sched->get(&asoc->stream, sid, value);
+}
+
+void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+ if (!list_is_last(&ch->frag_list, &ch->msg->chunks)) {
+ struct sctp_stream_out *sout;
+ __u16 sid;
+
+ /* datamsg is not finish, so save it as current one,
+ * in case application switch scheduler or a higher
+ * priority stream comes in.
+ */
+ sid = sctp_chunk_stream_no(ch);
+ sout = &q->asoc->stream.out[sid];
+ q->asoc->stream.out_curr = sout;
+ return;
+ }
+
+ q->asoc->stream.out_curr = NULL;
+ q->sched->dequeue_done(q, ch);
+}
+
+/* Auxiliary functions for the schedulers */
+void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch)
+{
+ list_del_init(&ch->list);
+ list_del_init(&ch->stream_list);
+ q->out_qlen -= ch->skb->len;
+}
+
+int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp)
+{
+ struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+
+ INIT_LIST_HEAD(&stream->out[sid].ext->outq);
+ return sched->init_sid(stream, sid, gfp);
+}
+
+struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream)
+{
+ struct sctp_association *asoc;
+
+ asoc = container_of(stream, struct sctp_association, stream);
+
+ return asoc->outqueue.sched;
+}
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 07/10] sctp: add sockopt to get/set stream scheduler
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
As defined per RFC Draft ndata Section 4.3.2, named as
SCTP_STREAM_SCHEDULER.
See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/uapi/linux/sctp.h | 1 +
net/sctp/socket.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 76 insertions(+)
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 4487e7625ddbd48be1868a8292a807ecd0a314bc..0050f10087d224bad87c8c54ad318003381aee12 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -122,6 +122,7 @@ typedef __s32 sctp_assoc_t;
#define SCTP_RESET_ASSOC 120
#define SCTP_ADD_STREAMS 121
#define SCTP_SOCKOPT_PEELOFF_FLAGS 122
+#define SCTP_STREAM_SCHEDULER 123
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d207734326b085e60625e4333f74221481114892..ae35dbf2810f78c71ce77115ffe4b0e27a672abc 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -79,6 +79,7 @@
#include <net/sock.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
/* Forward declarations for internal helper functions. */
static int sctp_writeable(struct sock *sk);
@@ -3914,6 +3915,36 @@ static int sctp_setsockopt_add_streams(struct sock *sk,
return retval;
}
+static int sctp_setsockopt_scheduler(struct sock *sk,
+ char __user *optval,
+ unsigned int optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_assoc_value params;
+ int retval = -EINVAL;
+
+ if (optlen < sizeof(params))
+ goto out;
+
+ optlen = sizeof(params);
+ if (copy_from_user(¶ms, optval, optlen)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ if (params.assoc_value > SCTP_SS_MAX)
+ goto out;
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (!asoc)
+ goto out;
+
+ retval = sctp_sched_set_sched(asoc, params.assoc_value);
+
+out:
+ return retval;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4095,6 +4126,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_ADD_STREAMS:
retval = sctp_setsockopt_add_streams(sk, optval, optlen);
break;
+ case SCTP_STREAM_SCHEDULER:
+ retval = sctp_setsockopt_scheduler(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -6793,6 +6827,43 @@ static int sctp_getsockopt_enable_strreset(struct sock *sk, int len,
return retval;
}
+static int sctp_getsockopt_scheduler(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) {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ params.assoc_value = sctp_sched_get_sched(asoc);
+
+ 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)
{
@@ -6975,6 +7046,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
retval = sctp_getsockopt_enable_strreset(sk, len, optval,
optlen);
break;
+ case SCTP_STREAM_SCHEDULER:
+ retval = sctp_getsockopt_scheduler(sk, len, optval,
+ optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 08/10] sctp: add sockopt to get/set stream scheduler parameters
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
As defined per RFC Draft ndata Section 4.3.3, named as
SCTP_STREAM_SCHEDULER_VALUE.
See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/uapi/linux/sctp.h | 7 +++++
net/sctp/socket.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 84 insertions(+)
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 0050f10087d224bad87c8c54ad318003381aee12..00ac417d2c4f8468ea2aad32e59806be5c5aa08d 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -123,6 +123,7 @@ typedef __s32 sctp_assoc_t;
#define SCTP_ADD_STREAMS 121
#define SCTP_SOCKOPT_PEELOFF_FLAGS 122
#define SCTP_STREAM_SCHEDULER 123
+#define SCTP_STREAM_SCHEDULER_VALUE 124
/* PR-SCTP policies */
#define SCTP_PR_SCTP_NONE 0x0000
@@ -815,6 +816,12 @@ struct sctp_assoc_value {
uint32_t assoc_value;
};
+struct sctp_stream_value {
+ sctp_assoc_t assoc_id;
+ uint16_t stream_id;
+ uint16_t stream_value;
+};
+
/*
* 7.2.2 Peer Address Information
*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index ae35dbf2810f78c71ce77115ffe4b0e27a672abc..88c28421ec151e83665efcbcbd8a6403b122205a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3945,6 +3945,34 @@ static int sctp_setsockopt_scheduler(struct sock *sk,
return retval;
}
+static int sctp_setsockopt_scheduler_value(struct sock *sk,
+ char __user *optval,
+ unsigned int optlen)
+{
+ struct sctp_association *asoc;
+ struct sctp_stream_value params;
+ int retval = -EINVAL;
+
+ if (optlen < sizeof(params))
+ goto out;
+
+ optlen = sizeof(params);
+ if (copy_from_user(¶ms, optval, optlen)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ asoc = sctp_id2assoc(sk, params.assoc_id);
+ if (!asoc)
+ goto out;
+
+ retval = sctp_sched_set_value(asoc, params.stream_id,
+ params.stream_value, GFP_KERNEL);
+
+out:
+ return retval;
+}
+
/* API 6.2 setsockopt(), getsockopt()
*
* Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4129,6 +4157,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
case SCTP_STREAM_SCHEDULER:
retval = sctp_setsockopt_scheduler(sk, optval, optlen);
break;
+ case SCTP_STREAM_SCHEDULER_VALUE:
+ retval = sctp_setsockopt_scheduler_value(sk, optval, optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
@@ -6864,6 +6895,48 @@ static int sctp_getsockopt_scheduler(struct sock *sk, int len,
return retval;
}
+static int sctp_getsockopt_scheduler_value(struct sock *sk, int len,
+ char __user *optval,
+ int __user *optlen)
+{
+ struct sctp_stream_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) {
+ retval = -EINVAL;
+ goto out;
+ }
+
+ retval = sctp_sched_get_value(asoc, params.stream_id,
+ ¶ms.stream_value);
+ if (retval)
+ goto out;
+
+ if (put_user(len, optlen)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+ if (copy_to_user(optval, ¶ms, len)) {
+ retval = -EFAULT;
+ goto out;
+ }
+
+out:
+ return retval;
+}
+
static int sctp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -7050,6 +7123,10 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
retval = sctp_getsockopt_scheduler(sk, len, optval,
optlen);
break;
+ case SCTP_STREAM_SCHEDULER_VALUE:
+ retval = sctp_getsockopt_scheduler_value(sk, len, optval,
+ optlen);
+ break;
default:
retval = -ENOPROTOOPT;
break;
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 09/10] sctp: introduce priority based stream scheduler
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
This patch introduces RFC Draft ndata section 3.4 Priority Based
Scheduler (SCTP_SS_PRIO).
It works by having a struct sctp_stream_priority for each priority
configured. This struct is then enlisted on a queue ordered per priority
if, and only if, there is a stream with data queued, so that dequeueing
is very straightforward: either finish current datamsg or simply dequeue
from the highest priority queued, which is the next stream pointed, and
that's it.
If there are multiple streams assigned with the same priority and with
data queued, it will do round robin amongst them while respecting
datamsgs boundaries (when not using idata chunks), to be reasonably
fair.
We intentionally don't maintain a list of priorities nor a list of all
streams with the same priority to save memory. The first would mean at
least 2 other pointers per priority (which, for 1000 priorities, that
can mean 16kB) and the second would also mean 2 other pointers but per
stream. As SCTP supports up to 65535 streams on a given asoc, that's
1MB. This impacts when giving a priority to some stream, as we have to
find out if the new priority is already being used and if we can free
the old one, and also when tearing down.
The new fields in struct sctp_stream_out_ext and sctp_stream are added
under a union because that memory is to be shared with other schedulers.
It could be defined as an opaque area like skb->cb, but that would make
the list handling a nightmare.
See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/net/sctp/structs.h | 24 +++
include/uapi/linux/sctp.h | 3 +-
net/sctp/Makefile | 2 +-
net/sctp/stream_sched.c | 3 +
net/sctp/stream_sched_prio.c | 347 +++++++++++++++++++++++++++++++++++++++++++
5 files changed, 377 insertions(+), 2 deletions(-)
create mode 100644 net/sctp/stream_sched_prio.c
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 3c22a30fd71b4ef87419a77cf69b00807a5986bb..40eb8d66a37c3ecee39141dc111663f7aac7326a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1328,10 +1328,27 @@ struct sctp_inithdr_host {
__u32 initial_tsn;
};
+struct sctp_stream_priorities {
+ /* List of priorities scheduled */
+ struct list_head prio_sched;
+ /* List of streams scheduled */
+ struct list_head active;
+ /* The next stream stream in line */
+ struct sctp_stream_out_ext *next;
+ __u16 prio;
+};
+
struct sctp_stream_out_ext {
__u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1];
__u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1];
struct list_head outq; /* chunks enqueued by this stream */
+ union {
+ struct {
+ /* Scheduled streams list */
+ struct list_head prio_list;
+ struct sctp_stream_priorities *prio_head;
+ };
+ };
};
struct sctp_stream_out {
@@ -1351,6 +1368,13 @@ struct sctp_stream {
__u16 incnt;
/* Current stream being sent, if any */
struct sctp_stream_out *out_curr;
+ union {
+ /* Fields used by priority scheduler */
+ struct {
+ /* List of priorities scheduled */
+ struct list_head prio_list;
+ };
+ };
};
#define SCTP_STREAM_CLOSED 0x00
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 00ac417d2c4f8468ea2aad32e59806be5c5aa08d..850fa8b29d7e8163dc4ee88af192309bb2535ae9 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -1099,7 +1099,8 @@ struct sctp_add_streams {
/* SCTP Stream schedulers */
enum sctp_sched_type {
SCTP_SS_FCFS,
- SCTP_SS_MAX = SCTP_SS_FCFS
+ SCTP_SS_PRIO,
+ SCTP_SS_MAX = SCTP_SS_PRIO
};
#endif /* _UAPI_SCTP_H */
diff --git a/net/sctp/Makefile b/net/sctp/Makefile
index 0f6e6d1d69fd336b4a99f896851b0120f9a0d1e0..647c9cfd4e95be4429d25792e5832d7be2efc5c8 100644
--- a/net/sctp/Makefile
+++ b/net/sctp/Makefile
@@ -12,7 +12,7 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
inqueue.o outqueue.o ulpqueue.o \
tsnmap.o bind_addr.o socket.o primitive.o \
output.o input.o debug.o stream.o auth.o \
- offload.o stream_sched.o
+ offload.o stream_sched.o stream_sched_prio.o
sctp_probe-y := probe.o
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 40a9a9de2b98a56786a4c8585f5ad514be9189af..115ddb7651695cca7417cb63004a1a59c93523b8 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -121,8 +121,11 @@ static struct sctp_sched_ops sctp_sched_fcfs = {
/* API to other parts of the stack */
+extern struct sctp_sched_ops sctp_sched_prio;
+
struct sctp_sched_ops *sctp_sched_ops[] = {
&sctp_sched_fcfs,
+ &sctp_sched_prio,
};
int sctp_sched_set_sched(struct sctp_association *asoc,
diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c
new file mode 100644
index 0000000000000000000000000000000000000000..384dbf3c876096e2ad98a6b6185d9da5cc4145c6
--- /dev/null
+++ b/net/sctp/stream_sched_prio.c
@@ -0,0 +1,347 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ * ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.4
+ */
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream);
+
+static struct sctp_stream_priorities *sctp_sched_prio_new_head(
+ struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+ struct sctp_stream_priorities *p;
+
+ p = kmalloc(sizeof(*p), gfp);
+ if (!p)
+ return NULL;
+
+ INIT_LIST_HEAD(&p->prio_sched);
+ INIT_LIST_HEAD(&p->active);
+ p->next = NULL;
+ p->prio = prio;
+
+ return p;
+}
+
+static struct sctp_stream_priorities *sctp_sched_prio_get_head(
+ struct sctp_stream *stream, int prio, gfp_t gfp)
+{
+ struct sctp_stream_priorities *p;
+ int i;
+
+ /* Look into scheduled priorities first, as they are sorted and
+ * we can find it fast IF it's scheduled.
+ */
+ list_for_each_entry(p, &stream->prio_list, prio_sched) {
+ if (p->prio == prio)
+ return p;
+ if (p->prio > prio)
+ break;
+ }
+
+ /* No luck. So we search on all streams now. */
+ for (i = 0; i < stream->outcnt; i++) {
+ if (!stream->out[i].ext)
+ continue;
+
+ p = stream->out[i].ext->prio_head;
+ if (!p)
+ /* Means all other streams won't be initialized
+ * as well.
+ */
+ break;
+ if (p->prio == prio)
+ return p;
+ }
+
+ /* If not even there, allocate a new one. */
+ return sctp_sched_prio_new_head(stream, prio, gfp);
+}
+
+static void sctp_sched_prio_next_stream(struct sctp_stream_priorities *p)
+{
+ struct list_head *pos;
+
+ pos = p->next->prio_list.next;
+ if (pos == &p->active)
+ pos = pos->next;
+ p->next = list_entry(pos, struct sctp_stream_out_ext, prio_list);
+}
+
+static bool sctp_sched_prio_unsched(struct sctp_stream_out_ext *soute)
+{
+ bool scheduled = false;
+
+ if (!list_empty(&soute->prio_list)) {
+ struct sctp_stream_priorities *prio_head = soute->prio_head;
+
+ /* Scheduled */
+ scheduled = true;
+
+ if (prio_head->next == soute)
+ /* Try to move to the next stream */
+ sctp_sched_prio_next_stream(prio_head);
+
+ list_del_init(&soute->prio_list);
+
+ /* Also unsched the priority if this was the last stream */
+ if (list_empty(&prio_head->active)) {
+ list_del_init(&prio_head->prio_sched);
+ /* If there is no stream left, clear next */
+ prio_head->next = NULL;
+ }
+ }
+
+ return scheduled;
+}
+
+static void sctp_sched_prio_sched(struct sctp_stream *stream,
+ struct sctp_stream_out_ext *soute)
+{
+ struct sctp_stream_priorities *prio, *prio_head;
+
+ prio_head = soute->prio_head;
+
+ /* Nothing to do if already scheduled */
+ if (!list_empty(&soute->prio_list))
+ return;
+
+ /* Schedule the stream. If there is a next, we schedule the new
+ * one before it, so it's the last in round robin order.
+ * If there isn't, we also have to schedule the priority.
+ */
+ if (prio_head->next) {
+ list_add(&soute->prio_list, prio_head->next->prio_list.prev);
+ return;
+ }
+
+ list_add(&soute->prio_list, &prio_head->active);
+ prio_head->next = soute;
+
+ list_for_each_entry(prio, &stream->prio_list, prio_sched) {
+ if (prio->prio > prio_head->prio) {
+ list_add(&prio_head->prio_sched, prio->prio_sched.prev);
+ return;
+ }
+ }
+
+ list_add_tail(&prio_head->prio_sched, &stream->prio_list);
+}
+
+static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
+ __u16 prio, gfp_t gfp)
+{
+ struct sctp_stream_out *sout = &stream->out[sid];
+ struct sctp_stream_out_ext *soute = sout->ext;
+ struct sctp_stream_priorities *prio_head, *old;
+ bool reschedule = false;
+ int i;
+
+ prio_head = sctp_sched_prio_get_head(stream, prio, gfp);
+ if (!prio_head)
+ return -ENOMEM;
+
+ reschedule = sctp_sched_prio_unsched(soute);
+ old = soute->prio_head;
+ soute->prio_head = prio_head;
+ if (reschedule)
+ sctp_sched_prio_sched(stream, soute);
+
+ if (!old)
+ /* Happens when we set the priority for the first time */
+ return 0;
+
+ for (i = 0; i < stream->outcnt; i++) {
+ soute = stream->out[i].ext;
+ if (soute && soute->prio_head == old)
+ /* It's still in use, nothing else to do here. */
+ return 0;
+ }
+
+ /* No hits, we are good to free it. */
+ kfree(old);
+
+ return 0;
+}
+
+static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid,
+ __u16 *value)
+{
+ *value = stream->out[sid].ext->prio_head->prio;
+ return 0;
+}
+
+static int sctp_sched_prio_init(struct sctp_stream *stream)
+{
+ INIT_LIST_HEAD(&stream->prio_list);
+
+ return 0;
+}
+
+static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid,
+ gfp_t gfp)
+{
+ INIT_LIST_HEAD(&stream->out[sid].ext->prio_list);
+ return sctp_sched_prio_set(stream, sid, 0, gfp);
+}
+
+static void sctp_sched_prio_free(struct sctp_stream *stream)
+{
+ struct sctp_stream_priorities *prio, *n;
+ LIST_HEAD(list);
+ int i;
+
+ /* As we don't keep a list of priorities, to avoid multiple
+ * frees we have to do it in 3 steps:
+ * 1. unsched everyone, so the lists are free to use in 2.
+ * 2. build the list of the priorities
+ * 3. free the list
+ */
+ sctp_sched_prio_unsched_all(stream);
+ for (i = 0; i < stream->outcnt; i++) {
+ if (!stream->out[i].ext)
+ continue;
+ prio = stream->out[i].ext->prio_head;
+ if (prio && list_empty(&prio->prio_sched))
+ list_add(&prio->prio_sched, &list);
+ }
+ list_for_each_entry_safe(prio, n, &list, prio_sched) {
+ list_del_init(&prio->prio_sched);
+ kfree(prio);
+ }
+}
+
+static void sctp_sched_prio_enqueue(struct sctp_outq *q,
+ struct sctp_datamsg *msg)
+{
+ struct sctp_stream *stream;
+ struct sctp_chunk *ch;
+ __u16 sid;
+
+ ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+ sid = sctp_chunk_stream_no(ch);
+ stream = &q->asoc->stream;
+ sctp_sched_prio_sched(stream, stream->out[sid].ext);
+}
+
+static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q)
+{
+ struct sctp_stream *stream = &q->asoc->stream;
+ struct sctp_stream_priorities *prio;
+ struct sctp_stream_out_ext *soute;
+ struct sctp_chunk *ch = NULL;
+
+ /* Bail out quickly if queue is empty */
+ if (list_empty(&q->out_chunk_list))
+ goto out;
+
+ /* Find which chunk is next. It's easy, it's either the current
+ * one or the first chunk on the next active stream.
+ */
+ if (stream->out_curr) {
+ soute = stream->out_curr->ext;
+ } else {
+ prio = list_entry(stream->prio_list.next,
+ struct sctp_stream_priorities, prio_sched);
+ soute = prio->next;
+ }
+ ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+ sctp_sched_dequeue_common(q, ch);
+
+out:
+ return ch;
+}
+
+static void sctp_sched_prio_dequeue_done(struct sctp_outq *q,
+ struct sctp_chunk *ch)
+{
+ struct sctp_stream_priorities *prio;
+ struct sctp_stream_out_ext *soute;
+ __u16 sid;
+
+ /* Last chunk on that msg, move to the next stream on
+ * this priority.
+ */
+ sid = sctp_chunk_stream_no(ch);
+ soute = q->asoc->stream.out[sid].ext;
+ prio = soute->prio_head;
+
+ sctp_sched_prio_next_stream(prio);
+
+ if (list_empty(&soute->outq))
+ sctp_sched_prio_unsched(soute);
+}
+
+static void sctp_sched_prio_sched_all(struct sctp_stream *stream)
+{
+ struct sctp_association *asoc;
+ struct sctp_stream_out *sout;
+ struct sctp_chunk *ch;
+
+ asoc = container_of(stream, struct sctp_association, stream);
+ list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+ __u16 sid;
+
+ sid = sctp_chunk_stream_no(ch);
+ sout = &stream->out[sid];
+ if (sout->ext)
+ sctp_sched_prio_sched(stream, sout->ext);
+ }
+}
+
+static void sctp_sched_prio_unsched_all(struct sctp_stream *stream)
+{
+ struct sctp_stream_priorities *p, *tmp;
+ struct sctp_stream_out_ext *soute, *souttmp;
+
+ list_for_each_entry_safe(p, tmp, &stream->prio_list, prio_sched)
+ list_for_each_entry_safe(soute, souttmp, &p->active, prio_list)
+ sctp_sched_prio_unsched(soute);
+}
+
+struct sctp_sched_ops sctp_sched_prio = {
+ .set = sctp_sched_prio_set,
+ .get = sctp_sched_prio_get,
+ .init = sctp_sched_prio_init,
+ .init_sid = sctp_sched_prio_init_sid,
+ .free = sctp_sched_prio_free,
+ .enqueue = sctp_sched_prio_enqueue,
+ .dequeue = sctp_sched_prio_dequeue,
+ .dequeue_done = sctp_sched_prio_dequeue_done,
+ .sched_all = sctp_sched_prio_sched_all,
+ .unsched_all = sctp_sched_prio_unsched_all,
+};
--
2.13.5
^ permalink raw reply related
* [PATCH net-next 10/10] sctp: introduce round robin stream scheduler
From: Marcelo Ricardo Leitner @ 2017-09-28 20:25 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long, David Laight
In-Reply-To: <cover.1506536044.git.marcelo.leitner@gmail.com>
This patch introduces RFC Draft ndata section 3.2 Priority Based
Scheduler (SCTP_SS_RR).
Works by maintaining a list of enqueued streams and tracking the last
one used to send data. When the datamsg is done, it switches to the next
stream.
See-also: https://tools.ietf.org/html/draft-ietf-tsvwg-sctp-ndata-13
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
include/net/sctp/structs.h | 11 +++
include/uapi/linux/sctp.h | 3 +-
net/sctp/Makefile | 3 +-
net/sctp/stream_sched.c | 2 +
net/sctp/stream_sched_rr.c | 201 +++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 218 insertions(+), 2 deletions(-)
create mode 100644 net/sctp/stream_sched_rr.c
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 40eb8d66a37c3ecee39141dc111663f7aac7326a..16f949eef52fdfd7c90fa15b44093334d1355aaf 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1348,6 +1348,10 @@ struct sctp_stream_out_ext {
struct list_head prio_list;
struct sctp_stream_priorities *prio_head;
};
+ /* Fields used by RR scheduler */
+ struct {
+ struct list_head rr_list;
+ };
};
};
@@ -1374,6 +1378,13 @@ struct sctp_stream {
/* List of priorities scheduled */
struct list_head prio_list;
};
+ /* Fields used by RR scheduler */
+ struct {
+ /* List of streams scheduled */
+ struct list_head rr_list;
+ /* The next stream stream in line */
+ struct sctp_stream_out_ext *rr_next;
+ };
};
};
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index 850fa8b29d7e8163dc4ee88af192309bb2535ae9..6cd7d416ca406e59d3214976fc425bb805f5c6cc 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -1100,7 +1100,8 @@ struct sctp_add_streams {
enum sctp_sched_type {
SCTP_SS_FCFS,
SCTP_SS_PRIO,
- SCTP_SS_MAX = SCTP_SS_PRIO
+ SCTP_SS_RR,
+ SCTP_SS_MAX = SCTP_SS_RR
};
#endif /* _UAPI_SCTP_H */
diff --git a/net/sctp/Makefile b/net/sctp/Makefile
index 647c9cfd4e95be4429d25792e5832d7be2efc5c8..bf90c53977190ff563c2b43af31afb7c431d4534 100644
--- a/net/sctp/Makefile
+++ b/net/sctp/Makefile
@@ -12,7 +12,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
inqueue.o outqueue.o ulpqueue.o \
tsnmap.o bind_addr.o socket.o primitive.o \
output.o input.o debug.o stream.o auth.o \
- offload.o stream_sched.o stream_sched_prio.o
+ offload.o stream_sched.o stream_sched_prio.o \
+ stream_sched_rr.o
sctp_probe-y := probe.o
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 115ddb7651695cca7417cb63004a1a59c93523b8..03513a9fa110b5317af4502f98ab37702c1eddb9 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -122,10 +122,12 @@ static struct sctp_sched_ops sctp_sched_fcfs = {
/* API to other parts of the stack */
extern struct sctp_sched_ops sctp_sched_prio;
+extern struct sctp_sched_ops sctp_sched_rr;
struct sctp_sched_ops *sctp_sched_ops[] = {
&sctp_sched_fcfs,
&sctp_sched_prio,
+ &sctp_sched_rr,
};
int sctp_sched_set_sched(struct sctp_association *asoc,
diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c
new file mode 100644
index 0000000000000000000000000000000000000000..7612a438c5b939ae1c26c4acc06902749b601524
--- /dev/null
+++ b/net/sctp/stream_sched_rr.c
@@ -0,0 +1,201 @@
+/* SCTP kernel implementation
+ * (C) Copyright Red Hat Inc. 2017
+ *
+ * This file is part of the SCTP kernel implementation
+ *
+ * These functions manipulate sctp stream queue/scheduling.
+ *
+ * This SCTP implementation is free software;
+ * you can redistribute it and/or modify it under the terms of
+ * the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This SCTP implementation is distributed in the hope that it
+ * will be useful, but WITHOUT ANY WARRANTY; without even the implied
+ * ************************
+ * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with GNU CC; see the file COPYING. If not, see
+ * <http://www.gnu.org/licenses/>.
+ *
+ * Please send any bug reports or fixes you make to the
+ * email addresched(es):
+ * lksctp developers <linux-sctp@vger.kernel.org>
+ *
+ * Written or modified by:
+ * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ */
+
+#include <linux/list.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+#include <net/sctp/stream_sched.h>
+
+/* Priority handling
+ * RFC DRAFT ndata section 3.2
+ */
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream);
+
+static void sctp_sched_rr_next_stream(struct sctp_stream *stream)
+{
+ struct list_head *pos;
+
+ pos = stream->rr_next->rr_list.next;
+ if (pos == &stream->rr_list)
+ pos = pos->next;
+ stream->rr_next = list_entry(pos, struct sctp_stream_out_ext, rr_list);
+}
+
+static void sctp_sched_rr_unsched(struct sctp_stream *stream,
+ struct sctp_stream_out_ext *soute)
+{
+ if (stream->rr_next == soute)
+ /* Try to move to the next stream */
+ sctp_sched_rr_next_stream(stream);
+
+ list_del_init(&soute->rr_list);
+
+ /* If we have no other stream queued, clear next */
+ if (list_empty(&stream->rr_list))
+ stream->rr_next = NULL;
+}
+
+static void sctp_sched_rr_sched(struct sctp_stream *stream,
+ struct sctp_stream_out_ext *soute)
+{
+ if (!list_empty(&soute->rr_list))
+ /* Already scheduled. */
+ return;
+
+ /* Schedule the stream */
+ list_add_tail(&soute->rr_list, &stream->rr_list);
+
+ if (!stream->rr_next)
+ stream->rr_next = soute;
+}
+
+static int sctp_sched_rr_set(struct sctp_stream *stream, __u16 sid,
+ __u16 prio, gfp_t gfp)
+{
+ return 0;
+}
+
+static int sctp_sched_rr_get(struct sctp_stream *stream, __u16 sid,
+ __u16 *value)
+{
+ return 0;
+}
+
+static int sctp_sched_rr_init(struct sctp_stream *stream)
+{
+ INIT_LIST_HEAD(&stream->rr_list);
+ stream->rr_next = NULL;
+
+ return 0;
+}
+
+static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid,
+ gfp_t gfp)
+{
+ INIT_LIST_HEAD(&stream->out[sid].ext->rr_list);
+
+ return 0;
+}
+
+static void sctp_sched_rr_free(struct sctp_stream *stream)
+{
+ sctp_sched_rr_unsched_all(stream);
+}
+
+static void sctp_sched_rr_enqueue(struct sctp_outq *q,
+ struct sctp_datamsg *msg)
+{
+ struct sctp_stream *stream;
+ struct sctp_chunk *ch;
+ __u16 sid;
+
+ ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
+ sid = sctp_chunk_stream_no(ch);
+ stream = &q->asoc->stream;
+ sctp_sched_rr_sched(stream, stream->out[sid].ext);
+}
+
+static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q)
+{
+ struct sctp_stream *stream = &q->asoc->stream;
+ struct sctp_stream_out_ext *soute;
+ struct sctp_chunk *ch = NULL;
+
+ /* Bail out quickly if queue is empty */
+ if (list_empty(&q->out_chunk_list))
+ goto out;
+
+ /* Find which chunk is next */
+ if (stream->out_curr)
+ soute = stream->out_curr->ext;
+ else
+ soute = stream->rr_next;
+ ch = list_entry(soute->outq.next, struct sctp_chunk, stream_list);
+
+ sctp_sched_dequeue_common(q, ch);
+
+out:
+ return ch;
+}
+
+static void sctp_sched_rr_dequeue_done(struct sctp_outq *q,
+ struct sctp_chunk *ch)
+{
+ struct sctp_stream_out_ext *soute;
+ __u16 sid;
+
+ /* Last chunk on that msg, move to the next stream */
+ sid = sctp_chunk_stream_no(ch);
+ soute = q->asoc->stream.out[sid].ext;
+
+ sctp_sched_rr_next_stream(&q->asoc->stream);
+
+ if (list_empty(&soute->outq))
+ sctp_sched_rr_unsched(&q->asoc->stream, soute);
+}
+
+static void sctp_sched_rr_sched_all(struct sctp_stream *stream)
+{
+ struct sctp_association *asoc;
+ struct sctp_stream_out_ext *soute;
+ struct sctp_chunk *ch;
+
+ asoc = container_of(stream, struct sctp_association, stream);
+ list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) {
+ __u16 sid;
+
+ sid = sctp_chunk_stream_no(ch);
+ soute = stream->out[sid].ext;
+ if (soute)
+ sctp_sched_rr_sched(stream, soute);
+ }
+}
+
+static void sctp_sched_rr_unsched_all(struct sctp_stream *stream)
+{
+ struct sctp_stream_out_ext *soute, *tmp;
+
+ list_for_each_entry_safe(soute, tmp, &stream->rr_list, rr_list)
+ sctp_sched_rr_unsched(stream, soute);
+}
+
+struct sctp_sched_ops sctp_sched_rr = {
+ .set = sctp_sched_rr_set,
+ .get = sctp_sched_rr_get,
+ .init = sctp_sched_rr_init,
+ .init_sid = sctp_sched_rr_init_sid,
+ .free = sctp_sched_rr_free,
+ .enqueue = sctp_sched_rr_enqueue,
+ .dequeue = sctp_sched_rr_dequeue,
+ .dequeue_done = sctp_sched_rr_dequeue_done,
+ .sched_all = sctp_sched_rr_sched_all,
+ .unsched_all = sctp_sched_rr_unsched_all,
+};
--
2.13.5
^ permalink raw reply related
* Re: [PATCH net-next 2/6] bpf: add meta pointer for direct access
From: Waskiewicz Jr, Peter @ 2017-09-28 20:52 UTC (permalink / raw)
To: Andy Gospodarek
Cc: Daniel Borkmann, davem@davemloft.net,
alexei.starovoitov@gmail.com, john.fastabend@gmail.com,
jakub.kicinski@netronome.com, netdev@vger.kernel.org,
mchan@broadcom.com
In-Reply-To: <CAHashqBMfXp-uYH9ANfdaNfez9f4pcrOjnbX2WAFAdBwaJAtvw@mail.gmail.com>
On 9/28/17 12:59 PM, Andy Gospodarek wrote:
> On Thu, Sep 28, 2017 at 1:59 AM, Waskiewicz Jr, Peter
> <peter.waskiewicz.jr@intel.com> wrote:
>> On 9/26/17 10:21 AM, Andy Gospodarek wrote:
>>> On Mon, Sep 25, 2017 at 08:50:28PM +0200, Daniel Borkmann wrote:
>>>> On 09/25/2017 08:10 PM, Andy Gospodarek wrote:
>>>> [...]
>>>>> First, thanks for this detailed description. It was helpful to read
>>>>> along with the patches.
>>>>>
>>>>> My only concern about this area being generic is that you are now in a
>>>>> state where any bpf program must know about all the bpf programs in the
>>>>> receive pipeline before it can properly parse what is stored in the
>>>>> meta-data and add it to an skb (or perform any other action).
>>>>> Especially if each program adds it's own meta-data along the way.
>>>>>
>>>>> Maybe this isn't a big concern based on the number of users of this
>>>>> today, but it just starts to seem like a concern as there are these
>>>>> hints being passed between layers that are challenging to track due to a
>>>>> lack of a standard format for passing data between.
>>>>
>>>> Btw, we do have similar kind of programmable scratch buffer also today
>>>> wrt skb cb[] that you can program from tc side, the perf ring buffer,
>>>> which doesn't have any fixed layout for the slots, or a per-cpu map
>>>> where you can transfer data between tail calls for example, then tail
>>>> calls themselves that need to coordinate, or simply mangling of packets
>>>> itself if you will, but more below to your use case ...
>>>>
>>>>> The main reason I bring this up is that Michael and I had discussed and
>>>>> designed a way for drivers to communicate between each other that rx
>>>>> resources could be freed after a tx completion on an XDP_REDIRECT
>>>>> action. Much like this code, it involved adding an new element to
>>>>> struct xdp_md that could point to the important information. Now that
>>>>> there is a generic way to handle this, it would seem nice to be able to
>>>>> leverage it, but I'm not sure how reliable this meta-data area would be
>>>>> without the ability to mark it in some manner.
>>>>>
>>>>> For additional background, the minimum amount of data needed in the case
>>>>> Michael and I were discussing was really 2 words. One to serve as a
>>>>> pointer to an rx_ring structure and one to have a counter to the rx
>>>>> producer entry. This data could be acessed by the driver processing the
>>>>> tx completions and callback to the driver that received the frame off the wire
>>>>> to perform any needed processing. (For those curious this would also require a
>>>>> new callback/netdev op to act on this data stored in the XDP buffer.)
>>>>
>>>> What you describe above doesn't seem to be fitting to the use-case of
>>>> this set, meaning the area here is fully programmable out of the BPF
>>>> program, the infrastructure you're describing is some sort of means of
>>>> communication between drivers for the XDP_REDIRECT, and should be
>>>> outside of the control of the BPF program to mangle.
>>>
>>> OK, I understand that perspective. I think saying this is really meant
>>> as a BPF<->BPF communication channel for now is fine.
>>>
>>>> You could probably reuse the base infra here and make a part of that
>>>> inaccessible for the program with some sort of a fixed layout, but I
>>>> haven't seen your code yet to be able to fully judge. Intention here
>>>> is to allow for programmability within the BPF prog in a generic way,
>>>> such that based on the use-case it can be populated in specific ways
>>>> and propagated to the skb w/o having to define a fixed layout and
>>>> bloat xdp_buff all the way to an skb while still retaining all the
>>>> flexibility.
>>>
>>> Some level of reuse might be proper, but I'd rather it be explicit for
>>> my use since it's not exclusively something that will need to be used by
>>> a BPF prog, but rather the driver. I'll produce some patches this week
>>> for reference.
>>
>> Sorry for chiming in late, I've been offline.
>>
>> We're looking to add some functionality from driver to XDP inside this
>> xdp_buff->data_meta region. We want to assign it to an opaque
>> structure, that would be specific per driver (think of a flex descriptor
>> coming out of the hardware). We'd like to pass these offloaded
>> computations into XDP programs to help accelerate them, such as packet
>> type, where headers are located, etc. It's similar to Jesper's RFC
>> patches back in May when passing through the mlx Rx descriptor to XDP.
>>
>> This is actually what a few of us are planning to present at NetDev 2.2
>> in November. If you're hoping to restrict this headroom in the xdp_buff
>> for an exclusive use case with XDP_REDIRECT, then I'd like to discuss
>> that further.
>>
>
> No sweat, PJ, thanks for replying. I saw the notes for your accepted
> session and I'm looking forward to it.
>
> John's suggestion earlier in the thread was actually similar to the
> conclusion I reached when thinking about Daniel's patch a bit more.
> (I like John's better though as it doesn't get constrained by UAPI.)
> Since redirect actions happen at a point where no other programs will
> run on the buffer, that space can be used for this redirect data and
> there are no conflicts.
Ah, yes, John and I spoke about this at Plumber's and this is basically
what we came to as well. A set of helpers that won't have to be in
UAPI, but they will be potentially vendor-specific to extract the
meta-data hints out for the XDP program to use.
> It sounds like the idea behind your proposal includes populating some
> data into the buffer before the XDP program is executed so that it can
> be used by the program. Would this data be useful later in the driver
> or stack or are you just hoping to accelerate processing of frames in
> the BPF program?
Right now we're thinking it would only be useful for XDP programs to
execute things quicker, i.e. not have to compute things that are already
computed by the hardware (rxhash, ptype, header locations, etc.). I
don't have any plans to pass this data off elsewhere in the stack or
back to the driver at this point.
> If the headroom needed for redirect info was only added after it was
> clear the redirect action was needed, would this conflict with the
> information you are trying to provide? I had planned to add this just
> after the action was XDP_REDIRECT was selected or at the end of the
> driver's ndo_xdp_xmit function -- it seems like it would not conflict.
I'm pretty sure I misunderstood what you were going after with
XDP_REDIRECT reserving the headroom. Our use case (patches coming in a
few weeks) will populate the headroom coming out of the driver to XDP,
and then once the XDP program extracts whatever hints it wants via
helpers, I fully expect that area in the headroom to get stomped by
something else. If we want to send any of that hint data up farther,
we'll already have it extracted via the helpers, and the eBPF program
can happily assign it to wherever in the outbound metadata area.
> (There's also Jesper's series from today -- I've seen it but have not
> had time to fully grok all of those changes.)
I'm also working through my inbox to get to that series. I have some
email to catch up on...
Thanks Andy,
-PJ
^ permalink raw reply
* [PATCH net-next] ibmvnic: Set state UP
From: Mick Tarsel @ 2017-09-28 20:53 UTC (permalink / raw)
To: netdev; +Cc: tlfalcon
State is initially reported as UNKNOWN. Before register call
netif_carrier_off(). Once the device is opened, call netif_carrier_on() in
order to set the state to UP.
Signed-off-by: Mick Tarsel <mjtarsel@linux.vnet.ibm.com>
---
drivers/net/ethernet/ibm/ibmvnic.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index cb8182f..4bc14a9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -927,6 +927,7 @@ static int ibmvnic_open(struct net_device *netdev)
}
rc = __ibmvnic_open(netdev);
+ netif_carrier_on(netdev);
mutex_unlock(&adapter->reset_lock);
return rc;
@@ -3899,6 +3900,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
if (rc)
goto ibmvnic_init_fail;
+ netif_carrier_off(netdev);
rc = register_netdev(netdev);
if (rc) {
dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc);
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH net-next 2/6] bpf: add meta pointer for direct access
From: John Fastabend @ 2017-09-28 21:22 UTC (permalink / raw)
To: Waskiewicz Jr, Peter, Andy Gospodarek
Cc: Daniel Borkmann, davem@davemloft.net,
alexei.starovoitov@gmail.com, jakub.kicinski@netronome.com,
netdev@vger.kernel.org, mchan@broadcom.com
In-Reply-To: <E0D909EE5BB15A4699798539EA149D7F077E6438@ORSMSX103.amr.corp.intel.com>
[...]
> I'm pretty sure I misunderstood what you were going after with
> XDP_REDIRECT reserving the headroom. Our use case (patches coming in a
> few weeks) will populate the headroom coming out of the driver to XDP,
> and then once the XDP program extracts whatever hints it wants via
> helpers, I fully expect that area in the headroom to get stomped by
> something else. If we want to send any of that hint data up farther,
> we'll already have it extracted via the helpers, and the eBPF program
> can happily assign it to wherever in the outbound metadata area.
In case its not obvious with the latest xdp metadata patches the outbound
metadata can then be pushed into skb fields via a tc_cls program if needed.
.John
>
>> (There's also Jesper's series from today -- I've seen it but have not
>> had time to fully grok all of those changes.)
>
> I'm also working through my inbox to get to that series. I have some
> email to catch up on...
>
> Thanks Andy,
> -PJ
>
^ permalink raw reply
* Re: [PATCH net-next 2/6] bpf: add meta pointer for direct access
From: Daniel Borkmann @ 2017-09-28 21:29 UTC (permalink / raw)
To: Waskiewicz Jr, Peter, Andy Gospodarek
Cc: davem@davemloft.net, alexei.starovoitov@gmail.com,
john.fastabend@gmail.com, jakub.kicinski@netronome.com,
netdev@vger.kernel.org, mchan@broadcom.com
In-Reply-To: <E0D909EE5BB15A4699798539EA149D7F077E6438@ORSMSX103.amr.corp.intel.com>
On 09/28/2017 10:52 PM, Waskiewicz Jr, Peter wrote:
> On 9/28/17 12:59 PM, Andy Gospodarek wrote:
>> On Thu, Sep 28, 2017 at 1:59 AM, Waskiewicz Jr, Peter
>> <peter.waskiewicz.jr@intel.com> wrote:
>>> On 9/26/17 10:21 AM, Andy Gospodarek wrote:
>>>> On Mon, Sep 25, 2017 at 08:50:28PM +0200, Daniel Borkmann wrote:
>>>>> On 09/25/2017 08:10 PM, Andy Gospodarek wrote:
>>>>> [...]
>>>>>> First, thanks for this detailed description. It was helpful to read
>>>>>> along with the patches.
>>>>>>
>>>>>> My only concern about this area being generic is that you are now in a
>>>>>> state where any bpf program must know about all the bpf programs in the
>>>>>> receive pipeline before it can properly parse what is stored in the
>>>>>> meta-data and add it to an skb (or perform any other action).
>>>>>> Especially if each program adds it's own meta-data along the way.
>>>>>>
>>>>>> Maybe this isn't a big concern based on the number of users of this
>>>>>> today, but it just starts to seem like a concern as there are these
>>>>>> hints being passed between layers that are challenging to track due to a
>>>>>> lack of a standard format for passing data between.
>>>>>
>>>>> Btw, we do have similar kind of programmable scratch buffer also today
>>>>> wrt skb cb[] that you can program from tc side, the perf ring buffer,
>>>>> which doesn't have any fixed layout for the slots, or a per-cpu map
>>>>> where you can transfer data between tail calls for example, then tail
>>>>> calls themselves that need to coordinate, or simply mangling of packets
>>>>> itself if you will, but more below to your use case ...
>>>>>
>>>>>> The main reason I bring this up is that Michael and I had discussed and
>>>>>> designed a way for drivers to communicate between each other that rx
>>>>>> resources could be freed after a tx completion on an XDP_REDIRECT
>>>>>> action. Much like this code, it involved adding an new element to
>>>>>> struct xdp_md that could point to the important information. Now that
>>>>>> there is a generic way to handle this, it would seem nice to be able to
>>>>>> leverage it, but I'm not sure how reliable this meta-data area would be
>>>>>> without the ability to mark it in some manner.
>>>>>>
>>>>>> For additional background, the minimum amount of data needed in the case
>>>>>> Michael and I were discussing was really 2 words. One to serve as a
>>>>>> pointer to an rx_ring structure and one to have a counter to the rx
>>>>>> producer entry. This data could be acessed by the driver processing the
>>>>>> tx completions and callback to the driver that received the frame off the wire
>>>>>> to perform any needed processing. (For those curious this would also require a
>>>>>> new callback/netdev op to act on this data stored in the XDP buffer.)
>>>>>
>>>>> What you describe above doesn't seem to be fitting to the use-case of
>>>>> this set, meaning the area here is fully programmable out of the BPF
>>>>> program, the infrastructure you're describing is some sort of means of
>>>>> communication between drivers for the XDP_REDIRECT, and should be
>>>>> outside of the control of the BPF program to mangle.
>>>>
>>>> OK, I understand that perspective. I think saying this is really meant
>>>> as a BPF<->BPF communication channel for now is fine.
>>>>
>>>>> You could probably reuse the base infra here and make a part of that
>>>>> inaccessible for the program with some sort of a fixed layout, but I
>>>>> haven't seen your code yet to be able to fully judge. Intention here
>>>>> is to allow for programmability within the BPF prog in a generic way,
>>>>> such that based on the use-case it can be populated in specific ways
>>>>> and propagated to the skb w/o having to define a fixed layout and
>>>>> bloat xdp_buff all the way to an skb while still retaining all the
>>>>> flexibility.
>>>>
>>>> Some level of reuse might be proper, but I'd rather it be explicit for
>>>> my use since it's not exclusively something that will need to be used by
>>>> a BPF prog, but rather the driver. I'll produce some patches this week
>>>> for reference.
>>>
>>> Sorry for chiming in late, I've been offline.
>>>
>>> We're looking to add some functionality from driver to XDP inside this
>>> xdp_buff->data_meta region. We want to assign it to an opaque
>>> structure, that would be specific per driver (think of a flex descriptor
>>> coming out of the hardware). We'd like to pass these offloaded
>>> computations into XDP programs to help accelerate them, such as packet
>>> type, where headers are located, etc. It's similar to Jesper's RFC
>>> patches back in May when passing through the mlx Rx descriptor to XDP.
>>>
>>> This is actually what a few of us are planning to present at NetDev 2.2
>>> in November. If you're hoping to restrict this headroom in the xdp_buff
>>> for an exclusive use case with XDP_REDIRECT, then I'd like to discuss
>>> that further.
>>
>> No sweat, PJ, thanks for replying. I saw the notes for your accepted
>> session and I'm looking forward to it.
>>
>> John's suggestion earlier in the thread was actually similar to the
>> conclusion I reached when thinking about Daniel's patch a bit more.
>> (I like John's better though as it doesn't get constrained by UAPI.)
>> Since redirect actions happen at a point where no other programs will
>> run on the buffer, that space can be used for this redirect data and
>> there are no conflicts.
Yep fully agree, it's not read anywhere else anymore or could go up
the stack where we'd read it out again, so that's the best solution
for your use-case moving forward, Andy. I do like that we don't expose
to uapi.
> Ah, yes, John and I spoke about this at Plumber's and this is basically
> what we came to as well. A set of helpers that won't have to be in
> UAPI, but they will be potentially vendor-specific to extract the
> meta-data hints out for the XDP program to use.
>
>> It sounds like the idea behind your proposal includes populating some
>> data into the buffer before the XDP program is executed so that it can
>> be used by the program. Would this data be useful later in the driver
>> or stack or are you just hoping to accelerate processing of frames in
>> the BPF program?
>
> Right now we're thinking it would only be useful for XDP programs to
> execute things quicker, i.e. not have to compute things that are already
> computed by the hardware (rxhash, ptype, header locations, etc.). I
> don't have any plans to pass this data off elsewhere in the stack or
> back to the driver at this point.
>
>> If the headroom needed for redirect info was only added after it was
>> clear the redirect action was needed, would this conflict with the
>> information you are trying to provide? I had planned to add this just
>> after the action was XDP_REDIRECT was selected or at the end of the
>> driver's ndo_xdp_xmit function -- it seems like it would not conflict.
>
> I'm pretty sure I misunderstood what you were going after with
> XDP_REDIRECT reserving the headroom. Our use case (patches coming in a
> few weeks) will populate the headroom coming out of the driver to XDP,
> and then once the XDP program extracts whatever hints it wants via
> helpers, I fully expect that area in the headroom to get stomped by
> something else. If we want to send any of that hint data up farther,
> we'll already have it extracted via the helpers, and the eBPF program
> can happily assign it to wherever in the outbound metadata area.
Sure, these two are compatible with each other; in your case it's
populated before the prog is called, and the prog can use it while
processing, in Andy's case it's populated after the prog was called
when we need to redirect, so both fine.
Thanks,
Daniel
^ permalink raw reply
* Re: [PATCH net-next 2/6] bpf: add meta pointer for direct access
From: Waskiewicz Jr, Peter @ 2017-09-28 21:40 UTC (permalink / raw)
To: John Fastabend, Andy Gospodarek
Cc: Daniel Borkmann, davem@davemloft.net,
alexei.starovoitov@gmail.com, jakub.kicinski@netronome.com,
netdev@vger.kernel.org, mchan@broadcom.com
In-Reply-To: <bdce98b7-1d32-3cd9-1289-79807af8443f@gmail.com>
On 9/28/17 2:23 PM, John Fastabend wrote:
> [...]
>
>> I'm pretty sure I misunderstood what you were going after with
>> XDP_REDIRECT reserving the headroom. Our use case (patches coming in a
>> few weeks) will populate the headroom coming out of the driver to XDP,
>> and then once the XDP program extracts whatever hints it wants via
>> helpers, I fully expect that area in the headroom to get stomped by
>> something else. If we want to send any of that hint data up farther,
>> we'll already have it extracted via the helpers, and the eBPF program
>> can happily assign it to wherever in the outbound metadata area.
>
> In case its not obvious with the latest xdp metadata patches the outbound
> metadata can then be pushed into skb fields via a tc_cls program if needed.
Yes, that was what I was alluding to with "can happily assign it to
wherever." The patches we're working on are driver->XDP, then anything
else using the latest meta-data patches would be XDP->anywhere else. So
I don't think we're going to step on any toes.
Thanks John,
-PJ
^ permalink raw reply
* Re: [PATCH net-next] libbpf: use map_flags when creating maps
From: Daniel Borkmann @ 2017-09-28 21:44 UTC (permalink / raw)
To: Craig Gallek; +Cc: Alexei Starovoitov, David S . Miller, Chonggang Li, netdev
In-Reply-To: <CAEfhGiwai3fZsWPx--Axyc1n4+WRwxeFO+uLgQKbQ-8wiJqtAw@mail.gmail.com>
On 09/28/2017 07:33 PM, Craig Gallek wrote:
> On Wed, Sep 27, 2017 at 6:03 PM, Daniel Borkmann <daniel@iogearbox.net> wrote:
>> On 09/27/2017 06:29 PM, Alexei Starovoitov wrote:
>>> On 9/27/17 7:04 AM, Craig Gallek wrote:
>>>> From: Craig Gallek <kraig@google.com>
[...]
>>>
>>> yes it will break loading of pre-compiled .o
>>> Instead of breaking, let's fix the loader to do it the way
>>> samples/bpf/bpf_load.c does.
>>> See commit 156450d9d964 ("samples/bpf: make bpf_load.c code compatible
>>> with ELF maps section changes")
>>
>> +1, iproute2 loader also does map spec fixup
>>
>> For libbpf it would be good also such that it reduces the diff
>> further between the libbpf and bpf_load so that it allows move
>> to libbpf for samples in future.
>
> Fair enough, I'll try to get this to work more dynamically. I did
> noticed that the fields of struct bpf_map_def in
> selftests/.../bpf_helpers.h and iproute2's struct bpf_elf_map have
> diverged. The flags field is the only thing missing from libbpf right
> now (and they are at the same offset for both), so it won't be an
> issue for this change, but it is going to make unifying all of these
> things under libbpf not trivial at some point...
Yes, iproute2 uses its own loader with own specifics related to
iproute2. With the above I rather meant that we can reduce the
gap between libbpf and bpf_load from the BPF samples, so that
it would allow us to migrate samples over entirely, there was
unfortunately never a follow-up on 156450d9d964 though, but given
there is need to extend libbpf (I guess mostly due to lpm map
handling ;)), we need to do a similar thing there as well to not
break existing obj files.
^ permalink raw reply
* linux-next: Signed-off-by missing for commit in the net-next tree
From: Stephen Rothwell @ 2017-09-28 21:46 UTC (permalink / raw)
To: David Miller, Networking
Cc: Linux-Next Mailing List, Linux Kernel Mailing List, Eric Dumazet
Hi all,
Commit
8f1975e31d8e ("inetpeer: speed up inetpeer_invalidate_tree()")
is missing a Signed-off-by from its author.
--
Cheers,
Stephen Rothwell
^ permalink raw reply
* [PATCH v3 net-next 0/8] flow_dissector: Protocol specific flow dissector offload
From: Tom Herbert @ 2017-09-28 21:46 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
This patch set adds a new offload type to perform flow dissection for
specific protocols (either by EtherType or by IP protocol). This is
primary useful to crack open UDP encapsulations (like VXLAN, GUE) for
the purposes of parsing the encapsulated packet.
Items in this patch set:
- Create new protocol case in __skb_dissect for ETH_P_TEB. This is based
on the code in the GRE dissect function and the special handling in
GRE can now be removed (it sets protocol to ETH_P_TEB and returns so
goto proto_again is done)
- Add infrastructure for protocol specific flow dissection offload
- Add infrastructure to perform UDP flow dissection. Uses same model of
GRO where a flow_dissect callback can be associated with a UDP
socket
- Use the infrastructure to support flow dissection of VXLAN and GUE
Tested:
Forced RPS to call flow dissection for VXLAN, FOU, and GUE. Observed
that inner packet was being properly dissected.
v2: Add signed off
v3:
- Make skb argument of flow dissector to be non const
- Change UDP GRO to only do something if encap_needed static
key is set
- don't reference inet6_offloads or inet_offloads, get to
them through ptype
Tom Herbert (8):
flow_dissector: Change skbuf argument to be non const
flow_dissector: Move ETH_P_TEB processing to main switch
udp: Check static key udp_encap_needed in udp_gro_receive
flow_dissector: Add protocol specific flow dissection offload
ip: Add callbacks to flow dissection by IP protocol
udp: flow dissector offload
fou: Support flow dissection
vxlan: support flow dissect
drivers/net/vxlan.c | 40 +++++++++++++++++++++++++
include/linux/netdevice.h | 27 +++++++++++++++++
include/linux/skbuff.h | 12 ++++----
include/linux/udp.h | 8 +++++
include/net/flow_dissector.h | 1 +
include/net/ip_fib.h | 4 +--
include/net/route.h | 4 +--
include/net/udp.h | 10 +++++++
include/net/udp_tunnel.h | 8 +++++
net/core/dev.c | 65 ++++++++++++++++++++++++++++++++++++++++
net/core/flow_dissector.c | 71 +++++++++++++++++++++++++++-----------------
net/ipv4/af_inet.c | 27 +++++++++++++++++
net/ipv4/fib_semantics.c | 2 +-
net/ipv4/fou.c | 63 +++++++++++++++++++++++++++++++++++++++
net/ipv4/route.c | 10 ++++---
net/ipv4/udp.c | 4 ++-
net/ipv4/udp_offload.c | 55 ++++++++++++++++++++++++++++++++++
net/ipv4/udp_tunnel.c | 1 +
net/ipv6/ip6_offload.c | 27 +++++++++++++++++
net/ipv6/udp_offload.c | 23 ++++++++++++++
net/sched/sch_sfq.c | 2 +-
21 files changed, 419 insertions(+), 45 deletions(-)
--
2.11.0
^ permalink raw reply
* [PATCH v3 net-next 1/8] flow_dissector: Change skbuf argument to be non const
From: Tom Herbert @ 2017-09-28 21:48 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
Change the skbuf argument of __skb_flow_dissect to be non constant so
that the function can call functions that take non constant skbuf
arguments. This is needed if we are to call socket lookup or BPF in the
flow dissector path.
The changes include unraveling the call chain into __skb_flow_dissect so
that those also use non constant skbufs.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/linux/skbuff.h | 12 ++++++------
include/net/ip_fib.h | 4 ++--
include/net/route.h | 4 ++--
net/core/flow_dissector.c | 10 +++++-----
net/ipv4/fib_semantics.c | 2 +-
net/ipv4/route.c | 6 +++---
net/sched/sch_sfq.c | 2 +-
7 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 19e64bfb1a66..5a6e765e120f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1155,8 +1155,8 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
}
void __skb_get_hash(struct sk_buff *skb);
-u32 __skb_get_hash_symmetric(const struct sk_buff *skb);
-u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
+u32 skb_get_poff(struct sk_buff *skb);
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
const struct flow_keys *keys, int hlen);
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
@@ -1172,13 +1172,13 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
const struct flow_dissector_key *key,
unsigned int key_count);
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container,
void *data, __be16 proto, int nhoff, int hlen,
unsigned int flags);
-static inline bool skb_flow_dissect(const struct sk_buff *skb,
+static inline bool skb_flow_dissect(struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container, unsigned int flags)
{
@@ -1186,7 +1186,7 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb,
NULL, 0, 0, 0, flags);
}
-static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+static inline bool skb_flow_dissect_flow_keys(struct sk_buff *skb,
struct flow_keys *flow,
unsigned int flags)
{
@@ -1225,7 +1225,7 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6
return skb->hash;
}
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(struct sk_buff *skb, u32 perturb);
static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
{
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1a7f7e424320..a376dfe1ad44 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -374,11 +374,11 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
- const struct sk_buff *skb);
+ struct sk_buff *skb);
#endif
void fib_select_multipath(struct fib_result *res, int hash);
void fib_select_path(struct net *net, struct fib_result *res,
- struct flowi4 *fl4, const struct sk_buff *skb);
+ struct flowi4 *fl4, struct sk_buff *skb);
/* Exported by fib_trie.c */
void fib_trie_init(void);
diff --git a/include/net/route.h b/include/net/route.h
index 57dfc6850d37..cb95b79f0117 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -114,10 +114,10 @@ int ip_rt_init(void);
void rt_cache_flush(struct net *net);
void rt_flush_dev(struct net_device *dev);
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
- const struct sk_buff *skb);
+ struct sk_buff *skb);
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
struct fib_result *res,
- const struct sk_buff *skb);
+ struct sk_buff *skb);
static inline struct rtable *__ip_route_output_key(struct net *net,
struct flowi4 *flp)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 0a977373d003..76f5e5bc3177 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -424,7 +424,7 @@ static bool skb_flow_dissect_allowed(int *num_hdrs)
*
* Caller must take care of zeroing target container memory.
*/
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(struct sk_buff *skb,
struct flow_dissector *flow_dissector,
void *target_container,
void *data, __be16 proto, int nhoff, int hlen,
@@ -1015,7 +1015,7 @@ u32 flow_hash_from_keys(struct flow_keys *keys)
}
EXPORT_SYMBOL(flow_hash_from_keys);
-static inline u32 ___skb_get_hash(const struct sk_buff *skb,
+static inline u32 ___skb_get_hash(struct sk_buff *skb,
struct flow_keys *keys, u32 keyval)
{
skb_flow_dissect_flow_keys(skb, keys,
@@ -1053,7 +1053,7 @@ EXPORT_SYMBOL(make_flow_keys_digest);
static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
-u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
{
struct flow_keys keys;
@@ -1090,7 +1090,7 @@ void __skb_get_hash(struct sk_buff *skb)
}
EXPORT_SYMBOL(__skb_get_hash);
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(struct sk_buff *skb, u32 perturb)
{
struct flow_keys keys;
@@ -1158,7 +1158,7 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data,
* truncate packets without needing to push actual payload to the user
* space and can analyze headers only, instead.
*/
-u32 skb_get_poff(const struct sk_buff *skb)
+u32 skb_get_poff(struct sk_buff *skb)
{
struct flow_keys keys;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 57a5d48acee8..dc610646bc4c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1759,7 +1759,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
#endif
void fib_select_path(struct net *net, struct fib_result *res,
- struct flowi4 *fl4, const struct sk_buff *skb)
+ struct flowi4 *fl4, struct sk_buff *skb)
{
bool oif_check;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 94d4cd2d5ea4..94c5b81d8f2b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1791,7 +1791,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
/* if skb is set it will be used and fl4 can be NULL */
int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
- const struct sk_buff *skb)
+ struct sk_buff *skb)
{
struct net *net = fi->fib_net;
struct flow_keys hash_keys;
@@ -2270,7 +2270,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
*/
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
- const struct sk_buff *skb)
+ struct sk_buff *skb)
{
__u8 tos = RT_FL_TOS(fl4);
struct fib_result res;
@@ -2295,7 +2295,7 @@ EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
struct fib_result *res,
- const struct sk_buff *skb)
+ struct sk_buff *skb)
{
struct net_device *dev_out = NULL;
int orig_oif = fl4->flowi4_oif;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 74ea863b8240..0d2d3a8d03f0 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -158,7 +158,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
}
static unsigned int sfq_hash(const struct sfq_sched_data *q,
- const struct sk_buff *skb)
+ struct sk_buff *skb)
{
return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1);
}
--
2.11.0
^ permalink raw reply related
* [PATCH v3 net-next 2/8] flow_dissector: Move ETH_P_TEB processing to main switch
From: Tom Herbert @ 2017-09-28 21:48 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
In-Reply-To: <20170928214823.2426-1-tom@quantonium.net>
Support for processing TEB is currently in GRE flow dissection as a
special case. This can be moved to be a case the main proto switch in
__skb_flow_dissect.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
net/core/flow_dissector.c | 45 ++++++++++++++++++++++++---------------------
1 file changed, 24 insertions(+), 21 deletions(-)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 76f5e5bc3177..c15b41f96cbe 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -282,27 +282,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb,
if (hdr->flags & GRE_SEQ)
offset += sizeof(((struct pptp_gre_header *) 0)->seq);
- if (gre_ver == 0) {
- if (*p_proto == htons(ETH_P_TEB)) {
- const struct ethhdr *eth;
- struct ethhdr _eth;
-
- eth = __skb_header_pointer(skb, *p_nhoff + offset,
- sizeof(_eth),
- data, *p_hlen, &_eth);
- if (!eth)
- return FLOW_DISSECT_RET_OUT_BAD;
- *p_proto = eth->h_proto;
- offset += sizeof(*eth);
-
- /* Cap headers that we access via pointers at the
- * end of the Ethernet header as our maximum alignment
- * at that point is only 2 bytes.
- */
- if (NET_IP_ALIGN)
- *p_hlen = *p_nhoff + offset;
- }
- } else { /* version 1, must be PPTP */
+ /* version 1, must be PPTP */
+ if (gre_ver == 1) {
u8 _ppp_hdr[PPP_HDRLEN];
u8 *ppp_hdr;
@@ -595,6 +576,28 @@ bool __skb_flow_dissect(struct sk_buff *skb,
break;
}
+ case htons(ETH_P_TEB): {
+ const struct ethhdr *eth;
+ struct ethhdr _eth;
+
+ eth = __skb_header_pointer(skb, nhoff, sizeof(_eth),
+ data, hlen, &_eth);
+ if (!eth)
+ goto out_bad;
+
+ proto = eth->h_proto;
+ nhoff += sizeof(*eth);
+
+ /* Cap headers that we access via pointers at the
+ * end of the Ethernet header as our maximum alignment
+ * at that point is only 2 bytes.
+ */
+ if (NET_IP_ALIGN)
+ hlen = nhoff;
+
+ fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+ break;
+ }
case htons(ETH_P_8021AD):
case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
--
2.11.0
^ permalink raw reply related
* [PATCH v3 net-next 3/8] udp: Check static key udp_encap_needed in udp_gro_receive
From: Tom Herbert @ 2017-09-28 21:48 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
In-Reply-To: <20170928214823.2426-1-tom@quantonium.net>
Currently, the only support for udp gro is provided by UDP encapsulation
protocols. Since they always set udp_encap_needed we can check that in
udp_gro_receive functions before performing a socket lookup.
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/net/udp.h | 2 ++
net/ipv4/udp.c | 4 +++-
net/ipv4/udp_offload.c | 7 +++++++
net/ipv6/udp_offload.c | 7 +++++++
4 files changed, 19 insertions(+), 1 deletion(-)
diff --git a/include/net/udp.h b/include/net/udp.h
index 12dfbfe2e2d7..c6b1c5d8d3c9 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -97,6 +97,8 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
extern struct proto udp_prot;
+extern struct static_key udp_encap_needed;
+
extern atomic_long_t udp_memory_allocated;
/* sysctl variables for udp */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 784ced0b9150..2788843e8eb2 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1813,7 +1813,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
return 0;
}
-static struct static_key udp_encap_needed __read_mostly;
+struct static_key udp_encap_needed __read_mostly;
+EXPORT_SYMBOL(udp_encap_needed);
+
void udp_encap_enable(void)
{
static_key_enable(&udp_encap_needed);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 97658bfc1b58..a744bb515455 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -261,6 +261,13 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ if (!static_key_false(&udp_encap_needed)) {
+ /* Currently udp_gro_receive only does something if
+ * a UDP encapsulation has been set.
+ */
+ goto flush;
+ }
+
if (unlikely(!uh))
goto flush;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 455fd4e39333..111b026e4f03 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -34,6 +34,13 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
{
struct udphdr *uh = udp_gro_udphdr(skb);
+ if (!static_key_false(&udp_encap_needed)) {
+ /* Currently udp_gro_receive only does something if
+ * a UDP encapsulation has been set.
+ */
+ goto flush;
+ }
+
if (unlikely(!uh))
goto flush;
--
2.11.0
^ permalink raw reply related
* [PATCH v3 net-next 4/8] flow_dissector: Add protocol specific flow dissection offload
From: Tom Herbert @ 2017-09-28 21:48 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
In-Reply-To: <20170928214823.2426-1-tom@quantonium.net>
Add offload capability for performing protocol specific flow dissection
(either by EtherType or IP protocol).
Specifically:
- Add flow_dissect to offload callbacks
- Move flow_dissect_ret enum to flow_dissector.h, cleanup names and add a
couple of values
- Unify handling of functions that return flow_dissect_ret enum
- In __skb_flow_dissect, add default case for switch(proto) as well as
switch(ip_proto) that looks up and calls protocol specific flow
dissection
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
include/linux/netdevice.h | 27 ++++++++++++++++++
include/net/flow_dissector.h | 1 +
net/core/dev.c | 65 ++++++++++++++++++++++++++++++++++++++++++++
net/core/flow_dissector.c | 16 +++++++++--
net/ipv4/route.c | 4 ++-
5 files changed, 110 insertions(+), 3 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f535779d9dc1..565d7cdfe967 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2207,12 +2207,25 @@ struct offload_callbacks {
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
+ enum flow_dissect_ret (*flow_dissect)(struct sk_buff *skb,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags);
};
struct packet_offload {
__be16 type; /* This is really htons(ether_type). */
u16 priority;
struct offload_callbacks callbacks;
+ enum flow_dissect_ret (*proto_flow_dissect)(struct sk_buff *skb,
+ u8 proto,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags);
struct list_head list;
};
@@ -3252,6 +3265,20 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi);
gro_result_t napi_gro_frags(struct napi_struct *napi);
struct packet_offload *gro_find_receive_by_type(__be16 type);
struct packet_offload *gro_find_complete_by_type(__be16 type);
+enum flow_dissect_ret flow_dissect_by_type(struct sk_buff *skb,
+ __be16 type,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags);
+enum flow_dissect_ret flow_dissect_by_type_proto(struct sk_buff *skb,
+ __be16 type, u8 proto,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags);
static inline void napi_free_frags(struct napi_struct *napi)
{
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index fc3dce730a6b..ad75bbfd1c9c 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -213,6 +213,7 @@ enum flow_dissector_key_id {
#define FLOW_DISSECTOR_F_STOP_AT_L3 BIT(1)
#define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(2)
#define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(3)
+#define FLOW_DISSECTOR_F_STOP_AT_L4 BIT(4)
struct flow_dissector_key {
enum flow_dissector_key_id key_id;
diff --git a/net/core/dev.c b/net/core/dev.c
index e350c768d4b5..f3cd884bd04b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -104,6 +104,7 @@
#include <linux/stat.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
+#include <net/flow_dissector.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/checksum.h>
@@ -4907,6 +4908,70 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
}
EXPORT_SYMBOL(gro_find_complete_by_type);
+enum flow_dissect_ret flow_dissect_by_type(struct sk_buff *skb,
+ __be16 type,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags)
+{
+ enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->callbacks.flow_dissect)
+ continue;
+ ret = ptype->callbacks.flow_dissect(skb, key_control,
+ flow_dissector,
+ target_container,
+ data, p_proto,
+ p_ip_proto, p_nhoff,
+ p_hlen, flags);
+ break;
+ }
+
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(flow_dissect_by_type);
+
+enum flow_dissect_ret flow_dissect_by_type_proto(struct sk_buff *skb,
+ __be16 type, u8 proto,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags)
+{
+ enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->proto_flow_dissect)
+ continue;
+ ret = ptype->proto_flow_dissect(skb, proto, key_control,
+ flow_dissector,
+ target_container,
+ data, p_proto,
+ p_ip_proto, p_nhoff,
+ p_hlen, flags);
+ break;
+ }
+
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(flow_dissect_by_type_proto);
+
static void napi_skb_free_stolen_head(struct sk_buff *skb)
{
skb_dst_drop(skb);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index c15b41f96cbe..84b8eb1f6664 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -9,6 +9,7 @@
#include <net/ipv6.h>
#include <net/gre.h>
#include <net/pptp.h>
+#include <net/protocol.h>
#include <linux/igmp.h>
#include <linux/icmp.h>
#include <linux/sctp.h>
@@ -721,7 +722,11 @@ bool __skb_flow_dissect(struct sk_buff *skb,
break;
default:
- fdret = FLOW_DISSECT_RET_OUT_BAD;
+ fdret = flow_dissect_by_type(skb, proto, key_control,
+ flow_dissector,
+ target_container,
+ data, &proto, &ip_proto, &nhoff,
+ &hlen, flags);
break;
}
@@ -838,6 +843,12 @@ bool __skb_flow_dissect(struct sk_buff *skb,
break;
default:
+ fdret = flow_dissect_by_type_proto(skb, proto,
+ ip_proto, key_control,
+ flow_dissector,
+ target_container,
+ data, &proto, &ip_proto, &nhoff,
+ &hlen, flags);
break;
}
@@ -1022,7 +1033,8 @@ static inline u32 ___skb_get_hash(struct sk_buff *skb,
struct flow_keys *keys, u32 keyval)
{
skb_flow_dissect_flow_keys(skb, keys,
- FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL |
+ FLOW_DISSECTOR_F_STOP_AT_L4);
return __flow_hash_from_keys(keys, keyval);
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 94c5b81d8f2b..69d6ce7dfa18 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1811,7 +1811,9 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
case 1:
/* skb is currently provided only when forwarding */
if (skb) {
- unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+ unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP |
+ FLOW_DISSECTOR_F_STOP_AT_L4;
+;
struct flow_keys keys;
/* short-circuit if we already have L4 hash present */
--
2.11.0
^ permalink raw reply related
* [PATCH v3 net-next 5/8] ip: Add callbacks to flow dissection by IP protocol
From: Tom Herbert @ 2017-09-28 21:48 UTC (permalink / raw)
To: davem; +Cc: netdev, rohit, Tom Herbert
In-Reply-To: <20170928214823.2426-1-tom@quantonium.net>
Populate the proto_flow_dissect function for IPv4 and IPv6 packet
offloads. This allows the caller to flow dissect a packet starting
at the given IP protocol (as parsed to that point by flow dissector
for instance).
Signed-off-by: Tom Herbert <tom@quantonium.net>
---
net/ipv4/af_inet.c | 27 +++++++++++++++++++++++++++
net/ipv6/ip6_offload.c | 27 +++++++++++++++++++++++++++
2 files changed, 54 insertions(+)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e31108e5ef79..18c1d884999a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1440,6 +1440,32 @@ static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
return inet_gro_receive(head, skb);
}
+static enum flow_dissect_ret inet_proto_flow_dissect(struct sk_buff *skb,
+ u8 proto,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags)
+{
+ enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+ const struct net_offload *ops;
+
+ rcu_read_lock();
+
+ ops = rcu_dereference(inet_offloads[proto]);
+ if (ops && ops->callbacks.flow_dissect)
+ ret = ops->callbacks.flow_dissect(skb, key_control,
+ flow_dissector,
+ target_container,
+ data, p_proto, p_ip_proto,
+ p_nhoff, p_hlen, flags);
+
+ rcu_read_unlock();
+
+ return ret;
+}
+
#define SECONDS_PER_DAY 86400
/* inet_current_timestamp - Return IP network timestamp
@@ -1763,6 +1789,7 @@ static int ipv4_proc_init(void);
static struct packet_offload ip_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IP),
+ .proto_flow_dissect = inet_proto_flow_dissect,
.callbacks = {
.gso_segment = inet_gso_segment,
.gro_receive = inet_gro_receive,
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index cdb3728faca7..a33a2b40b3d6 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -339,8 +339,35 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
return inet_gro_complete(skb, nhoff);
}
+static enum flow_dissect_ret inet6_proto_flow_dissect(struct sk_buff *skb,
+ u8 proto,
+ struct flow_dissector_key_control *key_control,
+ struct flow_dissector *flow_dissector,
+ void *target_container, void *data,
+ __be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+ int *p_hlen, unsigned int flags)
+{
+ enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+ const struct net_offload *ops;
+
+ rcu_read_lock();
+
+ ops = rcu_dereference(inet6_offloads[proto]);
+ if (ops && ops->callbacks.flow_dissect)
+ ret = ops->callbacks.flow_dissect(skb, key_control,
+ flow_dissector,
+ target_container, data,
+ p_proto, p_ip_proto, p_nhoff,
+ p_hlen, flags);
+
+ rcu_read_unlock();
+
+ return ret;
+}
+
static struct packet_offload ipv6_packet_offload __read_mostly = {
.type = cpu_to_be16(ETH_P_IPV6),
+ .proto_flow_dissect = inet6_proto_flow_dissect,
.callbacks = {
.gso_segment = ipv6_gso_segment,
.gro_receive = ipv6_gro_receive,
--
2.11.0
^ 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