* [PATCH v2 net-next] net: sk_buff rbnode reorg
From: Eric Dumazet @ 2017-09-19 12:14 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Soheil Hassas Yeganeh, Wei Wang, Willem de Bruijn
In-Reply-To: <1505797616.29839.40.camel@edumazet-glaptop3.roam.corp.google.com>
From: Eric Dumazet <edumazet@google.com>
skb->rbnode shares space with skb->next, skb->prev and skb->tstamp
Current uses (TCP receive ofo queue and netem) need to save/restore
tstamp, while skb->dev is either NULL (TCP) or a constant for a given
queue (netem).
Since we plan using an RB tree for TCP retransmit queue to speedup SACK
processing with large BDP, this patch exchanges skb->dev and
skb->tstamp.
This saves some overhead in both TCP and netem.
v2: removes the swtstamp field from struct tcp_skb_cb
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Willem de Bruijn <willemb@google.com>
---
include/linux/skbuff.h | 16 ++++++++--------
include/net/tcp.h | 6 ------
net/ipv4/tcp_input.c | 27 +++++----------------------
net/sched/sch_netem.c | 7 ++++---
4 files changed, 17 insertions(+), 39 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 72299ef00061db1ce70d34b96ae1639ecde08837..492828801acba42ac6bccb287d3cc5080039135c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -661,8 +661,12 @@ struct sk_buff {
struct sk_buff *prev;
union {
- ktime_t tstamp;
- u64 skb_mstamp;
+ struct net_device *dev;
+ /* Some protocols might use this space to store information,
+ * while device pointer would be NULL.
+ * UDP receive path is one user.
+ */
+ unsigned long dev_scratch;
};
};
struct rb_node rbnode; /* used in netem & tcp stack */
@@ -670,12 +674,8 @@ struct sk_buff {
struct sock *sk;
union {
- struct net_device *dev;
- /* Some protocols might use this space to store information,
- * while device pointer would be NULL.
- * UDP receive path is one user.
- */
- unsigned long dev_scratch;
+ ktime_t tstamp;
+ u64 skb_mstamp;
};
/*
* This is the control buffer. It is free to use for every
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b510f284427aabc1f508d24d29d0f812e5e0aa61..49a8a46466f32bd98b0c38a776fddc40bc621337 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -797,12 +797,6 @@ struct tcp_skb_cb {
u16 tcp_gso_segs;
u16 tcp_gso_size;
};
-
- /* Used to stash the receive timestamp while this skb is in the
- * out of order queue, as skb->tstamp is overwritten by the
- * rbnode.
- */
- ktime_t swtstamp;
};
__u8 tcp_flags; /* TCP header flags. (tcp[13]) */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bddf724f5c02abe1d11110cffe2517f6376e440d..db9bb46b5776f9ee332298c0e95afb0a5966b938 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4266,11 +4266,6 @@ static void tcp_sack_remove(struct tcp_sock *tp)
tp->rx_opt.num_sacks = num_sacks;
}
-enum tcp_queue {
- OOO_QUEUE,
- RCV_QUEUE,
-};
-
/**
* tcp_try_coalesce - try to merge skb to prior one
* @sk: socket
@@ -4286,7 +4281,6 @@ enum tcp_queue {
* Returns true if caller should free @from instead of queueing it
*/
static bool tcp_try_coalesce(struct sock *sk,
- enum tcp_queue dest,
struct sk_buff *to,
struct sk_buff *from,
bool *fragstolen)
@@ -4311,10 +4305,7 @@ static bool tcp_try_coalesce(struct sock *sk,
if (TCP_SKB_CB(from)->has_rxtstamp) {
TCP_SKB_CB(to)->has_rxtstamp = true;
- if (dest == OOO_QUEUE)
- TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp;
- else
- to->tstamp = from->tstamp;
+ to->tstamp = from->tstamp;
}
return true;
@@ -4351,9 +4342,6 @@ static void tcp_ofo_queue(struct sock *sk)
}
p = rb_next(p);
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
- /* Replace tstamp which was stomped by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- skb->tstamp = TCP_SKB_CB(skb)->swtstamp;
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
SOCK_DEBUG(sk, "ofo packet was already received\n");
@@ -4365,8 +4353,7 @@ static void tcp_ofo_queue(struct sock *sk)
TCP_SKB_CB(skb)->end_seq);
tail = skb_peek_tail(&sk->sk_receive_queue);
- eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE,
- tail, skb, &fragstolen);
+ eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen);
tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
if (!eaten)
@@ -4420,10 +4407,6 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
return;
}
- /* Stash tstamp to avoid being stomped on by rbnode */
- if (TCP_SKB_CB(skb)->has_rxtstamp)
- TCP_SKB_CB(skb)->swtstamp = skb->tstamp;
-
/* Disable header prediction. */
tp->pred_flags = 0;
inet_csk_schedule_ack(sk);
@@ -4451,7 +4434,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* In the typical case, we are adding an skb to the end of the list.
* Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
*/
- if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb,
+ if (tcp_try_coalesce(sk, tp->ooo_last_skb,
skb, &fragstolen)) {
coalesce_done:
tcp_grow_window(sk, skb);
@@ -4502,7 +4485,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
__kfree_skb(skb1);
goto merge_right;
}
- } else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1,
+ } else if (tcp_try_coalesce(sk, skb1,
skb, &fragstolen)) {
goto coalesce_done;
}
@@ -4554,7 +4537,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
__skb_pull(skb, hdrlen);
eaten = (tail &&
- tcp_try_coalesce(sk, RCV_QUEUE, tail,
+ tcp_try_coalesce(sk, tail,
skb, fragstolen)) ? 1 : 0;
tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
if (!eaten) {
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index b1266e75ca43cf5a66b951ecabccfc5b24069444..063a4bdb9ee6f26b01387959e8f6ccd15ec16191 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -146,7 +146,6 @@ struct netem_sched_data {
*/
struct netem_skb_cb {
psched_time_t time_to_send;
- ktime_t tstamp_save;
};
@@ -561,7 +560,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
}
cb->time_to_send = now + delay;
- cb->tstamp_save = skb->tstamp;
++q->counter;
tfifo_enqueue(skb, sch);
} else {
@@ -629,7 +627,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
qdisc_qstats_backlog_dec(sch, skb);
skb->next = NULL;
skb->prev = NULL;
- skb->tstamp = netem_skb_cb(skb)->tstamp_save;
+ /* skb->dev shares skb->rbnode area,
+ * we need to restore its value.
+ */
+ skb->dev = qdisc_dev(sch);
#ifdef CONFIG_NET_CLS_ACT
/*
^ permalink raw reply related
* Re: [PATCH 1/2] mac80211: Add rcu read side critical sections
From: Ville Syrjälä @ 2017-09-19 12:35 UTC (permalink / raw)
To: Johannes Berg; +Cc: linux-wireless, David S. Miller, netdev
In-Reply-To: <1505765477.13691.20.camel@sipsolutions.net>
On Mon, Sep 18, 2017 at 10:11:17PM +0200, Johannes Berg wrote:
> > I got the following lockdep warning about the rcu_dereference()s in
> > ieee80211_tx_h_select_key(). After tracing all callers of
> > ieee80211_tx_h_select_key() I discovered that
> > ieee80211_get_buffered_bc()
> > and ieee80211_build_data_template() had the rcu_read_lock/unlock()
> > but
> > three other places did not. So I just blindly added them and made the
> > read side critical section extend as far as the lifetime of 'tx'
> > which
> > is where we seem to be stuffing the rcu protected pointers. No real
> > clue whether this is correct or not.
>
> Heh.
>
> I think we should do it in ieee80211_tx_dequeue(),
Oh, I guess I didn't trace the call chains far enough. ieee80211_tx()
does indeed look OK. But unless I made another mistake in my analysis
ieee80211_tx_prepare_skb() is still busted.
> if not even in the
> driver (and document that it's required)
>
> johannes
>
> > @@ -3411,6 +3430,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct
> > ieee80211_hw *hw,
> > ieee80211_tx_result r;
> > struct ieee80211_vif *vif;
> >
> > + rcu_read_lock();
> > +
> > spin_lock_bh(&fq->lock);
> >
> > if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
> > @@ -3513,6 +3534,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct
> > ieee80211_hw *hw,
> > out:
> > spin_unlock_bh(&fq->lock);
> >
> > + rcu_read_unlock();
> >
>
> i.e. this in itself should be sufficient, though you should probably
> reorder and acquire the spinlock first since that might spin, and you
> want to keep the RCU section minimal (it's trivial here, after all)
Good point. I'll respin with that change.
--
Ville Syrjälä
Intel OTC
^ permalink raw reply
* [PATCH net-next] selftests: rtnetlink.sh: add test case for device ifalias
From: Florian Westphal @ 2017-09-19 12:42 UTC (permalink / raw)
To: netdev; +Cc: Florian Westphal
Signed-off-by: Florian Westphal <fw@strlen.de>
---
tools/testing/selftests/net/rtnetlink.sh | 57 ++++++++++++++++++++++++++++++++
1 file changed, 57 insertions(+)
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 57b5ff576240..4b48de565cae 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -15,6 +15,14 @@ check_err()
fi
}
+# same but inverted -- used when command must fail for test to pass
+check_fail()
+{
+ if [ $1 -eq 0 ]; then
+ ret=1
+ fi
+}
+
kci_add_dummy()
{
ip link add name "$devdummy" type dummy
@@ -235,6 +243,54 @@ kci_test_addrlabel()
echo "PASS: ipv6 addrlabel"
}
+kci_test_ifalias()
+{
+ ret=0
+ namewant=$(uuidgen)
+ syspathname="/sys/class/net/$devdummy/ifalias"
+
+ ip link set dev "$devdummy" alias "$namewant"
+ check_err $?
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: cannot set interface alias of $devdummy to $namewant"
+ return 1
+ fi
+
+ ip link show "$devdummy" | grep -q "alias $namewant"
+ check_err $?
+
+ if [ -r "$syspathname" ] ; then
+ read namehave < "$syspathname"
+ if [ "$namewant" != "$namehave" ]; then
+ echo "FAIL: did set ifalias $namewant but got $namehave"
+ return 1
+ fi
+
+ namewant=$(uuidgen)
+ echo "$namewant" > "$syspathname"
+ ip link show "$devdummy" | grep -q "alias $namewant"
+ check_err $?
+
+ # sysfs interface allows to delete alias again
+ echo "" > "$syspathname"
+
+ ip link show "$devdummy" | grep -q "alias $namewant"
+ check_fail $?
+
+ # re-add the alias -- kernel should free mem when dummy dev is removed
+ ip link set dev "$devdummy" alias "$namewant"
+ check_err $?
+ fi
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: set interface alias $devdummy to $namewant"
+ return 1
+ fi
+
+ echo "PASS: set ifalias $namewant for $devdummy"
+}
+
kci_test_rtnl()
{
kci_add_dummy
@@ -249,6 +305,7 @@ kci_test_rtnl()
kci_test_gre
kci_test_bridge
kci_test_addrlabel
+ kci_test_ifalias
kci_del_dummy
}
--
2.13.5
^ permalink raw reply related
* Re: [PATCH net-next 00/14] gtp: Additional feature support
From: Harald Welte @ 2017-09-19 12:43 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, pablo, rohit
In-Reply-To: <20170919003904.5124-1-tom@quantonium.net>
Hi Tom,
first of all, thanks a lot for your patch series. It makes me happy to
see contributions on the GTP code :)
On Mon, Sep 18, 2017 at 05:38:50PM -0700, Tom Herbert wrote:
> - IPv6 support
see my detailed comments in other mails. It's unfortunately only
support for the already "deprecated" IPv6-only PDP contexts, not the
more modern v4v6 type. In order to interoperate with old and new
approach, all three cases (v4, v6 and v4v6) should be supported from one
code base.
> - Configurable networking interfaces so that GTP kernel can be used
> and tested without needing GSN network emulation (i.e. no user space
> daemon needed).
We have some pretty decent userspace utilities for configuring the GTP
interfaces and tunnels in the libgtpnl repository, but if it helps
people to have another way of configuration, I won't be against it.
What we have to keep in mind is that the current model of 1:1 mapping of
a "UDP socket' to a GTP netdevice is conceptually broken and needs to be
refactored soon (without breaking backwards compatibility). See related
earlier discussions with patches submitted by Andreas Schultz.
Summary:
In real-world GGSNs you often want to host multiple virtual GGSNs on a
single GGSN (= UDP socket). Each virtual GGSN terminates into one
external PDN (packet data network), which can be a private corporate vpn
or any other IP network, with no routing between those networks.
Naively one would assume you "simply" run another virtual GGSN
instance on another IP address, and then differentiate like that.
However, the problem is that adding a new GGSN IP address will require
manual configuration changes at each of your roaming partners (easily
hundreds of operators!) and hence it is avoided at all cost due to the
related long schedule, requirement for interop testing with each of them,
etc.
So what you do in reality at operators is that you operate many of those
virtual GGSNs on the same IP:Port combination (and hence UDP socket),
which means you have PDP contexts for vGGSN A which terminate on e.g.
gtp0 and PDP contexts for vGGSN B on gtp1, and so on. The decision
which gtp-device a given PDP context is a member is made by the GTP-C
instance. In the kenel we'll have to decouple net-devices from sockets.
So whatever new configuration mechanism or architectural changes we
introduce, we need to make sure that those will accomodate the "new
model" rather than introducing further dependencies for which we will
have to maintain backwards compatibility workaronds later on.
> - Port numbers are configurable
I'm not sure if this is a useful feature. GTP is used only in
operator-controlled networks and only on standard ports. It's not
possible to negotiate any non-standard ports on the signaling plane
either.
> - Addition of a dst_cache in the GTP structure and other cleanup
looks fine to me.
> - GSO,GRO
> - Control of zero UDP checksums
[...]
> Additionally, this patch set also includes a couple of general support
> capabilities:
>
> - A facility that allows application specific GSO callbacks
> - Common functions to get a route fo for an IP tunnel
This is where the "core netdev" folks will have to comment. I'm too
remote from mainline kernel development these days and will focus on
reviewing the GTP specific bits of your patch series.
> For IPv6 support, the mobile subscriber needs to allow IPv6 addresses,
> and the remote enpoint can be IPv6.
Minor correction: The mobile subscriber specifically requests a PDP Type
when establishing the PDP context via Session Management related
signaling from MS/UE to SGSN. The SGSN simply translates this to GTP
and then forwards it to the GGSN. So it's acutally not "allow" but
"specifically request".
> Configured the matrix of IPv4/IPv6 mobile subscriber, IPv4/IPv6 remote
> peer, and GTP version 0 and 1 (eight combinations). Observed
> connectivity and proper GSO/GRO. Also, tested VXLAN for
> regression.
I presume those tests were done with manually configured GTP-devices and
PDP contexts to the (patched) kernel GTP module? If so, I would like to
strongly suggest interop testing with a different implementation, such
as real phones on the MS/UE side and e.g. OsmoSGSN. That would,
however, of course mean that the netlink related bits would have to be
added to libgtpnl and OsmoGGSN (or ergw) so that you have a daemon for
the control plane.
For IPv6 (and v4v6) PDP contexts there is quite a bit of extra headache
related to the way how router solicitation/advertisements are modified
in the 3GPP world.
The address allocation in v4 is simple:
* MS/UE requests dynamic or fixed IPv4 address via EUA IE of PDP context
activation
* GGSN responds with IPv4 address in EUA of Activate PDP context
response (and then uses netlink to tell the kernel about that
IPv4 address)
In v6 or the v6 portion of v4v6 it works differently:
* MS/UE requests dynamic or fixed IPv4 address in EUA IE of PDP context
activation
* GGSN responds with an IPv6 address, but that address is *not* used
for communication, but simply used as an "interface identifier" to
build a link-local address.
* MS then uses router solicitation using that link-local address
* GGSN responds with router advertisement, allocating a single /64
prefix, from which the MS then generates a fully-qualified IPv6
source address for communication.
How did you envision this to be done with the v6 support you just added?
At the very least, the /64 prefix matching would have to be implemented
so that in fact all addresses within that /64 prefix are matched +
encapsulated for a given PDP context in the downlink (to phone)
direction.
Also, I think the responsibility for the router advertisements would be
in the kernel, too. Otherwise, a GTP-C userspace implementation would
have to inject packets into the user plane (which is otherwise handled
completely inside the kernel). Injecting packets would mean that in caes
GTP sequence numbers are used, that userspace implementation would have
to alter the sequence numbers of the kernel gtp.ko code using netlink,
but therre would be race conditions, ...
The router advertisements and neighbor advertisements basically have the
semantics of one link per PDP context. Each of them is a point-to-point
link, and it's not one router advertisement that's sent to all of the
PDP contexts on that gtp-device.
I know it all sucks. I'm still happy to see somebody tackling v6
support in gtp.c :)
Regards,
Harald
--
- Harald Welte <laforge@gnumonks.org> http://laforge.gnumonks.org/
============================================================================
"Privacy in residential applications is a desirable marketing option."
(ETSI EN 300 175-7 Ch. A6)
^ permalink raw reply
* Re: [regression v4.11] 617f01211baf ("8139too: use napi_complete_done()")
From: Ville Syrjälä @ 2017-09-19 12:45 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Eric Dumazet, David S. Miller, netdev, LKML
In-Reply-To: <CANn89iJu82AcbsavkAfAJ3xT5wRp=ZVz==WEREktwxXPEdqBdw@mail.gmail.com>
On Mon, Sep 18, 2017 at 12:52:15PM -0700, Eric Dumazet wrote:
> On Mon, Sep 18, 2017 at 12:46 PM, Ville Syrjälä
> <ville.syrjala@linux.intel.com> wrote:
>
> > And five months later I'm still waiting for this patch to land...
>
> Sure, while I was on vacation, I received thousands of emails that I
> simply have not read.
Ah that explains where my previous ping went. Pardon the snarky comment,
and thanks for taking care of this.
--
Ville Syrjälä
Intel OTC
^ permalink raw reply
* [RESEND PATCH 0/6] staging: Introduce DPAA2 Ethernet Switch driver
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, linux-kernel, netdev, agraf, arnd, alexandru.marginean,
bogdan.purcareata, ruxandra.radulescu, laurentiu.tudor, stuyoder
This patchset introduces the Ethernet Switch Driver for Freescale/NXP SoCs
with DPAA2 (DataPath Acceleration Architecture v2). The driver manages
switch objects discovered on the fsl-mc bus. A description of the driver
can be found in the associated README file.
The patchset consists of:
* A set of libraries containing APIs for configuring and controlling
Management Complex (MC) switch objects
* The DPAA2 Ethernet Switch driver
* Patch adding ethtool support
Limitations:
* no support for control traffic to/from CPU
* only DPSW ports can be added to a bridge
Resending in order to add the netdev list (and remove the arm one), based
on Andrew Lunn's suggestion.
Razvan Stefanescu (6):
staging: fsl-dpaa2/ethsw: Add APIs for DPSW object
staging: fsl-dpaa2/ethsw: Add Freescale DPAA2 Ethernet Switch driver
staging: fsl-dpaa2/ethsw: Add ethtool support
staging: fsl-dpaa2/ethsw: Add maintainer for Ethernet Switch driver
staging: fsl-dpaa2/ethsw: Add README
staging: fsl-dpaa2/ethsw: Add TODO
MAINTAINERS | 6 +
drivers/staging/fsl-dpaa2/Kconfig | 8 +
drivers/staging/fsl-dpaa2/Makefile | 1 +
drivers/staging/fsl-dpaa2/ethsw/Makefile | 7 +
drivers/staging/fsl-dpaa2/ethsw/README | 106 ++
drivers/staging/fsl-dpaa2/ethsw/TODO | 14 +
drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h | 371 ++++++
drivers/staging/fsl-dpaa2/ethsw/dpsw.c | 1147 +++++++++++++++++
drivers/staging/fsl-dpaa2/ethsw/dpsw.h | 611 +++++++++
drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c | 207 +++
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 1526 +++++++++++++++++++++++
drivers/staging/fsl-dpaa2/ethsw/ethsw.h | 91 ++
12 files changed, 4095 insertions(+)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/Makefile
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/README
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/TODO
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw.c
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw.h
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw.c
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw.h
--
1.9.1
^ permalink raw reply
* [RESEND PATCH 1/6] staging: fsl-dpaa2/ethsw: Add APIs for DPSW object
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, linux-kernel, netdev, agraf, arnd, alexandru.marginean,
bogdan.purcareata, ruxandra.radulescu, laurentiu.tudor, stuyoder
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Add the command build/parse APIs for operating on DPSW objects through
the DPAA2 Management Complex.
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
drivers/staging/fsl-dpaa2/Kconfig | 8 +
drivers/staging/fsl-dpaa2/Makefile | 1 +
drivers/staging/fsl-dpaa2/ethsw/Makefile | 7 +
drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h | 358 +++++++++
drivers/staging/fsl-dpaa2/ethsw/dpsw.c | 1115 ++++++++++++++++++++++++++++
drivers/staging/fsl-dpaa2/ethsw/dpsw.h | 579 +++++++++++++++
6 files changed, 2068 insertions(+)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/Makefile
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw.c
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/dpsw.h
diff --git a/drivers/staging/fsl-dpaa2/Kconfig b/drivers/staging/fsl-dpaa2/Kconfig
index dfff675..8a508ef 100644
--- a/drivers/staging/fsl-dpaa2/Kconfig
+++ b/drivers/staging/fsl-dpaa2/Kconfig
@@ -16,3 +16,11 @@ config FSL_DPAA2_ETH
---help---
Ethernet driver for Freescale DPAA2 SoCs, using the
Freescale MC bus driver
+
+config FSL_DPAA2_ETHSW
+ tristate "Freescale DPAA2 Ethernet Switch"
+ depends on FSL_DPAA2
+ depends on NET_SWITCHDEV
+ ---help---
+ Driver for Freescale DPAA2 Ethernet Switch. Select
+ BRIDGE to have support for bridge tools.
diff --git a/drivers/staging/fsl-dpaa2/Makefile b/drivers/staging/fsl-dpaa2/Makefile
index 0836ba8..6cfd76b 100644
--- a/drivers/staging/fsl-dpaa2/Makefile
+++ b/drivers/staging/fsl-dpaa2/Makefile
@@ -3,3 +3,4 @@
#
obj-$(CONFIG_FSL_DPAA2_ETH) += ethernet/
+obj-$(CONFIG_FSL_DPAA2_ETHSW) += ethsw/
diff --git a/drivers/staging/fsl-dpaa2/ethsw/Makefile b/drivers/staging/fsl-dpaa2/ethsw/Makefile
new file mode 100644
index 0000000..db137f7
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the Freescale DPAA2 Ethernet Switch
+#
+
+obj-$(CONFIG_FSL_DPAA2_ETHSW) += dpaa2-ethsw.o
+
+dpaa2-ethsw-objs := dpsw.o
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h b/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
new file mode 100644
index 0000000..ddfd820
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
@@ -0,0 +1,358 @@
+/* Copyright 2013-2016 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __FSL_DPSW_CMD_H
+#define __FSL_DPSW_CMD_H
+
+/* DPSW Version */
+#define DPSW_VER_MAJOR 8
+#define DPSW_VER_MINOR 0
+
+#define DPSW_CMD_BASE_VERSION 1
+#define DPSW_CMD_ID_OFFSET 4
+
+#define DPSW_CMD_ID(id) (((id) << DPSW_CMD_ID_OFFSET) | DPSW_CMD_BASE_VERSION)
+
+/* Command IDs */
+#define DPSW_CMDID_CLOSE DPSW_CMD_ID(0x800)
+#define DPSW_CMDID_OPEN DPSW_CMD_ID(0x802)
+
+#define DPSW_CMDID_GET_API_VERSION DPSW_CMD_ID(0xa02)
+
+#define DPSW_CMDID_ENABLE DPSW_CMD_ID(0x002)
+#define DPSW_CMDID_DISABLE DPSW_CMD_ID(0x003)
+#define DPSW_CMDID_GET_ATTR DPSW_CMD_ID(0x004)
+#define DPSW_CMDID_RESET DPSW_CMD_ID(0x005)
+
+#define DPSW_CMDID_SET_IRQ_ENABLE DPSW_CMD_ID(0x012)
+
+#define DPSW_CMDID_SET_IRQ_MASK DPSW_CMD_ID(0x014)
+
+#define DPSW_CMDID_GET_IRQ_STATUS DPSW_CMD_ID(0x016)
+#define DPSW_CMDID_CLEAR_IRQ_STATUS DPSW_CMD_ID(0x017)
+
+#define DPSW_CMDID_IF_SET_TCI DPSW_CMD_ID(0x030)
+#define DPSW_CMDID_IF_SET_STP DPSW_CMD_ID(0x031)
+
+#define DPSW_CMDID_IF_GET_COUNTER DPSW_CMD_ID(0x034)
+
+#define DPSW_CMDID_IF_ENABLE DPSW_CMD_ID(0x03D)
+#define DPSW_CMDID_IF_DISABLE DPSW_CMD_ID(0x03E)
+
+#define DPSW_CMDID_IF_SET_MAX_FRAME_LENGTH DPSW_CMD_ID(0x044)
+
+#define DPSW_CMDID_IF_GET_LINK_STATE DPSW_CMD_ID(0x046)
+#define DPSW_CMDID_IF_SET_FLOODING DPSW_CMD_ID(0x047)
+#define DPSW_CMDID_IF_SET_BROADCAST DPSW_CMD_ID(0x048)
+
+#define DPSW_CMDID_VLAN_ADD DPSW_CMD_ID(0x060)
+#define DPSW_CMDID_VLAN_ADD_IF DPSW_CMD_ID(0x061)
+#define DPSW_CMDID_VLAN_ADD_IF_UNTAGGED DPSW_CMD_ID(0x062)
+
+#define DPSW_CMDID_VLAN_REMOVE_IF DPSW_CMD_ID(0x064)
+#define DPSW_CMDID_VLAN_REMOVE_IF_UNTAGGED DPSW_CMD_ID(0x065)
+#define DPSW_CMDID_VLAN_REMOVE_IF_FLOODING DPSW_CMD_ID(0x066)
+#define DPSW_CMDID_VLAN_REMOVE DPSW_CMD_ID(0x067)
+
+#define DPSW_CMDID_FDB_ADD_UNICAST DPSW_CMD_ID(0x084)
+#define DPSW_CMDID_FDB_REMOVE_UNICAST DPSW_CMD_ID(0x085)
+#define DPSW_CMDID_FDB_ADD_MULTICAST DPSW_CMD_ID(0x086)
+#define DPSW_CMDID_FDB_REMOVE_MULTICAST DPSW_CMD_ID(0x087)
+#define DPSW_CMDID_FDB_SET_LEARNING_MODE DPSW_CMD_ID(0x088)
+
+/* Macros for accessing command fields smaller than 1byte */
+#define DPSW_MASK(field) \
+ GENMASK(DPSW_##field##_SHIFT + DPSW_##field##_SIZE - 1, \
+ DPSW_##field##_SHIFT)
+#define dpsw_set_field(var, field, val) \
+ ((var) |= (((val) << DPSW_##field##_SHIFT) & DPSW_MASK(field)))
+#define dpsw_get_field(var, field) \
+ (((var) & DPSW_MASK(field)) >> DPSW_##field##_SHIFT)
+#define dpsw_get_bit(var, bit) \
+ (((var) >> (bit)) & GENMASK(0, 0))
+
+struct dpsw_cmd_open {
+ __le32 dpsw_id;
+};
+
+#define DPSW_COMPONENT_TYPE_SHIFT 0
+#define DPSW_COMPONENT_TYPE_SIZE 4
+
+struct dpsw_cmd_create {
+ /* cmd word 0 */
+ __le16 num_ifs;
+ u8 max_fdbs;
+ u8 max_meters_per_if;
+ /* from LSB: only the first 4 bits */
+ u8 component_type;
+ u8 pad[3];
+ /* cmd word 1 */
+ __le16 max_vlans;
+ __le16 max_fdb_entries;
+ __le16 fdb_aging_time;
+ __le16 max_fdb_mc_groups;
+ /* cmd word 2 */
+ __le64 options;
+};
+
+struct dpsw_cmd_destroy {
+ __le32 dpsw_id;
+};
+
+#define DPSW_ENABLE_SHIFT 0
+#define DPSW_ENABLE_SIZE 1
+
+struct dpsw_rsp_is_enabled {
+ /* from LSB: enable:1 */
+ u8 enabled;
+};
+
+struct dpsw_cmd_set_irq_enable {
+ u8 enable_state;
+ u8 pad[3];
+ u8 irq_index;
+};
+
+struct dpsw_cmd_get_irq_enable {
+ __le32 pad;
+ u8 irq_index;
+};
+
+struct dpsw_rsp_get_irq_enable {
+ u8 enable_state;
+};
+
+struct dpsw_cmd_set_irq_mask {
+ __le32 mask;
+ u8 irq_index;
+};
+
+struct dpsw_cmd_get_irq_mask {
+ __le32 pad;
+ u8 irq_index;
+};
+
+struct dpsw_rsp_get_irq_mask {
+ __le32 mask;
+};
+
+struct dpsw_cmd_get_irq_status {
+ __le32 status;
+ u8 irq_index;
+};
+
+struct dpsw_rsp_get_irq_status {
+ __le32 status;
+};
+
+struct dpsw_cmd_clear_irq_status {
+ __le32 status;
+ u8 irq_index;
+};
+
+#define DPSW_COMPONENT_TYPE_SHIFT 0
+#define DPSW_COMPONENT_TYPE_SIZE 4
+
+struct dpsw_rsp_get_attr {
+ /* cmd word 0 */
+ __le16 num_ifs;
+ u8 max_fdbs;
+ u8 num_fdbs;
+ __le16 max_vlans;
+ __le16 num_vlans;
+ /* cmd word 1 */
+ __le16 max_fdb_entries;
+ __le16 fdb_aging_time;
+ __le32 dpsw_id;
+ /* cmd word 2 */
+ __le16 mem_size;
+ __le16 max_fdb_mc_groups;
+ u8 max_meters_per_if;
+ /* from LSB only the first 4 bits */
+ u8 component_type;
+ __le16 pad;
+ /* cmd word 3 */
+ __le64 options;
+};
+
+struct dpsw_cmd_if_set_flooding {
+ __le16 if_id;
+ /* from LSB: enable:1 */
+ u8 enable;
+};
+
+struct dpsw_cmd_if_set_broadcast {
+ __le16 if_id;
+ /* from LSB: enable:1 */
+ u8 enable;
+};
+
+#define DPSW_VLAN_ID_SHIFT 0
+#define DPSW_VLAN_ID_SIZE 12
+#define DPSW_DEI_SHIFT 12
+#define DPSW_DEI_SIZE 1
+#define DPSW_PCP_SHIFT 13
+#define DPSW_PCP_SIZE 3
+
+struct dpsw_cmd_if_set_tci {
+ __le16 if_id;
+ /* from LSB: VLAN_ID:12 DEI:1 PCP:3 */
+ __le16 conf;
+};
+
+#define DPSW_STATE_SHIFT 0
+#define DPSW_STATE_SIZE 4
+
+struct dpsw_cmd_if_set_stp {
+ __le16 if_id;
+ __le16 vlan_id;
+ /* only the first LSB 4 bits */
+ u8 state;
+};
+
+#define DPSW_COUNTER_TYPE_SHIFT 0
+#define DPSW_COUNTER_TYPE_SIZE 5
+
+struct dpsw_cmd_if_get_counter {
+ __le16 if_id;
+ /* from LSB: type:5 */
+ u8 type;
+};
+
+struct dpsw_rsp_if_get_counter {
+ __le64 pad;
+ __le64 counter;
+};
+
+struct dpsw_cmd_if {
+ __le16 if_id;
+};
+
+struct dpsw_cmd_if_set_max_frame_length {
+ __le16 if_id;
+ __le16 frame_length;
+};
+
+struct dpsw_cmd_if_get_link_state {
+ __le16 if_id;
+};
+
+#define DPSW_UP_SHIFT 0
+#define DPSW_UP_SIZE 1
+
+struct dpsw_rsp_if_get_link_state {
+ /* cmd word 0 */
+ __le32 pad0;
+ u8 up;
+ u8 pad1[3];
+ /* cmd word 1 */
+ __le32 rate;
+ __le32 pad2;
+ /* cmd word 2 */
+ __le64 options;
+};
+
+struct dpsw_vlan_add {
+ __le16 fdb_id;
+ __le16 vlan_id;
+};
+
+struct dpsw_cmd_vlan_manage_if {
+ /* cmd word 0 */
+ __le16 pad0;
+ __le16 vlan_id;
+ __le32 pad1;
+ /* cmd word 1-4 */
+ __le64 if_id[4];
+};
+
+struct dpsw_cmd_vlan_remove {
+ __le16 pad;
+ __le16 vlan_id;
+};
+
+struct dpsw_cmd_fdb_add {
+ __le32 pad;
+ __le16 fdb_aging_time;
+ __le16 num_fdb_entries;
+};
+
+struct dpsw_rsp_fdb_add {
+ __le16 fdb_id;
+};
+
+struct dpsw_cmd_fdb_remove {
+ __le16 fdb_id;
+};
+
+#define DPSW_ENTRY_TYPE_SHIFT 0
+#define DPSW_ENTRY_TYPE_SIZE 4
+
+struct dpsw_cmd_fdb_unicast_op {
+ /* cmd word 0 */
+ __le16 fdb_id;
+ u8 mac_addr[6];
+ /* cmd word 1 */
+ __le16 if_egress;
+ /* only the first 4 bits from LSB */
+ u8 type;
+};
+
+struct dpsw_cmd_fdb_multicast_op {
+ /* cmd word 0 */
+ __le16 fdb_id;
+ __le16 num_ifs;
+ /* only the first 4 bits from LSB */
+ u8 type;
+ u8 pad[3];
+ /* cmd word 1 */
+ u8 mac_addr[6];
+ __le16 pad2;
+ /* cmd word 2-5 */
+ __le64 if_id[4];
+};
+
+#define DPSW_LEARNING_MODE_SHIFT 0
+#define DPSW_LEARNING_MODE_SIZE 4
+
+struct dpsw_cmd_fdb_set_learning_mode {
+ __le16 fdb_id;
+ /* only the first 4 bits from LSB */
+ u8 mode;
+};
+
+struct dpsw_rsp_get_api_version {
+ __le16 version_major;
+ __le16 version_minor;
+};
+
+#endif /* __FSL_DPSW_CMD_H */
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw.c b/drivers/staging/fsl-dpaa2/ethsw/dpsw.c
new file mode 100644
index 0000000..f36b92b
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw.c
@@ -0,0 +1,1115 @@
+/* Copyright 2013-2016 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#include "../../fsl-mc/include/mc.h"
+#include "dpsw.h"
+#include "dpsw-cmd.h"
+
+static void build_if_id_bitmap(__le64 *bmap,
+ const u16 *id,
+ const u16 num_ifs)
+{
+ int i;
+
+ for (i = 0; (i < num_ifs) && (i < DPSW_MAX_IF); i++) {
+ if (id[i] < DPSW_MAX_IF)
+ bmap[id[i] / 64] |= BIT_MASK(id[i] % 64);
+ }
+}
+
+/**
+ * dpsw_open() - Open a control session for the specified object
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @dpsw_id: DPSW unique ID
+ * @token: Returned token; use in subsequent API calls
+ *
+ * This function can be used to open a control session for an
+ * already created object; an object may have been declared in
+ * the DPL or by calling the dpsw_create() function.
+ * This function returns a unique authentication token,
+ * associated with the specific object ID and the specific MC
+ * portal; this token must be used in all subsequent commands for
+ * this specific object
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_open(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ int dpsw_id,
+ u16 *token)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_open *cmd_params;
+ int err;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_OPEN,
+ cmd_flags,
+ 0);
+ cmd_params = (struct dpsw_cmd_open *)cmd.params;
+ cmd_params->dpsw_id = cpu_to_le32(dpsw_id);
+
+ /* send command to mc*/
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ /* retrieve response parameters */
+ *token = mc_cmd_hdr_read_token(&cmd);
+
+ return 0;
+}
+
+/**
+ * dpsw_close() - Close the control session of the object
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ *
+ * After this function is called, no further operations are
+ * allowed on the object without opening a new control session.
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_close(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token)
+{
+ struct mc_command cmd = { 0 };
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_CLOSE,
+ cmd_flags,
+ token);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_enable() - Enable DPSW functionality
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token)
+{
+ struct mc_command cmd = { 0 };
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_ENABLE,
+ cmd_flags,
+ token);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_disable() - Disable DPSW functionality
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_disable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token)
+{
+ struct mc_command cmd = { 0 };
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_DISABLE,
+ cmd_flags,
+ token);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_reset() - Reset the DPSW, returns the object to initial state.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_reset(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token)
+{
+ struct mc_command cmd = { 0 };
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_RESET,
+ cmd_flags,
+ token);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_set_irq_enable() - Set overall interrupt state.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPCI object
+ * @irq_index: The interrupt index to configure
+ * @en: Interrupt state - enable = 1, disable = 0
+ *
+ * Allows GPP software to control when interrupts are generated.
+ * Each interrupt can have up to 32 causes. The enable/disable control's the
+ * overall interrupt state. if the interrupt is disabled no causes will cause
+ * an interrupt
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_set_irq_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u8 en)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_set_irq_enable *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_IRQ_ENABLE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_set_irq_enable *)cmd.params;
+ dpsw_set_field(cmd_params->enable_state, ENABLE, en);
+ cmd_params->irq_index = irq_index;
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_set_irq_mask() - Set interrupt mask.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPCI object
+ * @irq_index: The interrupt index to configure
+ * @mask: Event mask to trigger interrupt;
+ * each bit:
+ * 0 = ignore event
+ * 1 = consider event for asserting IRQ
+ *
+ * Every interrupt can have up to 32 causes and the interrupt model supports
+ * masking/unmasking each cause independently
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_set_irq_mask(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 mask)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_set_irq_mask *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_IRQ_MASK,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_set_irq_mask *)cmd.params;
+ cmd_params->mask = cpu_to_le32(mask);
+ cmd_params->irq_index = irq_index;
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_get_irq_status() - Get the current status of any pending interrupts
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @irq_index: The interrupt index to configure
+ * @status: Returned interrupts status - one bit per cause:
+ * 0 = no interrupt pending
+ * 1 = interrupt pending
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_get_irq_status(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 *status)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_get_irq_status *cmd_params;
+ struct dpsw_rsp_get_irq_status *rsp_params;
+ int err;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_GET_IRQ_STATUS,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_get_irq_status *)cmd.params;
+ cmd_params->status = cpu_to_le32(*status);
+ cmd_params->irq_index = irq_index;
+
+ /* send command to mc*/
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ /* retrieve response parameters */
+ rsp_params = (struct dpsw_rsp_get_irq_status *)cmd.params;
+ *status = le32_to_cpu(rsp_params->status);
+
+ return 0;
+}
+
+/**
+ * dpsw_clear_irq_status() - Clear a pending interrupt's status
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPCI object
+ * @irq_index: The interrupt index to configure
+ * @status: bits to clear (W1C) - one bit per cause:
+ * 0 = don't change
+ * 1 = clear status bit
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_clear_irq_status(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 status)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_clear_irq_status *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_CLEAR_IRQ_STATUS,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_clear_irq_status *)cmd.params;
+ cmd_params->status = cpu_to_le32(status);
+ cmd_params->irq_index = irq_index;
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_get_attributes() - Retrieve DPSW attributes
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @attr: Returned DPSW attributes
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_get_attributes(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ struct dpsw_attr *attr)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_rsp_get_attr *rsp_params;
+ int err;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_GET_ATTR,
+ cmd_flags,
+ token);
+
+ /* send command to mc*/
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ /* retrieve response parameters */
+ rsp_params = (struct dpsw_rsp_get_attr *)cmd.params;
+ attr->num_ifs = le16_to_cpu(rsp_params->num_ifs);
+ attr->max_fdbs = rsp_params->max_fdbs;
+ attr->num_fdbs = rsp_params->num_fdbs;
+ attr->max_vlans = le16_to_cpu(rsp_params->max_vlans);
+ attr->num_vlans = le16_to_cpu(rsp_params->num_vlans);
+ attr->max_fdb_entries = le16_to_cpu(rsp_params->max_fdb_entries);
+ attr->fdb_aging_time = le16_to_cpu(rsp_params->fdb_aging_time);
+ attr->id = le32_to_cpu(rsp_params->dpsw_id);
+ attr->mem_size = le16_to_cpu(rsp_params->mem_size);
+ attr->max_fdb_mc_groups = le16_to_cpu(rsp_params->max_fdb_mc_groups);
+ attr->max_meters_per_if = rsp_params->max_meters_per_if;
+ attr->options = le64_to_cpu(rsp_params->options);
+ attr->component_type = dpsw_get_field(rsp_params->component_type,
+ COMPONENT_TYPE);
+
+ return 0;
+}
+
+/**
+ * dpsw_if_get_link_state - Return the link state
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface id
+ * @state: Link state 1 - linkup, 0 - link down or disconnected
+ *
+ * @Return '0' on Success; Error code otherwise.
+ */
+int dpsw_if_get_link_state(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ struct dpsw_link_state *state)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_get_link_state *cmd_params;
+ struct dpsw_rsp_if_get_link_state *rsp_params;
+ int err;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_GET_LINK_STATE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_get_link_state *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+
+ /* send command to mc*/
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ /* retrieve response parameters */
+ rsp_params = (struct dpsw_rsp_if_get_link_state *)cmd.params;
+ state->rate = le32_to_cpu(rsp_params->rate);
+ state->options = le64_to_cpu(rsp_params->options);
+ state->up = dpsw_get_field(rsp_params->up, UP);
+
+ return 0;
+}
+
+/**
+ * dpsw_if_set_flooding() - Enable Disable flooding for particular interface
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @en: 1 - enable, 0 - disable
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_flooding(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ int en)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_flooding *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_FLOODING,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_flooding *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ dpsw_set_field(cmd_params->enable, ENABLE, en);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_broadcast() - Enable/disable broadcast for particular interface
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @en: 1 - enable, 0 - disable
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_broadcast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ int en)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_broadcast *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_BROADCAST,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_broadcast *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ dpsw_set_field(cmd_params->enable, ENABLE, en);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_tci() - Set default VLAN Tag Control Information (TCI)
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @cfg: Tag Control Information Configuration
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_tci(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ const struct dpsw_tci_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_tci *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_TCI,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_tci *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ dpsw_set_field(cmd_params->conf, VLAN_ID, cfg->vlan_id);
+ dpsw_set_field(cmd_params->conf, DEI, cfg->dei);
+ dpsw_set_field(cmd_params->conf, PCP, cfg->pcp);
+ cmd_params->conf = cpu_to_le16(cmd_params->conf);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_stp() - Function sets Spanning Tree Protocol (STP) state.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @cfg: STP State configuration parameters
+ *
+ * The following STP states are supported -
+ * blocking, listening, learning, forwarding and disabled.
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_stp(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ const struct dpsw_stp_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_stp *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_STP,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_stp *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ cmd_params->vlan_id = cpu_to_le16(cfg->vlan_id);
+ dpsw_set_field(cmd_params->state, STATE, cfg->state);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_get_counter() - Get specific counter of particular interface
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @type: Counter type
+ * @counter: return value
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_get_counter(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ enum dpsw_counter type,
+ u64 *counter)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_get_counter *cmd_params;
+ struct dpsw_rsp_if_get_counter *rsp_params;
+ int err;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_GET_COUNTER,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_get_counter *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ dpsw_set_field(cmd_params->type, COUNTER_TYPE, type);
+
+ /* send command to mc*/
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ /* retrieve response parameters */
+ rsp_params = (struct dpsw_rsp_if_get_counter *)cmd.params;
+ *counter = le64_to_cpu(rsp_params->counter);
+
+ return 0;
+}
+
+/**
+ * dpsw_if_enable() - Enable Interface
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_ENABLE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_disable() - Disable Interface
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_disable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_DISABLE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_max_frame_length() - Set Maximum Receive frame length.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface Identifier
+ * @frame_length: Maximum Frame Length
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_max_frame_length(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ u16 frame_length)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_max_frame_length *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_MAX_FRAME_LENGTH,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_max_frame_length *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ cmd_params->frame_length = cpu_to_le16(frame_length);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_add() - Adding new VLAN to DPSW.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ * @cfg: VLAN configuration
+ *
+ * Only VLAN ID and FDB ID are required parameters here.
+ * 12 bit VLAN ID is defined in IEEE802.1Q.
+ * Adding a duplicate VLAN ID is not allowed.
+ * FDB ID can be shared across multiple VLANs. Shared learning
+ * is obtained by calling dpsw_vlan_add for multiple VLAN IDs
+ * with same fdb_id
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_add(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_vlan_add *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_ADD,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_vlan_add *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(cfg->fdb_id);
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_add_if() - Adding a set of interfaces to an existing VLAN.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ * @cfg: Set of interfaces to add
+ *
+ * It adds only interfaces not belonging to this VLAN yet,
+ * otherwise an error is generated and an entire command is
+ * ignored. This function can be called numerous times always
+ * providing required interfaces delta.
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_add_if(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_vlan_manage_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_ADD_IF,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_vlan_manage_if *)cmd.params;
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_add_if_untagged() - Defining a set of interfaces that should be
+ * transmitted as untagged.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ * @cfg: Set of interfaces that should be transmitted as untagged
+ *
+ * These interfaces should already belong to this VLAN.
+ * By default all interfaces are transmitted as tagged.
+ * Providing un-existing interface or untagged interface that is
+ * configured untagged already generates an error and the entire
+ * command is ignored.
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_add_if_untagged(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_vlan_manage_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_ADD_IF_UNTAGGED,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_vlan_manage_if *)cmd.params;
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_remove_if() - Remove interfaces from an existing VLAN.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ * @cfg: Set of interfaces that should be removed
+ *
+ * Interfaces must belong to this VLAN, otherwise an error
+ * is returned and an the command is ignored
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_remove_if(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_vlan_manage_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_REMOVE_IF,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_vlan_manage_if *)cmd.params;
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_remove_if_untagged() - Define a set of interfaces that should be
+ * converted from transmitted as untagged to transmit as tagged.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ * @cfg: Set of interfaces that should be removed
+ *
+ * Interfaces provided by API have to belong to this VLAN and
+ * configured untagged, otherwise an error is returned and the
+ * command is ignored
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_remove_if_untagged(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_vlan_manage_if *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_REMOVE_IF_UNTAGGED,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_vlan_manage_if *)cmd.params;
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_vlan_remove() - Remove an entire VLAN
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @vlan_id: VLAN Identifier
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_vlan_remove(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_vlan_remove *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_VLAN_REMOVE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_vlan_remove *)cmd.params;
+ cmd_params->vlan_id = cpu_to_le16(vlan_id);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_fdb_add_unicast() - Function adds an unicast entry into MAC lookup table
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @fdb_id: Forwarding Database Identifier
+ * @cfg: Unicast entry configuration
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_fdb_add_unicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_unicast_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_fdb_unicast_op *cmd_params;
+ int i;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_FDB_ADD_UNICAST,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_fdb_unicast_op *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(fdb_id);
+ cmd_params->if_egress = cpu_to_le16(cfg->if_egress);
+ for (i = 0; i < 6; i++)
+ cmd_params->mac_addr[i] = cfg->mac_addr[5 - i];
+ dpsw_set_field(cmd_params->type, ENTRY_TYPE, cfg->type);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_fdb_remove_unicast() - removes an entry from MAC lookup table
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @fdb_id: Forwarding Database Identifier
+ * @cfg: Unicast entry configuration
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_fdb_remove_unicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_unicast_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_fdb_unicast_op *cmd_params;
+ int i;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_FDB_REMOVE_UNICAST,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_fdb_unicast_op *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(fdb_id);
+ for (i = 0; i < 6; i++)
+ cmd_params->mac_addr[i] = cfg->mac_addr[5 - i];
+ cmd_params->if_egress = cpu_to_le16(cfg->if_egress);
+ dpsw_set_field(cmd_params->type, ENTRY_TYPE, cfg->type);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_fdb_add_multicast() - Add a set of egress interfaces to multi-cast group
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @fdb_id: Forwarding Database Identifier
+ * @cfg: Multicast entry configuration
+ *
+ * If group doesn't exist, it will be created.
+ * It adds only interfaces not belonging to this multicast group
+ * yet, otherwise error will be generated and the command is
+ * ignored.
+ * This function may be called numerous times always providing
+ * required interfaces delta.
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_fdb_add_multicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_multicast_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_fdb_multicast_op *cmd_params;
+ int i;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_FDB_ADD_MULTICAST,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_fdb_multicast_op *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(fdb_id);
+ cmd_params->num_ifs = cpu_to_le16(cfg->num_ifs);
+ dpsw_set_field(cmd_params->type, ENTRY_TYPE, cfg->type);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+ for (i = 0; i < 6; i++)
+ cmd_params->mac_addr[i] = cfg->mac_addr[5 - i];
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_fdb_remove_multicast() - Removing interfaces from an existing multicast
+ * group.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @fdb_id: Forwarding Database Identifier
+ * @cfg: Multicast entry configuration
+ *
+ * Interfaces provided by this API have to exist in the group,
+ * otherwise an error will be returned and an entire command
+ * ignored. If there is no interface left in the group,
+ * an entire group is deleted
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_fdb_remove_multicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_multicast_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_fdb_multicast_op *cmd_params;
+ int i;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_FDB_REMOVE_MULTICAST,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_fdb_multicast_op *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(fdb_id);
+ cmd_params->num_ifs = cpu_to_le16(cfg->num_ifs);
+ dpsw_set_field(cmd_params->type, ENTRY_TYPE, cfg->type);
+ build_if_id_bitmap(cmd_params->if_id, cfg->if_id, cfg->num_ifs);
+ for (i = 0; i < 6; i++)
+ cmd_params->mac_addr[i] = cfg->mac_addr[5 - i];
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_fdb_set_learning_mode() - Define FDB learning mode
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @fdb_id: Forwarding Database Identifier
+ * @mode: Learning mode
+ *
+ * Return: Completion status. '0' on Success; Error code otherwise.
+ */
+int dpsw_fdb_set_learning_mode(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ enum dpsw_fdb_learning_mode mode)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_fdb_set_learning_mode *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_FDB_SET_LEARNING_MODE,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_fdb_set_learning_mode *)cmd.params;
+ cmd_params->fdb_id = cpu_to_le16(fdb_id);
+ dpsw_set_field(cmd_params->mode, LEARNING_MODE, mode);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_get_api_version() - Get Data Path Switch API version
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @major_ver: Major version of data path switch API
+ * @minor_ver: Minor version of data path switch API
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_get_api_version(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 *major_ver,
+ u16 *minor_ver)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_rsp_get_api_version *rsp_params;
+ int err;
+
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_GET_API_VERSION,
+ cmd_flags,
+ 0);
+
+ err = mc_send_command(mc_io, &cmd);
+ if (err)
+ return err;
+
+ rsp_params = (struct dpsw_rsp_get_api_version *)cmd.params;
+ *major_ver = le16_to_cpu(rsp_params->version_major);
+ *minor_ver = le16_to_cpu(rsp_params->version_minor);
+
+ return 0;
+}
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw.h b/drivers/staging/fsl-dpaa2/ethsw/dpsw.h
new file mode 100644
index 0000000..e9c2906
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw.h
@@ -0,0 +1,579 @@
+/* Copyright 2013-2016 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __FSL_DPSW_H
+#define __FSL_DPSW_H
+
+/* Data Path L2-Switch API
+ * Contains API for handling DPSW topology and functionality
+ */
+
+struct fsl_mc_io;
+
+/**
+ * DPSW general definitions
+ */
+
+/**
+ * Maximum number of traffic class priorities
+ */
+#define DPSW_MAX_PRIORITIES 8
+/**
+ * Maximum number of interfaces
+ */
+#define DPSW_MAX_IF 64
+
+int dpsw_open(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ int dpsw_id,
+ u16 *token);
+
+int dpsw_close(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token);
+
+/**
+ * DPSW options
+ */
+
+/**
+ * Disable flooding
+ */
+#define DPSW_OPT_FLOODING_DIS 0x0000000000000001ULL
+/**
+ * Disable Multicast
+ */
+#define DPSW_OPT_MULTICAST_DIS 0x0000000000000004ULL
+/**
+ * Support control interface
+ */
+#define DPSW_OPT_CTRL_IF_DIS 0x0000000000000010ULL
+/**
+ * Disable flooding metering
+ */
+#define DPSW_OPT_FLOODING_METERING_DIS 0x0000000000000020ULL
+/**
+ * Enable metering
+ */
+#define DPSW_OPT_METERING_EN 0x0000000000000040ULL
+
+/**
+ * enum dpsw_component_type - component type of a bridge
+ * @DPSW_COMPONENT_TYPE_C_VLAN: A C-VLAN component of an
+ * enterprise VLAN bridge or of a Provider Bridge used
+ * to process C-tagged frames
+ * @DPSW_COMPONENT_TYPE_S_VLAN: An S-VLAN component of a
+ * Provider Bridge
+ *
+ */
+enum dpsw_component_type {
+ DPSW_COMPONENT_TYPE_C_VLAN = 0,
+ DPSW_COMPONENT_TYPE_S_VLAN
+};
+
+/**
+ * struct dpsw_cfg - DPSW configuration
+ * @num_ifs: Number of external and internal interfaces
+ * @adv: Advanced parameters; default is all zeros;
+ * use this structure to change default settings
+ */
+struct dpsw_cfg {
+ u16 num_ifs;
+ /**
+ * struct adv - Advanced parameters
+ * @options: Enable/Disable DPSW features (bitmap)
+ * @max_vlans: Maximum Number of VLAN's; 0 - indicates default 16
+ * @max_meters_per_if: Number of meters per interface
+ * @max_fdbs: Maximum Number of FDB's; 0 - indicates default 16
+ * @max_fdb_entries: Number of FDB entries for default FDB table;
+ * 0 - indicates default 1024 entries.
+ * @fdb_aging_time: Default FDB aging time for default FDB table;
+ * 0 - indicates default 300 seconds
+ * @max_fdb_mc_groups: Number of multicast groups in each FDB table;
+ * 0 - indicates default 32
+ * @component_type: Indicates the component type of this bridge
+ */
+ struct {
+ u64 options;
+ u16 max_vlans;
+ u8 max_meters_per_if;
+ u8 max_fdbs;
+ u16 max_fdb_entries;
+ u16 fdb_aging_time;
+ u16 max_fdb_mc_groups;
+ enum dpsw_component_type component_type;
+ } adv;
+};
+
+int dpsw_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token);
+
+int dpsw_disable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token);
+
+int dpsw_reset(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token);
+
+/**
+ * DPSW IRQ Index and Events
+ */
+
+#define DPSW_IRQ_INDEX_IF 0x0000
+#define DPSW_IRQ_INDEX_L2SW 0x0001
+
+/**
+ * IRQ event - Indicates that the link state changed
+ */
+#define DPSW_IRQ_EVENT_LINK_CHANGED 0x0001
+
+/**
+ * struct dpsw_irq_cfg - IRQ configuration
+ * @addr: Address that must be written to signal a message-based interrupt
+ * @val: Value to write into irq_addr address
+ * @irq_num: A user defined number associated with this IRQ
+ */
+struct dpsw_irq_cfg {
+ u64 addr;
+ u32 val;
+ int irq_num;
+};
+
+int dpsw_set_irq_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u8 en);
+
+int dpsw_set_irq_mask(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 mask);
+
+int dpsw_get_irq_status(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 *status);
+
+int dpsw_clear_irq_status(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u8 irq_index,
+ u32 status);
+
+/**
+ * struct dpsw_attr - Structure representing DPSW attributes
+ * @id: DPSW object ID
+ * @options: Enable/Disable DPSW features
+ * @max_vlans: Maximum Number of VLANs
+ * @max_meters_per_if: Number of meters per interface
+ * @max_fdbs: Maximum Number of FDBs
+ * @max_fdb_entries: Number of FDB entries for default FDB table;
+ * 0 - indicates default 1024 entries.
+ * @fdb_aging_time: Default FDB aging time for default FDB table;
+ * 0 - indicates default 300 seconds
+ * @max_fdb_mc_groups: Number of multicast groups in each FDB table;
+ * 0 - indicates default 32
+ * @mem_size: DPSW frame storage memory size
+ * @num_ifs: Number of interfaces
+ * @num_vlans: Current number of VLANs
+ * @num_fdbs: Current number of FDBs
+ * @component_type: Component type of this bridge
+ */
+struct dpsw_attr {
+ int id;
+ u64 options;
+ u16 max_vlans;
+ u8 max_meters_per_if;
+ u8 max_fdbs;
+ u16 max_fdb_entries;
+ u16 fdb_aging_time;
+ u16 max_fdb_mc_groups;
+ u16 num_ifs;
+ u16 mem_size;
+ u16 num_vlans;
+ u8 num_fdbs;
+ enum dpsw_component_type component_type;
+};
+
+int dpsw_get_attributes(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ struct dpsw_attr *attr);
+
+/**
+ * enum dpsw_action - Action selection for special/control frames
+ * @DPSW_ACTION_DROP: Drop frame
+ * @DPSW_ACTION_REDIRECT: Redirect frame to control port
+ */
+enum dpsw_action {
+ DPSW_ACTION_DROP = 0,
+ DPSW_ACTION_REDIRECT = 1
+};
+
+/**
+ * struct dpsw_link_state - Structure representing DPSW link state
+ * @rate: Rate
+ * @options: Mask of available options; use 'DPSW_LINK_OPT_<X>' values
+ * @up: 0 - covers two cases: down and disconnected, 1 - up
+ */
+struct dpsw_link_state {
+ u32 rate;
+ u64 options;
+ u8 up;
+};
+
+int dpsw_if_get_link_state(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ struct dpsw_link_state *state);
+
+int dpsw_if_set_flooding(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ int en);
+
+int dpsw_if_set_broadcast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ int en);
+
+/**
+ * struct dpsw_tci_cfg - Tag Control Information (TCI) configuration
+ * @pcp: Priority Code Point (PCP): a 3-bit field which refers
+ * to the IEEE 802.1p priority
+ * @dei: Drop Eligible Indicator (DEI): a 1-bit field. May be used
+ * separately or in conjunction with PCP to indicate frames
+ * eligible to be dropped in the presence of congestion
+ * @vlan_id: VLAN Identifier (VID): a 12-bit field specifying the VLAN
+ * to which the frame belongs. The hexadecimal values
+ * of 0x000 and 0xFFF are reserved;
+ * all other values may be used as VLAN identifiers,
+ * allowing up to 4,094 VLANs
+ */
+struct dpsw_tci_cfg {
+ u8 pcp;
+ u8 dei;
+ u16 vlan_id;
+};
+
+int dpsw_if_set_tci(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ const struct dpsw_tci_cfg *cfg);
+
+/**
+ * enum dpsw_stp_state - Spanning Tree Protocol (STP) states
+ * @DPSW_STP_STATE_BLOCKING: Blocking state
+ * @DPSW_STP_STATE_LISTENING: Listening state
+ * @DPSW_STP_STATE_LEARNING: Learning state
+ * @DPSW_STP_STATE_FORWARDING: Forwarding state
+ *
+ */
+enum dpsw_stp_state {
+ DPSW_STP_STATE_DISABLED = 0,
+ DPSW_STP_STATE_LISTENING = 1,
+ DPSW_STP_STATE_LEARNING = 2,
+ DPSW_STP_STATE_FORWARDING = 3,
+ DPSW_STP_STATE_BLOCKING = 0
+};
+
+/**
+ * struct dpsw_stp_cfg - Spanning Tree Protocol (STP) Configuration
+ * @vlan_id: VLAN ID STP state
+ * @state: STP state
+ */
+struct dpsw_stp_cfg {
+ u16 vlan_id;
+ enum dpsw_stp_state state;
+};
+
+int dpsw_if_set_stp(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ const struct dpsw_stp_cfg *cfg);
+
+/**
+ * enum dpsw_accepted_frames - Types of frames to accept
+ * @DPSW_ADMIT_ALL: The device accepts VLAN tagged, untagged and
+ * priority tagged frames
+ * @DPSW_ADMIT_ONLY_VLAN_TAGGED: The device discards untagged frames or
+ * Priority-Tagged frames received on this interface.
+ *
+ */
+enum dpsw_accepted_frames {
+ DPSW_ADMIT_ALL = 1,
+ DPSW_ADMIT_ONLY_VLAN_TAGGED = 3
+};
+
+/**
+ * enum dpsw_counter - Counters types
+ * @DPSW_CNT_ING_FRAME: Counts ingress frames
+ * @DPSW_CNT_ING_BYTE: Counts ingress bytes
+ * @DPSW_CNT_ING_FLTR_FRAME: Counts filtered ingress frames
+ * @DPSW_CNT_ING_FRAME_DISCARD: Counts discarded ingress frame
+ * @DPSW_CNT_ING_MCAST_FRAME: Counts ingress multicast frames
+ * @DPSW_CNT_ING_MCAST_BYTE: Counts ingress multicast bytes
+ * @DPSW_CNT_ING_BCAST_FRAME: Counts ingress broadcast frames
+ * @DPSW_CNT_ING_BCAST_BYTES: Counts ingress broadcast bytes
+ * @DPSW_CNT_EGR_FRAME: Counts egress frames
+ * @DPSW_CNT_EGR_BYTE: Counts eEgress bytes
+ * @DPSW_CNT_EGR_FRAME_DISCARD: Counts discarded egress frames
+ * @DPSW_CNT_EGR_STP_FRAME_DISCARD: Counts egress STP discarded frames
+ */
+enum dpsw_counter {
+ DPSW_CNT_ING_FRAME = 0x0,
+ DPSW_CNT_ING_BYTE = 0x1,
+ DPSW_CNT_ING_FLTR_FRAME = 0x2,
+ DPSW_CNT_ING_FRAME_DISCARD = 0x3,
+ DPSW_CNT_ING_MCAST_FRAME = 0x4,
+ DPSW_CNT_ING_MCAST_BYTE = 0x5,
+ DPSW_CNT_ING_BCAST_FRAME = 0x6,
+ DPSW_CNT_ING_BCAST_BYTES = 0x7,
+ DPSW_CNT_EGR_FRAME = 0x8,
+ DPSW_CNT_EGR_BYTE = 0x9,
+ DPSW_CNT_EGR_FRAME_DISCARD = 0xa,
+ DPSW_CNT_EGR_STP_FRAME_DISCARD = 0xb
+};
+
+int dpsw_if_get_counter(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ enum dpsw_counter type,
+ u64 *counter);
+
+int dpsw_if_enable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id);
+
+int dpsw_if_disable(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id);
+
+int dpsw_if_set_max_frame_length(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ u16 frame_length);
+
+/**
+ * struct dpsw_vlan_cfg - VLAN Configuration
+ * @fdb_id: Forwarding Data Base
+ */
+struct dpsw_vlan_cfg {
+ u16 fdb_id;
+};
+
+int dpsw_vlan_add(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_cfg *cfg);
+
+/**
+ * struct dpsw_vlan_if_cfg - Set of VLAN Interfaces
+ * @num_ifs: The number of interfaces that are assigned to the egress
+ * list for this VLAN
+ * @if_id: The set of interfaces that are
+ * assigned to the egress list for this VLAN
+ */
+struct dpsw_vlan_if_cfg {
+ u16 num_ifs;
+ u16 if_id[DPSW_MAX_IF];
+};
+
+int dpsw_vlan_add_if(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg);
+
+int dpsw_vlan_add_if_untagged(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg);
+
+int dpsw_vlan_remove_if(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg);
+
+int dpsw_vlan_remove_if_untagged(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id,
+ const struct dpsw_vlan_if_cfg *cfg);
+
+int dpsw_vlan_remove(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 vlan_id);
+
+/**
+ * enum dpsw_fdb_entry_type - FDB Entry type - Static/Dynamic
+ * @DPSW_FDB_ENTRY_STATIC: Static entry
+ * @DPSW_FDB_ENTRY_DINAMIC: Dynamic entry
+ */
+enum dpsw_fdb_entry_type {
+ DPSW_FDB_ENTRY_STATIC = 0,
+ DPSW_FDB_ENTRY_DINAMIC = 1
+};
+
+/**
+ * struct dpsw_fdb_unicast_cfg - Unicast entry configuration
+ * @type: Select static or dynamic entry
+ * @mac_addr: MAC address
+ * @if_egress: Egress interface ID
+ */
+struct dpsw_fdb_unicast_cfg {
+ enum dpsw_fdb_entry_type type;
+ u8 mac_addr[6];
+ u16 if_egress;
+};
+
+int dpsw_fdb_add_unicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_unicast_cfg *cfg);
+
+int dpsw_fdb_remove_unicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_unicast_cfg *cfg);
+
+/**
+ * struct dpsw_fdb_multicast_cfg - Multi-cast entry configuration
+ * @type: Select static or dynamic entry
+ * @mac_addr: MAC address
+ * @num_ifs: Number of external and internal interfaces
+ * @if_id: Egress interface IDs
+ */
+struct dpsw_fdb_multicast_cfg {
+ enum dpsw_fdb_entry_type type;
+ u8 mac_addr[6];
+ u16 num_ifs;
+ u16 if_id[DPSW_MAX_IF];
+};
+
+int dpsw_fdb_add_multicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_multicast_cfg *cfg);
+
+int dpsw_fdb_remove_multicast(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ const struct dpsw_fdb_multicast_cfg *cfg);
+
+/**
+ * enum dpsw_fdb_learning_mode - Auto-learning modes
+ * @DPSW_FDB_LEARNING_MODE_DIS: Disable Auto-learning
+ * @DPSW_FDB_LEARNING_MODE_HW: Enable HW auto-Learning
+ * @DPSW_FDB_LEARNING_MODE_NON_SECURE: Enable None secure learning by CPU
+ * @DPSW_FDB_LEARNING_MODE_SECURE: Enable secure learning by CPU
+ *
+ * NONE - SECURE LEARNING
+ * SMAC found DMAC found CTLU Action
+ * v v Forward frame to
+ * 1. DMAC destination
+ * - v Forward frame to
+ * 1. DMAC destination
+ * 2. Control interface
+ * v - Forward frame to
+ * 1. Flooding list of interfaces
+ * - - Forward frame to
+ * 1. Flooding list of interfaces
+ * 2. Control interface
+ * SECURE LEARING
+ * SMAC found DMAC found CTLU Action
+ * v v Forward frame to
+ * 1. DMAC destination
+ * - v Forward frame to
+ * 1. Control interface
+ * v - Forward frame to
+ * 1. Flooding list of interfaces
+ * - - Forward frame to
+ * 1. Control interface
+ */
+enum dpsw_fdb_learning_mode {
+ DPSW_FDB_LEARNING_MODE_DIS = 0,
+ DPSW_FDB_LEARNING_MODE_HW = 1,
+ DPSW_FDB_LEARNING_MODE_NON_SECURE = 2,
+ DPSW_FDB_LEARNING_MODE_SECURE = 3
+};
+
+int dpsw_fdb_set_learning_mode(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 fdb_id,
+ enum dpsw_fdb_learning_mode mode);
+
+/**
+ * struct dpsw_fdb_attr - FDB Attributes
+ * @max_fdb_entries: Number of FDB entries
+ * @fdb_aging_time: Aging time in seconds
+ * @learning_mode: Learning mode
+ * @num_fdb_mc_groups: Current number of multicast groups
+ * @max_fdb_mc_groups: Maximum number of multicast groups
+ */
+struct dpsw_fdb_attr {
+ u16 max_fdb_entries;
+ u16 fdb_aging_time;
+ enum dpsw_fdb_learning_mode learning_mode;
+ u16 num_fdb_mc_groups;
+ u16 max_fdb_mc_groups;
+};
+
+int dpsw_get_api_version(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 *major_ver,
+ u16 *minor_ver);
+
+#endif /* __FSL_DPSW_H */
--
1.9.1
^ permalink raw reply related
* [RESEND PATCH 2/6] staging: fsl-dpaa2/ethsw: Add Freescale DPAA2 Ethernet Switch driver
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, arnd, netdev, alexandru.marginean, linux-kernel, agraf,
stuyoder, bogdan.purcareata, laurentiu.tudor
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Introduce the DPAA2 Ethernet Switch driver, which manages Datapath Switch
(DPSW) objects discovered on the MC bus.
Suggested-by: Alexandru Marginean <alexandru.marginean@nxp.com>
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
drivers/staging/fsl-dpaa2/ethsw/Makefile | 2 +-
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 1523 ++++++++++++++++++++++++++++++
drivers/staging/fsl-dpaa2/ethsw/ethsw.h | 88 ++
3 files changed, 1612 insertions(+), 1 deletion(-)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw.c
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw.h
diff --git a/drivers/staging/fsl-dpaa2/ethsw/Makefile b/drivers/staging/fsl-dpaa2/ethsw/Makefile
index db137f7..a6d72d1 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/Makefile
+++ b/drivers/staging/fsl-dpaa2/ethsw/Makefile
@@ -4,4 +4,4 @@
obj-$(CONFIG_FSL_DPAA2_ETHSW) += dpaa2-ethsw.o
-dpaa2-ethsw-objs := dpsw.o
+dpaa2-ethsw-objs := ethsw.o dpsw.o
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
new file mode 100644
index 0000000..ae86078
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -0,0 +1,1523 @@
+/* Copyright 2014-2016 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+
+#include <linux/interrupt.h>
+#include <linux/msi.h>
+#include <linux/kthread.h>
+#include <linux/workqueue.h>
+
+#include "../../fsl-mc/include/mc.h"
+
+#include "ethsw.h"
+
+static struct workqueue_struct *ethsw_owq;
+
+/* Minimal supported DPSW version */
+#define DPSW_MIN_VER_MAJOR 8
+#define DPSW_MIN_VER_MINOR 0
+
+#define DEFAULT_VLAN_ID 1
+
+static int ethsw_add_vlan(struct ethsw_core *ethsw, u16 vid)
+{
+ int err;
+
+ struct dpsw_vlan_cfg vcfg = {
+ .fdb_id = 0,
+ };
+
+ if (ethsw->vlans[vid]) {
+ dev_err(ethsw->dev, "VLAN already configured\n");
+ return -EEXIST;
+ }
+
+ err = dpsw_vlan_add(ethsw->mc_io, 0,
+ ethsw->dpsw_handle, vid, &vcfg);
+ if (err) {
+ dev_err(ethsw->dev, "dpsw_vlan_add err %d\n", err);
+ return err;
+ }
+ ethsw->vlans[vid] = ETHSW_VLAN_MEMBER;
+
+ return 0;
+}
+
+static int ethsw_port_add_vlan(struct ethsw_port_priv *port_priv,
+ u16 vid, u16 flags)
+{
+ struct ethsw_core *ethsw = port_priv->ethsw_data;
+ struct net_device *netdev = port_priv->netdev;
+ struct dpsw_vlan_if_cfg vcfg;
+ bool is_oper;
+ int err, err2;
+
+ if (port_priv->vlans[vid]) {
+ netdev_warn(netdev, "VLAN %d already configured\n", vid);
+ return -EEXIST;
+ }
+
+ vcfg.num_ifs = 1;
+ vcfg.if_id[0] = port_priv->idx;
+ err = dpsw_vlan_add_if(ethsw->mc_io, 0, ethsw->dpsw_handle, vid, &vcfg);
+ if (err) {
+ netdev_err(netdev, "dpsw_vlan_add_if err %d\n", err);
+ return err;
+ }
+
+ port_priv->vlans[vid] = ETHSW_VLAN_MEMBER;
+
+ if (flags & BRIDGE_VLAN_INFO_UNTAGGED) {
+ err = dpsw_vlan_add_if_untagged(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ vid, &vcfg);
+ if (err) {
+ netdev_err(netdev,
+ "dpsw_vlan_add_if_untagged err %d\n", err);
+ return err;
+ }
+ port_priv->vlans[vid] |= ETHSW_VLAN_UNTAGGED;
+ }
+
+ if (flags & BRIDGE_VLAN_INFO_PVID) {
+ struct dpsw_tci_cfg tci_cfg = {
+ .pcp = 0,
+ .dei = 0,
+ .vlan_id = vid,
+ };
+
+ /* Interface needs to be down to change PVID */
+ is_oper = netif_oper_up(netdev);
+ if (is_oper) {
+ err = dpsw_if_disable(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ port_priv->idx);
+ if (err) {
+ netdev_err(netdev,
+ "dpsw_if_disable err %d\n", err);
+ return err;
+ }
+ }
+
+ err = dpsw_if_set_tci(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ port_priv->idx, &tci_cfg);
+ if (!err) {
+ /* Delete previous PVID info and mark the new one */
+ if (port_priv->pvid)
+ port_priv->vlans[port_priv->pvid]
+ ^= ETHSW_VLAN_PVID;
+
+ port_priv->vlans[vid] |= ETHSW_VLAN_PVID;
+ port_priv->pvid = vid;
+ } else {
+ netdev_err(netdev, "dpsw_if_set_tci err %d\n", err);
+ }
+
+ if (is_oper) {
+ err2 = dpsw_if_enable(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ port_priv->idx);
+ if (err2) {
+ netdev_err(netdev,
+ "dpsw_if_enable err %d\n", err2);
+ return err2;
+ }
+ }
+ }
+
+ return err;
+}
+
+static int ethsw_set_learning(struct ethsw_core *ethsw, u8 flag)
+{
+ enum dpsw_fdb_learning_mode learn_mode;
+ int err;
+
+ if (flag)
+ learn_mode = DPSW_FDB_LEARNING_MODE_HW;
+ else
+ learn_mode = DPSW_FDB_LEARNING_MODE_DIS;
+
+ err = dpsw_fdb_set_learning_mode(ethsw->mc_io, 0, ethsw->dpsw_handle, 0,
+ learn_mode);
+ if (err) {
+ dev_err(ethsw->dev, "dpsw_fdb_set_learning_mode err %d\n", err);
+ return err;
+ }
+ ethsw->learning = !!flag;
+
+ return 0;
+}
+
+static int ethsw_port_set_flood(struct ethsw_port_priv *port_priv, u8 flag)
+{
+ int err;
+
+ err = dpsw_if_set_flooding(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx, (int)flag);
+ if (err) {
+ netdev_err(port_priv->netdev,
+ "dpsw_fdb_set_learning_mode err %d\n", err);
+ return err;
+ }
+ port_priv->flood = !!flag;
+
+ return 0;
+}
+
+static int ethsw_port_set_stp_state(struct ethsw_port_priv *port_priv, u8 state)
+{
+ struct dpsw_stp_cfg stp_cfg = {
+ .vlan_id = DEFAULT_VLAN_ID,
+ .state = state,
+ };
+ int err;
+
+ if (!netif_oper_up(port_priv->netdev) || state == port_priv->stp_state)
+ return 0; /* Nothing to do */
+
+ err = dpsw_if_set_stp(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx, &stp_cfg);
+ if (err) {
+ netdev_err(port_priv->netdev,
+ "dpsw_if_set_stp err %d\n", err);
+ return err;
+ }
+
+ port_priv->stp_state = state;
+
+ return 0;
+}
+
+static int ethsw_dellink_switch(struct ethsw_core *ethsw, u16 vid)
+{
+ struct ethsw_port_priv *ppriv_local = NULL;
+ int i, err;
+
+ if (!ethsw->vlans[vid])
+ return -ENOENT;
+
+ err = dpsw_vlan_remove(ethsw->mc_io, 0, ethsw->dpsw_handle, vid);
+ if (err) {
+ dev_err(ethsw->dev, "dpsw_vlan_remove err %d\n", err);
+ return err;
+ }
+ ethsw->vlans[vid] = 0;
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ ppriv_local = ethsw->ports[i];
+ ppriv_local->vlans[vid] = 0;
+ }
+
+ return 0;
+}
+
+static int ethsw_port_fdb_add_uc(struct ethsw_port_priv *port_priv,
+ const unsigned char *addr)
+{
+ struct dpsw_fdb_unicast_cfg entry = {0};
+ int err;
+
+ entry.if_egress = port_priv->idx;
+ entry.type = DPSW_FDB_ENTRY_STATIC;
+ ether_addr_copy(entry.mac_addr, addr);
+
+ err = dpsw_fdb_add_unicast(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ 0, &entry);
+ if (err)
+ netdev_err(port_priv->netdev,
+ "dpsw_fdb_add_unicast err %d\n", err);
+ return err;
+}
+
+static int ethsw_port_fdb_del_uc(struct ethsw_port_priv *port_priv,
+ const unsigned char *addr)
+{
+ struct dpsw_fdb_unicast_cfg entry = {0};
+ int err;
+
+ entry.if_egress = port_priv->idx;
+ entry.type = DPSW_FDB_ENTRY_STATIC;
+ ether_addr_copy(entry.mac_addr, addr);
+
+ err = dpsw_fdb_remove_unicast(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ 0, &entry);
+ if (err)
+ netdev_err(port_priv->netdev,
+ "dpsw_fdb_remove_unicast err %d\n", err);
+ return err;
+}
+
+static int ethsw_port_fdb_add_mc(struct ethsw_port_priv *port_priv,
+ const unsigned char *addr)
+{
+ struct dpsw_fdb_multicast_cfg entry = {0};
+ int err;
+
+ ether_addr_copy(entry.mac_addr, addr);
+ entry.type = DPSW_FDB_ENTRY_STATIC;
+ entry.num_ifs = 1;
+ entry.if_id[0] = port_priv->idx;
+
+ err = dpsw_fdb_add_multicast(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ 0, &entry);
+ if (err)
+ netdev_err(port_priv->netdev, "dpsw_fdb_add_multicast err %d\n",
+ err);
+ return err;
+}
+
+static int ethsw_port_fdb_del_mc(struct ethsw_port_priv *port_priv,
+ const unsigned char *addr)
+{
+ struct dpsw_fdb_multicast_cfg entry = {0};
+ int err;
+
+ ether_addr_copy(entry.mac_addr, addr);
+ entry.type = DPSW_FDB_ENTRY_STATIC;
+ entry.num_ifs = 1;
+ entry.if_id[0] = port_priv->idx;
+
+ err = dpsw_fdb_remove_multicast(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ 0, &entry);
+ if (err)
+ netdev_err(port_priv->netdev,
+ "dpsw_fdb_remove_multicast err %d\n", err);
+ return err;
+}
+
+static void port_get_stats(struct net_device *netdev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ u64 tmp;
+ int err;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_ING_FRAME, &stats->rx_packets);
+ if (err)
+ goto error;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_EGR_FRAME, &stats->tx_packets);
+ if (err)
+ goto error;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_ING_BYTE, &stats->rx_bytes);
+ if (err)
+ goto error;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_EGR_BYTE, &stats->tx_bytes);
+ if (err)
+ goto error;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_ING_FRAME_DISCARD,
+ &stats->rx_dropped);
+ if (err)
+ goto error;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_ING_FLTR_FRAME,
+ &tmp);
+ if (err)
+ goto error;
+ stats->rx_dropped += tmp;
+
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ DPSW_CNT_EGR_FRAME_DISCARD,
+ &stats->tx_dropped);
+ if (err)
+ goto error;
+
+ return;
+
+error:
+ netdev_err(netdev, "dpsw_if_get_counter err %d\n", err);
+}
+
+static bool port_has_offload_stats(const struct net_device *netdev,
+ int attr_id)
+{
+ return (attr_id == IFLA_OFFLOAD_XSTATS_CPU_HIT);
+}
+
+static int port_get_offload_stats(int attr_id,
+ const struct net_device *netdev,
+ void *sp)
+{
+ switch (attr_id) {
+ case IFLA_OFFLOAD_XSTATS_CPU_HIT:
+ port_get_stats((struct net_device *)netdev, sp);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static int port_change_mtu(struct net_device *netdev, int mtu)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err;
+
+ err = dpsw_if_set_max_frame_length(port_priv->ethsw_data->mc_io,
+ 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ (u16)ETHSW_L2_MAX_FRM(mtu));
+ if (err) {
+ netdev_err(netdev,
+ "dpsw_if_set_max_frame_length() err %d\n", err);
+ return err;
+ }
+
+ netdev->mtu = mtu;
+ return 0;
+}
+
+static int port_carrier_state_sync(struct net_device *netdev)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ struct dpsw_link_state state;
+ int err;
+
+ err = dpsw_if_get_link_state(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx, &state);
+ if (err) {
+ netdev_err(netdev, "dpsw_if_get_link_state() err %d\n", err);
+ return err;
+ }
+
+ WARN_ONCE(state.up > 1, "Garbage read into link_state");
+
+ if (state.up != port_priv->link_state) {
+ if (state.up)
+ netif_carrier_on(netdev);
+ else
+ netif_carrier_off(netdev);
+ port_priv->link_state = state.up;
+ }
+ return 0;
+}
+
+static int port_open(struct net_device *netdev)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err;
+
+ /* No need to allow Tx as control interface is disabled */
+ netif_tx_stop_all_queues(netdev);
+
+ err = dpsw_if_enable(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx);
+ if (err) {
+ netdev_err(netdev, "dpsw_if_enable err %d\n", err);
+ return err;
+ }
+
+ /* sync carrier state */
+ err = port_carrier_state_sync(netdev);
+ if (err) {
+ netdev_err(netdev,
+ "port_carrier_state_sync err %d\n", err);
+ goto err_carrier_sync;
+ }
+
+ return 0;
+
+err_carrier_sync:
+ dpsw_if_disable(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx);
+ return err;
+}
+
+static int port_stop(struct net_device *netdev)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err;
+
+ err = dpsw_if_disable(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx);
+ if (err) {
+ netdev_err(netdev, "dpsw_if_disable err %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static netdev_tx_t port_dropframe(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ /* we don't support I/O for now, drop the frame */
+ dev_kfree_skb_any(skb);
+
+ return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops ethsw_port_ops = {
+ .ndo_open = port_open,
+ .ndo_stop = port_stop,
+
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_change_mtu = port_change_mtu,
+ .ndo_has_offload_stats = port_has_offload_stats,
+ .ndo_get_offload_stats = port_get_offload_stats,
+
+ .ndo_start_xmit = port_dropframe,
+};
+
+static void ethsw_links_state_update(struct ethsw_core *ethsw)
+{
+ int i;
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+ port_carrier_state_sync(ethsw->ports[i]->netdev);
+}
+
+static irqreturn_t ethsw_irq0_handler(int irq_num, void *arg)
+{
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t ethsw_irq0_handler_thread(int irq_num, void *arg)
+{
+ struct device *dev = (struct device *)arg;
+ struct ethsw_core *ethsw = dev_get_drvdata(dev);
+
+ /* Mask the events and the if_id reserved bits to be cleared on read */
+ u32 status = DPSW_IRQ_EVENT_LINK_CHANGED | 0xFFFF0000;
+ int err;
+
+ err = dpsw_get_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, &status);
+ if (err) {
+ dev_err(dev, "Can't get irq status (err %d)", err);
+
+ err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, 0xFFFFFFFF);
+ if (err)
+ dev_err(dev, "Can't clear irq status (err %d)", err);
+ goto out;
+ }
+
+ if (status & DPSW_IRQ_EVENT_LINK_CHANGED)
+ ethsw_links_state_update(ethsw);
+
+out:
+ return IRQ_HANDLED;
+}
+
+static int ethsw_setup_irqs(struct fsl_mc_device *sw_dev)
+{
+ struct device *dev = &sw_dev->dev;
+ struct ethsw_core *ethsw = dev_get_drvdata(dev);
+ u32 mask = DPSW_IRQ_EVENT_LINK_CHANGED;
+ struct fsl_mc_device_irq *irq;
+ int err;
+
+ err = fsl_mc_allocate_irqs(sw_dev);
+ if (err) {
+ dev_err(dev, "MC irqs allocation failed\n");
+ return err;
+ }
+
+ if (WARN_ON(sw_dev->obj_desc.irq_count != DPSW_IRQ_NUM)) {
+ err = -EINVAL;
+ goto free_irq;
+ }
+
+ err = dpsw_set_irq_enable(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, 0);
+ if (err) {
+ dev_err(dev, "dpsw_set_irq_enable err %d\n", err);
+ goto free_irq;
+ }
+
+ irq = sw_dev->irqs[DPSW_IRQ_INDEX_IF];
+
+ err = devm_request_threaded_irq(dev, irq->msi_desc->irq,
+ ethsw_irq0_handler,
+ ethsw_irq0_handler_thread,
+ IRQF_NO_SUSPEND | IRQF_ONESHOT,
+ dev_name(dev), dev);
+ if (err) {
+ dev_err(dev, "devm_request_threaded_irq(): %d", err);
+ goto free_irq;
+ }
+
+ err = dpsw_set_irq_mask(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, mask);
+ if (err) {
+ dev_err(dev, "dpsw_set_irq_mask(): %d", err);
+ goto free_devm_irq;
+ }
+
+ err = dpsw_set_irq_enable(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, 1);
+ if (err) {
+ dev_err(dev, "dpsw_set_irq_enable(): %d", err);
+ goto free_devm_irq;
+ }
+
+ return 0;
+
+free_devm_irq:
+ devm_free_irq(dev, irq->msi_desc->irq, dev);
+free_irq:
+ fsl_mc_free_irqs(sw_dev);
+ return err;
+}
+
+static void ethsw_teardown_irqs(struct fsl_mc_device *sw_dev)
+{
+ struct device *dev = &sw_dev->dev;
+ struct ethsw_core *ethsw = dev_get_drvdata(dev);
+ struct fsl_mc_device_irq *irq;
+
+ irq = sw_dev->irqs[DPSW_IRQ_INDEX_IF];
+ dpsw_set_irq_enable(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DPSW_IRQ_INDEX_IF, 0);
+ fsl_mc_free_irqs(sw_dev);
+}
+
+static int swdev_port_attr_get(struct net_device *netdev,
+ struct switchdev_attr *attr)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+ attr->u.ppid.id_len = 1;
+ attr->u.ppid.id[0] = port_priv->ethsw_data->dev_id;
+ break;
+ case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+ attr->u.brport_flags =
+ (port_priv->ethsw_data->learning ? BR_LEARNING : 0) |
+ (port_priv->flood ? BR_FLOOD : 0);
+ break;
+ case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
+ attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD;
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static int port_attr_stp_state_set(struct net_device *netdev,
+ struct switchdev_trans *trans,
+ u8 state)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ return ethsw_port_set_stp_state(port_priv, state);
+}
+
+static int port_attr_br_flags_set(struct net_device *netdev,
+ struct switchdev_trans *trans,
+ unsigned long flags)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err = 0;
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ /* Learning is enabled per switch */
+ err = ethsw_set_learning(port_priv->ethsw_data, flags & BR_LEARNING);
+ if (err)
+ goto exit;
+
+ err = ethsw_port_set_flood(port_priv, flags & BR_FLOOD);
+
+exit:
+ return err;
+}
+
+static int swdev_port_attr_set(struct net_device *netdev,
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans)
+{
+ int err = 0;
+
+ switch (attr->id) {
+ case SWITCHDEV_ATTR_ID_PORT_STP_STATE:
+ err = port_attr_stp_state_set(netdev, trans,
+ attr->u.stp_state);
+ break;
+ case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+ err = port_attr_br_flags_set(netdev, trans,
+ attr->u.brport_flags);
+ break;
+ case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+ /* VLANs are supported by default */
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
+static int port_vlans_add(struct net_device *netdev,
+ const struct switchdev_obj_port_vlan *vlan,
+ struct switchdev_trans *trans)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int vid, err;
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+ if (!port_priv->ethsw_data->vlans[vid]) {
+ /* this is a new VLAN */
+ err = ethsw_add_vlan(port_priv->ethsw_data, vid);
+ if (err)
+ return err;
+
+ port_priv->ethsw_data->vlans[vid] |= ETHSW_VLAN_GLOBAL;
+ }
+ err = ethsw_port_add_vlan(port_priv, vid, vlan->flags);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+static int port_lookup_address(struct net_device *netdev, int is_uc,
+ const unsigned char *addr)
+{
+ struct netdev_hw_addr_list *list = (is_uc) ? &netdev->uc : &netdev->mc;
+ struct netdev_hw_addr *ha;
+
+ netif_addr_lock_bh(netdev);
+ list_for_each_entry(ha, &list->list, list) {
+ if (ether_addr_equal(ha->addr, addr)) {
+ netif_addr_unlock_bh(netdev);
+ return 1;
+ }
+ }
+ netif_addr_unlock_bh(netdev);
+ return 0;
+}
+
+static int port_mdb_add(struct net_device *netdev,
+ const struct switchdev_obj_port_mdb *mdb,
+ struct switchdev_trans *trans)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err;
+
+ if (switchdev_trans_ph_prepare(trans))
+ return 0;
+
+ /* Check if address is already set on this port */
+ if (port_lookup_address(netdev, 0, mdb->addr))
+ return -EEXIST;
+
+ err = ethsw_port_fdb_add_mc(port_priv, mdb->addr);
+ if (err)
+ return err;
+
+ err = dev_mc_add(netdev, mdb->addr);
+ if (err)
+ netdev_err(netdev, "dev_mc_add err %d\n", err);
+
+ return err;
+}
+
+static int swdev_port_obj_add(struct net_device *netdev,
+ const struct switchdev_obj *obj,
+ struct switchdev_trans *trans)
+{
+ int err;
+
+ switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ err = port_vlans_add(netdev,
+ SWITCHDEV_OBJ_PORT_VLAN(obj),
+ trans);
+ break;
+ case SWITCHDEV_OBJ_ID_PORT_MDB:
+ err = port_mdb_add(netdev,
+ SWITCHDEV_OBJ_PORT_MDB(obj),
+ trans);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
+static int ethsw_port_del_vlan(struct ethsw_port_priv *port_priv, u16 vid)
+{
+ struct ethsw_core *ethsw = port_priv->ethsw_data;
+ struct net_device *netdev = port_priv->netdev;
+ struct dpsw_vlan_if_cfg vcfg;
+ int i, err, err2;
+ bool is_oper;
+
+ if (!port_priv->vlans[vid])
+ return -ENOENT;
+
+ if (port_priv->vlans[vid] & ETHSW_VLAN_PVID) {
+ struct dpsw_tci_cfg tci_cfg = { 0 };
+ /* Interface needs to be down to change PVID */
+ is_oper = netif_oper_up(netdev);
+
+ if (is_oper) {
+ err = dpsw_if_disable(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ port_priv->idx);
+ if (err) {
+ netdev_err(netdev, "dpsw_if_disable err %d\n",
+ err);
+ goto exit_err;
+ }
+ }
+
+ err = dpsw_if_set_tci(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ port_priv->idx, &tci_cfg);
+ if (!err) {
+ port_priv->vlans[vid] &= ~ETHSW_VLAN_PVID;
+ port_priv->pvid = 0;
+ } else {
+ netdev_err(netdev, "dpsw_if_set_tci err %d\n", err);
+ }
+
+ if (is_oper) {
+ err2 = dpsw_if_enable(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ port_priv->idx);
+ if (err2) {
+ netdev_err(netdev, "dpsw_if_enable err %d\n",
+ err2);
+ return err2;
+ }
+ }
+
+ if (err)
+ goto exit_err;
+ }
+
+ vcfg.num_ifs = 1;
+ vcfg.if_id[0] = port_priv->idx;
+ if (port_priv->vlans[vid] & ETHSW_VLAN_UNTAGGED) {
+ err = dpsw_vlan_remove_if_untagged(ethsw->mc_io, 0,
+ ethsw->dpsw_handle,
+ vid, &vcfg);
+ if (err) {
+ netdev_err(netdev,
+ "dpsw_vlan_remove_if_untagged err %d\n",
+ err);
+ }
+ port_priv->vlans[vid] &= ~ETHSW_VLAN_UNTAGGED;
+ }
+
+ if (port_priv->vlans[vid] & ETHSW_VLAN_MEMBER) {
+ err = dpsw_vlan_remove_if(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ vid, &vcfg);
+ if (err) {
+ netdev_err(netdev,
+ "dpsw_vlan_remove_if err %d\n", err);
+ return err;
+ }
+ port_priv->vlans[vid] &= ~ETHSW_VLAN_MEMBER;
+
+ /* Delete VLAN from switch if it is no longer configured on
+ * any port
+ */
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+ if (ethsw->ports[i]->vlans[vid] & ETHSW_VLAN_MEMBER)
+ return 0; /* Found a port member in VID */
+
+ ethsw->vlans[vid] &= ~ETHSW_VLAN_GLOBAL;
+
+ err = ethsw_dellink_switch(ethsw, vid);
+ if (err)
+ goto exit_err;
+ }
+
+ return 0;
+exit_err:
+ return err;
+}
+
+static int port_vlans_del(struct net_device *netdev,
+ const struct switchdev_obj_port_vlan *vlan)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int vid, err;
+
+ for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+ err = ethsw_port_del_vlan(port_priv, vid);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+static int port_mdb_del(struct net_device *netdev,
+ const struct switchdev_obj_port_mdb *mdb)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int err;
+
+ if (!port_lookup_address(netdev, 0, mdb->addr))
+ return -ENOENT;
+
+ err = ethsw_port_fdb_del_mc(port_priv, mdb->addr);
+ if (err)
+ return err;
+
+ err = dev_mc_del(netdev, mdb->addr);
+ if (err) {
+ netdev_err(netdev, "dev_mc_del err %d\n", err);
+ return err;
+ }
+
+ return err;
+}
+
+static int swdev_port_obj_del(struct net_device *netdev,
+ const struct switchdev_obj *obj)
+{
+ int err;
+
+ switch (obj->id) {
+ case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ err = port_vlans_del(netdev, SWITCHDEV_OBJ_PORT_VLAN(obj));
+ break;
+ case SWITCHDEV_OBJ_ID_PORT_MDB:
+ err = port_mdb_del(netdev, SWITCHDEV_OBJ_PORT_MDB(obj));
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+ return err;
+}
+
+static const struct switchdev_ops ethsw_port_switchdev_ops = {
+ .switchdev_port_attr_get = swdev_port_attr_get,
+ .switchdev_port_attr_set = swdev_port_attr_set,
+ .switchdev_port_obj_add = swdev_port_obj_add,
+ .switchdev_port_obj_del = swdev_port_obj_del,
+};
+
+/* For the moment, only flood setting needs to be updated */
+static int port_bridge_join(struct net_device *netdev)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+
+ /* Enable flooding */
+ return ethsw_port_set_flood(port_priv, 1);
+}
+
+static int port_bridge_leave(struct net_device *netdev)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+
+ /* Disable flooding */
+ return ethsw_port_set_flood(port_priv, 0);
+}
+
+static int port_netdevice_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_changeupper_info *info = ptr;
+ struct net_device *upper_dev;
+ int err = 0;
+
+ if (netdev->netdev_ops != ðsw_port_ops)
+ return NOTIFY_DONE;
+
+ /* Handle just upper dev link/unlink for the moment */
+ if (event == NETDEV_CHANGEUPPER) {
+ upper_dev = info->upper_dev;
+ if (netif_is_bridge_master(upper_dev)) {
+ if (info->linking)
+ err = port_bridge_join(netdev);
+ else
+ err = port_bridge_leave(netdev);
+ }
+ }
+
+ return notifier_from_errno(err);
+}
+
+static struct notifier_block port_nb __read_mostly = {
+ .notifier_call = port_netdevice_event,
+};
+
+struct ethsw_switchdev_event_work {
+ struct work_struct work;
+ struct switchdev_notifier_fdb_info fdb_info;
+ struct net_device *dev;
+ unsigned long event;
+};
+
+static void ethsw_switchdev_event_work(struct work_struct *work)
+{
+ struct ethsw_switchdev_event_work *switchdev_work =
+ container_of(work, struct ethsw_switchdev_event_work, work);
+ struct net_device *dev = switchdev_work->dev;
+ struct switchdev_notifier_fdb_info *fdb_info;
+ struct ethsw_port_priv *port_priv;
+
+ rtnl_lock();
+ port_priv = netdev_priv(dev);
+ fdb_info = &switchdev_work->fdb_info;
+
+ switch (switchdev_work->event) {
+ case SWITCHDEV_FDB_ADD_TO_DEVICE:
+ ethsw_port_fdb_add_uc(netdev_priv(dev), fdb_info->addr);
+ break;
+ case SWITCHDEV_FDB_DEL_TO_DEVICE:
+ ethsw_port_fdb_del_uc(netdev_priv(dev), fdb_info->addr);
+ break;
+ }
+
+ rtnl_unlock();
+ kfree(switchdev_work->fdb_info.addr);
+ kfree(switchdev_work);
+ dev_put(dev);
+}
+
+/* Called under rcu_read_lock() */
+static int port_switchdev_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+ struct ethsw_switchdev_event_work *switchdev_work;
+ struct switchdev_notifier_fdb_info *fdb_info = ptr;
+
+ switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
+ if (!switchdev_work)
+ return NOTIFY_BAD;
+
+ INIT_WORK(&switchdev_work->work, ethsw_switchdev_event_work);
+ switchdev_work->dev = dev;
+ switchdev_work->event = event;
+
+ switch (event) {
+ case SWITCHDEV_FDB_ADD_TO_DEVICE:
+ case SWITCHDEV_FDB_DEL_TO_DEVICE:
+ memcpy(&switchdev_work->fdb_info, ptr,
+ sizeof(switchdev_work->fdb_info));
+ switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
+ if (!switchdev_work->fdb_info.addr)
+ goto err_addr_alloc;
+
+ ether_addr_copy((u8 *)switchdev_work->fdb_info.addr,
+ fdb_info->addr);
+
+ /* Take a reference on the device to avoid being freed. */
+ dev_hold(dev);
+ break;
+ default:
+ return NOTIFY_DONE;
+ }
+
+ queue_work(ethsw_owq, &switchdev_work->work);
+
+ return NOTIFY_DONE;
+
+err_addr_alloc:
+ kfree(switchdev_work);
+ return NOTIFY_BAD;
+}
+
+static struct notifier_block port_switchdev_nb = {
+ .notifier_call = port_switchdev_event,
+};
+
+static int ethsw_register_notifier(struct device *dev)
+{
+ int err;
+
+ err = register_netdevice_notifier(&port_nb);
+ if (err) {
+ dev_err(dev, "Failed to register netdev notifier\n");
+ return err;
+ }
+
+ err = register_switchdev_notifier(&port_switchdev_nb);
+ if (err) {
+ dev_err(dev, "Failed to register switchdev notifier\n");
+ goto err_switchdev_nb;
+ }
+
+ return 0;
+
+err_switchdev_nb:
+ unregister_netdevice_notifier(&port_nb);
+ return err;
+}
+
+static int ethsw_open(struct ethsw_core *ethsw)
+{
+ struct ethsw_port_priv *port_priv = NULL;
+ int i, err;
+
+ err = dpsw_enable(ethsw->mc_io, 0, ethsw->dpsw_handle);
+ if (err) {
+ dev_err(ethsw->dev, "dpsw_enable err %d\n", err);
+ return err;
+ }
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ port_priv = ethsw->ports[i];
+ err = dev_open(port_priv->netdev);
+ if (err) {
+ netdev_err(port_priv->netdev, "dev_open err %d\n", err);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int ethsw_stop(struct ethsw_core *ethsw)
+{
+ struct ethsw_port_priv *port_priv = NULL;
+ int i, err;
+
+ destroy_workqueue(ethsw_owq);
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ port_priv = ethsw->ports[i];
+ dev_close(port_priv->netdev);
+ }
+
+ err = dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
+ if (err) {
+ dev_err(ethsw->dev, "dpsw_disable err %d\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static int ethsw_init(struct fsl_mc_device *sw_dev)
+{
+ struct device *dev = &sw_dev->dev;
+ struct ethsw_core *ethsw = dev_get_drvdata(dev);
+ u16 version_major, version_minor, i;
+ struct dpsw_stp_cfg stp_cfg;
+ int err;
+
+ ethsw->dev_id = sw_dev->obj_desc.id;
+
+ err = dpsw_open(ethsw->mc_io, 0, ethsw->dev_id, ðsw->dpsw_handle);
+ if (err) {
+ dev_err(dev, "dpsw_open err %d\n", err);
+ return err;
+ }
+
+ err = dpsw_get_attributes(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ ðsw->sw_attr);
+ if (err) {
+ dev_err(dev, "dpsw_get_attributes err %d\n", err);
+ goto err_close;
+ }
+
+ err = dpsw_get_api_version(ethsw->mc_io, 0,
+ &version_major,
+ &version_minor);
+ if (err) {
+ dev_err(dev, "dpsw_get_api_version err %d\n", err);
+ goto err_close;
+ }
+
+ /* Minimum supported DPSW version check */
+ if (version_major < DPSW_MIN_VER_MAJOR ||
+ (version_major == DPSW_MIN_VER_MAJOR &&
+ version_minor < DPSW_MIN_VER_MINOR)) {
+ dev_err(dev, "DPSW version %d:%d not supported. Use %d.%d or greater.\n",
+ version_major,
+ version_minor,
+ DPSW_MIN_VER_MAJOR, DPSW_MIN_VER_MINOR);
+ err = -ENOTSUPP;
+ goto err_close;
+ }
+
+ err = dpsw_reset(ethsw->mc_io, 0, ethsw->dpsw_handle);
+ if (err) {
+ dev_err(dev, "dpsw_reset err %d\n", err);
+ goto err_close;
+ }
+
+ err = dpsw_fdb_set_learning_mode(ethsw->mc_io, 0, ethsw->dpsw_handle, 0,
+ DPSW_FDB_LEARNING_MODE_HW);
+ if (err) {
+ dev_err(dev, "dpsw_fdb_set_learning_mode err %d\n", err);
+ goto err_close;
+ }
+
+ stp_cfg.vlan_id = DEFAULT_VLAN_ID;
+ stp_cfg.state = DPSW_STP_STATE_FORWARDING;
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ err = dpsw_if_set_stp(ethsw->mc_io, 0, ethsw->dpsw_handle, i,
+ &stp_cfg);
+ if (err) {
+ dev_err(dev, "dpsw_if_set_stp err %d for port %d\n",
+ err, i);
+ goto err_close;
+ }
+
+ err = dpsw_if_set_broadcast(ethsw->mc_io, 0,
+ ethsw->dpsw_handle, i, 1);
+ if (err) {
+ dev_err(dev,
+ "dpsw_if_set_broadcast err %d for port %d\n",
+ err, i);
+ goto err_close;
+ }
+ }
+
+ ethsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+ "ethsw");
+ if (!ethsw_owq) {
+ err = -ENOMEM;
+ goto err_close;
+ }
+
+ err = ethsw_register_notifier(dev);
+ if (err)
+ goto err_destroy_ordered_workqueue;
+
+ return 0;
+
+err_destroy_ordered_workqueue:
+ destroy_workqueue(ethsw_owq);
+
+err_close:
+ dpsw_close(ethsw->mc_io, 0, ethsw->dpsw_handle);
+ return err;
+}
+
+static int ethsw_port_init(struct ethsw_port_priv *port_priv, u16 port)
+{
+ const char def_mcast[ETH_ALEN] = {0x01, 0x00, 0x5e, 0x00, 0x00, 0x01};
+ struct net_device *netdev = port_priv->netdev;
+ struct ethsw_core *ethsw = port_priv->ethsw_data;
+ struct dpsw_tci_cfg tci_cfg = {0};
+ struct dpsw_vlan_if_cfg vcfg;
+ int err;
+
+ /* Switch starts with all ports configured to VLAN 1. Need to
+ * remove this setting to allow configuration at bridge join
+ */
+ vcfg.num_ifs = 1;
+ vcfg.if_id[0] = port_priv->idx;
+
+ err = dpsw_vlan_remove_if_untagged(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DEFAULT_VLAN_ID, &vcfg);
+ if (err) {
+ netdev_err(netdev, "dpsw_vlan_remove_if_untagged err %d\n",
+ err);
+ return err;
+ }
+
+ err = dpsw_if_set_tci(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ port_priv->idx, &tci_cfg);
+ if (err) {
+ netdev_err(netdev, "dpsw_if_set_tci err %d\n", err);
+ return err;
+ }
+
+ err = dpsw_vlan_remove_if(ethsw->mc_io, 0, ethsw->dpsw_handle,
+ DEFAULT_VLAN_ID, &vcfg);
+ if (err) {
+ netdev_err(netdev, "dpsw_vlan_remove_if err %d\n", err);
+ return err;
+ }
+
+ err = ethsw_port_fdb_add_mc(port_priv, def_mcast);
+
+ return err;
+}
+
+static void ethsw_takedown(struct fsl_mc_device *sw_dev)
+{
+ struct device *dev = &sw_dev->dev;
+ struct ethsw_core *ethsw = dev_get_drvdata(dev);
+ int err;
+
+ err = unregister_switchdev_notifier(&port_switchdev_nb);
+ if (err)
+ dev_err(dev,
+ "Failed to unregister switchdev notifier (%d)\n", err);
+
+ err = unregister_netdevice_notifier(&port_nb);
+ if (err)
+ dev_err(dev,
+ "Failed to unregister netdev notifier (%d)\n", err);
+
+ err = dpsw_close(ethsw->mc_io, 0, ethsw->dpsw_handle);
+ if (err)
+ dev_warn(dev, "dpsw_close err %d\n", err);
+}
+
+static int ethsw_remove(struct fsl_mc_device *sw_dev)
+{
+ struct ethsw_port_priv *port_priv;
+ struct ethsw_core *ethsw;
+ struct device *dev;
+ int i;
+
+ dev = &sw_dev->dev;
+ ethsw = dev_get_drvdata(dev);
+
+ ethsw_teardown_irqs(sw_dev);
+
+ rtnl_lock();
+ ethsw_stop(ethsw);
+ rtnl_unlock();
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ port_priv = ethsw->ports[i];
+ unregister_netdev(port_priv->netdev);
+ free_netdev(port_priv->netdev);
+ }
+ kfree(ethsw->ports);
+
+ ethsw_takedown(sw_dev);
+ fsl_mc_portal_free(ethsw->mc_io);
+
+ kfree(ethsw);
+
+ dev_set_drvdata(dev, NULL);
+
+ return 0;
+}
+
+static int ethsw_probe_port(struct ethsw_core *ethsw, u16 port_idx)
+{
+ struct ethsw_port_priv *port_priv;
+ struct device *dev = ethsw->dev;
+ struct net_device *port_netdev;
+ int err;
+
+ port_netdev = alloc_etherdev(sizeof(struct ethsw_port_priv));
+ if (!port_netdev) {
+ dev_err(dev, "alloc_etherdev error\n");
+ return -ENOMEM;
+ }
+
+ port_priv = netdev_priv(port_netdev);
+ port_priv->netdev = port_netdev;
+ port_priv->ethsw_data = ethsw;
+
+ port_priv->idx = port_idx;
+ port_priv->stp_state = BR_STATE_FORWARDING;
+
+ /* Flooding is implicitly enabled */
+ port_priv->flood = true;
+
+ SET_NETDEV_DEV(port_netdev, dev);
+ port_netdev->netdev_ops = ðsw_port_ops;
+ port_netdev->switchdev_ops = ðsw_port_switchdev_ops;
+
+ /* Set MTU limits */
+ port_netdev->min_mtu = ETH_MIN_MTU;
+ port_netdev->max_mtu = ETHSW_MAX_FRAME_LENGTH;
+
+ err = register_netdev(port_netdev);
+ if (err < 0) {
+ dev_err(dev, "register_netdev error %d\n", err);
+ free_netdev(port_netdev);
+ return err;
+ }
+
+ ethsw->ports[port_idx] = port_priv;
+
+ return ethsw_port_init(port_priv, port_idx);
+}
+
+static int ethsw_probe(struct fsl_mc_device *sw_dev)
+{
+ struct device *dev = &sw_dev->dev;
+ struct ethsw_core *ethsw;
+ int err;
+ u16 i, j;
+
+ /* Allocate switch core*/
+ ethsw = kzalloc(sizeof(*ethsw), GFP_KERNEL);
+
+ if (!ethsw)
+ return -ENOMEM;
+
+ ethsw->dev = dev;
+ dev_set_drvdata(dev, ethsw);
+
+ err = fsl_mc_portal_allocate(sw_dev, 0, ðsw->mc_io);
+ if (err) {
+ dev_err(dev, "fsl_mc_portal_allocate err %d\n", err);
+ goto err_free_drvdata;
+ }
+
+ err = ethsw_init(sw_dev);
+ if (err)
+ goto err_free_cmdport;
+
+ /* DEFAULT_VLAN_ID is implicitly configured on the switch */
+ ethsw->vlans[DEFAULT_VLAN_ID] = ETHSW_VLAN_MEMBER;
+
+ /* Learning is implicitly enabled */
+ ethsw->learning = true;
+
+ ethsw->ports = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->ports),
+ GFP_KERNEL);
+ if (!(ethsw->ports)) {
+ err = -ENOMEM;
+ goto err_takedown;
+ }
+
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ err = ethsw_probe_port(ethsw, i);
+ if (err) {
+ /* Cleanup previous ports only */
+ for (j = 0; j < i; j++) {
+ unregister_netdev(ethsw->ports[j]->netdev);
+ free_netdev(ethsw->ports[j]->netdev);
+ }
+ goto err_takedown;
+ }
+ }
+
+ /* Switch starts up enabled */
+ rtnl_lock();
+ err = ethsw_open(ethsw);
+ rtnl_unlock();
+ if (err)
+ goto err_free_ports;
+
+ /* Setup IRQs */
+ err = ethsw_setup_irqs(sw_dev);
+ if (err)
+ goto err_stop;
+
+ dev_info(dev, "probed %d port switch\n", ethsw->sw_attr.num_ifs);
+ return 0;
+
+err_stop:
+ rtnl_lock();
+ ethsw_stop(ethsw);
+ rtnl_unlock();
+
+err_free_ports:
+ for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+ unregister_netdev(ethsw->ports[i]->netdev);
+ free_netdev(ethsw->ports[i]->netdev);
+ }
+ kfree(ethsw->ports);
+
+err_takedown:
+ ethsw_takedown(sw_dev);
+
+err_free_cmdport:
+ fsl_mc_portal_free(ethsw->mc_io);
+
+err_free_drvdata:
+ kfree(ethsw);
+ dev_set_drvdata(dev, NULL);
+
+ return err;
+}
+
+static const struct fsl_mc_device_id ethsw_match_id_table[] = {
+ {
+ .vendor = FSL_MC_VENDOR_FREESCALE,
+ .obj_type = "dpsw",
+ },
+ { .vendor = 0x0 }
+};
+MODULE_DEVICE_TABLE(fslmc, ethsw_match_id_table);
+
+static struct fsl_mc_driver eth_sw_drv = {
+ .driver = {
+ .name = KBUILD_MODNAME,
+ .owner = THIS_MODULE,
+ },
+ .probe = ethsw_probe,
+ .remove = ethsw_remove,
+ .match_id_table = ethsw_match_id_table
+};
+
+module_fsl_mc_driver(eth_sw_drv);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("DPAA2 Ethernet Switch Driver");
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.h b/drivers/staging/fsl-dpaa2/ethsw/ethsw.h
new file mode 100644
index 0000000..8c1d645
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.h
@@ -0,0 +1,88 @@
+/* Copyright 2014-2017 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __ETHSW_H
+#define __ETHSW_H
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
+#include <uapi/linux/if_bridge.h>
+#include <net/switchdev.h>
+#include <linux/if_bridge.h>
+
+#include "dpsw.h"
+
+/* Number of IRQs supported */
+#define DPSW_IRQ_NUM 2
+
+#define ETHSW_VLAN_MEMBER 1
+#define ETHSW_VLAN_UNTAGGED 2
+#define ETHSW_VLAN_PVID 4
+#define ETHSW_VLAN_GLOBAL 8
+
+/* Maximum Frame Length supported by HW (currently 10k) */
+#define DPAA2_MFL (10 * 1024)
+#define ETHSW_MAX_FRAME_LENGTH (DPAA2_MFL - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define ETHSW_L2_MAX_FRM(mtu) ((mtu) + VLAN_ETH_HLEN + ETH_FCS_LEN)
+
+struct ethsw_core;
+
+/* Per port private data */
+struct ethsw_port_priv {
+ struct net_device *netdev;
+ u16 idx;
+ struct ethsw_core *ethsw_data;
+ u8 link_state;
+ u8 stp_state;
+ bool flood;
+
+ u8 vlans[VLAN_VID_MASK + 1];
+ u16 pvid;
+};
+
+/* Switch data */
+struct ethsw_core {
+ struct device *dev;
+ struct fsl_mc_io *mc_io;
+ u16 dpsw_handle;
+ struct dpsw_attr sw_attr;
+ int dev_id;
+ struct ethsw_port_priv **ports;
+
+ u8 vlans[VLAN_VID_MASK + 1];
+ bool learning;
+};
+
+#endif /* __ETHSW_H */
--
1.9.1
^ permalink raw reply related
* [RESEND PATCH 3/6] staging: fsl-dpaa2/ethsw: Add ethtool support
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, arnd, netdev, alexandru.marginean, linux-kernel, agraf,
stuyoder, bogdan.purcareata, laurentiu.tudor
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Add driver information, link details and hardware statistics to be
reported via ethtool -S.
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
drivers/staging/fsl-dpaa2/ethsw/Makefile | 2 +-
drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h | 13 ++
drivers/staging/fsl-dpaa2/ethsw/dpsw.c | 32 ++++
drivers/staging/fsl-dpaa2/ethsw/dpsw.h | 32 ++++
drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c | 207 ++++++++++++++++++++++++
drivers/staging/fsl-dpaa2/ethsw/ethsw.c | 3 +
drivers/staging/fsl-dpaa2/ethsw/ethsw.h | 3 +
7 files changed, 291 insertions(+), 1 deletion(-)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
diff --git a/drivers/staging/fsl-dpaa2/ethsw/Makefile b/drivers/staging/fsl-dpaa2/ethsw/Makefile
index a6d72d1..de92cd9 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/Makefile
+++ b/drivers/staging/fsl-dpaa2/ethsw/Makefile
@@ -4,4 +4,4 @@
obj-$(CONFIG_FSL_DPAA2_ETHSW) += dpaa2-ethsw.o
-dpaa2-ethsw-objs := ethsw.o dpsw.o
+dpaa2-ethsw-objs := ethsw.o ethsw-ethtool.o dpsw.o
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h b/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
index ddfd820..06b71122 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw-cmd.h
@@ -74,6 +74,8 @@
#define DPSW_CMDID_IF_SET_FLOODING DPSW_CMD_ID(0x047)
#define DPSW_CMDID_IF_SET_BROADCAST DPSW_CMD_ID(0x048)
+#define DPSW_CMDID_IF_SET_LINK_CFG DPSW_CMD_ID(0x04C)
+
#define DPSW_CMDID_VLAN_ADD DPSW_CMD_ID(0x060)
#define DPSW_CMDID_VLAN_ADD_IF DPSW_CMD_ID(0x061)
#define DPSW_CMDID_VLAN_ADD_IF_UNTAGGED DPSW_CMD_ID(0x062)
@@ -262,6 +264,17 @@ struct dpsw_cmd_if_set_max_frame_length {
__le16 frame_length;
};
+struct dpsw_cmd_if_set_link_cfg {
+ /* cmd word 0 */
+ __le16 if_id;
+ u8 pad[6];
+ /* cmd word 1 */
+ __le32 rate;
+ __le32 pad1;
+ /* cmd word 2 */
+ __le64 options;
+};
+
struct dpsw_cmd_if_get_link_state {
__le16 if_id;
};
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw.c b/drivers/staging/fsl-dpaa2/ethsw/dpsw.c
index f36b92b..601172a 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/dpsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw.c
@@ -383,6 +383,38 @@ int dpsw_get_attributes(struct fsl_mc_io *mc_io,
}
/**
+ * dpsw_if_set_link_cfg() - Set the link configuration.
+ * @mc_io: Pointer to MC portal's I/O object
+ * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token: Token of DPSW object
+ * @if_id: Interface id
+ * @cfg: Link configuration
+ *
+ * Return: '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_link_cfg(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ struct dpsw_link_cfg *cfg)
+{
+ struct mc_command cmd = { 0 };
+ struct dpsw_cmd_if_set_link_cfg *cmd_params;
+
+ /* prepare command */
+ cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_LINK_CFG,
+ cmd_flags,
+ token);
+ cmd_params = (struct dpsw_cmd_if_set_link_cfg *)cmd.params;
+ cmd_params->if_id = cpu_to_le16(if_id);
+ cmd_params->rate = cpu_to_le32(cfg->rate);
+ cmd_params->options = cpu_to_le64(cfg->options);
+
+ /* send command to mc*/
+ return mc_send_command(mc_io, &cmd);
+}
+
+/**
* dpsw_if_get_link_state - Return the link state
* @mc_io: Pointer to MC portal's I/O object
* @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_'
diff --git a/drivers/staging/fsl-dpaa2/ethsw/dpsw.h b/drivers/staging/fsl-dpaa2/ethsw/dpsw.h
index e9c2906..5feadc2 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/dpsw.h
+++ b/drivers/staging/fsl-dpaa2/ethsw/dpsw.h
@@ -245,6 +245,38 @@ enum dpsw_action {
};
/**
+ * Enable auto-negotiation
+ */
+#define DPSW_LINK_OPT_AUTONEG 0x0000000000000001ULL
+/**
+ * Enable half-duplex mode
+ */
+#define DPSW_LINK_OPT_HALF_DUPLEX 0x0000000000000002ULL
+/**
+ * Enable pause frames
+ */
+#define DPSW_LINK_OPT_PAUSE 0x0000000000000004ULL
+/**
+ * Enable a-symmetric pause frames
+ */
+#define DPSW_LINK_OPT_ASYM_PAUSE 0x0000000000000008ULL
+
+/**
+ * struct dpsw_link_cfg - Structure representing DPSW link configuration
+ * @rate: Rate
+ * @options: Mask of available options; use 'DPSW_LINK_OPT_<X>' values
+ */
+struct dpsw_link_cfg {
+ u32 rate;
+ u64 options;
+};
+
+int dpsw_if_set_link_cfg(struct fsl_mc_io *mc_io,
+ u32 cmd_flags,
+ u16 token,
+ u16 if_id,
+ struct dpsw_link_cfg *cfg);
+/**
* struct dpsw_link_state - Structure representing DPSW link state
* @rate: Rate
* @options: Mask of available options; use 'DPSW_LINK_OPT_<X>' values
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
new file mode 100644
index 0000000..dcd49d2
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw-ethtool.c
@@ -0,0 +1,207 @@
+/* Copyright 2014-2016 Freescale Semiconductor Inc.
+ * Copyright 2017 NXP
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of the above-listed copyright holders nor the
+ * names of any contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "ethsw.h"
+
+static struct {
+ enum dpsw_counter id;
+ char name[ETH_GSTRING_LEN];
+} ethsw_ethtool_counters[] = {
+ {DPSW_CNT_ING_FRAME, "rx frames"},
+ {DPSW_CNT_ING_BYTE, "rx bytes"},
+ {DPSW_CNT_ING_FLTR_FRAME, "rx filtered frames"},
+ {DPSW_CNT_ING_FRAME_DISCARD, "rx discarded frames"},
+ {DPSW_CNT_ING_BCAST_FRAME, "rx b-cast frames"},
+ {DPSW_CNT_ING_BCAST_BYTES, "rx b-cast bytes"},
+ {DPSW_CNT_ING_MCAST_FRAME, "rx m-cast frames"},
+ {DPSW_CNT_ING_MCAST_BYTE, "rx m-cast bytes"},
+ {DPSW_CNT_EGR_FRAME, "tx frames"},
+ {DPSW_CNT_EGR_BYTE, "tx bytes"},
+ {DPSW_CNT_EGR_FRAME_DISCARD, "tx discarded frames"},
+
+};
+
+#define ETHSW_NUM_COUNTERS ARRAY_SIZE(ethsw_ethtool_counters)
+
+static void ethsw_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ u16 version_major, version_minor;
+ int err;
+
+ strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, ethsw_drv_version, sizeof(drvinfo->version));
+
+ err = dpsw_get_api_version(port_priv->ethsw_data->mc_io, 0,
+ &version_major,
+ &version_minor);
+ if (err)
+ strlcpy(drvinfo->fw_version, "N/A",
+ sizeof(drvinfo->fw_version));
+ else
+ snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+ "%u.%u", version_major, version_minor);
+
+ strlcpy(drvinfo->bus_info, dev_name(netdev->dev.parent->parent),
+ sizeof(drvinfo->bus_info));
+}
+
+static int
+ethsw_get_link_ksettings(struct net_device *netdev,
+ struct ethtool_link_ksettings *link_ksettings)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ struct dpsw_link_state state = {0};
+ int err = 0;
+
+ err = dpsw_if_get_link_state(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ &state);
+ if (err) {
+ netdev_err(netdev, "ERROR %d getting link state", err);
+ goto out;
+ }
+
+ /* At the moment, we have no way of interrogating the DPMAC
+ * from the DPSW side or there may not exist a DPMAC at all.
+ * Report only autoneg state, duplexity and speed.
+ */
+ if (state.options & DPSW_LINK_OPT_AUTONEG)
+ link_ksettings->base.autoneg = AUTONEG_ENABLE;
+ if (!(state.options & DPSW_LINK_OPT_HALF_DUPLEX))
+ link_ksettings->base.duplex = DUPLEX_FULL;
+ link_ksettings->base.speed = state.rate;
+
+out:
+ return err;
+}
+
+static int
+ethsw_set_link_ksettings(struct net_device *netdev,
+ const struct ethtool_link_ksettings *link_ksettings)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ struct dpsw_link_cfg cfg = {0};
+ int err = 0;
+
+ netdev_dbg(netdev, "Setting link parameters...");
+
+ /* Due to a temporary MC limitation, the DPSW port must be down
+ * in order to be able to change link settings. Taking steps to let
+ * the user know that.
+ */
+ if (netif_running(netdev)) {
+ netdev_info(netdev, "Sorry, interface must be brought down first.\n");
+ return -EACCES;
+ }
+
+ cfg.rate = link_ksettings->base.speed;
+ if (link_ksettings->base.autoneg == AUTONEG_ENABLE)
+ cfg.options |= DPSW_LINK_OPT_AUTONEG;
+ else
+ cfg.options &= ~DPSW_LINK_OPT_AUTONEG;
+ if (link_ksettings->base.duplex == DUPLEX_HALF)
+ cfg.options |= DPSW_LINK_OPT_HALF_DUPLEX;
+ else
+ cfg.options &= ~DPSW_LINK_OPT_HALF_DUPLEX;
+
+ err = dpsw_if_set_link_cfg(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ &cfg);
+ if (err)
+ /* ethtool will be loud enough if we return an error; no point
+ * in putting our own error message on the console by default
+ */
+ netdev_dbg(netdev, "ERROR %d setting link cfg", err);
+
+ return err;
+}
+
+static int ethsw_ethtool_get_sset_count(struct net_device *dev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return ETHSW_NUM_COUNTERS;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static void ethsw_ethtool_get_strings(struct net_device *netdev,
+ u32 stringset, u8 *data)
+{
+ int i;
+
+ switch (stringset) {
+ case ETH_SS_STATS:
+ for (i = 0; i < ETHSW_NUM_COUNTERS; i++)
+ memcpy(data + i * ETH_GSTRING_LEN,
+ ethsw_ethtool_counters[i].name, ETH_GSTRING_LEN);
+ break;
+ }
+}
+
+static void ethsw_ethtool_get_stats(struct net_device *netdev,
+ struct ethtool_stats *stats,
+ u64 *data)
+{
+ struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+ int i, err;
+
+ memset(data, 0,
+ sizeof(u64) * ETHSW_NUM_COUNTERS);
+
+ for (i = 0; i < ETHSW_NUM_COUNTERS; i++) {
+ err = dpsw_if_get_counter(port_priv->ethsw_data->mc_io, 0,
+ port_priv->ethsw_data->dpsw_handle,
+ port_priv->idx,
+ ethsw_ethtool_counters[i].id,
+ &data[i]);
+ if (err)
+ netdev_err(netdev, "dpsw_if_get_counter[%s] err %d\n",
+ ethsw_ethtool_counters[i].name, err);
+ }
+}
+
+const struct ethtool_ops ethsw_port_ethtool_ops = {
+ .get_drvinfo = ethsw_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+ .get_link_ksettings = ethsw_get_link_ksettings,
+ .set_link_ksettings = ethsw_set_link_ksettings,
+ .get_strings = ethsw_ethtool_get_strings,
+ .get_ethtool_stats = ethsw_ethtool_get_stats,
+ .get_sset_count = ethsw_ethtool_get_sset_count,
+};
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
index ae86078..12bf88a 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c
@@ -44,6 +44,8 @@
static struct workqueue_struct *ethsw_owq;
+const char ethsw_drv_version[] = "0.1";
+
/* Minimal supported DPSW version */
#define DPSW_MIN_VER_MAJOR 8
#define DPSW_MIN_VER_MINOR 0
@@ -1389,6 +1391,7 @@ static int ethsw_probe_port(struct ethsw_core *ethsw, u16 port_idx)
SET_NETDEV_DEV(port_netdev, dev);
port_netdev->netdev_ops = ðsw_port_ops;
+ port_netdev->ethtool_ops = ðsw_port_ethtool_ops;
port_netdev->switchdev_ops = ðsw_port_switchdev_ops;
/* Set MTU limits */
diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.h b/drivers/staging/fsl-dpaa2/ethsw/ethsw.h
index 8c1d645..ba53cc5 100644
--- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.h
+++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.h
@@ -57,6 +57,9 @@
#define ETHSW_MAX_FRAME_LENGTH (DPAA2_MFL - VLAN_ETH_HLEN - ETH_FCS_LEN)
#define ETHSW_L2_MAX_FRM(mtu) ((mtu) + VLAN_ETH_HLEN + ETH_FCS_LEN)
+extern const char ethsw_drv_version[];
+extern const struct ethtool_ops ethsw_port_ethtool_ops;
+
struct ethsw_core;
/* Per port private data */
--
1.9.1
^ permalink raw reply related
* [RESEND PATCH 4/6] staging: fsl-dpaa2/ethsw: Add maintainer for Ethernet Switch driver
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, linux-kernel, netdev, agraf, arnd, alexandru.marginean,
bogdan.purcareata, ruxandra.radulescu, laurentiu.tudor, stuyoder
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
MAINTAINERS | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 2281af4..cfd4f74 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4297,6 +4297,12 @@ L: linux-kernel@vger.kernel.org
S: Maintained
F: drivers/staging/fsl-dpaa2/ethernet
+DPAA2 ETHERNET SWITCH DRIVER
+M: Razvan Stefanescu <razvan.stefanescu@nxp.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: drivers/staging/fsl-dpaa2/ethsw
+
DPT_I2O SCSI RAID DRIVER
M: Adaptec OEM Raid Solutions <aacraid@adaptec.com>
L: linux-scsi@vger.kernel.org
--
1.9.1
^ permalink raw reply related
* [RESEND PATCH 5/6] staging: fsl-dpaa2/ethsw: Add README
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, arnd, netdev, alexandru.marginean, linux-kernel, agraf,
stuyoder, bogdan.purcareata, laurentiu.tudor
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Add a README file describing the driver architecture, components and
interfaces.
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
drivers/staging/fsl-dpaa2/ethsw/README | 106 +++++++++++++++++++++++++++++++++
1 file changed, 106 insertions(+)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/README
diff --git a/drivers/staging/fsl-dpaa2/ethsw/README b/drivers/staging/fsl-dpaa2/ethsw/README
new file mode 100644
index 0000000..f6fc07f
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/README
@@ -0,0 +1,106 @@
+DPAA2 Ethernet Switch driver
+============================
+
+This file provides documentation for the DPAA2 Ethernet Switch driver
+
+
+Contents
+========
+ Supported Platforms
+ Architecture Overview
+ Creating an Ethernet Switch
+ Features
+
+
+ Supported Platforms
+===================
+This driver provides networking support for Freescale LS2085A, LS2088A
+DPAA2 SoCs.
+
+
+Architecture Overview
+=====================
+The Ethernet Switch in the DPAA2 architecture consists of several hardware
+resources that provide the functionality. These are allocated and
+configured via the Management Complex (MC) portals. MC abstracts most of
+these resources as DPAA2 objects and exposes ABIs through which they can
+be configured and controlled.
+
+For a more detailed description of the DPAA2 architecture and its object
+abstractions see:
+ drivers/staging/fsl-mc/README.txt
+
+The Ethernet Switch is built on top of a Datapath Switch (DPSW) object.
+
+Configuration interface:
+
+ ---------------------
+ | DPAA2 Switch driver |
+ ---------------------
+ .
+ .
+ ----------
+ | DPSW API |
+ ----------
+ . software
+ ================= . ==============
+ . hardware
+ ---------------------
+ | MC hardware portals |
+ ---------------------
+ .
+ .
+ ------
+ | DPSW |
+ ------
+
+Driver uses the switch device driver model and exposes each switch port as
+a network interface, which can be included in a bridge. Traffic switched
+between ports is offloaded into the hardware. Exposed network interfaces
+are not used for I/O, they are used just for configuration. This
+limitation is going to be addressed in the future.
+
+The DPSW can have ports connected to DPNIs or to PHYs via DPMACs.
+
+
+ [ethA] [ethB] [ethC] [ethD] [ethE] [ethF]
+ : : : : : :
+ : : : : : :
+[eth drv] [eth drv] [ ethsw drv ]
+ : : : : : : kernel
+========================================================================
+ : : : : : : hardware
+ [DPNI] [DPNI] [============= DPSW =================]
+ | | | | | |
+ | ---------- | [DPMAC] [DPMAC]
+ ------------------------------- | |
+ | |
+ [PHY] [PHY]
+
+For a more detailed description of the Ethernet switch device driver model
+see:
+ Documentation/networking/switchdev.txt
+
+Creating an Ethernet Switch
+===========================
+A device is created for the switch objects probed on the MC bus. Each DPSW
+has a number of properties which determine the configuration options and
+associated hardware resources.
+
+A DPSW object (and the other DPAA2 objects needed for a DPAA2 switch) can
+be added to a container on the MC bus in one of two ways: statically,
+through a Datapath Layout Binary file (DPL) that is parsed by MC at boot
+time; or created dynamically at runtime, via the DPAA2 objects APIs.
+
+Features
+========
+Driver configures DPSW to perform hardware switching offload of
+unicast/multicast/broadcast (VLAN tagged or untagged) traffic between its
+ports.
+
+It allows configuration of hardware learning, flooding, multicast groups,
+port VLAN configuration and STP state.
+
+Static entries can be added/removed from the FDB.
+
+Hardware statistics for each port are provided through ethtool -S option.
--
1.9.1
^ permalink raw reply related
* [RESEND PATCH 6/6] staging: fsl-dpaa2/ethsw: Add TODO
From: Razvan Stefanescu @ 2017-09-19 12:45 UTC (permalink / raw)
To: gregkh
Cc: devel, arnd, netdev, alexandru.marginean, linux-kernel, agraf,
stuyoder, bogdan.purcareata, laurentiu.tudor
In-Reply-To: <1505825158-8192-1-git-send-email-razvan.stefanescu@nxp.com>
Add a TODO file describing what needs to be added/changed before the driver
can be moved out of staging.
Signed-off-by: Razvan Stefanescu <razvan.stefanescu@nxp.com>
---
drivers/staging/fsl-dpaa2/ethsw/TODO | 14 ++++++++++++++
1 file changed, 14 insertions(+)
create mode 100644 drivers/staging/fsl-dpaa2/ethsw/TODO
diff --git a/drivers/staging/fsl-dpaa2/ethsw/TODO b/drivers/staging/fsl-dpaa2/ethsw/TODO
new file mode 100644
index 0000000..d3f12c3
--- /dev/null
+++ b/drivers/staging/fsl-dpaa2/ethsw/TODO
@@ -0,0 +1,14 @@
+* Add I/O capabilities on switch port netdevices. This will allow control
+traffic to reach the CPU.
+* Add ACL to redirect control traffic to CPU.
+* Add support for displaying learned FDB entries
+* MC firmware uprev; the DPAA2 objects used by the Ethernet Switch driver
+need to be kept in sync with binary interface changes in MC
+* refine README file
+* cleanup
+
+NOTE: At least first three of the above are required before getting the
+DPAA2 Ethernet Switch driver out of staging. Another requirement is that
+the fsl-mc bus driver is moved to drivers/bus and dpio driver is moved to
+drivers/soc (this is required for I/O).
+
--
1.9.1
^ permalink raw reply related
* Re: [PATCH net-next] net: avoid a full fib lookup when rp_filter is disabled.
From: Paolo Abeni @ 2017-09-19 12:46 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev, David S. Miller, Hannes Frederic Sowa
In-Reply-To: <1505822433.29839.44.camel@edumazet-glaptop3.roam.corp.google.com>
Hi,
On Tue, 2017-09-19 at 05:00 -0700, Eric Dumazet wrote:
> On Tue, 2017-09-19 at 12:46 +0200, Paolo Abeni wrote:
> ..
>
> > Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
> > Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> > ---
> > +/* called under RCU lock */
> > +struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
> > +{
> > + u32 hash = inet_addr_hash(net, addr);
> > + struct in_ifaddr *ifa;
> > +
> > + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
> > + if (ifa->ifa_local == addr &&
> > + net_eq(dev_net(ifa->ifa_dev->dev), net))
> > + return ifa;
> > +
> > + return NULL;
> > +}
> > +
Thank you for reviewing this!
> Any particular reason you do not use this helper to replace the lookup
> in __ip_dev_find() ?
uh, I just missed that opportunity. I'll send a v2, thanks!
Paolo
^ permalink raw reply
* RE: [PATCH net-next 05/12] net: dsa: b53: Use a macro to define I/O operations
From: David Laight @ 2017-09-19 12:53 UTC (permalink / raw)
To: 'Florian Fainelli', netdev@vger.kernel.org
Cc: davem@davemloft.net, andrew@lunn.ch,
vivien.didelot@savoirfairelinux.com
In-Reply-To: <20170918214128.27896-6-f.fainelli@gmail.com>
From: Florian Fainelli
> Sent: 18 September 2017 22:41
> Instead of repeating the same pattern: acquire mutex, read/write, release
> mutex, define a macro: b53_build_op() which takes the type (read|write), I/O
> size, and value (scalar or pointer). This helps with fixing bugs that could
> exit (e.g: missing barrier, lock etc.).
....
> +#define b53_build_op(type, op_size, val_type) \
> +static inline int b53_##type##op_size(struct b53_device *dev, u8 page, \
> + u8 reg, val_type val) \
> +{ \
> + int ret; \
> + \
> + mutex_lock(&dev->reg_mutex); \
> + ret = dev->ops->type##op_size(dev, page, reg, val); \
> + mutex_unlock(&dev->reg_mutex); \
> + \
> + return ret; \
> }
Why separate the 'type' and 'op_size' arguments since they
are always pasted together?
David
^ permalink raw reply
* [PATCH] ipv6_skip_exthdr: use ipv6_authlen for AH hdrlen
From: Xiang Gao @ 2017-09-19 12:59 UTC (permalink / raw)
To: trivial, netdev, davem, kuznet, yoshfuji; +Cc: qasdfgtyuiop
In ipv6_skip_exthdr, the lengh of AH header is computed manually
as (hp->hdrlen+2)<<2. However, in include/linux/ipv6.h, a macro
named ipv6_authlen is already defined for exactly the same job. This
commit replaces the manual computation code with the macro.
---
net/ipv6/exthdrs_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 305e2ed730bf..115d60919f72 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -99,7 +99,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
break;
hdrlen = 8;
} else if (nexthdr == NEXTHDR_AUTH)
- hdrlen = (hp->hdrlen+2)<<2;
+ hdrlen = ipv6_authlen(hp);
else
hdrlen = ipv6_optlen(hp);
--
2.14.1
^ permalink raw reply related
* Re: [RFC net-next 0/5] TSN: Add qdisc-based config interfaces for traffic shapers
From: Henrik Austad @ 2017-09-19 13:14 UTC (permalink / raw)
To: Richard Cochran
Cc: Vinicius Costa Gomes, netdev, jhs, xiyou.wangcong, jiri,
intel-wired-lan, andre.guedes, ivan.briano,
jesus.sanchez-palencia, boon.leong.ong
In-Reply-To: <20170919052244.77umdxuze53t6j22@localhost>
[-- Attachment #1: Type: text/plain, Size: 4710 bytes --]
Hi all,
On Tue, Sep 19, 2017 at 07:22:44AM +0200, Richard Cochran wrote:
> On Mon, Sep 18, 2017 at 04:06:28PM -0700, Vinicius Costa Gomes wrote:
> > That's the point, the application does not need to know that, and asking
> > that would be stupid.
>
> On the contrary, this information is essential to the application.
> Probably you have never seen an actual Ethernet field bus in
> operation? In any case, you are missing the point.
>
> > (And that's another nice point of how 802.1Qbv works, applications do
> > not need to be changed to use it, and I think we should work to achieve
> > this on the Linux side)
>
> Once you start to care about real time performance, then you need to
> consider the applications. This is industrial control, not streaming
> your tunes from your ipod.
Do not underestimate the need for media over TSN. I fully see your point of
real-time systems, but they are not the only valid use-cases for TSN.
> > That being said, that only works for kinds of traffic that maps well to
> > this configuration in advance model, which is the model that the IEEE
> > (see 802.1Qcc) and the AVNU Alliance[1] are pushing for.
>
> Again, you are missing the point of what they aiming for. I have
> looked at a number of production systems, and in each case the
> developers want total control over the transmission, in order to
> reduce latency to an absolute minimum. Typically the data to be sent
> are available only microseconds before the transmission deadline.
>
> Consider OpenAVB on github that people are already using. Take a look
> at simple_talker.c and explain how "applications do not need to be
> changed to use it."
I do not think simple-talker was everintended to be how users of AVB should
be implemented, but as a demonstration of what the protocol could do.
ALSA/V4L2 should supply some interface to this so that you can attach
media-applications to it without the application itself having to be "TSN
aware".
> > [1]
> > http://avnu.org/theory-of-operation-for-tsn-enabled-industrial-systems/
>
> Did you even read this?
>
> [page 24]
>
> As described in section 2, some industrial control systems require
> predictable, very low latency and cycle-to-cycle variation to meet
> hard real-time application requirements. In these systems,
> multiple distributed controllers commonly synchronize their
> sensor/actuator operations with other controllers by scheduling
> these operations in time, typically using a repeating control
> cycle.
> ...
> The gate control mechanism is itself a time-aware PTP application
> operating within a bridge or end station port.
>
> It is an application, not a "god box."
>
> > In short, I see a per-packet transmission time and a per-queue schedule
> > as solutions to different problems.
>
> Well, I can agree with that. For some non real-time applications,
> bandwidth shaping is enough, and your Qdisc idea is sufficient. For
> the really challenging TSN targets (industrial control, automotive),
> your idea of an opaque schedule file won't fly.
Would it make sense to adapt the proposed Qdisc here as well as the
back-o-the-napkin idea in the other thread to to a per-socket queue for
each priority and then sort those sockets based on SO_TXTIME?
TSN operates on a per-StreamID basis, and that should map fairly well to a
per-socket approach I think (let us just assume that an application that
sends TSN traffic will open up a separate socket for each stream.
This should allow a userspace application that is _very_ aware of its
timing constraints to send frames exactly when it needs to as you have
SO_TXTIME available. It would also let applications that basically want a
fine-grained rate control (audio and video comes to mind) to use the same
qdisc.
For those sockets that do not support SO_TXTIME, but still map to a
priority handled by sch_cbs (or whatever it'll end up being called) you can
set the transmit-time to be the time of the last skb in the queue + an
delta which will give you the correct rate (TSN operates on observation
intervals which you can specify via tc when you create the queues).
Then you can have, as you propose in your other series, a hrtimer that is
being called when the next SO_TXTIME enters, grab a skb and move it to the
hw-queue. This should also allow you to keep a sorted per-socket queue
should an application send frames in the wrong order, without having to
rearrange descriptors for the DMA machinery.
If this makes sense, I am more than happy to give it a stab and see how it
goes.
-Henrik
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 181 bytes --]
^ permalink raw reply
* software interrupts close to 100 with 9000 tc filter entries
From: Marco Berizzi @ 2017-09-19 13:28 UTC (permalink / raw)
To: netdev
Hi Folks,
I'm running linux 4.12.10 x86_64 on a Slackware 14.2 64bit
as a simple 4 NIC router. Network throughput processed by
this machine is less than 200Mbit/s
The cpu model is Intel(R) Xeon(R) CPU 5160 @ 3.00GHz with
2GB ram.
I need to blacklist about 9000 single ip addresses.
This is the relevant script to blacklist these ip addresses:
tc qdisc add dev eth0 ingress
tc qdisc add dev eth1 ingress
while read -r line
do
tc filter add dev eth0 parent ffff: protocol ip prio 50 u32 match ip src $line action drop
tc filter add dev eth1 parent ffff: protocol ip prio 50 u32 match ip src $line action drop
done < blacklisted_ip_addresses
After loading these ip addresses, the si (software interrupts)
number shown by top is always close to 100
If I delete the ingress qdisc on both the device, the si
fall down to less than 5
Running the same script with 'only' 700 ip addresses is
flawless.
Kindly I would like to ask if am I doing anything in
a wrong way or if the hardware is too old for this kind
of setup.
I have selected the tc filter setup instead of netfilter
one, because I was reading this from iproute2/doc/actions:
A side effect is that we can now get stateless firewalling to work with tc..
Essentially this is now an alternative to iptables.
I wont go into details of my dislike for iptables at times, but.
scalability is one of the main issues; however, if you need stateful
classification - use netfilter (for now).
Any response are welcome
TIA
Marco
^ permalink raw reply
* Re: [PATCH 2/3] selftests: actually run the various net selftests
From: Josef Bacik @ 2017-09-19 13:34 UTC (permalink / raw)
To: Willem de Bruijn
Cc: josef, Josef Bacik, David S. Miller, linux-kernel,
linux-kselftest, netdev, Shuah Khan, Shuah Khan
In-Reply-To: <09f17145-5f0a-ec61-3dfb-69216eac7133@kernel.org>
On Mon, Sep 18, 2017 at 04:14:41PM -0600, Shuah Khan wrote:
> On 09/18/2017 11:32 AM, josef@toxicpanda.com wrote:
> > From: Josef Bacik <jbacik@fb.com>
> >
> > These self tests are just self contained binaries, they are not run by
> > any of the scripts in the directory. This means they need to be marked
> > with TEST_GEN_PROGS to actually be run, not TEST_GEN_FILES.
> >
> > Signed-off-by: Josef Bacik <jbacik@fb.com>
> > ---
> > tools/testing/selftests/net/Makefile | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
> > index 3df542c84610..45a4e77a47c4 100644
> > --- a/tools/testing/selftests/net/Makefile
> > +++ b/tools/testing/selftests/net/Makefile
> > @@ -6,8 +6,8 @@ CFLAGS += -I../../../../usr/include/
> > TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
> > TEST_GEN_FILES = socket
> > TEST_GEN_FILES += psock_fanout psock_tpacket
> > -TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
> > -TEST_GEN_FILES += reuseport_dualstack msg_zerocopy reuseaddr_conflict
> > +TEST_GEN_PROGS += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
> > +TEST_GEN_PROGS += reuseport_dualstack msg_zerocopy reuseaddr_conflict
>
> Hmm. I see msg_zerocopy.sh for running msg_zerocopy. msg_zerocopy should
> still stay in TEST_GEN_FILES and msg_zerocopy.sh needs to be added to
> TEST_PROGS so it runs.
>
Actually the shell script requires arguments, it doesn't just run the test.
I'll fix this to just omit the test for now as it's not setup to run properly.
Willem, could you follow up with a patch so that the zero copy test is run
properly the way you envision it running? You need to make sure that
make -C tools/testing/selftests TARGETS=net run_tests
actually runs your zero copy test the way you expect it to, otherwise it's just
sitting there collecting dust. Thanks,
Josef
^ permalink raw reply
* [PATCH net v2] l2tp: fix race condition in l2tp_tunnel_delete
From: Sabrina Dubroca @ 2017-09-19 13:40 UTC (permalink / raw)
To: netdev; +Cc: Sabrina Dubroca, Guillaume Nault, Xin Long, Tom Parkin
If we try to delete the same tunnel twice, the first delete operation
does a lookup (l2tp_tunnel_get), finds the tunnel, calls
l2tp_tunnel_delete, which queues it for deletion by
l2tp_tunnel_del_work.
The second delete operation also finds the tunnel and calls
l2tp_tunnel_delete. If the workqueue has already fired and started
running l2tp_tunnel_del_work, then l2tp_tunnel_delete will queue the
same tunnel a second time, and try to free the socket again.
Add a dead flag to prevent firing the workqueue twice. Then we can
remove the check of queue_work's result that was meant to prevent that
race but doesn't.
Also check the flag in the tunnel lookup functions, to avoid returning a
tunnel that is already scheduled for destruction.
Reproducer:
ip l2tp add tunnel tunnel_id 3000 peer_tunnel_id 4000 local 192.168.0.2 remote 192.168.0.1 encap udp udp_sport 5000 udp_dport 6000
ip l2tp add session name l2tp1 tunnel_id 3000 session_id 1000 peer_session_id 2000
ip link set l2tp1 up
ip l2tp del tunnel tunnel_id 3000
ip l2tp del tunnel tunnel_id 3000
Fixes: f8ccac0e4493 ("l2tp: put tunnel socket release on a workqueue")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
---
v2: as Tom Parkin explained, we can't remove the tunnel from the
per-net list from netlink. v2 uses only a dead flag, and adds
corresponding checks during lookups
net/l2tp/l2tp_core.c | 18 +++++++++---------
net/l2tp/l2tp_core.h | 5 ++++-
2 files changed, 13 insertions(+), 10 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ee485df73ccd..3891f0260f2b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -203,7 +203,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id) {
+ if (tunnel->tunnel_id == tunnel_id &&
+ !test_bit(0, &tunnel->dead)) {
l2tp_tunnel_inc_refcount(tunnel);
rcu_read_unlock_bh();
@@ -390,7 +391,8 @@ struct l2tp_tunnel *l2tp_tunnel_find(const struct net *net, u32 tunnel_id)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id) {
+ if (tunnel->tunnel_id == tunnel_id &&
+ !test_bit(0, &tunnel->dead)) {
rcu_read_unlock_bh();
return tunnel;
}
@@ -409,7 +411,7 @@ struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth)
rcu_read_lock_bh();
list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth) {
+ if (++count > nth && !test_bit(0, &tunnel->dead)) {
rcu_read_unlock_bh();
return tunnel;
}
@@ -1685,14 +1687,12 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
/* This function is used by the netlink TUNNEL_DELETE command.
*/
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
{
- l2tp_tunnel_inc_refcount(tunnel);
- if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
- l2tp_tunnel_dec_refcount(tunnel);
- return 1;
+ if (!test_and_set_bit(0, &tunnel->dead)) {
+ l2tp_tunnel_inc_refcount(tunnel);
+ queue_work(l2tp_wq, &tunnel->del_work);
}
- return 0;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a305e0c5925a..deda869504d0 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -160,6 +160,9 @@ struct l2tp_tunnel_cfg {
struct l2tp_tunnel {
int magic; /* Should be L2TP_TUNNEL_MAGIC */
+
+ unsigned long dead;
+
struct rcu_head rcu;
rwlock_t hlist_lock; /* protect session_hlist */
bool acpt_newsess; /* Indicates whether this
@@ -254,7 +257,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
struct l2tp_tunnel **tunnelp);
void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
-int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
+void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
struct l2tp_session *l2tp_session_create(int priv_size,
struct l2tp_tunnel *tunnel,
u32 session_id, u32 peer_session_id,
--
2.14.1
^ permalink raw reply related
* [net-next,RESEND] igb: add function to get maximum RSS queues
From: Zhang Shengju @ 2017-09-19 13:40 UTC (permalink / raw)
To: jeffrey.t.kirsher, intel-wired-lan, netdev
This patch adds a new function igb_get_max_rss_queues() to get maximum
RSS queues, this will reduce duplicate code and facilitate future
maintenance.
Signed-off-by: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
---
drivers/net/ethernet/intel/igb/igb.h | 1 +
drivers/net/ethernet/intel/igb/igb_ethtool.c | 32 +---------------------------
drivers/net/ethernet/intel/igb/igb_main.c | 12 +++++++++--
3 files changed, 12 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 06ffb2b..ca94eff 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -684,6 +684,7 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
+unsigned int igb_get_max_rss_queues(struct igb_adapter *);
#ifdef CONFIG_IGB_HWMON
void igb_sysfs_exit(struct igb_adapter *adapter);
int igb_sysfs_init(struct igb_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index d06a8db..606e676 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -3338,37 +3338,7 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
static unsigned int igb_max_channels(struct igb_adapter *adapter)
{
- struct e1000_hw *hw = &adapter->hw;
- unsigned int max_combined = 0;
-
- switch (hw->mac.type) {
- case e1000_i211:
- max_combined = IGB_MAX_RX_QUEUES_I211;
- break;
- case e1000_82575:
- case e1000_i210:
- max_combined = IGB_MAX_RX_QUEUES_82575;
- break;
- case e1000_i350:
- if (!!adapter->vfs_allocated_count) {
- max_combined = 1;
- break;
- }
- /* fall through */
- case e1000_82576:
- if (!!adapter->vfs_allocated_count) {
- max_combined = 2;
- break;
- }
- /* fall through */
- case e1000_82580:
- case e1000_i354:
- default:
- max_combined = IGB_MAX_RX_QUEUES;
- break;
- }
-
- return max_combined;
+ return igb_get_max_rss_queues(adapter);
}
static void igb_get_channels(struct net_device *netdev,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ec62410..e6cc6b5 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3026,10 +3026,10 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
#endif /* CONFIG_PCI_IOV */
}
-static void igb_init_queue_configuration(struct igb_adapter *adapter)
+unsigned int igb_get_max_rss_queues(struct igb_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
- u32 max_rss_queues;
+ unsigned int max_rss_queues;
/* Determine the maximum number of RSS queues supported. */
switch (hw->mac.type) {
@@ -3060,6 +3060,14 @@ static void igb_init_queue_configuration(struct igb_adapter *adapter)
break;
}
+ return max_rss_queues;
+}
+
+static void igb_init_queue_configuration(struct igb_adapter *adapter)
+{
+ u32 max_rss_queues;
+
+ max_rss_queues = igb_get_max_rss_queues(adapter);
adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus());
igb_set_flag_queue_pairs(adapter, max_rss_queues);
--
1.8.3.1
^ permalink raw reply related
* Re: [regression v4.11] 617f01211baf ("8139too: use napi_complete_done()")
From: Eric Dumazet @ 2017-09-19 13:51 UTC (permalink / raw)
To: Ville Syrjälä; +Cc: Eric Dumazet, David S. Miller, netdev, LKML
In-Reply-To: <20170919124503.GO4914@intel.com>
On Tue, 2017-09-19 at 15:45 +0300, Ville Syrjälä wrote:
> On Mon, Sep 18, 2017 at 12:52:15PM -0700, Eric Dumazet wrote:
> > On Mon, Sep 18, 2017 at 12:46 PM, Ville Syrjälä
> > <ville.syrjala@linux.intel.com> wrote:
> >
> > > And five months later I'm still waiting for this patch to land...
> >
> > Sure, while I was on vacation, I received thousands of emails that I
> > simply have not read.
>
> Ah that explains where my previous ping went. Pardon the snarky comment,
> and thanks for taking care of this.
>
No problem, this was my fault not following this bug.
Thanks a lot !
^ permalink raw reply
* [PATCH 1/3][v2] selftest: add a reuseaddr test
From: josef @ 2017-09-19 13:51 UTC (permalink / raw)
To: shuah, davem, netdev, linux-kselftest; +Cc: Josef Bacik
From: Josef Bacik <jbacik@fb.com>
This is to test for a regression introduced by
b9470c27607b ("inet: kill smallest_size and smallest_port")
which introduced a problem with reuseaddr and bind conflicts.
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/reuseaddr_conflict.c | 114 +++++++++++++++++++++++
3 files changed, 116 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/net/reuseaddr_conflict.c
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 9801253e4802..c612d6e38c62 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -6,3 +6,4 @@ reuseport_bpf
reuseport_bpf_cpu
reuseport_bpf_numa
reuseport_dualstack
+reuseaddr_conflict
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index de1f5772b878..3df542c84610 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetl
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket
TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_FILES += reuseport_dualstack msg_zerocopy
+TEST_GEN_FILES += reuseport_dualstack msg_zerocopy reuseaddr_conflict
include ../lib.mk
diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c
new file mode 100644
index 000000000000..7c5b12664b03
--- /dev/null
+++ b/tools/testing/selftests/net/reuseaddr_conflict.c
@@ -0,0 +1,114 @@
+/*
+ * Test for the regression introduced by
+ *
+ * b9470c27607b ("inet: kill smallest_size and smallest_port")
+ *
+ * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb
+ * when we open the ipv6 conterpart, which is what was happening previously.
+ */
+#include <errno.h>
+#include <error.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define PORT 9999
+
+int open_port(int ipv6, int any)
+{
+ int fd = -1;
+ int reuseaddr = 1;
+ int v6only = 1;
+ int addrlen;
+ int ret = -1;
+ struct sockaddr *addr;
+ int family = ipv6 ? AF_INET6 : AF_INET;
+
+ struct sockaddr_in6 addr6 = {
+ .sin6_family = AF_INET6,
+ .sin6_port = htons(PORT),
+ .sin6_addr = in6addr_any
+ };
+ struct sockaddr_in addr4 = {
+ .sin_family = AF_INET,
+ .sin_port = htons(PORT),
+ .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"),
+ };
+
+
+ if (ipv6) {
+ addr = (struct sockaddr*)&addr6;
+ addrlen = sizeof(addr6);
+ } else {
+ addr = (struct sockaddr*)&addr4;
+ addrlen = sizeof(addr4);
+ }
+
+ if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) {
+ perror("socket");
+ goto out;
+ }
+
+ if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only,
+ sizeof(v6only)) < 0) {
+ perror("setsockopt IPV6_V6ONLY");
+ goto out;
+ }
+
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr,
+ sizeof(reuseaddr)) < 0) {
+ perror("setsockopt SO_REUSEADDR");
+ goto out;
+ }
+
+ if (bind(fd, addr, addrlen) < 0) {
+ perror("bind");
+ goto out;
+ }
+
+ if (any)
+ return fd;
+
+ if (listen(fd, 1) < 0) {
+ perror("listen");
+ goto out;
+ }
+ return fd;
+out:
+ close(fd);
+ return ret;
+}
+
+int main(void)
+{
+ int listenfd;
+ int fd1, fd2;
+
+ fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT);
+ listenfd = open_port(0, 0);
+ if (listenfd < 0)
+ error(1, errno, "Couldn't open listen socket");
+ fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+ fd1 = open_port(0, 1);
+ if (fd1 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+ fprintf(stderr, "Opening in6addr_any:%d\n", PORT);
+ fd1 = open_port(1, 1);
+ if (fd1 < 0)
+ error(1, errno, "Couldn't open ipv6 reuseport");
+ fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+ fd2 = open_port(0, 1);
+ if (fd2 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+ close(fd1);
+ fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT);
+ fd1 = open_port(0, 1);
+ if (fd1 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
+ fprintf(stderr, "Success");
+ return 0;
+}
--
2.7.4
^ permalink raw reply related
* [PATCH 2/3][v2] selftests: actually run the various net selftests
From: josef @ 2017-09-19 13:51 UTC (permalink / raw)
To: shuah, davem, netdev, linux-kselftest; +Cc: Josef Bacik
In-Reply-To: <1505829088-1823-1-git-send-email-jbacik@fb.com>
From: Josef Bacik <jbacik@fb.com>
These self tests are just self contained binaries, they are not run by
any of the scripts in the directory. This means they need to be marked
with TEST_GEN_PROGS to actually be run, not TEST_GEN_FILES.
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
v1->v2:
- Moved msg_zerocopy to TEST_GEN_FILES since it's not runnable in it's current
state
tools/testing/selftests/net/Makefile | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3df542c84610..d86bca991f45 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,9 +5,9 @@ CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
TEST_GEN_FILES = socket
-TEST_GEN_FILES += psock_fanout psock_tpacket
-TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_FILES += reuseport_dualstack msg_zerocopy reuseaddr_conflict
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
include ../lib.mk
--
2.7.4
^ permalink raw reply related
* [PATCH 3/3][v2] selftests: silence test output by default
From: josef @ 2017-09-19 13:51 UTC (permalink / raw)
To: shuah, davem, netdev, linux-kselftest; +Cc: Josef Bacik
In-Reply-To: <1505829088-1823-1-git-send-email-jbacik@fb.com>
From: Josef Bacik <jbacik@fb.com>
Some of the networking tests are very noisy and make it impossible to
see if we actually passed the tests as they run. Default to suppressing
the output from any tests run in order to make it easier to track what
failed.
Signed-off-by: Josef Bacik <jbacik@fb.com>
---
v1->v2:
- dump output into /tmp/testname instead of /dev/null
tools/testing/selftests/lib.mk | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 693616651da5..4665463779f5 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -24,7 +24,7 @@ define RUN_TESTS
echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
else \
- cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
+ cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
fi; \
done;
endef
@@ -55,7 +55,7 @@ endif
define EMIT_TESTS
@for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
BASENAME_TEST=`basename $$TEST`; \
- echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+ echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
done;
endef
--
2.7.4
^ permalink raw reply related
* Re: software interrupts close to 100 with 9000 tc filter entries
From: Eric Dumazet @ 2017-09-19 14:01 UTC (permalink / raw)
To: Marco Berizzi; +Cc: netdev
In-Reply-To: <1627070802.486441.1505827738125@mail.libero.it>
On Tue, 2017-09-19 at 15:28 +0200, Marco Berizzi wrote:
> Hi Folks,
>
> I'm running linux 4.12.10 x86_64 on a Slackware 14.2 64bit
> as a simple 4 NIC router. Network throughput processed by
> this machine is less than 200Mbit/s
> The cpu model is Intel(R) Xeon(R) CPU 5160 @ 3.00GHz with
> 2GB ram.
>
> I need to blacklist about 9000 single ip addresses.
> This is the relevant script to blacklist these ip addresses:
>
> tc qdisc add dev eth0 ingress
> tc qdisc add dev eth1 ingress
>
> while read -r line
> do
> tc filter add dev eth0 parent ffff: protocol ip prio 50 u32 match ip src $line action drop
> tc filter add dev eth1 parent ffff: protocol ip prio 50 u32 match ip src $line action drop
> done < blacklisted_ip_addresses
>
> After loading these ip addresses, the si (software interrupts)
> number shown by top is always close to 100
> If I delete the ingress qdisc on both the device, the si
> fall down to less than 5
>
> Running the same script with 'only' 700 ip addresses is
> flawless.
>
> Kindly I would like to ask if am I doing anything in
> a wrong way or if the hardware is too old for this kind
> of setup.
>
> I have selected the tc filter setup instead of netfilter
> one, because I was reading this from iproute2/doc/actions:
>
> A side effect is that we can now get stateless firewalling to work with tc..
> Essentially this is now an alternative to iptables.
> I wont go into details of my dislike for iptables at times, but.
> scalability is one of the main issues; however, if you need stateful
> classification - use netfilter (for now).
>
> Any response are welcome
> TIA
Processing a list of 700 rules per incoming packet is not wise.
Alternatives :
- netfilter with IPSET : This probably can be done with one lookup in a
table. Probably easiest way to setup.
- BPF filter (XDP or TC )
^ permalink raw reply
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