2019-05-27 08:55:01 +02:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
2016-02-16 15:14:42 +01:00
|
|
|
/*
|
|
|
|
|
* drivers/net/ethernet/rocker/rocker.h - Rocker switch device driver
|
|
|
|
|
* Copyright (c) 2014-2016 Jiri Pirko <jiri@mellanox.com>
|
|
|
|
|
* Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#ifndef _ROCKER_H
|
|
|
|
|
#define _ROCKER_H
|
|
|
|
|
|
2016-02-16 15:14:45 +01:00
|
|
|
#include <linux/kernel.h>
|
2016-02-16 15:14:42 +01:00
|
|
|
#include <linux/types.h>
|
2016-02-16 15:14:45 +01:00
|
|
|
#include <linux/netdevice.h>
|
2016-09-26 12:52:32 +02:00
|
|
|
#include <linux/notifier.h>
|
2016-02-16 15:14:45 +01:00
|
|
|
#include <net/neighbour.h>
|
|
|
|
|
#include <net/switchdev.h>
|
2016-02-16 15:14:42 +01:00
|
|
|
|
|
|
|
|
#include "rocker_hw.h"
|
|
|
|
|
|
|
|
|
|
struct rocker_desc_info {
|
|
|
|
|
char *data; /* mapped */
|
|
|
|
|
size_t data_size;
|
|
|
|
|
size_t tlv_size;
|
|
|
|
|
struct rocker_desc *desc;
|
|
|
|
|
dma_addr_t mapaddr;
|
|
|
|
|
};
|
|
|
|
|
|
2016-02-16 15:14:44 +01:00
|
|
|
struct rocker_dma_ring_info {
|
|
|
|
|
size_t size;
|
|
|
|
|
u32 head;
|
|
|
|
|
u32 tail;
|
|
|
|
|
struct rocker_desc *desc; /* mapped */
|
|
|
|
|
dma_addr_t mapaddr;
|
|
|
|
|
struct rocker_desc_info *desc_info;
|
|
|
|
|
unsigned int type;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
struct rocker;
|
|
|
|
|
|
|
|
|
|
struct rocker_port {
|
|
|
|
|
struct net_device *dev;
|
|
|
|
|
struct rocker *rocker;
|
2016-02-16 15:14:45 +01:00
|
|
|
void *wpriv;
|
2016-02-16 15:14:44 +01:00
|
|
|
unsigned int port_number;
|
|
|
|
|
u32 pport;
|
|
|
|
|
struct napi_struct napi_tx;
|
|
|
|
|
struct napi_struct napi_rx;
|
|
|
|
|
struct rocker_dma_ring_info tx_ring;
|
|
|
|
|
struct rocker_dma_ring_info rx_ring;
|
|
|
|
|
};
|
|
|
|
|
|
2016-09-26 12:52:32 +02:00
|
|
|
struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev,
|
|
|
|
|
struct rocker *rocker);
|
|
|
|
|
|
2016-02-16 15:14:45 +01:00
|
|
|
struct rocker_world_ops;
|
|
|
|
|
|
2016-02-16 15:14:44 +01:00
|
|
|
struct rocker {
|
|
|
|
|
struct pci_dev *pdev;
|
|
|
|
|
u8 __iomem *hw_addr;
|
|
|
|
|
struct msix_entry *msix_entries;
|
|
|
|
|
unsigned int port_count;
|
|
|
|
|
struct rocker_port **ports;
|
|
|
|
|
struct {
|
|
|
|
|
u64 id;
|
|
|
|
|
} hw;
|
|
|
|
|
spinlock_t cmd_ring_lock; /* for cmd ring accesses */
|
|
|
|
|
struct rocker_dma_ring_info cmd_ring;
|
|
|
|
|
struct rocker_dma_ring_info event_ring;
|
2016-09-26 12:52:32 +02:00
|
|
|
struct notifier_block fib_nb;
|
2016-02-16 15:14:45 +01:00
|
|
|
struct rocker_world_ops *wops;
|
2016-12-03 16:45:02 +01:00
|
|
|
struct workqueue_struct *rocker_owq;
|
2016-02-16 15:14:45 +01:00
|
|
|
void *wpriv;
|
2016-02-16 15:14:44 +01:00
|
|
|
};
|
|
|
|
|
|
2016-02-16 15:14:50 +01:00
|
|
|
typedef int (*rocker_cmd_prep_cb_t)(const struct rocker_port *rocker_port,
|
|
|
|
|
struct rocker_desc_info *desc_info,
|
|
|
|
|
void *priv);
|
|
|
|
|
|
|
|
|
|
typedef int (*rocker_cmd_proc_cb_t)(const struct rocker_port *rocker_port,
|
|
|
|
|
const struct rocker_desc_info *desc_info,
|
|
|
|
|
void *priv);
|
|
|
|
|
|
|
|
|
|
int rocker_cmd_exec(struct rocker_port *rocker_port, bool nowait,
|
|
|
|
|
rocker_cmd_prep_cb_t prepare, void *prepare_priv,
|
|
|
|
|
rocker_cmd_proc_cb_t process, void *process_priv);
|
|
|
|
|
|
|
|
|
|
int rocker_port_set_learning(struct rocker_port *rocker_port,
|
|
|
|
|
bool learning);
|
|
|
|
|
|
2016-02-16 15:14:45 +01:00
|
|
|
struct rocker_world_ops {
|
|
|
|
|
const char *kind;
|
|
|
|
|
size_t priv_size;
|
|
|
|
|
size_t port_priv_size;
|
|
|
|
|
u8 mode;
|
|
|
|
|
int (*init)(struct rocker *rocker);
|
|
|
|
|
void (*fini)(struct rocker *rocker);
|
|
|
|
|
int (*port_pre_init)(struct rocker_port *rocker_port);
|
|
|
|
|
int (*port_init)(struct rocker_port *rocker_port);
|
|
|
|
|
void (*port_fini)(struct rocker_port *rocker_port);
|
|
|
|
|
void (*port_post_fini)(struct rocker_port *rocker_port);
|
|
|
|
|
int (*port_open)(struct rocker_port *rocker_port);
|
|
|
|
|
void (*port_stop)(struct rocker_port *rocker_port);
|
|
|
|
|
int (*port_attr_stp_state_set)(struct rocker_port *rocker_port,
|
2017-06-08 08:44:25 +02:00
|
|
|
u8 state);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_attr_bridge_flags_set)(struct rocker_port *rocker_port,
|
net: switchdev: remove the transaction structure from port attributes
Since the introduction of the switchdev API, port attributes were
transmitted to drivers for offloading using a two-step transactional
model, with a prepare phase that was supposed to catch all errors, and a
commit phase that was supposed to never fail.
Some classes of failures can never be avoided, like hardware access, or
memory allocation. In the latter case, merely attempting to move the
memory allocation to the preparation phase makes it impossible to avoid
memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused
transaction item queue") which has removed the unused mechanism of
passing on the allocated memory between one phase and another.
It is time we admit that separating the preparation from the commit
phase is something that is best left for the driver to decide, and not
something that should be baked into the API, especially since there are
no switchdev callers that depend on this.
This patch removes the struct switchdev_trans member from switchdev port
attribute notifier structures, and converts drivers to not look at this
member.
In part, this patch contains a revert of my previous commit 2e554a7a5d8a
("net: dsa: propagate switchdev vlan_filtering prepare phase to
drivers").
For the most part, the conversion was trivial except for:
- Rocker's world implementation based on Broadcom OF-DPA had an odd
implementation of ofdpa_port_attr_bridge_flags_set. The conversion was
done mechanically, by pasting the implementation twice, then only
keeping the code that would get executed during prepare phase on top,
then only keeping the code that gets executed during the commit phase
on bottom, then simplifying the resulting code until this was obtained.
- DSA's offloading of STP state, bridge flags, VLAN filtering and
multicast router could be converted right away. But the ageing time
could not, so a shim was introduced and this was left for a further
commit.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek
Reviewed-by: Linus Walleij <linus.walleij@linaro.org> # RTL8366RB
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 02:01:50 +02:00
|
|
|
unsigned long brport_flags);
|
2017-06-08 08:44:24 +02:00
|
|
|
int (*port_attr_bridge_flags_support_get)(const struct rocker_port *
|
|
|
|
|
rocker_port,
|
|
|
|
|
unsigned long *
|
|
|
|
|
p_brport_flags);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_attr_bridge_ageing_time_set)(struct rocker_port *rocker_port,
|
net: switchdev: remove the transaction structure from port attributes
Since the introduction of the switchdev API, port attributes were
transmitted to drivers for offloading using a two-step transactional
model, with a prepare phase that was supposed to catch all errors, and a
commit phase that was supposed to never fail.
Some classes of failures can never be avoided, like hardware access, or
memory allocation. In the latter case, merely attempting to move the
memory allocation to the preparation phase makes it impossible to avoid
memory leaks, since commit 91cf8eceffc1 ("switchdev: Remove unused
transaction item queue") which has removed the unused mechanism of
passing on the allocated memory between one phase and another.
It is time we admit that separating the preparation from the commit
phase is something that is best left for the driver to decide, and not
something that should be baked into the API, especially since there are
no switchdev callers that depend on this.
This patch removes the struct switchdev_trans member from switchdev port
attribute notifier structures, and converts drivers to not look at this
member.
In part, this patch contains a revert of my previous commit 2e554a7a5d8a
("net: dsa: propagate switchdev vlan_filtering prepare phase to
drivers").
For the most part, the conversion was trivial except for:
- Rocker's world implementation based on Broadcom OF-DPA had an odd
implementation of ofdpa_port_attr_bridge_flags_set. The conversion was
done mechanically, by pasting the implementation twice, then only
keeping the code that would get executed during prepare phase on top,
then only keeping the code that gets executed during the commit phase
on bottom, then simplifying the resulting code until this was obtained.
- DSA's offloading of STP state, bridge flags, VLAN filtering and
multicast router could be converted right away. But the ageing time
could not, so a shim was introduced and this was left for a further
commit.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek
Reviewed-by: Linus Walleij <linus.walleij@linaro.org> # RTL8366RB
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 02:01:50 +02:00
|
|
|
u32 ageing_time);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_obj_vlan_add)(struct rocker_port *rocker_port,
|
2017-06-08 08:44:25 +02:00
|
|
|
const struct switchdev_obj_port_vlan *vlan);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_obj_vlan_del)(struct rocker_port *rocker_port,
|
|
|
|
|
const struct switchdev_obj_port_vlan *vlan);
|
|
|
|
|
int (*port_obj_fdb_add)(struct rocker_port *rocker_port,
|
2017-06-08 08:44:25 +02:00
|
|
|
u16 vid, const unsigned char *addr);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_obj_fdb_del)(struct rocker_port *rocker_port,
|
2017-06-08 08:44:25 +02:00
|
|
|
u16 vid, const unsigned char *addr);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_master_linked)(struct rocker_port *rocker_port,
|
net: bridge: switchdev: let drivers inform which bridge ports are offloaded
On reception of an skb, the bridge checks if it was marked as 'already
forwarded in hardware' (checks if skb->offload_fwd_mark == 1), and if it
is, it assigns the source hardware domain of that skb based on the
hardware domain of the ingress port. Then during forwarding, it enforces
that the egress port must have a different hardware domain than the
ingress one (this is done in nbp_switchdev_allowed_egress).
Non-switchdev drivers don't report any physical switch id (neither
through devlink nor .ndo_get_port_parent_id), therefore the bridge
assigns them a hardware domain of 0, and packets coming from them will
always have skb->offload_fwd_mark = 0. So there aren't any restrictions.
Problems appear due to the fact that DSA would like to perform software
fallback for bonding and team interfaces that the physical switch cannot
offload.
+-- br0 ---+
/ / | \
/ / | \
/ | | bond0
/ | | / \
swp0 swp1 swp2 swp3 swp4
There, it is desirable that the presence of swp3 and swp4 under a
non-offloaded LAG does not preclude us from doing hardware bridging
beteen swp0, swp1 and swp2. The bandwidth of the CPU is often times high
enough that software bridging between {swp0,swp1,swp2} and bond0 is not
impractical.
But this creates an impossible paradox given the current way in which
port hardware domains are assigned. When the driver receives a packet
from swp0 (say, due to flooding), it must set skb->offload_fwd_mark to
something.
- If we set it to 0, then the bridge will forward it towards swp1, swp2
and bond0. But the switch has already forwarded it towards swp1 and
swp2 (not to bond0, remember, that isn't offloaded, so as far as the
switch is concerned, ports swp3 and swp4 are not looking up the FDB,
and the entire bond0 is a destination that is strictly behind the
CPU). But we don't want duplicated traffic towards swp1 and swp2, so
it's not ok to set skb->offload_fwd_mark = 0.
- If we set it to 1, then the bridge will not forward the skb towards
the ports with the same switchdev mark, i.e. not to swp1, swp2 and
bond0. Towards swp1 and swp2 that's ok, but towards bond0? It should
have forwarded the skb there.
So the real issue is that bond0 will be assigned the same hardware
domain as {swp0,swp1,swp2}, because the function that assigns hardware
domains to bridge ports, nbp_switchdev_add(), recurses through bond0's
lower interfaces until it finds something that implements devlink (calls
dev_get_port_parent_id with bool recurse = true). This is a problem
because the fact that bond0 can be offloaded by swp3 and swp4 in our
example is merely an assumption.
A solution is to give the bridge explicit hints as to what hardware
domain it should use for each port.
Currently, the bridging offload is very 'silent': a driver registers a
netdevice notifier, which is put on the netns's notifier chain, and
which sniffs around for NETDEV_CHANGEUPPER events where the upper is a
bridge, and the lower is an interface it knows about (one registered by
this driver, normally). Then, from within that notifier, it does a bunch
of stuff behind the bridge's back, without the bridge necessarily
knowing that there's somebody offloading that port. It looks like this:
ip link set swp0 master br0
|
v
br_add_if() calls netdev_master_upper_dev_link()
|
v
call_netdevice_notifiers
|
v
dsa_slave_netdevice_event
|
v
oh, hey! it's for me!
|
v
.port_bridge_join
What we do to solve the conundrum is to be less silent, and change the
switchdev drivers to present themselves to the bridge. Something like this:
ip link set swp0 master br0
|
v
br_add_if() calls netdev_master_upper_dev_link()
|
v bridge: Aye! I'll use this
call_netdevice_notifiers ^ ppid as the
| | hardware domain for
v | this port, and zero
dsa_slave_netdevice_event | if I got nothing.
| |
v |
oh, hey! it's for me! |
| |
v |
.port_bridge_join |
| |
+------------------------+
switchdev_bridge_port_offload(swp0, swp0)
Then stacked interfaces (like bond0 on top of swp3/swp4) would be
treated differently in DSA, depending on whether we can or cannot
offload them.
The offload case:
ip link set bond0 master br0
|
v
br_add_if() calls netdev_master_upper_dev_link()
|
v bridge: Aye! I'll use this
call_netdevice_notifiers ^ ppid as the
| | switchdev mark for
v | bond0.
dsa_slave_netdevice_event | Coincidentally (or not),
| | bond0 and swp0, swp1, swp2
v | all have the same switchdev
hmm, it's not quite for me, | mark now, since the ASIC
but my driver has already | is able to forward towards
called .port_lag_join | all these ports in hw.
for it, because I have |
a port with dp->lag_dev == bond0. |
| |
v |
.port_bridge_join |
for swp3 and swp4 |
| |
+------------------------+
switchdev_bridge_port_offload(bond0, swp3)
switchdev_bridge_port_offload(bond0, swp4)
And the non-offload case:
ip link set bond0 master br0
|
v
br_add_if() calls netdev_master_upper_dev_link()
|
v bridge waiting:
call_netdevice_notifiers ^ huh, switchdev_bridge_port_offload
| | wasn't called, okay, I'll use a
v | hwdom of zero for this one.
dsa_slave_netdevice_event : Then packets received on swp0 will
| : not be software-forwarded towards
v : swp1, but they will towards bond0.
it's not for me, but
bond0 is an upper of swp3
and swp4, but their dp->lag_dev
is NULL because they couldn't
offload it.
Basically we can draw the conclusion that the lowers of a bridge port
can come and go, so depending on the configuration of lowers for a
bridge port, it can dynamically toggle between offloaded and unoffloaded.
Therefore, we need an equivalent switchdev_bridge_port_unoffload too.
This patch changes the way any switchdev driver interacts with the
bridge. From now on, everybody needs to call switchdev_bridge_port_offload
and switchdev_bridge_port_unoffload, otherwise the bridge will treat the
port as non-offloaded and allow software flooding to other ports from
the same ASIC.
Note that these functions lay the ground for a more complex handshake
between switchdev drivers and the bridge in the future.
For drivers that will request a replay of the switchdev objects when
they offload and unoffload a bridge port (DSA, dpaa2-switch, ocelot), we
place the call to switchdev_bridge_port_unoffload() strategically inside
the NETDEV_PRECHANGEUPPER notifier's code path, and not inside
NETDEV_CHANGEUPPER. This is because the switchdev object replay helpers
need the netdev adjacency lists to be valid, and that is only true in
NETDEV_PRECHANGEUPPER.
Cc: Vadym Kochan <vkochan@marvell.com>
Cc: Taras Chornyi <tchornyi@marvell.com>
Cc: Ioana Ciornei <ioana.ciornei@nxp.com>
Cc: Lars Povlsen <lars.povlsen@microchip.com>
Cc: Steen Hegelund <Steen.Hegelund@microchip.com>
Cc: UNGLinuxDriver@microchip.com
Cc: Claudiu Manoil <claudiu.manoil@nxp.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Ioana Ciornei <ioana.ciornei@nxp.com> # dpaa2-switch: regression
Acked-by: Ioana Ciornei <ioana.ciornei@nxp.com> # dpaa2-switch
Tested-by: Horatiu Vultur <horatiu.vultur@microchip.com> # ocelot-switch
Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-21 19:24:01 +03:00
|
|
|
struct net_device *master,
|
|
|
|
|
struct netlink_ext_ack *extack);
|
2016-02-16 15:14:45 +01:00
|
|
|
int (*port_master_unlinked)(struct rocker_port *rocker_port,
|
|
|
|
|
struct net_device *master);
|
|
|
|
|
int (*port_neigh_update)(struct rocker_port *rocker_port,
|
|
|
|
|
struct neighbour *n);
|
|
|
|
|
int (*port_neigh_destroy)(struct rocker_port *rocker_port,
|
|
|
|
|
struct neighbour *n);
|
|
|
|
|
int (*port_ev_mac_vlan_seen)(struct rocker_port *rocker_port,
|
|
|
|
|
const unsigned char *addr,
|
|
|
|
|
__be16 vlan_id);
|
2016-09-26 12:52:32 +02:00
|
|
|
int (*fib4_add)(struct rocker *rocker,
|
|
|
|
|
const struct fib_entry_notifier_info *fen_info);
|
|
|
|
|
int (*fib4_del)(struct rocker *rocker,
|
|
|
|
|
const struct fib_entry_notifier_info *fen_info);
|
|
|
|
|
void (*fib4_abort)(struct rocker *rocker);
|
2016-02-16 15:14:45 +01:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
extern struct rocker_world_ops rocker_ofdpa_ops;
|
|
|
|
|
|
2016-02-16 15:14:42 +01:00
|
|
|
#endif
|