* [PATCH net-next 4/8] devlink: allow subports on devlink PCI ports
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
PCI endpoint corresponds to a PCI device, but such device
can have one more more logical device ports associated with it.
We need a way to distinguish those. Add a PCI subport in the
dumps and print the info in phys_port_name appropriately.
This is not equivalent to port splitting, there is no split
group. It's just a way of representing multiple netdevs on
a single PCI function.
Note that the quality of being multiport pertains only to
the PCI function itself. A PF having multiple netdevs does
not mean that its VFs will also have multiple, or that VFs
are associated with any particular port of a multiport VF.
Example (bus 05 device has subports, bus 82 has only one port per
function):
$ devlink port
pci/0000:05:00.0/0: type eth netdev enp5s0np0 flavour physical
pci/0000:05:00.0/10000: type eth netdev enp5s0npf0s0 flavour pci_pf pf 0 subport 0
pci/0000:05:00.0/4: type eth netdev enp5s0np1 flavour physical
pci/0000:05:00.0/11000: type eth netdev enp5s0npf0s1 flavour pci_pf pf 0 subport 1
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth0 flavour pci_pf pf 0
$ devlink -jp port
{
"port": {
"pci/0000:05:00.0/0": {
"type": "eth",
"netdev": "enp5s0np0",
"flavour": "physical"
},
"pci/0000:05:00.0/10000": {
"type": "eth",
"netdev": "enp5s0npf0s0",
"flavour": "pci_pf",
"pf": 0,
"subport": 0
},
"pci/0000:05:00.0/4": {
"type": "eth",
"netdev": "enp5s0np1",
"flavour": "physical"
},
"pci/0000:05:00.0/11000": {
"type": "eth",
"netdev": "enp5s0npf0s1",
"flavour": "pci_pf",
"pf": 0,
"subport": 1
},
"pci/0000:82:00.0/0": {
"type": "eth",
"netdev": "p4p1",
"flavour": "physical"
},
"pci/0000:82:00.0/10000": {
"type": "eth",
"netdev": "eth0",
"flavour": "pci_pf",
"pf": 0
}
}
}
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
.../net/ethernet/netronome/nfp/nfp_devlink.c | 3 +-
include/net/devlink.h | 9 ++++--
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 29 ++++++++++++++++---
4 files changed, 35 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 36976e37d162..bb07be4117a3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -375,7 +375,8 @@ nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
{
devlink_port_type_eth_set(&port->dl_port, port->netdev);
devlink_port_attrs_pci_set(&port->dl_port, flavour,
- port->pf_id, port->vf_id);
+ port->pf_id, port->vf_id,
+ port->pf_split, port->pf_split_id);
return 0;
}
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b5376ef492f1..13e0a479c546 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -53,6 +53,8 @@ struct devlink_port_attrs {
struct {
u32 pf_number;
u32 vf_number;
+ bool multiport;
+ u32 subport_number;
} pci;
};
};
@@ -580,7 +582,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
u32 split_subport_number);
void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number);
+ u32 pf_number, u32 vf_number,
+ bool multiport, u32 subport_number);
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
@@ -797,7 +800,9 @@ static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
static inline void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number)
+ u32 pf_number, u32 vf_number,
+ bool multiport,
+ u32 subport_number)
{
}
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 9ce76d4f640d..417ae8233cce 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -336,6 +336,7 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_PCI_SUBPORT, /* u32 */
/* add new attributes above here, update the policy in devlink.c */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index af177284830b..6cdf7e87d7fc 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -541,6 +541,11 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
attrs->pci.pf_number))
return -EMSGSIZE;
+
+ if (attrs->pci.multiport &&
+ nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_SUBPORT,
+ attrs->pci.subport_number))
+ return -EMSGSIZE;
return 0;
default:
return -EINVAL;
@@ -5449,10 +5454,13 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
* @pf_number: PCI PF number, in multi-host mapping to hosts depends
* on the platform
* @vf_number: PCI VF number within given PF (ignored for PF itself)
+ * @multiport: PCI function has more than one logical port
+ * @subport_number: PCI function has more than one logical port
*/
void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
- u32 pf_number, u32 vf_number)
+ u32 pf_number, u32 vf_number,
+ bool multiport, u32 subport_number)
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
@@ -5463,6 +5471,8 @@ void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
attrs->flavour = flavour;
attrs->pci.pf_number = pf_number;
attrs->pci.vf_number = vf_number;
+ attrs->pci.multiport = multiport;
+ attrs->pci.subport_number = subport_number;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_set);
@@ -5492,11 +5502,22 @@ int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
WARN_ON(1);
return -EINVAL;
case DEVLINK_PORT_FLAVOUR_PCI_PF:
- n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ if (!attrs->pci.multiport)
+ n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ else
+ n = snprintf(name, len, "pf%us%u", attrs->pci.pf_number,
+ attrs->pci.subport_number);
break;
case DEVLINK_PORT_FLAVOUR_PCI_VF:
- n = snprintf(name, len, "pf%uvf%u",
- attrs->pf_number, attrs->pci.vf_number);
+ if (!attrs->pci.multiport)
+ n = snprintf(name, len, "pf%uvf%u",
+ attrs->pci.pf_number,
+ attrs->pci.vf_number);
+ else
+ n = snprintf(name, len, "pf%uvf%us%u",
+ attrs->pci.pf_number,
+ attrs->pci.vf_number,
+ attrs->pci.subport_number);
break;
}
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 3/8] nfp: register devlink ports of all reprs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Register all representors as devlink ports.
The port_index is slightly tricky to figure out, we use a bit of
arbitrary math to create unique IDs for PCI ports.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
.../net/ethernet/netronome/nfp/nfp_devlink.c | 47 ++++++++++++++++++-
.../net/ethernet/netronome/nfp/nfp_net_repr.c | 16 ++++++-
2 files changed, 60 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 9af3cb1f2f17..36976e37d162 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -350,7 +350,8 @@ const struct devlink_ops nfp_devlink_ops = {
.flash_update = nfp_devlink_flash_update,
};
-int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
+static int
+nfp_devlink_port_init_phys(struct devlink *devlink, struct nfp_port *port)
{
struct nfp_eth_table_port eth_port;
int ret;
@@ -368,6 +369,34 @@ int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
return 0;
}
+static int
+nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
+ u32 flavour)
+{
+ devlink_port_type_eth_set(&port->dl_port, port->netdev);
+ devlink_port_attrs_pci_set(&port->dl_port, flavour,
+ port->pf_id, port->vf_id);
+ return 0;
+}
+
+int nfp_devlink_port_init(struct nfp_app *app, struct nfp_port *port)
+{
+ struct devlink *devlink = priv_to_devlink(app->pf);
+
+ switch (port->type) {
+ case NFP_PORT_PHYS_PORT:
+ return nfp_devlink_port_init_phys(devlink, port);
+ case NFP_PORT_PF_PORT:
+ return nfp_devlink_port_init_pci(devlink, port,
+ DEVLINK_PORT_FLAVOUR_PCI_PF);
+ case NFP_PORT_VF_PORT:
+ return nfp_devlink_port_init_pci(devlink, port,
+ DEVLINK_PORT_FLAVOUR_PCI_VF);
+ default:
+ return -EINVAL;
+ }
+}
+
void nfp_devlink_port_clean(struct nfp_port *port)
{
}
@@ -376,7 +405,21 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
{
struct devlink *devlink = priv_to_devlink(app->pf);
- return devlink_port_register(devlink, &port->dl_port, port->eth_id);
+ switch (port->type) {
+ case NFP_PORT_PHYS_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ port->eth_id);
+ case NFP_PORT_PF_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ (port->pf_id + 1) * 10000 +
+ port->pf_split_id * 1000);
+ case NFP_PORT_VF_PORT:
+ return devlink_port_register(devlink, &port->dl_port,
+ (port->pf_id + 1) * 10000 +
+ port->vf_id + 1);
+ default:
+ return -EINVAL;
+ }
}
void nfp_devlink_port_unregister(struct nfp_port *port)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d2c803bb4e56..869d22760a6e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -292,7 +292,9 @@ nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower)
static void nfp_repr_clean(struct nfp_repr *repr)
{
+ nfp_devlink_port_unregister(repr->port);
unregister_netdev(repr->netdev);
+ nfp_devlink_port_clean(repr->port);
nfp_app_repr_clean(repr->app, repr->netdev);
dst_release((struct dst_entry *)repr->dst);
nfp_port_free(repr->port);
@@ -395,12 +397,24 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
if (err)
goto err_clean;
- err = register_netdev(netdev);
+ err = nfp_devlink_port_init(app, repr->port);
if (err)
goto err_repr_clean;
+ err = register_netdev(netdev);
+ if (err)
+ goto err_port_clean;
+
+ err = nfp_devlink_port_register(app, repr->port);
+ if (err)
+ goto err_unreg_netdev;
+
return 0;
+err_unreg_netdev:
+ unregister_netdev(repr->netdev);
+err_port_clean:
+ nfp_devlink_port_clean(repr->port);
err_repr_clean:
nfp_app_repr_clean(app, netdev);
err_clean:
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 6/8] devlink: introduce port's peer netdevs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Devlink ports represent ports of a switch device (or SR-IOV
NIC which has an embedded switch). In case of SR-IOV when
PCIe PFs are exposed the PFs which are directly connected
to the local machine may also spawn PF netdev (much like
VFs have a port/"repr" and an actual VF netdev).
Allow devlink to expose such linking. There is currently no
way to find out which netdev corresponds to which PF.
Example:
$ devlink port
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth1 flavour pci_pf pf 0 peer_netdev enp130s0
pci/0000:82:00.0/10001: type eth netdev eth0 flavour pci_vf pf 0 vf 0
pci/0000:82:00.0/10002: type eth netdev eth2 flavour pci_vf pf 0 vf 1
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
include/net/devlink.h | 11 ++++++++
include/uapi/linux/devlink.h | 3 +++
net/core/devlink.c | 51 +++++++++++++++++++++++++++++-------
3 files changed, 55 insertions(+), 10 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 13e0a479c546..15912cca5d16 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -68,6 +68,7 @@ struct devlink_port {
enum devlink_port_type type;
enum devlink_port_type desired_type;
void *type_dev;
+ void *type_peer;
struct devlink_port_attrs attrs;
};
@@ -573,6 +574,9 @@ int devlink_port_register(struct devlink *devlink,
void devlink_port_unregister(struct devlink_port *devlink_port);
void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev);
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer);
void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev);
void devlink_port_type_clear(struct devlink_port *devlink_port);
@@ -782,6 +786,13 @@ static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
{
}
+static inline void
+devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+}
+
static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 417ae8233cce..9ce4718f8b8b 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -338,6 +338,9 @@ enum devlink_attr {
DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
DEVLINK_ATTR_PORT_PCI_SUBPORT, /* u32 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX, /* u32 */
+ DEVLINK_ATTR_PORT_PEER_NETDEV_NAME, /* string */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6cdf7e87d7fc..b514be300839 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -552,6 +552,17 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
}
}
+static int devlink_nl_port_put_netdev(struct sk_buff *msg,
+ int attr_ifindex, int attr_name,
+ struct net_device *netdev)
+{
+ if (netdev &&
+ (nla_put_u32(msg, attr_ifindex, netdev->ifindex) ||
+ nla_put_string(msg, attr_name, netdev->name)))
+ return -EMSGSIZE;
+ return 0;
+}
+
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
struct devlink_port *devlink_port,
enum devlink_command cmd, u32 portid,
@@ -574,13 +585,16 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
devlink_port->desired_type))
goto nla_put_failure;
if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
- struct net_device *netdev = devlink_port->type_dev;
+ if (devlink_nl_port_put_netdev(msg,
+ DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
+ DEVLINK_ATTR_PORT_NETDEV_NAME,
+ devlink_port->type_dev))
+ goto nla_put_failure;
- if (netdev &&
- (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
- netdev->ifindex) ||
- nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
- netdev->name)))
+ if (devlink_nl_port_put_netdev(msg,
+ DEVLINK_ATTR_PORT_PEER_NETDEV_IFINDEX,
+ DEVLINK_ATTR_PORT_PEER_NETDEV_NAME,
+ devlink_port->type_peer))
goto nla_put_failure;
}
if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
@@ -5369,10 +5383,11 @@ EXPORT_SYMBOL_GPL(devlink_port_unregister);
static void __devlink_port_type_set(struct devlink_port *devlink_port,
enum devlink_port_type type,
- void *type_dev)
+ void *type_dev, void *type_peer)
{
devlink_port->type = type;
devlink_port->type_dev = type_dev;
+ devlink_port->type_peer = type_peer;
devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
}
@@ -5386,10 +5401,26 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port,
struct net_device *netdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_ETH, netdev);
+ DEVLINK_PORT_TYPE_ETH, netdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
+/**
+ * devlink_port_type_eth_set_peer - Set port type to Ethernet with peer
+ *
+ * @devlink_port: devlink port
+ * @netdev: related netdevice
+ * @peer: for PCIe ports the non-port netdev (actual VF or PF)
+ */
+void devlink_port_type_eth_set_peer(struct devlink_port *devlink_port,
+ struct net_device *netdev,
+ struct net_device *peer)
+{
+ return __devlink_port_type_set(devlink_port,
+ DEVLINK_PORT_TYPE_ETH, netdev, peer);
+}
+EXPORT_SYMBOL_GPL(devlink_port_type_eth_set_peer);
+
/**
* devlink_port_type_ib_set - Set port type to InfiniBand
*
@@ -5400,7 +5431,7 @@ void devlink_port_type_ib_set(struct devlink_port *devlink_port,
struct ib_device *ibdev)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_IB, ibdev);
+ DEVLINK_PORT_TYPE_IB, ibdev, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
@@ -5412,7 +5443,7 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set);
void devlink_port_type_clear(struct devlink_port *devlink_port)
{
return __devlink_port_type_set(devlink_port,
- DEVLINK_PORT_TYPE_NOTSET, NULL);
+ DEVLINK_PORT_TYPE_NOTSET, NULL, NULL);
}
EXPORT_SYMBOL_GPL(devlink_port_type_clear);
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 7/8] nfp: expose PF peer netdevs
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Expose PF netdevs as devlink port's peers.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
drivers/net/ethernet/netronome/nfp/abm/main.c | 1 +
drivers/net/ethernet/netronome/nfp/flower/main.c | 1 +
drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 3 ++-
drivers/net/ethernet/netronome/nfp/nfp_port.h | 2 ++
4 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index 4d4ff5844c47..8d7ff1200fd4 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -113,6 +113,7 @@ nfp_abm_spawn_repr(struct nfp_app *app, struct nfp_abm_link *alink,
port->pf_id = alink->abm->pf_id;
port->pf_split = app->pf->max_data_vnics > 1;
port->pf_split_id = alink->id;
+ port->peer = alink->vnic->dp.netdev;
port->vnic = alink->vnic->dp.ctrl_bar;
}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 408089133599..13aa21923bf7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -300,6 +300,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
if (repr_type == NFP_REPR_TYPE_PF) {
port->pf_id = i;
port->vnic = priv->nn->dp.ctrl_bar;
+ port->peer = priv->nn->dp.netdev;
} else {
port->pf_id = 0;
port->vf_id = i;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index bb07be4117a3..3d59a57eda0c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -373,7 +373,8 @@ static int
nfp_devlink_port_init_pci(struct devlink *devlink, struct nfp_port *port,
u32 flavour)
{
- devlink_port_type_eth_set(&port->dl_port, port->netdev);
+ devlink_port_type_eth_set_peer(&port->dl_port, port->netdev,
+ port->peer);
devlink_port_attrs_pci_set(&port->dl_port, flavour,
port->pf_id, port->vf_id,
port->pf_split, port->pf_split_id);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h
index 09c55ca2371a..c75a25cc5cea 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h
@@ -51,6 +51,7 @@ enum nfp_port_flags {
* @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change
* @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry
* @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available
+ * @peer: for %NFP_PORT_PF_PORT netdev of the actual vNIC, if reachable
* @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3)
* @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id
* @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC
@@ -79,6 +80,7 @@ struct nfp_port {
};
/* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */
struct {
+ struct net_device *peer;
unsigned int pf_id;
unsigned int vf_id;
bool pf_split;
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 8/8] devlink: fix kdoc
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
devlink suffers from a few kdoc warnings:
net/core/devlink.c:5292: warning: Function parameter or member 'dev' not described in 'devlink_register'
net/core/devlink.c:5351: warning: Function parameter or member 'port_index' not described in 'devlink_port_register'
net/core/devlink.c:5753: warning: Function parameter or member 'parent_resource_id' not described in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Function parameter or member 'size_params' not described in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'top_hierarchy' description in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'reload_required' description in 'devlink_resource_register'
net/core/devlink.c:5753: warning: Excess function parameter 'parent_reosurce_id' description in 'devlink_resource_register'
net/core/devlink.c:6451: warning: Function parameter or member 'region' not described in 'devlink_region_snapshot_create'
net/core/devlink.c:6451: warning: Excess function parameter 'devlink_region' description in 'devlink_region_snapshot_create'
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
net/core/devlink.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b514be300839..cd3f466496d3 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5287,6 +5287,7 @@ EXPORT_SYMBOL_GPL(devlink_alloc);
* devlink_register - Register devlink instance
*
* @devlink: devlink
+ * @dev: parent device
*/
int devlink_register(struct devlink *devlink, struct device *dev)
{
@@ -5337,7 +5338,7 @@ EXPORT_SYMBOL_GPL(devlink_free);
*
* @devlink: devlink
* @devlink_port: devlink port
- * @port_index
+ * @port_index: driver-specific numerical identifier of the port
*
* Register devlink port with provided port index. User can use
* any indexing, even hw-related one. devlink_port structure
@@ -5736,13 +5737,10 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister);
*
* @devlink: devlink
* @resource_name: resource's name
- * @top_hierarchy: top hierarchy
- * @reload_required: reload is required for new configuration to
- * apply
* @resource_size: resource's size
* @resource_id: resource's id
- * @parent_reosurce_id: resource's parent id
- * @size params: size parameters
+ * @parent_resource_id: resource's parent id
+ * @size_params: size parameters
*/
int devlink_resource_register(struct devlink *devlink,
const char *resource_name,
@@ -6439,7 +6437,7 @@ EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
* Multiple snapshots can be created on a region.
* The @snapshot_id should be obtained using the getter function.
*
- * @devlink_region: devlink region of the snapshot
+ * @region: devlink region of the snapshot
* @data_len: size of snapshot data
* @data: snapshot data
* @snapshot_id: snapshot id to be created
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 5/8] nfp: switch to devlink_port_get_phys_port_name()
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Now that devlink understands all port flavours - switch
to the devlink_port_get_phys_port_name() helper.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
drivers/net/ethernet/netronome/nfp/nfp_port.c | 33 +------------------
1 file changed, 1 insertion(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c
index 93c5bfc0510b..3e2ff8d35e8d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c
@@ -117,44 +117,13 @@ struct nfp_eth_table_port *nfp_port_get_eth_port(struct nfp_port *port)
int
nfp_port_get_phys_port_name(struct net_device *netdev, char *name, size_t len)
{
- struct nfp_eth_table_port *eth_port;
struct nfp_port *port;
- int n;
port = nfp_port_from_netdev(netdev);
if (!port)
return -EOPNOTSUPP;
- switch (port->type) {
- case NFP_PORT_PHYS_PORT:
- eth_port = __nfp_port_get_eth_port(port);
- if (!eth_port)
- return -EOPNOTSUPP;
-
- if (!eth_port->is_split)
- n = snprintf(name, len, "p%d", eth_port->label_port);
- else
- n = snprintf(name, len, "p%ds%d", eth_port->label_port,
- eth_port->label_subport);
- break;
- case NFP_PORT_PF_PORT:
- if (!port->pf_split)
- n = snprintf(name, len, "pf%d", port->pf_id);
- else
- n = snprintf(name, len, "pf%ds%d", port->pf_id,
- port->pf_split_id);
- break;
- case NFP_PORT_VF_PORT:
- n = snprintf(name, len, "pf%dvf%d", port->pf_id, port->vf_id);
- break;
- default:
- return -EOPNOTSUPP;
- }
-
- if (n >= len)
- return -EINVAL;
-
- return 0;
+ return devlink_port_get_phys_port_name(&port->dl_port, name, len);
}
/**
--
2.19.2
^ permalink raw reply related
* [PATCH net-next 2/8] devlink: add PF and VF port flavours
From: Jakub Kicinski @ 2019-02-26 18:24 UTC (permalink / raw)
To: davem, jiri; +Cc: oss-drivers, netdev, Jakub Kicinski
In-Reply-To: <20190226182436.23811-1-jakub.kicinski@netronome.com>
Current port flavours cover simple switches and DSA. Add PF
and VF flavours to cover "switchdev" SR-IOV NICs.
Example devlink user space output:
$ devlink port
pci/0000:82:00.0/0: type eth netdev p4p1 flavour physical
pci/0000:82:00.0/10000: type eth netdev eth0 flavour pcie_pf pf 0
pci/0000:82:00.0/10001: type eth netdev eth1 flavour pcie_vf pf 0 vf 0
pci/0000:82:00.0/10002: type eth netdev eth2 flavour pcie_vf pf 0 vf 1
$ devlink -jp port
{
"port": {
"pci/0000:82:00.0/0": {
"type": "eth",
"netdev": "p4p1",
"flavour": "physical"
},
"pci/0000:82:00.0/10000": {
"type": "eth",
"netdev": "eth0",
"flavour": "pci_pf",
"pf": 0,
},
"pci/0000:82:00.0/10001": {
"type": "eth",
"netdev": "eth1",
"flavour": "pci_vf",
"pf": 0,
"vf": 0
},
"pci/0000:82:00.0/10002": {
"type": "eth",
"netdev": "eth2",
"flavour": "pci_vf",
"pf": 0,
"vf": 1
}
}
}
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
include/net/devlink.h | 25 ++++++++++--
include/uapi/linux/devlink.h | 5 +++
net/core/devlink.c | 73 +++++++++++++++++++++++++++++++-----
3 files changed, 91 insertions(+), 12 deletions(-)
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 7f5a0bdca228..b5376ef492f1 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -42,9 +42,19 @@ struct devlink {
struct devlink_port_attrs {
bool set;
enum devlink_port_flavour flavour;
- u32 port_number; /* same value as "split group" */
- bool split;
- u32 split_subport_number;
+ union { /* port identifiers differ per-flavour */
+ /* PHYSICAL, CPU, DSA */
+ struct {
+ bool split;
+ u32 split_subport_number;
+ u32 port_number; /* same value as "split group" */
+ };
+ /* PCI_PF, PCI_VF */
+ struct {
+ u32 pf_number;
+ u32 vf_number;
+ } pci;
+ };
};
struct devlink_port {
@@ -568,6 +578,9 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
enum devlink_port_flavour flavour,
u32 port_number, bool split,
u32 split_subport_number);
+void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number);
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len);
int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
@@ -782,6 +795,12 @@ static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
{
}
+static inline void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number)
+{
+}
+
static inline int
devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 5bb4ea67d84f..9ce76d4f640d 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -167,6 +167,8 @@ enum devlink_port_flavour {
DEVLINK_PORT_FLAVOUR_DSA, /* Distributed switch architecture
* interconnect port.
*/
+ DEVLINK_PORT_FLAVOUR_PCI_PF, /* PCI Physical function port */
+ DEVLINK_PORT_FLAVOUR_PCI_VF, /* PCI Physical function port */
};
enum devlink_param_cmode {
@@ -332,6 +334,9 @@ enum devlink_attr {
DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */
DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */
+ DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u32 */
+ DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u32 */
+
/* add new attributes above here, update the policy in devlink.c */
__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index a49dee67e66f..af177284830b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -516,16 +516,35 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour))
return -EMSGSIZE;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->port_number))
- return -EMSGSIZE;
- if (!attrs->split)
+
+ switch (attrs->flavour) {
+ case DEVLINK_PORT_FLAVOUR_PHYSICAL:
+ case DEVLINK_PORT_FLAVOUR_CPU:
+ case DEVLINK_PORT_FLAVOUR_DSA:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
+ attrs->port_number))
+ return -EMSGSIZE;
+
+ if (attrs->split &&
+ (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP,
+ attrs->port_number) ||
+ nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
+ attrs->split_subport_number)))
+ return -EMSGSIZE;
return 0;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->port_number))
- return -EMSGSIZE;
- if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,
- attrs->split_subport_number))
- return -EMSGSIZE;
- return 0;
+ case DEVLINK_PORT_FLAVOUR_PCI_VF:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
+ attrs->pci.vf_number))
+ return -EMSGSIZE;
+ /* fall through */
+ case DEVLINK_PORT_FLAVOUR_PCI_PF:
+ if (nla_put_u32(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
+ attrs->pci.pf_number))
+ return -EMSGSIZE;
+ return 0;
+ default:
+ return -EINVAL;
+ }
}
static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
@@ -5410,6 +5429,9 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
{
struct devlink_port_attrs *attrs = &devlink_port->attrs;
+ WARN_ON(flavour == DEVLINK_PORT_FLAVOUR_PCI_PF ||
+ flavour == DEVLINK_PORT_FLAVOUR_PCI_VF);
+
attrs->set = true;
attrs->flavour = flavour;
attrs->port_number = port_number;
@@ -5419,6 +5441,32 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
}
EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
+/**
+ * devlink_port_attrs_pci_set - Set port attributes for a PCI port
+ *
+ * @devlink_port: devlink port
+ * @flavour: flavour of the port (PF or VF only)
+ * @pf_number: PCI PF number, in multi-host mapping to hosts depends
+ * on the platform
+ * @vf_number: PCI VF number within given PF (ignored for PF itself)
+ */
+void devlink_port_attrs_pci_set(struct devlink_port *devlink_port,
+ enum devlink_port_flavour flavour,
+ u32 pf_number, u32 vf_number)
+{
+ struct devlink_port_attrs *attrs = &devlink_port->attrs;
+
+ WARN_ON(flavour != DEVLINK_PORT_FLAVOUR_PCI_PF &&
+ flavour != DEVLINK_PORT_FLAVOUR_PCI_VF);
+
+ attrs->set = true;
+ attrs->flavour = flavour;
+ attrs->pci.pf_number = pf_number;
+ attrs->pci.vf_number = vf_number;
+ devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_set);
+
int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
char *name, size_t len)
{
@@ -5443,6 +5491,13 @@ int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
*/
WARN_ON(1);
return -EINVAL;
+ case DEVLINK_PORT_FLAVOUR_PCI_PF:
+ n = snprintf(name, len, "pf%u", attrs->pci.pf_number);
+ break;
+ case DEVLINK_PORT_FLAVOUR_PCI_VF:
+ n = snprintf(name, len, "pf%uvf%u",
+ attrs->pf_number, attrs->pci.vf_number);
+ break;
}
if (n >= len)
--
2.19.2
^ permalink raw reply related
* [PATCH v3 net] net: phy: phylink: fix uninitialized variable in phylink_get_mac_state
From: Heiner Kallweit @ 2019-02-26 18:29 UTC (permalink / raw)
To: Russell King - ARM Linux, David Miller, Andrew Lunn,
Florian Fainelli
Cc: netdev@vger.kernel.org
When debugging an issue I found implausible values in state->pause.
Reason in that state->pause isn't initialized and later only single
bits are changed. Also the struct itself isn't initialized in
phylink_resolve(). So better initialize state->pause and other
not yet initialized fields.
v2:
- use right function name in subject
v3:
- initialize additional fields
Fixes: 9525ae83959b ("phylink: add phylink infrastructure")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
---
drivers/net/phy/phylink.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 59d175a5b..89750c7df 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -324,6 +324,10 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state *
linkmode_zero(state->lp_advertising);
state->interface = pl->link_config.interface;
state->an_enabled = pl->link_config.an_enabled;
+ state->speed = SPEED_UNKNOWN;
+ state->duplex = DUPLEX_UNKNOWN;
+ state->pause = MLO_PAUSE_NONE;
+ state->an_complete = 0;
state->link = 1;
return pl->ops->mac_link_state(ndev, state);
--
2.20.1
^ permalink raw reply related
* Re: [PATCH net] selftests: fixes for UDP GRO
From: Willem de Bruijn @ 2019-02-26 18:38 UTC (permalink / raw)
To: Paolo Abeni; +Cc: Network Development, David S. Miller, Willem de Bruijn
In-Reply-To: <2b1f4d9fe21346bc9f85c096e1b0922e4ff3c19d.1551173111.git.pabeni@redhat.com>
On Tue, Feb 26, 2019 at 9:28 AM Paolo Abeni <pabeni@redhat.com> wrote:
>
> The current implementation for UDP GRO tests is racy: the receiver
> may flush the RX queue while the sending is still transmitting and
> incorrectly report RX errors, with a wrong number of packet received.
>
> Add explicit timeouts to the receiver for both connection activation
> (first packet received for UDP) and reception completion, so that
> in the above critical scenario the receiver will wait for the
> transfer completion.
>
> Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO")
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
---
This is because of that "force termination after the second poll()"?
Could perhaps also just extend do_recv to wait while (!interrupted &&
tnow < tstart + 2000) and avoid the explicit arguments.
^ permalink raw reply
* [PATCH v2] iov_iter: optimize page_copy_sane()
From: Eric Dumazet @ 2019-02-26 18:42 UTC (permalink / raw)
To: Al Viro, David S . Miller
Cc: linux-kernel, netdev, Eric Dumazet, Eric Dumazet
Avoid cache line miss dereferencing struct page if we can.
page_copy_sane() mostly deals with order-0 pages.
Extra cache line miss is visible on TCP recvmsg() calls dealing
with GRO packets (typically 45 page frags are attached to one skb).
Bringing the 45 struct pages into cpu cache while copying the data
is not free, since the freeing of the skb (and associated
page frags put_page()) can happen after cache lines have been evicted.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
---
lib/iov_iter.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index be4bd627caf060cd89aa41ac88208946da568035..4d6b19c1b1294e1c30f6bbb7137e98cca5121f13 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -861,8 +861,21 @@ EXPORT_SYMBOL(_copy_from_iter_full_nocache);
static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
{
- struct page *head = compound_head(page);
- size_t v = n + offset + page_address(page) - page_address(head);
+ struct page *head;
+ size_t v = n + offset;
+
+ /*
+ * The general case needs to access the page order in order
+ * to compute the page size.
+ * However, we mostly deal with order-0 pages and thus can
+ * avoid a possible cache line miss for requests that fit all
+ * page orders.
+ */
+ if (n <= v && v <= PAGE_SIZE)
+ return true;
+
+ head = compound_head(page);
+ v += (page - head) << PAGE_SHIFT;
if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
return true;
--
2.21.0.rc2.261.ga7da99ff1b-goog
^ permalink raw reply related
* [PATCH net-next 0/6] net: add individual virtual device filtering
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
One of the reasons of this proposition is safety and performance -
host should not receive traffic which is not designated for it.
Some network devices can hold separate address tables for vlans and
real device, but for some reason there is no possibility to apply it
with generic net addressing scheme easily. At this moment the fastest
solution is to add mcast/ucast entries for every created vlan
including real device. But it not only consumes forwarding table but
also adds holes in the filtering and thus wastes cpus cycles.
This patchseries tries to correct core to assign mcast and ucast
addresses only for vlans that really require it and as result an end
driver can exclusively and simply set its rx filters. As an example
it's implemented on cpsw TI driver, but generic changes provided by
this series can be reused by other ethernet drivers having similar
rx filter address possibilities.
An address+vid is considered as separate address. The reserved device
address length is 32 Bytes, for ethernet devices it's additional
opportunity to pass auxiliary address info, like virtual ID
identifying a device the address belongs to. This series makes it
possible at least for ETH_P_8021Q.
Thus end real device can setup separate tables for virtual devices
just retrieving VID from the address. A device address space can
maintain addresses and references on them separately for each virtual
device if it needs so, or only addresses for real device (and all its
vlans) it holds usually.
A vlan device can be in any place of device chain upper real device,
say smth like rdevice/bonding/vlan or even rdevice/macvlan/vlan.
This series is verified on TI am572x EVM that can hold separate tables
for vlans. Potentially it can be easily extended to netcp driver for
keystone 2 boards (including k2g) and also new am6 chipsets. As a
simple test case, different combinations of vlan+macvlan, macvlan+vlan
were used and tested as with unicast as multicast addresses.
Based on net-next/master
It's continuation of RFC:
[RFC PATCH net-next 0/5] net: allow hw addresses for virtual device
https://lkml.org/lkml/2018/12/3/817
Ivan Khoronzhuk (6):
net: core: dev_addr_lists: add VID to device address
net: 8021q: vlan_dev: add vid tag to addresses of uc and mc lists
net: 8021q: vlan_dev: add vid tag for vlan device own address
ethernet: eth: add default vid len for all ehternet kind devices
net: ethernet: ti: cpsw: update mc filtering to use IVDF
net: ethernet: ti: cpsw: add macvlan and ucast/vlan filtering support
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 139 ++++++++++++--------------------
include/linux/if_vlan.h | 2 +
include/linux/netdevice.h | 4 +
net/8021q/Kconfig | 12 +++
net/8021q/vlan.c | 3 +
net/8021q/vlan.h | 2 +
net/8021q/vlan_core.c | 25 ++++++
net/8021q/vlan_dev.c | 103 ++++++++++++++++++-----
net/core/dev_addr_lists.c | 124 ++++++++++++++++++++++------
net/ethernet/eth.c | 10 ++-
11 files changed, 292 insertions(+), 133 deletions(-)
--
2.17.1
^ permalink raw reply
* [PATCH net-next 6/6] net: ethernet: ti: cpsw: add macvlan and ucast/vlan filtering support
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
The cpsw supports unicast filtering as for real as for vlan devices
now, but has no flag set for that. As result, once macvlan or vlan
adds new ucast address the cpsw is silently toggled to promiscuous
mode. That's smth not expected, so patch fixes it.
A unicast address for vlan has to be presented by vlan/unicast entry
in ALE table. At this moment, while vlan address change, entry is not
created in any form, even just like real device unicast used for
macvlan, leaving only address inherited from real device created
while vlan addition.
Therefore, program unicast entries for vlans by using IVDF, it allows
to add only vlan/unicast entries for vlans, omitting real device
ucast entries unless they are added for macvans or so, as they are
redundant for vlans and just consume forwarding table and in case of
matching packet income - CPU time.
So, after this patch, cpsw has ability to handle macvlan and vlan
ucasts, synchronizing ucast tables for these devices with cpsw ALE
table exclusively.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/cpsw.c | 62 ++++++++++++++++++++++++++++++----
1 file changed, 56 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index fd76d1f12911..c6d5ddc05299 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -693,6 +693,31 @@ static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
return ret;
}
+static int cpsw_set_uc(struct net_device *ndev, const u8 *addr,
+ int vid, int add)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+ struct cpsw_common *cpsw = priv->cpsw;
+ int flags, port, ret;
+
+ if (vid < 0) {
+ if (cpsw->data.dual_emac)
+ vid = cpsw->slaves[priv->emac_port].port_vlan;
+ else
+ vid = 0;
+ }
+
+ port = HOST_PORT_NUM;
+ flags = vid ? ALE_VLAN : 0;
+
+ if (add)
+ ret = cpsw_ale_add_ucast(cpsw->ale, addr, port, flags, vid);
+ else
+ ret = cpsw_ale_del_ucast(cpsw->ale, addr, port, flags, vid);
+
+ return ret;
+}
+
static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr)
{
u16 vid;
@@ -711,6 +736,24 @@ static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr)
return 0;
}
+static int cpsw_add_uc_addr(struct net_device *ndev, const u8 *addr)
+{
+ u16 vid;
+
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_uc(ndev, addr, vid ? vid : -1, 1);
+ return 0;
+}
+
+static int cpsw_del_uc_addr(struct net_device *ndev, const u8 *addr)
+{
+ u16 vid;
+
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_uc(ndev, addr, vid ? vid : -1, 0);
+ return 0;
+}
+
static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
{
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -730,6 +773,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
/* add/remove mcast address either for real netdev or for vlan */
__dev_mc_sync(ndev, cpsw_add_mc_addr, cpsw_del_mc_addr);
+ __dev_uc_sync(ndev, cpsw_add_uc_addr, cpsw_del_uc_addr);
}
static void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -2009,6 +2053,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
cpsw_info(priv, ifdown, "shutting down cpsw device\n");
__dev_mc_unsync(ndev, cpsw_del_mc_addr);
+ __dev_uc_unsync(ndev, cpsw_del_uc_addr);
netif_tx_stop_all_queues(priv->ndev);
netif_carrier_off(priv->ndev);
@@ -2369,10 +2414,12 @@ static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
if (ret != 0)
return ret;
- ret = cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
- HOST_PORT_NUM, ALE_VLAN, vid);
- if (ret != 0)
- goto clean_vid;
+ if (!priv->ndev->vid_len) {
+ ret = cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr,
+ HOST_PORT_NUM, ALE_VLAN, vid);
+ if (ret != 0)
+ goto clean_vid;
+ }
ret = cpsw_ale_add_mcast(cpsw->ale, priv->ndev->broadcast,
mcast_mask, ALE_VLAN, vid, 0);
@@ -2381,8 +2428,9 @@ static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv,
return 0;
clean_vlan_ucast:
- cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
- HOST_PORT_NUM, ALE_VLAN, vid);
+ if (!priv->ndev->vid_len)
+ cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr,
+ HOST_PORT_NUM, ALE_VLAN, vid);
clean_vid:
cpsw_ale_del_vlan(cpsw->ale, vid, 0);
return ret;
@@ -3344,6 +3392,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
priv_sl2->emac_port = 1;
cpsw->slaves[1].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
@@ -3606,6 +3655,7 @@ static int cpsw_probe(struct platform_device *pdev)
}
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->priv_flags |= IFF_UNICAST_FLT;
vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 5/6] net: ethernet: ti: cpsw: update mc filtering to use IVDF
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
The cpsw can filter multicast addresses only per vlan. Thus if mcast
address is set for one of them or only for real device it must be
added for every created vlan consuming ALE table w/o reason. In order to
simplify dispatching vlan filters, the IVDF recently added is resused.
In case IVDF is disabled - mc is updated only for real device as before.
The previous method is harder to reuse and vlan filtering is limited
only for vlans directly connected to real netdev, so drop it in flavor
of IVDF decision.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 113 ++++----------------------------
2 files changed, 13 insertions(+), 101 deletions(-)
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index bb126be1eb72..c99c08ece9a1 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -65,6 +65,7 @@ config TI_CPSW
select TI_DAVINCI_CPDMA
select TI_DAVINCI_MDIO
select TI_CPSW_PHY_SEL
+ select VLAN_8021Q_IVDF
select TI_CPSW_ALE
select MFD_SYSCON
select REGMAP
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index a591583d120e..fd76d1f12911 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -693,108 +693,21 @@ static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
return ret;
}
-static int cpsw_update_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr)
{
- struct addr_sync_ctx *sync_ctx = ctx;
- struct netdev_hw_addr *ha;
- int found = 0, ret = 0;
-
- if (!vdev || !(vdev->flags & IFF_UP))
- return 0;
-
- /* vlan address is relevant if its sync_cnt != 0 */
- netdev_for_each_mc_addr(ha, vdev) {
- if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
- found = ha->sync_cnt;
- break;
- }
- }
-
- if (found)
- sync_ctx->consumed++;
-
- if (sync_ctx->flush) {
- if (!found)
- cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
- return 0;
- }
-
- if (found)
- ret = cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 1);
-
- return ret;
-}
-
-static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr, int num)
-{
- struct addr_sync_ctx sync_ctx;
- int ret;
-
- sync_ctx.consumed = 0;
- sync_ctx.addr = addr;
- sync_ctx.ndev = ndev;
- sync_ctx.flush = 0;
-
- ret = vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
- if (sync_ctx.consumed < num && !ret)
- ret = cpsw_set_mc(ndev, addr, -1, 1);
-
- return ret;
-}
-
-static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr, int num)
-{
- struct addr_sync_ctx sync_ctx;
-
- sync_ctx.consumed = 0;
- sync_ctx.addr = addr;
- sync_ctx.ndev = ndev;
- sync_ctx.flush = 1;
-
- vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
- if (sync_ctx.consumed == num)
- cpsw_set_mc(ndev, addr, -1, 0);
+ u16 vid;
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_mc(ndev, addr, vid ? vid : -1, 1);
return 0;
}
-static int cpsw_purge_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr)
{
- struct addr_sync_ctx *sync_ctx = ctx;
- struct netdev_hw_addr *ha;
- int found = 0;
-
- if (!vdev || !(vdev->flags & IFF_UP))
- return 0;
-
- /* vlan address is relevant if its sync_cnt != 0 */
- netdev_for_each_mc_addr(ha, vdev) {
- if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
- found = ha->sync_cnt;
- break;
- }
- }
-
- if (!found)
- return 0;
-
- sync_ctx->consumed++;
- cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
- return 0;
-}
-
-static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
-{
- struct addr_sync_ctx sync_ctx;
-
- sync_ctx.addr = addr;
- sync_ctx.ndev = ndev;
- sync_ctx.consumed = 0;
-
- vlan_for_each(ndev, cpsw_purge_vlan_mc, &sync_ctx);
- if (sync_ctx.consumed < num)
- cpsw_set_mc(ndev, addr, -1, 0);
+ u16 vid;
+ vid = vlan_dev_get_addr_vid(ndev, addr);
+ cpsw_set_mc(ndev, addr, vid ? vid : -1, 0);
return 0;
}
@@ -816,8 +729,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
cpsw_ale_set_allmulti(cpsw->ale, ndev->flags & IFF_ALLMULTI);
/* add/remove mcast address either for real netdev or for vlan */
- __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
- cpsw_del_mc_addr);
+ __dev_mc_sync(ndev, cpsw_add_mc_addr, cpsw_del_mc_addr);
}
static void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -1970,9 +1882,6 @@ static int cpsw_restore_vlans(struct net_device *vdev, int vid, void *arg)
{
struct cpsw_priv *priv = arg;
- if (!vdev)
- return 0;
-
cpsw_ndo_vlan_rx_add_vid(priv->ndev, 0, vid);
return 0;
}
@@ -2099,7 +2008,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
struct cpsw_common *cpsw = priv->cpsw;
cpsw_info(priv, ifdown, "shutting down cpsw device\n");
- __hw_addr_ref_unsync_dev(&ndev->mc, ndev, cpsw_purge_all_mc);
+ __dev_mc_unsync(ndev, cpsw_del_mc_addr);
netif_tx_stop_all_queues(priv->ndev);
netif_carrier_off(priv->ndev);
@@ -3435,6 +3344,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
priv_sl2->emac_port = 1;
cpsw->slaves[1].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
@@ -3696,6 +3606,7 @@ static int cpsw_probe(struct platform_device *pdev)
}
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ vlan_dev_ivdf_set(ndev, 1);
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 4/6] ethernet: eth: add default vid len for all ehternet kind devices
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
IVDF - individual virtual device filtering. Allows to set per vlan
l2 address filters on end real network device (for unicast and for
multicast) and drop redundant not expected packet income.
If CONFIG_VLAN_8021Q_IVDF is enabled the following changes are
applied, and only for ethernet network devices.
By default every ethernet netdev needs vid len = 2 bytes to be able to
hold up to 4096 vids. So set it for every eth device to be correct,
except vlan devs.
In order to shrink all addresses of devices above vlan, the vid_len
for vlan dev = 0, as result all suckers sync their addresses to common
base not taking in to account vid part (vid_len of "to" devices is
important only). And only vlan device is the source of addresses with
actual its vid set, propagating it to parent devices while rx_mode().
Also, don't bother those ethernet devices that at this moment are not
moved to vlan addressing scheme, so while end ethernet device is
created - set vid_len to 0, thus, while syncing, its address space is
concatenated to one dimensional like usual, and who needs IVDF - set
it to NET_8021Q_VID_TSIZE.
There is another decision - is to inherit vid_len or some feature flag
from end root device in order to all upper devices have vlan extended
address space only if exact end real device have such capability. But
I didn't, because it requires more changes and probably I'm not
familiar with all places where it should be inherited, I would
appreciate if someone can guid where it's applicable, then it could
become a little bit more limited.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
include/linux/if_vlan.h | 1 +
net/8021q/Kconfig | 12 ++++++++++++
net/8021q/vlan_core.c | 12 ++++++++++++
net/8021q/vlan_dev.c | 1 +
net/ethernet/eth.c | 10 ++++++++--
5 files changed, 34 insertions(+), 2 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 94657f3c483a..9c914b31d208 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -137,6 +137,7 @@ extern int vlan_for_each(struct net_device *dev,
int (*action)(struct net_device *dev, int vid,
void *arg), void *arg);
extern u16 vlan_dev_get_addr_vid(struct net_device *dev, const u8 *addr);
+extern void vlan_dev_ivdf_set(struct net_device *dev, int enable);
extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig
index 42320180967f..3e843045739c 100644
--- a/net/8021q/Kconfig
+++ b/net/8021q/Kconfig
@@ -38,3 +38,15 @@ config VLAN_8021Q_MVRP
supersedes GVRP and is not backwards-compatible.
If unsure, say N.
+
+config VLAN_8021Q_IVDF
+ bool "IVDF (Individual Virtual Device Filtering) support"
+ depends on VLAN_8021Q
+ help
+ Select this to enable IVDF addressing scheme support. IVDF is used
+ for automatic propagation of registered VLANs addresses to real end
+ devices. If no device supporting IVDF then disable this as it can
+ consume some memory in configuration with complex network device
+ structures to hold vlan addresses.
+
+ If unsure, say N.
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index fe2ac64c13f8..310b6cd39f22 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -454,6 +454,18 @@ bool vlan_uses_dev(const struct net_device *dev)
}
EXPORT_SYMBOL(vlan_uses_dev);
+void vlan_dev_ivdf_set(struct net_device *dev, int enable)
+{
+#ifdef CONFIG_VLAN_8021Q_IVDF
+ if (enable) {
+ dev->vid_len = NET_8021Q_VID_TSIZE;
+ return;
+ }
+#endif
+ dev->vid_len = 0;
+}
+EXPORT_SYMBOL(vlan_dev_ivdf_set);
+
u16 vlan_dev_get_addr_vid(struct net_device *dev, const u8 *addr)
{
u16 vid = 0;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 634436e780f1..e4120aca4b9b 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -896,5 +896,6 @@ void vlan_setup(struct net_device *dev)
dev->min_mtu = 0;
dev->max_mtu = ETH_MAX_MTU;
+ vlan_dev_ivdf_set(dev, 0);
eth_zero_addr(dev->broadcast);
}
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f7a3d7a171c7..95497cac24eb 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -381,6 +381,7 @@ void ether_setup(struct net_device *dev)
dev->flags = IFF_BROADCAST|IFF_MULTICAST;
dev->priv_flags |= IFF_TX_SKB_SHARING;
+ vlan_dev_ivdf_set(dev, 1);
eth_broadcast_addr(dev->broadcast);
}
@@ -404,8 +405,13 @@ EXPORT_SYMBOL(ether_setup);
struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
unsigned int rxqs)
{
- return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN,
- ether_setup, txqs, rxqs);
+ struct net_device *dev;
+
+ dev = alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN,
+ ether_setup, txqs, rxqs);
+
+ vlan_dev_ivdf_set(dev, 0);
+ return dev;
}
EXPORT_SYMBOL(alloc_etherdev_mqs);
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 3/6] net: 8021q: vlan_dev: add vid tag for vlan device own address
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
The vlan device address is held separately from uc/mc lists and
handled differently. The vlan dev address is bound with real device
address only if it's inherited from init, in all other cases it's
separate address entry in uc list. With vid set, the address becomes
not inherited from real device after it's set manually as before, but
is part of uc list any way, with appropriate vid tag set. If vid_len
for real device is 0, the behaviour is the same as before this change,
so shouldn't be any impact on systems w/o individual virtual device
filtering (IVDF) enabled. This allows to control and sync vlan device
address and disable concrete vlan packet income when vlan interface is
down.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
net/8021q/vlan.c | 3 ++
net/8021q/vlan_dev.c | 76 +++++++++++++++++++++++++++++++++-----------
2 files changed, 60 insertions(+), 19 deletions(-)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index dc4411165e43..9c72551a9a1e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -295,6 +295,9 @@ static void vlan_sync_address(struct net_device *dev,
if (vlan_dev_inherit_address(vlandev, dev))
goto out;
+ if (dev->vid_len)
+ goto out;
+
/* vlan address was different from the old address and is equal to
* the new address */
if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) &&
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 93d20b1f4916..634436e780f1 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -257,12 +257,61 @@ static void vlan_dev_set_addr_vid(struct net_device *vlan_dev, u8 *addr)
addr[vlan_dev->addr_len + 1] = (vid >> 8) & 0xf;
}
+static int vlan_dev_add_addr(struct net_device *dev, u8 *addr)
+{
+ struct net_device *real_dev = vlan_dev_real_dev(dev);
+ unsigned char naddr[ETH_ALEN + NET_8021Q_VID_TSIZE];
+
+ if (real_dev->vid_len) {
+ memcpy(naddr, addr, dev->addr_len);
+ vlan_dev_set_addr_vid(dev, naddr);
+ return dev_vid_uc_add(real_dev, naddr);
+ }
+
+ if (ether_addr_equal(addr, real_dev->dev_addr))
+ return 0;
+
+ return dev_uc_add(real_dev, addr);
+}
+
+static void vlan_dev_del_addr(struct net_device *dev, u8 *addr)
+{
+ struct net_device *real_dev = vlan_dev_real_dev(dev);
+ unsigned char naddr[ETH_ALEN + NET_8021Q_VID_TSIZE];
+
+ if (real_dev->vid_len) {
+ memcpy(naddr, addr, dev->addr_len);
+ vlan_dev_set_addr_vid(dev, naddr);
+ dev_vid_uc_del(real_dev, naddr);
+ return;
+ }
+
+ if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
+ dev_uc_del(real_dev, addr);
+}
+
+static int vlan_dev_subs_addr(struct net_device *dev, u8 *addr)
+{
+ int err;
+
+ err = vlan_dev_add_addr(dev, addr);
+ if (err < 0)
+ return err;
+
+ vlan_dev_del_addr(dev, dev->dev_addr);
+ return err;
+}
+
bool vlan_dev_inherit_address(struct net_device *dev,
struct net_device *real_dev)
{
if (dev->addr_assign_type != NET_ADDR_STOLEN)
return false;
+ if (real_dev->vid_len)
+ if (vlan_dev_subs_addr(dev, real_dev->dev_addr))
+ return false;
+
ether_addr_copy(dev->dev_addr, real_dev->dev_addr);
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return true;
@@ -278,9 +327,10 @@ static int vlan_dev_open(struct net_device *dev)
!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
return -ENETDOWN;
- if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) &&
- !vlan_dev_inherit_address(dev, real_dev)) {
- err = dev_uc_add(real_dev, dev->dev_addr);
+ if (ether_addr_equal(dev->dev_addr, real_dev->dev_addr) ||
+ (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr) &&
+ !vlan_dev_inherit_address(dev, real_dev))) {
+ err = vlan_dev_add_addr(dev, dev->dev_addr);
if (err < 0)
goto out;
}
@@ -312,8 +362,7 @@ static int vlan_dev_open(struct net_device *dev)
if (dev->flags & IFF_ALLMULTI)
dev_set_allmulti(real_dev, -1);
del_unicast:
- if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
- dev_uc_del(real_dev, dev->dev_addr);
+ vlan_dev_del_addr(dev, dev->dev_addr);
out:
netif_carrier_off(dev);
return err;
@@ -331,18 +380,14 @@ static int vlan_dev_stop(struct net_device *dev)
if (dev->flags & IFF_PROMISC)
dev_set_promiscuity(real_dev, -1);
- if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
- dev_uc_del(real_dev, dev->dev_addr);
-
+ vlan_dev_del_addr(dev, dev->dev_addr);
netif_carrier_off(dev);
return 0;
}
static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
{
- struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
struct sockaddr *addr = p;
- int err;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
@@ -350,15 +395,8 @@ static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
if (!(dev->flags & IFF_UP))
goto out;
- if (!ether_addr_equal(addr->sa_data, real_dev->dev_addr)) {
- err = dev_uc_add(real_dev, addr->sa_data);
- if (err < 0)
- return err;
- }
-
- if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
- dev_uc_del(real_dev, dev->dev_addr);
-
+ if (vlan_dev_subs_addr(dev, addr->sa_data))
+ return true;
out:
ether_addr_copy(dev->dev_addr, addr->sa_data);
return 0;
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 2/6] net: 8021q: vlan_dev: add vid tag to addresses of uc and mc lists
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
Update vlan mc and uc addresses with VID tag while propagating
addresses to lower devices, do this only if address is not synced.
It allows at end driver level to distinguish addresses belonging
to vlan devices.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
include/linux/if_vlan.h | 1 +
net/8021q/vlan.h | 2 ++
net/8021q/vlan_core.c | 13 +++++++++++++
net/8021q/vlan_dev.c | 26 ++++++++++++++++++++++++++
4 files changed, 42 insertions(+)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 4cca4da7a6de..94657f3c483a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -136,6 +136,7 @@ extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
extern int vlan_for_each(struct net_device *dev,
int (*action)(struct net_device *dev, int vid,
void *arg), void *arg);
+extern u16 vlan_dev_get_addr_vid(struct net_device *dev, const u8 *addr);
extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index c46daf09a501..f083c43c508f 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -6,6 +6,8 @@
#include <linux/u64_stats_sync.h>
#include <linux/list.h>
+#define NET_8021Q_VID_TSIZE 2
+
/* if this changes, algorithm will have to be reworked because this
* depends on completely exhausting the VLAN identifier space. Thus
* it gives constant time look-up, but in many cases it wastes memory.
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index a313165e7a67..fe2ac64c13f8 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -454,6 +454,19 @@ bool vlan_uses_dev(const struct net_device *dev)
}
EXPORT_SYMBOL(vlan_uses_dev);
+u16 vlan_dev_get_addr_vid(struct net_device *dev, const u8 *addr)
+{
+ u16 vid = 0;
+
+ if (dev->vid_len != NET_8021Q_VID_TSIZE)
+ return vid;
+
+ vid = addr[dev->addr_len];
+ vid |= (addr[dev->addr_len + 1] & 0xf) << 8;
+ return vid;
+}
+EXPORT_SYMBOL(vlan_dev_get_addr_vid);
+
static struct sk_buff *vlan_gro_receive(struct list_head *head,
struct sk_buff *skb)
{
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 15293c2a5dd8..93d20b1f4916 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -249,6 +249,14 @@ void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
}
+static void vlan_dev_set_addr_vid(struct net_device *vlan_dev, u8 *addr)
+{
+ u16 vid = vlan_dev_vlan_id(vlan_dev);
+
+ addr[vlan_dev->addr_len] = vid & 0xff;
+ addr[vlan_dev->addr_len + 1] = (vid >> 8) & 0xf;
+}
+
bool vlan_dev_inherit_address(struct net_device *dev,
struct net_device *real_dev)
{
@@ -480,8 +488,26 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
}
}
+static void vlan_dev_align_addr_vid(struct net_device *vlan_dev)
+{
+ struct net_device *real_dev = vlan_dev_real_dev(vlan_dev);
+ struct netdev_hw_addr *ha;
+
+ if (!real_dev->vid_len)
+ return;
+
+ netdev_for_each_mc_addr(ha, vlan_dev)
+ if (!ha->sync_cnt)
+ vlan_dev_set_addr_vid(vlan_dev, ha->addr);
+
+ netdev_for_each_uc_addr(ha, vlan_dev)
+ if (!ha->sync_cnt)
+ vlan_dev_set_addr_vid(vlan_dev, ha->addr);
+}
+
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
{
+ vlan_dev_align_addr_vid(vlan_dev);
dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
--
2.17.1
^ permalink raw reply related
* [PATCH net-next 1/6] net: core: dev_addr_lists: add VID to device address
From: Ivan Khoronzhuk @ 2019-02-26 18:45 UTC (permalink / raw)
To: davem, grygorii.strashko, f.fainelli
Cc: linux-omap, netdev, linux-kernel, jiri, ilias.apalodimas,
Ivan Khoronzhuk
In-Reply-To: <20190226184556.16082-1-ivan.khoronzhuk@linaro.org>
Despite this is supposed to be used for Ethernet VLANs, not Ethernet
addresses with space for VID also can reuse this, so VID is considered
as virtual ID extension, not belonging strictly to Ethernet VLAN VIDs,
and overall change can be named individual virtual device filtering
(IVDF).
This patch adds VID tag at the end of each address. The actual
reserved address size is 32 bytes. For Ethernet addresses with 6 bytes
long that's possible to add tag w/o increasing address size. Thus,
each address for the case has 32 - 6 = 26 bytes to hold additional
info, say VID for virtual device addresses.
Therefore, when addresses are synced to the address list of parent
device the address list of latter can contain separate addresses for
virtual devices. It allows to track separate address tables for
virtual devices if they present and the device can be placed on
any place of device tree as the address is propagated to to the end
real device thru *_sync()/ndo_set_rx_mode() APIs. Also it simplifies
handling VID addresses at real device when it supports IVDF.
If parent device doesn't want to have virtual addresses in its address
space the vid_len has to be 0, thus its address space is "shrunk" to
the state as before this patch. For now it's 0 for every device. It
allows two devices with and w/o IVDF to be part of same bond device
for instance.
The end real device supporting IVDF can retrieve VID tag from an
address and set it for a given virtual device only. By default, vid 0
is used for real devices to distinguish it from virtual addresses.
See next patches to see how it's used.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
include/linux/netdevice.h | 4 ++
net/core/dev_addr_lists.c | 124 +++++++++++++++++++++++++++++++-------
2 files changed, 105 insertions(+), 23 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 58e83bd7a861..74fef35b6bec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1660,6 +1660,7 @@ enum netdev_priv_flags {
* @perm_addr: Permanent hw address
* @addr_assign_type: Hw address assignment type
* @addr_len: Hardware address length
+ * @vid_len: Virtual ID length, set in case of IVDF
* @neigh_priv_len: Used in neigh_alloc()
* @dev_id: Used to differentiate devices that share
* the same link layer address
@@ -1889,6 +1890,7 @@ struct net_device {
unsigned char perm_addr[MAX_ADDR_LEN];
unsigned char addr_assign_type;
unsigned char addr_len;
+ unsigned char vid_len;
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
@@ -4141,8 +4143,10 @@ int dev_addr_init(struct net_device *dev);
/* Functions used for unicast addresses handling */
int dev_uc_add(struct net_device *dev, const unsigned char *addr);
+int dev_vid_uc_add(struct net_device *dev, const unsigned char *addr);
int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr);
int dev_uc_del(struct net_device *dev, const unsigned char *addr);
+int dev_vid_uc_del(struct net_device *dev, const unsigned char *addr);
int dev_uc_sync(struct net_device *to, struct net_device *from);
int dev_uc_sync_multiple(struct net_device *to, struct net_device *from);
void dev_uc_unsync(struct net_device *to, struct net_device *from);
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index a6723b306717..e3c80e044b8c 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -545,6 +545,26 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr,
}
EXPORT_SYMBOL(dev_addr_del);
+static int get_addr_len(struct net_device *dev)
+{
+ return dev->addr_len + dev->vid_len;
+}
+
+static int set_vid_addr(struct net_device *dev, const unsigned char *addr,
+ unsigned char *naddr)
+{
+ int i;
+
+ if (!dev->vid_len)
+ return dev->addr_len;
+
+ memcpy(naddr, addr, dev->addr_len);
+ for (i = 0; i < dev->vid_len; i++)
+ naddr[dev->addr_len + i] = 0;
+
+ return get_addr_len(dev);
+}
+
/*
* Unicast list handling functions
*/
@@ -556,18 +576,22 @@ EXPORT_SYMBOL(dev_addr_del);
*/
int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr)
{
+ unsigned char naddr[MAX_ADDR_LEN];
struct netdev_hw_addr *ha;
- int err;
+ int addr_len, err;
+
+ addr_len = set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
netif_addr_lock_bh(dev);
list_for_each_entry(ha, &dev->uc.list, list) {
- if (!memcmp(ha->addr, addr, dev->addr_len) &&
+ if (!memcmp(ha->addr, addr, addr_len) &&
ha->type == NETDEV_HW_ADDR_T_UNICAST) {
err = -EEXIST;
goto out;
}
}
- err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len,
+ err = __hw_addr_create_ex(&dev->uc, addr, addr_len,
NETDEV_HW_ADDR_T_UNICAST, true, false);
if (!err)
__dev_set_rx_mode(dev);
@@ -578,47 +602,89 @@ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr)
EXPORT_SYMBOL(dev_uc_add_excl);
/**
- * dev_uc_add - Add a secondary unicast address
+ * dev_vid_uc_add - Add a secondary unicast address with tag
* @dev: device
- * @addr: address to add
+ * @addr: address to add, includes vid tag already
*
* Add a secondary unicast address to the device or increase
* the reference count if it already exists.
*/
-int dev_uc_add(struct net_device *dev, const unsigned char *addr)
+int dev_vid_uc_add(struct net_device *dev, const unsigned char *addr)
{
int err;
netif_addr_lock_bh(dev);
- err = __hw_addr_add(&dev->uc, addr, dev->addr_len,
+ err = __hw_addr_add(&dev->uc, addr, get_addr_len(dev),
NETDEV_HW_ADDR_T_UNICAST);
if (!err)
__dev_set_rx_mode(dev);
netif_addr_unlock_bh(dev);
return err;
}
+EXPORT_SYMBOL(dev_vid_uc_add);
+
+/**
+ * dev_uc_add - Add a secondary unicast address
+ * @dev: device
+ * @addr: address to add
+ *
+ * Add a secondary unicast address to the device or increase
+ * the reference count if it already exists.
+ */
+int dev_uc_add(struct net_device *dev, const unsigned char *addr)
+{
+ unsigned char naddr[MAX_ADDR_LEN];
+ int err;
+
+ set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
+
+ err = dev_vid_uc_add(dev, addr);
+ return err;
+}
EXPORT_SYMBOL(dev_uc_add);
/**
* dev_uc_del - Release secondary unicast address.
* @dev: device
- * @addr: address to delete
+ * @addr: address to delete, includes vid tag already
*
* Release reference to a secondary unicast address and remove it
* from the device if the reference count drops to zero.
*/
-int dev_uc_del(struct net_device *dev, const unsigned char *addr)
+int dev_vid_uc_del(struct net_device *dev, const unsigned char *addr)
{
int err;
netif_addr_lock_bh(dev);
- err = __hw_addr_del(&dev->uc, addr, dev->addr_len,
+ err = __hw_addr_del(&dev->uc, addr, get_addr_len(dev),
NETDEV_HW_ADDR_T_UNICAST);
if (!err)
__dev_set_rx_mode(dev);
netif_addr_unlock_bh(dev);
return err;
}
+EXPORT_SYMBOL(dev_vid_uc_del);
+
+/**
+ * dev_uc_del - Release secondary unicast address.
+ * @dev: device
+ * @addr: address to delete
+ *
+ * Release reference to a secondary unicast address and remove it
+ * from the device if the reference count drops to zero.
+ */
+int dev_uc_del(struct net_device *dev, const unsigned char *addr)
+{
+ unsigned char naddr[MAX_ADDR_LEN];
+ int err;
+
+ set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
+
+ err = dev_vid_uc_del(dev, addr);
+ return err;
+}
EXPORT_SYMBOL(dev_uc_del);
/**
@@ -642,7 +708,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
return -EINVAL;
netif_addr_lock_nested(to);
- err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
+ err = __hw_addr_sync(&to->uc, &from->uc, get_addr_len(to));
if (!err)
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -672,7 +738,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
return -EINVAL;
netif_addr_lock_nested(to);
- err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
+ err = __hw_addr_sync_multiple(&to->uc, &from->uc, get_addr_len(to));
if (!err)
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -696,7 +762,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
- __hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
+ __hw_addr_unsync(&to->uc, &from->uc, get_addr_len(to));
__dev_set_rx_mode(to);
netif_addr_unlock(to);
netif_addr_unlock_bh(from);
@@ -740,18 +806,22 @@ EXPORT_SYMBOL(dev_uc_init);
*/
int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr)
{
+ unsigned char naddr[MAX_ADDR_LEN];
struct netdev_hw_addr *ha;
- int err;
+ int addr_len, err;
+
+ addr_len = set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
netif_addr_lock_bh(dev);
list_for_each_entry(ha, &dev->mc.list, list) {
- if (!memcmp(ha->addr, addr, dev->addr_len) &&
+ if (!memcmp(ha->addr, addr, addr_len) &&
ha->type == NETDEV_HW_ADDR_T_MULTICAST) {
err = -EEXIST;
goto out;
}
}
- err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len,
+ err = __hw_addr_create_ex(&dev->mc, addr, addr_len,
NETDEV_HW_ADDR_T_MULTICAST, true, false);
if (!err)
__dev_set_rx_mode(dev);
@@ -764,10 +834,14 @@ EXPORT_SYMBOL(dev_mc_add_excl);
static int __dev_mc_add(struct net_device *dev, const unsigned char *addr,
bool global)
{
- int err;
+ unsigned char naddr[MAX_ADDR_LEN];
+ int addr_len, err;
+
+ addr_len = set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
netif_addr_lock_bh(dev);
- err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len,
+ err = __hw_addr_add_ex(&dev->mc, addr, addr_len,
NETDEV_HW_ADDR_T_MULTICAST, global, false, 0);
if (!err)
__dev_set_rx_mode(dev);
@@ -804,10 +878,14 @@ EXPORT_SYMBOL(dev_mc_add_global);
static int __dev_mc_del(struct net_device *dev, const unsigned char *addr,
bool global)
{
- int err;
+ unsigned char naddr[MAX_ADDR_LEN];
+ int addr_len, err;
+
+ addr_len = set_vid_addr(dev, addr, naddr);
+ addr = dev->vid_len ? naddr : addr;
netif_addr_lock_bh(dev);
- err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len,
+ err = __hw_addr_del_ex(&dev->mc, addr, addr_len,
NETDEV_HW_ADDR_T_MULTICAST, global, false);
if (!err)
__dev_set_rx_mode(dev);
@@ -863,7 +941,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
return -EINVAL;
netif_addr_lock_nested(to);
- err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
+ err = __hw_addr_sync(&to->mc, &from->mc, get_addr_len(to));
if (!err)
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -893,7 +971,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
return -EINVAL;
netif_addr_lock_nested(to);
- err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
+ err = __hw_addr_sync_multiple(&to->mc, &from->mc, get_addr_len(to));
if (!err)
__dev_set_rx_mode(to);
netif_addr_unlock(to);
@@ -917,7 +995,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
- __hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
+ __hw_addr_unsync(&to->mc, &from->mc, get_addr_len(to));
__dev_set_rx_mode(to);
netif_addr_unlock(to);
netif_addr_unlock_bh(from);
--
2.17.1
^ permalink raw reply related
* Re: [RFC] nasty corner case in unix_dgram_sendmsg()
From: Al Viro @ 2019-02-26 19:03 UTC (permalink / raw)
To: Rainer Weikusat; +Cc: Jason Baron, netdev
In-Reply-To: <878sy2k1m3.fsf@doppelsaurus.mobileactivedefense.com>
On Tue, Feb 26, 2019 at 03:31:32PM +0000, Rainer Weikusat wrote:
> Al Viro <viro@zeniv.linux.org.uk> writes:
> > On Tue, Feb 26, 2019 at 06:28:17AM +0000, Al Viro wrote:
>
> [...]
>
>
> >> * if after relocking we see that unix_peer(sk) now
> >> is equal to other, we arrange for wakeup forwarding from other's
> >> peer_wait *and* if that has (likely) succeeded we fail with -EAGAIN.
> >> Huh?
>
> This returns 1 if sending isn't possible at the moment, ie, if the
> process which tries to send has to wait.
Except that in _this_ case we won't be waiting at all - we'll just
return -EAGAIN (as one could expect, what with no timeout given/left).
So what's the point of forwarding wakeups? IOW, what is it that we
expect to be waiting on sk_sleep(sk)? Note that it won't be this
call of sendmsg(2) (it'll bugger off without any further waiting).
It won't be subsequent calls of sendmsg(2) either - they either
sleep on skb allocation (which has nothing to do with destination)
_or_ they sleep directly on other->peer_wait. And poll(), while it
will be sleeping on sk_sleep(sk), will make sure to set the forwarding
up.
I understand what the unix_dgram_peer_wake_me() is doing; I understand
what unix_dgram_poll() is using it for. What I do not understand is
what's the point of doing that in unix_dgram_sendmsg()...
^ permalink raw reply
* Re: [PATCH 0/3] soc: fsl: dpio: enable and configure cache stashing
From: Li Yang @ 2019-02-26 19:03 UTC (permalink / raw)
To: Ioana Ciornei
Cc: David Miller, Roy Pledge, Ioana Ciocoi Radulescu, Laurentiu Tudor,
Horia Geanta, brouer@redhat.com, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <VI1PR0402MB280056BBF62A86E1703C549BE07A0@VI1PR0402MB2800.eurprd04.prod.outlook.com>
On Mon, Feb 25, 2019 at 1:01 AM Ioana Ciornei <ioana.ciornei@nxp.com> wrote:
>
> > Subject: Re: [PATCH 0/3] soc: fsl: dpio: enable and configure cache stashing
> >
> > From: Ioana Ciornei <ioana.ciornei@nxp.com>
> > Date: Sat, 23 Feb 2019 08:48:42 +0000
> >
> > > The first two patches enable cache stashing and configure the core
> > > cluster destination per software portal while the third patch is the
> > > one configuring the amount of stashing on a queue.
> >
> > Should I merge this series in via my networking tree?
>
> Even though it would be really good to have this on the networking tree as soon as possible, I am afraid that patch 2/3 is not going to apply cleanly because it touches the same areas of code that some other patches on Leo's tree are.
Hi David,
What shall we do if we want to get this in the 5.1? Since the change
on the ethernet driver is pretty small, can I get your ACK on that
patch and merge the series through my tree? Otherwise I can also try
to get the dpio patches in next merge window, and you can apply the
Ethernet patch after that.
Regards,
Leo
^ permalink raw reply
* Re: [PATCH v2] iov_iter: optimize page_copy_sane()
From: Al Viro @ 2019-02-26 19:04 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David S . Miller, linux-kernel, netdev, Eric Dumazet
In-Reply-To: <20190226184239.49946-1-edumazet@google.com>
On Tue, Feb 26, 2019 at 10:42:39AM -0800, Eric Dumazet wrote:
> Avoid cache line miss dereferencing struct page if we can.
>
> page_copy_sane() mostly deals with order-0 pages.
>
> Extra cache line miss is visible on TCP recvmsg() calls dealing
> with GRO packets (typically 45 page frags are attached to one skb).
>
> Bringing the 45 struct pages into cpu cache while copying the data
> is not free, since the freeing of the skb (and associated
> page frags put_page()) can happen after cache lines have been evicted.
Applied.
^ permalink raw reply
* [PATCH v1 net] lan743x: Fix TX Stall Issue
From: Bryan Whitehead @ 2019-02-26 19:06 UTC (permalink / raw)
To: davem; +Cc: netdev, UNGLinuxDriver
It has been observed that tx queue stalls while downloading
from certain web sites (example www.speedtest.net)
The cause has been tracked down to a corner case where
dma descriptors where not setup properly. And there for a tx
completion interrupt was not signaled.
This fix corrects the problem by properly marking the end of
a multi descriptor transmission.
fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
---
drivers/net/ethernet/microchip/lan743x_main.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 310807e..4d1b4a2 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1400,7 +1400,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
}
static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
- unsigned int frame_length)
+ unsigned int frame_length,
+ int nr_frags)
{
/* called only from within lan743x_tx_xmit_frame.
* assuming tx->ring_lock has already been acquired.
@@ -1410,6 +1411,10 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
/* wrap up previous descriptor */
tx->frame_data0 |= TX_DESC_DATA0_EXT_;
+ if (nr_frags <= 0) {
+ tx->frame_data0 |= TX_DESC_DATA0_LS_;
+ tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ }
tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
tx_descriptor->data0 = tx->frame_data0;
@@ -1514,8 +1519,11 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
u32 tx_tail_flags = 0;
/* wrap up previous descriptor */
- tx->frame_data0 |= TX_DESC_DATA0_LS_;
- tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ if ((tx->frame_data0 & TX_DESC_DATA0_DTYPE_MASK_) ==
+ TX_DESC_DATA0_DTYPE_DATA_) {
+ tx->frame_data0 |= TX_DESC_DATA0_LS_;
+ tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+ }
tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
buffer_info = &tx->buffer_info[tx->frame_tail];
@@ -1600,7 +1608,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
}
if (gso)
- lan743x_tx_frame_add_lso(tx, frame_length);
+ lan743x_tx_frame_add_lso(tx, frame_length, nr_frags);
if (nr_frags <= 0)
goto finish;
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v1 iproute2-next 1/4] rdma: add helper rd_sendrecv_msg()
From: Leon Romanovsky @ 2019-02-26 19:16 UTC (permalink / raw)
To: Steve Wise; +Cc: dsahern, stephen, netdev, linux-rdma
In-Reply-To: <7f48fc85-45ab-fe7d-9614-4c5eb50f8401@opengridcomputing.com>
[-- Attachment #1: Type: text/plain, Size: 3133 bytes --]
On Tue, Feb 26, 2019 at 11:19:12AM -0600, Steve Wise wrote:
>
> On 2/23/2019 3:31 AM, Leon Romanovsky wrote:
> > On Sat, Feb 23, 2019 at 11:26:15AM +0200, Leon Romanovsky wrote:
> >> On Thu, Feb 21, 2019 at 08:19:03AM -0800, Steve Wise wrote:
> >>> This function sends the constructed netlink message and then
> >>> receives the response, displaying any error text.
> >>>
> >>> Change 'rdma dev set' to use it.
> >>>
> >>> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
> >>> ---
> >>> rdma/dev.c | 2 +-
> >>> rdma/rdma.h | 1 +
> >>> rdma/utils.c | 21 +++++++++++++++++++++
> >>> 3 files changed, 23 insertions(+), 1 deletion(-)
> >>>
> >>> diff --git a/rdma/dev.c b/rdma/dev.c
> >>> index 60ff4b31e320..d2949c378f08 100644
> >>> --- a/rdma/dev.c
> >>> +++ b/rdma/dev.c
> >>> @@ -273,7 +273,7 @@ static int dev_set_name(struct rd *rd)
> >>> mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
> >>> mnl_attr_put_strz(rd->nlh, RDMA_NLDEV_ATTR_DEV_NAME, rd_argv(rd));
> >>>
> >>> - return rd_send_msg(rd);
> >>> + return rd_sendrecv_msg(rd, seq);
> >>> }
> >>>
> >>> static int dev_one_set(struct rd *rd)
> >>> diff --git a/rdma/rdma.h b/rdma/rdma.h
> >>> index 547bb5749a39..20be2f12c4f8 100644
> >>> --- a/rdma/rdma.h
> >>> +++ b/rdma/rdma.h
> >>> @@ -115,6 +115,7 @@ bool rd_check_is_key_exist(struct rd *rd, const char *key);
> >>> */
> >>> int rd_send_msg(struct rd *rd);
> >>> int rd_recv_msg(struct rd *rd, mnl_cb_t callback, void *data, uint32_t seq);
> >>> +int rd_sendrecv_msg(struct rd *rd, unsigned int seq);
> >>> void rd_prepare_msg(struct rd *rd, uint32_t cmd, uint32_t *seq, uint16_t flags);
> >>> int rd_dev_init_cb(const struct nlmsghdr *nlh, void *data);
> >>> int rd_attr_cb(const struct nlattr *attr, void *data);
> >>> diff --git a/rdma/utils.c b/rdma/utils.c
> >>> index 069d44fece10..a6f2826c9605 100644
> >>> --- a/rdma/utils.c
> >>> +++ b/rdma/utils.c
> >>> @@ -664,6 +664,27 @@ int rd_recv_msg(struct rd *rd, mnl_cb_t callback, void *data, unsigned int seq)
> >>> return ret;
> >>> }
> >>>
> >>> +static int null_cb(const struct nlmsghdr *nlh, void *data)
> >>> +{
> >>> + return MNL_CB_OK;
> >>> +}
> >>> +
> >>> +int rd_sendrecv_msg(struct rd *rd, unsigned int seq)
> >>> +{
> >>> + int ret;
> >>> +
> >>> + ret = rd_send_msg(rd);
> >>> + if (ret) {
> >>> + perror(NULL);
> >> This is more or less already done in rd_send_msg() and that function
> >> prints something in case of execution error. So the missing piece
> >> is to update rd_recv_msg(), so all places will "magically" print errors
> >> and not only dev_set_name().
> >>
> >>> + goto out;
> >>> + }
> >>> + ret = rd_recv_msg(rd, null_cb, rd, seq);
> > Will this "null_cb" work for all send/recv flows or only in flows where
> > response can be error only?
>
>
> Only those flows where no nl attributes are expected to be returned.
>
>
> > Will we need this recv_msg if we implement
> > extack support?
>
>
> I'm not sure how extack works. Do you know?
I can't say that :)
>
> Thanks!
>
> Steve.
>
>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 801 bytes --]
^ permalink raw reply
* Re: [PATCH v1 iproute2-next 1/4] rdma: add helper rd_sendrecv_msg()
From: Steve Wise @ 2019-02-26 19:55 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: dsahern, stephen, netdev, linux-rdma
In-Reply-To: <20190226191637.GW11231@mtr-leonro.mtl.com>
On 2/26/2019 1:16 PM, Leon Romanovsky wrote:
> On Tue, Feb 26, 2019 at 11:19:12AM -0600, Steve Wise wrote:
>> On 2/23/2019 3:31 AM, Leon Romanovsky wrote:
>>> On Sat, Feb 23, 2019 at 11:26:15AM +0200, Leon Romanovsky wrote:
>>>> On Thu, Feb 21, 2019 at 08:19:03AM -0800, Steve Wise wrote:
>>>>> This function sends the constructed netlink message and then
>>>>> receives the response, displaying any error text.
>>>>>
>>>>> Change 'rdma dev set' to use it.
>>>>>
>>>>> Signed-off-by: Steve Wise <swise@opengridcomputing.com>
>>>>> ---
>>>>> rdma/dev.c | 2 +-
>>>>> rdma/rdma.h | 1 +
>>>>> rdma/utils.c | 21 +++++++++++++++++++++
>>>>> 3 files changed, 23 insertions(+), 1 deletion(-)
>>>>>
>>>>> diff --git a/rdma/dev.c b/rdma/dev.c
>>>>> index 60ff4b31e320..d2949c378f08 100644
>>>>> --- a/rdma/dev.c
>>>>> +++ b/rdma/dev.c
>>>>> @@ -273,7 +273,7 @@ static int dev_set_name(struct rd *rd)
>>>>> mnl_attr_put_u32(rd->nlh, RDMA_NLDEV_ATTR_DEV_INDEX, rd->dev_idx);
>>>>> mnl_attr_put_strz(rd->nlh, RDMA_NLDEV_ATTR_DEV_NAME, rd_argv(rd));
>>>>>
>>>>> - return rd_send_msg(rd);
>>>>> + return rd_sendrecv_msg(rd, seq);
>>>>> }
>>>>>
>>>>> static int dev_one_set(struct rd *rd)
>>>>> diff --git a/rdma/rdma.h b/rdma/rdma.h
>>>>> index 547bb5749a39..20be2f12c4f8 100644
>>>>> --- a/rdma/rdma.h
>>>>> +++ b/rdma/rdma.h
>>>>> @@ -115,6 +115,7 @@ bool rd_check_is_key_exist(struct rd *rd, const char *key);
>>>>> */
>>>>> int rd_send_msg(struct rd *rd);
>>>>> int rd_recv_msg(struct rd *rd, mnl_cb_t callback, void *data, uint32_t seq);
>>>>> +int rd_sendrecv_msg(struct rd *rd, unsigned int seq);
>>>>> void rd_prepare_msg(struct rd *rd, uint32_t cmd, uint32_t *seq, uint16_t flags);
>>>>> int rd_dev_init_cb(const struct nlmsghdr *nlh, void *data);
>>>>> int rd_attr_cb(const struct nlattr *attr, void *data);
>>>>> diff --git a/rdma/utils.c b/rdma/utils.c
>>>>> index 069d44fece10..a6f2826c9605 100644
>>>>> --- a/rdma/utils.c
>>>>> +++ b/rdma/utils.c
>>>>> @@ -664,6 +664,27 @@ int rd_recv_msg(struct rd *rd, mnl_cb_t callback, void *data, unsigned int seq)
>>>>> return ret;
>>>>> }
>>>>>
>>>>> +static int null_cb(const struct nlmsghdr *nlh, void *data)
>>>>> +{
>>>>> + return MNL_CB_OK;
>>>>> +}
>>>>> +
>>>>> +int rd_sendrecv_msg(struct rd *rd, unsigned int seq)
>>>>> +{
>>>>> + int ret;
>>>>> +
>>>>> + ret = rd_send_msg(rd);
>>>>> + if (ret) {
>>>>> + perror(NULL);
>>>> This is more or less already done in rd_send_msg() and that function
>>>> prints something in case of execution error. So the missing piece
>>>> is to update rd_recv_msg(), so all places will "magically" print errors
>>>> and not only dev_set_name().
>>>>
>>>>> + goto out;
>>>>> + }
>>>>> + ret = rd_recv_msg(rd, null_cb, rd, seq);
>>> Will this "null_cb" work for all send/recv flows or only in flows where
>>> response can be error only?
>>
>> Only those flows where no nl attributes are expected to be returned.
>>
>>
>>> Will we need this recv_msg if we implement
>>> extack support?
>>
>> I'm not sure how extack works. Do you know?
> I can't say that :)
We can change things if/when we support extack.
Stevo.
^ permalink raw reply
* Re: [PATCH v1 iproute2-next 1/4] rdma: add helper rd_sendrecv_msg()
From: David Ahern @ 2019-02-26 19:55 UTC (permalink / raw)
To: Steve Wise, Leon Romanovsky; +Cc: stephen, netdev, linux-rdma
In-Reply-To: <7f48fc85-45ab-fe7d-9614-4c5eb50f8401@opengridcomputing.com>
On 2/26/19 10:19 AM, Steve Wise wrote:
>
>> Will we need this recv_msg if we implement
>> extack support?
>
> I'm not sure how extack works. Do you know?
see devlink/mnlg.c
mnlg_socket_open()
{
...
mnl_socket_setsockopt(nlg->nl, NETLINK_EXT_ACK, &one, sizeof(one));
...
}
and
mnlg_cb_error()
That code under devlink needs to be generic for both tools.
^ permalink raw reply
* [PATCH iproute2-next] devlink: add support for updating device flash
From: Jakub Kicinski @ 2019-02-26 20:20 UTC (permalink / raw)
To: dsahern, jiri, stephen; +Cc: oss-drivers, netdev, Jakub Kicinski
Add new command for updating flash of devices via devlink API.
Example:
$ cp flash-boot.bin /lib/firmware/
$ devlink dev flash pci/0000:05:00.0 file flash-boot.bin
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
devlink/devlink.c | 54 ++++++++++++++++++++++++++++++++++++++++++
man/man8/devlink-dev.8 | 32 +++++++++++++++++++++++++
2 files changed, 86 insertions(+)
diff --git a/devlink/devlink.c b/devlink/devlink.c
index 960cdda99b5b..5c6cac1f76dd 100644
--- a/devlink/devlink.c
+++ b/devlink/devlink.c
@@ -199,6 +199,8 @@ static void ifname_map_free(struct ifname_map *ifname_map)
#define DL_OPT_REGION_SNAPSHOT_ID BIT(22)
#define DL_OPT_REGION_ADDRESS BIT(23)
#define DL_OPT_REGION_LENGTH BIT(24)
+#define DL_OPT_FLASH_FILE_NAME BIT(25)
+#define DL_OPT_FLASH_COMPONENT BIT(26)
struct dl_opts {
uint32_t present; /* flags of present items */
@@ -230,6 +232,8 @@ struct dl_opts {
uint32_t region_snapshot_id;
uint64_t region_address;
uint64_t region_length;
+ const char *flash_file_name;
+ const char *flash_component;
};
struct dl {
@@ -1185,6 +1189,20 @@ static int dl_argv_parse(struct dl *dl, uint32_t o_required,
if (err)
return err;
o_found |= DL_OPT_REGION_LENGTH;
+ } else if (dl_argv_match(dl, "file") &&
+ (o_all & DL_OPT_FLASH_FILE_NAME)) {
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &opts->flash_file_name);
+ if (err)
+ return err;
+ o_found |= DL_OPT_FLASH_FILE_NAME;
+ } else if (dl_argv_match(dl, "component") &&
+ (o_all & DL_OPT_FLASH_COMPONENT)) {
+ dl_arg_inc(dl);
+ err = dl_argv_str(dl, &opts->flash_component);
+ if (err)
+ return err;
+ o_found |= DL_OPT_FLASH_COMPONENT;
} else {
pr_err("Unknown option \"%s\"\n", dl_argv(dl));
return -EINVAL;
@@ -1389,6 +1407,12 @@ static void dl_opts_put(struct nlmsghdr *nlh, struct dl *dl)
if (opts->present & DL_OPT_REGION_LENGTH)
mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN,
opts->region_length);
+ if (opts->present & DL_OPT_FLASH_FILE_NAME)
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME,
+ opts->flash_file_name);
+ if (opts->present & DL_OPT_FLASH_COMPONENT)
+ mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,
+ opts->flash_component);
}
static int dl_argv_parse_put(struct nlmsghdr *nlh, struct dl *dl,
@@ -1451,6 +1475,7 @@ static void cmd_dev_help(void)
pr_err(" devlink dev param show [DEV name PARAMETER]\n");
pr_err(" devlink dev reload DEV\n");
pr_err(" devlink dev info [ DEV ]\n");
+ pr_err(" devlink dev flash DEV file PATH [ component NAME ]\n");
}
static bool cmp_arr_last_handle(struct dl *dl, const char *bus_name,
@@ -2583,6 +2608,32 @@ static int cmd_dev_info(struct dl *dl)
return err;
}
+static void cmd_dev_flash_help(void)
+{
+ pr_err("Usage: devlink dev flash DEV file PATH [ component NAME ]\n");
+}
+
+static int cmd_dev_flash(struct dl *dl)
+{
+ struct nlmsghdr *nlh;
+ int err;
+
+ if (dl_argv_match(dl, "help") || dl_no_arg(dl)) {
+ cmd_dev_flash_help();
+ return 0;
+ }
+
+ nlh = mnlg_msg_prepare(dl->nlg, DEVLINK_CMD_FLASH_UPDATE,
+ NLM_F_REQUEST | NLM_F_ACK);
+
+ err = dl_argv_parse_put(nlh, dl, DL_OPT_HANDLE | DL_OPT_FLASH_FILE_NAME,
+ DL_OPT_FLASH_COMPONENT);
+ if (err)
+ return err;
+
+ return _mnlg_socket_sndrcv(dl->nlg, nlh, NULL, NULL);
+}
+
static int cmd_dev(struct dl *dl)
{
if (dl_argv_match(dl, "help")) {
@@ -2604,6 +2655,9 @@ static int cmd_dev(struct dl *dl)
} else if (dl_argv_match(dl, "info")) {
dl_arg_inc(dl);
return cmd_dev_info(dl);
+ } else if (dl_argv_match(dl, "flash")) {
+ dl_arg_inc(dl);
+ return cmd_dev_flash(dl);
}
pr_err("Command \"%s\" not found\n", dl_argv(dl));
return -ENOENT;
diff --git a/man/man8/devlink-dev.8 b/man/man8/devlink-dev.8
index 47838371fecd..1804463b2321 100644
--- a/man/man8/devlink-dev.8
+++ b/man/man8/devlink-dev.8
@@ -69,6 +69,16 @@ devlink-dev \- devlink device configuration
.IR DEV
.RI "]"
+.ti -8
+.BR "devlink dev flash"
+.IR DEV
+.BR file
+.IR PATH
+.RI "["
+.BR target
+.IR ID
+.RI "]"
+
.SH "DESCRIPTION"
.SS devlink dev show - display devlink device attributes
@@ -177,6 +187,28 @@ versions may differ after flash has been updated, but before reboot.
- specifies the devlink device to show.
If this argument is omitted all devices are listed.
+.SS devlink dev flash - write device's non-volatile memory.
+
+.PP
+.I "DEV"
+- specifies the devlink device to write to.
+
+.BR file
+.I PATH
+- Path to the file which will be written into device's flash. The path needs
+to be relative to one of the directories searched by the kernel firmware loaded,
+such as /lib/firmware.
+
+.BR component
+.I NAME
+- If device stores multiple firmware images in non-volatile memory, this
+parameter may be used to indicate which firmware image should be written.
+The value of
+.I NAME
+should match the component names from
+.B "devlink dev info"
+and may be driver-dependent.
+
.SH "EXAMPLES"
.PP
devlink dev show
--
2.19.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox