* [PATCH net-next v2 13/14] openvswitch: Refactor action alloc and copy api.
From: Pravin B Shelar @ 2014-11-06 9:19 UTC (permalink / raw)
To: davem; +Cc: netdev, Pravin B Shelar
There are two separate API to allocate and copy actions list. Anytime
OVS needs to copy action list, it needs to call both functions.
Following patch moves action allocation to copy function to avoid
code duplication.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Jarno Rajahalme <jrajahalme@nicira.com>
---
net/openvswitch/datapath.c | 25 ++++---------------------
net/openvswitch/flow_netlink.c | 24 +++++++++++++++++-------
net/openvswitch/flow_netlink.h | 1 -
3 files changed, 21 insertions(+), 29 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 5101780..014485e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -543,18 +543,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
if (err)
goto err_flow_free;
- acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_PACKET_ATTR_ACTIONS]));
- err = PTR_ERR(acts);
- if (IS_ERR(acts))
- goto err_flow_free;
-
err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
&flow->key, &acts);
if (err)
goto err_flow_free;
rcu_assign_pointer(flow->sf_acts, acts);
-
OVS_CB(packet)->egress_tun_info = NULL;
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
@@ -872,16 +866,11 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
/* Validate actions. */
- acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
- error = PTR_ERR(acts);
- if (IS_ERR(acts))
- goto err_kfree_flow;
-
error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
&acts);
if (error) {
OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
- goto err_kfree_acts;
+ goto err_kfree_flow;
}
reply = ovs_flow_cmd_alloc_info(acts, info, false);
@@ -972,6 +961,7 @@ error:
return error;
}
+/* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
const struct sw_flow_key *key,
const struct sw_flow_mask *mask)
@@ -980,15 +970,10 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
struct sw_flow_key masked_key;
int error;
- acts = ovs_nla_alloc_flow_actions(nla_len(a));
- if (IS_ERR(acts))
- return acts;
-
ovs_flow_mask_key(&masked_key, key, mask);
error = ovs_nla_copy_actions(a, &masked_key, &acts);
if (error) {
- OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
- kfree(acts);
+ OVS_NLERR("Actions may not be safe on all matching packets.\n");
return ERR_PTR(error);
}
@@ -1028,10 +1013,8 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
error = PTR_ERR(acts);
goto error;
}
- }
- /* Can allocate before locking if have acts. */
- if (acts) {
+ /* Can allocate before locking if have acts. */
reply = ovs_flow_cmd_alloc_info(acts, info, false);
if (IS_ERR(reply)) {
error = PTR_ERR(reply);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 1050b28..482a0cb 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1284,7 +1284,7 @@ nla_put_failure:
#define MAX_ACTIONS_BUFSIZE (32 * 1024)
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size)
{
struct sw_flow_actions *sfa;
@@ -1329,7 +1329,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
new_acts_size = MAX_ACTIONS_BUFSIZE;
}
- acts = ovs_nla_alloc_flow_actions(new_acts_size);
+ acts = nla_alloc_flow_actions(new_acts_size);
if (IS_ERR(acts))
return (void *)acts;
@@ -1396,7 +1396,7 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
a->nla_len = sfa->actions_len - st_offset;
}
-static int ovs_nla_copy_actions__(const struct nlattr *attr,
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci);
@@ -1441,7 +1441,7 @@ static int validate_and_copy_sample(const struct nlattr *attr,
if (st_acts < 0)
return st_acts;
- err = ovs_nla_copy_actions__(actions, key, depth + 1, sfa,
+ err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa,
eth_type, vlan_tci);
if (err)
return err;
@@ -1684,7 +1684,7 @@ static int copy_action(const struct nlattr *from,
return 0;
}
-static int ovs_nla_copy_actions__(const struct nlattr *attr,
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci)
@@ -1846,8 +1846,18 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa)
{
- return ovs_nla_copy_actions__(attr, key, 0, sfa, key->eth.type,
- key->eth.tci);
+ int err;
+
+ *sfa = nla_alloc_flow_actions(nla_len(attr));
+ if (IS_ERR(*sfa))
+ return PTR_ERR(*sfa);
+
+ err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
+ key->eth.tci);
+ if (err)
+ kfree(*sfa);
+
+ return err;
}
static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 4f03706..eb0b177 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -56,7 +56,6 @@ int ovs_nla_copy_actions(const struct nlattr *attr,
int ovs_nla_put_actions(const struct nlattr *attr,
int len, struct sk_buff *skb);
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int actions_len);
void ovs_nla_free_flow_actions(struct sw_flow_actions *);
#endif /* flow_netlink.h */
--
1.9.3
^ permalink raw reply related
* [PATCH net-next v2 14/14] openvswitch: Avoid NULL mask check while building mask
From: Pravin B Shelar @ 2014-11-06 9:19 UTC (permalink / raw)
To: davem; +Cc: netdev, Pravin B Shelar
OVS does mask validation even if it does not need to convert
netlink mask attributes to mask structure. ovs_nla_get_match()
caller can pass NULL mask structure pointer if the caller does
not need mask. Therefore NULL check is required in SW_FLOW_KEY*
macros. Following patch does not convert mask netlink attributes
if mask pointer is NULL, so we do not need these checks in
SW_FLOW_KEY* macro.
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Acked-by: Daniele Di Proietto <ddiproietto@vmware.com>
Acked-by: Andy Zhou <azhou@nicira.com>
---
net/openvswitch/flow_netlink.c | 107 ++++++++++++++++++++---------------------
1 file changed, 53 insertions(+), 54 deletions(-)
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 482a0cb..ed31097 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -50,21 +50,18 @@
#include "flow_netlink.h"
-static void update_range__(struct sw_flow_match *match,
- size_t offset, size_t size, bool is_mask)
+static void update_range(struct sw_flow_match *match,
+ size_t offset, size_t size, bool is_mask)
{
- struct sw_flow_key_range *range = NULL;
+ struct sw_flow_key_range *range;
size_t start = rounddown(offset, sizeof(long));
size_t end = roundup(offset + size, sizeof(long));
if (!is_mask)
range = &match->range;
- else if (match->mask)
+ else
range = &match->mask->range;
- if (!range)
- return;
-
if (range->start == range->end) {
range->start = start;
range->end = end;
@@ -80,22 +77,20 @@ static void update_range__(struct sw_flow_match *match,
#define SW_FLOW_KEY_PUT(match, field, value, is_mask) \
do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- sizeof((match)->key->field), is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- (match)->mask->key.field = value; \
- } else { \
+ update_range(match, offsetof(struct sw_flow_key, field), \
+ sizeof((match)->key->field), is_mask); \
+ if (is_mask) \
+ (match)->mask->key.field = value; \
+ else \
(match)->key->field = value; \
- } \
} while (0)
#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \
do { \
- update_range__(match, offset, len, is_mask); \
+ update_range(match, offset, len, is_mask); \
if (is_mask) \
memcpy((u8 *)&(match)->mask->key + offset, value_p, \
- len); \
+ len); \
else \
memcpy((u8 *)(match)->key + offset, value_p, len); \
} while (0)
@@ -104,18 +99,16 @@ static void update_range__(struct sw_flow_match *match,
SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
value_p, len, is_mask)
-#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \
- do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- sizeof((match)->key->field), is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- memset((u8 *)&(match)->mask->key.field, value,\
- sizeof((match)->mask->key.field)); \
- } else { \
+#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \
+ do { \
+ update_range(match, offsetof(struct sw_flow_key, field), \
+ sizeof((match)->key->field), is_mask); \
+ if (is_mask) \
+ memset((u8 *)&(match)->mask->key.field, value, \
+ sizeof((match)->mask->key.field)); \
+ else \
memset((u8 *)&(match)->key->field, value, \
sizeof((match)->key->field)); \
- } \
} while (0)
static bool match_validate(const struct sw_flow_match *match,
@@ -677,8 +670,7 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
- } else if (!is_mask)
- SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
+ }
if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
__be16 eth_type;
@@ -903,8 +895,8 @@ static void mask_set_nlattr(struct nlattr *attr, u8 val)
* attribute specifies the mask field of the wildcarded flow.
*/
int ovs_nla_get_match(struct sw_flow_match *match,
- const struct nlattr *key,
- const struct nlattr *mask)
+ const struct nlattr *nla_key,
+ const struct nlattr *nla_mask)
{
const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
const struct nlattr *encap;
@@ -914,7 +906,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
bool encap_valid = false;
int err;
- err = parse_flow_nlattrs(key, a, &key_attrs);
+ err = parse_flow_nlattrs(nla_key, a, &key_attrs);
if (err)
return err;
@@ -955,36 +947,43 @@ int ovs_nla_get_match(struct sw_flow_match *match,
if (err)
return err;
- if (match->mask && !mask) {
- /* Create an exact match mask. We need to set to 0xff all the
- * 'match->mask' fields that have been touched in 'match->key'.
- * We cannot simply memset 'match->mask', because padding bytes
- * and fields not specified in 'match->key' should be left to 0.
- * Instead, we use a stream of netlink attributes, copied from
- * 'key' and set to 0xff: ovs_key_from_nlattrs() will take care
- * of filling 'match->mask' appropriately.
- */
- newmask = kmemdup(key, nla_total_size(nla_len(key)),
- GFP_KERNEL);
- if (!newmask)
- return -ENOMEM;
+ if (match->mask) {
+ if (!nla_mask) {
+ /* Create an exact match mask. We need to set to 0xff
+ * all the 'match->mask' fields that have been touched
+ * in 'match->key'. We cannot simply memset
+ * 'match->mask', because padding bytes and fields not
+ * specified in 'match->key' should be left to 0.
+ * Instead, we use a stream of netlink attributes,
+ * copied from 'key' and set to 0xff.
+ * ovs_key_from_nlattrs() will take care of filling
+ * 'match->mask' appropriately.
+ */
+ newmask = kmemdup(nla_key,
+ nla_total_size(nla_len(nla_key)),
+ GFP_KERNEL);
+ if (!newmask)
+ return -ENOMEM;
- mask_set_nlattr(newmask, 0xff);
+ mask_set_nlattr(newmask, 0xff);
- /* The userspace does not send tunnel attributes that are 0,
- * but we should not wildcard them nonetheless.
- */
- if (match->key->tun_key.ipv4_dst)
- SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true);
+ /* The userspace does not send tunnel attributes that
+ * are 0, but we should not wildcard them nonetheless.
+ */
+ if (match->key->tun_key.ipv4_dst)
+ SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
+ 0xff, true);
- mask = newmask;
- }
+ nla_mask = newmask;
+ }
- if (mask) {
- err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
+ err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs);
if (err)
goto free_newmask;
+ /* Always match on tci. */
+ SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
+
if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) {
__be16 eth_type = 0;
__be16 tci = 0;
--
1.9.3
^ permalink raw reply related
* [patch net-next 00/10] introduce rocker switch driver with hardware accelerated datapath api - phase 1: bridge fdb offload
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
Hi all.
This patchset is just the first phase of switch and switch-ish device
support api in kernel. Note that the api will extend (our complete work
can be pulled from https://github.com/jpirko/net-next-rocker).
So what this patchset includes:
- introduce switchdev api for implementing switch drivers (so far
only linux bridge fdb offload is covered)
- introduce rocker switch driver which implements switchdev api
As to the discussion if there is need to have specific class of device
representing the switch itself, so far we found no need to introduce that.
But we are generally ok with the idea and when the time comes and it will
be needed, it can be easily introduced without any disturbance.
This patchset introduces switch id export through rtnetlink and sysfs,
which is similar to what we have for port id in SR-IOV. I will send iproute2
patchset for showing the switch id for port netdevs once this is applied.
For detailed description, please see individual patches.
Jiri Pirko (5):
net: rename netdev_phys_port_id to more generic name
net: introduce generic switch devices support
rtnl: expose physical switch id for particular device
net-sysfs: expose physical switch id for particular device
rocker: introduce rocker switch driver
Scott Feldman (5):
bridge: introduce fdb offloading via switchdev
bridge: call netdev_sw_port_stp_update when bridge port STP status
changes
bridge: add API to notify bridge driver of learned FBD on offloaded
device
rocker: implement rocker ofdpa flow table manipulation
rocker: implement L2 bridge offloading
Documentation/networking/switchdev.txt | 59 +
MAINTAINERS | 14 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +-
drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +-
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +-
drivers/net/ethernet/rocker/Kconfig | 27 +
drivers/net/ethernet/rocker/Makefile | 5 +
drivers/net/ethernet/rocker/rocker.c | 4180 ++++++++++++++++++++++
drivers/net/ethernet/rocker/rocker.h | 427 +++
include/linux/if_bridge.h | 18 +
include/linux/netdevice.h | 48 +-
include/net/switchdev.h | 53 +
include/uapi/linux/if_link.h | 1 +
net/Kconfig | 1 +
net/Makefile | 3 +
net/bridge/br_fdb.c | 94 +-
net/bridge/br_netlink.c | 2 +
net/bridge/br_stp.c | 4 +
net/bridge/br_stp_if.c | 3 +
net/bridge/br_stp_timer.c | 2 +
net/core/dev.c | 2 +-
net/core/net-sysfs.c | 26 +-
net/core/rtnetlink.c | 30 +-
net/switchdev/Kconfig | 13 +
net/switchdev/Makefile | 5 +
net/switchdev/switchdev.c | 93 +
29 files changed, 5102 insertions(+), 18 deletions(-)
create mode 100644 Documentation/networking/switchdev.txt
create mode 100644 drivers/net/ethernet/rocker/Kconfig
create mode 100644 drivers/net/ethernet/rocker/Makefile
create mode 100644 drivers/net/ethernet/rocker/rocker.c
create mode 100644 drivers/net/ethernet/rocker/rocker.h
create mode 100644 include/net/switchdev.h
create mode 100644 net/switchdev/Kconfig
create mode 100644 net/switchdev/Makefile
create mode 100644 net/switchdev/switchdev.c
--
1.9.3
^ permalink raw reply
* [patch net-next 01/10] net: rename netdev_phys_port_id to more generic name
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
So this can be reused for identification of other "items" as well.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +-
drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 +-
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +-
include/linux/netdevice.h | 16 ++++++++--------
net/core/dev.c | 2 +-
net/core/net-sysfs.c | 2 +-
net/core/rtnetlink.c | 6 +++---
8 files changed, 17 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c4bd025..336ef3c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12537,7 +12537,7 @@ static int bnx2x_validate_addr(struct net_device *dev)
}
static int bnx2x_get_phys_port_id(struct net_device *netdev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
struct bnx2x *bp = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 1a98e23..d749165 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7373,7 +7373,7 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
#endif
static int i40e_get_phys_port_id(struct net_device *netdev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_pf *pf = np->vsi->back;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0efbae9..bd007c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2258,7 +2258,7 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st
#define PORT_ID_BYTE_LEN 8
static int mlx4_en_get_phys_port_id(struct net_device *dev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_dev *mdev = priv->mdev->dev;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index f5e29f7..6e514d2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -460,7 +460,7 @@ static void qlcnic_82xx_cancel_idc_work(struct qlcnic_adapter *adapter)
}
static int qlcnic_get_phys_port_id(struct net_device *netdev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_hardware_context *ahw = adapter->ahw;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4767f54..bbc730f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -753,13 +753,13 @@ struct netdev_fcoe_hbainfo {
};
#endif
-#define MAX_PHYS_PORT_ID_LEN 32
+#define MAX_PHYS_ITEM_ID_LEN 32
-/* This structure holds a unique identifier to identify the
- * physical port used by a netdevice.
+/* This structure holds a unique identifier to identify some
+ * physical item (port for example) used by a netdevice.
*/
-struct netdev_phys_port_id {
- unsigned char id[MAX_PHYS_PORT_ID_LEN];
+struct netdev_phys_item_id {
+ unsigned char id[MAX_PHYS_ITEM_ID_LEN];
unsigned char id_len;
};
@@ -975,7 +975,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
*
* int (*ndo_get_phys_port_id)(struct net_device *dev,
- * struct netdev_phys_port_id *ppid);
+ * struct netdev_phys_item_id *ppid);
* Called to get ID of physical port of this device. If driver does
* not implement this, it is assumed that the hw is not able to have
* multiple net devices on single physical port.
@@ -1149,7 +1149,7 @@ struct net_device_ops {
int (*ndo_change_carrier)(struct net_device *dev,
bool new_carrier);
int (*ndo_get_phys_port_id)(struct net_device *dev,
- struct netdev_phys_port_id *ppid);
+ struct netdev_phys_item_id *ppid);
void (*ndo_add_vxlan_port)(struct net_device *dev,
sa_family_t sa_family,
__be16 port);
@@ -2878,7 +2878,7 @@ void dev_set_group(struct net_device *, int);
int dev_set_mac_address(struct net_device *, struct sockaddr *);
int dev_change_carrier(struct net_device *, bool new_carrier);
int dev_get_phys_port_id(struct net_device *dev,
- struct netdev_phys_port_id *ppid);
+ struct netdev_phys_item_id *ppid);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
diff --git a/net/core/dev.c b/net/core/dev.c
index 40be481..a170bcb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5817,7 +5817,7 @@ EXPORT_SYMBOL(dev_change_carrier);
* Get device physical port ID
*/
int dev_get_phys_port_id(struct net_device *dev,
- struct netdev_phys_port_id *ppid)
+ struct netdev_phys_item_id *ppid)
{
const struct net_device_ops *ops = dev->netdev_ops;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 9dd0669..55dc4da 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -387,7 +387,7 @@ static ssize_t phys_port_id_show(struct device *dev,
return restart_syscall();
if (dev_isalive(netdev)) {
- struct netdev_phys_port_id ppid;
+ struct netdev_phys_item_id ppid;
ret = dev_get_phys_port_id(netdev, &ppid);
if (!ret)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a688268..1087c6d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -868,7 +868,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
- + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_PORT_ID */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -952,7 +952,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
- struct netdev_phys_port_id ppid;
+ struct netdev_phys_item_id ppid;
err = dev_get_phys_port_id(dev, &ppid);
if (err) {
@@ -1196,7 +1196,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_PROMISCUITY] = { .type = NLA_U32 },
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
- [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+ [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
};
--
1.9.3
^ permalink raw reply related
* [patch net-next 03/10] rtnl: expose physical switch id for particular device
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
The netdevice represents a port in a switch, it will expose
IFLA_PHYS_SWITCH_ID value via rtnl. Two netdevices with the same value
belong to one physical switch.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
include/uapi/linux/if_link.h | 1 +
net/core/rtnetlink.c | 26 +++++++++++++++++++++++++-
2 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7072d83..4163753 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -145,6 +145,7 @@ enum {
IFLA_CARRIER,
IFLA_PHYS_PORT_ID,
IFLA_CARRIER_CHANGES,
+ IFLA_PHYS_SWITCH_ID,
__IFLA_MAX
};
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1087c6d..f839354 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -43,6 +43,7 @@
#include <linux/inet.h>
#include <linux/netdevice.h>
+#include <net/switchdev.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
@@ -868,7 +869,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
- + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_PORT_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */
+ + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -967,6 +969,24 @@ static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
return 0;
}
+static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+ int err;
+ struct netdev_phys_item_id psid;
+
+ err = netdev_sw_parent_id_get(dev, &psid);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ if (nla_put(skb, IFLA_PHYS_SWITCH_ID, psid.id_len, psid.id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask)
@@ -1039,6 +1059,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (rtnl_phys_port_id_fill(skb, dev))
goto nla_put_failure;
+ if (rtnl_phys_switch_id_fill(skb, dev))
+ goto nla_put_failure;
+
attr = nla_reserve(skb, IFLA_STATS,
sizeof(struct rtnl_link_stats));
if (attr == NULL)
@@ -1198,6 +1221,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
[IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
+ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
--
1.9.3
^ permalink raw reply related
* [patch net-next 04/10] net-sysfs: expose physical switch id for particular device
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
net/core/net-sysfs.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 55dc4da..8e6603c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -12,6 +12,7 @@
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <net/switchdev.h>
#include <linux/if_arp.h>
#include <linux/slab.h>
#include <linux/nsproxy.h>
@@ -399,6 +400,28 @@ static ssize_t phys_port_id_show(struct device *dev,
}
static DEVICE_ATTR_RO(phys_port_id);
+static ssize_t phys_switch_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ ssize_t ret = -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (dev_isalive(netdev)) {
+ struct netdev_phys_item_id ppid;
+
+ ret = netdev_sw_parent_id_get(netdev, &ppid);
+ if (!ret)
+ ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
+ }
+ rtnl_unlock();
+
+ return ret;
+}
+static DEVICE_ATTR_RO(phys_switch_id);
+
static struct attribute *net_class_attrs[] = {
&dev_attr_netdev_group.attr,
&dev_attr_type.attr,
@@ -423,6 +446,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_flags.attr,
&dev_attr_tx_queue_len.attr,
&dev_attr_phys_port_id.attr,
+ &dev_attr_phys_switch_id.attr,
NULL,
};
ATTRIBUTE_GROUPS(net_class);
--
1.9.3
^ permalink raw reply related
* [patch net-next 05/10] rocker: introduce rocker switch driver
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
This patch introduces the first driver to benefit from the switchdev
infrastructure and to implement newly introduced switch ndos. This is a
driver for emulated switch chip implemented in qemu:
https://github.com/sfeldma/qemu-rocker/
This patch is a result of joint work with Scott Feldman.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
MAINTAINERS | 7 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/rocker/Kconfig | 27 +
drivers/net/ethernet/rocker/Makefile | 5 +
drivers/net/ethernet/rocker/rocker.c | 2062 ++++++++++++++++++++++++++++++++++
drivers/net/ethernet/rocker/rocker.h | 427 +++++++
7 files changed, 2530 insertions(+)
create mode 100644 drivers/net/ethernet/rocker/Kconfig
create mode 100644 drivers/net/ethernet/rocker/Makefile
create mode 100644 drivers/net/ethernet/rocker/rocker.c
create mode 100644 drivers/net/ethernet/rocker/rocker.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 776e078..7e15b50 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7807,6 +7807,13 @@ F: drivers/hid/hid-roccat*
F: include/linux/hid-roccat*
F: Documentation/ABI/*/sysfs-driver-hid-roccat*
+ROCKER DRIVER
+M: Jiri Pirko <jiri@resnulli.us>
+M: Scott Feldman <sfeldma@gmail.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/ethernet/rocker/
+
ROCKETPORT DRIVER
P: Comtrol Corp.
W: http://www.comtrol.com
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 1ed1fbb..df76050 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -155,6 +155,7 @@ source "drivers/net/ethernet/qualcomm/Kconfig"
source "drivers/net/ethernet/realtek/Kconfig"
source "drivers/net/ethernet/renesas/Kconfig"
source "drivers/net/ethernet/rdc/Kconfig"
+source "drivers/net/ethernet/rocker/Kconfig"
config S6GMAC
tristate "S6105 GMAC ethernet support"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 6e0b629..bf56f8b 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_NET_VENDOR_QUALCOMM) += qualcomm/
obj-$(CONFIG_NET_VENDOR_REALTEK) += realtek/
obj-$(CONFIG_SH_ETH) += renesas/
obj-$(CONFIG_NET_VENDOR_RDC) += rdc/
+obj-$(CONFIG_NET_VENDOR_ROCKER) += rocker/
obj-$(CONFIG_S6GMAC) += s6gmac.o
obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
diff --git a/drivers/net/ethernet/rocker/Kconfig b/drivers/net/ethernet/rocker/Kconfig
new file mode 100644
index 0000000..11a850e
--- /dev/null
+++ b/drivers/net/ethernet/rocker/Kconfig
@@ -0,0 +1,27 @@
+#
+# Rocker device configuration
+#
+
+config NET_VENDOR_ROCKER
+ bool "Rocker devices"
+ default y
+ ---help---
+ If you have a network device belonging to this class, say Y.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Rocker devices. If you say Y, you will be asked for
+ your specific card in the following questions.
+
+if NET_VENDOR_ROCKER
+
+config ROCKER
+ tristate "Rocker switch driver (EXPERIMENTAL)"
+ depends on PCI && NET_SWITCHDEV
+ ---help---
+ This driver supports Rocker switch device.
+
+ To compile this driver as a module, choose M here: the
+ module will be called rocker.
+
+endif # NET_VENDOR_ROCKER
diff --git a/drivers/net/ethernet/rocker/Makefile b/drivers/net/ethernet/rocker/Makefile
new file mode 100644
index 0000000..f85fb12
--- /dev/null
+++ b/drivers/net/ethernet/rocker/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Rocker network device drivers.
+#
+
+obj-$(CONFIG_ROCKER) += rocker.o
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
new file mode 100644
index 0000000..797481b
--- /dev/null
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -0,0 +1,2062 @@
+/*
+ * drivers/net/ethernet/rocker/rocker.c - Rocker switch device driver
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/spinlock.h>
+#include <linux/crc32.h>
+#include <linux/sort.h>
+#include <linux/random.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/switchdev.h>
+#include <net/rtnetlink.h>
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
+#include <generated/utsrelease.h>
+
+#include "rocker.h"
+
+static const char rocker_driver_name[] = "rocker";
+
+static const struct pci_device_id rocker_pci_id_table[] = {
+ {PCI_VDEVICE(REDHAT, PCI_DEVICE_ID_REDHAT_ROCKER), 0},
+ {0, }
+};
+
+struct rocker_desc_info {
+ char *data; /* mapped */
+ size_t data_size;
+ size_t tlv_size;
+ struct rocker_desc *desc;
+ DEFINE_DMA_UNMAP_ADDR(mapaddr);
+};
+
+struct rocker_dma_ring_info {
+ size_t size;
+ u32 head;
+ u32 tail;
+ struct rocker_desc *desc; /* mapped */
+ dma_addr_t mapaddr;
+ struct rocker_desc_info *desc_info;
+ unsigned int type;
+};
+
+struct rocker;
+
+struct rocker_port {
+ struct net_device *dev;
+ struct rocker *rocker;
+ unsigned port_number;
+ u32 lport;
+ struct napi_struct napi_tx;
+ struct napi_struct napi_rx;
+ struct rocker_dma_ring_info tx_ring;
+ struct rocker_dma_ring_info rx_ring;
+};
+
+struct rocker {
+ struct pci_dev *pdev;
+ u8 __iomem *hw_addr;
+ struct msix_entry *msix_entries;
+ unsigned port_count;
+ struct rocker_port **ports;
+ struct {
+ u64 id;
+ } hw;
+ spinlock_t cmd_ring_lock;
+ struct rocker_dma_ring_info cmd_ring;
+ struct rocker_dma_ring_info event_ring;
+};
+
+struct rocker_wait {
+ wait_queue_head_t wait;
+ bool done;
+ bool nowait;
+};
+
+static void rocker_wait_reset(struct rocker_wait *wait)
+{
+ wait->done = false;
+ wait->nowait = false;
+}
+
+static void rocker_wait_init(struct rocker_wait *wait)
+{
+ init_waitqueue_head(&wait->wait);
+ rocker_wait_reset(wait);
+}
+
+static struct rocker_wait *rocker_wait_create(gfp_t gfp)
+{
+ struct rocker_wait *wait;
+
+ wait = kmalloc(sizeof(*wait), gfp);
+ if (!wait)
+ return NULL;
+ rocker_wait_init(wait);
+ return wait;
+}
+
+static void rocker_wait_destroy(struct rocker_wait *work)
+{
+ kfree(work);
+}
+
+static bool rocker_wait_event_timeout(struct rocker_wait *wait,
+ unsigned long timeout)
+{
+ wait_event_timeout(wait->wait, wait->done, HZ / 10);
+ if (!wait->done)
+ return false;
+ return true;
+}
+
+static void rocker_wait_wake_up(struct rocker_wait *wait)
+{
+ wait->done = true;
+ wake_up(&wait->wait);
+}
+
+static u32 rocker_msix_vector(struct rocker *rocker, unsigned vector)
+{
+ return rocker->msix_entries[vector].vector;
+}
+
+static u32 rocker_msix_tx_vector(struct rocker_port *rocker_port)
+{
+ return rocker_msix_vector(rocker_port->rocker,
+ ROCKER_MSIX_VEC_TX(rocker_port->port_number));
+}
+
+static u32 rocker_msix_rx_vector(struct rocker_port *rocker_port)
+{
+ return rocker_msix_vector(rocker_port->rocker,
+ ROCKER_MSIX_VEC_RX(rocker_port->port_number));
+}
+
+#define rocker_write32(rocker, reg, val) \
+ writel((val), (rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_read32(rocker, reg) \
+ readl((rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_write64(rocker, reg, val) \
+ writeq((val), (rocker)->hw_addr + (ROCKER_ ## reg))
+#define rocker_read64(rocker, reg) \
+ readq((rocker)->hw_addr + (ROCKER_ ## reg))
+
+/*****************************
+ * HW basic testing functions
+ *****************************/
+
+static int rocker_reg_test(struct rocker *rocker)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ u64 test_reg;
+ u64 rnd;
+
+ rnd = prandom_u32();
+ rnd >>= 1;
+ rocker_write32(rocker, TEST_REG, rnd);
+ test_reg = rocker_read32(rocker, TEST_REG);
+ if (test_reg != rnd * 2) {
+ dev_err(&pdev->dev, "unexpected 32bit register value %08llx, expected %08llx\n",
+ test_reg, rnd * 2);
+ return -EIO;
+ }
+
+ rnd = prandom_u32();
+ rnd <<= 31;
+ rnd |= prandom_u32();
+ rocker_write64(rocker, TEST_REG64, rnd);
+ test_reg = rocker_read64(rocker, TEST_REG64);
+ if (test_reg != rnd * 2) {
+ dev_err(&pdev->dev, "unexpected 64bit register value %16llx, expected %16llx\n",
+ test_reg, rnd * 2);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static int rocker_dma_test_one(struct rocker *rocker, struct rocker_wait *wait,
+ u32 test_type, dma_addr_t dma_handle,
+ unsigned char *buf, unsigned char *expect,
+ size_t size)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int i;
+
+ rocker_wait_reset(wait);
+ rocker_write32(rocker, TEST_DMA_CTRL, test_type);
+
+ if (!rocker_wait_event_timeout(wait, HZ / 10)) {
+ dev_err(&pdev->dev, "no interrupt received within a timeout\n");
+ return -EIO;
+ }
+
+ for (i = 0; i < size; i++) {
+ if (buf[i] != expect[i]) {
+ dev_err(&pdev->dev, "unexpected memory content %02x at byte %x\n, %02x expected",
+ buf[i], i, expect[i]);
+ return -EIO;
+ }
+ }
+ return 0;
+}
+
+#define ROCKER_TEST_DMA_BUF_SIZE (PAGE_SIZE * 4)
+#define ROCKER_TEST_DMA_FILL_PATTERN 0x96
+
+static int rocker_dma_test_offset(struct rocker *rocker,
+ struct rocker_wait *wait, int offset)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ unsigned char *alloc;
+ unsigned char *buf;
+ unsigned char *expect;
+ dma_addr_t dma_handle;
+ int i;
+ int err;
+
+ alloc = kzalloc(ROCKER_TEST_DMA_BUF_SIZE * 2 + offset,
+ GFP_KERNEL | GFP_DMA);
+ if (!alloc)
+ return -ENOMEM;
+ buf = alloc + offset;
+ expect = buf + ROCKER_TEST_DMA_BUF_SIZE;
+
+ dma_handle = pci_map_single(pdev, buf, ROCKER_TEST_DMA_BUF_SIZE,
+ PCI_DMA_BIDIRECTIONAL);
+ if (pci_dma_mapping_error(pdev, dma_handle)) {
+ err = -EIO;
+ goto free_alloc;
+ }
+
+ rocker_write64(rocker, TEST_DMA_ADDR, dma_handle);
+ rocker_write32(rocker, TEST_DMA_SIZE, ROCKER_TEST_DMA_BUF_SIZE);
+
+ memset(expect, ROCKER_TEST_DMA_FILL_PATTERN, ROCKER_TEST_DMA_BUF_SIZE);
+ err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_FILL,
+ dma_handle, buf, expect,
+ ROCKER_TEST_DMA_BUF_SIZE);
+ if (err)
+ goto unmap;
+
+ memset(expect, 0, ROCKER_TEST_DMA_BUF_SIZE);
+ err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_CLEAR,
+ dma_handle, buf, expect,
+ ROCKER_TEST_DMA_BUF_SIZE);
+ if (err)
+ goto unmap;
+
+ prandom_bytes(buf, ROCKER_TEST_DMA_BUF_SIZE);
+ for (i = 0; i < ROCKER_TEST_DMA_BUF_SIZE; i++)
+ expect[i] = ~buf[i];
+ err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_INVERT,
+ dma_handle, buf, expect,
+ ROCKER_TEST_DMA_BUF_SIZE);
+ if (err)
+ goto unmap;
+
+unmap:
+ pci_unmap_single(pdev, dma_handle, ROCKER_TEST_DMA_BUF_SIZE,
+ PCI_DMA_BIDIRECTIONAL);
+free_alloc:
+ kfree(alloc);
+
+ return err;
+}
+
+static int rocker_dma_test(struct rocker *rocker, struct rocker_wait *wait)
+{
+ int i;
+ int err;
+
+ for (i = 0; i < 8; i++) {
+ err = rocker_dma_test_offset(rocker, wait, i);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+static irqreturn_t rocker_test_irq_handler(int irq, void *dev_id)
+{
+ struct rocker_wait *wait = dev_id;
+
+ rocker_wait_wake_up(wait);
+
+ return IRQ_HANDLED;
+}
+
+static int rocker_basic_hw_test(struct rocker *rocker)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ struct rocker_wait wait;
+ int err;
+
+ err = rocker_reg_test(rocker);
+ if (err) {
+ dev_err(&pdev->dev, "reg test failed\n");
+ return err;
+ }
+
+ err = request_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_TEST),
+ rocker_test_irq_handler, 0,
+ rocker_driver_name, &wait);
+ if (err) {
+ dev_err(&pdev->dev, "cannot assign test irq\n");
+ return err;
+ }
+
+ rocker_wait_init(&wait);
+ rocker_write32(rocker, TEST_IRQ, ROCKER_MSIX_VEC_TEST);
+
+ if (!rocker_wait_event_timeout(&wait, HZ / 10)) {
+ dev_err(&pdev->dev, "no interrupt received within a timeout\n");
+ err = -EIO;
+ goto free_irq;
+ }
+
+ err = rocker_dma_test(rocker, &wait);
+ if (err)
+ dev_err(&pdev->dev, "dma test failed\n");
+
+free_irq:
+ free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_TEST), &wait);
+ return err;
+}
+
+/******
+ * TLV
+ ******/
+
+#define ROCKER_TLV_ALIGNTO 8U
+#define ROCKER_TLV_ALIGN(len) \
+ (((len) + ROCKER_TLV_ALIGNTO - 1) & ~(ROCKER_TLV_ALIGNTO - 1))
+#define ROCKER_TLV_HDRLEN ROCKER_TLV_ALIGN(sizeof(struct rocker_tlv))
+
+/* <------- ROCKER_TLV_HDRLEN -------> <--- ROCKER_TLV_ALIGN(payload) --->
+ * +-----------------------------+- - -+- - - - - - - - - - - - - - -+- - -+
+ * | Header | Pad | Payload | Pad |
+ * | (struct rocker_tlv) | ing | | ing |
+ * +-----------------------------+- - -+- - - - - - - - - - - - - - -+- - -+
+ * <--------------------------- tlv->len -------------------------->
+ */
+
+static struct rocker_tlv *rocker_tlv_next(const struct rocker_tlv *tlv,
+ int *remaining)
+{
+ int totlen = ROCKER_TLV_ALIGN(tlv->len);
+
+ *remaining -= totlen;
+ return (struct rocker_tlv *) ((char *) tlv + totlen);
+}
+
+static int rocker_tlv_ok(const struct rocker_tlv *tlv, int remaining)
+{
+ return remaining >= (int) ROCKER_TLV_HDRLEN &&
+ tlv->len >= ROCKER_TLV_HDRLEN &&
+ tlv->len <= remaining;
+}
+
+#define rocker_tlv_for_each(pos, head, len, rem) \
+ for (pos = head, rem = len; \
+ rocker_tlv_ok(pos, rem); \
+ pos = rocker_tlv_next(pos, &(rem)))
+
+#define rocker_tlv_for_each_nested(pos, tlv, rem) \
+ rocker_tlv_for_each(pos, rocker_tlv_data(tlv), \
+ rocker_tlv_len(tlv), rem)
+
+static int rocker_tlv_attr_size(int payload)
+{
+ return ROCKER_TLV_HDRLEN + payload;
+}
+
+static int rocker_tlv_total_size(int payload)
+{
+ return ROCKER_TLV_ALIGN(rocker_tlv_attr_size(payload));
+}
+
+static int rocker_tlv_padlen(int payload)
+{
+ return rocker_tlv_total_size(payload) - rocker_tlv_attr_size(payload);
+}
+
+static int rocker_tlv_type(const struct rocker_tlv *tlv)
+{
+ return tlv->type;
+}
+
+static void *rocker_tlv_data(const struct rocker_tlv *tlv)
+{
+ return (char *) tlv + ROCKER_TLV_HDRLEN;
+}
+
+static int rocker_tlv_len(const struct rocker_tlv *tlv)
+{
+ return tlv->len - ROCKER_TLV_HDRLEN;
+}
+
+static u8 rocker_tlv_get_u8(const struct rocker_tlv *tlv)
+{
+ return *(u8 *) rocker_tlv_data(tlv);
+}
+
+static u16 rocker_tlv_get_u16(const struct rocker_tlv *tlv)
+{
+ return *(u16 *) rocker_tlv_data(tlv);
+}
+
+static u32 rocker_tlv_get_u32(const struct rocker_tlv *tlv)
+{
+ return *(u32 *) rocker_tlv_data(tlv);
+}
+
+static u64 rocker_tlv_get_u64(const struct rocker_tlv *tlv)
+{
+ return *(u64 *) rocker_tlv_data(tlv);
+}
+
+static void rocker_tlv_parse(struct rocker_tlv **tb, int maxtype,
+ const char *buf, int buf_len)
+{
+ const struct rocker_tlv *tlv;
+ const struct rocker_tlv *head = (const struct rocker_tlv *) buf;
+ int rem;
+
+ memset(tb, 0, sizeof(struct rocker_tlv *) * (maxtype + 1));
+
+ rocker_tlv_for_each(tlv, head, buf_len, rem) {
+ u32 type = rocker_tlv_type(tlv);
+
+ if (type > 0 && type <= maxtype)
+ tb[type] = (struct rocker_tlv *) tlv;
+ }
+}
+
+static void rocker_tlv_parse_nested(struct rocker_tlv **tb, int maxtype,
+ const struct rocker_tlv *tlv)
+{
+ rocker_tlv_parse(tb, maxtype, rocker_tlv_data(tlv),
+ rocker_tlv_len(tlv));
+}
+
+static void rocker_tlv_parse_desc(struct rocker_tlv **tb, int maxtype,
+ struct rocker_desc_info *desc_info)
+{
+ rocker_tlv_parse(tb, maxtype, desc_info->data,
+ desc_info->desc->tlv_size);
+}
+
+static struct rocker_tlv *rocker_tlv_start(struct rocker_desc_info *desc_info)
+{
+ return (struct rocker_tlv *) ((char *) desc_info->data +
+ desc_info->tlv_size);
+}
+
+static int rocker_tlv_put(struct rocker_desc_info *desc_info,
+ int attrtype, int attrlen, const void *data)
+{
+ int tail_room = desc_info->data_size - desc_info->tlv_size;
+ int total_size = rocker_tlv_total_size(attrlen);
+ struct rocker_tlv *tlv;
+
+ if (unlikely(tail_room < total_size))
+ return -EMSGSIZE;
+
+ tlv = rocker_tlv_start(desc_info);
+ desc_info->tlv_size += total_size;
+ tlv->type = attrtype;
+ tlv->len = rocker_tlv_attr_size(attrlen);
+ memcpy(rocker_tlv_data(tlv), data, attrlen);
+ memset((char *) tlv + tlv->len, 0, rocker_tlv_padlen(attrlen));
+ return 0;
+}
+
+static int rocker_tlv_put_u8(struct rocker_desc_info *desc_info,
+ int attrtype, u8 value)
+{
+ return rocker_tlv_put(desc_info, attrtype, sizeof(u8), &value);
+}
+
+static int rocker_tlv_put_u16(struct rocker_desc_info *desc_info,
+ int attrtype, u16 value)
+{
+ return rocker_tlv_put(desc_info, attrtype, sizeof(u16), &value);
+}
+
+static int rocker_tlv_put_u32(struct rocker_desc_info *desc_info,
+ int attrtype, u32 value)
+{
+ return rocker_tlv_put(desc_info, attrtype, sizeof(u32), &value);
+}
+
+static int rocker_tlv_put_u64(struct rocker_desc_info *desc_info,
+ int attrtype, u64 value)
+{
+ return rocker_tlv_put(desc_info, attrtype, sizeof(u64), &value);
+}
+
+static struct rocker_tlv *
+rocker_tlv_nest_start(struct rocker_desc_info *desc_info, int attrtype)
+{
+ struct rocker_tlv *start = rocker_tlv_start(desc_info);
+
+ if (rocker_tlv_put(desc_info, attrtype, 0, NULL) < 0)
+ return NULL;
+
+ return start;
+}
+
+static void rocker_tlv_nest_end(struct rocker_desc_info *desc_info,
+ struct rocker_tlv *start)
+{
+ start->len = (char *) rocker_tlv_start(desc_info) - (char *) start;
+}
+
+static void rocker_tlv_nest_cancel(struct rocker_desc_info *desc_info,
+ struct rocker_tlv *start)
+{
+ desc_info->tlv_size = (char *) start - desc_info->data;
+}
+
+/******************************************
+ * DMA rings and descriptors manipulations
+ ******************************************/
+
+static u32 __pos_inc(u32 pos, size_t limit)
+{
+ return ++pos == limit ? 0 : pos;
+}
+
+static int rocker_desc_err(struct rocker_desc_info *desc_info)
+{
+ return -(desc_info->desc->comp_err & ~ROCKER_DMA_DESC_COMP_ERR_GEN);
+}
+
+static void rocker_desc_gen_clear(struct rocker_desc_info *desc_info)
+{
+ desc_info->desc->comp_err &= ~ROCKER_DMA_DESC_COMP_ERR_GEN;
+}
+
+static bool rocker_desc_gen(struct rocker_desc_info *desc_info)
+{
+ u32 comp_err = desc_info->desc->comp_err;
+
+ return comp_err & ROCKER_DMA_DESC_COMP_ERR_GEN ? true : false;
+}
+
+static void *rocker_desc_cookie_ptr_get(struct rocker_desc_info *desc_info)
+{
+ return (void *) desc_info->desc->cookie;
+}
+
+static void rocker_desc_cookie_ptr_set(struct rocker_desc_info *desc_info,
+ void *ptr)
+{
+ desc_info->desc->cookie = (long) ptr;
+}
+
+static struct rocker_desc_info *
+rocker_desc_head_get(struct rocker_dma_ring_info *info)
+{
+ static struct rocker_desc_info *desc_info;
+ u32 head = __pos_inc(info->head, info->size);
+
+ desc_info = &info->desc_info[info->head];
+ if (head == info->tail)
+ return NULL; /* ring full */
+ desc_info->tlv_size = 0;
+ return desc_info;
+}
+
+static void rocker_desc_commit(struct rocker_desc_info *desc_info)
+{
+ desc_info->desc->buf_size = desc_info->data_size;
+ desc_info->desc->tlv_size = desc_info->tlv_size;
+}
+
+static void rocker_desc_head_set(struct rocker *rocker,
+ struct rocker_dma_ring_info *info,
+ struct rocker_desc_info *desc_info)
+{
+ u32 head = __pos_inc(info->head, info->size);
+
+ BUG_ON(head == info->tail);
+ rocker_desc_commit(desc_info);
+ info->head = head;
+ rocker_write32(rocker, DMA_DESC_HEAD(info->type), head);
+}
+
+static struct rocker_desc_info *
+rocker_desc_tail_get(struct rocker_dma_ring_info *info)
+{
+ static struct rocker_desc_info *desc_info;
+
+ if (info->tail == info->head)
+ return NULL; /* nothing to be done between head and tail */
+ desc_info = &info->desc_info[info->tail];
+ if (!rocker_desc_gen(desc_info))
+ return NULL; /* gen bit not set, desc is not ready yet */
+ info->tail = __pos_inc(info->tail, info->size);
+ desc_info->tlv_size = desc_info->desc->tlv_size;
+ return desc_info;
+}
+
+static void rocker_dma_ring_credits_set(struct rocker *rocker,
+ struct rocker_dma_ring_info *info,
+ u32 credits)
+{
+ if (credits)
+ rocker_write32(rocker, DMA_DESC_CREDITS(info->type), credits);
+}
+
+static unsigned long rocker_dma_ring_size_fix(size_t size)
+{
+ return max(ROCKER_DMA_SIZE_MIN,
+ min(roundup_pow_of_two(size), ROCKER_DMA_SIZE_MAX));
+}
+
+static int rocker_dma_ring_create(struct rocker *rocker,
+ unsigned int type,
+ size_t size,
+ struct rocker_dma_ring_info *info)
+{
+ int i;
+
+ BUG_ON(size != rocker_dma_ring_size_fix(size));
+ info->size = size;
+ info->type = type;
+ info->head = 0;
+ info->tail = 0;
+ info->desc_info = kcalloc(info->size, sizeof(*info->desc_info),
+ GFP_KERNEL);
+ if (!info->desc_info)
+ return -ENOMEM;
+
+ info->desc = pci_alloc_consistent(rocker->pdev,
+ info->size * sizeof(*info->desc),
+ &info->mapaddr);
+ if (!info->desc) {
+ kfree(info->desc_info);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < info->size; i++)
+ info->desc_info[i].desc = &info->desc[i];
+
+ rocker_write32(rocker, DMA_DESC_CTRL(info->type),
+ ROCKER_DMA_DESC_CTRL_RESET);
+ rocker_write64(rocker, DMA_DESC_ADDR(info->type), info->mapaddr);
+ rocker_write32(rocker, DMA_DESC_SIZE(info->type), info->size);
+
+ return 0;
+}
+
+static void rocker_dma_ring_destroy(struct rocker *rocker,
+ struct rocker_dma_ring_info *info)
+{
+ rocker_write64(rocker, DMA_DESC_ADDR(info->type), 0);
+
+ pci_free_consistent(rocker->pdev,
+ info->size * sizeof(struct rocker_desc),
+ info->desc, info->mapaddr);
+ kfree(info->desc_info);
+}
+
+static void rocker_dma_ring_pass_to_producer(struct rocker *rocker,
+ struct rocker_dma_ring_info *info)
+{
+ int i;
+
+ BUG_ON(info->head || info->tail);
+
+ /* When ring is consumer, we need to advance head for each desc.
+ * That tells hw that the desc is ready to be used by it.
+ */
+ for (i = 0; i < info->size - 1; i++)
+ rocker_desc_head_set(rocker, info, &info->desc_info[i]);
+ rocker_desc_commit(&info->desc_info[i]);
+}
+
+static int rocker_dma_ring_bufs_alloc(struct rocker *rocker,
+ struct rocker_dma_ring_info *info,
+ int direction, size_t buf_size)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int i;
+ int err;
+
+ for (i = 0; i < info->size; i++) {
+ struct rocker_desc_info *desc_info = &info->desc_info[i];
+ struct rocker_desc *desc = &info->desc[i];
+ dma_addr_t dma_handle;
+ char *buf;
+
+ buf = kzalloc(buf_size, GFP_KERNEL | GFP_DMA);
+ if (!buf) {
+ err = -ENOMEM;
+ goto rollback;
+ }
+
+ dma_handle = pci_map_single(pdev, buf, buf_size, direction);
+ if (pci_dma_mapping_error(pdev, dma_handle)) {
+ kfree(buf);
+ err = -EIO;
+ goto rollback;
+ }
+
+ desc_info->data = buf;
+ desc_info->data_size = buf_size;
+ dma_unmap_addr_set(desc_info, mapaddr, dma_handle);
+
+ desc->buf_addr = dma_handle;
+ desc->buf_size = buf_size;
+ }
+ return 0;
+
+rollback:
+ for (i--; i >= 0; i--) {
+ struct rocker_desc_info *desc_info = &info->desc_info[i];
+
+ pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr),
+ desc_info->data_size, direction);
+ kfree(desc_info->data);
+ }
+ return err;
+}
+
+static void rocker_dma_ring_bufs_free(struct rocker *rocker,
+ struct rocker_dma_ring_info *info,
+ int direction)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int i;
+
+ for (i = 0; i < info->size; i++) {
+ struct rocker_desc_info *desc_info = &info->desc_info[i];
+ struct rocker_desc *desc = &info->desc[i];
+
+ desc->buf_addr = 0;
+ desc->buf_size = 0;
+ pci_unmap_single(pdev, dma_unmap_addr(desc_info, mapaddr),
+ desc_info->data_size, direction);
+ kfree(desc_info->data);
+ }
+}
+
+static int rocker_dma_rings_init(struct rocker *rocker)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int err;
+
+ err = rocker_dma_ring_create(rocker, ROCKER_DMA_CMD,
+ ROCKER_DMA_CMD_DEFAULT_SIZE,
+ &rocker->cmd_ring);
+ if (err) {
+ dev_err(&pdev->dev, "failed to create command dma ring\n");
+ return err;
+ }
+
+ spin_lock_init(&rocker->cmd_ring_lock);
+
+ err = rocker_dma_ring_bufs_alloc(rocker, &rocker->cmd_ring,
+ PCI_DMA_BIDIRECTIONAL, PAGE_SIZE);
+ if (err) {
+ dev_err(&pdev->dev, "failed to alloc command dma ring buffers\n");
+ goto err_dma_cmd_ring_bufs_alloc;
+ }
+
+ err = rocker_dma_ring_create(rocker, ROCKER_DMA_EVENT,
+ ROCKER_DMA_EVENT_DEFAULT_SIZE,
+ &rocker->event_ring);
+ if (err) {
+ dev_err(&pdev->dev, "failed to create event dma ring\n");
+ goto err_dma_event_ring_create;
+ }
+
+ err = rocker_dma_ring_bufs_alloc(rocker, &rocker->event_ring,
+ PCI_DMA_FROMDEVICE, PAGE_SIZE);
+ if (err) {
+ dev_err(&pdev->dev, "failed to alloc event dma ring buffers\n");
+ goto err_dma_event_ring_bufs_alloc;
+ }
+ rocker_dma_ring_pass_to_producer(rocker, &rocker->event_ring);
+ return 0;
+
+err_dma_event_ring_bufs_alloc:
+ rocker_dma_ring_destroy(rocker, &rocker->event_ring);
+err_dma_event_ring_create:
+ rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
+ PCI_DMA_BIDIRECTIONAL);
+err_dma_cmd_ring_bufs_alloc:
+ rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
+ return err;
+}
+
+static void rocker_dma_rings_fini(struct rocker *rocker)
+{
+ rocker_dma_ring_bufs_free(rocker, &rocker->event_ring,
+ PCI_DMA_BIDIRECTIONAL);
+ rocker_dma_ring_destroy(rocker, &rocker->event_ring);
+ rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
+ PCI_DMA_BIDIRECTIONAL);
+ rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
+}
+
+static int rocker_dma_rx_ring_skb_map(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ struct sk_buff *skb, size_t buf_len)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ dma_addr_t dma_handle;
+
+ dma_handle = pci_map_single(pdev, skb->data, buf_len,
+ PCI_DMA_FROMDEVICE);
+ if (pci_dma_mapping_error(pdev, dma_handle))
+ return -EIO;
+ if (rocker_tlv_put_u64(desc_info, ROCKER_TLV_RX_FRAG_ADDR, dma_handle))
+ goto tlv_put_failure;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_RX_FRAG_MAX_LEN, buf_len))
+ goto tlv_put_failure;
+ return 0;
+
+tlv_put_failure:
+ pci_unmap_single(pdev, dma_handle, buf_len, PCI_DMA_FROMDEVICE);
+ desc_info->tlv_size = 0;
+ return -EMSGSIZE;
+}
+
+static size_t rocker_port_rx_buf_len(struct rocker_port *rocker_port)
+{
+ return rocker_port->dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+}
+
+static int rocker_dma_rx_ring_skb_alloc(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info)
+{
+ struct net_device *dev = rocker_port->dev;
+ struct sk_buff *skb;
+ size_t buf_len = rocker_port_rx_buf_len(rocker_port);
+ int err;
+
+ /* Ensure that hw will see tlv_size zero in case of an error.
+ * That tells hw to use another descriptor.
+ */
+ rocker_desc_cookie_ptr_set(desc_info, NULL);
+ desc_info->tlv_size = 0;
+
+ skb = netdev_alloc_skb_ip_align(dev, buf_len);
+ if (!skb)
+ return -ENOMEM;
+ err = rocker_dma_rx_ring_skb_map(rocker, rocker_port, desc_info,
+ skb, buf_len);
+ if (err) {
+ dev_kfree_skb_any(skb);
+ return err;
+ }
+ rocker_desc_cookie_ptr_set(desc_info, skb);
+ return 0;
+}
+
+static void rocker_dma_rx_ring_skb_unmap(struct rocker *rocker,
+ struct rocker_tlv **attrs)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ dma_addr_t dma_handle;
+ size_t len;
+
+ if (!attrs[ROCKER_TLV_RX_FRAG_ADDR] ||
+ !attrs[ROCKER_TLV_RX_FRAG_MAX_LEN])
+ return;
+ dma_handle = rocker_tlv_get_u64(attrs[ROCKER_TLV_RX_FRAG_ADDR]);
+ len = rocker_tlv_get_u16(attrs[ROCKER_TLV_RX_FRAG_MAX_LEN]);
+ pci_unmap_single(pdev, dma_handle, len, PCI_DMA_FROMDEVICE);
+}
+
+static void rocker_dma_rx_ring_skb_free(struct rocker *rocker,
+ struct rocker_desc_info *desc_info)
+{
+ struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
+ struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info);
+
+ if (!skb)
+ return;
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_RX_MAX, desc_info);
+ rocker_dma_rx_ring_skb_unmap(rocker, attrs);
+ dev_kfree_skb_any(skb);
+}
+
+static int rocker_dma_rx_ring_skbs_alloc(struct rocker *rocker,
+ struct rocker_port *rocker_port)
+{
+ struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+ int i;
+ int err;
+
+ for (i = 0; i < rx_ring->size; i++) {
+ err = rocker_dma_rx_ring_skb_alloc(rocker, rocker_port,
+ &rx_ring->desc_info[i]);
+ if (err)
+ goto rollback;
+ }
+ return 0;
+
+rollback:
+ for (i--; i >= 0; i--)
+ rocker_dma_rx_ring_skb_free(rocker, &rx_ring->desc_info[i]);
+ return err;
+}
+
+static void rocker_dma_rx_ring_skbs_free(struct rocker *rocker,
+ struct rocker_port *rocker_port)
+{
+ struct rocker_dma_ring_info *rx_ring = &rocker_port->rx_ring;
+ int i;
+
+ for (i = 0; i < rx_ring->size; i++)
+ rocker_dma_rx_ring_skb_free(rocker, &rx_ring->desc_info[i]);
+}
+
+static int rocker_port_dma_rings_init(struct rocker_port *rocker_port)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ int err;
+
+ err = rocker_dma_ring_create(rocker,
+ ROCKER_DMA_TX(rocker_port->port_number),
+ ROCKER_DMA_TX_DEFAULT_SIZE,
+ &rocker_port->tx_ring);
+ if (err) {
+ netdev_err(rocker_port->dev, "failed to create tx dma ring\n");
+ return err;
+ }
+
+ err = rocker_dma_ring_bufs_alloc(rocker, &rocker_port->tx_ring,
+ PCI_DMA_TODEVICE,
+ ROCKER_DMA_TX_DESC_SIZE);
+ if (err) {
+ netdev_err(rocker_port->dev, "failed to alloc tx dma ring buffers\n");
+ goto err_dma_tx_ring_bufs_alloc;
+ }
+
+ err = rocker_dma_ring_create(rocker,
+ ROCKER_DMA_RX(rocker_port->port_number),
+ ROCKER_DMA_RX_DEFAULT_SIZE,
+ &rocker_port->rx_ring);
+ if (err) {
+ netdev_err(rocker_port->dev, "failed to create rx dma ring\n");
+ goto err_dma_rx_ring_create;
+ }
+
+ err = rocker_dma_ring_bufs_alloc(rocker, &rocker_port->rx_ring,
+ PCI_DMA_BIDIRECTIONAL,
+ ROCKER_DMA_RX_DESC_SIZE);
+ if (err) {
+ netdev_err(rocker_port->dev, "failed to alloc rx dma ring buffers\n");
+ goto err_dma_rx_ring_bufs_alloc;
+ }
+
+ err = rocker_dma_rx_ring_skbs_alloc(rocker, rocker_port);
+ if (err) {
+ netdev_err(rocker_port->dev, "failed to alloc rx dma ring skbs\n");
+ goto err_dma_rx_ring_skbs_alloc;
+ }
+ rocker_dma_ring_pass_to_producer(rocker, &rocker_port->rx_ring);
+
+ return 0;
+
+err_dma_rx_ring_skbs_alloc:
+ rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring,
+ PCI_DMA_BIDIRECTIONAL);
+err_dma_rx_ring_bufs_alloc:
+ rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring);
+err_dma_rx_ring_create:
+ rocker_dma_ring_bufs_free(rocker, &rocker_port->tx_ring,
+ PCI_DMA_TODEVICE);
+err_dma_tx_ring_bufs_alloc:
+ rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring);
+ return err;
+}
+
+static void rocker_port_dma_rings_fini(struct rocker_port *rocker_port)
+{
+ struct rocker *rocker = rocker_port->rocker;
+
+ rocker_dma_rx_ring_skbs_free(rocker, rocker_port);
+ rocker_dma_ring_bufs_free(rocker, &rocker_port->rx_ring,
+ PCI_DMA_BIDIRECTIONAL);
+ rocker_dma_ring_destroy(rocker, &rocker_port->rx_ring);
+ rocker_dma_ring_bufs_free(rocker, &rocker_port->tx_ring,
+ PCI_DMA_TODEVICE);
+ rocker_dma_ring_destroy(rocker, &rocker_port->tx_ring);
+}
+
+static void rocker_port_set_enable(struct rocker_port *rocker_port, bool enable)
+{
+ u64 val = rocker_read64(rocker_port->rocker, PORT_PHYS_ENABLE);
+
+ if (enable)
+ val |= 1 << rocker_port->lport;
+ else
+ val &= ~(1 << rocker_port->lport);
+ rocker_write64(rocker_port->rocker, PORT_PHYS_ENABLE, val);
+}
+
+/********************************
+ * Interrupt handler and helpers
+ ********************************/
+
+static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id)
+{
+ struct rocker *rocker = dev_id;
+ struct rocker_desc_info *desc_info;
+ struct rocker_wait *wait;
+ u32 credits = 0;
+
+ spin_lock(&rocker->cmd_ring_lock);
+ while ((desc_info = rocker_desc_tail_get(&rocker->cmd_ring))) {
+ wait = rocker_desc_cookie_ptr_get(desc_info);
+ if (wait->nowait) {
+ rocker_desc_gen_clear(desc_info);
+ rocker_wait_destroy(wait);
+ } else {
+ rocker_wait_wake_up(wait);
+ }
+ credits++;
+ }
+ spin_unlock(&rocker->cmd_ring_lock);
+ rocker_dma_ring_credits_set(rocker, &rocker->cmd_ring, credits);
+
+ return IRQ_HANDLED;
+}
+
+static void rocker_port_link_up(struct rocker_port *rocker_port)
+{
+ netif_carrier_on(rocker_port->dev);
+ netdev_info(rocker_port->dev, "Link is up\n");
+}
+
+static void rocker_port_link_down(struct rocker_port *rocker_port)
+{
+ netif_carrier_off(rocker_port->dev);
+ netdev_info(rocker_port->dev, "Link is down\n");
+}
+
+static int rocker_event_link_change(struct rocker *rocker,
+ const struct rocker_tlv *info)
+{
+ struct rocker_tlv *attrs[ROCKER_TLV_EVENT_LINK_CHANGED_MAX + 1];
+ unsigned port_number;
+ bool link_up;
+ struct rocker_port *rocker_port;
+
+ rocker_tlv_parse_nested(attrs, ROCKER_TLV_EVENT_LINK_CHANGED_MAX, info);
+ if (!attrs[ROCKER_TLV_EVENT_LINK_CHANGED_LPORT] ||
+ !attrs[ROCKER_TLV_EVENT_LINK_CHANGED_LINKUP])
+ return -EIO;
+ port_number =
+ rocker_tlv_get_u32(attrs[ROCKER_TLV_EVENT_LINK_CHANGED_LPORT]) - 1;
+ link_up = rocker_tlv_get_u8(attrs[ROCKER_TLV_EVENT_LINK_CHANGED_LINKUP]);
+
+ if (port_number >= rocker->port_count)
+ return -EINVAL;
+
+ rocker_port = rocker->ports[port_number];
+ if (netif_carrier_ok(rocker_port->dev) != link_up) {
+ if (link_up)
+ rocker_port_link_up(rocker_port);
+ else
+ rocker_port_link_down(rocker_port);
+ }
+
+ return 0;
+}
+
+static int rocker_event_process(struct rocker *rocker,
+ struct rocker_desc_info *desc_info)
+{
+ struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAX + 1];
+ struct rocker_tlv *info;
+ u16 type;
+
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_EVENT_MAX, desc_info);
+ if (!attrs[ROCKER_TLV_EVENT_TYPE] ||
+ !attrs[ROCKER_TLV_EVENT_INFO])
+ return -EIO;
+
+ type = rocker_tlv_get_u16(attrs[ROCKER_TLV_EVENT_TYPE]);
+ info = attrs[ROCKER_TLV_EVENT_INFO];
+
+ switch (type) {
+ case ROCKER_TLV_EVENT_TYPE_LINK_CHANGED:
+ return rocker_event_link_change(rocker, info);
+ }
+
+ return -EOPNOTSUPP;
+}
+
+static irqreturn_t rocker_event_irq_handler(int irq, void *dev_id)
+{
+ struct rocker *rocker = dev_id;
+ struct pci_dev *pdev = rocker->pdev;
+ struct rocker_desc_info *desc_info;
+ u32 credits = 0;
+ int err;
+
+ while ((desc_info = rocker_desc_tail_get(&rocker->event_ring))) {
+ err = rocker_desc_err(desc_info);
+ if (err) {
+ dev_err(&pdev->dev, "event desc received with err %d\n",
+ err);
+ } else {
+ err = rocker_event_process(rocker, desc_info);
+ if (err)
+ dev_err(&pdev->dev, "event processing failed with err %d\n",
+ err);
+ }
+ rocker_desc_gen_clear(desc_info);
+ rocker_desc_head_set(rocker, &rocker->event_ring, desc_info);
+ credits++;
+ }
+ rocker_dma_ring_credits_set(rocker, &rocker->event_ring, credits);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t rocker_tx_irq_handler(int irq, void *dev_id)
+{
+ struct rocker_port *rocker_port = dev_id;
+
+ napi_schedule(&rocker_port->napi_tx);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t rocker_rx_irq_handler(int irq, void *dev_id)
+{
+ struct rocker_port *rocker_port = dev_id;
+
+ napi_schedule(&rocker_port->napi_rx);
+ return IRQ_HANDLED;
+}
+
+/********************
+ * Command interface
+ ********************/
+
+typedef int (*rocker_cmd_cb_t)(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv);
+
+static int rocker_cmd_exec(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ rocker_cmd_cb_t prepare, void *prepare_priv,
+ rocker_cmd_cb_t process, void *process_priv,
+ bool nowait)
+{
+ struct rocker_desc_info *desc_info;
+ struct rocker_wait *wait;
+ unsigned long flags;
+ int err;
+
+ wait = rocker_wait_create(nowait ? GFP_ATOMIC : GFP_KERNEL);
+ if (!wait)
+ return -ENOMEM;
+ wait->nowait = nowait;
+
+ spin_lock_irqsave(&rocker->cmd_ring_lock, flags);
+ desc_info = rocker_desc_head_get(&rocker->cmd_ring);
+ if (!desc_info) {
+ spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+ err = -EAGAIN;
+ goto out;
+ }
+ err = prepare(rocker, rocker_port, desc_info, prepare_priv);
+ if (err) {
+ spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+ goto out;
+ }
+ rocker_desc_cookie_ptr_set(desc_info, wait);
+ rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info);
+ spin_unlock_irqrestore(&rocker->cmd_ring_lock, flags);
+
+ if (nowait)
+ return 0;
+
+ if (!rocker_wait_event_timeout(wait, HZ / 10))
+ return -EIO;
+
+ err = rocker_desc_err(desc_info);
+ if (err)
+ return err;
+
+ if (process)
+ err = process(rocker, rocker_port, desc_info, process_priv);
+
+ rocker_desc_gen_clear(desc_info);
+out:
+ rocker_wait_destroy(wait);
+ return err;
+}
+
+static int
+rocker_cmd_get_port_settings_prep(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ struct rocker_tlv *cmd_info;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
+ ROCKER_TLV_CMD_TYPE_GET_PORT_SETTINGS))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_LPORT,
+ rocker_port->lport))
+ return -EMSGSIZE;
+ rocker_tlv_nest_end(desc_info, cmd_info);
+ return 0;
+}
+
+static int
+rocker_cmd_get_port_settings_ethtool_proc(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ struct ethtool_cmd *ecmd = priv;
+ struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+ struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
+ u32 speed;
+ u8 duplex;
+ u8 autoneg;
+
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info);
+ if (!attrs[ROCKER_TLV_CMD_INFO])
+ return -EIO;
+
+ rocker_tlv_parse_nested(info_attrs, ROCKER_TLV_CMD_PORT_SETTINGS_MAX,
+ attrs[ROCKER_TLV_CMD_INFO]);
+ if (!info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_SPEED] ||
+ !info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX] ||
+ !info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG])
+ return -EIO;
+
+ speed = rocker_tlv_get_u32(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_SPEED]);
+ duplex = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX]);
+ autoneg = rocker_tlv_get_u8(info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG]);
+
+ ecmd->transceiver = XCVR_INTERNAL;
+ ecmd->supported = SUPPORTED_TP;
+ ecmd->phy_address = 0xff;
+ ecmd->port = PORT_TP;
+ ethtool_cmd_speed_set(ecmd, speed);
+ ecmd->duplex = duplex ? DUPLEX_FULL : DUPLEX_HALF;
+ ecmd->autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+ return 0;
+}
+
+static int
+rocker_cmd_get_port_settings_macaddr_proc(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ unsigned char *macaddr = priv;
+ struct rocker_tlv *attrs[ROCKER_TLV_CMD_MAX + 1];
+ struct rocker_tlv *info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MAX + 1];
+ struct rocker_tlv *attr;
+
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_CMD_MAX, desc_info);
+ if (!attrs[ROCKER_TLV_CMD_INFO])
+ return -EIO;
+
+ rocker_tlv_parse_nested(info_attrs, ROCKER_TLV_CMD_PORT_SETTINGS_MAX,
+ attrs[ROCKER_TLV_CMD_INFO]);
+ attr = info_attrs[ROCKER_TLV_CMD_PORT_SETTINGS_MACADDR];
+ if (!attr)
+ return -EIO;
+
+ if (rocker_tlv_len(attr) != ETH_ALEN)
+ return -EINVAL;
+
+ ether_addr_copy(macaddr, rocker_tlv_data(attr));
+ return 0;
+}
+
+static int
+rocker_cmd_set_port_settings_ethtool_prep(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ struct ethtool_cmd *ecmd = priv;
+ struct rocker_tlv *cmd_info;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
+ ROCKER_TLV_CMD_TYPE_SET_PORT_SETTINGS))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_LPORT,
+ rocker_port->lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_SPEED,
+ ethtool_cmd_speed(ecmd)))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX,
+ ecmd->duplex))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG,
+ ecmd->autoneg))
+ return -EMSGSIZE;
+ rocker_tlv_nest_end(desc_info, cmd_info);
+ return 0;
+}
+
+static int
+rocker_cmd_set_port_settings_macaddr_prep(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ unsigned char *macaddr = priv;
+ struct rocker_tlv *cmd_info;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
+ ROCKER_TLV_CMD_TYPE_SET_PORT_SETTINGS))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_LPORT,
+ rocker_port->lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_CMD_PORT_SETTINGS_MACADDR,
+ ETH_ALEN, macaddr))
+ return -EMSGSIZE;
+ rocker_tlv_nest_end(desc_info, cmd_info);
+ return 0;
+}
+
+static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port,
+ struct ethtool_cmd *ecmd)
+{
+ return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+ rocker_cmd_get_port_settings_prep, NULL,
+ rocker_cmd_get_port_settings_ethtool_proc,
+ ecmd, false);
+}
+
+static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port,
+ unsigned char *macaddr)
+{
+ return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+ rocker_cmd_get_port_settings_prep, NULL,
+ rocker_cmd_get_port_settings_macaddr_proc,
+ macaddr, false);
+}
+
+static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port,
+ struct ethtool_cmd *ecmd)
+{
+ return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+ rocker_cmd_set_port_settings_ethtool_prep,
+ ecmd, NULL, NULL, false);
+}
+
+static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port,
+ unsigned char *macaddr)
+{
+ return rocker_cmd_exec(rocker_port->rocker, rocker_port,
+ rocker_cmd_set_port_settings_macaddr_prep,
+ macaddr, NULL, NULL, false);
+}
+
+/*****************
+ * Net device ops
+ *****************/
+
+static int rocker_port_open(struct net_device *dev)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ int err;
+
+ err = rocker_port_dma_rings_init(rocker_port);
+ if (err)
+ return err;
+
+ err = request_irq(rocker_msix_tx_vector(rocker_port),
+ rocker_tx_irq_handler, 0,
+ rocker_driver_name, rocker_port);
+ if (err) {
+ netdev_err(rocker_port->dev, "cannot assign tx irq\n");
+ goto err_request_tx_irq;
+ }
+
+ err = request_irq(rocker_msix_rx_vector(rocker_port),
+ rocker_rx_irq_handler, 0,
+ rocker_driver_name, rocker_port);
+ if (err) {
+ netdev_err(rocker_port->dev, "cannot assign rx irq\n");
+ goto err_request_rx_irq;
+ }
+
+ napi_enable(&rocker_port->napi_tx);
+ napi_enable(&rocker_port->napi_rx);
+ rocker_port_set_enable(rocker_port, true);
+ netif_start_queue(dev);
+ return 0;
+
+err_request_rx_irq:
+ free_irq(rocker_msix_tx_vector(rocker_port), rocker_port);
+err_request_tx_irq:
+ rocker_port_dma_rings_fini(rocker_port);
+ return err;
+}
+
+static int rocker_port_stop(struct net_device *dev)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+
+ netif_stop_queue(dev);
+ rocker_port_set_enable(rocker_port, false);
+ napi_disable(&rocker_port->napi_rx);
+ napi_disable(&rocker_port->napi_tx);
+ free_irq(rocker_msix_rx_vector(rocker_port), rocker_port);
+ free_irq(rocker_msix_tx_vector(rocker_port), rocker_port);
+ rocker_port_dma_rings_fini(rocker_port);
+
+ return 0;
+}
+
+static void rocker_tx_desc_frags_unmap(struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct pci_dev *pdev = rocker->pdev;
+ struct rocker_tlv *attrs[ROCKER_TLV_TX_MAX + 1];
+ struct rocker_tlv *attr;
+ int rem;
+
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_TX_MAX, desc_info);
+ if (!attrs[ROCKER_TLV_TX_FRAGS])
+ return;
+ rocker_tlv_for_each_nested(attr, attrs[ROCKER_TLV_TX_FRAGS], rem) {
+ struct rocker_tlv *frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_MAX + 1];
+ dma_addr_t dma_handle;
+ size_t len;
+
+ if (rocker_tlv_type(attr) != ROCKER_TLV_TX_FRAG)
+ continue;
+ rocker_tlv_parse_nested(frag_attrs, ROCKER_TLV_TX_FRAG_ATTR_MAX,
+ attr);
+ if (!frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_ADDR] ||
+ !frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_LEN])
+ continue;
+ dma_handle = rocker_tlv_get_u64(frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_ADDR]);
+ len = rocker_tlv_get_u16(frag_attrs[ROCKER_TLV_TX_FRAG_ATTR_LEN]);
+ pci_unmap_single(pdev, dma_handle, len, DMA_TO_DEVICE);
+ }
+}
+
+static int rocker_tx_desc_frag_map_put(struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ char *buf, size_t buf_len)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct pci_dev *pdev = rocker->pdev;
+ dma_addr_t dma_handle;
+ struct rocker_tlv *frag;
+
+ dma_handle = pci_map_single(pdev, buf, buf_len, DMA_TO_DEVICE);
+ if (unlikely(pci_dma_mapping_error(pdev, dma_handle))) {
+ if (net_ratelimit())
+ netdev_err(rocker_port->dev, "failed to dma map tx frag\n");
+ return -EIO;
+ }
+ frag = rocker_tlv_nest_start(desc_info, ROCKER_TLV_TX_FRAG);
+ if (!frag)
+ goto unmap_frag;
+ if (rocker_tlv_put_u64(desc_info, ROCKER_TLV_TX_FRAG_ATTR_ADDR,
+ dma_handle))
+ goto nest_cancel;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_TX_FRAG_ATTR_LEN,
+ buf_len))
+ goto nest_cancel;
+ rocker_tlv_nest_end(desc_info, frag);
+ return 0;
+
+nest_cancel:
+ rocker_tlv_nest_cancel(desc_info, frag);
+unmap_frag:
+ pci_unmap_single(pdev, dma_handle, buf_len, DMA_TO_DEVICE);
+ return -EMSGSIZE;
+}
+
+static netdev_tx_t rocker_port_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_desc_info *desc_info;
+ struct rocker_tlv *frags;
+ int i;
+ int err;
+
+ desc_info = rocker_desc_head_get(&rocker_port->tx_ring);
+ if (unlikely(!desc_info)) {
+ if (net_ratelimit())
+ netdev_err(dev, "tx ring full when queue awake\n");
+ return NETDEV_TX_BUSY;
+ }
+
+ rocker_desc_cookie_ptr_set(desc_info, skb);
+
+ frags = rocker_tlv_nest_start(desc_info, ROCKER_TLV_TX_FRAGS);
+ if (!frags)
+ goto out;
+ err = rocker_tx_desc_frag_map_put(rocker_port, desc_info,
+ skb->data, skb_headlen(skb));
+ if (err)
+ goto nest_cancel;
+ if (skb_shinfo(skb)->nr_frags > ROCKER_TX_FRAGS_MAX)
+ goto nest_cancel;
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+ err = rocker_tx_desc_frag_map_put(rocker_port, desc_info,
+ skb_frag_address(frag),
+ skb_frag_size(frag));
+ if (err)
+ goto unmap_frags;
+ }
+ rocker_tlv_nest_end(desc_info, frags);
+
+ rocker_desc_gen_clear(desc_info);
+ rocker_desc_head_set(rocker, &rocker_port->tx_ring, desc_info);
+
+ desc_info = rocker_desc_head_get(&rocker_port->tx_ring);
+ if (!desc_info)
+ netif_stop_queue(dev);
+
+ return NETDEV_TX_OK;
+
+unmap_frags:
+ rocker_tx_desc_frags_unmap(rocker_port, desc_info);
+nest_cancel:
+ rocker_tlv_nest_cancel(desc_info, frags);
+out:
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static int rocker_port_set_mac_address(struct net_device *dev, void *p)
+{
+ struct sockaddr *addr = p;
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ int err;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ err = rocker_cmd_set_port_settings_macaddr(rocker_port, addr->sa_data);
+ if (err)
+ return err;
+ memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+ return 0;
+}
+
+static int rocker_port_sw_parent_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *psid)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ struct rocker *rocker = rocker_port->rocker;
+
+ psid->id_len = sizeof(rocker->hw.id);
+ memcpy(&psid->id, &rocker->hw.id, psid->id_len);
+ return 0;
+}
+
+static const struct net_device_ops rocker_port_netdev_ops = {
+ .ndo_open = rocker_port_open,
+ .ndo_stop = rocker_port_stop,
+ .ndo_start_xmit = rocker_port_xmit,
+ .ndo_set_mac_address = rocker_port_set_mac_address,
+#ifdef CONFIG_NET_SWITCHDEV
+ .ndo_sw_parent_id_get = rocker_port_sw_parent_id_get,
+#endif
+};
+
+/********************
+ * ethtool interface
+ ********************/
+
+static int rocker_port_get_settings(struct net_device *dev,
+ struct ethtool_cmd *ecmd)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+
+ return rocker_cmd_get_port_settings_ethtool(rocker_port, ecmd);
+}
+
+static int rocker_port_set_settings(struct net_device *dev,
+ struct ethtool_cmd *ecmd)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+
+ return rocker_cmd_set_port_settings_ethtool(rocker_port, ecmd);
+}
+
+static void rocker_port_get_drvinfo(struct net_device *dev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ strlcpy(drvinfo->driver, rocker_driver_name, sizeof(drvinfo->driver));
+ strlcpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version));
+}
+
+static const struct ethtool_ops rocker_port_ethtool_ops = {
+ .get_settings = rocker_port_get_settings,
+ .set_settings = rocker_port_set_settings,
+ .get_drvinfo = rocker_port_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+};
+
+/*****************
+ * NAPI interface
+ *****************/
+
+static struct rocker_port *rocker_port_napi_tx_get(struct napi_struct *napi)
+{
+ return container_of(napi, struct rocker_port, napi_tx);
+}
+
+static int rocker_port_poll_tx(struct napi_struct *napi, int budget)
+{
+ struct rocker_port *rocker_port = rocker_port_napi_tx_get(napi);
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_desc_info *desc_info;
+ u32 credits = 0;
+ int err;
+
+ /* Cleanup tx descriptors */
+ while ((desc_info = rocker_desc_tail_get(&rocker_port->tx_ring))) {
+ err = rocker_desc_err(desc_info);
+ if (err && net_ratelimit())
+ netdev_err(rocker_port->dev, "tx desc received with err %d\n",
+ err);
+ rocker_tx_desc_frags_unmap(rocker_port, desc_info);
+ dev_kfree_skb_any(rocker_desc_cookie_ptr_get(desc_info));
+ credits++;
+ }
+
+ if (credits && netif_queue_stopped(rocker_port->dev))
+ netif_wake_queue(rocker_port->dev);
+
+ napi_complete(napi);
+ rocker_dma_ring_credits_set(rocker, &rocker_port->tx_ring, credits);
+
+ return 0;
+}
+
+static int rocker_port_rx_proc(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info)
+{
+ struct rocker_tlv *attrs[ROCKER_TLV_RX_MAX + 1];
+ struct sk_buff *skb = rocker_desc_cookie_ptr_get(desc_info);
+ size_t rx_len;
+
+ if (!skb)
+ return -ENOENT;
+
+ rocker_tlv_parse_desc(attrs, ROCKER_TLV_RX_MAX, desc_info);
+ if (!attrs[ROCKER_TLV_RX_FRAG_LEN])
+ return -EINVAL;
+
+ rocker_dma_rx_ring_skb_unmap(rocker, attrs);
+
+ rx_len = rocker_tlv_get_u16(attrs[ROCKER_TLV_RX_FRAG_LEN]);
+ skb_put(skb, rx_len);
+ skb->protocol = eth_type_trans(skb, rocker_port->dev);
+ netif_receive_skb(skb);
+
+ return rocker_dma_rx_ring_skb_alloc(rocker, rocker_port, desc_info);
+}
+
+static struct rocker_port *rocker_port_napi_rx_get(struct napi_struct *napi)
+{
+ return container_of(napi, struct rocker_port, napi_rx);
+}
+
+static int rocker_port_poll_rx(struct napi_struct *napi, int budget)
+{
+ struct rocker_port *rocker_port = rocker_port_napi_rx_get(napi);
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_desc_info *desc_info;
+ u32 credits = 0;
+ int err;
+
+ /* Process rx descriptors */
+ while (credits < budget &&
+ (desc_info = rocker_desc_tail_get(&rocker_port->rx_ring))) {
+ err = rocker_desc_err(desc_info);
+ if (err) {
+ if (net_ratelimit())
+ netdev_err(rocker_port->dev, "rx desc received with err %d\n",
+ err);
+ } else {
+ err = rocker_port_rx_proc(rocker, rocker_port,
+ desc_info);
+ if (err && net_ratelimit())
+ netdev_err(rocker_port->dev, "rx processing failed with err %d\n",
+ err);
+ }
+ rocker_desc_gen_clear(desc_info);
+ rocker_desc_head_set(rocker, &rocker_port->rx_ring, desc_info);
+ credits++;
+ }
+
+ if (credits < budget)
+ napi_complete(napi);
+
+ rocker_dma_ring_credits_set(rocker, &rocker_port->rx_ring, credits);
+
+ return credits;
+}
+
+/*****************
+ * PCI driver ops
+ *****************/
+
+static void rocker_carrier_init(struct rocker_port *rocker_port)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ u64 link_status = rocker_read64(rocker, PORT_PHYS_LINK_STATUS);
+ bool link_up;
+
+ link_up = link_status & (1 << rocker_port->lport);
+ if (link_up)
+ netif_carrier_on(rocker_port->dev);
+ else
+ netif_carrier_off(rocker_port->dev);
+}
+
+static void rocker_remove_ports(struct rocker *rocker)
+{
+ int i;
+
+ for (i = 0; i < rocker->port_count; i++)
+ unregister_netdev(rocker->ports[i]->dev);
+ kfree(rocker->ports);
+}
+
+static void rocker_port_dev_addr_init(struct rocker *rocker,
+ struct rocker_port *rocker_port)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int err;
+
+ err = rocker_cmd_get_port_settings_macaddr(rocker_port,
+ rocker_port->dev->dev_addr);
+ if (err) {
+ dev_warn(&pdev->dev, "failed to get mac address, using random\n");
+ eth_hw_addr_random(rocker_port->dev);
+ }
+}
+
+static int rocker_probe_port(struct rocker *rocker, unsigned port_number)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ struct rocker_port *rocker_port;
+ struct net_device *dev;
+ int err;
+
+ dev = alloc_etherdev(sizeof(struct rocker_port));
+ if (!dev)
+ return -ENOMEM;
+ rocker_port = netdev_priv(dev);
+ rocker_port->dev = dev;
+ rocker_port->rocker = rocker;
+ rocker_port->port_number = port_number;
+ rocker_port->lport = port_number + 1;
+
+ rocker_port_dev_addr_init(rocker, rocker_port);
+ dev->netdev_ops = &rocker_port_netdev_ops;
+ dev->ethtool_ops = &rocker_port_ethtool_ops;
+ netif_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
+ NAPI_POLL_WEIGHT);
+ netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
+ NAPI_POLL_WEIGHT);
+ rocker_carrier_init(rocker_port);
+
+ dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+ err = register_netdev(dev);
+ if (err) {
+ dev_err(&pdev->dev, "register_netdev failed\n");
+ goto err_register_netdev;
+ }
+ rocker->ports[port_number] = rocker_port;
+
+ return 0;
+
+err_register_netdev:
+ free_netdev(dev);
+ return err;
+}
+
+static int rocker_probe_ports(struct rocker *rocker)
+{
+ int i;
+ size_t alloc_size;
+ int err;
+
+ alloc_size = sizeof(struct rocker_port *) * rocker->port_count;
+ rocker->ports = kmalloc(alloc_size, GFP_KERNEL);
+ for (i = 0; i < rocker->port_count; i++) {
+ err = rocker_probe_port(rocker, i);
+ if (err)
+ goto remove_ports;
+ }
+ return 0;
+
+remove_ports:
+ rocker_remove_ports(rocker);
+ return err;
+}
+
+static int rocker_msix_init(struct rocker *rocker)
+{
+ struct pci_dev *pdev = rocker->pdev;
+ int msix_entries;
+ int i;
+ int err;
+
+ msix_entries = pci_msix_vec_count(pdev);
+ if (msix_entries < 0)
+ return msix_entries;
+
+ if (msix_entries != ROCKER_MSIX_VEC_COUNT(rocker->port_count))
+ return -EINVAL;
+
+ rocker->msix_entries = kmalloc_array(msix_entries,
+ sizeof(struct msix_entry),
+ GFP_KERNEL);
+ if (!rocker->msix_entries)
+ return -ENOMEM;
+
+ for (i = 0; i < msix_entries; i++)
+ rocker->msix_entries[i].entry = i;
+
+ err = pci_enable_msix_exact(pdev, rocker->msix_entries, msix_entries);
+ if (err < 0)
+ goto err_enable_msix;
+
+ return 0;
+
+err_enable_msix:
+ kfree(rocker->msix_entries);
+ return err;
+}
+
+static void rocker_msix_fini(struct rocker *rocker)
+{
+ pci_disable_msix(rocker->pdev);
+ kfree(rocker->msix_entries);
+}
+
+static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+ struct rocker *rocker;
+ int err;
+
+ rocker = kzalloc(sizeof(*rocker), GFP_KERNEL);
+ if (!rocker)
+ return -ENOMEM;
+
+ err = pci_enable_device(pdev);
+ if (err) {
+ dev_err(&pdev->dev, "pci_enable_device failed\n");
+ goto err_pci_enable_device;
+ }
+
+ err = pci_request_regions(pdev, rocker_driver_name);
+ if (err) {
+ dev_err(&pdev->dev, "pci_request_regions failed\n");
+ goto err_pci_request_regions;
+ }
+
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (!err) {
+ err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+ if (err) {
+ dev_err(&pdev->dev, "pci_set_consistent_dma_mask failed\n");
+ goto err_pci_set_dma_mask;
+ }
+ } else {
+ err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+ if (err) {
+ dev_err(&pdev->dev, "pci_set_dma_mask failed\n");
+ goto err_pci_set_dma_mask;
+ }
+ }
+
+ if (pci_resource_len(pdev, 0) < ROCKER_PCI_BAR0_SIZE) {
+ dev_err(&pdev->dev, "invalid PCI region size\n");
+ goto err_pci_resource_len_check;
+ }
+
+ rocker->hw_addr = ioremap(pci_resource_start(pdev, 0),
+ pci_resource_len(pdev, 0));
+ if (!rocker->hw_addr) {
+ dev_err(&pdev->dev, "ioremap failed\n");
+ err = -EIO;
+ goto err_ioremap;
+ }
+ pci_set_master(pdev);
+
+ rocker->pdev = pdev;
+ pci_set_drvdata(pdev, rocker);
+
+ rocker->port_count = rocker_read32(rocker, PORT_PHYS_COUNT);
+
+ err = rocker_msix_init(rocker);
+ if (err) {
+ dev_err(&pdev->dev, "MSI-X init failed\n");
+ goto err_msix_init;
+ }
+
+ err = rocker_basic_hw_test(rocker);
+ if (err) {
+ dev_err(&pdev->dev, "basic hw test failed\n");
+ goto err_basic_hw_test;
+ }
+
+ rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET);
+
+ err = rocker_dma_rings_init(rocker);
+ if (err)
+ goto err_dma_rings_init;
+
+ err = request_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_CMD),
+ rocker_cmd_irq_handler, 0,
+ rocker_driver_name, rocker);
+ if (err) {
+ dev_err(&pdev->dev, "cannot assign cmd irq\n");
+ goto err_request_cmd_irq;
+ }
+
+ err = request_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT),
+ rocker_event_irq_handler, 0,
+ rocker_driver_name, rocker);
+ if (err) {
+ dev_err(&pdev->dev, "cannot assign event irq\n");
+ goto err_request_event_irq;
+ }
+
+ rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
+
+ err = rocker_probe_ports(rocker);
+ if (err) {
+ dev_err(&pdev->dev, "failed to probe ports\n");
+ goto err_probe_ports;
+ }
+
+ dev_info(&pdev->dev, "Rocker switch with id %016llx\n", rocker->hw.id);
+
+ return 0;
+
+err_probe_ports:
+ free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
+err_request_event_irq:
+ free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_CMD), rocker);
+err_request_cmd_irq:
+ rocker_dma_rings_fini(rocker);
+err_dma_rings_init:
+err_basic_hw_test:
+ rocker_msix_fini(rocker);
+err_msix_init:
+ iounmap(rocker->hw_addr);
+err_ioremap:
+err_pci_resource_len_check:
+err_pci_set_dma_mask:
+ pci_release_regions(pdev);
+err_pci_request_regions:
+ pci_disable_device(pdev);
+err_pci_enable_device:
+ kfree(rocker);
+ return err;
+}
+
+static void rocker_remove(struct pci_dev *pdev)
+{
+ struct rocker *rocker = pci_get_drvdata(pdev);
+
+ rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET);
+ rocker_remove_ports(rocker);
+ free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
+ free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_CMD), rocker);
+ rocker_dma_rings_fini(rocker);
+ rocker_msix_fini(rocker);
+ iounmap(rocker->hw_addr);
+ pci_release_regions(rocker->pdev);
+ pci_disable_device(rocker->pdev);
+ kfree(rocker);
+}
+
+static struct pci_driver rocker_pci_driver = {
+ .name = rocker_driver_name,
+ .id_table = rocker_pci_id_table,
+ .probe = rocker_probe,
+ .remove = rocker_remove,
+};
+
+/***********************
+ * Module init and exit
+ ***********************/
+
+static int __init rocker_module_init(void)
+{
+ return pci_register_driver(&rocker_pci_driver);
+}
+
+static void __exit rocker_module_exit(void)
+{
+ pci_unregister_driver(&rocker_pci_driver);
+}
+
+module_init(rocker_module_init);
+module_exit(rocker_module_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_AUTHOR("Scott Feldman <sfeldma@gmail.com>");
+MODULE_DESCRIPTION("Rocker switch device driver");
+MODULE_DEVICE_TABLE(pci, rocker_pci_id_table);
diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h
new file mode 100644
index 0000000..56f779e
--- /dev/null
+++ b/drivers/net/ethernet/rocker/rocker.h
@@ -0,0 +1,427 @@
+/*
+ * drivers/net/ethernet/rocker/rocker.h - Rocker switch device driver
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ROCKER_H
+#define _ROCKER_H
+
+#include <linux/types.h>
+
+#define PCI_VENDOR_ID_REDHAT 0x1b36
+#define PCI_DEVICE_ID_REDHAT_ROCKER 0x0006
+
+#define ROCKER_PCI_BAR0_SIZE 0x2000
+
+/* MSI-X vectors */
+enum {
+ ROCKER_MSIX_VEC_CMD,
+ ROCKER_MSIX_VEC_EVENT,
+ ROCKER_MSIX_VEC_TEST,
+ ROCKER_MSIX_VEC_RESERVED0,
+ __ROCKER_MSIX_VEC_TX,
+ __ROCKER_MSIX_VEC_RX,
+#define ROCKER_MSIX_VEC_TX(port) \
+ (__ROCKER_MSIX_VEC_TX + ((port) * 2))
+#define ROCKER_MSIX_VEC_RX(port) \
+ (__ROCKER_MSIX_VEC_RX + ((port) * 2))
+#define ROCKER_MSIX_VEC_COUNT(portcnt) \
+ (ROCKER_MSIX_VEC_RX((portcnt - 1)) + 1)
+};
+
+/* Rocker bogus registers */
+#define ROCKER_BOGUS_REG0 0x0000
+#define ROCKER_BOGUS_REG1 0x0004
+#define ROCKER_BOGUS_REG2 0x0008
+#define ROCKER_BOGUS_REG3 0x000c
+
+/* Rocker test registers */
+#define ROCKER_TEST_REG 0x0010
+#define ROCKER_TEST_REG64 0x0018 /* 8-byte */
+#define ROCKER_TEST_IRQ 0x0020
+#define ROCKER_TEST_DMA_ADDR 0x0028 /* 8-byte */
+#define ROCKER_TEST_DMA_SIZE 0x0030
+#define ROCKER_TEST_DMA_CTRL 0x0034
+
+/* Rocker test register ctrl */
+#define ROCKER_TEST_DMA_CTRL_CLEAR (1 << 0)
+#define ROCKER_TEST_DMA_CTRL_FILL (1 << 1)
+#define ROCKER_TEST_DMA_CTRL_INVERT (1 << 2)
+
+/* Rocker DMA ring register offsets */
+#define ROCKER_DMA_DESC_ADDR(x) (0x1000 + (x) * 32) /* 8-byte */
+#define ROCKER_DMA_DESC_SIZE(x) (0x1008 + (x) * 32)
+#define ROCKER_DMA_DESC_HEAD(x) (0x100c + (x) * 32)
+#define ROCKER_DMA_DESC_TAIL(x) (0x1010 + (x) * 32)
+#define ROCKER_DMA_DESC_CTRL(x) (0x1014 + (x) * 32)
+#define ROCKER_DMA_DESC_CREDITS(x) (0x1018 + (x) * 32)
+#define ROCKER_DMA_DESC_RES1(x) (0x101c + (x) * 32)
+
+/* Rocker dma ctrl register bits */
+#define ROCKER_DMA_DESC_CTRL_RESET (1 << 0)
+
+/* Rocker DMA ring types */
+enum rocker_dma_type {
+ ROCKER_DMA_CMD,
+ ROCKER_DMA_EVENT,
+ __ROCKER_DMA_TX,
+ __ROCKER_DMA_RX,
+#define ROCKER_DMA_TX(port) (__ROCKER_DMA_TX + (port) * 2)
+#define ROCKER_DMA_RX(port) (__ROCKER_DMA_RX + (port) * 2)
+};
+
+/* Rocker DMA ring size limits and default sizes */
+#define ROCKER_DMA_SIZE_MIN 2ul
+#define ROCKER_DMA_SIZE_MAX 65536ul
+#define ROCKER_DMA_CMD_DEFAULT_SIZE 32ul
+#define ROCKER_DMA_EVENT_DEFAULT_SIZE 32ul
+#define ROCKER_DMA_TX_DEFAULT_SIZE 64ul
+#define ROCKER_DMA_TX_DESC_SIZE 256
+#define ROCKER_DMA_RX_DEFAULT_SIZE 64ul
+#define ROCKER_DMA_RX_DESC_SIZE 256
+
+/* Rocker DMA descriptor struct */
+struct rocker_desc {
+ u64 buf_addr;
+ u64 cookie;
+ u16 buf_size;
+ u16 tlv_size;
+ u16 resv[5];
+ u16 comp_err;
+} __packed __aligned(8);
+
+#define ROCKER_DMA_DESC_COMP_ERR_GEN (1 << 15)
+
+/* Rocker DMA TLV struct */
+struct rocker_tlv {
+ u32 type;
+ u16 len;
+} __packed __aligned(8);
+
+/* TLVs */
+enum {
+ ROCKER_TLV_CMD_UNSPEC,
+ ROCKER_TLV_CMD_TYPE, /* u16 */
+ ROCKER_TLV_CMD_INFO, /* nest */
+
+ __ROCKER_TLV_CMD_MAX,
+ ROCKER_TLV_CMD_MAX = __ROCKER_TLV_CMD_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_CMD_TYPE_UNSPEC,
+ ROCKER_TLV_CMD_TYPE_GET_PORT_SETTINGS,
+ ROCKER_TLV_CMD_TYPE_SET_PORT_SETTINGS,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_MOD,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_GET_STATS,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_GET_STATS,
+
+ __ROCKER_TLV_CMD_TYPE_MAX,
+ ROCKER_TLV_CMD_TYPE_MAX = __ROCKER_TLV_CMD_TYPE_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_CMD_PORT_SETTINGS_UNSPEC,
+ ROCKER_TLV_CMD_PORT_SETTINGS_LPORT, /* u32 */
+ ROCKER_TLV_CMD_PORT_SETTINGS_SPEED, /* u32 */
+ ROCKER_TLV_CMD_PORT_SETTINGS_DUPLEX, /* u8 */
+ ROCKER_TLV_CMD_PORT_SETTINGS_AUTONEG, /* u8 */
+ ROCKER_TLV_CMD_PORT_SETTINGS_MACADDR, /* binary */
+ ROCKER_TLV_CMD_PORT_SETTINGS_MODE, /* u8 */
+
+ __ROCKER_TLV_CMD_PORT_SETTINGS_MAX,
+ ROCKER_TLV_CMD_PORT_SETTINGS_MAX =
+ __ROCKER_TLV_CMD_PORT_SETTINGS_MAX - 1,
+};
+
+enum rocker_port_mode {
+ ROCKER_PORT_MODE_OF_DPA,
+};
+
+enum {
+ ROCKER_TLV_EVENT_UNSPEC,
+ ROCKER_TLV_EVENT_TYPE, /* u16 */
+ ROCKER_TLV_EVENT_INFO, /* nest */
+
+ __ROCKER_TLV_EVENT_MAX,
+ ROCKER_TLV_EVENT_MAX = __ROCKER_TLV_EVENT_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_EVENT_TYPE_UNSPEC,
+ ROCKER_TLV_EVENT_TYPE_LINK_CHANGED,
+ ROCKER_TLV_EVENT_TYPE_MAC_VLAN_SEEN,
+
+ __ROCKER_TLV_EVENT_TYPE_MAX,
+ ROCKER_TLV_EVENT_TYPE_MAX = __ROCKER_TLV_EVENT_TYPE_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_EVENT_LINK_CHANGED_UNSPEC,
+ ROCKER_TLV_EVENT_LINK_CHANGED_LPORT, /* u32 */
+ ROCKER_TLV_EVENT_LINK_CHANGED_LINKUP, /* u8 */
+
+ __ROCKER_TLV_EVENT_LINK_CHANGED_MAX,
+ ROCKER_TLV_EVENT_LINK_CHANGED_MAX =
+ __ROCKER_TLV_EVENT_LINK_CHANGED_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_EVENT_MAC_VLAN_UNSPEC,
+ ROCKER_TLV_EVENT_MAC_VLAN_LPORT, /* u32 */
+ ROCKER_TLV_EVENT_MAC_VLAN_MAC, /* binary */
+ ROCKER_TLV_EVENT_MAC_VLAN_VLAN_ID, /* __be16 */
+
+ __ROCKER_TLV_EVENT_MAC_VLAN_MAX,
+ ROCKER_TLV_EVENT_MAC_VLAN_MAX = __ROCKER_TLV_EVENT_MAC_VLAN_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_RX_UNSPEC,
+ ROCKER_TLV_RX_FLAGS, /* u16, see ROCKER_RX_FLAGS_ */
+ ROCKER_TLV_RX_CSUM, /* u16 */
+ ROCKER_TLV_RX_FRAG_ADDR, /* u64 */
+ ROCKER_TLV_RX_FRAG_MAX_LEN, /* u16 */
+ ROCKER_TLV_RX_FRAG_LEN, /* u16 */
+
+ __ROCKER_TLV_RX_MAX,
+ ROCKER_TLV_RX_MAX = __ROCKER_TLV_RX_MAX - 1,
+};
+
+#define ROCKER_RX_FLAGS_IPV4 (1 << 0)
+#define ROCKER_RX_FLAGS_IPV6 (1 << 1)
+#define ROCKER_RX_FLAGS_CSUM_CALC (1 << 2)
+#define ROCKER_RX_FLAGS_IPV4_CSUM_GOOD (1 << 3)
+#define ROCKER_RX_FLAGS_IP_FRAG (1 << 4)
+#define ROCKER_RX_FLAGS_TCP (1 << 5)
+#define ROCKER_RX_FLAGS_UDP (1 << 6)
+#define ROCKER_RX_FLAGS_TCP_UDP_CSUM_GOOD (1 << 7)
+
+enum {
+ ROCKER_TLV_TX_UNSPEC,
+ ROCKER_TLV_TX_OFFLOAD, /* u8, see ROCKER_TX_OFFLOAD_ */
+ ROCKER_TLV_TX_L3_CSUM_OFF, /* u16 */
+ ROCKER_TLV_TX_TSO_MSS, /* u16 */
+ ROCKER_TLV_TX_TSO_HDR_LEN, /* u16 */
+ ROCKER_TLV_TX_FRAGS, /* array */
+
+ __ROCKER_TLV_TX_MAX,
+ ROCKER_TLV_TX_MAX = __ROCKER_TLV_TX_MAX - 1,
+};
+
+#define ROCKER_TX_OFFLOAD_NONE 0
+#define ROCKER_TX_OFFLOAD_IP_CSUM 1
+#define ROCKER_TX_OFFLOAD_TCP_UDP_CSUM 2
+#define ROCKER_TX_OFFLOAD_L3_CSUM 3
+#define ROCKER_TX_OFFLOAD_TSO 4
+
+#define ROCKER_TX_FRAGS_MAX 16
+
+enum {
+ ROCKER_TLV_TX_FRAG_UNSPEC,
+ ROCKER_TLV_TX_FRAG, /* nest */
+
+ __ROCKER_TLV_TX_FRAG_MAX,
+ ROCKER_TLV_TX_FRAG_MAX = __ROCKER_TLV_TX_FRAG_MAX - 1,
+};
+
+enum {
+ ROCKER_TLV_TX_FRAG_ATTR_UNSPEC,
+ ROCKER_TLV_TX_FRAG_ATTR_ADDR, /* u64 */
+ ROCKER_TLV_TX_FRAG_ATTR_LEN, /* u16 */
+
+ __ROCKER_TLV_TX_FRAG_ATTR_MAX,
+ ROCKER_TLV_TX_FRAG_ATTR_MAX = __ROCKER_TLV_TX_FRAG_ATTR_MAX - 1,
+};
+
+/* cmd info nested for OF-DPA msgs */
+enum {
+ ROCKER_TLV_OF_DPA_UNSPEC,
+ ROCKER_TLV_OF_DPA_TABLE_ID, /* u16 */
+ ROCKER_TLV_OF_DPA_PRIORITY, /* u32 */
+ ROCKER_TLV_OF_DPA_HARDTIME, /* u32 */
+ ROCKER_TLV_OF_DPA_IDLETIME, /* u32 */
+ ROCKER_TLV_OF_DPA_COOKIE, /* u64 */
+ ROCKER_TLV_OF_DPA_IN_LPORT, /* u32 */
+ ROCKER_TLV_OF_DPA_IN_LPORT_MASK, /* u32 */
+ ROCKER_TLV_OF_DPA_OUT_LPORT, /* u32 */
+ ROCKER_TLV_OF_DPA_GOTO_TABLE_ID, /* u16 */
+ ROCKER_TLV_OF_DPA_GROUP_ID, /* u32 */
+ ROCKER_TLV_OF_DPA_GROUP_ID_LOWER, /* u32 */
+ ROCKER_TLV_OF_DPA_GROUP_COUNT, /* u16 */
+ ROCKER_TLV_OF_DPA_GROUP_IDS, /* u32 array */
+ ROCKER_TLV_OF_DPA_VLAN_ID, /* __be16 */
+ ROCKER_TLV_OF_DPA_VLAN_ID_MASK, /* __be16 */
+ ROCKER_TLV_OF_DPA_VLAN_PCP, /* __be16 */
+ ROCKER_TLV_OF_DPA_VLAN_PCP_MASK, /* __be16 */
+ ROCKER_TLV_OF_DPA_VLAN_PCP_ACTION, /* u8 */
+ ROCKER_TLV_OF_DPA_NEW_VLAN_ID, /* __be16 */
+ ROCKER_TLV_OF_DPA_NEW_VLAN_PCP, /* u8 */
+ ROCKER_TLV_OF_DPA_TUNNEL_ID, /* u32 */
+ ROCKER_TLV_OF_DPA_TUN_LOG_LPORT, /* u32 */
+ ROCKER_TLV_OF_DPA_ETHERTYPE, /* __be16 */
+ ROCKER_TLV_OF_DPA_DST_MAC, /* binary */
+ ROCKER_TLV_OF_DPA_DST_MAC_MASK, /* binary */
+ ROCKER_TLV_OF_DPA_SRC_MAC, /* binary */
+ ROCKER_TLV_OF_DPA_SRC_MAC_MASK, /* binary */
+ ROCKER_TLV_OF_DPA_IP_PROTO, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_PROTO_MASK, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_DSCP, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_DSCP_MASK, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_DSCP_ACTION, /* u8 */
+ ROCKER_TLV_OF_DPA_NEW_IP_DSCP, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_ECN, /* u8 */
+ ROCKER_TLV_OF_DPA_IP_ECN_MASK, /* u8 */
+ ROCKER_TLV_OF_DPA_DST_IP, /* __be32 */
+ ROCKER_TLV_OF_DPA_DST_IP_MASK, /* __be32 */
+ ROCKER_TLV_OF_DPA_SRC_IP, /* __be32 */
+ ROCKER_TLV_OF_DPA_SRC_IP_MASK, /* __be32 */
+ ROCKER_TLV_OF_DPA_DST_IPV6, /* binary */
+ ROCKER_TLV_OF_DPA_DST_IPV6_MASK, /* binary */
+ ROCKER_TLV_OF_DPA_SRC_IPV6, /* binary */
+ ROCKER_TLV_OF_DPA_SRC_IPV6_MASK, /* binary */
+ ROCKER_TLV_OF_DPA_SRC_ARP_IP, /* __be32 */
+ ROCKER_TLV_OF_DPA_SRC_ARP_IP_MASK, /* __be32 */
+ ROCKER_TLV_OF_DPA_L4_DST_PORT, /* __be16 */
+ ROCKER_TLV_OF_DPA_L4_DST_PORT_MASK, /* __be16 */
+ ROCKER_TLV_OF_DPA_L4_SRC_PORT, /* __be16 */
+ ROCKER_TLV_OF_DPA_L4_SRC_PORT_MASK, /* __be16 */
+ ROCKER_TLV_OF_DPA_ICMP_TYPE, /* u8 */
+ ROCKER_TLV_OF_DPA_ICMP_TYPE_MASK, /* u8 */
+ ROCKER_TLV_OF_DPA_ICMP_CODE, /* u8 */
+ ROCKER_TLV_OF_DPA_ICMP_CODE_MASK, /* u8 */
+ ROCKER_TLV_OF_DPA_IPV6_LABEL, /* __be32 */
+ ROCKER_TLV_OF_DPA_IPV6_LABEL_MASK, /* __be32 */
+ ROCKER_TLV_OF_DPA_QUEUE_ID_ACTION, /* u8 */
+ ROCKER_TLV_OF_DPA_NEW_QUEUE_ID, /* u8 */
+ ROCKER_TLV_OF_DPA_CLEAR_ACTIONS, /* u32 */
+ ROCKER_TLV_OF_DPA_POP_VLAN, /* u8 */
+ ROCKER_TLV_OF_DPA_TTL_CHECK, /* u8 */
+ ROCKER_TLV_OF_DPA_COPY_CPU_ACTION, /* u8 */
+
+ __ROCKER_TLV_OF_DPA_MAX,
+ ROCKER_TLV_OF_DPA_MAX = __ROCKER_TLV_OF_DPA_MAX - 1,
+};
+
+/* OF-DPA table IDs */
+
+enum rocker_of_dpa_table_id {
+ ROCKER_OF_DPA_TABLE_ID_INGRESS_PORT = 0,
+ ROCKER_OF_DPA_TABLE_ID_VLAN = 10,
+ ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC = 20,
+ ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING = 30,
+ ROCKER_OF_DPA_TABLE_ID_MULTICAST_ROUTING = 40,
+ ROCKER_OF_DPA_TABLE_ID_BRIDGING = 50,
+ ROCKER_OF_DPA_TABLE_ID_ACL_POLICY = 60,
+};
+
+/* OF-DPA flow stats */
+enum {
+ ROCKER_TLV_OF_DPA_FLOW_STAT_UNSPEC,
+ ROCKER_TLV_OF_DPA_FLOW_STAT_DURATION, /* u32 */
+ ROCKER_TLV_OF_DPA_FLOW_STAT_RX_PKTS, /* u64 */
+ ROCKER_TLV_OF_DPA_FLOW_STAT_TX_PKTS, /* u64 */
+
+ __ROCKER_TLV_OF_DPA_FLOW_STAT_MAX,
+ ROCKER_TLV_OF_DPA_FLOW_STAT_MAX = __ROCKER_TLV_OF_DPA_FLOW_STAT_MAX - 1,
+};
+
+/* OF-DPA group types */
+enum rocker_of_dpa_group_type {
+ ROCKER_OF_DPA_GROUP_TYPE_L2_INTERFACE = 0,
+ ROCKER_OF_DPA_GROUP_TYPE_L2_REWRITE,
+ ROCKER_OF_DPA_GROUP_TYPE_L3_UCAST,
+ ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST,
+ ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD,
+ ROCKER_OF_DPA_GROUP_TYPE_L3_INTERFACE,
+ ROCKER_OF_DPA_GROUP_TYPE_L3_MCAST,
+ ROCKER_OF_DPA_GROUP_TYPE_L3_ECMP,
+ ROCKER_OF_DPA_GROUP_TYPE_L2_OVERLAY,
+};
+
+/* OF-DPA group L2 overlay types */
+enum rocker_of_dpa_overlay_type {
+ ROCKER_OF_DPA_OVERLAY_TYPE_FLOOD_UCAST = 0,
+ ROCKER_OF_DPA_OVERLAY_TYPE_FLOOD_MCAST,
+ ROCKER_OF_DPA_OVERLAY_TYPE_MCAST_UCAST,
+ ROCKER_OF_DPA_OVERLAY_TYPE_MCAST_MCAST,
+};
+
+/* OF-DPA group ID encoding */
+#define ROCKER_GROUP_TYPE_SHIFT 28
+#define ROCKER_GROUP_TYPE_MASK 0xf0000000
+#define ROCKER_GROUP_VLAN_SHIFT 16
+#define ROCKER_GROUP_VLAN_MASK 0x0fff0000
+#define ROCKER_GROUP_PORT_SHIFT 0
+#define ROCKER_GROUP_PORT_MASK 0x0000ffff
+#define ROCKER_GROUP_TUNNEL_ID_SHIFT 12
+#define ROCKER_GROUP_TUNNEL_ID_MASK 0x0ffff000
+#define ROCKER_GROUP_SUBTYPE_SHIFT 10
+#define ROCKER_GROUP_SUBTYPE_MASK 0x00000c00
+#define ROCKER_GROUP_INDEX_SHIFT 0
+#define ROCKER_GROUP_INDEX_MASK 0x0000ffff
+#define ROCKER_GROUP_INDEX_LONG_SHIFT 0
+#define ROCKER_GROUP_INDEX_LONG_MASK 0x0fffffff
+
+#define ROCKER_GROUP_TYPE_GET(group_id) \
+ (((group_id) & ROCKER_GROUP_TYPE_MASK) >> ROCKER_GROUP_TYPE_SHIFT)
+#define ROCKER_GROUP_TYPE_SET(type) \
+ (((type) << ROCKER_GROUP_TYPE_SHIFT) & ROCKER_GROUP_TYPE_MASK)
+#define ROCKER_GROUP_VLAN_GET(group_id) \
+ (((group_id) & ROCKER_GROUP_VLAN_ID_MASK) >> ROCKER_GROUP_VLAN_ID_SHIFT)
+#define ROCKER_GROUP_VLAN_SET(vlan_id) \
+ (((vlan_id) << ROCKER_GROUP_VLAN_SHIFT) & ROCKER_GROUP_VLAN_MASK)
+#define ROCKER_GROUP_PORT_GET(group_id) \
+ (((group_id) & ROCKER_GROUP_PORT_MASK) >> ROCKER_GROUP_PORT_SHIFT)
+#define ROCKER_GROUP_PORT_SET(port) \
+ (((port) << ROCKER_GROUP_PORT_SHIFT) & ROCKER_GROUP_PORT_MASK)
+#define ROCKER_GROUP_INDEX_GET(group_id) \
+ (((group_id) & ROCKER_GROUP_INDEX_MASK) >> ROCKER_GROUP_INDEX_SHIFT)
+#define ROCKER_GROUP_INDEX_SET(index) \
+ (((index) << ROCKER_GROUP_INDEX_SHIFT) & ROCKER_GROUP_INDEX_MASK)
+#define ROCKER_GROUP_INDEX_LONG_GET(group_id) \
+ (((group_id) & ROCKER_GROUP_INDEX_LONG_MASK) >> \
+ ROCKER_GROUP_INDEX_LONG_SHIFT)
+#define ROCKER_GROUP_INDEX_LONG_SET(index) \
+ (((index) << ROCKER_GROUP_INDEX_LONG_SHIFT) & \
+ ROCKER_GROUP_INDEX_LONG_MASK)
+
+#define ROCKER_GROUP_NONE 0
+#define ROCKER_GROUP_L2_INTERFACE(vlan_id, port) \
+ (ROCKER_GROUP_TYPE_SET(ROCKER_OF_DPA_GROUP_TYPE_L2_INTERFACE) |\
+ ROCKER_GROUP_VLAN_SET(ntohs(vlan_id)) | ROCKER_GROUP_PORT_SET(port))
+#define ROCKER_GROUP_L2_REWRITE(index) \
+ (ROCKER_GROUP_TYPE_SET(ROCKER_OF_DPA_GROUP_TYPE_L2_REWRITE) |\
+ ROCKER_GROUP_INDEX_LONG_SET(index))
+#define ROCKER_GROUP_L2_MCAST(vlan_id, index) \
+ (ROCKER_GROUP_TYPE_SET(ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST) |\
+ ROCKER_GROUP_VLAN_SET(ntohs(vlan_id)) | ROCKER_GROUP_INDEX_SET(index))
+#define ROCKER_GROUP_L2_FLOOD(vlan_id, index) \
+ (ROCKER_GROUP_TYPE_SET(ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD) |\
+ ROCKER_GROUP_VLAN_SET(ntohs(vlan_id)) | ROCKER_GROUP_INDEX_SET(index))
+#define ROCKER_GROUP_L3_UNICAST(index) \
+ (ROCKER_GROUP_TYPE_SET(ROCKER_OF_DPA_GROUP_TYPE_L3_UCAST) |\
+ ROCKER_GROUP_INDEX_LONG_SET(index))
+
+/* Rocker general purpose registers */
+#define ROCKER_CONTROL 0x0300
+#define ROCKER_PORT_PHYS_COUNT 0x0304
+#define ROCKER_PORT_PHYS_LINK_STATUS 0x0310 /* 8-byte */
+#define ROCKER_PORT_PHYS_ENABLE 0x0318 /* 8-byte */
+#define ROCKER_SWITCH_ID 0x0320 /* 8-byte */
+
+/* Rocker control bits */
+#define ROCKER_CONTROL_RESET (1 << 0)
+
+#endif
--
1.9.3
^ permalink raw reply related
* [patch net-next 07/10] bridge: call netdev_sw_port_stp_update when bridge port STP status changes
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
From: Scott Feldman <sfeldma@gmail.com>
To notify switch driver of change in STP state of bridge port, add new
.ndo op and provide swdev wrapper func to call ndo op. Use it in bridge
code then.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
include/linux/netdevice.h | 6 ++++++
include/net/switchdev.h | 6 ++++++
net/bridge/br_netlink.c | 2 ++
net/bridge/br_stp.c | 4 ++++
net/bridge/br_stp_if.c | 3 +++
net/bridge/br_stp_timer.c | 2 ++
net/switchdev/switchdev.c | 19 +++++++++++++++++++
7 files changed, 42 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7de65c5..21e5869 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1033,6 +1033,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* const unsigned char *addr,
* u16 vid);
* Called to delete a fdb from switch device port.
+ *
+ * int (*ndo_sw_port_stp_update)(struct net_device *dev, u8 state);
+ * Called to notify switch device port of bridge port STP
+ * state change.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1193,6 +1197,8 @@ struct net_device_ops {
int (*ndo_sw_port_fdb_del)(struct net_device *dev,
const unsigned char *addr,
u16 vid);
+ int (*ndo_sw_port_stp_update)(struct net_device *dev,
+ u8 state);
#endif
};
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 130cef7..bbf7369 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -21,6 +21,7 @@ int netdev_sw_port_fdb_add(struct net_device *dev,
const unsigned char *addr, u16 vid);
int netdev_sw_port_fdb_del(struct net_device *dev,
const unsigned char *addr, u16 vid);
+int netdev_sw_port_stp_update(struct net_device *dev, u8 state);
#else
@@ -42,6 +43,11 @@ static inline int netdev_sw_port_fdb_del(struct net_device *dev,
return -EOPNOTSUPP;
}
+static inline int netdev_sw_port_stp_update(struct net_device *dev, u8 state)
+{
+ return -EOPNOTSUPP;
+}
+
#endif
#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 86c239b..13fecf1 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -17,6 +17,7 @@
#include <net/net_namespace.h>
#include <net/sock.h>
#include <uapi/linux/if_bridge.h>
+#include <net/switchdev.h>
#include "br_private.h"
#include "br_private_stp.h"
@@ -304,6 +305,7 @@ static int br_set_port_state(struct net_bridge_port *p, u8 state)
br_set_state(p, state);
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_port_state_selection(p->br);
return 0;
}
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 2b047bc..c00139b 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -12,6 +12,7 @@
*/
#include <linux/kernel.h>
#include <linux/rculist.h>
+#include <net/switchdev.h>
#include "br_private.h"
#include "br_private_stp.h"
@@ -114,6 +115,7 @@ static void br_root_port_block(const struct net_bridge *br,
br_set_state(p, BR_STATE_LISTENING);
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
if (br->forward_delay > 0)
@@ -394,6 +396,7 @@ static void br_make_blocking(struct net_bridge_port *p)
br_set_state(p, BR_STATE_BLOCKING);
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
del_timer(&p->forward_delay_timer);
@@ -419,6 +422,7 @@ static void br_make_forwarding(struct net_bridge_port *p)
br_multicast_enable_port(p);
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
if (br->forward_delay != 0)
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 4114687..91279f8 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -15,6 +15,7 @@
#include <linux/kmod.h>
#include <linux/etherdevice.h>
#include <linux/rtnetlink.h>
+#include <net/switchdev.h>
#include "br_private.h"
#include "br_private_stp.h"
@@ -89,6 +90,7 @@ void br_stp_enable_port(struct net_bridge_port *p)
br_init_port(p);
br_port_state_selection(p->br);
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
}
@@ -105,6 +107,7 @@ void br_stp_disable_port(struct net_bridge_port *p)
p->config_pending = 0;
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
del_timer(&p->message_age_timer);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 4fcaa67..5bb8997 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#include <linux/times.h>
+#include <net/switchdev.h>
#include "br_private.h"
#include "br_private_stp.h"
@@ -97,6 +98,7 @@ static void br_forward_delay_timer_expired(unsigned long arg)
netif_carrier_on(br->dev);
}
br_log_state(p);
+ netdev_sw_port_stp_update(p->dev, p->state);
br_ifinfo_notify(RTM_NEWLINK, p);
spin_unlock(&br->lock);
}
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 93d47b7..75997a5 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -72,3 +72,22 @@ int netdev_sw_port_fdb_del(struct net_device *dev,
return ops->ndo_sw_port_fdb_del(dev, addr, vid);
}
EXPORT_SYMBOL(netdev_sw_port_fdb_del);
+
+/**
+ * netdev_sw_port_stp_update - Notify switch device port of STP
+ * state change
+ * @dev: port device
+ * @state: port STP state
+ *
+ * Notify switch device port of bridge port STP state change.
+ */
+int netdev_sw_port_stp_update(struct net_device *dev, u8 state)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_sw_port_stp_update)
+ return -EOPNOTSUPP;
+ WARN_ON(!ops->ndo_sw_parent_id_get);
+ return ops->ndo_sw_port_stp_update(dev, state);
+}
+EXPORT_SYMBOL(netdev_sw_port_stp_update);
--
1.9.3
^ permalink raw reply related
* [patch net-next 06/10] bridge: introduce fdb offloading via switchdev
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
From: Scott Feldman <sfeldma@gmail.com>
Add two new ndos: ndo_sw_port_fdb_add/del to offload static bridge
fdb entries. Static bridge FDB entries are installed, for example,
using iproute2 bridge cmd:
bridge fdb add ADDR dev DEV master vlan VID
This would install ADDR into the bridge's FDB for port DEV on vlan VID. The
switch driver implements two ndo_swdev ops to add/delete FDB entries in the
switch device:
int ndo_sw_port_fdb_add(struct net_device *dev,
const unsigned char *addr,
u16 vid);
int ndo_sw_port_fdb_del(struct net_device *dev,
const unsigned char *addr,
u16 vid);
The driver returns 0 on success, negative error code on failure.
Note: the switch driver would not implement ndo_fdb_add/del/dump on a port
netdev as these are intended for devices maintaining their own FDB. In our
case, we want the Linux bridge to own the FBD.
Note: by default, the bridge does not filter on VLAN and only bridges untagged
traffic. To enable VLAN support, turn on VLAN filtering:
echo 1 >/sys/class/net/<bridge>/bridge/vlan_filtering
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
include/linux/netdevice.h | 16 ++++++++++++++++
include/net/switchdev.h | 17 +++++++++++++++++
net/bridge/br_fdb.c | 10 +++++++++-
net/switchdev/switchdev.c | 41 +++++++++++++++++++++++++++++++++++++++++
4 files changed, 83 insertions(+), 1 deletion(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 54b08a7..7de65c5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1023,6 +1023,16 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* Called to get an ID of the switch chip this port is part of.
* If driver implements this, it indicates that it represents a port
* of a switch chip.
+ *
+ * int (*ndo_sw_port_fdb_add)(struct net_device *dev,
+ * const unsigned char *addr,
+ * u16 vid);
+ * Called to add a fdb to switch device port.
+ *
+ * int (*ndo_sw_port_fdb_del)(struct net_device *dev,
+ * const unsigned char *addr,
+ * u16 vid);
+ * Called to delete a fdb from switch device port.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1177,6 +1187,12 @@ struct net_device_ops {
#ifdef CONFIG_NET_SWITCHDEV
int (*ndo_sw_parent_id_get)(struct net_device *dev,
struct netdev_phys_item_id *psid);
+ int (*ndo_sw_port_fdb_add)(struct net_device *dev,
+ const unsigned char *addr,
+ u16 vid);
+ int (*ndo_sw_port_fdb_del)(struct net_device *dev,
+ const unsigned char *addr,
+ u16 vid);
#endif
};
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 79bf9bd..130cef7 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -1,6 +1,7 @@
/*
* include/net/switchdev.h - Switch device API
* Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -16,6 +17,10 @@
int netdev_sw_parent_id_get(struct net_device *dev,
struct netdev_phys_item_id *psid);
+int netdev_sw_port_fdb_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid);
+int netdev_sw_port_fdb_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid);
#else
@@ -25,6 +30,18 @@ static inline int netdev_sw_parent_id_get(struct net_device *dev,
return -EOPNOTSUPP;
}
+static inline int netdev_sw_port_fdb_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int netdev_sw_port_fdb_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ return -EOPNOTSUPP;
+}
+
#endif
#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 6f6c95c..f6f8bb5 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -24,6 +24,7 @@
#include <linux/atomic.h>
#include <asm/unaligned.h>
#include <linux/if_vlan.h>
+#include <net/switchdev.h>
#include "br_private.h"
static struct kmem_cache *br_fdb_cache __read_mostly;
@@ -132,8 +133,12 @@ static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr)
static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
{
- if (f->is_static)
+ if (f->is_static) {
fdb_del_hw(br, f->addr.addr);
+ if (f->dst)
+ netdev_sw_port_fdb_del(f->dst->dev,
+ f->addr.addr, f->vlan_id);
+ }
hlist_del_rcu(&f->hlist);
fdb_notify(br, f, RTM_DELNEIGH);
@@ -755,18 +760,21 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
if (!fdb->is_static) {
fdb->is_static = 1;
fdb_add_hw(br, addr);
+ netdev_sw_port_fdb_add(source->dev, addr, vid);
}
} else if (state & NUD_NOARP) {
fdb->is_local = 0;
if (!fdb->is_static) {
fdb->is_static = 1;
fdb_add_hw(br, addr);
+ netdev_sw_port_fdb_add(source->dev, addr, vid);
}
} else {
fdb->is_local = 0;
if (fdb->is_static) {
fdb->is_static = 0;
fdb_del_hw(br, addr);
+ netdev_sw_port_fdb_del(source->dev, addr, vid);
}
}
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 5010f646..93d47b7 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1,6 +1,7 @@
/*
* net/switchdev/switchdev.c - Switch device API
* Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014 Scott Feldman <sfeldma@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -31,3 +32,43 @@ int netdev_sw_parent_id_get(struct net_device *dev,
return ops->ndo_sw_parent_id_get(dev, psid);
}
EXPORT_SYMBOL(netdev_sw_parent_id_get);
+
+/**
+ * netdev_sw_port_fdb_add - Add a fdb into switch port
+ * @dev: port device
+ * @addr: mac address
+ * @vid: vlan id
+ *
+ * Add a fdb into switch port.
+ */
+int netdev_sw_port_fdb_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_sw_port_fdb_add)
+ return -EOPNOTSUPP;
+ WARN_ON(!ops->ndo_sw_parent_id_get);
+ return ops->ndo_sw_port_fdb_add(dev, addr, vid);
+}
+EXPORT_SYMBOL(netdev_sw_port_fdb_add);
+
+/**
+ * netdev_sw_port_fdb_del - Delete a fdb from switch port
+ * @dev: port device
+ * @addr: mac address
+ * @vid: vlan id
+ *
+ * Delete a fdb from switch port.
+ */
+int netdev_sw_port_fdb_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_sw_port_fdb_del)
+ return -EOPNOTSUPP;
+ WARN_ON(!ops->ndo_sw_parent_id_get);
+ return ops->ndo_sw_port_fdb_del(dev, addr, vid);
+}
+EXPORT_SYMBOL(netdev_sw_port_fdb_del);
--
1.9.3
^ permalink raw reply related
* [patch net-next 08/10] bridge: add API to notify bridge driver of learned FBD on offloaded device
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
From: Scott Feldman <sfeldma@gmail.com>
When the swdev device learns a new mac/vlan on a port, it sends some async
notification to the driver and the driver installs an FDB in the device.
To give a holistic system view, the learned mac/vlan should be reflected
in the bridge's FBD table, so the user, using normal iproute2 cmds, can view
what is currently learned by the device. This API on the bridge driver gives
a way for the swdev driver to install an FBD entry in the bridge FBD table.
(And remove one).
This is equivalent to the device running these cmds:
bridge fdb [add|del] <mac> dev <dev> vid <vlan id> master
This patch needs some extra eyeballs for review, in paricular around the
locking and contexts.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
include/linux/if_bridge.h | 18 ++++++++++
net/bridge/br_fdb.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 102 insertions(+)
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 808dcb8..27ab217 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -37,6 +37,24 @@ extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __use
typedef int br_should_route_hook_t(struct sk_buff *skb);
extern br_should_route_hook_t __rcu *br_should_route_hook;
+#if IS_ENABLED(CONFIG_BRIDGE)
+int br_fdb_learn_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid);
+int br_fdb_learn_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid);
+#else
+static inline int br_fdb_learn_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ return 0;
+}
+static inline int br_fdb_learn_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ return 0;
+}
+#endif
+
#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
int br_multicast_list_adjacent(struct net_device *dev,
struct list_head *br_ip_list);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index f6f8bb5..e02d21b 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -1022,3 +1022,87 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
}
}
}
+
+int br_fdb_learn_add(struct net_device *dev, const unsigned char *addr,
+ u16 vid)
+{
+ struct net_bridge_port *p;
+ struct net_bridge *br;
+ struct hlist_head *head;
+ struct net_bridge_fdb_entry *fdb;
+ int err = 0;
+
+ rtnl_lock();
+
+ p = br_port_get_rtnl(dev);
+ if (p == NULL) {
+ pr_info("bridge: %s not a bridge port\n", dev->name);
+ err = -EINVAL;
+ goto err_rtnl_unlock;
+ }
+
+ br = p->br;
+
+ spin_lock(&br->hash_lock);
+
+ head = &br->hash[br_mac_hash(addr, vid)];
+ fdb = fdb_find(head, addr, vid);
+ if (fdb == NULL) {
+ fdb = fdb_create(head, p, addr, vid);
+ if (!fdb) {
+ err = -ENOMEM;
+ goto err_unlock;
+ }
+ fdb->is_local = 1;
+ fdb->used = jiffies;
+ fdb->updated = jiffies;
+ fdb_notify(br, fdb, RTM_NEWNEIGH);
+ } else {
+ err = -EEXIST;
+ }
+
+err_unlock:
+ spin_unlock(&br->hash_lock);
+err_rtnl_unlock:
+ rtnl_unlock();
+
+ return err;
+}
+EXPORT_SYMBOL(br_fdb_learn_add);
+
+int br_fdb_learn_del(struct net_device *dev, const unsigned char *addr,
+ u16 vid)
+{
+ struct net_bridge_port *p;
+ struct net_bridge *br;
+ struct hlist_head *head;
+ struct net_bridge_fdb_entry *fdb;
+ int err = 0;
+
+ rtnl_lock();
+
+ p = br_port_get_rtnl(dev);
+ if (p == NULL) {
+ pr_info("bridge: %s not a bridge port\n", dev->name);
+ err = -EINVAL;
+ goto err_rtnl_unlock;
+ }
+
+ br = p->br;
+
+ spin_lock(&br->hash_lock);
+
+ head = &br->hash[br_mac_hash(addr, vid)];
+ fdb = fdb_find(head, addr, vid);
+ if (fdb)
+ fdb_delete(br, fdb);
+ else
+ err = -ENOENT;
+
+ spin_unlock(&br->hash_lock);
+err_rtnl_unlock:
+ rtnl_unlock();
+
+ return err;
+}
+EXPORT_SYMBOL(br_fdb_learn_del);
--
1.9.3
^ permalink raw reply related
* [patch net-next 09/10] rocker: implement rocker ofdpa flow table manipulation
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
From: Scott Feldman <sfeldma@gmail.com>
The rocker driver maintains 4 hash tables: flows, groups, FDB, and VLANs.
Flow and group tables track the entries installed to OF-DPA tables,
per the OF-DPA spec. See OF-DPA spec for full description of fields
in each flow and group table. New table entries are pushed to the
device with ADD cmd. Updated entries are pushed to the device with
MOD cmd. For flow table entries, a crc32 key is made from fields of
the particular field. For group table entries, the group_id is used
as the key.
The FDB table tracks fdb entries learned by the device or manually
pushed to the bridge by the user. A crc32 key is made from the
port/mac/vlan tuple for the fdb entry.
The VLAN table tracks the ifindex-to-internal-vlan mapping for
untagged pkts. On ingress, an untagged pkt is inserted with an
internal VLAN ID based on the input port's current internal VLAN ID.
The input port's internal VLAN will either be referenced by the port's
ifindex, if not bridged, or the containing bridge's ifindex, if
bridged. Since the ifindex space isn't within a fixed range, uses a
hash table (with ifindex as key) to track internal VLAN ID for a given
ifindex. The internal VLAN ID range is fixed and currently uses the
upper 255 VLAN IDs, starting at 0xf00.
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
drivers/net/ethernet/rocker/rocker.c | 1464 +++++++++++++++++++++++++++++++++-
1 file changed, 1462 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 797481b..b940be0 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -16,6 +16,7 @@
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/spinlock.h>
+#include <linux/hashtable.h>
#include <linux/crc32.h>
#include <linux/sort.h>
#include <linux/random.h>
@@ -41,6 +42,123 @@ static const struct pci_device_id rocker_pci_id_table[] = {
{0, }
};
+struct rocker_flow_tbl_key {
+ u32 priority;
+ enum rocker_of_dpa_table_id tbl_id;
+ union {
+ struct {
+ u32 in_lport;
+ u32 in_lport_mask;
+ enum rocker_of_dpa_table_id goto_tbl;
+ } ig_port;
+ struct {
+ u32 in_lport;
+ __be16 vlan_id;
+ __be16 vlan_id_mask;
+ enum rocker_of_dpa_table_id goto_tbl;
+ bool untagged;
+ __be16 new_vlan_id;
+ } vlan;
+ struct {
+ u32 in_lport;
+ u32 in_lport_mask;
+ __be16 eth_type;
+ u8 eth_dst[ETH_ALEN];
+ u8 eth_dst_mask[ETH_ALEN];
+ __be16 vlan_id;
+ __be16 vlan_id_mask;
+ enum rocker_of_dpa_table_id goto_tbl;
+ bool copy_to_cpu;
+ } term_mac;
+ struct {
+ __be16 eth_type;
+ __be32 dst4;
+ __be32 dst4_mask;
+ enum rocker_of_dpa_table_id goto_tbl;
+ u32 group_id;
+ } ucast_routing;
+ struct {
+ u8 eth_dst[ETH_ALEN];
+ u8 eth_dst_mask[ETH_ALEN];
+ int has_eth_dst;
+ int has_eth_dst_mask;
+ __be16 vlan_id;
+ u32 tunnel_id;
+ enum rocker_of_dpa_table_id goto_tbl;
+ u32 group_id;
+ bool copy_to_cpu;
+ } bridge;
+ struct {
+ u32 in_lport;
+ u32 in_lport_mask;
+ u8 eth_src[ETH_ALEN];
+ u8 eth_src_mask[ETH_ALEN];
+ u8 eth_dst[ETH_ALEN];
+ u8 eth_dst_mask[ETH_ALEN];
+ __be16 eth_type;
+ __be16 vlan_id;
+ __be16 vlan_id_mask;
+ u8 ip_proto;
+ u8 ip_proto_mask;
+ u8 ip_tos;
+ u8 ip_tos_mask;
+ u32 group_id;
+ } acl;
+ };
+};
+
+struct rocker_flow_tbl_entry {
+ struct hlist_node entry;
+ u32 ref_count;
+ u64 cookie;
+ struct rocker_flow_tbl_key key;
+ u32 key_crc32; /* key */
+};
+
+struct rocker_group_tbl_entry {
+ struct hlist_node entry;
+ u32 cmd;
+ u32 group_id; /* key */
+ u16 group_count;
+ u32 *group_ids;
+ union {
+ struct {
+ u8 pop_vlan;
+ } l2_interface;
+ struct {
+ u8 eth_src[ETH_ALEN];
+ u8 eth_dst[ETH_ALEN];
+ __be16 vlan_id;
+ u32 group_id;
+ } l2_rewrite;
+ struct {
+ u8 eth_src[ETH_ALEN];
+ u8 eth_dst[ETH_ALEN];
+ __be16 vlan_id;
+ bool ttl_check;
+ u32 group_id;
+ } l3_unicast;
+ };
+};
+
+struct rocker_fdb_tbl_entry {
+ struct hlist_node entry;
+ u32 key_crc32; /* key */
+ bool learned;
+ struct rocker_fdb_tbl_key {
+ u32 lport;
+ u8 addr[ETH_ALEN];
+ __be16 vlan_id;
+ } key;
+};
+
+struct rocker_internal_vlan_tbl_entry {
+ struct hlist_node entry;
+ int ifindex; /* key */
+ u32 ref_count;
+ __be16 vlan_id;
+};
+
struct rocker_desc_info {
char *data; /* mapped */
size_t data_size;
@@ -61,11 +179,28 @@ struct rocker_dma_ring_info {
struct rocker;
+enum {
+ ROCKER_CTRL_LINK_LOCAL_MCAST,
+ ROCKER_CTRL_LOCAL_ARP,
+ ROCKER_CTRL_IPV4_MCAST,
+ ROCKER_CTRL_IPV6_MCAST,
+ ROCKER_CTRL_DFLT_BRIDGING,
+ ROCKER_CTRL_MAX,
+};
+
+#define ROCKER_INTERNAL_VLAN_ID_BASE 0x0f00
+#define ROCKER_N_INTERNAL_VLANS 255
+#define ROCKER_VLAN_BITMAP_LEN BITS_TO_LONGS(VLAN_N_VID)
+#define ROCKER_INTERNAL_VLAN_BITMAP_LEN BITS_TO_LONGS(ROCKER_N_INTERNAL_VLANS)
+
struct rocker_port {
struct net_device *dev;
struct rocker *rocker;
unsigned port_number;
u32 lport;
+ __be16 internal_vlan_id;
+ bool ctrls[ROCKER_CTRL_MAX];
+ unsigned long vlan_bitmap[ROCKER_VLAN_BITMAP_LEN];
struct napi_struct napi_tx;
struct napi_struct napi_rx;
struct rocker_dma_ring_info tx_ring;
@@ -84,8 +219,76 @@ struct rocker {
spinlock_t cmd_ring_lock;
struct rocker_dma_ring_info cmd_ring;
struct rocker_dma_ring_info event_ring;
+ DECLARE_HASHTABLE(flow_tbl, 16);
+ spinlock_t flow_tbl_lock;
+ u64 flow_tbl_next_cookie;
+ DECLARE_HASHTABLE(group_tbl, 16);
+ spinlock_t group_tbl_lock;
+ DECLARE_HASHTABLE(fdb_tbl, 16);
+ spinlock_t fdb_tbl_lock;
+ unsigned long internal_vlan_bitmap[ROCKER_INTERNAL_VLAN_BITMAP_LEN];
+ DECLARE_HASHTABLE(internal_vlan_tbl, 8);
+ spinlock_t internal_vlan_tbl_lock;
};
+static const u8 zero_mac[ETH_ALEN] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
+static const u8 ff_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+static const u8 ll_mac[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+static const u8 ll_mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xf0 };
+static const u8 mcast_mac[ETH_ALEN] = { 0x01, 0x00, 0x00, 0x00, 0x00, 0x00 };
+static const u8 ipv4_mcast[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
+static const u8 ipv4_mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 };
+static const u8 ipv6_mcast[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
+static const u8 ipv6_mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 };
+
+/* Rocker priority levels for flow table entries. Higher
+ * priority match takes precedence over lower priority match.
+ */
+
+enum {
+ ROCKER_PRIORITY_UNKNOWN = 0,
+ ROCKER_PRIORITY_IG_PORT = 1,
+ ROCKER_PRIORITY_VLAN = 1,
+ ROCKER_PRIORITY_TERM_MAC_UCAST = 0,
+ ROCKER_PRIORITY_TERM_MAC_MCAST = 1,
+ ROCKER_PRIORITY_UNICAST_ROUTING = 1,
+ ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_EXACT = 1,
+ ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_WILD = 2,
+ ROCKER_PRIORITY_BRIDGING_VLAN = 3,
+ ROCKER_PRIORITY_BRIDGING_TENANT_DFLT_EXACT = 1,
+ ROCKER_PRIORITY_BRIDGING_TENANT_DFLT_WILD = 2,
+ ROCKER_PRIORITY_BRIDGING_TENANT = 3,
+ ROCKER_PRIORITY_ACL_CTRL = 3,
+ ROCKER_PRIORITY_ACL_NORMAL = 2,
+ ROCKER_PRIORITY_ACL_DFLT = 1,
+};
+
+static bool rocker_vlan_id_is_internal(__be16 vlan_id)
+{
+ u16 start = ROCKER_INTERNAL_VLAN_ID_BASE;
+ u16 end = 0xffe;
+ u16 _vlan_id = ntohs(vlan_id);
+
+ return (_vlan_id >= start && _vlan_id <= end);
+}
+
+static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port,
+ u16 vid, bool *pop_vlan)
+{
+ __be16 vlan_id;
+
+ if (pop_vlan)
+ *pop_vlan = false;
+ vlan_id = htons(vid);
+ if (!vlan_id) {
+ vlan_id = rocker_port->internal_vlan_id;
+ if (pop_vlan)
+ *pop_vlan = true;
+ }
+
+ return vlan_id;
+}
+
struct rocker_wait {
wait_queue_head_t wait;
bool done;
@@ -1094,6 +1297,10 @@ static int rocker_event_link_change(struct rocker *rocker,
return 0;
}
+#define ROCKER_OP_FLAG_REMOVE (1 << 0)
+#define ROCKER_OP_FLAG_NOWAIT (1 << 1)
+#define ROCKER_OP_FLAG_LEARNED (1 << 2)
+
static int rocker_event_process(struct rocker *rocker,
struct rocker_desc_info *desc_info)
{
@@ -1399,6 +1606,1236 @@ static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port,
macaddr, NULL, NULL, false);
}
+static int rocker_cmd_flow_tbl_add_ig_port(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT,
+ entry->key.ig_port.in_lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT_MASK,
+ entry->key.ig_port.in_lport_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GOTO_TABLE_ID,
+ entry->key.ig_port.goto_tbl))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_add_vlan(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT,
+ entry->key.vlan.in_lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->key.vlan.vlan_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID_MASK,
+ entry->key.vlan.vlan_id_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GOTO_TABLE_ID,
+ entry->key.vlan.goto_tbl))
+ return -EMSGSIZE;
+ if (entry->key.vlan.untagged &&
+ rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_NEW_VLAN_ID,
+ entry->key.vlan.new_vlan_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_add_term_mac(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT,
+ entry->key.term_mac.in_lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT_MASK,
+ entry->key.term_mac.in_lport_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_ETHERTYPE,
+ entry->key.term_mac.eth_type))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
+ ETH_ALEN, entry->key.term_mac.eth_dst))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC_MASK,
+ ETH_ALEN, entry->key.term_mac.eth_dst_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->key.term_mac.vlan_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID_MASK,
+ entry->key.term_mac.vlan_id_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GOTO_TABLE_ID,
+ entry->key.term_mac.goto_tbl))
+ return -EMSGSIZE;
+ if (entry->key.term_mac.copy_to_cpu &&
+ rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_COPY_CPU_ACTION,
+ entry->key.term_mac.copy_to_cpu))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int
+rocker_cmd_flow_tbl_add_ucast_routing(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_ETHERTYPE,
+ entry->key.ucast_routing.eth_type))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_DST_IP,
+ entry->key.ucast_routing.dst4))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_DST_IP_MASK,
+ entry->key.ucast_routing.dst4_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GOTO_TABLE_ID,
+ entry->key.ucast_routing.goto_tbl))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID,
+ entry->key.ucast_routing.group_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_add_bridge(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (entry->key.bridge.has_eth_dst &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
+ ETH_ALEN, entry->key.bridge.eth_dst))
+ return -EMSGSIZE;
+ if (entry->key.bridge.has_eth_dst_mask &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC_MASK,
+ ETH_ALEN, entry->key.bridge.eth_dst_mask))
+ return -EMSGSIZE;
+ if (entry->key.bridge.vlan_id &&
+ rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->key.bridge.vlan_id))
+ return -EMSGSIZE;
+ if (entry->key.bridge.tunnel_id &&
+ rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_TUNNEL_ID,
+ entry->key.bridge.tunnel_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GOTO_TABLE_ID,
+ entry->key.bridge.goto_tbl))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID,
+ entry->key.bridge.group_id))
+ return -EMSGSIZE;
+ if (entry->key.bridge.copy_to_cpu &&
+ rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_COPY_CPU_ACTION,
+ entry->key.bridge.copy_to_cpu))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_add_acl(struct rocker_desc_info *desc_info,
+ struct rocker_flow_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT,
+ entry->key.acl.in_lport))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_IN_LPORT_MASK,
+ entry->key.acl.in_lport_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC,
+ ETH_ALEN, entry->key.acl.eth_src))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC_MASK,
+ ETH_ALEN, entry->key.acl.eth_src_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
+ ETH_ALEN, entry->key.acl.eth_dst))
+ return -EMSGSIZE;
+ if (rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC_MASK,
+ ETH_ALEN, entry->key.acl.eth_dst_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_ETHERTYPE,
+ entry->key.acl.eth_type))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->key.acl.vlan_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID_MASK,
+ entry->key.acl.vlan_id_mask))
+ return -EMSGSIZE;
+
+ switch (ntohs(entry->key.acl.eth_type)) {
+ case ETH_P_IP:
+ case ETH_P_IPV6:
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_IP_PROTO,
+ entry->key.acl.ip_proto))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info,
+ ROCKER_TLV_OF_DPA_IP_PROTO_MASK,
+ entry->key.acl.ip_proto_mask))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_IP_DSCP,
+ entry->key.acl.ip_tos & 0x3f))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info,
+ ROCKER_TLV_OF_DPA_IP_DSCP_MASK,
+ entry->key.acl.ip_tos_mask & 0x3f))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_IP_ECN,
+ (entry->key.acl.ip_tos & 0xc0) >> 6))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info,
+ ROCKER_TLV_OF_DPA_IP_ECN_MASK,
+ (entry->key.acl.ip_tos_mask & 0xc0) >> 6))
+ return -EMSGSIZE;
+ break;
+ }
+
+ if (entry->key.acl.group_id != ROCKER_GROUP_NONE &&
+ rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID,
+ entry->key.acl.group_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_add(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ struct rocker_flow_tbl_entry *entry = priv;
+ struct rocker_tlv *cmd_info;
+ int err = 0;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_TABLE_ID,
+ entry->key.tbl_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_PRIORITY,
+ entry->key.priority))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_HARDTIME, 0))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u64(desc_info, ROCKER_TLV_OF_DPA_COOKIE,
+ entry->cookie))
+ return -EMSGSIZE;
+
+ switch (entry->key.tbl_id) {
+ case ROCKER_OF_DPA_TABLE_ID_INGRESS_PORT:
+ err = rocker_cmd_flow_tbl_add_ig_port(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_TABLE_ID_VLAN:
+ err = rocker_cmd_flow_tbl_add_vlan(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC:
+ err = rocker_cmd_flow_tbl_add_term_mac(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING:
+ err = rocker_cmd_flow_tbl_add_ucast_routing(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_TABLE_ID_BRIDGING:
+ err = rocker_cmd_flow_tbl_add_bridge(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_TABLE_ID_ACL_POLICY:
+ err = rocker_cmd_flow_tbl_add_acl(desc_info, entry);
+ break;
+ default:
+ err = -ENOTSUPP;
+ break;
+ }
+
+ if (err)
+ return err;
+
+ rocker_tlv_nest_end(desc_info, cmd_info);
+
+ return 0;
+}
+
+static int rocker_cmd_flow_tbl_del(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ const struct rocker_flow_tbl_entry *entry = priv;
+ struct rocker_tlv *cmd_info;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE,
+ ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u64(desc_info, ROCKER_TLV_OF_DPA_COOKIE,
+ entry->cookie))
+ return -EMSGSIZE;
+ rocker_tlv_nest_end(desc_info, cmd_info);
+
+ return 0;
+}
+
+static int
+rocker_cmd_group_tbl_add_l2_interface(struct rocker_desc_info *desc_info,
+ struct rocker_group_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_OUT_LPORT,
+ ROCKER_GROUP_PORT_GET(entry->group_id)))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_POP_VLAN,
+ entry->l2_interface.pop_vlan))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int
+rocker_cmd_group_tbl_add_l2_rewrite(struct rocker_desc_info *desc_info,
+ struct rocker_group_tbl_entry *entry)
+{
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID_LOWER,
+ entry->l2_rewrite.group_id))
+ return -EMSGSIZE;
+ if (!is_zero_ether_addr(entry->l2_rewrite.eth_src) &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC,
+ ETH_ALEN, entry->l2_rewrite.eth_src))
+ return -EMSGSIZE;
+ if (!is_zero_ether_addr(entry->l2_rewrite.eth_dst) &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
+ ETH_ALEN, entry->l2_rewrite.eth_dst))
+ return -EMSGSIZE;
+ if (entry->l2_rewrite.vlan_id &&
+ rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->l2_rewrite.vlan_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int
+rocker_cmd_group_tbl_add_group_ids(struct rocker_desc_info *desc_info,
+ struct rocker_group_tbl_entry *entry)
+{
+ int i;
+ struct rocker_tlv *group_ids;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_GROUP_COUNT,
+ entry->group_count))
+ return -EMSGSIZE;
+
+ group_ids = rocker_tlv_nest_start(desc_info,
+ ROCKER_TLV_OF_DPA_GROUP_IDS);
+ if (!group_ids)
+ return -EMSGSIZE;
+
+ for (i = 0; i < entry->group_count; i++)
+ /* Note TLV array is 1-based */
+ if (rocker_tlv_put_u32(desc_info, i + 1, entry->group_ids[i]))
+ return -EMSGSIZE;
+
+ rocker_tlv_nest_end(desc_info, group_ids);
+
+ return 0;
+}
+
+static int
+rocker_cmd_group_tbl_add_l3_unicast(struct rocker_desc_info *desc_info,
+ struct rocker_group_tbl_entry *entry)
+{
+ if (!is_zero_ether_addr(entry->l3_unicast.eth_src) &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_SRC_MAC,
+ ETH_ALEN, entry->l3_unicast.eth_src))
+ return -EMSGSIZE;
+ if (!is_zero_ether_addr(entry->l3_unicast.eth_dst) &&
+ rocker_tlv_put(desc_info, ROCKER_TLV_OF_DPA_DST_MAC,
+ ETH_ALEN, entry->l3_unicast.eth_dst))
+ return -EMSGSIZE;
+ if (entry->l3_unicast.vlan_id &&
+ rocker_tlv_put_u16(desc_info, ROCKER_TLV_OF_DPA_VLAN_ID,
+ entry->l3_unicast.vlan_id))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u8(desc_info, ROCKER_TLV_OF_DPA_TTL_CHECK,
+ entry->l3_unicast.ttl_check))
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID_LOWER,
+ entry->l3_unicast.group_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int rocker_cmd_group_tbl_add(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ struct rocker_group_tbl_entry *entry = priv;
+ struct rocker_tlv *cmd_info;
+ int err = 0;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, entry->cmd))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID,
+ entry->group_id))
+ return -EMSGSIZE;
+
+ switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) {
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_INTERFACE:
+ err = rocker_cmd_group_tbl_add_l2_interface(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_REWRITE:
+ err = rocker_cmd_group_tbl_add_l2_rewrite(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD:
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST:
+ err = rocker_cmd_group_tbl_add_group_ids(desc_info, entry);
+ break;
+ case ROCKER_OF_DPA_GROUP_TYPE_L3_UCAST:
+ err = rocker_cmd_group_tbl_add_l3_unicast(desc_info, entry);
+ break;
+ default:
+ err = -ENOTSUPP;
+ break;
+ }
+
+ if (err)
+ return err;
+
+ rocker_tlv_nest_end(desc_info, cmd_info);
+
+ return 0;
+}
+
+static int rocker_cmd_group_tbl_del(struct rocker *rocker,
+ struct rocker_port *rocker_port,
+ struct rocker_desc_info *desc_info,
+ void *priv)
+{
+ const struct rocker_group_tbl_entry *entry = priv;
+ struct rocker_tlv *cmd_info;
+
+ if (rocker_tlv_put_u16(desc_info, ROCKER_TLV_CMD_TYPE, entry->cmd))
+ return -EMSGSIZE;
+ cmd_info = rocker_tlv_nest_start(desc_info, ROCKER_TLV_CMD_INFO);
+ if (!cmd_info)
+ return -EMSGSIZE;
+ if (rocker_tlv_put_u32(desc_info, ROCKER_TLV_OF_DPA_GROUP_ID,
+ entry->group_id))
+ return -EMSGSIZE;
+ rocker_tlv_nest_end(desc_info, cmd_info);
+
+ return 0;
+}
+
+/*****************************************
+ * Flow, group, FDB, internal VLAN tables
+ *****************************************/
+
+static int rocker_init_tbls(struct rocker *rocker)
+{
+ hash_init(rocker->flow_tbl);
+ spin_lock_init(&rocker->flow_tbl_lock);
+
+ hash_init(rocker->group_tbl);
+ spin_lock_init(&rocker->group_tbl_lock);
+
+ hash_init(rocker->fdb_tbl);
+ spin_lock_init(&rocker->fdb_tbl_lock);
+
+ hash_init(rocker->internal_vlan_tbl);
+ spin_lock_init(&rocker->internal_vlan_tbl_lock);
+
+ return 0;
+}
+
+static void rocker_free_tbls(struct rocker *rocker)
+{
+ unsigned long flags;
+ struct rocker_flow_tbl_entry *flow_entry;
+ struct rocker_group_tbl_entry *group_entry;
+ struct rocker_fdb_tbl_entry *fdb_entry;
+ struct rocker_internal_vlan_tbl_entry *internal_vlan_entry;
+ struct hlist_node *tmp;
+ int bkt;
+
+ spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+ hash_for_each_safe(rocker->flow_tbl, bkt, tmp, flow_entry, entry)
+ hash_del(&flow_entry->entry);
+ spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+
+ spin_lock_irqsave(&rocker->group_tbl_lock, flags);
+ hash_for_each_safe(rocker->group_tbl, bkt, tmp, group_entry, entry)
+ hash_del(&group_entry->entry);
+ spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
+
+ spin_lock_irqsave(&rocker->fdb_tbl_lock, flags);
+ hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, fdb_entry, entry)
+ hash_del(&fdb_entry->entry);
+ spin_unlock_irqrestore(&rocker->fdb_tbl_lock, flags);
+
+ spin_lock_irqsave(&rocker->internal_vlan_tbl_lock, flags);
+ hash_for_each_safe(rocker->internal_vlan_tbl, bkt,
+ tmp, internal_vlan_entry, entry)
+ hash_del(&internal_vlan_entry->entry);
+ spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, flags);
+}
+
+static struct rocker_flow_tbl_entry *
+rocker_flow_tbl_find(struct rocker *rocker, struct rocker_flow_tbl_entry *match)
+{
+ struct rocker_flow_tbl_entry *found;
+
+ hash_for_each_possible(rocker->flow_tbl, found, entry, match->key_crc32)
+ if (memcmp(&found->key, &match->key, sizeof(found->key)) == 0)
+ return found;
+
+ return NULL;
+}
+
+static int rocker_flow_tbl_add(struct rocker_port *rocker_port,
+ struct rocker_flow_tbl_entry *match,
+ bool nowait)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_flow_tbl_entry *found;
+ unsigned long flags;
+ bool add_to_hw = false;
+ int err = 0;
+
+ match->key_crc32 = crc32(~0, &match->key, sizeof(match->key));
+
+ spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+
+ found = rocker_flow_tbl_find(rocker, match);
+
+ if (found) {
+ kfree(match);
+ } else {
+ found = match;
+ found->cookie = rocker->flow_tbl_next_cookie++;
+ hash_add(rocker->flow_tbl, &found->entry, found->key_crc32);
+ add_to_hw = true;
+ }
+
+ found->ref_count++;
+
+ spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+
+ if (add_to_hw) {
+ err = rocker_cmd_exec(rocker, rocker_port,
+ rocker_cmd_flow_tbl_add,
+ found, NULL, NULL, nowait);
+ if (err) {
+ spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+ hash_del(&found->entry);
+ spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+ kfree(found);
+ }
+ }
+
+ return err;
+}
+
+static int rocker_flow_tbl_del(struct rocker_port *rocker_port,
+ struct rocker_flow_tbl_entry *match,
+ bool nowait)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_flow_tbl_entry *found;
+ unsigned long flags;
+ bool del_from_hw = false;
+ int err = 0;
+
+ match->key_crc32 = crc32(~0, &match->key, sizeof(match->key));
+
+ spin_lock_irqsave(&rocker->flow_tbl_lock, flags);
+
+ found = rocker_flow_tbl_find(rocker, match);
+
+ if (found) {
+ found->ref_count--;
+ if (found->ref_count == 0) {
+ hash_del(&found->entry);
+ del_from_hw = true;
+ }
+ }
+
+ spin_unlock_irqrestore(&rocker->flow_tbl_lock, flags);
+
+ kfree(match);
+
+ if (del_from_hw) {
+ err = rocker_cmd_exec(rocker, rocker_port,
+ rocker_cmd_flow_tbl_del,
+ found, NULL, NULL, nowait);
+ kfree(found);
+ }
+
+ return err;
+}
+
+static gfp_t rocker_op_flags_gfp(int flags)
+{
+ return flags & ROCKER_OP_FLAG_NOWAIT ? GFP_ATOMIC : GFP_KERNEL;
+}
+
+static int rocker_flow_tbl_do(struct rocker_port *rocker_port,
+ int flags, struct rocker_flow_tbl_entry *entry)
+{
+ bool nowait = flags & ROCKER_OP_FLAG_NOWAIT;
+
+ if (flags & ROCKER_OP_FLAG_REMOVE)
+ return rocker_flow_tbl_del(rocker_port, entry, nowait);
+ else
+ return rocker_flow_tbl_add(rocker_port, entry, nowait);
+}
+
+static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port,
+ int flags, u32 in_lport, u32 in_lport_mask,
+ enum rocker_of_dpa_table_id goto_tbl)
+{
+ struct rocker_flow_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->key.priority = ROCKER_PRIORITY_IG_PORT;
+ entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_INGRESS_PORT;
+ entry->key.ig_port.in_lport = in_lport;
+ entry->key.ig_port.in_lport_mask = in_lport_mask;
+ entry->key.ig_port.goto_tbl = goto_tbl;
+
+ return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port,
+ int flags, u32 in_lport,
+ __be16 vlan_id, __be16 vlan_id_mask,
+ enum rocker_of_dpa_table_id goto_tbl,
+ bool untagged, __be16 new_vlan_id)
+{
+ struct rocker_flow_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->key.priority = ROCKER_PRIORITY_VLAN;
+ entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_VLAN;
+ entry->key.vlan.in_lport = in_lport;
+ entry->key.vlan.vlan_id = vlan_id;
+ entry->key.vlan.vlan_id_mask = vlan_id_mask;
+ entry->key.vlan.goto_tbl = goto_tbl;
+
+ entry->key.vlan.untagged = untagged;
+ entry->key.vlan.new_vlan_id = new_vlan_id;
+
+ return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port,
+ u32 in_lport, u32 in_lport_mask,
+ __be16 eth_type, const u8 *eth_dst,
+ const u8 *eth_dst_mask, __be16 vlan_id,
+ __be16 vlan_id_mask, bool copy_to_cpu,
+ int flags)
+{
+ struct rocker_flow_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ if (is_multicast_ether_addr(eth_dst)) {
+ entry->key.priority = ROCKER_PRIORITY_TERM_MAC_MCAST;
+ entry->key.term_mac.goto_tbl =
+ ROCKER_OF_DPA_TABLE_ID_MULTICAST_ROUTING;
+ } else {
+ entry->key.priority = ROCKER_PRIORITY_TERM_MAC_UCAST;
+ entry->key.term_mac.goto_tbl =
+ ROCKER_OF_DPA_TABLE_ID_UNICAST_ROUTING;
+ }
+
+ entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC;
+ entry->key.term_mac.in_lport = in_lport;
+ entry->key.term_mac.in_lport_mask = in_lport_mask;
+ entry->key.term_mac.eth_type = eth_type;
+ ether_addr_copy(entry->key.term_mac.eth_dst, eth_dst);
+ ether_addr_copy(entry->key.term_mac.eth_dst_mask, eth_dst_mask);
+ entry->key.term_mac.vlan_id = vlan_id;
+ entry->key.term_mac.vlan_id_mask = vlan_id_mask;
+ entry->key.term_mac.copy_to_cpu = copy_to_cpu;
+
+ return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port,
+ int flags,
+ const u8 *eth_dst, const u8 *eth_dst_mask,
+ __be16 vlan_id, u32 tunnel_id,
+ enum rocker_of_dpa_table_id goto_tbl,
+ u32 group_id, bool copy_to_cpu)
+{
+ struct rocker_flow_tbl_entry *entry;
+ u32 priority;
+ bool vlan_bridging = !!vlan_id;
+ bool dflt = !eth_dst || (eth_dst && eth_dst_mask);
+ bool wild = false;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_BRIDGING;
+
+ if (eth_dst) {
+ entry->key.bridge.has_eth_dst = 1;
+ ether_addr_copy(entry->key.bridge.eth_dst, eth_dst);
+ }
+ if (eth_dst_mask) {
+ entry->key.bridge.has_eth_dst_mask = 1;
+ ether_addr_copy(entry->key.bridge.eth_dst_mask, eth_dst_mask);
+ if (memcmp(eth_dst_mask, ff_mac, ETH_ALEN))
+ wild = true;
+ }
+
+ priority = ROCKER_PRIORITY_UNKNOWN;
+ if (vlan_bridging & dflt & wild)
+ priority = ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_WILD;
+ else if (vlan_bridging & dflt & !wild)
+ priority = ROCKER_PRIORITY_BRIDGING_VLAN_DFLT_EXACT;
+ else if (vlan_bridging & !dflt)
+ priority = ROCKER_PRIORITY_BRIDGING_VLAN;
+ else if (!vlan_bridging & dflt & wild)
+ priority = ROCKER_PRIORITY_BRIDGING_TENANT_DFLT_WILD;
+ else if (!vlan_bridging & dflt & !wild)
+ priority = ROCKER_PRIORITY_BRIDGING_TENANT_DFLT_EXACT;
+ else if (!vlan_bridging & !dflt)
+ priority = ROCKER_PRIORITY_BRIDGING_TENANT;
+
+ entry->key.priority = priority;
+ entry->key.bridge.vlan_id = vlan_id;
+ entry->key.bridge.tunnel_id = tunnel_id;
+ entry->key.bridge.goto_tbl = goto_tbl;
+ entry->key.bridge.group_id = group_id;
+ entry->key.bridge.copy_to_cpu = copy_to_cpu;
+
+ return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_flow_tbl_acl(struct rocker_port *rocker_port,
+ int flags, u32 in_lport,
+ u32 in_lport_mask,
+ const u8 *eth_src, const u8 *eth_src_mask,
+ const u8 *eth_dst, const u8 *eth_dst_mask,
+ __be16 eth_type,
+ __be16 vlan_id, __be16 vlan_id_mask,
+ u8 ip_proto, u8 ip_proto_mask,
+ u8 ip_tos, u8 ip_tos_mask,
+ u32 group_id)
+{
+ u32 priority;
+ struct rocker_flow_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ priority = ROCKER_PRIORITY_ACL_NORMAL;
+ if (eth_dst && eth_dst_mask) {
+ if (memcmp(eth_dst_mask, mcast_mac, ETH_ALEN) == 0)
+ priority = ROCKER_PRIORITY_ACL_DFLT;
+ else if (is_link_local_ether_addr(eth_dst))
+ priority = ROCKER_PRIORITY_ACL_CTRL;
+ }
+
+ entry->key.priority = priority;
+ entry->key.tbl_id = ROCKER_OF_DPA_TABLE_ID_ACL_POLICY;
+ entry->key.acl.in_lport = in_lport;
+ entry->key.acl.in_lport_mask = in_lport_mask;
+
+ if (eth_src)
+ ether_addr_copy(entry->key.acl.eth_src, eth_src);
+ if (eth_src_mask)
+ ether_addr_copy(entry->key.acl.eth_src_mask, eth_src_mask);
+ if (eth_dst)
+ ether_addr_copy(entry->key.acl.eth_dst, eth_dst);
+ if (eth_dst_mask)
+ ether_addr_copy(entry->key.acl.eth_dst_mask, eth_dst_mask);
+
+ entry->key.acl.eth_type = eth_type;
+ entry->key.acl.vlan_id = vlan_id;
+ entry->key.acl.vlan_id_mask = vlan_id_mask;
+ entry->key.acl.ip_proto = ip_proto;
+ entry->key.acl.ip_proto_mask = ip_proto_mask;
+ entry->key.acl.ip_tos = ip_tos;
+ entry->key.acl.ip_tos_mask = ip_tos_mask;
+ entry->key.acl.group_id = group_id;
+
+ return rocker_flow_tbl_do(rocker_port, flags, entry);
+}
+
+static struct rocker_group_tbl_entry *
+rocker_group_tbl_find(struct rocker *rocker,
+ struct rocker_group_tbl_entry *match)
+{
+ struct rocker_group_tbl_entry *found;
+
+ hash_for_each_possible(rocker->group_tbl, found,
+ entry, match->group_id)
+ if (found->group_id == match->group_id)
+ return found;
+
+ return NULL;
+}
+
+static void rocker_group_tbl_entry_free(struct rocker_group_tbl_entry *entry)
+{
+ switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) {
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_FLOOD:
+ case ROCKER_OF_DPA_GROUP_TYPE_L2_MCAST:
+ kfree(entry->group_ids);
+ break;
+ default:
+ break;
+ }
+ kfree(entry);
+}
+
+static int rocker_group_tbl_add(struct rocker_port *rocker_port,
+ struct rocker_group_tbl_entry *match,
+ bool nowait)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_group_tbl_entry *found;
+ unsigned long flags;
+ int err = 0;
+
+ spin_lock_irqsave(&rocker->group_tbl_lock, flags);
+
+ found = rocker_group_tbl_find(rocker, match);
+
+ if (found) {
+ hash_del(&found->entry);
+ rocker_group_tbl_entry_free(found);
+ found = match;
+ found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_MOD;
+ } else {
+ found = match;
+ found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD;
+ }
+
+ hash_add(rocker->group_tbl, &found->entry, found->group_id);
+
+ spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
+
+ if (found->cmd)
+ err = rocker_cmd_exec(rocker, rocker_port,
+ rocker_cmd_group_tbl_add,
+ found, NULL, NULL, nowait);
+
+ return err;
+}
+
+static int rocker_group_tbl_del(struct rocker_port *rocker_port,
+ struct rocker_group_tbl_entry *match,
+ bool nowait)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_group_tbl_entry *found;
+ unsigned long flags;
+ int err = 0;
+
+ spin_lock_irqsave(&rocker->group_tbl_lock, flags);
+
+ found = rocker_group_tbl_find(rocker, match);
+
+ if (found) {
+ hash_del(&found->entry);
+ found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL;
+ }
+
+ spin_unlock_irqrestore(&rocker->group_tbl_lock, flags);
+
+ rocker_group_tbl_entry_free(match);
+
+ if (found) {
+ err = rocker_cmd_exec(rocker, rocker_port,
+ rocker_cmd_group_tbl_del,
+ found, NULL, NULL, nowait);
+ rocker_group_tbl_entry_free(found);
+ }
+
+ return err;
+}
+
+static int rocker_group_tbl_do(struct rocker_port *rocker_port,
+ int flags, struct rocker_group_tbl_entry *entry)
+{
+ bool nowait = flags & ROCKER_OP_FLAG_NOWAIT;
+
+ if (flags & ROCKER_OP_FLAG_REMOVE)
+ return rocker_group_tbl_del(rocker_port, entry, nowait);
+ else
+ return rocker_group_tbl_add(rocker_port, entry, nowait);
+}
+
+static int rocker_group_l2_interface(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id,
+ u32 out_lport, int pop_vlan)
+{
+ struct rocker_group_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_lport);
+ entry->l2_interface.pop_vlan = pop_vlan;
+
+ return rocker_group_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_group_l2_fan_out(struct rocker_port *rocker_port,
+ int flags, u8 group_count,
+ u32 *group_ids, u32 group_id)
+{
+ struct rocker_group_tbl_entry *entry;
+
+ entry = kzalloc(sizeof(*entry), rocker_op_flags_gfp(flags));
+ if (!entry)
+ return -ENOMEM;
+
+ entry->group_id = group_id;
+ entry->group_count = group_count;
+
+ entry->group_ids = kcalloc(group_count, sizeof(u32),
+ rocker_op_flags_gfp(flags));
+ if (!entry->group_ids) {
+ kfree(entry);
+ return -ENOMEM;
+ }
+ memcpy(entry->group_ids, group_ids, group_count * sizeof(u32));
+
+ return rocker_group_tbl_do(rocker_port, flags, entry);
+}
+
+static int rocker_group_l2_flood(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id,
+ u8 group_count, u32 *group_ids,
+ u32 group_id)
+{
+ return rocker_group_l2_fan_out(rocker_port, flags,
+ group_count, group_ids,
+ group_id);
+}
+
+static struct rocker_ctrl {
+ const u8 *eth_dst;
+ const u8 *eth_dst_mask;
+ u16 eth_type;
+ bool acl;
+ bool bridge;
+ bool term;
+ bool copy_to_cpu;
+} rocker_ctrls[] = {
+ [ROCKER_CTRL_LINK_LOCAL_MCAST] = {
+ /* pass link local multicast pkts up to CPU for filtering */
+ .eth_dst = ll_mac,
+ .eth_dst_mask = ll_mask,
+ .acl = true,
+ },
+ [ROCKER_CTRL_LOCAL_ARP] = {
+ /* pass local ARP pkts up to CPU */
+ .eth_dst = zero_mac,
+ .eth_dst_mask = zero_mac,
+ .eth_type = htons(ETH_P_ARP),
+ .acl = true,
+ },
+ [ROCKER_CTRL_IPV4_MCAST] = {
+ /* pass IPv4 mcast pkts up to CPU, RFC 1112 */
+ .eth_dst = ipv4_mcast,
+ .eth_dst_mask = ipv4_mask,
+ .eth_type = htons(ETH_P_IP),
+ .term = true,
+ .copy_to_cpu = true,
+ },
+ [ROCKER_CTRL_IPV6_MCAST] = {
+ /* pass IPv6 mcast pkts up to CPU, RFC 2464 */
+ .eth_dst = ipv6_mcast,
+ .eth_dst_mask = ipv6_mask,
+ .eth_type = htons(ETH_P_IPV6),
+ .term = true,
+ .copy_to_cpu = true,
+ },
+ [ROCKER_CTRL_DFLT_BRIDGING] = {
+ /* flood any pkts on vlan */
+ .bridge = true,
+ .copy_to_cpu = true,
+ },
+};
+
+static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port,
+ int flags, struct rocker_ctrl *ctrl,
+ __be16 vlan_id)
+{
+ u32 in_lport = rocker_port->lport;
+ u32 in_lport_mask = 0xffffffff;
+ u32 out_lport = 0;
+ u8 *eth_src = NULL;
+ u8 *eth_src_mask = NULL;
+ __be16 vlan_id_mask = htons(0xffff);
+ u8 ip_proto = 0;
+ u8 ip_proto_mask = 0;
+ u8 ip_tos = 0;
+ u8 ip_tos_mask = 0;
+ u32 group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_lport);
+ int err;
+
+ err = rocker_flow_tbl_acl(rocker_port, flags,
+ in_lport, in_lport_mask,
+ eth_src, eth_src_mask,
+ ctrl->eth_dst, ctrl->eth_dst_mask,
+ ctrl->eth_type,
+ vlan_id, vlan_id_mask,
+ ip_proto, ip_proto_mask,
+ ip_tos, ip_tos_mask,
+ group_id);
+
+ if (err)
+ netdev_err(rocker_port->dev, "Error (%d) ctrl ACL\n", err);
+
+ return err;
+}
+
+static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port,
+ int flags, struct rocker_ctrl *ctrl,
+ __be16 vlan_id)
+{
+ u32 in_lport_mask = 0xffffffff;
+ __be16 vlan_id_mask = htons(0xffff);
+ int err;
+
+ if (ntohs(vlan_id) == 0)
+ vlan_id = rocker_port->internal_vlan_id;
+
+ err = rocker_flow_tbl_term_mac(rocker_port,
+ rocker_port->lport, in_lport_mask,
+ ctrl->eth_type, ctrl->eth_dst,
+ ctrl->eth_dst_mask, vlan_id,
+ vlan_id_mask, ctrl->copy_to_cpu,
+ flags);
+
+ if (err)
+ netdev_err(rocker_port->dev, "Error (%d) ctrl term\n", err);
+
+ return err;
+}
+
+static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, int flags,
+ struct rocker_ctrl *ctrl, __be16 vlan_id)
+{
+ if (ctrl->acl)
+ return rocker_port_ctrl_vlan_acl(rocker_port, flags,
+ ctrl, vlan_id);
+
+ if (ctrl->term)
+ return rocker_port_ctrl_vlan_term(rocker_port, flags,
+ ctrl, vlan_id);
+
+ return -EOPNOTSUPP;
+}
+
+static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id)
+{
+ int err = 0;
+ int i;
+
+ for (i = 0; i < ROCKER_CTRL_MAX; i++) {
+ if (rocker_port->ctrls[i]) {
+ err = rocker_port_ctrl_vlan(rocker_port, flags,
+ &rocker_ctrls[i], vlan_id);
+ if (err)
+ return err;
+ }
+ }
+
+ return err;
+}
+
+static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags,
+ struct rocker_ctrl *ctrl)
+{
+ u16 vid;
+ int err = 0;
+
+ for (vid = 1; vid < VLAN_N_VID; vid++) {
+ if (!test_bit(vid, rocker_port->vlan_bitmap))
+ continue;
+ err = rocker_port_ctrl_vlan(rocker_port, flags,
+ ctrl, htons(vid));
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
+{
+ enum rocker_of_dpa_table_id goto_tbl;
+ u32 in_lport;
+ u32 in_lport_mask;
+ int err;
+
+ /* Normal Ethernet Frames. Matches pkts from any local physical
+ * ports. Goto VLAN tbl.
+ */
+
+ in_lport = 0;
+ in_lport_mask = 0xffff0000;
+ goto_tbl = ROCKER_OF_DPA_TABLE_ID_VLAN;
+
+ err = rocker_flow_tbl_ig_port(rocker_port, flags,
+ in_lport, in_lport_mask,
+ goto_tbl);
+ if (err)
+ netdev_err(rocker_port->dev,
+ "Error (%d) ingress port table entry\n", err);
+
+ return err;
+}
+
+static int rocker_port_router_mac(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id)
+{
+ u32 in_lport_mask = 0xffffffff;
+ __be16 eth_type;
+ const u8 *dst_mac_mask = ff_mac;
+ __be16 vlan_id_mask = htons(0xffff);
+ bool copy_to_cpu = false;
+ int err;
+
+ if (ntohs(vlan_id) == 0)
+ vlan_id = rocker_port->internal_vlan_id;
+
+ eth_type = htons(ETH_P_IP);
+ err = rocker_flow_tbl_term_mac(rocker_port,
+ rocker_port->lport, in_lport_mask,
+ eth_type, rocker_port->dev->dev_addr,
+ dst_mac_mask, vlan_id, vlan_id_mask,
+ copy_to_cpu, flags);
+ if (err)
+ return err;
+
+ eth_type = htons(ETH_P_IPV6);
+ err = rocker_flow_tbl_term_mac(rocker_port,
+ rocker_port->lport, in_lport_mask,
+ eth_type, rocker_port->dev->dev_addr,
+ dst_mac_mask, vlan_id, vlan_id_mask,
+ copy_to_cpu, flags);
+
+ return err;
+}
+
+static struct rocker_internal_vlan_tbl_entry *
+rocker_internal_vlan_tbl_find(struct rocker *rocker, int ifindex)
+{
+ struct rocker_internal_vlan_tbl_entry *found;
+
+ hash_for_each_possible(rocker->internal_vlan_tbl,
+ found, entry, ifindex)
+ if (found->ifindex == ifindex)
+ return found;
+
+ return NULL;
+}
+
+static __be16 rocker_port_internal_vlan_id_get(struct rocker_port *rocker_port,
+ int ifindex)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_internal_vlan_tbl_entry *entry;
+ struct rocker_internal_vlan_tbl_entry *found;
+ unsigned long lock_flags;
+ int i;
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return 0;
+
+ entry->ifindex = ifindex;
+
+ spin_lock_irqsave(&rocker->internal_vlan_tbl_lock, lock_flags);
+
+ found = rocker_internal_vlan_tbl_find(rocker, ifindex);
+ if (found) {
+ kfree(entry);
+ goto found;
+ }
+
+ found = entry;
+ hash_add(rocker->internal_vlan_tbl, &found->entry, found->ifindex);
+
+ for (i = 0; i < ROCKER_N_INTERNAL_VLANS; i++) {
+ if (test_and_set_bit(i, rocker->internal_vlan_bitmap))
+ continue;
+ found->vlan_id = htons(ROCKER_INTERNAL_VLAN_ID_BASE + i);
+ goto found;
+ }
+
+ netdev_err(rocker_port->dev, "Out of internal VLAN IDs\n");
+
+found:
+ found->ref_count++;
+ spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, lock_flags);
+
+ return found->vlan_id;
+}
+
+static void rocker_port_internal_vlan_id_put(struct rocker_port *rocker_port,
+ int ifindex)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_internal_vlan_tbl_entry *found;
+ unsigned long lock_flags;
+ unsigned long bit;
+
+ spin_lock_irqsave(&rocker->internal_vlan_tbl_lock, lock_flags);
+
+ found = rocker_internal_vlan_tbl_find(rocker, ifindex);
+ if (!found) {
+ netdev_err(rocker_port->dev,
+ "ifindex (%d) not found in internal VLAN tbl\n",
+ ifindex);
+ goto not_found;
+ }
+
+ if (--found->ref_count <= 0) {
+ bit = ntohs(found->vlan_id) - ROCKER_INTERNAL_VLAN_ID_BASE;
+ clear_bit(bit, rocker->internal_vlan_bitmap);
+ hash_del(&found->entry);
+ kfree(found);
+ }
+
+not_found:
+ spin_unlock_irqrestore(&rocker->internal_vlan_tbl_lock, lock_flags);
+}
+
/*****************
* Net device ops
*****************/
@@ -1770,10 +3207,14 @@ static void rocker_carrier_init(struct rocker_port *rocker_port)
static void rocker_remove_ports(struct rocker *rocker)
{
+ struct rocker_port *rocker_port;
int i;
- for (i = 0; i < rocker->port_count; i++)
- unregister_netdev(rocker->ports[i]->dev);
+ for (i = 0; i < rocker->port_count; i++) {
+ rocker_port = rocker->ports[i];
+ rocker_port_ig_tbl(rocker_port, ROCKER_OP_FLAG_REMOVE);
+ unregister_netdev(rocker_port->dev);
+ }
kfree(rocker->ports);
}
@@ -1825,8 +3266,18 @@ static int rocker_probe_port(struct rocker *rocker, unsigned port_number)
}
rocker->ports[port_number] = rocker_port;
+ rocker_port->internal_vlan_id =
+ rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex);
+ err = rocker_port_ig_tbl(rocker_port, 0);
+ if (err) {
+ dev_err(&pdev->dev, "install ig port table failed\n");
+ goto err_port_ig_tbl;
+ }
+
return 0;
+err_port_ig_tbl:
+ unregister_netdev(dev);
err_register_netdev:
free_netdev(dev);
return err;
@@ -1983,6 +3434,12 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
+ err = rocker_init_tbls(rocker);
+ if (err) {
+ dev_err(&pdev->dev, "cannot init rocker tables\n");
+ goto err_init_tbls;
+ }
+
err = rocker_probe_ports(rocker);
if (err) {
dev_err(&pdev->dev, "failed to probe ports\n");
@@ -1994,6 +3451,8 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
return 0;
err_probe_ports:
+ rocker_free_tbls(rocker);
+err_init_tbls:
free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
err_request_event_irq:
free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_CMD), rocker);
@@ -2019,6 +3478,7 @@ static void rocker_remove(struct pci_dev *pdev)
{
struct rocker *rocker = pci_get_drvdata(pdev);
+ rocker_free_tbls(rocker);
rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET);
rocker_remove_ports(rocker);
free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker);
--
1.9.3
^ permalink raw reply related
* [patch net-next 10/10] rocker: implement L2 bridge offloading
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
From: Scott Feldman <sfeldma@gmail.com>
Add L2 bridge offloading support to rocker driver. Here, the Linux bridge
driver is used to collect swdev ports into a tagged (or untagged) VLAN
bridge. The swdev will offload from the bridge driver the following L2
bridging functions:
- Learning of neighbor MAC addresses on VLAN X Learned mac/vlan is
installed in bridge FDB. (And removed when device unlearns mac/vlan).
Learning must be turned off on each bridge port to disable the feature in
the bridge driver.
- Flooding of multicast/broadcast and unknown unicast pkts to (STP)
active ports in bridge. The bridge driver is unaware of the flooding happening
at the device level. Flooding must be turned off on each bridge port to
disable the feature on the bridge driver.
- STP port state is pushed down to driver/device. The bridge still processes
STP BDPUs and maintains port STP state (for all VLANs in bridge), but
the driver/device must be notified of port STP state change to program
the device.
Multiple (VLAN) bridges are supported. The device (implemented per
the OF-DPA spec) must use a portion of the VLAN namespace for
internal VLANs. Right now, the upper 255 VLANs (0xf00 to 0xffe) are
used as internal VLAN IDs for untagged traffic and are not available
as port VLANs.
The driver uses the following interfaces:
1. To track VLAN add/del on ports in bridge:
.ndo_vlan_rx_add_vid
.ndo_vlan_rx_kill_vid
2. To track port add/del membership in bridge:
NETDEV_CHANGEUPPER netdevice notifier
3. To catch static FDB entries installed on bridge/vlan by user using netlink:
.ndo_sw_port_fdb_add
.ndo_sw_port_fdb_del
4. To be notified on port STP state change:
.ndo_sw_port_stp_update
5. To notify bridge driver on learned/forgotten mac/vlans on bridge port:
br_fdb_learn_add
br_fdb_learn_del
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
drivers/net/ethernet/rocker/rocker.c | 660 ++++++++++++++++++++++++++++++++++-
1 file changed, 659 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index b940be0..e0b47d6 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -28,6 +28,7 @@
#include <linux/ethtool.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
+#include <linux/if_bridge.h>
#include <net/switchdev.h>
#include <net/rtnetlink.h>
#include <asm-generic/io-64-nonatomic-lo-hi.h>
@@ -195,10 +196,12 @@ enum {
struct rocker_port {
struct net_device *dev;
+ struct net_device *bridge_dev;
struct rocker *rocker;
unsigned port_number;
u32 lport;
__be16 internal_vlan_id;
+ int stp_state;
bool ctrls[ROCKER_CTRL_MAX];
unsigned long vlan_bitmap[ROCKER_VLAN_BITMAP_LEN];
struct napi_struct napi_tx;
@@ -289,6 +292,20 @@ static __be16 rocker_port_vid_to_vlan(struct rocker_port *rocker_port,
return vlan_id;
}
+static u16 rocker_port_vlan_to_vid(struct rocker_port *rocker_port,
+ __be16 vlan_id)
+{
+ if (rocker_vlan_id_is_internal(vlan_id))
+ return 0;
+
+ return ntohs(vlan_id);
+}
+
+static bool rocker_port_is_bridged(struct rocker_port *rocker_port)
+{
+ return !!rocker_port->bridge_dev;
+}
+
struct rocker_wait {
wait_queue_head_t wait;
bool done;
@@ -1301,6 +1318,42 @@ static int rocker_event_link_change(struct rocker *rocker,
#define ROCKER_OP_FLAG_NOWAIT (1 << 1)
#define ROCKER_OP_FLAG_LEARNED (1 << 2)
+static int rocker_port_fdb(struct rocker_port *rocker_port,
+ const unsigned char *addr,
+ __be16 vlan_id, int flags);
+
+static int rocker_event_mac_vlan_seen(struct rocker *rocker,
+ const struct rocker_tlv *info)
+{
+ struct rocker_tlv *attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAX + 1];
+ unsigned port_number;
+ struct rocker_port *rocker_port;
+ unsigned char *addr;
+ int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_LEARNED;
+ __be16 vlan_id;
+
+ rocker_tlv_parse_nested(attrs, ROCKER_TLV_EVENT_MAC_VLAN_MAX, info);
+ if (!attrs[ROCKER_TLV_EVENT_MAC_VLAN_LPORT] ||
+ !attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAC] ||
+ !attrs[ROCKER_TLV_EVENT_MAC_VLAN_VLAN_ID])
+ return -EIO;
+ port_number =
+ rocker_tlv_get_u32(attrs[ROCKER_TLV_EVENT_MAC_VLAN_LPORT]) - 1;
+ addr = rocker_tlv_data(attrs[ROCKER_TLV_EVENT_MAC_VLAN_MAC]);
+ vlan_id = rocker_tlv_get_u16(attrs[ROCKER_TLV_EVENT_MAC_VLAN_VLAN_ID]);
+
+ if (port_number >= rocker->port_count)
+ return -EINVAL;
+
+ rocker_port = rocker->ports[port_number];
+
+ if (rocker_port->stp_state != BR_STATE_LEARNING &&
+ rocker_port->stp_state != BR_STATE_FORWARDING)
+ return 0;
+
+ return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+}
+
static int rocker_event_process(struct rocker *rocker,
struct rocker_desc_info *desc_info)
{
@@ -1319,6 +1372,8 @@ static int rocker_event_process(struct rocker *rocker,
switch (type) {
case ROCKER_TLV_EVENT_TYPE_LINK_CHANGED:
return rocker_event_link_change(rocker, info);
+ case ROCKER_TLV_EVENT_TYPE_MAC_VLAN_SEEN:
+ return rocker_event_mac_vlan_seen(rocker, info);
}
return -EOPNOTSUPP;
@@ -2543,6 +2598,104 @@ static int rocker_group_l2_flood(struct rocker_port *rocker_port,
group_id);
}
+static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id)
+{
+ struct rocker_port *p;
+ struct rocker *rocker = rocker_port->rocker;
+ u32 group_id = ROCKER_GROUP_L2_FLOOD(vlan_id, 0);
+ u32 group_ids[rocker->port_count];
+ u8 group_count = 0;
+ int err;
+ int i;
+
+ /* Adjust the flood group for this VLAN. The flood group
+ * references an L2 interface group for each port in this
+ * VLAN.
+ */
+
+ for (i = 0; i < rocker->port_count; i++) {
+ p = rocker->ports[i];
+ if (!rocker_port_is_bridged(p))
+ continue;
+ if (test_bit(ntohs(vlan_id), p->vlan_bitmap)) {
+ group_ids[group_count++] =
+ ROCKER_GROUP_L2_INTERFACE(vlan_id,
+ p->lport);
+ }
+ }
+
+ /* If there are no bridged ports in this VLAN, we're done */
+ if (group_count == 0)
+ return 0;
+
+ err = rocker_group_l2_flood(rocker_port, flags, vlan_id,
+ group_count, group_ids,
+ group_id);
+ if (err)
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 flood group\n", err);
+
+ return err;
+}
+
+static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port,
+ int flags, __be16 vlan_id,
+ bool pop_vlan)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_port *p;
+ bool adding = !(flags & ROCKER_OP_FLAG_REMOVE);
+ u32 out_lport;
+ int ref = 0;
+ int err;
+ int i;
+
+ /* An L2 interface group for this port in this VLAN, but
+ * only when port STP state is LEARNING|FORWARDING.
+ */
+
+ if (rocker_port->stp_state == BR_STATE_LEARNING ||
+ rocker_port->stp_state == BR_STATE_FORWARDING) {
+ out_lport = rocker_port->lport;
+ err = rocker_group_l2_interface(rocker_port, flags,
+ vlan_id, out_lport,
+ pop_vlan);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 group for lport %d\n",
+ err, out_lport);
+ return err;
+ }
+ }
+
+ /* An L2 interface group for this VLAN to CPU port.
+ * Add when first port joins this VLAN and destroy when
+ * last port leaves this VLAN.
+ */
+
+ for (i = 0; i < rocker->port_count; i++) {
+ p = rocker->ports[i];
+ if (test_bit(ntohs(vlan_id), p->vlan_bitmap))
+ ref++;
+ }
+
+ if ((!adding || ref != 1) && (adding || ref != 0))
+ return 0;
+
+ out_lport = 0;
+ err = rocker_group_l2_interface(rocker_port, flags,
+ vlan_id, out_lport,
+ pop_vlan);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 group for CPU port\n", err);
+ return err;
+ }
+
+ return 0;
+}
+
static struct rocker_ctrl {
const u8 *eth_dst;
const u8 *eth_dst_mask;
@@ -2621,6 +2774,30 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port,
return err;
}
+static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port,
+ int flags, struct rocker_ctrl *ctrl,
+ __be16 vlan_id)
+{
+ enum rocker_of_dpa_table_id goto_tbl =
+ ROCKER_OF_DPA_TABLE_ID_ACL_POLICY;
+ u32 group_id = ROCKER_GROUP_L2_FLOOD(vlan_id, 0);
+ u32 tunnel_id = 0;
+ int err;
+
+ if (!rocker_port_is_bridged(rocker_port))
+ return 0;
+
+ err = rocker_flow_tbl_bridge(rocker_port, flags,
+ ctrl->eth_dst, ctrl->eth_dst_mask,
+ vlan_id, tunnel_id,
+ goto_tbl, group_id, ctrl->copy_to_cpu);
+
+ if (err)
+ netdev_err(rocker_port->dev, "Error (%d) ctrl FLOOD\n", err);
+
+ return err;
+}
+
static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port,
int flags, struct rocker_ctrl *ctrl,
__be16 vlan_id)
@@ -2651,6 +2828,9 @@ static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, int flags,
if (ctrl->acl)
return rocker_port_ctrl_vlan_acl(rocker_port, flags,
ctrl, vlan_id);
+ if (ctrl->bridge)
+ return rocker_port_ctrl_vlan_bridge(rocker_port, flags,
+ ctrl, vlan_id);
if (ctrl->term)
return rocker_port_ctrl_vlan_term(rocker_port, flags,
@@ -2695,6 +2875,64 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, int flags,
return err;
}
+static int rocker_port_vlan(struct rocker_port *rocker_port, int flags,
+ u16 vid)
+{
+ enum rocker_of_dpa_table_id goto_tbl =
+ ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC;
+ u32 in_lport = rocker_port->lport;
+ __be16 vlan_id = htons(vid);
+ __be16 vlan_id_mask = htons(0xffff);
+ __be16 internal_vlan_id;
+ bool untagged;
+ bool adding = !(flags & ROCKER_OP_FLAG_REMOVE);
+ int err;
+
+ internal_vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, &untagged);
+
+ if (adding && test_and_set_bit(ntohs(internal_vlan_id),
+ rocker_port->vlan_bitmap))
+ return 0; /* already added */
+ else if (!adding && !test_and_clear_bit(ntohs(internal_vlan_id),
+ rocker_port->vlan_bitmap))
+ return 0; /* already removed */
+
+ if (adding) {
+ err = rocker_port_ctrl_vlan_add(rocker_port, flags,
+ internal_vlan_id);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port ctrl vlan add\n", err);
+ return err;
+ }
+ }
+
+ err = rocker_port_vlan_l2_groups(rocker_port, flags,
+ internal_vlan_id, untagged);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 groups\n", err);
+ return err;
+ }
+
+ err = rocker_port_vlan_flood_group(rocker_port, flags,
+ internal_vlan_id);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 flood group\n", err);
+ return err;
+ }
+
+ err = rocker_flow_tbl_vlan(rocker_port, flags,
+ in_lport, vlan_id, vlan_id_mask,
+ goto_tbl, untagged, internal_vlan_id);
+ if (err)
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN table\n", err);
+
+ return err;
+}
+
static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
{
enum rocker_of_dpa_table_id goto_tbl;
@@ -2720,6 +2958,158 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, int flags)
return err;
}
+struct rocker_fdb_learn_work {
+ struct work_struct work;
+ struct net_device *dev;
+ int flags;
+ u8 addr[ETH_ALEN];
+ u16 vid;
+};
+
+static void rocker_port_fdb_learn_work(struct work_struct *work)
+{
+ struct rocker_fdb_learn_work *lw =
+ container_of(work, struct rocker_fdb_learn_work, work);
+ bool removing = (lw->flags & ROCKER_OP_FLAG_REMOVE);
+ bool learned = (lw->flags & ROCKER_OP_FLAG_LEARNED);
+
+ if (learned & removing)
+ br_fdb_learn_del(lw->dev, lw->addr, lw->vid);
+ else if (learned & !removing)
+ br_fdb_learn_add(lw->dev, lw->addr, lw->vid);
+
+ kfree(work);
+}
+
+static int rocker_port_fdb_learn(struct rocker_port *rocker_port,
+ int flags, const u8 *addr, __be16 vlan_id)
+{
+ struct rocker_fdb_learn_work *lw;
+ enum rocker_of_dpa_table_id goto_tbl =
+ ROCKER_OF_DPA_TABLE_ID_ACL_POLICY;
+ u32 out_lport = rocker_port->lport;
+ u32 tunnel_id = 0;
+ u32 group_id = ROCKER_GROUP_NONE;
+ bool copy_to_cpu = false;
+ int err;
+
+ if (rocker_port_is_bridged(rocker_port))
+ group_id = ROCKER_GROUP_L2_INTERFACE(vlan_id, out_lport);
+
+ err = rocker_flow_tbl_bridge(rocker_port, flags, addr, NULL,
+ vlan_id, tunnel_id, goto_tbl,
+ group_id, copy_to_cpu);
+ if (err)
+ return err;
+
+ if (!rocker_port_is_bridged(rocker_port))
+ return 0;
+
+ lw = kmalloc(sizeof(*lw), rocker_op_flags_gfp(flags));
+ if (!lw)
+ return -ENOMEM;
+
+ INIT_WORK(&lw->work, rocker_port_fdb_learn_work);
+
+ lw->dev = rocker_port->dev;
+ lw->flags = flags;
+ ether_addr_copy(lw->addr, addr);
+ lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id);
+
+ schedule_work(&lw->work);
+
+ return 0;
+}
+
+static struct rocker_fdb_tbl_entry *
+rocker_fdb_tbl_find(struct rocker *rocker, struct rocker_fdb_tbl_entry *match)
+{
+ struct rocker_fdb_tbl_entry *found;
+
+ hash_for_each_possible(rocker->fdb_tbl, found, entry, match->key_crc32)
+ if (memcmp(&found->key, &match->key, sizeof(found->key)) == 0)
+ return found;
+
+ return NULL;
+}
+
+static int rocker_port_fdb(struct rocker_port *rocker_port,
+ const unsigned char *addr,
+ __be16 vlan_id, int flags)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_fdb_tbl_entry *fdb;
+ struct rocker_fdb_tbl_entry *found;
+ bool removing = (flags & ROCKER_OP_FLAG_REMOVE);
+ unsigned long lock_flags;
+
+ fdb = kzalloc(sizeof(*fdb), rocker_op_flags_gfp(flags));
+ if (!fdb)
+ return -ENOMEM;
+
+ fdb->learned = (flags & ROCKER_OP_FLAG_LEARNED);
+ fdb->key.lport = rocker_port->lport;
+ ether_addr_copy(fdb->key.addr, addr);
+ fdb->key.vlan_id = vlan_id;
+ fdb->key_crc32 = crc32(~0, &fdb->key, sizeof(fdb->key));
+
+ spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags);
+
+ found = rocker_fdb_tbl_find(rocker, fdb);
+
+ if (removing && found) {
+ kfree(fdb);
+ hash_del(&found->entry);
+ } else if (!removing && !found) {
+ hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32);
+ }
+
+ spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags);
+
+ /* Check if adding and already exists, or removing and can't find */
+ if (!found != !removing) {
+ kfree(fdb);
+ return 0;
+ }
+
+ return rocker_port_fdb_learn(rocker_port, flags, addr, vlan_id);
+}
+
+static int rocker_port_fdb_flush(struct rocker_port *rocker_port)
+{
+ struct rocker *rocker = rocker_port->rocker;
+ struct rocker_fdb_tbl_entry *found;
+ unsigned long lock_flags;
+ int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE;
+ struct hlist_node *tmp;
+ int bkt;
+ int err = 0;
+
+ if (rocker_port->stp_state == BR_STATE_LEARNING ||
+ rocker_port->stp_state == BR_STATE_FORWARDING)
+ return 0;
+
+ spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags);
+
+ hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) {
+ if (found->key.lport != rocker_port->lport)
+ continue;
+ if (!found->learned)
+ continue;
+ err = rocker_port_fdb_learn(rocker_port, flags,
+ found->key.addr,
+ found->key.vlan_id);
+ if (err)
+ goto err_out;
+ hash_del(&found->entry);
+ }
+
+err_out:
+ spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags);
+
+ return err;
+}
+
static int rocker_port_router_mac(struct rocker_port *rocker_port,
int flags, __be16 vlan_id)
{
@@ -2752,6 +3142,98 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port,
return err;
}
+static int rocker_port_fwding(struct rocker_port *rocker_port)
+{
+ bool pop_vlan;
+ u32 out_lport;
+ __be16 vlan_id;
+ u16 vid;
+ int flags = ROCKER_OP_FLAG_NOWAIT;
+ int err;
+
+ /* Port will be forwarding-enabled if its STP state is LEARNING
+ * or FORWARDING. Traffic from CPU can still egress, regardless of
+ * port STP state. Use L2 interface group on port VLANs as a way
+ * to toggle port forwarding: if forwarding is disabled, L2
+ * interface group will not exist.
+ */
+
+ if (rocker_port->stp_state != BR_STATE_LEARNING &&
+ rocker_port->stp_state != BR_STATE_FORWARDING)
+ flags |= ROCKER_OP_FLAG_REMOVE;
+
+ out_lport = rocker_port->lport;
+ for (vid = 1; vid < VLAN_N_VID; vid++) {
+ if (!test_bit(vid, rocker_port->vlan_bitmap))
+ continue;
+ vlan_id = htons(vid);
+ pop_vlan = rocker_vlan_id_is_internal(vlan_id);
+ err = rocker_group_l2_interface(rocker_port, flags,
+ vlan_id, out_lport,
+ pop_vlan);
+ if (err) {
+ netdev_err(rocker_port->dev,
+ "Error (%d) port VLAN l2 group for lport %d\n",
+ err, out_lport);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int rocker_port_stp_update(struct net_device *dev, u8 state)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ bool want[ROCKER_CTRL_MAX] = { 0, };
+ int flags;
+ int err;
+ int i;
+
+ if (rocker_port->stp_state == state)
+ return 0;
+
+ rocker_port->stp_state = state;
+
+ switch (state) {
+ case BR_STATE_DISABLED:
+ /* port is completely disabled */
+ break;
+ case BR_STATE_LISTENING:
+ case BR_STATE_BLOCKING:
+ want[ROCKER_CTRL_LINK_LOCAL_MCAST] = true;
+ break;
+ case BR_STATE_LEARNING:
+ case BR_STATE_FORWARDING:
+ want[ROCKER_CTRL_LINK_LOCAL_MCAST] = true;
+ want[ROCKER_CTRL_IPV4_MCAST] = true;
+ want[ROCKER_CTRL_IPV6_MCAST] = true;
+ if (rocker_port_is_bridged(rocker_port))
+ want[ROCKER_CTRL_DFLT_BRIDGING] = true;
+ else
+ want[ROCKER_CTRL_LOCAL_ARP] = true;
+ break;
+ }
+
+ for (i = 0; i < ROCKER_CTRL_MAX; i++) {
+ if (want[i] != rocker_port->ctrls[i]) {
+ flags = ROCKER_OP_FLAG_NOWAIT |
+ (want[i] ? 0 : ROCKER_OP_FLAG_REMOVE);
+ err = rocker_port_ctrl(rocker_port, flags,
+ &rocker_ctrls[i]);
+ if (err)
+ return err;
+ rocker_port->ctrls[i] = want[i];
+ }
+ }
+
+ err = rocker_port_fdb_flush(rocker_port);
+ if (err)
+ return err;
+
+ return rocker_port_fwding(rocker_port);
+}
+
static struct rocker_internal_vlan_tbl_entry *
rocker_internal_vlan_tbl_find(struct rocker *rocker, int ifindex)
{
@@ -2843,6 +3325,8 @@ not_found:
static int rocker_port_open(struct net_device *dev)
{
struct rocker_port *rocker_port = netdev_priv(dev);
+ u8 stp_state = rocker_port_is_bridged(rocker_port) ?
+ BR_STATE_BLOCKING : BR_STATE_FORWARDING;
int err;
err = rocker_port_dma_rings_init(rocker_port);
@@ -2865,12 +3349,18 @@ static int rocker_port_open(struct net_device *dev)
goto err_request_rx_irq;
}
+ err = rocker_port_stp_update(dev, stp_state);
+ if (err)
+ goto err_stp_update;
+
napi_enable(&rocker_port->napi_tx);
napi_enable(&rocker_port->napi_rx);
rocker_port_set_enable(rocker_port, true);
netif_start_queue(dev);
return 0;
+err_stp_update:
+ free_irq(rocker_msix_rx_vector(rocker_port), rocker_port);
err_request_rx_irq:
free_irq(rocker_msix_tx_vector(rocker_port), rocker_port);
err_request_tx_irq:
@@ -2886,6 +3376,7 @@ static int rocker_port_stop(struct net_device *dev)
rocker_port_set_enable(rocker_port, false);
napi_disable(&rocker_port->napi_rx);
napi_disable(&rocker_port->napi_tx);
+ rocker_port_stp_update(dev, BR_STATE_DISABLED);
free_irq(rocker_msix_rx_vector(rocker_port), rocker_port);
free_irq(rocker_msix_tx_vector(rocker_port), rocker_port);
rocker_port_dma_rings_fini(rocker_port);
@@ -3030,6 +3521,33 @@ static int rocker_port_set_mac_address(struct net_device *dev, void *p)
return 0;
}
+static int rocker_port_vlan_rx_add_vid(struct net_device *dev,
+ __be16 proto, u16 vid)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ int err;
+
+ err = rocker_port_vlan(rocker_port, 0, vid);
+ if (err)
+ return err;
+
+ return rocker_port_router_mac(rocker_port, 0, htons(vid));
+}
+
+static int rocker_port_vlan_rx_kill_vid(struct net_device *dev,
+ __be16 proto, u16 vid)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ int err;
+
+ err = rocker_port_router_mac(rocker_port, ROCKER_OP_FLAG_REMOVE,
+ htons(vid));
+ if (err)
+ return err;
+
+ return rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, vid);
+}
+
static int rocker_port_sw_parent_id_get(struct net_device *dev,
struct netdev_phys_item_id *psid)
{
@@ -3041,13 +3559,49 @@ static int rocker_port_sw_parent_id_get(struct net_device *dev,
return 0;
}
+static int rocker_port_sw_port_fdb_add(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, NULL);
+ int flags = 0;
+
+ if (!rocker_port_is_bridged(rocker_port))
+ return -EINVAL;
+
+ return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+}
+
+static int rocker_port_sw_port_fdb_del(struct net_device *dev,
+ const unsigned char *addr, u16 vid)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, vid, NULL);
+ int flags = ROCKER_OP_FLAG_REMOVE;
+
+ if (!rocker_port_is_bridged(rocker_port))
+ return -EINVAL;
+
+ return rocker_port_fdb(rocker_port, addr, vlan_id, flags);
+}
+
+static int rocker_port_sw_port_stp_update(struct net_device *dev, u8 state)
+{
+ return rocker_port_stp_update(dev, state);
+}
+
static const struct net_device_ops rocker_port_netdev_ops = {
.ndo_open = rocker_port_open,
.ndo_stop = rocker_port_stop,
.ndo_start_xmit = rocker_port_xmit,
.ndo_set_mac_address = rocker_port_set_mac_address,
+ .ndo_vlan_rx_add_vid = rocker_port_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = rocker_port_vlan_rx_kill_vid,
#ifdef CONFIG_NET_SWITCHDEV
.ndo_sw_parent_id_get = rocker_port_sw_parent_id_get,
+ .ndo_sw_port_fdb_add = rocker_port_sw_port_fdb_add,
+ .ndo_sw_port_fdb_del = rocker_port_sw_port_fdb_del,
+ .ndo_sw_port_stp_update = rocker_port_sw_port_stp_update,
#endif
};
@@ -3498,17 +4052,121 @@ static struct pci_driver rocker_pci_driver = {
.remove = rocker_remove,
};
+/************************************
+ * Net device notifier event handler
+ ************************************/
+
+static bool rocker_port_dev_check(struct net_device *dev)
+{
+ return dev->netdev_ops == &rocker_port_netdev_ops;
+}
+
+static int rocker_port_bridge_join(struct rocker_port *rocker_port,
+ struct net_device *bridge)
+{
+ int err;
+
+ rocker_port_internal_vlan_id_put(rocker_port,
+ rocker_port->dev->ifindex);
+
+ rocker_port->bridge_dev = bridge;
+
+ /* Use bridge internal VLAN ID for untagged pkts */
+ err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0);
+ if (err)
+ return err;
+ rocker_port->internal_vlan_id =
+ rocker_port_internal_vlan_id_get(rocker_port,
+ bridge->ifindex);
+ err = rocker_port_vlan(rocker_port, 0, 0);
+
+ return err;
+}
+
+static int rocker_port_bridge_leave(struct rocker_port *rocker_port)
+{
+ int err;
+
+ rocker_port_internal_vlan_id_put(rocker_port,
+ rocker_port->bridge_dev->ifindex);
+
+ rocker_port->bridge_dev = NULL;
+
+ /* Use port internal VLAN ID for untagged pkts */
+ err = rocker_port_vlan(rocker_port, ROCKER_OP_FLAG_REMOVE, 0);
+ if (err)
+ return err;
+ rocker_port->internal_vlan_id =
+ rocker_port_internal_vlan_id_get(rocker_port,
+ rocker_port->dev->ifindex);
+ err = rocker_port_vlan(rocker_port, 0, 0);
+
+ return err;
+}
+
+static int rocker_port_master_changed(struct net_device *dev)
+{
+ struct rocker_port *rocker_port = netdev_priv(dev);
+ struct net_device *master = netdev_master_upper_dev_get(dev);
+ int err = 0;
+
+ if (master && master->rtnl_link_ops &&
+ !strcmp(master->rtnl_link_ops->kind, "bridge"))
+ err = rocker_port_bridge_join(rocker_port, master);
+ else
+ err = rocker_port_bridge_leave(rocker_port);
+
+ return err;
+}
+
+static int rocker_netdevice_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev;
+ int err;
+
+ switch (event) {
+ case NETDEV_CHANGEUPPER:
+ dev = netdev_notifier_info_to_dev(ptr);
+ if (!rocker_port_dev_check(dev))
+ return NOTIFY_DONE;
+ err = rocker_port_master_changed(dev);
+ if (err)
+ netdev_warn(dev,
+ "failed to reflect master change (err %d)\n",
+ err);
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block rocker_netdevice_nb __read_mostly = {
+ .notifier_call = rocker_netdevice_event,
+};
+
/***********************
* Module init and exit
***********************/
static int __init rocker_module_init(void)
{
- return pci_register_driver(&rocker_pci_driver);
+ int err;
+
+ register_netdevice_notifier(&rocker_netdevice_nb);
+ err = pci_register_driver(&rocker_pci_driver);
+ if (err)
+ goto err_pci_register_driver;
+ return 0;
+
+err_pci_register_driver:
+ unregister_netdevice_notifier(&rocker_netdevice_nb);
+ return err;
}
static void __exit rocker_module_exit(void)
{
+ unregister_netdevice_notifier(&rocker_netdevice_nb);
pci_unregister_driver(&rocker_pci_driver);
}
--
1.9.3
^ permalink raw reply related
* [PATCH net-next] net/fm10k: Avoid double setting of NETIF_F_SG for the HW encapsulation feature mask
From: Or Gerlitz @ 2014-11-06 9:21 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: netdev, Or Gerlitz
The networking core does it for the driver during registration time.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 5 ++---
1 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 8811364..2b17cd8 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -1414,13 +1414,12 @@ struct net_device *fm10k_alloc_netdev(void)
dev->vlan_features |= dev->features;
/* configure tunnel offloads */
- dev->hw_enc_features = NETIF_F_IP_CSUM |
+ dev->hw_enc_features |= NETIF_F_IP_CSUM |
NETIF_F_TSO |
NETIF_F_TSO6 |
NETIF_F_TSO_ECN |
NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_IPV6_CSUM |
- NETIF_F_SG;
+ NETIF_F_IPV6_CSUM;
/* we want to leave these both on as we cannot disable VLAN tag
* insertion or stripping on the hardware since it is contained
--
1.7.1
^ permalink raw reply related
* [patch net-next 02/10] net: introduce generic switch devices support
From: Jiri Pirko @ 2014-11-06 9:20 UTC (permalink / raw)
To: netdev
Cc: davem, nhorman, andy, tgraf, dborkman, ogerlitz, jesse, pshelar,
azhou, ben, stephen, jeffrey.t.kirsher, vyasevic, xiyou.wangcong,
john.r.fastabend, edumazet, jhs, sfeldma, f.fainelli, roopa,
linville, jasowang, ebiederm, nicolas.dichtel, ryazanov.s.a,
buytenh, aviadr, nbd, alexei.starovoitov, Neil.Jerram, ronye,
simon.horman, alexander.h.duyck, john.ronciak, mleitner, shrijeet,
gospo, bcrl
In-Reply-To: <1415265610-9338-1-git-send-email-jiri@resnulli.us>
The goal of this is to provide a possibility to support various switch
chips. Drivers should implement relevant ndos to do so. Now there is
only one ndo defined:
- for getting physical switch id is in place.
Note that user can use random port netdevice to access the switch.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
Documentation/networking/switchdev.txt | 59 ++++++++++++++++++++++++++++++++++
MAINTAINERS | 7 ++++
include/linux/netdevice.h | 10 ++++++
include/net/switchdev.h | 30 +++++++++++++++++
net/Kconfig | 1 +
net/Makefile | 3 ++
net/switchdev/Kconfig | 13 ++++++++
net/switchdev/Makefile | 5 +++
net/switchdev/switchdev.c | 33 +++++++++++++++++++
9 files changed, 161 insertions(+)
create mode 100644 Documentation/networking/switchdev.txt
create mode 100644 include/net/switchdev.h
create mode 100644 net/switchdev/Kconfig
create mode 100644 net/switchdev/Makefile
create mode 100644 net/switchdev/switchdev.c
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt
new file mode 100644
index 0000000..98be76c
--- /dev/null
+++ b/Documentation/networking/switchdev.txt
@@ -0,0 +1,59 @@
+Switch (and switch-ish) device drivers HOWTO
+===========================
+
+Please note that the word "switch" is here used in very generic meaning.
+This include devices supporting L2/L3 but also various flow offloading chips,
+including switches embedded into SR-IOV NICs.
+
+Lets describe a topology a bit. Imagine the following example:
+
+ +----------------------------+ +---------------+
+ | SOME switch chip | | CPU |
+ +----------------------------+ +---------------+
+ port1 port2 port3 port4 MNGMNT | PCI-E |
+ | | | | | +---------------+
+ PHY PHY | | | | NIC0 NIC1
+ | | | | | |
+ | | +- PCI-E -+ | |
+ | +------- MII -------+ |
+ +------------- MII ------------+
+
+In this example, there are two independent lines between the switch silicon
+and CPU. NIC0 and NIC1 drivers are not aware of a switch presence. They are
+separate from the switch driver. SOME switch chip is by managed by a driver
+via PCI-E device MNGMNT. Note that MNGMNT device, NIC0 and NIC1 may be
+connected to some other type of bus.
+
+Now, for the previous example show the representation in kernel:
+
+ +----------------------------+ +---------------+
+ | SOME switch chip | | CPU |
+ +----------------------------+ +---------------+
+ sw0p0 sw0p1 sw0p2 sw0p3 MNGMNT | PCI-E |
+ | | | | | +---------------+
+ PHY PHY | | | | eth0 eth1
+ | | | | | |
+ | | +- PCI-E -+ | |
+ | +------- MII -------+ |
+ +------------- MII ------------+
+
+Lets call the example switch driver for SOME switch chip "SOMEswitch". This
+driver takes care of PCI-E device MNGMNT. There is a netdevice instance sw0pX
+created for each port of a switch. These netdevices are instances
+of "SOMEswitch" driver. sw0pX netdevices serve as a "representation"
+of the switch chip. eth0 and eth1 are instances of some other existing driver.
+
+The only difference of the switch-port netdevice from the ordinary netdevice
+is that is implements couple more NDOs:
+
+ ndo_sw_parent_get_id - This returns the same ID for two port netdevices
+ of the same physical switch chip. This is
+ mandatory to be implemented by all switch drivers
+ and serves the caller for recognition of a port
+ netdevice.
+ ndo_sw_parent_* - Functions that serve for a manipulation of the switch
+ chip itself (it can be though of as a "parent" of the
+ port, therefore the name). They are not port-specific.
+ Caller might use arbitrary port netdevice of the same
+ switch and it will make no difference.
+ ndo_sw_port_* - Functions that serve for a port-specific manipulation.
diff --git a/MAINTAINERS b/MAINTAINERS
index 3a41fb0..776e078 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9003,6 +9003,13 @@ F: lib/swiotlb.c
F: arch/*/kernel/pci-swiotlb.c
F: include/linux/swiotlb.h
+SWITCHDEV
+M: Jiri Pirko <jiri@resnulli.us>
+L: netdev@vger.kernel.org
+S: Supported
+F: net/switchdev/
+F: include/net/switchdev.h
+
SYNOPSYS ARC ARCHITECTURE
M: Vineet Gupta <vgupta@synopsys.com>
S: Supported
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bbc730f..54b08a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1017,6 +1017,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* performing GSO on a packet. The device returns true if it is
* able to GSO the packet, false otherwise. If the return value is
* false the stack will do software GSO.
+ *
+ * int (*ndo_sw_parent_id_get)(struct net_device *dev,
+ * struct netdev_phys_item_id *psid);
+ * Called to get an ID of the switch chip this port is part of.
+ * If driver implements this, it indicates that it represents a port
+ * of a switch chip.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1168,6 +1174,10 @@ struct net_device_ops {
int (*ndo_get_lock_subclass)(struct net_device *dev);
bool (*ndo_gso_check) (struct sk_buff *skb,
struct net_device *dev);
+#ifdef CONFIG_NET_SWITCHDEV
+ int (*ndo_sw_parent_id_get)(struct net_device *dev,
+ struct netdev_phys_item_id *psid);
+#endif
};
/**
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
new file mode 100644
index 0000000..79bf9bd
--- /dev/null
+++ b/include/net/switchdev.h
@@ -0,0 +1,30 @@
+/*
+ * include/net/switchdev.h - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef _LINUX_SWITCHDEV_H_
+#define _LINUX_SWITCHDEV_H_
+
+#include <linux/netdevice.h>
+
+#ifdef CONFIG_NET_SWITCHDEV
+
+int netdev_sw_parent_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *psid);
+
+#else
+
+static inline int netdev_sw_parent_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *psid)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif
+
+#endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 99815b5..ff9ffc1 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -228,6 +228,7 @@ source "net/vmw_vsock/Kconfig"
source "net/netlink/Kconfig"
source "net/mpls/Kconfig"
source "net/hsr/Kconfig"
+source "net/switchdev/Kconfig"
config RPS
boolean
diff --git a/net/Makefile b/net/Makefile
index 7ed1970..95fc694 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -73,3 +73,6 @@ obj-$(CONFIG_OPENVSWITCH) += openvswitch/
obj-$(CONFIG_VSOCKETS) += vmw_vsock/
obj-$(CONFIG_NET_MPLS_GSO) += mpls/
obj-$(CONFIG_HSR) += hsr/
+ifneq ($(CONFIG_NET_SWITCHDEV),)
+obj-y += switchdev/
+endif
diff --git a/net/switchdev/Kconfig b/net/switchdev/Kconfig
new file mode 100644
index 0000000..1557545
--- /dev/null
+++ b/net/switchdev/Kconfig
@@ -0,0 +1,13 @@
+#
+# Configuration for Switch device support
+#
+
+config NET_SWITCHDEV
+ boolean "Switch (and switch-ish) device support (EXPERIMENTAL)"
+ depends on INET
+ ---help---
+ This module provides glue between core networking code and device
+ drivers in order to support hardware switch chips in very generic
+ meaning of the word "switch". This include devices supporting L2/L3 but
+ also various flow offloading chips, including switches embedded into
+ SR-IOV NICs.
diff --git a/net/switchdev/Makefile b/net/switchdev/Makefile
new file mode 100644
index 0000000..5ed63ed
--- /dev/null
+++ b/net/switchdev/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Switch device API
+#
+
+obj-$(CONFIG_NET_SWITCHDEV) += switchdev.o
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
new file mode 100644
index 0000000..5010f646
--- /dev/null
+++ b/net/switchdev/switchdev.c
@@ -0,0 +1,33 @@
+/*
+ * net/switchdev/switchdev.c - Switch device API
+ * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <net/switchdev.h>
+
+/**
+ * netdev_sw_parent_id_get - Get ID of a switch
+ * @dev: port device
+ * @psid: switch ID
+ *
+ * Get ID of a switch this port is part of.
+ */
+int netdev_sw_parent_id_get(struct net_device *dev,
+ struct netdev_phys_item_id *psid)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (!ops->ndo_sw_parent_id_get)
+ return -EOPNOTSUPP;
+ return ops->ndo_sw_parent_id_get(dev, psid);
+}
+EXPORT_SYMBOL(netdev_sw_parent_id_get);
--
1.9.3
^ permalink raw reply related
* Re: [PATCH net-next 1/2] ethtool: Support for configurable RSS hash function
From: Eyal perry @ 2014-11-06 9:41 UTC (permalink / raw)
To: Ben Hutchings, Amir Vadai
Cc: David S. Miller, netdev, Or Gerlitz, Eyal Perry, Yevgeny Petrilin
In-Reply-To: <1415224298.3398.27.camel@decadent.org.uk>
On 11/5/2014 11:51 PM, Ben Hutchings wrote:
> On Wed, 2014-11-05 at 13:59 +0200, Amir Vadai wrote:
>> From: Eyal Perry <eyalpe@mellanox.com>
>>
>> This patch adds an RSS hash functions string-set, and two
>> ethtool-options for set/get current RSS hash function. User-kernel API is done
>> through the new hfunc mask field in the ethtool_rxfh struct. A bit set
>> in the hfunc is corresponding to an index in the string-set.
>>
>> Signed-off-by: Eyal Perry <eyalpe@mellanox.com>
>> Signed-off-by: Amir Vadai <amirv@mellanox.com>
>> ---
>> include/linux/ethtool.h | 28 ++++++++++++++++++++++++
>> include/uapi/linux/ethtool.h | 6 ++++-
>> net/core/ethtool.c | 52 ++++++++++++++++++++++++++++++--------------
>> 3 files changed, 69 insertions(+), 17 deletions(-)
>>
>> diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
>> index c1a2d60..61003b1 100644
>> --- a/include/linux/ethtool.h
>> +++ b/include/linux/ethtool.h
>> @@ -59,6 +59,29 @@ enum ethtool_phys_id_state {
>> ETHTOOL_ID_OFF
>> };
>>
>> +enum {
>> + RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */
>> + RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */
>> +
>> + /*
>> + * Add your fresh new hash function bits above and remember to update
>> + * rss_hash_func_strings[] below
>> + */
>> + RSS_HASH_FUNCS_COUNT
>> +};
>> +
>> +#define __RSS_HASH_BIT(bit) ((u32)1 << (bit))
>> +#define __RSS_HASH(name) __RSS_HASH_BIT(RSS_HASH_##name##_BIT)
>> +
>> +#define RSS_HASH_TOP __RSS_HASH(TOP)
>> +#define RSS_HASH_XOR __RSS_HASH(XOR)
>
> I think #define RSS_HASH_UNKNOWN 0 might also be useful.
>
> And I think all of these names should get an ETH_ prefix.
>
I'll add it in V1.
>> +static const char
>> +rss_hash_func_strings[RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = {
>> + [RSS_HASH_TOP_BIT] = "toeplitz",
>> + [RSS_HASH_XOR_BIT] = "xor",
>> +};
>
> This belongs in net/core/ethtool.c.
>
I agree, will be fixed in V1.
>> struct net_device;
>>
>> /* Some generic methods drivers may use in their ethtool_ops */
>> @@ -158,6 +181,9 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
>> * Returns zero if not supported for this specific device.
>> * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
>> * Returns zero if not supported for this specific device.
>> + * @get_rxfh_func: Get the hardware RX flow hash function.
>> + * @set_rxfh_func: Set the hardware RX flow hash function. Returns a negative
>> + * error code or zero.
>> * @get_rxfh: Get the contents of the RX flow hash indirection table and hash
>> * key.
>> * Will only be called if one or both of @get_rxfh_indir_size and
>> @@ -241,6 +267,8 @@ struct ethtool_ops {
>> int (*reset)(struct net_device *, u32 *);
>> u32 (*get_rxfh_key_size)(struct net_device *);
>> u32 (*get_rxfh_indir_size)(struct net_device *);
>> + u32 (*get_rxfh_func)(struct net_device *);
>> + int (*set_rxfh_func)(struct net_device *, u32);
>
> Why not another parameter to get_rxfh/set_rxfh? I know it's a pain to
> update all the implementations, but changing algorithm potentially
> changes the supported indirection table and key lengths. They have to
> be validated together.
>
OK, I'll do it for V1.
>> int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key);
>> int (*set_rxfh)(struct net_device *, const u32 *indir,
>> const u8 *key);
>> diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
>> index eb2095b..eb91da4 100644
>> --- a/include/uapi/linux/ethtool.h
>> +++ b/include/uapi/linux/ethtool.h
>> @@ -534,6 +534,7 @@ struct ethtool_pauseparam {
>> * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE;
>> * now deprecated
>> * @ETH_SS_FEATURES: Device feature names
>> + * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
>> */
>> enum ethtool_stringset {
>> ETH_SS_TEST = 0,
>> @@ -541,6 +542,7 @@ enum ethtool_stringset {
>> ETH_SS_PRIV_FLAGS,
>> ETH_SS_NTUPLE_FILTERS,
>> ETH_SS_FEATURES,
>> + ETH_SS_RSS_HASH_FUNCS,
>> };
>>
>> /**
>> @@ -900,7 +902,9 @@ struct ethtool_rxfh {
>> __u32 rss_context;
>> __u32 indir_size;
>> __u32 key_size;
>> - __u32 rsvd[2];
>> + __u8 hfunc;
>
> Missing kernel-doc. This needs to be very clear about what the valid
> values are.
>
I'll add it in V1.
>> + __u8 rsvd8[3];
>> + __u32 rsvd32;
>> __u32 rss_config[0];
>> };
>> #define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff
>> diff --git a/net/core/ethtool.c b/net/core/ethtool.c
>> index 06dfb29..4791c17 100644
>> --- a/net/core/ethtool.c
>> +++ b/net/core/ethtool.c
>> @@ -185,6 +185,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset)
>> if (sset == ETH_SS_FEATURES)
>> return ARRAY_SIZE(netdev_features_strings);
>>
>> + if (sset == ETH_SS_RSS_HASH_FUNCS)
>> + return ARRAY_SIZE(rss_hash_func_strings);
>> +
>> if (ops->get_sset_count && ops->get_strings)
>> return ops->get_sset_count(dev, sset);
>> else
> [...]
>> @@ -760,32 +769,43 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
>> const struct ethtool_ops *ops = dev->ethtool_ops;
>> struct ethtool_rxnfc rx_rings;
>> struct ethtool_rxfh rxfh;
>> - u32 dev_indir_size = 0, dev_key_size = 0, i;
>> + u32 dev_indir_size = 0, dev_key_size = 0, dev_hfunc = 0, i;
>> u32 *indir = NULL, indir_bytes = 0;
>> u8 *hkey = NULL;
>> u8 *rss_config;
>> u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
>>
>> - if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
>> - !ops->get_rxnfc || !ops->set_rxfh)
>> + if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size ||
>> + ops->get_rxfh_func) || !ops->get_rxnfc || !ops->set_rxfh)
>> return -EOPNOTSUPP;
>>
>> + if (ops->get_rxfh_func)
>> + dev_hfunc = ops->get_rxfh_func(dev);
>> if (ops->get_rxfh_indir_size)
>> dev_indir_size = ops->get_rxfh_indir_size(dev);
>> if (ops->get_rxfh_key_size)
>> dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
>> - if ((dev_key_size + dev_indir_size) == 0)
>> + if ((dev_key_size + dev_indir_size + dev_hfunc) == 0)
>> return -EOPNOTSUPP;
>>
>> if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
>> return -EFAULT;
>>
>> /* Check that reserved fields are 0 for now */
>> - if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
>> + if (rxfh.rss_context || rxfh.rsvd8[0] || rxfh.rsvd8[1] ||
>> + rxfh.rsvd8[2] || rxfh.rsvd32)
>> return -EINVAL;
>>
>> + if (rxfh.hfunc != dev_hfunc) {
>> + if (!ops->set_rxfh_func)
>> + return -EOPNOTSUPP;
>> + ret = ops->set_rxfh_func(dev, rxfh.hfunc);
>> + if (ret)
>> + return ret;
>> + }
>> +
>> /* If either indir or hash key is valid, proceed further.
>> - * It is not valid to request that both be unchanged.
>> + * Must request at least one change: indir size, hash key or function.
>> */
>> if ((rxfh.indir_size &&
>> rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
>> @@ -793,7 +813,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
>> (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
>> (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
>> rxfh.key_size == 0))
>> - return -EINVAL;
>> + return rxfh.hfunc ? 0 : -EINVAL;
>
> Shouldn't the condition be rxfh.hfunc != dev_hfunc ?
>
> Ben.
>
On current implementation it's not necessary since we have already
checked that above. However, according to your suggestion, after I'll
remove the set/get_rxfh_func() callbacks I wouldn't be able to check
that condition at this point of the code.
Best Regards,
Eyal.
^ permalink raw reply
* RE: [PATCH 1/4] inet: Add skb_copy_datagram_iter
From: Jon Maloy @ 2014-11-06 9:50 UTC (permalink / raw)
To: Al Viro, David Miller
Cc: herbert@gondor.apana.org.au, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, bcrl@kvack.org
In-Reply-To: <20141106032533.GU7996@ZenIV.linux.org.uk>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of Al Viro
> Sent: November-06-14 4:26 AM
> To: David Miller
> Cc: herbert@gondor.apana.org.au; netdev@vger.kernel.org; linux-
> kernel@vger.kernel.org; bcrl@kvack.org
> Subject: Re: [PATCH 1/4] inet: Add skb_copy_datagram_iter
>
> On Wed, Nov 05, 2014 at 04:57:19PM -0500, David Miller wrote:
> > From: Al Viro <viro@ZenIV.linux.org.uk>
> > Date: Wed, 5 Nov 2014 21:07:45 +0000
> >
> > > Ping me when you put it there, OK? I'll rebase the rest of old
> > > stuff on top of it (similar helpers, mostly).
> >
> > I just pushed it into net-next, thanks Al.
>
> OK, I've taken the beginning of the old queue on top of net-next; it's in
> git://git.kernel.org//pub/scm/linux/kernel/git/viro/vfs.git iov_iter-net.
>
> From the quick look at the remaining ->msg_iov users:
>
> * I'll need to add several iov_iter primitives - counterparts of
> checksum.h stuff (copy_and_csum_{from,to}_iter(), maybe some more).
> Not a big deal, I'll do that tomorrow. That will give us a clean iov_iter-based
> counterpart of skb_copy_and_csum_datagram_iovec().
>
> * a new helper: zerocopy_sg_from_iter(). I have it, actually, but I'd
> rather not step on Herbert's toes - it's too close to the areas his series will
> touch, so that's probably for when his series goes in.
> It will be needed for complete macvtap conversion...
>
> * why doesn't verify_iovec() use rw_copy_check_uvector()? The
> only real differences I see is that (a) you do allocation in callers (same as
> rw_copy_check_uvector() would've done), (b) you return EMSGSIZE in case
> of too long vector, while rw_copy_check_uvector() returns EINVAL in that
> case and (c) you don't do access_ok(). The last one is described as
> optimization, but for iov_iter primitives it's a serious PITA - for iovec-backed
> instances they are using __copy_from_user()/__copy_to_user(), etc.
> It certainly would be nice to have the same code doing all copying of
> iovecs from userland - readv/writev/aio/sendmsg/recvmsg/etc. Am I
> missing something subtle semantical difference in there? EMSGSIZE vs
> EINVAL is trivial (we can lift that check into the callers, if nothing else), but I
> could miss something more interesting...
>
> * various getfrag will need to grow iov_iter-based counterparts, but
> ip_append_output() needs no changes, AFAICS.
>
> * crypto stuff will be easy to convert - iov_iter_get_pages() would
> suffice for a primitive
>
> * there's some really weird stuff in there. Just what is this static int
> raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg) {
> struct iovec *iov;
> u8 __user *type = NULL;
> u8 __user *code = NULL;
> int probed = 0;
> unsigned int i;
>
> if (!msg->msg_iov)
> return 0;
>
> for (i = 0; i < msg->msg_iovlen; i++) {
> iov = &msg->msg_iov[i];
> if (!iov)
> continue;
> trying to do? "If non-NULL pointer + i somehow happened to be NULL, skip it
> and try to use the same pointer + i + 1"? Huh? Had been that way since the
> function first went in back in 2004 ("[IPV4] XFRM: probe icmp type/code
> when sending packets via raw socket.", according to historical tree)...
>
> * rds, bluetooth and vsock are doing something odd; need to RTFS
> some more.
>
> * not sure I understand what TIPC is doing - does it prohibit too short
> first segment of ->msg_iov?
Yes, that is the purpose. It was needed in early versions of TIPC, which was
using TIPC itself, instead of netlink, as carrier of configuration commands.
This option is long gone, and we can safely remove those checks. I'll
post a patch.
///jon
net/tipc/socket.c:dest_name_check() looks
> odd _and_ potentially racy - we read the same data twice and hope our
> checks still apply. I asked TIPC folks about that race back in April, but it looks
> like that fell through the cracks...
>
> Overall, so far it looks more or less feasible - other than the missing csum
> primitives, current mm/iov_iter.c should suffice. I have _not_ seriously
> looked into sendpage yet; that might very well require some more.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in the body
> of a message to majordomo@vger.kernel.org More majordomo info at
> http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net 1/2] enic: handle error condition properly in enic_rq_indicate_buf
From: Govindarajulu Varadarajan @ 2014-11-06 9:51 UTC (permalink / raw)
To: ssujith, netdev, davem; +Cc: Govindarajulu Varadarajan
In case of error in rx path, we free the buf->os_buf but we do not make it NULL.
In next iteration we use the skb which is already freed. This causes the
following crash.
[ 886.154772] general protection fault: 0000 [#1] PREEMPT SMP
[ 886.154851] Modules linked in: rpcsec_gss_krb5 auth_rpcgss oid_registry nfsv4 microcode evdev cirrus ttm drm_kms_helper drm enic syscopyarea sysfillrect sysimgblt psmouse i2c_piix4 serio_raw pcspkr i2c_core nfs lockd grace sunrpc fscache ext4 crc16 mbcache jbd2 sd_mod crc_t10dif crct10dif_common ata_generic ata_piix virtio_balloon libata scsi_mod uhci_hcd usbcore virtio_pci virtio_ring virtio usb_common
[ 886.155199] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 3.17.0-netnext-05668-g876bc7f #272
[ 886.155263] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 886.155304] task: ffffffff81a1d580 ti: ffffffff81a00000 task.ti: ffffffff81a00000
[ 886.155356] RIP: 0010:[<ffffffff81384030>] [<ffffffff81384030>] kfree_skb_list+0x10/0x30
[ 886.155418] RSP: 0018:ffff880210603d48 EFLAGS: 00010206
[ 886.155456] RAX: 0000000000000020 RBX: 0000000000000000 RCX: 0000000000000000
[ 886.155504] RDX: 0000000000000000 RSI: 0000000000000001 RDI: 004500084e000017
[ 886.155553] RBP: ffff880210603d50 R08: 00000000fe13d1b6 R09: 0000000000000001
[ 886.155601] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880209ff2f00
[ 886.155650] R13: ffff88020ac0fe40 R14: ffff880209ff2f00 R15: ffff8800da8e3a80
[ 886.155699] FS: 0000000000000000(0000) GS:ffff880210600000(0000) knlGS:0000000000000000
[ 886.155774] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 886.155814] CR2: 00007f0e0c925000 CR3: 0000000035e8b000 CR4: 00000000000006f0
[ 886.155865] Stack:
[ 886.155882] 0000000000000000 ffff880210603d78 ffffffff81383f79 ffff880209ff2f00
[ 886.155942] ffff88020b0c0b40 000000000000c000 ffff880210603d90 ffffffff81383faf
[ 886.156001] ffff880209ff2f00 ffff880210603da8 ffffffff8138406d ffff88020b1b08c0
[ 886.156061] Call Trace:
[ 886.156080] <IRQ>
[ 886.156095]
[ 886.156112] [<ffffffff81383f79>] skb_release_data+0xa9/0xc0
[ 886.157656] [<ffffffff81383faf>] skb_release_all+0x1f/0x30
[ 886.159195] [<ffffffff8138406d>] consume_skb+0x1d/0x40
[ 886.160719] [<ffffffff813942e5>] __dev_kfree_skb_any+0x35/0x40
[ 886.162224] [<ffffffffa02dc1d5>] enic_rq_service.constprop.47+0xe5/0x5a0 [enic]
[ 886.163756] [<ffffffffa02dc829>] enic_poll_msix_rq+0x199/0x370 [enic]
[ 886.164730] [<ffffffff81397e29>] net_rx_action+0x139/0x210
[ 886.164730] [<ffffffff8105fb2e>] __do_softirq+0x14e/0x280
[ 886.164730] [<ffffffff8105ff2e>] irq_exit+0x8e/0xb0
[ 886.164730] [<ffffffff8100fc1d>] do_IRQ+0x5d/0x100
[ 886.164730] [<ffffffff81496832>] common_interrupt+0x72/0x72
fixes: a03bb56e67c357980dae886683733dab5583dc14 ("enic: implement rx_copybreak")
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
---
drivers/net/ethernet/cisco/enic/enic_main.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 180e53f..cd254d1 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1037,7 +1037,10 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
enic->rq_truncated_pkts++;
}
+ pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
+ PCI_DMA_FROMDEVICE);
dev_kfree_skb_any(skb);
+ buf->os_buf = NULL;
return;
}
@@ -1088,7 +1091,10 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
/* Buffer overflow
*/
+ pci_unmap_single(enic->pdev, buf->dma_addr, buf->len,
+ PCI_DMA_FROMDEVICE);
dev_kfree_skb_any(skb);
+ buf->os_buf = NULL;
}
}
--
2.1.0
^ permalink raw reply related
* [PATCH net 2/2] enic: update desc properly in rx_copybreak
From: Govindarajulu Varadarajan @ 2014-11-06 9:51 UTC (permalink / raw)
To: ssujith, netdev, davem; +Cc: Govindarajulu Varadarajan
In-Reply-To: <1415267499-25955-1-git-send-email-_govind@gmx.com>
When we reuse the rx buffer, we need to update the desc. If not hardware sees
stale value.
In the following crash, when mtu is changed, hardware sees old rx buffer value
and crashes on skb_put.
Fix this by using enic_queue_rq_desc helper function which updates the necessary
desc.
[ 64.657376] skbuff: skb_over_panic: text:ffffffffa041f55d len:9010 put:9010 head:ffff8800d3ca9fc0 data:ffff8800d3caa000 tail:0x2372 end:0x640 dev:enp0s3
[ 64.659965] ------------[ cut here ]------------
[ 64.661322] kernel BUG at net/core/skbuff.c:100!
[ 64.662644] invalid opcode: 0000 [#1] PREEMPT SMP
[ 64.664001] Modules linked in: rpcsec_gss_krb5 auth_rpcgss oid_registry nfsv4 cirrus ttm drm_kms_helper drm enic psmouse microcode evdev serio_raw syscopyarea sysfillrect sysimgblt i2c_piix4 i2c_core pcspkr nfs lockd grace sunrpc fscache ext4 crc16 mbcache jbd2 sd_mod ata_generic virtio_balloon ata_piix libata uhci_hcd virtio_pci virtio_ring usbcore usb_common virtio scsi_mod
[ 64.664834] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 3.17.0-netnext-10335-g942396b-dirty #273
[ 64.664834] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 64.664834] task: ffffffff81a1d580 ti: ffffffff81a00000 task.ti: ffffffff81a00000
[ 64.664834] RIP: 0010:[<ffffffff81392cf1>] [<ffffffff81392cf1>] skb_panic+0x61/0x70
[ 64.664834] RSP: 0018:ffff880210603d48 EFLAGS: 00010292
[ 64.664834] RAX: 000000000000008c RBX: ffff88020b0f6930 RCX: 0000000000000000
[ 64.664834] RDX: 000000000000008c RSI: ffffffff8178b288 RDI: 00000000ffffffff
[ 64.664834] RBP: ffff880210603d68 R08: 0000000000000001 R09: 0000000000000001
[ 64.664834] R10: 00000000000005ce R11: 0000000000000001 R12: ffff88020b1f0b40
[ 64.664834] R13: 000000000000a332 R14: ffff880209a1a000 R15: 0000000000000001
[ 64.664834] FS: 0000000000000000(0000) GS:ffff880210600000(0000) knlGS:0000000000000000
[ 64.664834] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 64.664834] CR2: 00007f6752935e48 CR3: 0000000035743000 CR4: 00000000000006f0
[ 64.664834] Stack:
[ 64.664834] ffff8800d3caa000 0000000000002372 0000000000000640 ffff88020b1f0000
[ 64.664834] ffff880210603d78 ffffffff81392d54 ffff880210603e08 ffffffffa041f55d
[ 64.664834] 0000000000000296 ffffffff00000000 00008e7e00008e7e ffff880200002332
[ 64.664834] Call Trace:
[ 64.664834] <IRQ>
[ 64.664834]
[ 64.664834] [<ffffffff81392d54>] skb_put+0x54/0x60
[ 64.664834] [<ffffffffa041f55d>] enic_rq_service.constprop.47+0x3ad/0x730 [enic]
[ 64.664834] [<ffffffffa041fa79>] enic_poll_msix_rq+0x199/0x370 [enic]
[ 64.664834] [<ffffffff813a5499>] net_rx_action+0x139/0x210
[ 64.664834] [<ffffffff81290db3>] ? __this_cpu_preempt_check+0x13/0x20
[ 64.664834] [<ffffffff8106110e>] __do_softirq+0x14e/0x280
[ 64.664834] [<ffffffff8106152e>] irq_exit+0x8e/0xb0
[ 64.664834] [<ffffffff8100fd21>] do_IRQ+0x61/0x100
[ 64.664834] [<ffffffff814a2bf2>] common_interrupt+0x72/0x72
fixes: a03bb56e67c357980dae886683733dab5583dc14 ("enic: implement rx_copybreak")
Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com>
---
drivers/net/ethernet/cisco/enic/enic_main.c | 14 ++------------
1 file changed, 2 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index cd254d1..73cf165 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -940,18 +940,8 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
struct vnic_rq_buf *buf = rq->to_use;
if (buf->os_buf) {
- buf = buf->next;
- rq->to_use = buf;
- rq->ring.desc_avail--;
- if ((buf->index & VNIC_RQ_RETURN_RATE) == 0) {
- /* Adding write memory barrier prevents compiler and/or
- * CPU reordering, thus avoiding descriptor posting
- * before descriptor is initialized. Otherwise, hardware
- * can read stale descriptor fields.
- */
- wmb();
- iowrite32(buf->index, &rq->ctrl->posted_index);
- }
+ enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
+ buf->len);
return 0;
}
--
2.1.0
^ permalink raw reply related
* RE: ipv4: Use standard iovec primitive in raw_probe_proto_opt
From: Jon Maloy @ 2014-11-06 9:55 UTC (permalink / raw)
To: Al Viro, Herbert Xu
Cc: David Miller, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, bcrl@kvack.org, Masahide Nakamura,
Hideaki YOSHIFUJI
In-Reply-To: <20141106071109.GX7996@ZenIV.linux.org.uk>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of Al Viro
> Sent: November-06-14 8:11 AM
> To: Herbert Xu
> Cc: David Miller; netdev@vger.kernel.org; linux-kernel@vger.kernel.org;
> bcrl@kvack.org; Masahide Nakamura; Hideaki YOSHIFUJI
> Subject: Re: ipv4: Use standard iovec primitive in raw_probe_proto_opt
>
> On Thu, Nov 06, 2014 at 02:46:29PM +0800, Herbert Xu wrote:
> > On Thu, Nov 06, 2014 at 06:43:18AM +0000, Al Viro wrote:
> > > On Thu, Nov 06, 2014 at 01:50:23PM +0800, Herbert Xu wrote:
> > > > + /* We only need the first two bytes. */
> > > > + err = memcpy_fromiovecend((void *)&icmph, msg->msg_iov, 0, 2);
> > > > + if (err)
> > > > + return err;
> > > > +
> > > > + fl4->fl4_icmp_type = icmph.type;
> > > > + fl4->fl4_icmp_code = icmph.code;
> > >
> > > That's more readable, but that exposes another problem in there - we
> > > read the same piece of userland data twice, with no promise
> > > whatsoever that we'll get the same value both times...
> >
> > Sure, but you have to be root anyway to write to raw sockets.
>
> Point, but that might very well be a pattern to watch for - there's at least one
> more instance in TIPC (also not exploitable, according to TIPC folks) and such
I don't recall this, and I can't see where it would be either. Can you please
point to where it is?
///jon
> bugs are easily repeated...
>
> BTW, I've picked the tun and macvtap related bits from another part of old
> queue; see vfs.git#untested-macvtap - it's on top of #iov_iter-net and it's
> really completely untested. Back then I was mostly interested in killing as
> many ->aio_write() instances as I could, so it's only the "send" side of things.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in the body
> of a message to majordomo@vger.kernel.org More majordomo info at
> http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: "asix: Don't reset PHY on if_up for ASIX 88772" breaks net on arndale platform
From: Charles Keepax @ 2014-11-06 10:01 UTC (permalink / raw)
To: Riku Voipio
Cc: Stam, Michel [FINT], freddy, davem, linux-usb, netdev,
linux-kernel, linux-samsung-soc
In-Reply-To: <20141106090651.GA19109@afflict.kos.to>
On Thu, Nov 06, 2014 at 11:06:51AM +0200, Riku Voipio wrote:
> On Wed, Nov 05, 2014 at 03:02:58PM +0000, Charles Keepax wrote:
> > On Wed, Nov 05, 2014 at 01:04:37PM +0100, Stam, Michel [FINT] wrote:
> > > Hello Charles,
> > >
> > > After looking around I found the reset value for the 8772 chip, which
> > > seems to be 0x1E1 (ANAR register).
> > >
> > > This equates to (according to include/uapi/linux/mii.h)
> > > ADVERTISE_ALL | ADVERTISE_CSMA.
> > >
> > > The register only seems to become 0 if the software reset fails.
>
> > Odd it definitely reads back as zero on Arndale. I am guessing
> > that the root of the problem here is that for some reason Arndale
> > POR of the ethernet is pants and it needs a full software reset
> > before it will work and the patch removes the full reset
> > callback.
>
> The asix on arndale comes semi-configured from u-boot, which I guess is
> not the state kernel expects it to come in. At least in my case where
> I use tftp from u-boot to load my kernel.
>
> So probably the full reset is needed here to make the asix chip come
> to a truly pristine state.
>
> The commit that Michel partially reverted (by returning to use
> ax88772_link_reset instead of ax88772_reset), indicates that a strong reset
> is needed for suspend/resume as well:
Ok I think I have cracked this one. I am pretty sure you are
right that the USB comes to us in a strange state and needs
a full reset, but that only needs to happen once when the driver
is bound in. So there is some code in ax88772_bind that appears
to try to reset the device but does a lot less than ax88772_reset
and I think that must be the problem. Applying the following on
top of the patch we have been debating I think will make
everything work for all of us:
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -465,19 +465,7 @@ static int ax88772_bind(struct usbnet *dev,
struct usb_interface *in
return ret;
}
- ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_PRL);
- if (ret < 0)
- return ret;
-
- msleep(150);
-
- ret = asix_sw_reset(dev, AX_SWRESET_CLEAR);
- if (ret < 0)
- return ret;
-
- msleep(150);
-
- ret = asix_sw_reset(dev, embd_phy ? AX_SWRESET_IPRL : AX_SWRESET_PRTE);
+ ax88772_reset(dev);
If you guys could test that and let me know how you get on I will
send in a proper patch if it looks good.
Thanks,
Charles
^ permalink raw reply
* [PATCH net 0/2] mlx5_core fixes for 3.18
From: Eli Cohen @ 2014-11-06 10:51 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-rdma, ogerlitz, Eli Cohen
Hi Dave,
the following two patches fix races to could lead to kernel panic in some cases.
Thanks,
Eli
Eli Cohen (2):
net/mlx5_core: Fix race in create EQ
net/mlx5_core: Fix race on driver load
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 7 +++----
drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ++--
2 files changed, 5 insertions(+), 6 deletions(-)
--
2.1.2
^ permalink raw reply
* [PATCH net 1/2] net/mlx5_core: Fix race in create EQ
From: Eli Cohen @ 2014-11-06 10:51 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-rdma, ogerlitz, Eli Cohen
In-Reply-To: <1415271082-7644-1-git-send-email-eli@mellanox.com>
After the EQ is created, it can possibly generate interrupts and the interrupt
handler is referencing eq->dev. It is therefore required to set eq->dev before
calling request_irq() so if an event is generated before request_irq() returns,
we will have a valid eq->dev field.
Signed-off-by: Eli Cohen <eli@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index a278238a2db6..ad2c96a02a53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -374,15 +374,14 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
snprintf(eq->name, MLX5_MAX_EQ_NAME, "%s@pci:%s",
name, pci_name(dev->pdev));
eq->eqn = out.eq_number;
+ eq->irqn = vecidx;
+ eq->dev = dev;
+ eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET;
err = request_irq(table->msix_arr[vecidx].vector, mlx5_msix_handler, 0,
eq->name, eq);
if (err)
goto err_eq;
- eq->irqn = vecidx;
- eq->dev = dev;
- eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET;
-
err = mlx5_debug_eq_add(dev, eq);
if (err)
goto err_irq;
--
2.1.2
^ permalink raw reply related
* [PATCH net 2/2] net/mlx5_core: Fix race on driver load
From: Eli Cohen @ 2014-11-06 10:51 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-rdma, ogerlitz, Eli Cohen
In-Reply-To: <1415271082-7644-1-git-send-email-eli@mellanox.com>
When events arrive at driver load, the event handler gets called even before
the spinlock and list are initialized. Fix this by moving the initialization
before EQs creation.
Signed-off-by: Eli Cohen <eli@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 88b2ffa0edfb..ecc6341e728a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -855,14 +855,14 @@ static int init_one(struct pci_dev *pdev,
dev->profile = &profile[prof_sel];
dev->event = mlx5_core_event;
+ INIT_LIST_HEAD(&priv->ctx_list);
+ spin_lock_init(&priv->ctx_lock);
err = mlx5_dev_init(dev, pdev);
if (err) {
dev_err(&pdev->dev, "mlx5_dev_init failed %d\n", err);
goto out;
}
- INIT_LIST_HEAD(&priv->ctx_list);
- spin_lock_init(&priv->ctx_lock);
err = mlx5_register_device(dev);
if (err) {
dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err);
--
2.1.2
^ permalink raw reply related
* Re: [PATCH] bridge: missing null bridge device check causing null pointer dereference (bugfix)
From: Eric Dumazet @ 2014-11-06 11:35 UTC (permalink / raw)
To: 박수현
Cc: netdev@vger.kernel.org, bridge@lists.linux-foundation.org,
linux-kernel@vger.kernel.org, Stephen Hemminger, David S. Miller
In-Reply-To: <8D1F1238A24CE743B8F3CED0F137C69E408AA087@EXMB02.ahnbang.ahnlab.com>
On Thu, 2014-11-06 at 07:58 +0000, 박수현 wrote:
> >-----Original Message-----
> >From: Toshiaki Makita [mailto:makita.toshiaki@lab.ntt.co.jp]
> >Sent: Thursday, November 06, 2014 4:07 PM
> >To: 박수현; Stephen Hemminger; David S. Miller
> >Cc: bridge@lists.linux-foundation.org; netdev@vger.kernel.org; linux-
> >kernel@vger.kernel.org
> >Subject: Re: [PATCH] bridge: missing null bridge device check causing null
> >pointer dereference (bugfix)
> >
> >On 2014/11/06 15:26, Su-Hyun Park wrote:
> >> the bridge device can be null if the bridge is being deleted while
> >> processing the packet, which causes the null pointer dereference in
> >switch statement.
> >
> >How can this happen??
> >It is guarded by rcu.
> >netdev_rx_handler_unregister() ensures rx_handler_data is non NULL.
> >
>
> The RCU protect rx_handler_data, not the bridge member port. It can be NULL according to below code.
>
Where do you find this 'below code' ?
Are you sending a patch for an old linux kernel ?
> static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev) {
> struct net_bridge_port *port = rcu_dereference(dev->rx_handler_data);
> return br_port_exists(dev) ? port : NULL;
> }
Actual code is :
static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
{
return rcu_dereference(dev->rx_handler_data);
}
>
> The crash happens at the below switch statement in br_handle_frame, where p is NULL.
>
> switch (p->state)
Is your tree really including the fix we already did to fix this issue ?
(commit 716ec052d2280d511e10e90ad54a86f5b5d4dcc2 )
bridge: fix NULL pointer deref of br_port_get_rcu
^ permalink raw reply
* Re: [PATCH] rtlwifi: Add more checks for get_btc_status callback
From: Murilo Opsfelder Araujo @ 2014-11-06 11:40 UTC (permalink / raw)
To: Larry Finger, Mike Galbraith
Cc: linux-kernel, linux-wireless, netdev, Chaoming Li,
John W. Linville, Thadeu Cascardo, troy_tan
In-Reply-To: <545A6894.7040506@lwfinger.net>
On 11/05/2014 04:12 PM, Larry Finger wrote:
> On 11/05/2014 03:16 AM, Mike Galbraith wrote:
>> On Wed, 2014-10-29 at 23:30 -0500, Larry Finger wrote:
>>> On 10/29/2014 06:28 PM, Murilo Opsfelder Araujo wrote:
>>>> This is a complement of commit 08054200117a95afc14c3d2ed3a38bf4e345bf78
>>>> "rtlwifi: Add check for get_btc_status callback".
>>>>
>>>> With this patch, next-20141029 at least does not panic with rtl8192se
>>>> device.
>>>>
>>>
>>> This patch is OK, but as noted it is not complete.
>>>
>>> I have patches to fix all the kernel panics for rtl8192se AND
>>> rtl8192ce. There
>>> are missing parts, but I would prefer submitting mine, which would
>>> conflict with
>>> this one. For that reason, NACK for this one, and please apply the
>>> set I am
>>> submitting now.
>>
>> It's all in there now, but my RTL8191SEvB is still dead. Squabbling
>> with it isn't going all that well either.
>>
>> As soon as 38506ece rtlwifi: rtl_pci: Start modification for new drivers
>> is applied, explosions appear. Subsequently applying...
>>
>> 08054200 rtlwifi: Add check for get_btc_status callback
>> c0386f15 rtlwifi: rtl8192ce: rtl8192de: rtl8192se: Fix handling for
>> missing get_btc_status
>> 50147969 rtlwifi: rtl8192se: Fix duplicate calls to
>> ieee80211_register_hw()
>> 30c5ccc6 rtlwifi: rtl8192se: Add missing section to read descriptor
>> setting
>> 75a916e1 rtlwifi: rtl8192se: Fix firmware loading
>>
>> ...fixes that mess up, but leaves the interface dead in the same manner
>> as if nothing has been reverted. So it _seems_ the bustage lurks in
>> 38506ece somewhere. Too bad it's non-dinky, and written in wifi-ese :)
>
> Yes, I am aware that rtl8192se is failing, and now that I am back from
> vacation, I am working on the problem. If you want to use the driver
> with kernel 3.18, clone the repo at
> http://github.com/lwfinger/rtlwifi_new.git and build and install either
> the master or kernel_version branches. Both work.
>
> I am in the process of trying to find what the crucial difference is
> between that repo and the kernel version.
>
> Larry
>
>
I'm sending to everyone so others can jump in as well.
Here are the steps I've followed.
Installed and booted my kernel:
$ sudo dpkg -i linux-image-3.18.0-rc3-next-20141105-panda_3.18.0-rc3-next-20141105-panda-1_amd64.deb linux-headers-3.18.0-rc3-next-20141105-panda_3.18.0-rc3-next-20141105-panda-1_amd64.deb
Built modules from Larry's github repository.
$ cd rtlwifi_new
$ make
$ sudo make install
$ sudo modprobe -rv rtl8192se
rmmod rtl8192se
rmmod rtl_pci
rmmod rtlwifi
rmmod mac80211
rmmod cfg80211
The module does not load:
$ sudo modprobe -v rtl8192se
insmod /lib/modules/3.18.0-rc3-next-20141105-panda/kernel/net/wireless/cfg80211.ko
insmod /lib/modules/3.18.0-rc3-next-20141105-panda/kernel/net/mac80211/mac80211.ko
insmod /lib/modules/3.18.0-rc3-next-20141105-panda/kernel/drivers/net/wireless/rtlwifi/rtlwifi.ko
insmod /lib/modules/3.18.0-rc3-next-20141105-panda/kernel/drivers/net/wireless/rtlwifi/rtl_pci.ko
insmod /lib/modules/3.18.0-rc3-next-20141105-panda/extra/rtl8192se.ko
ERROR: could not insert 'rtl8192se': Invalid argument
And /var/log/messages showed:
Nov 5 22:28:01 laptop kernel: [ 301.276806] rtl8192se: disagrees about version of symbol rtl_process_phyinfo
Nov 5 22:28:01 laptop kernel: [ 301.276812] rtl8192se: Unknown symbol rtl_process_phyinfo (err -22)
Nov 5 22:28:01 laptop kernel: [ 301.276864] rtl8192se: disagrees about version of symbol rtl_get_tcb_desc
Nov 5 22:28:01 laptop kernel: [ 301.276866] rtl8192se: Unknown symbol rtl_get_tcb_desc (err -22)
--
Murilo
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox