* [net-next-2.6 PATCH v2 0/4] dcbnl: Extending dcbnl to support non-host DCBX
From: Shmulik Ravid @ 2010-12-30 16:26 UTC (permalink / raw)
To: davem; +Cc: Eilon Greenstein, John Fastabend, lucy.liu, netdev
DCBX is the exchange protocol for negotiating DCB parameters between a
host and a switch. In some circumstances the DCBX negotiator can not
reside in the host directly on top of the networking interface. For
instance many converged network adapters support an embedded DCBX engine
that performs the negotiation and configures the device with the
negotiated parameters. Another example is virtual hosts and SRIOV
virtual functions.
The following patches extend the dcbnl netlink interface so in addition
to its current semantics it offers a standard mechanism for managing
such non-host DCBX engines. In this new mode 'set' operations are used
to set the initial negotiation configuration and the 'get' operation are
used to retrieve the negotiated results.
The current definition of dcbnl assumes a host based stack is performing
the negotiation. As DCBX is encapsulated by LLDP there can be only one
DCBX negotiator per physical link. Thus the current scheme does not
allow the coexistence of CNAs that have embedded DCBX engines and CNAs
that do not, or even just retrieving DCB parameters by VF drivers.
The last patch adds an implementation of the dcbnl operations in their
proposed new semantics to the bnx2x, allowing users to configure and
manage the embedded DCBX engine.
The entire patch series is dependent on the following patches:
[net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
[net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
[net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
^ permalink raw reply
* [net-next-2.6 PATCH v2 1/4] dcbnl: adding DCBX engine capability
From: Shmulik Ravid @ 2010-12-30 16:26 UTC (permalink / raw)
To: davem; +Cc: Eilon Greenstein, John Fastabend, lucy.liu, netdev
Adding an optional DCBX capability and a pair for get-set routines for
setting the device DCBX mode. The DCBX capability is a bit field of
supported attributes. The user is expected to set the DCBX mode with a
subset of the advertised attributes.
This patch is dependent on the following patches:
[net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
[net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
[net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
---
include/linux/dcbnl.h | 43 +++++++++++++++++++++++++++++++++++++++++++
include/net/dcbnl.h | 5 +++++
net/dcb/dcbnl.c | 43 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 91 insertions(+), 0 deletions(-)
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 9071e1c..dd5c84e 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -124,6 +124,8 @@ struct dcbmsg {
* @DCB_CMD_SAPP: set application protocol configuration
* @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration
* @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration
+ * @DCB_CMD_GDCBX: get DCBX engine configuration
+ * @DCB_CMD_SDCBX: set DCBX engine configuration
*/
enum dcbnl_commands {
DCB_CMD_UNDEFINED,
@@ -160,6 +162,9 @@ enum dcbnl_commands {
DCB_CMD_IEEE_SET,
DCB_CMD_IEEE_GET,
+ DCB_CMD_GDCBX,
+ DCB_CMD_SDCBX,
+
__DCB_CMD_ENUM_MAX,
DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
};
@@ -180,6 +185,7 @@ enum dcbnl_commands {
* @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED)
* @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED)
* @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
+ * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8)
*/
enum dcbnl_attrs {
DCB_ATTR_UNDEFINED,
@@ -200,6 +206,8 @@ enum dcbnl_attrs {
/* IEEE std attributes */
DCB_ATTR_IEEE,
+ DCB_ATTR_DCBX,
+
__DCB_ATTR_ENUM_MAX,
DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
};
@@ -359,6 +367,8 @@ enum dcbnl_tc_attrs {
* @DCB_CAP_ATTR_GSP: (NLA_U8) device supports group strict priority
* @DCB_CAP_ATTR_BCN: (NLA_U8) device supports Backwards Congestion
* Notification
+ * @DCB_CAP_ATTR_DCBX: (NLA_U8) device supports DCBX engine
+ *
*/
enum dcbnl_cap_attrs {
DCB_CAP_ATTR_UNDEFINED,
@@ -370,12 +380,45 @@ enum dcbnl_cap_attrs {
DCB_CAP_ATTR_PFC_TCS,
DCB_CAP_ATTR_GSP,
DCB_CAP_ATTR_BCN,
+ DCB_CAP_ATTR_DCBX,
__DCB_CAP_ATTR_ENUM_MAX,
DCB_CAP_ATTR_MAX = __DCB_CAP_ATTR_ENUM_MAX - 1,
};
/**
+ * DCBX capability flags
+ *
+ * @DCB_CAP_DCBX_HOST: DCBX negotiation is performed by the host LLDP agent.
+ * 'set' routines are used to configure the device with
+ * the negotiated parameters
+ *
+ * @DCB_CAP_DCBX_LLD_MANAGED: DCBX negotiation is not performed in the host but
+ * by another entity
+ * 'get' routines are used to retrieve the
+ * negotiated parameters
+ * 'set' routines can be used to set the initial
+ * negotiation configuration
+ *
+ * @DCB_CAP_DCBX_VER_CEE: for a non-host DCBX engine, indicates the engine
+ * supports the CEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_VER_IEEE: for a non-host DCBX engine, indicates the engine
+ * supports the IEEE protocol flavor
+ *
+ * @DCB_CAP_DCBX_STATIC: for a non-host DCBX engine, indicates the engine
+ * supports static configuration (i.e no actual
+ * negotiation is performed negotiated parameters equal
+ * the initial configuration)
+ *
+ */
+#define DCB_CAP_DCBX_HOST 0x01
+#define DCB_CAP_DCBX_LLD_MANAGED 0x02
+#define DCB_CAP_DCBX_VER_CEE 0x04
+#define DCB_CAP_DCBX_VER_IEEE 0x08
+#define DCB_CAP_DCBX_STATIC 0x10
+
+/**
* enum dcbnl_numtcs_attrs - number of traffic classes
*
* @DCB_NUMTCS_ATTR_UNDEFINED: unspecified attribute to catch errors
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index ab7d623..c65347b 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -70,6 +70,11 @@ struct dcbnl_rtnl_ops {
void (*setbcnrp)(struct net_device *, int, u8);
u8 (*setapp)(struct net_device *, u8, u16, u8);
u8 (*getapp)(struct net_device *, u8, u16);
+
+ /* DCBX configuration */
+ u8 (*getdcbx)(struct net_device *);
+ u8 (*setdcbx)(struct net_device *, u8);
+
};
#endif /* __NET_DCBNL_H__ */
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 5f1d0ee..4603691 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -68,6 +68,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_BCN] = {.type = NLA_NESTED},
[DCB_ATTR_APP] = {.type = NLA_NESTED},
[DCB_ATTR_IEEE] = {.type = NLA_NESTED},
+ [DCB_ATTR_DCBX] = {.type = NLA_U8},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -124,6 +125,7 @@ static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = {
[DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8},
[DCB_CAP_ATTR_GSP] = {.type = NLA_U8},
[DCB_CAP_ATTR_BCN] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_DCBX] = {.type = NLA_U8},
};
/* DCB capabilities nested attributes. */
@@ -1271,6 +1273,39 @@ nlmsg_failure:
return -1;
}
+/* DCBX configuration */
+static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+
+ if (!netdev->dcbnl_ops->getdcbx)
+ return ret;
+
+ ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB,
+ DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags);
+
+ return ret;
+}
+
+static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+ u8 value;
+
+ if (!tb[DCB_ATTR_DCBX] || !netdev->dcbnl_ops->setdcbx)
+ return ret;
+
+ value = nla_get_u8(tb[DCB_ATTR_DCBX]);
+
+ ret = dcbnl_reply(netdev->dcbnl_ops->setdcbx(netdev, value),
+ RTM_SETDCB, DCB_CMD_SDCBX, DCB_ATTR_DCBX,
+ pid, seq, flags);
+
+ return ret;
+}
+
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
@@ -1384,6 +1419,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_GDCBX:
+ ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_SDCBX:
+ ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
1.7.1
^ permalink raw reply related
* [net-next-2.6 PATCH v2 2/4] dcbnl: adding DCBX feature flags get-set
From: Shmulik Ravid @ 2010-12-30 16:26 UTC (permalink / raw)
To: davem; +Cc: Eilon Greenstein, John Fastabend, lucy.liu, netdev
Adding a pair of set-get routines to dcbnl for setting the negotiation
flags of the various DCB features. Conforms to the CEE flavor of DCBX
The user sets these flags (enable, advertise, willing) for each feature
to be used by the DCBX engine. The 'get' routine returns which of the
features is enabled after the negotiation.
This patch is dependent on the following patches:
[net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
[net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
[net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
---
include/linux/dcbnl.h | 33 ++++++++++++
include/net/dcbnl.h | 3 +
net/dcb/dcbnl.c | 133 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 169 insertions(+), 0 deletions(-)
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index dd5c84e..18cab06 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -126,6 +126,8 @@ struct dcbmsg {
* @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration
* @DCB_CMD_GDCBX: get DCBX engine configuration
* @DCB_CMD_SDCBX: set DCBX engine configuration
+ * @DCB_CMD_GFEATCFG: get DCBX features flags
+ * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags
*/
enum dcbnl_commands {
DCB_CMD_UNDEFINED,
@@ -165,6 +167,9 @@ enum dcbnl_commands {
DCB_CMD_GDCBX,
DCB_CMD_SDCBX,
+ DCB_CMD_GFEATCFG,
+ DCB_CMD_SFEATCFG,
+
__DCB_CMD_ENUM_MAX,
DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
};
@@ -186,6 +191,7 @@ enum dcbnl_commands {
* @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED)
* @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
* @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8)
+ * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED)
*/
enum dcbnl_attrs {
DCB_ATTR_UNDEFINED,
@@ -207,6 +213,7 @@ enum dcbnl_attrs {
DCB_ATTR_IEEE,
DCB_ATTR_DCBX,
+ DCB_ATTR_FEATCFG,
__DCB_ATTR_ENUM_MAX,
DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
@@ -495,4 +502,30 @@ enum dcbnl_app_attrs {
DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1,
};
+/**
+ * enum dcbnl_featcfg_attrs - features conifiguration flags
+ *
+ * @DCB_FEATCFG_ATTR_UNDEFINED: unspecified attribute to catch errors
+ * @DCB_FEATCFG_ATTR_ALL: (NLA_FLAG) all features configuration attributes
+ * @DCB_FEATCFG_ATTR_PG: (NLA_U8) configuration flags for priority groups
+ * @DCB_FEATCFG_ATTR_PFC: (NLA_U8) configuration flags for priority
+ * flow control
+ * @DCB_FEATCFG_ATTR_APP: (NLA_U8) configuration flags for application TLV
+ *
+ */
+#define DCB_FEATCFG_ERROR 0x01 /* error in feature resolution */
+#define DCB_FEATCFG_ENABLE 0x02 /* enable feature */
+#define DCB_FEATCFG_WILLING 0x04 /* feature is willing */
+#define DCB_FEATCFG_ADVERTISE 0x08 /* advertise feature */
+enum dcbnl_featcfg_attrs {
+ DCB_FEATCFG_ATTR_UNDEFINED,
+ DCB_FEATCFG_ATTR_ALL,
+ DCB_FEATCFG_ATTR_PG,
+ DCB_FEATCFG_ATTR_PFC,
+ DCB_FEATCFG_ATTR_APP,
+
+ __DCB_FEATCFG_ATTR_ENUM_MAX,
+ DCB_FEATCFG_ATTR_MAX = __DCB_FEATCFG_ATTR_ENUM_MAX - 1,
+};
+
#endif /* __LINUX_DCBNL_H__ */
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index c65347b..a8e7852 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -70,11 +70,14 @@ struct dcbnl_rtnl_ops {
void (*setbcnrp)(struct net_device *, int, u8);
u8 (*setapp)(struct net_device *, u8, u16, u8);
u8 (*getapp)(struct net_device *, u8, u16);
+ u8 (*getfeatcfg)(struct net_device *, int, u8 *);
+ u8 (*setfeatcfg)(struct net_device *, int, u8);
/* DCBX configuration */
u8 (*getdcbx)(struct net_device *);
u8 (*setdcbx)(struct net_device *, u8);
+
};
#endif /* __NET_DCBNL_H__ */
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 4603691..b387816 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -69,6 +69,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_APP] = {.type = NLA_NESTED},
[DCB_ATTR_IEEE] = {.type = NLA_NESTED},
[DCB_ATTR_DCBX] = {.type = NLA_U8},
+ [DCB_ATTR_FEATCFG] = {.type = NLA_NESTED},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -182,6 +183,14 @@ static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = {
[DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)},
};
+/* DCB number of traffic classes nested attributes. */
+static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = {
+ [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG},
+ [DCB_FEATCFG_ATTR_PG] = {.type = NLA_U8},
+ [DCB_FEATCFG_ATTR_PFC] = {.type = NLA_U8},
+ [DCB_FEATCFG_ATTR_APP] = {.type = NLA_U8},
+};
+
static LIST_HEAD(dcb_app_list);
static DEFINE_SPINLOCK(dcb_lock);
@@ -1306,6 +1315,122 @@ static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb,
return ret;
}
+static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest;
+ u8 value;
+ int ret = -EINVAL;
+ int i;
+ int getall = 0;
+
+ if (!tb[DCB_ATTR_FEATCFG] || !netdev->dcbnl_ops->getfeatcfg)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
+ dcbnl_featcfg_nest);
+ if (ret) {
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb) {
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_GFEATCFG;
+
+ nest = nla_nest_start(dcbnl_skb, DCB_ATTR_FEATCFG);
+ if (!nest) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (data[DCB_FEATCFG_ATTR_ALL])
+ getall = 1;
+
+ for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) {
+ if (!getall && !data[i])
+ continue;
+
+ ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value);
+ if (!ret) {
+ ret = nla_put_u8(dcbnl_skb, i, value);
+
+ if (ret) {
+ nla_nest_cancel(dcbnl_skb, nest);
+ ret = -EINVAL;
+ goto err;
+ }
+ } else
+ goto err;
+ }
+ nla_nest_end(dcbnl_skb, nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret) {
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ return 0;
+nlmsg_failure:
+err:
+ kfree_skb(dcbnl_skb);
+err_out:
+ return ret;
+}
+
+static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1];
+ int ret = -EINVAL;
+ u8 value;
+ int i;
+
+ if (!tb[DCB_ATTR_FEATCFG] || !netdev->dcbnl_ops->setfeatcfg)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
+ dcbnl_featcfg_nest);
+
+ if (ret) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) {
+ if (data[i] == NULL)
+ continue;
+
+ value = nla_get_u8(data[i]);
+
+ ret = netdev->dcbnl_ops->setfeatcfg(netdev, i, value);
+
+ if (ret)
+ goto operr;
+ }
+
+operr:
+ ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SFEATCFG,
+ DCB_ATTR_FEATCFG, pid, seq, flags);
+
+err:
+ return ret;
+}
+
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
@@ -1427,6 +1552,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_GFEATCFG:
+ ret = dcbnl_getfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_SFEATCFG:
+ ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
1.7.1
^ permalink raw reply related
* [net-next-2.6 PATCH v2 4/4] dcbnl: cleanup
From: Shmulik Ravid @ 2010-12-30 16:27 UTC (permalink / raw)
To: davem; +Cc: John Fastabend, Eilon Greenstein, lucy.liu, netdev
A couple of small cleanups for patches:
[net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
[net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
[net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
---
net/dcb/dcbnl.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index b387816..ff3c12d 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1626,8 +1626,10 @@ u8 dcb_setapp(struct net_device *dev, struct dcb_app *new)
if (new->priority) {
struct dcb_app_type *entry;
entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
- if (!entry)
+ if (!entry) {
+ spin_unlock(&dcb_lock);
return -ENOMEM;
+ }
memcpy(&entry->app, new, sizeof(*new));
strncpy(entry->name, dev->name, IFNAMSIZ);
@@ -1640,7 +1642,7 @@ out:
}
EXPORT_SYMBOL(dcb_setapp);
-void dcb_flushapp(void)
+static void dcb_flushapp(void)
{
struct dcb_app_type *app;
--
1.7.1
^ permalink raw reply related
* [net-next-2.6 PATCH v2 3/4] bnx2x: adding dcbnl support
From: Shmulik Ravid @ 2010-12-30 16:27 UTC (permalink / raw)
To: davem; +Cc: Eilon Greenstein, John Fastabend, lucy.liu, netdev
Adding dcbnl implementation to bnx2x allowing users to manage the
embedded DCBX engine.
This patch is dependent on the following patches:
[net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
[net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
[net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
drivers/net/bnx2x/bnx2x.h | 23 ++-
drivers/net/bnx2x/bnx2x_dcb.c | 663 ++++++++++++++++++++++++++++++++++++++--
drivers/net/bnx2x/bnx2x_dcb.h | 9 +-
drivers/net/bnx2x/bnx2x_main.c | 8 +-
4 files changed, 677 insertions(+), 26 deletions(-)
diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h
index f14c6ed..77d6c8d 100644
--- a/drivers/net/bnx2x/bnx2x.h
+++ b/drivers/net/bnx2x/bnx2x.h
@@ -22,15 +22,17 @@
* (you will need to reboot afterwards) */
/* #define BNX2X_STOP_ON_ERROR */
-#define DRV_MODULE_VERSION "1.62.00-2"
-#define DRV_MODULE_RELDATE "2010/12/13"
+#define DRV_MODULE_VERSION "1.62.00-3"
+#define DRV_MODULE_RELDATE "2010/12/21"
#define BNX2X_BC_VER 0x040200
#define BNX2X_MULTI_QUEUE
#define BNX2X_NEW_NAPI
-
+#if defined(CONFIG_DCB)
+#define BCM_DCB
+#endif
#if defined(CONFIG_CNIC) || defined(CONFIG_CNIC_MODULE)
#define BCM_CNIC 1
#include "../cnic_if.h"
@@ -1186,7 +1188,20 @@ struct bnx2x {
/* LLDP params */
struct bnx2x_config_lldp_params lldp_config_params;
- /* DCBX params */
+ /* DCB support on/off */
+ u16 dcb_state;
+#define BNX2X_DCB_STATE_OFF 0
+#define BNX2X_DCB_STATE_ON 1
+
+ /* DCBX engine mode */
+ int dcbx_enabled;
+#define BNX2X_DCBX_ENABLED_OFF 0
+#define BNX2X_DCBX_ENABLED_ON_NEG_OFF 1
+#define BNX2X_DCBX_ENABLED_ON_NEG_ON 2
+#define BNX2X_DCBX_ENABLED_INVALID (-1)
+
+ bool dcbx_mode_uset;
+
struct bnx2x_config_dcbx_params dcbx_config_params;
struct bnx2x_dcbx_port_params dcbx_port_params;
diff --git a/drivers/net/bnx2x/bnx2x_dcb.c b/drivers/net/bnx2x/bnx2x_dcb.c
index 0b86480..fb60021 100644
--- a/drivers/net/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/bnx2x/bnx2x_dcb.c
@@ -619,13 +619,10 @@ static void bnx2x_dcbx_admin_mib_updated_params(struct bnx2x *bp,
for (i = 0; i < sizeof(struct lldp_admin_mib); i += 4, buff++)
*buff = REG_RD(bp, (offset + i));
-
- if (BNX2X_DCBX_CONFIG_INV_VALUE != dp->admin_dcbx_enable) {
- if (dp->admin_dcbx_enable)
- SET_FLAGS(admin_mib.ver_cfg_flags, DCBX_DCBX_ENABLED);
- else
- RESET_FLAGS(admin_mib.ver_cfg_flags, DCBX_DCBX_ENABLED);
- }
+ if (bp->dcbx_enabled == BNX2X_DCBX_ENABLED_ON_NEG_ON)
+ SET_FLAGS(admin_mib.ver_cfg_flags, DCBX_DCBX_ENABLED);
+ else
+ RESET_FLAGS(admin_mib.ver_cfg_flags, DCBX_DCBX_ENABLED);
if ((BNX2X_DCBX_OVERWRITE_SETTINGS_ENABLE ==
dp->overwrite_settings)) {
@@ -734,12 +731,26 @@ static void bnx2x_dcbx_admin_mib_updated_params(struct bnx2x *bp,
REG_WR(bp, (offset + i), *buff);
}
-/* default */
+void bnx2x_dcbx_set_state(struct bnx2x *bp, bool dcb_on, u32 dcbx_enabled)
+{
+ if (CHIP_IS_E2(bp) && !CHIP_MODE_IS_4_PORT(bp)) {
+ bp->dcb_state = dcb_on;
+ bp->dcbx_enabled = dcbx_enabled;
+ } else {
+ bp->dcb_state = false;
+ bp->dcbx_enabled = BNX2X_DCBX_ENABLED_INVALID;
+ }
+ DP(NETIF_MSG_LINK, "DCB state [%s:%s]\n",
+ dcb_on ? "ON" : "OFF",
+ dcbx_enabled == BNX2X_DCBX_ENABLED_OFF ? "user-mode" :
+ dcbx_enabled == BNX2X_DCBX_ENABLED_ON_NEG_OFF ? "on-chip static" :
+ dcbx_enabled == BNX2X_DCBX_ENABLED_ON_NEG_ON ?
+ "on-chip with negotiation" : "invalid");
+}
+
void bnx2x_dcbx_init_params(struct bnx2x *bp)
{
bp->dcbx_config_params.admin_dcbx_version = 0x0; /* 0 - CEE; 1 - IEEE */
- bp->dcbx_config_params.dcb_enable = 1;
- bp->dcbx_config_params.admin_dcbx_enable = 1;
bp->dcbx_config_params.admin_ets_willing = 1;
bp->dcbx_config_params.admin_pfc_willing = 1;
bp->dcbx_config_params.overwrite_settings = 1;
@@ -807,23 +818,27 @@ void bnx2x_dcbx_init_params(struct bnx2x *bp)
void bnx2x_dcbx_init(struct bnx2x *bp)
{
u32 dcbx_lldp_params_offset = SHMEM_LLDP_DCBX_PARAMS_NONE;
+
+ if (bp->dcbx_enabled <= 0)
+ return;
+
/* validate:
* chip of good for dcbx version,
* dcb is wanted
* the function is pmf
* shmem2 contains DCBX support fields
*/
- DP(NETIF_MSG_LINK, "dcb_enable %d bp->port.pmf %d\n",
- bp->dcbx_config_params.dcb_enable, bp->port.pmf);
+ DP(NETIF_MSG_LINK, "dcb_state %d bp->port.pmf %d\n",
+ bp->dcb_state, bp->port.pmf);
- if (CHIP_IS_E2(bp) && !CHIP_MODE_IS_4_PORT(bp) &&
- bp->dcbx_config_params.dcb_enable &&
- bp->port.pmf &&
+ if (bp->dcb_state == BNX2X_DCB_STATE_ON && bp->port.pmf &&
SHMEM2_HAS(bp, dcbx_lldp_params_offset)) {
- dcbx_lldp_params_offset = SHMEM2_RD(bp,
- dcbx_lldp_params_offset);
+ dcbx_lldp_params_offset =
+ SHMEM2_RD(bp, dcbx_lldp_params_offset);
+
DP(NETIF_MSG_LINK, "dcbx_lldp_params_offset 0x%x\n",
dcbx_lldp_params_offset);
+
if (SHMEM_LLDP_DCBX_PARAMS_NONE != dcbx_lldp_params_offset) {
bnx2x_dcbx_lldp_updated_params(bp,
dcbx_lldp_params_offset);
@@ -1452,7 +1467,7 @@ static void bnx2x_dcbx_get_ets_pri_pg_tbl(struct bnx2x *bp,
******************************************************************************/
static void bnx2x_pfc_fw_struct_e2(struct bnx2x *bp)
{
- struct flow_control_configuration *pfc_fw_cfg = 0;
+ struct flow_control_configuration *pfc_fw_cfg = NULL;
u16 pri_bit = 0;
u8 cos = 0, pri = 0;
struct priority_cos *tt2cos;
@@ -1489,3 +1504,615 @@ static void bnx2x_pfc_fw_struct_e2(struct bnx2x *bp)
}
bnx2x_dcbx_print_cos_params(bp, pfc_fw_cfg);
}
+/* DCB netlink */
+#ifdef BCM_DCB
+#include <linux/dcbnl.h>
+
+#define BNX2X_DCBX_CAPS (DCB_CAP_DCBX_LLD_MANAGED | \
+ DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_STATIC)
+
+static inline bool bnx2x_dcbnl_set_valid(struct bnx2x *bp)
+{
+ /* validate dcbnl call that may change HW state:
+ * DCB is on and DCBX mode was SUCCESSFULLY set by the user.
+ */
+ return bp->dcb_state && bp->dcbx_mode_uset;
+}
+
+static u8 bnx2x_dcbnl_get_state(struct net_device *netdev)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "state = %d\n", bp->dcb_state);
+ return bp->dcb_state;
+}
+
+static u8 bnx2x_dcbnl_set_state(struct net_device *netdev, u8 state)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "state = %s\n", state ? "on" : "off");
+
+ bnx2x_dcbx_set_state(bp, (state ? true : false), bp->dcbx_enabled);
+ return 0;
+}
+
+static void bnx2x_dcbnl_get_perm_hw_addr(struct net_device *netdev,
+ u8 *perm_addr)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "GET-PERM-ADDR\n");
+
+ /* first the HW mac address */
+ memcpy(perm_addr, netdev->dev_addr, netdev->addr_len);
+
+#ifdef BCM_CNIC
+ /* second SAN address */
+ memcpy(perm_addr+netdev->addr_len, bp->fip_mac, netdev->addr_len);
+#endif
+}
+
+static void bnx2x_dcbnl_set_pg_tccfg_tx(struct net_device *netdev, int prio,
+ u8 prio_type, u8 pgid, u8 bw_pct,
+ u8 up_map)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+
+ DP(NETIF_MSG_LINK, "prio[%d] = %d\n", prio, pgid);
+ if (!bnx2x_dcbnl_set_valid(bp) || prio >= DCBX_MAX_NUM_PRI_PG_ENTRIES)
+ return;
+
+ /**
+ * bw_pct ingnored - band-width percentage devision between user
+ * priorities within the same group is not
+ * standard and hence not supported
+ *
+ * prio_type igonred - priority levels within the same group are not
+ * standard and hence are not supported. According
+ * to the standard pgid 15 is dedicated to strict
+ * prioirty traffic (on the port level).
+ *
+ * up_map ignored
+ */
+
+ bp->dcbx_config_params.admin_configuration_ets_pg[prio] = pgid;
+ bp->dcbx_config_params.admin_ets_configuration_tx_enable = 1;
+}
+
+static void bnx2x_dcbnl_set_pg_bwgcfg_tx(struct net_device *netdev,
+ int pgid, u8 bw_pct)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "pgid[%d] = %d\n", pgid, bw_pct);
+
+ if (!bnx2x_dcbnl_set_valid(bp) || pgid >= DCBX_MAX_NUM_PG_BW_ENTRIES)
+ return;
+
+ bp->dcbx_config_params.admin_configuration_bw_precentage[pgid] = bw_pct;
+ bp->dcbx_config_params.admin_ets_configuration_tx_enable = 1;
+}
+
+static void bnx2x_dcbnl_set_pg_tccfg_rx(struct net_device *netdev, int prio,
+ u8 prio_type, u8 pgid, u8 bw_pct,
+ u8 up_map)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "Nothing to set; No RX support\n");
+}
+
+static void bnx2x_dcbnl_set_pg_bwgcfg_rx(struct net_device *netdev,
+ int pgid, u8 bw_pct)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "Nothing to set; No RX support\n");
+}
+
+static void bnx2x_dcbnl_get_pg_tccfg_tx(struct net_device *netdev, int prio,
+ u8 *prio_type, u8 *pgid, u8 *bw_pct,
+ u8 *up_map)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "prio = %d\n", prio);
+
+ /**
+ * bw_pct ingnored - band-width percentage devision between user
+ * priorities within the same group is not
+ * standard and hence not supported
+ *
+ * prio_type igonred - priority levels within the same group are not
+ * standard and hence are not supported. According
+ * to the standard pgid 15 is dedicated to strict
+ * prioirty traffic (on the port level).
+ *
+ * up_map ignored
+ */
+ *up_map = *bw_pct = *prio_type = *pgid = 0;
+
+ if (!bp->dcb_state || prio >= DCBX_MAX_NUM_PRI_PG_ENTRIES)
+ return;
+
+ *pgid = DCBX_PRI_PG_GET(bp->dcbx_local_feat.ets.pri_pg_tbl, prio);
+}
+
+static void bnx2x_dcbnl_get_pg_bwgcfg_tx(struct net_device *netdev,
+ int pgid, u8 *bw_pct)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "pgid = %d\n", pgid);
+
+ *bw_pct = 0;
+
+ if (!bp->dcb_state || pgid >= DCBX_MAX_NUM_PG_BW_ENTRIES)
+ return;
+
+ *bw_pct = DCBX_PG_BW_GET(bp->dcbx_local_feat.ets.pg_bw_tbl, pgid);
+}
+
+static void bnx2x_dcbnl_get_pg_tccfg_rx(struct net_device *netdev, int prio,
+ u8 *prio_type, u8 *pgid, u8 *bw_pct,
+ u8 *up_map)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "Nothing to get; No RX support\n");
+
+ *prio_type = *pgid = *bw_pct = *up_map = 0;
+}
+
+static void bnx2x_dcbnl_get_pg_bwgcfg_rx(struct net_device *netdev,
+ int pgid, u8 *bw_pct)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "Nothing to get; No RX support\n");
+
+ *bw_pct = 0;
+}
+
+static void bnx2x_dcbnl_set_pfc_cfg(struct net_device *netdev, int prio,
+ u8 setting)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "prio[%d] = %d\n", prio, setting);
+
+ if (!bnx2x_dcbnl_set_valid(bp) || prio >= MAX_PFC_PRIORITIES)
+ return;
+
+ bp->dcbx_config_params.admin_pfc_bitmap |= ((setting ? 1 : 0) << prio);
+
+ if (setting)
+ bp->dcbx_config_params.admin_pfc_tx_enable = 1;
+}
+
+static void bnx2x_dcbnl_get_pfc_cfg(struct net_device *netdev, int prio,
+ u8 *setting)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "prio = %d\n", prio);
+
+ *setting = 0;
+
+ if (!bp->dcb_state || prio >= MAX_PFC_PRIORITIES)
+ return;
+
+ *setting = (bp->dcbx_local_feat.pfc.pri_en_bitmap >> prio) & 0x1;
+}
+
+static u8 bnx2x_dcbnl_set_all(struct net_device *netdev)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ int rc = 0;
+
+ DP(NETIF_MSG_LINK, "SET-ALL\n");
+
+ if (!bnx2x_dcbnl_set_valid(bp))
+ return 1;
+
+ if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
+ netdev_err(bp->dev, "Handling parity error recovery. "
+ "Try again later\n");
+ return 1;
+ }
+ if (netif_running(bp->dev)) {
+ bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+ rc = bnx2x_nic_load(bp, LOAD_NORMAL);
+ }
+ DP(NETIF_MSG_LINK, "set_dcbx_params done (%d)\n", rc);
+ if (rc)
+ return 1;
+
+ return 0;
+}
+
+static u8 bnx2x_dcbnl_get_cap(struct net_device *netdev, int capid, u8 *cap)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ u8 rval = 0;
+
+ if (bp->dcb_state) {
+ switch (capid) {
+ case DCB_CAP_ATTR_PG:
+ *cap = true;
+ break;
+ case DCB_CAP_ATTR_PFC:
+ *cap = true;
+ break;
+ case DCB_CAP_ATTR_UP2TC:
+ *cap = false;
+ break;
+ case DCB_CAP_ATTR_PG_TCS:
+ *cap = 0x80; /* 8 priorities for PGs */
+ break;
+ case DCB_CAP_ATTR_PFC_TCS:
+ *cap = 0x80; /* 8 priorities for PFC */
+ break;
+ case DCB_CAP_ATTR_GSP:
+ *cap = true;
+ break;
+ case DCB_CAP_ATTR_BCN:
+ *cap = false;
+ break;
+ case DCB_CAP_ATTR_DCBX:
+ *cap = BNX2X_DCBX_CAPS;
+ default:
+ rval = -EINVAL;
+ break;
+ }
+ } else
+ rval = -EINVAL;
+
+ DP(NETIF_MSG_LINK, "capid %d:%x\n", capid, *cap);
+ return rval;
+}
+
+static u8 bnx2x_dcbnl_get_numtcs(struct net_device *netdev, int tcid, u8 *num)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ u8 rval = 0;
+
+ DP(NETIF_MSG_LINK, "tcid %d\n", tcid);
+
+ if (bp->dcb_state) {
+ switch (tcid) {
+ case DCB_NUMTCS_ATTR_PG:
+ *num = E2_NUM_OF_COS;
+ break;
+ case DCB_NUMTCS_ATTR_PFC:
+ *num = E2_NUM_OF_COS;
+ break;
+ default:
+ rval = -EINVAL;
+ break;
+ }
+ } else
+ rval = -EINVAL;
+
+ return rval;
+}
+
+static u8 bnx2x_dcbnl_set_numtcs(struct net_device *netdev, int tcid, u8 num)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "num tcs = %d; Not supported\n", num);
+ return -EINVAL;
+}
+
+static u8 bnx2x_dcbnl_get_pfc_state(struct net_device *netdev)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "state = %d\n", bp->dcbx_local_feat.pfc.enabled);
+
+ if (!bp->dcb_state)
+ return 0;
+
+ return bp->dcbx_local_feat.pfc.enabled;
+}
+
+static void bnx2x_dcbnl_set_pfc_state(struct net_device *netdev, u8 state)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "state = %s\n", state ? "on" : "off");
+
+ if (!bnx2x_dcbnl_set_valid(bp))
+ return;
+
+ bp->dcbx_config_params.admin_pfc_tx_enable =
+ bp->dcbx_config_params.admin_pfc_enable = (state ? 1 : 0);
+}
+
+static bool bnx2x_app_is_equal(struct dcbx_app_priority_entry *app_ent,
+ u8 idtype, u16 idval)
+{
+ if (!(app_ent->appBitfield & DCBX_APP_ENTRY_VALID))
+ return false;
+
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+ if ((app_ent->appBitfield & DCBX_APP_ENTRY_SF_MASK) !=
+ DCBX_APP_SF_ETH_TYPE)
+ return false;
+ break;
+ case DCB_APP_IDTYPE_PORTNUM:
+ if ((app_ent->appBitfield & DCBX_APP_ENTRY_SF_MASK) !=
+ DCBX_APP_SF_PORT)
+ return false;
+ break;
+ default:
+ return false;
+ }
+ if (app_ent->app_id != idval)
+ return false;
+
+ return true;
+}
+
+static void bnx2x_admin_app_set_ent(
+ struct bnx2x_admin_priority_app_table *app_ent,
+ u8 idtype, u16 idval, u8 up)
+{
+ app_ent->valid = 1;
+
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+ app_ent->traffic_type = TRAFFIC_TYPE_ETH;
+ break;
+ case DCB_APP_IDTYPE_PORTNUM:
+ app_ent->traffic_type = TRAFFIC_TYPE_PORT;
+ break;
+ default:
+ break; /* never gets here */
+ }
+ app_ent->app_id = idval;
+ app_ent->priority = up;
+}
+
+static bool bnx2x_admin_app_is_equal(
+ struct bnx2x_admin_priority_app_table *app_ent,
+ u8 idtype, u16 idval)
+{
+ if (!app_ent->valid)
+ return false;
+
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+ if (app_ent->traffic_type != TRAFFIC_TYPE_ETH)
+ return false;
+ break;
+ case DCB_APP_IDTYPE_PORTNUM:
+ if (app_ent->traffic_type != TRAFFIC_TYPE_PORT)
+ return false;
+ break;
+ default:
+ return false;
+ }
+ if (app_ent->app_id != idval)
+ return false;
+
+ return true;
+}
+
+static int bnx2x_set_admin_app_up(struct bnx2x *bp, u8 idtype, u16 idval, u8 up)
+{
+ int i, ff;
+
+ /* iterate over the app entries looking for idtype and idval */
+ for (i = 0, ff = -1; i < 4; i++) {
+ struct bnx2x_admin_priority_app_table *app_ent =
+ &bp->dcbx_config_params.admin_priority_app_table[i];
+ if (bnx2x_admin_app_is_equal(app_ent, idtype, idval))
+ break;
+
+ if (ff < 0 && !app_ent->valid)
+ ff = i;
+ }
+ if (i < 4)
+ /* if found overwrite up */
+ bp->dcbx_config_params.
+ admin_priority_app_table[i].priority = up;
+ else if (ff >= 0)
+ /* not found use first-free */
+ bnx2x_admin_app_set_ent(
+ &bp->dcbx_config_params.admin_priority_app_table[ff],
+ idtype, idval, up);
+ else
+ /* app table is full */
+ return -EBUSY;
+
+ /* up configured, if not 0 make sure feature is enabled */
+ if (up)
+ bp->dcbx_config_params.admin_application_priority_tx_enable = 1;
+
+ return 0;
+}
+
+static u8 bnx2x_dcbnl_set_app_up(struct net_device *netdev, u8 idtype,
+ u16 idval, u8 up)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+
+ DP(NETIF_MSG_LINK, "app_type %d, app_id %x, prio bitmap %d\n",
+ idtype, idval, up);
+
+ if (!bnx2x_dcbnl_set_valid(bp))
+ return -EINVAL;
+
+ /* verify idtype */
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+ case DCB_APP_IDTYPE_PORTNUM:
+ break;
+ default:
+ return -EINVAL;
+ }
+ return bnx2x_set_admin_app_up(bp, idtype, idval, up);
+}
+
+static u8 bnx2x_dcbnl_get_app_up(struct net_device *netdev, u8 idtype,
+ u16 idval)
+{
+ int i;
+ u8 up = 0;
+
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "app_type %d, app_id 0x%x\n", idtype, idval);
+
+ /* iterate over the app entries looking for idtype and idval */
+ for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++)
+ if (bnx2x_app_is_equal(&bp->dcbx_local_feat.app.app_pri_tbl[i],
+ idtype, idval))
+ break;
+
+ if (i < DCBX_MAX_APP_PROTOCOL)
+ /* if found return up */
+ up = bp->dcbx_local_feat.app.app_pri_tbl[i].pri_bitmap;
+ else
+ DP(NETIF_MSG_LINK, "app not found\n");
+
+ return up;
+}
+
+static u8 bnx2x_dcbnl_get_dcbx(struct net_device *netdev)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ u8 state;
+
+ state = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_CEE;
+
+ if (bp->dcbx_enabled == BNX2X_DCBX_ENABLED_ON_NEG_OFF)
+ state |= DCB_CAP_DCBX_STATIC;
+
+ return state;
+}
+
+static u8 bnx2x_dcbnl_set_dcbx(struct net_device *netdev, u8 state)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ DP(NETIF_MSG_LINK, "state = %02x\n", state);
+
+ /* set dcbx mode */
+
+ if ((state & BNX2X_DCBX_CAPS) != state) {
+ BNX2X_ERR("Requested DCBX mode %x is beyond advertised "
+ "capabilities\n", state);
+ return 1;
+ }
+
+ if (bp->dcb_state != BNX2X_DCB_STATE_ON) {
+ BNX2X_ERR("DCB turned off, DCBX configuration is invalid\n");
+ return 1;
+ }
+
+ if (state & DCB_CAP_DCBX_STATIC)
+ bp->dcbx_enabled = BNX2X_DCBX_ENABLED_ON_NEG_OFF;
+ else
+ bp->dcbx_enabled = BNX2X_DCBX_ENABLED_ON_NEG_ON;
+
+ bp->dcbx_mode_uset = true;
+ return 0;
+}
+
+
+static u8 bnx2x_dcbnl_get_featcfg(struct net_device *netdev, int featid,
+ u8 *flags)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ u8 rval = 0;
+
+ DP(NETIF_MSG_LINK, "featid %d\n", featid);
+
+ if (bp->dcb_state) {
+ *flags = 0;
+ switch (featid) {
+ case DCB_FEATCFG_ATTR_PG:
+ if (bp->dcbx_local_feat.ets.enabled)
+ *flags |= DCB_FEATCFG_ENABLE;
+ if (bp->dcbx_error & DCBX_LOCAL_ETS_ERROR)
+ *flags |= DCB_FEATCFG_ERROR;
+ break;
+ case DCB_FEATCFG_ATTR_PFC:
+ if (bp->dcbx_local_feat.pfc.enabled)
+ *flags |= DCB_FEATCFG_ENABLE;
+ if (bp->dcbx_error & (DCBX_LOCAL_PFC_ERROR |
+ DCBX_LOCAL_PFC_MISMATCH))
+ *flags |= DCB_FEATCFG_ERROR;
+ break;
+ case DCB_FEATCFG_ATTR_APP:
+ if (bp->dcbx_local_feat.app.enabled)
+ *flags |= DCB_FEATCFG_ENABLE;
+ if (bp->dcbx_error & (DCBX_LOCAL_APP_ERROR |
+ DCBX_LOCAL_APP_MISMATCH))
+ *flags |= DCB_FEATCFG_ERROR;
+ break;
+ default:
+ rval = -EINVAL;
+ break;
+ }
+ } else
+ rval = -EINVAL;
+
+ return rval;
+}
+
+static u8 bnx2x_dcbnl_set_featcfg(struct net_device *netdev, int featid,
+ u8 flags)
+{
+ struct bnx2x *bp = netdev_priv(netdev);
+ u8 rval = 0;
+
+ DP(NETIF_MSG_LINK, "featid = %d flags = %02x\n", featid, flags);
+
+ /* ignore the 'advertise' flag */
+ if (bnx2x_dcbnl_set_valid(bp)) {
+ switch (featid) {
+ case DCB_FEATCFG_ATTR_PG:
+ bp->dcbx_config_params.admin_ets_enable =
+ flags & DCB_FEATCFG_ENABLE ? 1 : 0;
+ bp->dcbx_config_params.admin_ets_willing =
+ flags & DCB_FEATCFG_WILLING ? 1 : 0;
+ break;
+ case DCB_FEATCFG_ATTR_PFC:
+ bp->dcbx_config_params.admin_pfc_enable =
+ flags & DCB_FEATCFG_ENABLE ? 1 : 0;
+ bp->dcbx_config_params.admin_pfc_willing =
+ flags & DCB_FEATCFG_WILLING ? 1 : 0;
+ break;
+ case DCB_FEATCFG_ATTR_APP:
+ /* ignore enable, always enabled */
+ bp->dcbx_config_params.admin_app_priority_willing =
+ flags & DCB_FEATCFG_WILLING ? 1 : 0;
+ break;
+ default:
+ rval = -EINVAL;
+ break;
+ }
+ } else
+ rval = -EINVAL;
+
+ return rval;
+}
+
+const struct dcbnl_rtnl_ops bnx2x_dcbnl_ops = {
+ .getstate = bnx2x_dcbnl_get_state,
+ .setstate = bnx2x_dcbnl_set_state,
+ .getpermhwaddr = bnx2x_dcbnl_get_perm_hw_addr,
+ .setpgtccfgtx = bnx2x_dcbnl_set_pg_tccfg_tx,
+ .setpgbwgcfgtx = bnx2x_dcbnl_set_pg_bwgcfg_tx,
+ .setpgtccfgrx = bnx2x_dcbnl_set_pg_tccfg_rx,
+ .setpgbwgcfgrx = bnx2x_dcbnl_set_pg_bwgcfg_rx,
+ .getpgtccfgtx = bnx2x_dcbnl_get_pg_tccfg_tx,
+ .getpgbwgcfgtx = bnx2x_dcbnl_get_pg_bwgcfg_tx,
+ .getpgtccfgrx = bnx2x_dcbnl_get_pg_tccfg_rx,
+ .getpgbwgcfgrx = bnx2x_dcbnl_get_pg_bwgcfg_rx,
+ .setpfccfg = bnx2x_dcbnl_set_pfc_cfg,
+ .getpfccfg = bnx2x_dcbnl_get_pfc_cfg,
+ .setall = bnx2x_dcbnl_set_all,
+ .getcap = bnx2x_dcbnl_get_cap,
+ .getnumtcs = bnx2x_dcbnl_get_numtcs,
+ .setnumtcs = bnx2x_dcbnl_set_numtcs,
+ .getpfcstate = bnx2x_dcbnl_get_pfc_state,
+ .setpfcstate = bnx2x_dcbnl_set_pfc_state,
+ .getapp = bnx2x_dcbnl_get_app_up,
+ .setapp = bnx2x_dcbnl_set_app_up,
+ .getdcbx = bnx2x_dcbnl_get_dcbx,
+ .setdcbx = bnx2x_dcbnl_set_dcbx,
+ .getfeatcfg = bnx2x_dcbnl_get_featcfg,
+ .setfeatcfg = bnx2x_dcbnl_set_featcfg,
+};
+
+#endif /* BCM_DCB */
diff --git a/drivers/net/bnx2x/bnx2x_dcb.h b/drivers/net/bnx2x/bnx2x_dcb.h
index 8dea56b..f650f98 100644
--- a/drivers/net/bnx2x/bnx2x_dcb.h
+++ b/drivers/net/bnx2x/bnx2x_dcb.h
@@ -51,7 +51,6 @@ struct bnx2x_dcbx_pfc_params {
};
struct bnx2x_dcbx_port_params {
- u32 dcbx_enabled;
struct bnx2x_dcbx_pfc_params pfc;
struct bnx2x_dcbx_pg_params ets;
struct bnx2x_dcbx_app_params app;
@@ -88,8 +87,6 @@ struct bnx2x_admin_priority_app_table {
* DCBX protocol configuration parameters.
******************************************************************************/
struct bnx2x_config_dcbx_params {
- u32 dcb_enable;
- u32 admin_dcbx_enable;
u32 overwrite_settings;
u32 admin_dcbx_version;
u32 admin_ets_enable;
@@ -182,6 +179,7 @@ struct bnx2x;
void bnx2x_dcb_init_intmem_pfc(struct bnx2x *bp);
void bnx2x_dcbx_update(struct work_struct *work);
void bnx2x_dcbx_init_params(struct bnx2x *bp);
+void bnx2x_dcbx_set_state(struct bnx2x *bp, bool dcb_on, u32 dcbx_enabled);
enum {
BNX2X_DCBX_STATE_NEG_RECEIVED = 0x1,
@@ -190,4 +188,9 @@ enum {
};
void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state);
+/* DCB netlink */
+#ifdef BCM_DCB
+extern const struct dcbnl_rtnl_ops bnx2x_dcbnl_ops;
+#endif /* BCM_DCB */
+
#endif /* BNX2X_DCB_H */
diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c
index cf54427..489a551 100644
--- a/drivers/net/bnx2x/bnx2x_main.c
+++ b/drivers/net/bnx2x/bnx2x_main.c
@@ -3107,7 +3107,8 @@ static inline void bnx2x_attn_int_deasserted3(struct bnx2x *bp, u32 attn)
bnx2x_pmf_update(bp);
if (bp->port.pmf &&
- (val & DRV_STATUS_DCBX_NEGOTIATION_RESULTS))
+ (val & DRV_STATUS_DCBX_NEGOTIATION_RESULTS) &&
+ bp->dcbx_enabled > 0)
/* start dcbx state machine */
bnx2x_dcbx_set_params(bp,
BNX2X_DCBX_STATE_NEG_RECEIVED);
@@ -8795,6 +8796,7 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
bp->timer.data = (unsigned long) bp;
bp->timer.function = bnx2x_timer;
+ bnx2x_dcbx_set_state(bp, true, BNX2X_DCBX_ENABLED_ON_NEG_ON);
bnx2x_dcbx_init_params(bp);
return rc;
@@ -9146,6 +9148,10 @@ static int __devinit bnx2x_init_dev(struct pci_dev *pdev,
dev->vlan_features |= (NETIF_F_TSO | NETIF_F_TSO_ECN);
dev->vlan_features |= NETIF_F_TSO6;
+#ifdef BCM_DCB
+ dev->dcbnl_ops = &bnx2x_dcbnl_ops;
+#endif
+
/* get_port_hwinfo() will set prtad and mmds properly */
bp->mdio.prtad = MDIO_PRTAD_NONE;
bp->mdio.mmds = 0;
--
1.7.1
^ permalink raw reply related
* Re: linux-next: Tree for December 29 (netfilter build errors)
From: Sedat Dilek @ 2010-12-30 16:47 UTC (permalink / raw)
To: Changli Gao
Cc: Randy Dunlap, Stephen Rothwell, netfilter-devel, linux-next, LKML,
netdev
In-Reply-To: <AANLkTin8Zc4wkx9BjD0vJSNdne8LVHx=JyeSC2YdKTKH@mail.gmail.com>
On Thu, Dec 30, 2010 at 3:18 AM, Changli Gao <xiaosuo@gmail.com> wrote:
> On Thu, Dec 30, 2010 at 12:53 AM, Randy Dunlap <randy.dunlap@oracle.com> wrote:
>> On Wed, 29 Dec 2010 13:07:00 +1100 Stephen Rothwell wrote:
>>
>>> Hi all,
>>>
>>> Changes since 20101228:
>>
>>
>> In file included from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:22:
>> linux-next-20101229/include/net/netfilter/nf_conntrack.h:94: error: field 'ct_general' has incomplete type
>> linux-next-20101229/include/net/netfilter/nf_conntrack.h: In function 'nf_ct_get':
>> linux-next-20101229/include/net/netfilter/nf_conntrack.h:174: error: 'const struct sk_buff' has no member named 'nfct'
>> linux-next-20101229/include/net/netfilter/nf_conntrack.h: In function 'nf_ct_put':
>> linux-next-20101229/include/net/netfilter/nf_conntrack.h:181: error: implicit declaration of function 'nf_conntrack_put'
>> CC net/ipv6/exthdrs_core.o
>> In file included from linux-next-20101229/include/net/netfilter/nf_conntrack_core.h:18,
>> from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:26:
>> linux-next-20101229/include/net/netfilter/nf_conntrack_ecache.h: In function 'nf_ct_ecache_ext_add':
>> linux-next-20101229/include/net/netfilter/nf_conntrack_ecache.h:35: error: 'struct net' has no member named 'ct'
>> In file included from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:26:
>> linux-next-20101229/include/net/netfilter/nf_conntrack_core.h: In function 'nf_conntrack_confirm':
>> linux-next-20101229/include/net/netfilter/nf_conntrack_core.h:60: error: 'struct sk_buff' has no member named 'nfct'
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c: In function 'nf_ct6_defrag_user':
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:36: error: 'struct sk_buff' has no member named 'nfct'
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:37: error: implicit declaration of function 'nf_ct_zone'
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:37: error: 'struct sk_buff' has no member named 'nfct'
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c: In function 'ipv6_defrag':
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:60: error: 'struct sk_buff' has no member named 'nfct'
>> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:60: error: 'struct sk_buff' has no member named 'nfct'
>> make[4]: *** [net/ipv6/netfilter/nf_defrag_ipv6_hooks.o] Error 1
>> make[3]: *** [net/ipv6/netfilter] Error 2
>>
>>
>>
>
> This bug has been already fixed in nf-next-2.6:
> http://git.kernel.org/?p=linux/kernel/git/kaber/nf-next-2.6.git;a=commitdiff;h=ae90bdeaeac6b964b7a1e853a90a19f358a9ac20;hp=f1c722295e029eace7960fc687efd5afd67dc555
>
> Thanks.
>
> --
> Regards,
> Changli Gao(xiaosuo@gmail.com)
>
Does not look like the nf-next-2.6 is triggered by linux-next... Does
this tree passes net-next-2.6 and then enters linux-next?
- Sedat -
P.S.:
sd@tbox:/mnt/sdb5/linux-kernel/linux-next$ git pull
git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git
master:nf-next-2.6
remote: Counting objects: 705, done.
remote: Compressing objects: 100% (415/415), done.
remote: Total 545 (delta 475), reused 149 (delta 130)
Receiving objects: 100% (545/545), 88.80 KiB | 47 KiB/s, done.
Resolving deltas: 100% (475/475), completed with 136 local objects.
From git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6
* [new branch] master -> nf-next-2.6
warning: too many files (created: 931 deleted: 428), skipping inexact
rename detection
Auto-merging include/linux/netfilter.h
Auto-merging include/linux/skbuff.h
Auto-merging net/core/skbuff.c
Auto-merging net/ipv6/netfilter/nf_conntrack_reasm.c
Auto-merging net/netfilter/core.c
Auto-merging net/netfilter/ipvs/ip_vs_ctl.c
Auto-merging net/netfilter/ipvs/ip_vs_xmit.c
Merge made by recursive.
include/linux/ip_vs.h | 8 +
include/linux/netfilter.h | 6 +-
include/linux/netfilter/xt_CT.h | 10 +-
include/linux/netfilter/xt_TCPOPTSTRIP.h | 2 +-
include/linux/netfilter/xt_TPROXY.h | 8 +-
include/linux/netfilter/xt_cluster.h | 8 +-
include/linux/netfilter/xt_quota.h | 6 +-
include/linux/netfilter/xt_time.h | 14 +-
include/linux/netfilter/xt_u32.h | 16 +-
include/linux/skbuff.h | 15 +
include/net/ip_vs.h | 25 +-
include/net/netfilter/ipv6/nf_conntrack_ipv6.h | 10 -
include/net/netfilter/ipv6/nf_defrag_ipv6.h | 10 +
include/net/netfilter/nf_conntrack.h | 19 +-
include/net/netfilter/nf_conntrack_ecache.h | 12 +-
include/net/netfilter/nf_conntrack_extend.h | 6 +
include/net/netfilter/nf_conntrack_l3proto.h | 2 +-
include/net/netfilter/nf_nat.h | 6 +
include/net/netfilter/nf_nat_core.h | 4 +-
net/core/skbuff.c | 2 +
net/ipv4/netfilter/ipt_LOG.c | 3 +-
.../netfilter/nf_conntrack_l3proto_ipv4_compat.c | 17 +-
net/ipv4/netfilter/nf_nat_amanda.c | 8 +-
net/ipv4/netfilter/nf_nat_core.c | 9 +-
net/ipv6/netfilter/ip6t_LOG.c | 3 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +-
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 8 +-
net/netfilter/core.c | 4 +-
net/netfilter/ipvs/ip_vs_conn.c | 36 +-
net/netfilter/ipvs/ip_vs_core.c | 94 ++-
net/netfilter/ipvs/ip_vs_ctl.c | 36 +-
net/netfilter/ipvs/ip_vs_ftp.c | 5 +-
net/netfilter/ipvs/ip_vs_pe.c | 17 +-
net/netfilter/ipvs/ip_vs_pe_sip.c | 3 +
net/netfilter/ipvs/ip_vs_proto_sctp.c | 11 +-
net/netfilter/ipvs/ip_vs_proto_tcp.c | 10 +-
net/netfilter/ipvs/ip_vs_proto_udp.c | 10 +-
net/netfilter/ipvs/ip_vs_sync.c | 962 +++++++++++++++++---
net/netfilter/ipvs/ip_vs_xmit.c | 26 +-
net/netfilter/nf_conntrack_core.c | 3 +-
net/netfilter/nf_conntrack_expect.c | 25 +-
net/netfilter/nf_conntrack_extend.c | 11 +-
net/netfilter/nf_conntrack_helper.c | 10 +-
net/netfilter/nf_conntrack_netlink.c | 1 +
net/netfilter/nf_conntrack_proto.c | 24 +-
net/netfilter/nf_conntrack_proto_dccp.c | 3 +
net/netfilter/nf_conntrack_proto_sctp.c | 1 +
net/netfilter/nf_conntrack_proto_tcp.c | 14 +-
net/netfilter/nf_conntrack_standalone.c | 9 +-
net/netfilter/nf_log.c | 6 +-
net/netfilter/nf_queue.c | 18 +-
net/netfilter/nfnetlink_log.c | 6 +-
net/netfilter/xt_CLASSIFY.c | 36 +-
net/netfilter/xt_NFQUEUE.c | 6 +-
54 files changed, 1258 insertions(+), 368 deletions(-)
sd@tbox:/mnt/sdb5/linux-kernel/linux-next$
^ permalink raw reply
* Re: linux-next: Tree for December 29 (netfilter build errors)
From: Eric Dumazet @ 2010-12-30 17:07 UTC (permalink / raw)
To: sedat.dilek
Cc: Changli Gao, Randy Dunlap, Stephen Rothwell, netfilter-devel,
linux-next, LKML, netdev
In-Reply-To: <AANLkTikPbKOQseJ8qfoSqv4XWgH5fjbg488jd6_Xv22E@mail.gmail.com>
Le jeudi 30 décembre 2010 à 17:47 +0100, Sedat Dilek a écrit :
> On Thu, Dec 30, 2010 at 3:18 AM, Changli Gao <xiaosuo@gmail.com> wrote:
> > On Thu, Dec 30, 2010 at 12:53 AM, Randy Dunlap <randy.dunlap@oracle.com> wrote:
> >> On Wed, 29 Dec 2010 13:07:00 +1100 Stephen Rothwell wrote:
> >>
> >>> Hi all,
> >>>
> >>> Changes since 20101228:
> >>
> >>
> >> In file included from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:22:
> >> linux-next-20101229/include/net/netfilter/nf_conntrack.h:94: error: field 'ct_general' has incomplete type
> >> linux-next-20101229/include/net/netfilter/nf_conntrack.h: In function 'nf_ct_get':
> >> linux-next-20101229/include/net/netfilter/nf_conntrack.h:174: error: 'const struct sk_buff' has no member named 'nfct'
> >> linux-next-20101229/include/net/netfilter/nf_conntrack.h: In function 'nf_ct_put':
> >> linux-next-20101229/include/net/netfilter/nf_conntrack.h:181: error: implicit declaration of function 'nf_conntrack_put'
> >> CC net/ipv6/exthdrs_core.o
> >> In file included from linux-next-20101229/include/net/netfilter/nf_conntrack_core.h:18,
> >> from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:26:
> >> linux-next-20101229/include/net/netfilter/nf_conntrack_ecache.h: In function 'nf_ct_ecache_ext_add':
> >> linux-next-20101229/include/net/netfilter/nf_conntrack_ecache.h:35: error: 'struct net' has no member named 'ct'
> >> In file included from linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:26:
> >> linux-next-20101229/include/net/netfilter/nf_conntrack_core.h: In function 'nf_conntrack_confirm':
> >> linux-next-20101229/include/net/netfilter/nf_conntrack_core.h:60: error: 'struct sk_buff' has no member named 'nfct'
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c: In function 'nf_ct6_defrag_user':
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:36: error: 'struct sk_buff' has no member named 'nfct'
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:37: error: implicit declaration of function 'nf_ct_zone'
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:37: error: 'struct sk_buff' has no member named 'nfct'
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c: In function 'ipv6_defrag':
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:60: error: 'struct sk_buff' has no member named 'nfct'
> >> linux-next-20101229/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:60: error: 'struct sk_buff' has no member named 'nfct'
> >> make[4]: *** [net/ipv6/netfilter/nf_defrag_ipv6_hooks.o] Error 1
> >> make[3]: *** [net/ipv6/netfilter] Error 2
> >>
> >>
> >>
> >
> > This bug has been already fixed in nf-next-2.6:
> > http://git.kernel.org/?p=linux/kernel/git/kaber/nf-next-2.6.git;a=commitdiff;h=ae90bdeaeac6b964b7a1e853a90a19f358a9ac20;hp=f1c722295e029eace7960fc687efd5afd67dc555
> >
> > Thanks.
> >
> > --
> > Regards,
> > Changli Gao(xiaosuo@gmail.com)
> >
>
> Does not look like the nf-next-2.6 is triggered by linux-next... Does
> this tree passes net-next-2.6 and then enters linux-next?
>
Yes it does. Patrick is probably too busy right now to push fixes to
David.
^ permalink raw reply
* [PATCH/RFC] Re: Compilation of pktgen fails for ARCH=um
From: Randy Dunlap @ 2010-12-30 17:39 UTC (permalink / raw)
To: christoph.paasch; +Cc: netdev, linux-arch
In-Reply-To: <201012301133.14524.christoph.paasch@uclouvain.be>
On Thu, 30 Dec 2010 11:33:14 +0100 Christoph Paasch wrote:
> Hi,
>
> compiling the packet generator (NET_PKTGEN) for ARCH=um does not work.
>
> Since commit 43d28b6515a6ea580a198df3e253e88236f08978 (pktgen: increasing
> transmission granularity), function spin(...) uses ndelay(...), which is not
> implemented for uml.
>
> Should pktgen be disabled for uml?
> Or should ndelay be an empty macro? (in arch/um/include/asm/delay.h)
or ndelay() in arch/um/include/asm/delay.y can be removed completely
and then the default implementation of ndelay() will be used from
include/linux/delay.h.
This builds cleanly, but I don't know how well it would work.
---
From: Randy Dunlap <randy.dunlap@oracle.com>
Allow uml to use the default implementation of ndelay() from
<linux/delay.h>. Fixes build error:
net/built-in.o: In function `spin':
pktgen.c:(.text+0x27391): undefined reference to `__unimplemented_ndelay'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
---
arch/um/include/asm/delay.h | 5 -----
1 file changed, 5 deletions(-)
--- linux-next-20101214.orig/arch/um/include/asm/delay.h
+++ linux-next-20101214/arch/um/include/asm/delay.h
@@ -12,9 +12,4 @@ extern void __delay(unsigned long loops)
#define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \
__bad_udelay() : __udelay(n))
-/* It appears that ndelay is not used at all for UML, and has never been
- * implemented. */
-extern void __unimplemented_ndelay(void);
-#define ndelay(n) __unimplemented_ndelay()
-
#endif
^ permalink raw reply
* Re: [PATCH net-next-2.6] sfq: fix slot_dequeue_head()
From: Jarek Poplawski @ 2010-12-30 17:49 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, netdev
In-Reply-To: <1293721368.7150.307.camel@edumazet-laptop>
On Thu, Dec 30, 2010 at 04:02:48PM +0100, Eric Dumazet wrote:
> Le mercredi 22 décembre 2010 ?? 07:32 +0000, Jarek Poplawski a écrit :
> > > Also, slot_dequeue_tail() should make sure slot skb chain is correctly
> > > terminated, or sfq_dump_class_stats() can access freed skbs.
> >
> > ...and a good hint for code reusing ;-)
>
> Yes, and of course same fix is needed in slot_dequeue_head(), as further
> testing on my side made it pretty clear.
>
> I was adding possibility to have more packets queued in SFQ (more
> packets than max number of flows) and got unexpected crashes.
>
> Reverting to net-next-2.6, I still got crashes. Oops.
>
> [PATCH net-next-2.6] sfq: fix slot_dequeue_head()
>
> slot_dequeue_head() should make sure slot skb chain is correct in both
> ways, or we can crash if all possible flows are in use.
Nice scenario ;-) Of course, it's easy to guess I looked for something
like this after your previous fix and missed that :-| Btw, it looks
like slot_queue_init() could go back to sfq_init() now.
Jarek P.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> Cc: Jarek Poplawski <jarkao2@gmail.com>
> ---
> net/sched/sch_sfq.c | 1 +
> 1 files changed, 1 insertion(+)
>
> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
> index 6a2f88f..3977e56 100644
> --- a/net/sched/sch_sfq.c
> +++ b/net/sched/sch_sfq.c
> @@ -292,6 +292,7 @@ static inline struct sk_buff *slot_dequeue_head(struct sfq_slot *slot)
> struct sk_buff *skb = slot->skblist_next;
>
> slot->skblist_next = skb->next;
> + skb->next->prev = (struct sk_buff *)slot;
> skb->next = skb->prev = NULL;
> return skb;
> }
>
>
^ permalink raw reply
* Re: [PATCH net-2.6] bridge: fix br_multicast_ipv6_rcv for paged skbs
From: Stephen Hemminger @ 2010-12-30 18:46 UTC (permalink / raw)
To: Tomas Winkler; +Cc: davem, netdev, linux-wireless, Johannes Berg
In-Reply-To: <1293708753-17728-1-git-send-email-tomas.winkler@intel.com>
On Thu, 30 Dec 2010 13:32:33 +0200
Tomas Winkler <tomas.winkler@intel.com> wrote:
> use pskb_may_pull to access header correctly for paged skbs
>
> the pskb_may_pull ideom is used ipv6 heder parsing
> but omitted int the bridge code
>
> this fixes bug https://bugzilla.kernel.org/show_bug.cgi?id=25202
>
> Dec 15 14:36:40 User-PC hostapd: wlan0: STA 00:15:00:60:5d:34 IEEE 802.11: authenticated
> Dec 15 14:36:40 User-PC hostapd: wlan0: STA 00:15:00:60:5d:34 IEEE 802.11: associated (aid 2)
> Dec 15 14:36:40 User-PC hostapd: wlan0: STA 00:15:00:60:5d:34 RADIUS: starting accounting session 4D0608A3-00000005
> Dec 15 14:36:41 User-PC kernel: [175576.120287] ------------[ cut here ]------------
> Dec 15 14:36:41 User-PC kernel: [175576.120452] kernel BUG at include/linux/skbuff.h:1178!
> Dec 15 14:36:41 User-PC kernel: [175576.120609] invalid opcode: 0000 [#1] SMP
> Dec 15 14:36:41 User-PC kernel: [175576.120749] last sysfs file: /sys/devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/uevent
> Dec 15 14:36:41 User-PC kernel: [175576.121035] Modules linked in: oprofile binfmt_misc bridge stp llc parport_pc ppdev arc4 iwlagn snd_hda_codec_realtek iwlcore i915 snd_hda_intel mac80211 joydev snd_hda_codec snd_hwdep snd_pcm snd_seq_midi drm_kms_helper snd_rawmidi drm snd_seq_midi_event snd_seq snd_timer snd_seq_device cfg80211 eeepc_wmi usbhid psmouse intel_agp i2c_algo_bit intel_gtt uvcvideo agpgart videodev sparse_keymap snd shpchp v4l1_compat lp hid video serio_raw soundcore output snd_page_alloc ahci libahci atl1c
> Dec 15 14:36:41 User-PC kernel: [175576.122712]
> Dec 15 14:36:41 User-PC kernel: [175576.122769] Pid: 0, comm: kworker/0:0 Tainted: G W 2.6.37-rc5-wl+ #3 1015PE/1016P
> Dec 15 14:36:41 User-PC kernel: [175576.123012] EIP: 0060:[<f83edd65>] EFLAGS: 00010283 CPU: 1
> Dec 15 14:36:41 User-PC kernel: [175576.123193] EIP is at br_multicast_rcv+0xc95/0xe1c [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.123362] EAX: 0000001c EBX: f5626318 ECX: 00000000 EDX: 00000000
> Dec 15 14:36:41 User-PC kernel: [175576.123550] ESI: ec512262 EDI: f5626180 EBP: f60b5ca0 ESP: f60b5bd8
> Dec 15 14:36:41 User-PC kernel: [175576.123737] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
> Dec 15 14:36:41 User-PC kernel: [175576.123902] Process kworker/0:0 (pid: 0, ti=f60b4000 task=f60a8000 task.ti=f60b0000)
> Dec 15 14:36:41 User-PC kernel: [175576.124137] Stack:
> Dec 15 14:36:41 User-PC kernel: [175576.124181] ec556500 f6d06800 f60b5be8 c01087d8 ec512262 00000030 00000024 f5626180
> Dec 15 14:36:41 User-PC kernel: [175576.124181] f572c200 ef463440 f5626300 3affffff f6d06dd0 e60766a4 000000c4 f6d06860
> Dec 15 14:36:41 User-PC kernel: [175576.124181] ffffffff ec55652c 00000001 f6d06844 f60b5c64 c0138264 c016e451 c013e47d
> Dec 15 14:36:41 User-PC kernel: [175576.124181] Call Trace:
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c01087d8>] ? sched_clock+0x8/0x10
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0138264>] ? enqueue_entity+0x174/0x440
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c016e451>] ? sched_clock_cpu+0x131/0x190
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c013e47d>] ? select_task_rq_fair+0x2ad/0x730
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0524fc1>] ? nf_iterate+0x71/0x90
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f83e4914>] ? br_handle_frame_finish+0x184/0x220 [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f83e4790>] ? br_handle_frame_finish+0x0/0x220 [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f83e46e9>] ? br_handle_frame+0x189/0x230 [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f83e4790>] ? br_handle_frame_finish+0x0/0x220 [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f83e4560>] ? br_handle_frame+0x0/0x230 [bridge]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c04ff026>] ? __netif_receive_skb+0x1b6/0x5b0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c04f7a30>] ? skb_copy_bits+0x110/0x210
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0503a7f>] ? netif_receive_skb+0x6f/0x80
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f82cb74c>] ? ieee80211_deliver_skb+0x8c/0x1a0 [mac80211]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f82cc836>] ? ieee80211_rx_handlers+0xeb6/0x1aa0 [mac80211]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c04ff1f0>] ? __netif_receive_skb+0x380/0x5b0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c016e242>] ? sched_clock_local+0xb2/0x190
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c012b688>] ? default_spin_lock_flags+0x8/0x10
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c05d83df>] ? _raw_spin_lock_irqsave+0x2f/0x50
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f82cd621>] ? ieee80211_prepare_and_rx_handle+0x201/0xa90 [mac80211]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f82ce154>] ? ieee80211_rx+0x2a4/0x830 [mac80211]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f815a8d6>] ? iwl_update_stats+0xa6/0x2a0 [iwlcore]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f8499212>] ? iwlagn_rx_reply_rx+0x292/0x3b0 [iwlagn]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c05d83df>] ? _raw_spin_lock_irqsave+0x2f/0x50
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f8483697>] ? iwl_rx_handle+0xe7/0x350 [iwlagn]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<f8486ab7>] ? iwl_irq_tasklet+0xf7/0x5c0 [iwlagn]
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c01aece1>] ? __rcu_process_callbacks+0x201/0x2d0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0150d05>] ? tasklet_action+0xc5/0x100
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0150a07>] ? __do_softirq+0x97/0x1d0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c05d910c>] ? nmi_stack_correct+0x2f/0x34
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0150970>] ? __do_softirq+0x0/0x1d0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] <IRQ>
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c01508f5>] ? irq_exit+0x65/0x70
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c05df062>] ? do_IRQ+0x52/0xc0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c01036b0>] ? common_interrupt+0x30/0x38
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c03a1fc2>] ? intel_idle+0xc2/0x160
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c04daebb>] ? cpuidle_idle_call+0x6b/0x100
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c0101dea>] ? cpu_idle+0x8a/0xf0
> Dec 15 14:36:41 User-PC kernel: [175576.124181] [<c05d2702>] ? start_secondary+0x1e8/0x1ee
>
> Cc:YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
> Cc: Johannes Berg <johannes@sipsolutions.net>
> Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
> ---
> net/bridge/br_multicast.c | 4 ++++
> 1 files changed, 4 insertions(+), 0 deletions(-)
>
> diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
> index f19e347..074c478 100644
> --- a/net/bridge/br_multicast.c
> +++ b/net/bridge/br_multicast.c
> @@ -1464,6 +1464,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
> if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
> return 0;
>
> + if (!pskb_may_pull(skb,
> + (skb_network_header(skb) + offset + 1 - skb->data)))
> + return 0;
> +
> /* Okay, we found ICMPv6 header */
> skb2 = skb_clone(skb, GFP_ATOMIC);
> if (!skb2)
This doesn't look correct. The calculation of the offset doesn't look correct.
Just following the skb_clone(), the skb_pull value is "offset".
Also, the other checks return -EINVAL for incorrectly formed packet.
--- a/net/bridge/br_multicast.c 2010-12-30 10:29:58.579510488 -0800
+++ b/net/bridge/br_multicast.c 2010-12-30 10:43:27.273386691 -0800
@@ -1464,6 +1464,9 @@ static int br_multicast_ipv6_rcv(struct
if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
return 0;
+ if (!pskb_may_pull(skb, offset))
+ return -EINVAL;
+
/* Okay, we found ICMPv6 header */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
--
^ permalink raw reply
* Re: [PATCH net-2.6] bridge: fix br_multicast_ipv6_rcv for paged skbs
From: Johannes Berg @ 2010-12-30 18:52 UTC (permalink / raw)
To: Stephen Hemminger
Cc: Tomas Winkler, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20101230104656.6c5a4b4e@nehalam>
On Thu, 2010-12-30 at 10:46 -0800, Stephen Hemminger wrote:
> This doesn't look correct. The calculation of the offset doesn't look correct.
> Just following the skb_clone(), the skb_pull value is "offset".
> Also, the other checks return -EINVAL for incorrectly formed packet.
>
> --- a/net/bridge/br_multicast.c 2010-12-30 10:29:58.579510488 -0800
> +++ b/net/bridge/br_multicast.c 2010-12-30 10:43:27.273386691 -0800
> @@ -1464,6 +1464,9 @@ static int br_multicast_ipv6_rcv(struct
> if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
> return 0;
>
> + if (!pskb_may_pull(skb, offset))
> + return -EINVAL;
> +
> /* Okay, we found ICMPv6 header */
> skb2 = skb_clone(skb, GFP_ATOMIC);
> if (!skb2)
Wouldn't that make more sense after the clone anyway? But if you look at
my email, you'll find that there's potentially, and conditionally, more
stuff that will be read from the skb's header, which hasn't necessarily
been pulled in, so I think this still won't fix all the issues.
Seeing how this only affects some ICMPv6 packets, maybe we should just
use skb_copy() instead?
johannes
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH] skge: Do not use legacy PCI power management
From: Stephen Hemminger @ 2010-12-30 18:52 UTC (permalink / raw)
To: Rafael J. Wysocki; +Cc: netdev, David Miller, Linux-pm mailing list
In-Reply-To: <201012261944.32517.rjw@sisk.pl>
The skge driver used the legacy PCI power management, and did its
own PCI callbacks. Use the same code model as Rafael's changes to
sky2. Let the PCI subsystem take care of all the PCI-specific aspects of
device handling during system power transitions.
Compile tested only (so far).
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/skge.c 2010-12-30 10:19:01.191095951 -0800
+++ b/drivers/net/skge.c 2010-12-30 10:49:30.780295215 -0800
@@ -4044,53 +4044,40 @@ static void __devexit skge_remove(struct
}
#ifdef CONFIG_PM
-static int skge_suspend(struct pci_dev *pdev, pm_message_t state)
+static int skge_suspend(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct skge_hw *hw = pci_get_drvdata(pdev);
- int i, err, wol = 0;
+ int i;
if (!hw)
return 0;
- err = pci_save_state(pdev);
- if (err)
- return err;
-
for (i = 0; i < hw->ports; i++) {
struct net_device *dev = hw->dev[i];
struct skge_port *skge = netdev_priv(dev);
if (netif_running(dev))
skge_down(dev);
+
if (skge->wol)
skge_wol_init(skge);
-
- wol |= skge->wol;
}
skge_write32(hw, B0_IMSK, 0);
- pci_prepare_to_sleep(pdev);
-
return 0;
}
-static int skge_resume(struct pci_dev *pdev)
+static int skge_resume(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct skge_hw *hw = pci_get_drvdata(pdev);
int i, err;
if (!hw)
return 0;
- err = pci_back_from_sleep(pdev);
- if (err)
- goto out;
-
- err = pci_restore_state(pdev);
- if (err)
- goto out;
-
err = skge_reset(hw);
if (err)
goto out;
@@ -4111,12 +4098,19 @@ static int skge_resume(struct pci_dev *p
out:
return err;
}
+
+static SIMPLE_DEV_PM_OPS(skge_pm_ops, skge_suspend, skge_resume);
+#define SKGE_PM_OPS (&skge_pm_ops)
+
+#else
+
+#define SKGE_PM_OPS NULL
#endif
static void skge_shutdown(struct pci_dev *pdev)
{
struct skge_hw *hw = pci_get_drvdata(pdev);
- int i, wol = 0;
+ int i;
if (!hw)
return;
@@ -4127,15 +4121,10 @@ static void skge_shutdown(struct pci_dev
if (skge->wol)
skge_wol_init(skge);
- wol |= skge->wol;
}
- if (pci_enable_wake(pdev, PCI_D3cold, wol))
- pci_enable_wake(pdev, PCI_D3hot, wol);
-
- pci_disable_device(pdev);
+ pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev));
pci_set_power_state(pdev, PCI_D3hot);
-
}
static struct pci_driver skge_driver = {
@@ -4143,11 +4132,8 @@ static struct pci_driver skge_driver = {
.id_table = skge_id_table,
.probe = skge_probe,
.remove = __devexit_p(skge_remove),
-#ifdef CONFIG_PM
- .suspend = skge_suspend,
- .resume = skge_resume,
-#endif
.shutdown = skge_shutdown,
+ .driver.pm = SKGE_PM_OPS,
};
static struct dmi_system_id skge_32bit_dma_boards[] = {
^ permalink raw reply
* Re: [net-next-2.6 PATCH v2 1/4] dcbnl: adding DCBX engine capability
From: John Fastabend @ 2010-12-30 18:54 UTC (permalink / raw)
To: Shmulik Ravid
Cc: davem@davemloft.net, Eilon Greenstein, Liu, Lucy,
netdev@vger.kernel.org
In-Reply-To: <1293726408.29378.92.camel@lb-tlvb-shmulik.il.broadcom.com>
On 12/30/2010 8:26 AM, Shmulik Ravid wrote:
> Adding an optional DCBX capability and a pair for get-set routines for
> setting the device DCBX mode. The DCBX capability is a bit field of
> supported attributes. The user is expected to set the DCBX mode with a
> subset of the advertised attributes.
>
> This patch is dependent on the following patches:
> [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
> [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
> [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
>
> Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
> ---
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Thanks for doing this Shmulik.
^ permalink raw reply
* Re: [net-next-2.6 PATCH v2 2/4] dcbnl: adding DCBX feature flags get-set
From: John Fastabend @ 2010-12-30 19:05 UTC (permalink / raw)
To: Shmulik Ravid
Cc: davem@davemloft.net, Eilon Greenstein, Liu, Lucy,
netdev@vger.kernel.org
In-Reply-To: <1293726415.29378.93.camel@lb-tlvb-shmulik.il.broadcom.com>
On 12/30/2010 8:26 AM, Shmulik Ravid wrote:
> Adding a pair of set-get routines to dcbnl for setting the negotiation
> flags of the various DCB features. Conforms to the CEE flavor of DCBX
> The user sets these flags (enable, advertise, willing) for each feature
> to be used by the DCBX engine. The 'get' routine returns which of the
> features is enabled after the negotiation.
>
> This patch is dependent on the following patches:
> [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
> [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
> [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
>
> Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
> ---
[...]
One more nit ;)
> +
> + ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
> + dcbnl_featcfg_nest);
> + if (ret) {
> + ret = -EINVAL;
> + goto err_out;
> + }
Why do you set EINVAL here if you use the returned error code from nla_parse_nested you get a more descriptive error. See ./lib/nlattr.c:nla_parse()/validate_nla().
[...]
> +static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb,
> + u32 pid, u32 seq, u16 flags)
> +{
> + struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1];
> + int ret = -EINVAL;
> + u8 value;
> + int i;
> +
> + if (!tb[DCB_ATTR_FEATCFG] || !netdev->dcbnl_ops->setfeatcfg)
> + return ret;
> +
> + ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
> + dcbnl_featcfg_nest);
> +
> + if (ret) {
> + ret = -EINVAL;
> + goto err;
> + }
Same here.
Thanks,
John.
^ permalink raw reply
* Re: [PATCH net-2.6] bridge: fix br_multicast_ipv6_rcv for paged skbs
From: Stephen Hemminger @ 2010-12-30 19:06 UTC (permalink / raw)
To: Johannes Berg
Cc: Tomas Winkler, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1293735134.21956.1.camel-8upI4CBIZJIJvtFkdXX2HixXY32XiHfO@public.gmane.org>
On Thu, 30 Dec 2010 19:52:14 +0100
Johannes Berg <johannes-cdvu00un1VgdHxzADdlk8Q@public.gmane.org> wrote:
> On Thu, 2010-12-30 at 10:46 -0800, Stephen Hemminger wrote:
>
> > This doesn't look correct. The calculation of the offset doesn't look correct.
> > Just following the skb_clone(), the skb_pull value is "offset".
> > Also, the other checks return -EINVAL for incorrectly formed packet.
> >
> > --- a/net/bridge/br_multicast.c 2010-12-30 10:29:58.579510488 -0800
> > +++ b/net/bridge/br_multicast.c 2010-12-30 10:43:27.273386691 -0800
> > @@ -1464,6 +1464,9 @@ static int br_multicast_ipv6_rcv(struct
> > if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
> > return 0;
> >
> > + if (!pskb_may_pull(skb, offset))
> > + return -EINVAL;
> > +
> > /* Okay, we found ICMPv6 header */
> > skb2 = skb_clone(skb, GFP_ATOMIC);
> > if (!skb2)
>
> Wouldn't that make more sense after the clone anyway? But if you look at
> my email, you'll find that there's potentially, and conditionally, more
> stuff that will be read from the skb's header, which hasn't necessarily
> been pulled in, so I think this still won't fix all the issues.
>
> Seeing how this only affects some ICMPv6 packets, maybe we should just
> use skb_copy() instead?
It comes out cleaner, and the check can be simplified.
--- a/net/bridge/br_multicast.c 2010-12-30 10:47:12.031733855 -0800
+++ b/net/bridge/br_multicast.c 2010-12-30 11:00:12.135801266 -0800
@@ -1465,19 +1465,19 @@ static int br_multicast_ipv6_rcv(struct
return 0;
/* Okay, we found ICMPv6 header */
- skb2 = skb_clone(skb, GFP_ATOMIC);
+ skb2 = skb_copy(skb, GFP_ATOMIC);
if (!skb2)
return -ENOMEM;
+ err = -EINVAL;
+ if (skb2->len < offset + sizeof(*icmp6h))
+ goto out;
+
len -= offset - skb_network_offset(skb2);
__skb_pull(skb2, offset);
skb_reset_transport_header(skb2);
- err = -EINVAL;
- if (!pskb_may_pull(skb2, sizeof(*icmp6h)))
- goto out;
^ permalink raw reply
* Re: [net-next-2.6 PATCH v2 1/4] dcbnl: adding DCBX engine capability
From: John Fastabend @ 2010-12-30 19:09 UTC (permalink / raw)
To: Shmulik Ravid
Cc: davem@davemloft.net, Eilon Greenstein, Liu, Lucy,
netdev@vger.kernel.org
In-Reply-To: <4D1CD560.3000609@intel.com>
On 12/30/2010 10:54 AM, John Fastabend wrote:
> On 12/30/2010 8:26 AM, Shmulik Ravid wrote:
>> Adding an optional DCBX capability and a pair for get-set routines for
>> setting the device DCBX mode. The DCBX capability is a bit field of
>> supported attributes. The user is expected to set the DCBX mode with a
>> subset of the advertised attributes.
>>
>> This patch is dependent on the following patches:
>> [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
>> [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
>> [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
>>
>> Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
>> ---
>
> Acked-by: John Fastabend <john.r.fastabend@intel.com>
>
> Thanks for doing this Shmulik.
>
Sorry missed this on my first pass.
>
> +/* DCBX configuration */
> +static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb,
> + u32 pid, u32 seq, u16 flags)
> +{
> + int ret = -EINVAL;
> +
> + if (!netdev->dcbnl_ops->getdcbx)
> + return ret;
I think we should actually return -EOPNOTSUPP here.
> +
> + ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB,
> + DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags);
> +
> + return ret;
> +}
> +
^ permalink raw reply
* Re: [net-next-2.6 PATCH v2 4/4] dcbnl: cleanup
From: John Fastabend @ 2010-12-30 19:17 UTC (permalink / raw)
To: Shmulik Ravid
Cc: davem@davemloft.net, Eilon Greenstein, Liu, Lucy,
netdev@vger.kernel.org
In-Reply-To: <1293726430.29378.95.camel@lb-tlvb-shmulik.il.broadcom.com>
On 12/30/2010 8:27 AM, Shmulik Ravid wrote:
> A couple of small cleanups for patches:
> [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes
> [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers
> [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers
>
> Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
> ---
Good catch, thanks a lot. I will roll this into my patch and push a v2 so that we don't introduce a known bug. Of course I'll give you credit.
Thanks,
John.
> net/dcb/dcbnl.c | 6 ++++--
> 1 files changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
> index b387816..ff3c12d 100644
> --- a/net/dcb/dcbnl.c
> +++ b/net/dcb/dcbnl.c
> @@ -1626,8 +1626,10 @@ u8 dcb_setapp(struct net_device *dev, struct dcb_app *new)
> if (new->priority) {
> struct dcb_app_type *entry;
> entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
> - if (!entry)
> + if (!entry) {
> + spin_unlock(&dcb_lock);
> return -ENOMEM;
> + }
>
> memcpy(&entry->app, new, sizeof(*new));
> strncpy(entry->name, dev->name, IFNAMSIZ);
> @@ -1640,7 +1642,7 @@ out:
> }
> EXPORT_SYMBOL(dcb_setapp);
>
> -void dcb_flushapp(void)
> +static void dcb_flushapp(void)
> {
> struct dcb_app_type *app;
>
^ permalink raw reply
* [net-next-2.6 PATCH v2 0/3] Series short description
From: John Fastabend @ 2010-12-30 19:25 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, lucy.liu, shmulikr
Version 2 adds the recommended tlv attributes to the ets struct this will
be needed for offloaded LLDP engines. Host controlled LLDP agents will most
likely not use these fields.
Also Shmulik Ravid caught an error with a spin_lock on kmalloc failure.
---
John Fastabend (3):
net_dcb: add application notifiers
dcbnl: add appliction tlv handlers
dcbnl: add support for ieee8021Qaz attributes
include/linux/dcbnl.h | 108 ++++++++++++++++++++
include/net/dcbevent.h | 31 ++++++
include/net/dcbnl.h | 20 ++++
net/dcb/Makefile | 2
net/dcb/dcbevent.c | 40 +++++++
net/dcb/dcbnl.c | 260 +++++++++++++++++++++++++++++++++++++++++++++++-
6 files changed, 453 insertions(+), 8 deletions(-)
create mode 100644 include/net/dcbevent.h
create mode 100644 net/dcb/dcbevent.c
--
Signature
^ permalink raw reply
* [net-next-2.6 PATCH v2 1/3] dcbnl: add support for ieee8021Qaz attributes
From: John Fastabend @ 2010-12-30 19:25 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, lucy.liu, shmulikr
In-Reply-To: <20101230192449.21487.9764.stgit@jf-dev1-dcblab>
The IEEE8021Qaz is the IEEE standard version of CEE. The
standard has had enough significant changes from the CEE
version that many of the CEE attributes have no meaning
in the new spec or do not easily map to IEEE standards.
Rather then attempt to create a complicated mapping
between CEE and IEEE standards this patch adds a nested
IEEE attribute to the list of DCB attributes. The policy
is,
[DCB_ATTR_IFNAME]
[DCB_ATTR_STATE]
...
[DCB_ATTR_IEEE]
[DCB_ATTR_IEEE_ETS]
[DCB_ATTR_IEEE_PFC]
[DCB_ATTR_IEEE_APP_TABLE]
[DCB_ATTR_IEEE_APP]
...
The following dcbnl_rtnl_ops routines were added to handle
the IEEE standard,
int (*ieee_getets) (struct net_device *, struct ieee_ets *);
int (*ieee_setets) (struct net_device *, struct ieee_ets *);
int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *);
int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *);
int (*ieee_getapp) (struct net_device *, struct dcb_app *);
int (*ieee_setapp) (struct net_device *, struct dcb_app *);
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/linux/dcbnl.h | 106 ++++++++++++++++++++++++++++++++++++++++
include/net/dcbnl.h | 11 ++++
net/dcb/dcbnl.c | 131 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 248 insertions(+), 0 deletions(-)
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 8723491..287b561 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -22,6 +22,87 @@
#include <linux/types.h>
+/* IEEE 802.1Qaz std supported values */
+#define IEEE_8021QAZ_MAX_TCS 8
+
+/* This structure contains the IEEE 802.1Qaz ETS managed object
+ *
+ * @willing: willing bit in ETS configuratin TLV
+ * @ets_cap: indicates supported capacity of ets feature
+ * @cbs: credit based shaper ets algorithm supported
+ * @tc_tx_bw: tc tx bandwidth indexed by traffic class
+ * @tc_rx_bw: tc rx bandwidth indexed by traffic class
+ * @tc_tsa: TSA Assignment table, indexed by traffic class
+ * @prio_tc: priority assignment table mapping 8021Qp to traffic class
+ * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV
+ * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV
+ * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV
+ *
+ * Recommended values are used to set fields in the ETS recommendation TLV
+ * with hardware offloaded LLDP.
+ *
+ * ----
+ * TSA Assignment 8 bit identifiers
+ * 0 strict priority
+ * 1 credit-based shaper
+ * 2 enhanced transmission selection
+ * 3-254 reserved
+ * 255 vendor specific
+ */
+struct ieee_ets {
+ __u8 willing;
+ __u8 ets_cap;
+ __u8 cbs;
+ __u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_rx_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_tsa[IEEE_8021QAZ_MAX_TCS];
+ __u8 prio_tc[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_reco_bw[IEEE_8021QAZ_MAX_TCS];
+ __u8 tc_reco_tsa[IEEE_8021QAZ_MAX_TCS];
+ __u8 reco_prio_tc[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qaz PFC managed object
+ *
+ * @pfc_cap: Indicates the number of traffic classes on the local device
+ * that may simultaneously have PFC enabled.
+ * @pfc_en: bitmap indicating pfc enabled traffic classes
+ * @mbc: enable macsec bypass capability
+ * @delay: the allowance made for a round-trip propagation delay of the
+ * link in bits.
+ * @requests: count of the sent pfc frames
+ * @indications: count of the received pfc frames
+ */
+struct ieee_pfc {
+ __u8 pfc_cap;
+ __u8 pfc_en;
+ __u8 mbc;
+ __u16 delay;
+ __u64 requests[IEEE_8021QAZ_MAX_TCS];
+ __u64 indications[IEEE_8021QAZ_MAX_TCS];
+};
+
+/* This structure contains the IEEE 802.1Qaz APP managed object
+ *
+ * @selector: protocol identifier type
+ * @protocol: protocol of type indicated
+ * @priority: 3-bit unsigned integer indicating priority
+ *
+ * ----
+ * Selector field values
+ * 0 Reserved
+ * 1 Ethertype
+ * 2 Well known port number over TCP or SCTP
+ * 3 Well known port number over UDP or DCCP
+ * 4 Well known port number over TCP, SCTP, UDP, or DCCP
+ * 5-7 Reserved
+ */
+struct dcb_app {
+ __u8 selector;
+ __u32 protocol;
+ __u8 priority;
+};
+
struct dcbmsg {
__u8 dcb_family;
__u8 cmd;
@@ -50,6 +131,8 @@ struct dcbmsg {
* @DCB_CMD_SBCN: get backward congestion notification configration.
* @DCB_CMD_GAPP: get application protocol configuration
* @DCB_CMD_SAPP: set application protocol configuration
+ * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration
+ * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration
*/
enum dcbnl_commands {
DCB_CMD_UNDEFINED,
@@ -83,6 +166,9 @@ enum dcbnl_commands {
DCB_CMD_GAPP,
DCB_CMD_SAPP,
+ DCB_CMD_IEEE_SET,
+ DCB_CMD_IEEE_GET,
+
__DCB_CMD_ENUM_MAX,
DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
};
@@ -102,6 +188,7 @@ enum dcbnl_commands {
* @DCB_ATTR_CAP: DCB capabilities of the device (NLA_NESTED)
* @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED)
* @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED)
+ * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED)
*/
enum dcbnl_attrs {
DCB_ATTR_UNDEFINED,
@@ -119,10 +206,29 @@ enum dcbnl_attrs {
DCB_ATTR_BCN,
DCB_ATTR_APP,
+ /* IEEE std attributes */
+ DCB_ATTR_IEEE,
+
__DCB_ATTR_ENUM_MAX,
DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
};
+enum ieee_attrs {
+ DCB_ATTR_IEEE_UNSPEC,
+ DCB_ATTR_IEEE_ETS,
+ DCB_ATTR_IEEE_PFC,
+ DCB_ATTR_IEEE_APP_TABLE,
+ __DCB_ATTR_IEEE_MAX
+};
+#define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1)
+
+enum ieee_attrs_app {
+ DCB_ATTR_IEEE_APP_UNSPEC,
+ DCB_ATTR_IEEE_APP,
+ __DCB_ATTR_IEEE_APP_MAX
+};
+#define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1)
+
/**
* enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs
*
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index b36ac7e..e2d841e 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -20,11 +20,22 @@
#ifndef __NET_DCBNL_H__
#define __NET_DCBNL_H__
+#include <linux/dcbnl.h>
+
/*
* Ops struct for the netlink callbacks. Used by DCB-enabled drivers through
* the netdevice struct.
*/
struct dcbnl_rtnl_ops {
+ /* IEEE 802.1Qaz std */
+ int (*ieee_getets) (struct net_device *, struct ieee_ets *);
+ int (*ieee_setets) (struct net_device *, struct ieee_ets *);
+ int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *);
+ int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *);
+ int (*ieee_getapp) (struct net_device *, struct dcb_app *);
+ int (*ieee_setapp) (struct net_device *, struct dcb_app *);
+
+ /* CEE std */
u8 (*getstate)(struct net_device *);
u8 (*setstate)(struct net_device *, u8);
void (*getpermhwaddr)(struct net_device *, u8 *);
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 19ac2b9..2ff9084 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -66,6 +66,7 @@ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_PFC_STATE] = {.type = NLA_U8},
[DCB_ATTR_BCN] = {.type = NLA_NESTED},
[DCB_ATTR_APP] = {.type = NLA_NESTED},
+ [DCB_ATTR_IEEE] = {.type = NLA_NESTED},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -167,6 +168,17 @@ static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = {
[DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8},
};
+/* IEEE 802.1Qaz nested attributes. */
+static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = {
+ [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)},
+ [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)},
+ [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED},
+};
+
+static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = {
+ [DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)},
+};
+
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
u32 seq, u16 flags)
@@ -1118,6 +1130,117 @@ err:
return ret;
}
+/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not
+ * be completed the entire msg is aborted and error value is returned.
+ * No attempt is made to reconcile the case where only part of the
+ * cmd can be completed.
+ */
+static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
+ struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
+ int err = -EOPNOTSUPP;
+
+ if (!ops)
+ goto err;
+
+ err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX,
+ tb[DCB_ATTR_IEEE], dcbnl_ieee_policy);
+ if (err)
+ goto err;
+
+ if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) {
+ struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]);
+ err = ops->ieee_setets(netdev, ets);
+ if (err)
+ goto err;
+ }
+
+ if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setets) {
+ struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]);
+ err = ops->ieee_setpfc(netdev, pfc);
+ if (err)
+ goto err;
+ }
+
+ if (ieee[DCB_ATTR_IEEE_APP_TABLE] && ops->ieee_setapp) {
+ struct nlattr *attr;
+ int rem;
+
+ nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) {
+ struct dcb_app *app_data;
+ if (nla_type(attr) != DCB_ATTR_IEEE_APP)
+ continue;
+ app_data = nla_data(attr);
+ err = ops->ieee_setapp(netdev, app_data);
+ if (err)
+ goto err;
+ }
+ }
+
+err:
+ dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE,
+ pid, seq, flags);
+ return err;
+}
+
+
+/* Handle IEEE 802.1Qaz GET commands. */
+static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *ieee;
+ const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
+ int err;
+
+ if (!ops)
+ return -EOPNOTSUPP;
+
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ nlh = NLMSG_NEW(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_IEEE_GET;
+
+ NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name);
+
+ ieee = nla_nest_start(skb, DCB_ATTR_IEEE);
+ if (!ieee)
+ goto nla_put_failure;
+
+ if (ops->ieee_getets) {
+ struct ieee_ets ets;
+ err = ops->ieee_getets(netdev, &ets);
+ if (!err)
+ NLA_PUT(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets);
+ }
+
+ if (ops->ieee_getpfc) {
+ struct ieee_pfc pfc;
+ err = ops->ieee_getpfc(netdev, &pfc);
+ if (!err)
+ NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc);
+ }
+
+ nla_nest_end(skb, ieee);
+ nlmsg_end(skb, nlh);
+
+ return rtnl_unicast(skb, &init_net, pid);
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+nlmsg_failure:
+ kfree_skb(skb);
+ return -1;
+}
+
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
@@ -1223,6 +1346,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_IEEE_SET:
+ ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_IEEE_GET:
+ ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
^ permalink raw reply related
* [net-next-2.6 PATCH v2 2/3] dcbnl: add appliction tlv handlers
From: John Fastabend @ 2010-12-30 19:26 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, lucy.liu, shmulikr
In-Reply-To: <20101230192449.21487.9764.stgit@jf-dev1-dcblab>
This patch adds application tlv handlers. Networking stacks
may use the application priority to set the skb priority of
their stack using the negoatiated dcbx priority.
This patch provides the dcb_{get|set}app() routines for the
stack to query these parameters. Notice lower layer drivers
can use the dcbnl_ops routines if additional handling is
needed. Perhaps in the firmware case for example
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
---
include/linux/dcbnl.h | 4 +
include/net/dcbnl.h | 9 +++
net/dcb/dcbnl.c | 133 +++++++++++++++++++++++++++++++++++++++++++++----
3 files changed, 135 insertions(+), 11 deletions(-)
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 287b561..775bdb4 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -82,7 +82,9 @@ struct ieee_pfc {
__u64 indications[IEEE_8021QAZ_MAX_TCS];
};
-/* This structure contains the IEEE 802.1Qaz APP managed object
+/* This structure contains the IEEE 802.1Qaz APP managed object. This
+ * object is also used for the CEE std as well. There is no difference
+ * between the objects.
*
* @selector: protocol identifier type
* @protocol: protocol of type indicated
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index e2d841e..ab7d623 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -22,6 +22,15 @@
#include <linux/dcbnl.h>
+struct dcb_app_type {
+ char name[IFNAMSIZ];
+ struct dcb_app app;
+ struct list_head list;
+};
+
+u8 dcb_setapp(struct net_device *, struct dcb_app *);
+u8 dcb_getapp(struct net_device *, struct dcb_app *);
+
/*
* Ops struct for the netlink callbacks. Used by DCB-enabled drivers through
* the netdevice struct.
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 2ff9084..cfd731f 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -179,6 +179,9 @@ static const struct nla_policy dcbnl_ieee_app[DCB_ATTR_IEEE_APP_MAX + 1] = {
[DCB_ATTR_IEEE_APP] = {.len = sizeof(struct dcb_app)},
};
+static LIST_HEAD(dcb_app_list);
+static DEFINE_SPINLOCK(dcb_lock);
+
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
u32 seq, u16 flags)
@@ -634,12 +637,12 @@ out:
static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb,
u32 pid, u32 seq, u16 flags)
{
- int ret = -EINVAL;
+ int err, ret = -EINVAL;
u16 id;
u8 up, idtype;
struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
- if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->setapp)
+ if (!tb[DCB_ATTR_APP])
goto out;
ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
@@ -663,9 +666,18 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb,
id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]);
- ret = dcbnl_reply(netdev->dcbnl_ops->setapp(netdev, idtype, id, up),
- RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP,
- pid, seq, flags);
+ if (netdev->dcbnl_ops->setapp) {
+ err = netdev->dcbnl_ops->setapp(netdev, idtype, id, up);
+ } else {
+ struct dcb_app app;
+ app.selector = idtype;
+ app.protocol = id;
+ app.priority = up;
+ err = dcb_setapp(netdev, &app);
+ }
+
+ ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP,
+ pid, seq, flags);
out:
return ret;
}
@@ -1164,7 +1176,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
goto err;
}
- if (ieee[DCB_ATTR_IEEE_APP_TABLE] && ops->ieee_setapp) {
+ if (ieee[DCB_ATTR_IEEE_APP_TABLE]) {
struct nlattr *attr;
int rem;
@@ -1173,7 +1185,10 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
if (nla_type(attr) != DCB_ATTR_IEEE_APP)
continue;
app_data = nla_data(attr);
- err = ops->ieee_setapp(netdev, app_data);
+ if (ops->ieee_setapp)
+ err = ops->ieee_setapp(netdev, app_data);
+ else
+ err = dcb_setapp(netdev, app_data);
if (err)
goto err;
}
@@ -1193,7 +1208,8 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
struct sk_buff *skb;
struct nlmsghdr *nlh;
struct dcbmsg *dcb;
- struct nlattr *ieee;
+ struct nlattr *ieee, *app;
+ struct dcb_app_type *itr;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
int err;
@@ -1230,6 +1246,19 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
NLA_PUT(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc);
}
+ app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE);
+ if (!app)
+ goto nla_put_failure;
+
+ spin_lock(&dcb_lock);
+ list_for_each_entry(itr, &dcb_app_list, list) {
+ if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0)
+ NLA_PUT(skb, DCB_ATTR_IEEE_APP,
+ sizeof(itr->app), &itr->app);
+ }
+ spin_unlock(&dcb_lock);
+ nla_nest_end(skb, app);
+
nla_nest_end(skb, ieee);
nlmsg_end(skb, nlh);
@@ -1364,8 +1393,93 @@ out:
return ret;
}
+/**
+ * dcb_getapp - retrieve the DCBX application user priority
+ *
+ * On success returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to
+ * indicate an error.
+ */
+u8 dcb_getapp(struct net_device *dev, struct dcb_app *app)
+{
+ struct dcb_app_type *itr;
+ u8 prio = 0;
+
+ spin_lock(&dcb_lock);
+ list_for_each_entry(itr, &dcb_app_list, list) {
+ if (itr->app.selector == app->selector &&
+ itr->app.protocol == app->protocol &&
+ (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ prio = itr->app.priority;
+ break;
+ }
+ }
+ spin_unlock(&dcb_lock);
+
+ return prio;
+}
+EXPORT_SYMBOL(dcb_getapp);
+
+/**
+ * ixgbe_dcbnl_setapp - add dcb application data to app list
+ *
+ * Priority 0 is the default priority this removes applications
+ * from the app list if the priority is set to zero.
+ */
+u8 dcb_setapp(struct net_device *dev, struct dcb_app *new)
+{
+ struct dcb_app_type *itr;
+
+ spin_lock(&dcb_lock);
+ /* Search for existing match and replace */
+ list_for_each_entry(itr, &dcb_app_list, list) {
+ if (itr->app.selector == new->selector &&
+ itr->app.protocol == new->protocol &&
+ (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) {
+ if (new->priority)
+ itr->app.priority = new->priority;
+ else {
+ list_del(&itr->list);
+ kfree(itr);
+ }
+ goto out;
+ }
+ }
+ /* App type does not exist add new application type */
+ if (new->priority) {
+ struct dcb_app_type *entry;
+ entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
+ if (!entry) {
+ spin_unlock(&dcb_lock);
+ return -ENOMEM;
+ }
+
+ memcpy(&entry->app, new, sizeof(*new));
+ strncpy(entry->name, dev->name, IFNAMSIZ);
+ list_add(&entry->list, &dcb_app_list);
+ }
+out:
+ spin_unlock(&dcb_lock);
+ return 0;
+}
+EXPORT_SYMBOL(dcb_setapp);
+
+void dcb_flushapp(void)
+{
+ struct dcb_app_type *app;
+
+ spin_lock(&dcb_lock);
+ list_for_each_entry(app, &dcb_app_list, list) {
+ list_del(&app->list);
+ kfree(app);
+ }
+ spin_unlock(&dcb_lock);
+}
+
static int __init dcbnl_init(void)
{
+ INIT_LIST_HEAD(&dcb_app_list);
+
rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL);
rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL);
@@ -1377,7 +1491,6 @@ static void __exit dcbnl_exit(void)
{
rtnl_unregister(PF_UNSPEC, RTM_GETDCB);
rtnl_unregister(PF_UNSPEC, RTM_SETDCB);
+ dcb_flushapp();
}
module_exit(dcbnl_exit);
-
-
^ permalink raw reply related
* [net-next-2.6 PATCH v2 3/3] net_dcb: add application notifiers
From: John Fastabend @ 2010-12-30 19:26 UTC (permalink / raw)
To: davem; +Cc: john.r.fastabend, netdev, lucy.liu, shmulikr
In-Reply-To: <20101230192449.21487.9764.stgit@jf-dev1-dcblab>
DCBx applications priorities can be changed dynamically. If
application stacks are expected to keep the skb priority
consistent with the dcbx priority the stack will need to
be notified when these changes occur.
This patch adds application notifiers for the stack to register
with.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
---
include/net/dcbevent.h | 31 +++++++++++++++++++++++++++++++
net/dcb/Makefile | 2 +-
net/dcb/dcbevent.c | 40 ++++++++++++++++++++++++++++++++++++++++
net/dcb/dcbnl.c | 2 ++
4 files changed, 74 insertions(+), 1 deletions(-)
create mode 100644 include/net/dcbevent.h
create mode 100644 net/dcb/dcbevent.c
diff --git a/include/net/dcbevent.h b/include/net/dcbevent.h
new file mode 100644
index 0000000..bc1e7ef
--- /dev/null
+++ b/include/net/dcbevent.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2010, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: John Fastabend <john.r.fastabend@intel.com>
+ */
+
+#ifndef _DCB_EVENT_H
+#define _DCB_EVENT_H
+
+enum dcbevent_notif_type {
+ DCB_APP_EVENT = 1,
+};
+
+extern int register_dcbevent_notifier(struct notifier_block *nb);
+extern int unregister_dcbevent_notifier(struct notifier_block *nb);
+extern int call_dcbevent_notifiers(unsigned long val, void *v);
+
+#endif
diff --git a/net/dcb/Makefile b/net/dcb/Makefile
index 9930f4c..c1282c9 100644
--- a/net/dcb/Makefile
+++ b/net/dcb/Makefile
@@ -1 +1 @@
-obj-$(CONFIG_DCB) += dcbnl.o
+obj-$(CONFIG_DCB) += dcbnl.o dcbevent.o
diff --git a/net/dcb/dcbevent.c b/net/dcb/dcbevent.c
new file mode 100644
index 0000000..665a880
--- /dev/null
+++ b/net/dcb/dcbevent.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2010, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: John Fastabend <john.r.fastabend@intel.com>
+ */
+
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+
+static ATOMIC_NOTIFIER_HEAD(dcbevent_notif_chain);
+
+int register_dcbevent_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_register(&dcbevent_notif_chain, nb);
+}
+EXPORT_SYMBOL(register_dcbevent_notifier);
+
+int unregister_dcbevent_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_unregister(&dcbevent_notif_chain, nb);
+}
+EXPORT_SYMBOL(unregister_dcbevent_notifier);
+
+int call_dcbevent_notifiers(unsigned long val, void *v)
+{
+ return atomic_notifier_call_chain(&dcbevent_notif_chain, val, v);
+}
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index cfd731f..6914412 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -23,6 +23,7 @@
#include <net/netlink.h>
#include <net/rtnetlink.h>
#include <linux/dcbnl.h>
+#include <net/dcbevent.h>
#include <linux/rtnetlink.h>
#include <net/sock.h>
@@ -1460,6 +1461,7 @@ u8 dcb_setapp(struct net_device *dev, struct dcb_app *new)
}
out:
spin_unlock(&dcb_lock);
+ call_dcbevent_notifiers(DCB_APP_EVENT, new);
return 0;
}
EXPORT_SYMBOL(dcb_setapp);
^ permalink raw reply related
* Re: sysctls below net.ipv[46].conf.all not working as expected
From: Uwe Kleine-König @ 2010-12-30 20:20 UTC (permalink / raw)
To: netdev; +Cc: Marco d'Itri
In-Reply-To: <20101229160607.GH14221@pengutronix.de>
Hello again,
On Wed, Dec 29, 2010 at 05:06:07PM +0100, Uwe Kleine-König wrote:
> I did the following:
>
> cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> net.ipv6.conf.all.use_tempaddr = 0
>
> cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> net.ipv6.conf.eth0.use_tempaddr = 0
>
> cassiopeia:~# sysctl -w net.ipv6.conf.all.use_tempaddr=1
> net.ipv6.conf.all.use_tempaddr = 1
>
> cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> net.ipv6.conf.all.use_tempaddr = 1
>
> cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> net.ipv6.conf.eth0.use_tempaddr = 0
>
> Here I would have expected that eth0's use_tempaddr is 1, too. The
> problem is not that this entry isn't writeable:
>
> cassiopeia:~# sysctl -w net.ipv6.conf.eth0.use_tempaddr=1
> net.ipv6.conf.eth0.use_tempaddr = 1
>
> cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> net.ipv6.conf.eth0.use_tempaddr = 1
>
> I got the same results when using net.ipv4.conf.all.rp_filter (and
> net.ipv4.conf.eth0.rp_filter resp.)
>
> Is this a bug or just my failure to see how conf/all works?
I put the following in my /etc/sysctl.conf:
net.ipv6.conf.default.use_tempaddr = 1
net.ipv6.conf.all.use_tempaddr = 1
net.ipv6.conf.eth0.use_tempaddr = 1
and after a reboot eth0 got a temporary dynamic address, eth1 did not.
So it doesn't seem to be as guessed by someone on #debian-kernel that
the setting works but isn't propagated back to the sysctl of the
interface.
This makes me wonder how useful the lines
net.ipv4.conf.default.rp_filter = 1
net.ipv4.conf.all.rp_filter = 1
(suggested by the Debian package netbase) are.
Best regards
Uwe
--
Pengutronix e.K. | Uwe Kleine-König |
Industrial Linux Solutions | http://www.pengutronix.de/ |
^ permalink raw reply
* Re: sysctls below net.ipv[46].conf.all not working as expected
From: David Miller @ 2010-12-30 20:30 UTC (permalink / raw)
To: u.kleine-koenig; +Cc: netdev
In-Reply-To: <20101229160607.GH14221@pengutronix.de>
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Wed, 29 Dec 2010 17:06:07 +0100
> I did the following:
>
> cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> net.ipv6.conf.all.use_tempaddr = 0
>
> cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> net.ipv6.conf.eth0.use_tempaddr = 0
>
> cassiopeia:~# sysctl -w net.ipv6.conf.all.use_tempaddr=1
> net.ipv6.conf.all.use_tempaddr = 1
>
> cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> net.ipv6.conf.all.use_tempaddr = 1
>
> cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> net.ipv6.conf.eth0.use_tempaddr = 0
>
> Here I would have expected that eth0's use_tempaddr is 1, too. The
> problem is not that this entry isn't writeable:
The "all" value is propagated at the first moment that the ipv6 device
private is created, usually that is when the device is first brought up
which means it can happen as early as the exact moment the device is
registered.
Therefore, if you want "all" to apply to "eth0", you must make sure
the sysctl is set properly before the device is registered.
^ permalink raw reply
* Re: sysctls below net.ipv[46].conf.all not working as expected
From: Uwe Kleine-König @ 2010-12-30 20:43 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20101230.123023.226775556.davem@davemloft.net>
Hello David,
On Thu, Dec 30, 2010 at 12:30:23PM -0800, David Miller wrote:
> From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
> Date: Wed, 29 Dec 2010 17:06:07 +0100
>
> > I did the following:
> >
> > cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> > net.ipv6.conf.all.use_tempaddr = 0
> >
> > cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> > net.ipv6.conf.eth0.use_tempaddr = 0
> >
> > cassiopeia:~# sysctl -w net.ipv6.conf.all.use_tempaddr=1
> > net.ipv6.conf.all.use_tempaddr = 1
> >
> > cassiopeia:~# sysctl net.ipv6.conf.all.use_tempaddr
> > net.ipv6.conf.all.use_tempaddr = 1
> >
> > cassiopeia:~# sysctl net.ipv6.conf.eth0.use_tempaddr
> > net.ipv6.conf.eth0.use_tempaddr = 0
> >
> > Here I would have expected that eth0's use_tempaddr is 1, too. The
> > problem is not that this entry isn't writeable:
>
> The "all" value is propagated at the first moment that the ipv6 device
> private is created, usually that is when the device is first brought up
> which means it can happen as early as the exact moment the device is
> registered.
>
> Therefore, if you want "all" to apply to "eth0", you must make sure
> the sysctl is set properly before the device is registered.
I thought this is what "default" was used for?!
If you are really right, the documentation is (IMHO) misleading. e.g.
Documentation/networking/ip-sysctl.txt tells:
conf/default/*:
Change the interface-specific default settings.
conf/all/*:
Change all the interface-specific settings.
Best regards
Uwe
--
Pengutronix e.K. | Uwe Kleine-König |
Industrial Linux Solutions | http://www.pengutronix.de/ |
^ permalink raw reply
* RE: [PATCH net-2.6] bridge: fix br_multicast_ipv6_rcv for paged skbs
From: Winkler, Tomas @ 2010-12-30 21:00 UTC (permalink / raw)
To: Stephen Hemminger, Johannes Berg
Cc: davem@davemloft.net, netdev@vger.kernel.org,
linux-wireless@vger.kernel.org
In-Reply-To: <20101230110609.08b7ee38@nehalam>
> -----Original Message-----
> From: Stephen Hemminger [mailto:shemminger@vyatta.com]
> Sent: Thursday, December 30, 2010 9:06 PM
> To: Johannes Berg
> Cc: Winkler, Tomas; davem@davemloft.net; netdev@vger.kernel.org; linux-
> wireless@vger.kernel.org
> Subject: Re: [PATCH net-2.6] bridge: fix br_multicast_ipv6_rcv for paged
> skbs
>
> On Thu, 30 Dec 2010 19:52:14 +0100
> Johannes Berg <johannes@sipsolutions.net> wrote:
>
> > On Thu, 2010-12-30 at 10:46 -0800, Stephen Hemminger wrote:
> >
> > > This doesn't look correct. The calculation of the offset doesn't look
> correct.
> > > Just following the skb_clone(), the skb_pull value is "offset".
> > > Also, the other checks return -EINVAL for incorrectly formed packet.
> > >
> > > --- a/net/bridge/br_multicast.c 2010-12-30 10:29:58.579510488 -0800
> > > +++ b/net/bridge/br_multicast.c 2010-12-30 10:43:27.273386691 -0800
> > > @@ -1464,6 +1464,9 @@ static int br_multicast_ipv6_rcv(struct
> > > if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
> > > return 0;
> > >
> > > + if (!pskb_may_pull(skb, offset))
> > > + return -EINVAL;
> > > +
> > > /* Okay, we found ICMPv6 header */
> > > skb2 = skb_clone(skb, GFP_ATOMIC);
> > > if (!skb2)
> >
> > Wouldn't that make more sense after the clone anyway? But if you look at
> > my email, you'll find that there's potentially, and conditionally, more
> > stuff that will be read from the skb's header, which hasn't necessarily
> > been pulled in, so I think this still won't fix all the issues.
> >
> > Seeing how this only affects some ICMPv6 packets, maybe we should just
> > use skb_copy() instead?
>
> It comes out cleaner, and the check can be simplified.
>
> --- a/net/bridge/br_multicast.c 2010-12-30 10:47:12.031733855 -0800
> +++ b/net/bridge/br_multicast.c 2010-12-30 11:00:12.135801266 -0800
> @@ -1465,19 +1465,19 @@ static int br_multicast_ipv6_rcv(struct
> return 0;
>
> /* Okay, we found ICMPv6 header */
> - skb2 = skb_clone(skb, GFP_ATOMIC);
> + skb2 = skb_copy(skb, GFP_ATOMIC);
> if (!skb2)
> return -ENOMEM;
>
> + err = -EINVAL;
> + if (skb2->len < offset + sizeof(*icmp6h))
> + goto out;
> +
> len -= offset - skb_network_offset(skb2);
>
> __skb_pull(skb2, offset);
> skb_reset_transport_header(skb2);
>
> - err = -EINVAL;
> - if (!pskb_may_pull(skb2, sizeof(*icmp6h)))
> - goto out;
> -
> icmp6h = icmp6_hdr(skb2);
>
> switch (icmp6h->icmp6_type) {
>
>
Sorry for dump question but isn't there performance penalty on using skb_copy vs. skb_clone?
Anyhow Below is a code snippet from ip6_input.c so you probably would want to fix it all over.
BTW offset and the pointer arithmetic really gives the same number +1, I'm not surly why the original author would thought it be safer than just using offset.
offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
&nexthdr);
if (offset < 0)
goto out;
if (nexthdr != IPPROTO_ICMPV6)
goto out;
if (!pskb_may_pull(skb, (skb_network_header(skb) +
offset + 1 - skb->data)))
goto out;
icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset);
Thanks
Tomas
---------------------------------------------------------------------
Intel Israel (74) Limited
This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
^ 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