* Re: [net-next PATCH 02/12] ixgbe: updates vlan feature flags to enable FCoE offloads on vlan interface
From: David Miller @ 2009-08-14 23:12 UTC (permalink / raw)
To: jeffrey.t.kirsher
Cc: netdev, linux-scsi, gospo, vasu.dev, yi.zou,
peter.p.waskiewicz.jr
In-Reply-To: <20090814224127.1640.84665.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Fri, 14 Aug 2009 15:41:28 -0700
> From: Vasu Dev <vasu.dev@intel.com>
>
> Updates netdev->vlan_features for NETIF_F_FCOE_CRC and NETIF_F_FSO, so that
> FCoE CRC and GSO offloads will get used for FCoE over ixgbe based vlan
> interface.
>
> Signed-off-by: Vasu Dev <vasu.dev@intel.com>
> Signed-off-by: Yi Zou <yi.zou@intel.com>
> Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied.
^ permalink raw reply
* [net-next PATCH 12/12] ixgbe: Add support for dcbnl_rtnl_ops.setapp/getapp
From: Jeff Kirsher @ 2009-08-14 22:45 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Add support for dcbnl_rtnl_ops.setapp/getapp to set or get the current user
priority bitmap for the given application protocol. Currently, 82599 only
supports setapp/getapp for Fiber Channel over Ethernet (FCoE) protocol.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 4 ++
drivers/net/ixgbe/ixgbe_dcb_nl.c | 60 ++++++++++++++++++++++++++++++++++++
drivers/net/ixgbe/ixgbe_fcoe.c | 64 ++++++++++++++++++++++++++++++++++++++
drivers/net/ixgbe/ixgbe_fcoe.h | 4 ++
drivers/net/ixgbe/ixgbe_main.c | 2 +
5 files changed, 134 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 3c25524..cc324f3 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -486,6 +486,10 @@ extern int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid,
struct scatterlist *sgl, unsigned int sgc);
extern int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid);
extern int ixgbe_fcoe_control(struct net_device *netdev, u32 op);
+#ifdef CONFIG_IXGBE_DCB
+extern u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter);
+extern u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up);
+#endif /* CONFIG_IXGBE_DCB */
#endif /* IXGBE_FCOE */
#endif /* _IXGBE_H_ */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index e05c62a..47d9dde 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -480,6 +480,64 @@ static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
return;
}
+/**
+ * ixgbe_dcbnl_getapp - retrieve the DCBX application user priority
+ * @netdev : the corresponding netdev
+ * @idtype : identifies the id as ether type or TCP/UDP port number
+ * @id: id is either ether type or TCP/UDP port number
+ *
+ * Returns : on success, returns a non-zero 802.1p user priority bitmap
+ * otherwise returns 0 as the invalid user priority bitmap to indicate an
+ * error.
+ */
+static u8 ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id)
+{
+ u8 rval = 0;
+
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+#ifdef IXGBE_FCOE
+ if (id == ETH_P_FCOE)
+ rval = ixgbe_fcoe_getapp(netdev_priv(netdev));
+#endif
+ break;
+ case DCB_APP_IDTYPE_PORTNUM:
+ break;
+ default:
+ break;
+ }
+ return rval;
+}
+
+/**
+ * ixgbe_dcbnl_setapp - set the DCBX application user priority
+ * @netdev : the corresponding netdev
+ * @idtype : identifies the id as ether type or TCP/UDP port number
+ * @id: id is either ether type or TCP/UDP port number
+ * @up: the 802.1p user priority bitmap
+ *
+ * Returns : 0 on success or 1 on error
+ */
+static u8 ixgbe_dcbnl_setapp(struct net_device *netdev,
+ u8 idtype, u16 id, u8 up)
+{
+ u8 rval = 1;
+
+ switch (idtype) {
+ case DCB_APP_IDTYPE_ETHTYPE:
+#ifdef IXGBE_FCOE
+ if (id == ETH_P_FCOE)
+ rval = ixgbe_fcoe_setapp(netdev_priv(netdev), up);
+#endif
+ break;
+ case DCB_APP_IDTYPE_PORTNUM:
+ break;
+ default:
+ break;
+ }
+ return rval;
+}
+
struct dcbnl_rtnl_ops dcbnl_ops = {
.getstate = ixgbe_dcbnl_get_state,
.setstate = ixgbe_dcbnl_set_state,
@@ -500,5 +558,7 @@ struct dcbnl_rtnl_ops dcbnl_ops = {
.setnumtcs = ixgbe_dcbnl_setnumtcs,
.getpfcstate = ixgbe_dcbnl_getpfcstate,
.setpfcstate = ixgbe_dcbnl_setpfcstate,
+ .getapp = ixgbe_dcbnl_getapp,
+ .setapp = ixgbe_dcbnl_setapp,
};
diff --git a/drivers/net/ixgbe/ixgbe_fcoe.c b/drivers/net/ixgbe/ixgbe_fcoe.c
index b67ed27..39336f0 100644
--- a/drivers/net/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ixgbe/ixgbe_fcoe.c
@@ -27,6 +27,9 @@
#include "ixgbe.h"
+#ifdef CONFIG_IXGBE_DCB
+#include "ixgbe_dcb_82599.h"
+#endif /* CONFIG_IXGBE_DCB */
#include <linux/if_ether.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
@@ -674,3 +677,64 @@ int ixgbe_fcoe_control(struct net_device *netdev, u32 op)
out:
return rc;
}
+
+#ifdef CONFIG_IXGBE_DCB
+/**
+ * ixgbe_fcoe_getapp - retrieves current user priority bitmap for FCoE
+ * @adapter : ixgbe adapter
+ *
+ * Finds out the corresponding user priority bitmap from the current
+ * traffic class that FCoE belongs to. Returns 0 as the invalid user
+ * priority bitmap to indicate an error.
+ *
+ * Returns : 802.1p user priority bitmap for FCoE
+ */
+u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter)
+{
+ int i;
+ u8 tc;
+ u32 up2tc;
+
+ up2tc = IXGBE_READ_REG(&adapter->hw, IXGBE_RTTUP2TC);
+ for (i = 0; i < MAX_USER_PRIORITY; i++) {
+ tc = (u8)(up2tc >> (i * IXGBE_RTTUP2TC_UP_SHIFT));
+ tc &= (MAX_TRAFFIC_CLASS - 1);
+ if (adapter->fcoe.tc == tc)
+ return 1 << i;
+ }
+
+ return 0;
+}
+
+/**
+ * ixgbe_fcoe_setapp - sets the user priority bitmap for FCoE
+ * @adapter : ixgbe adapter
+ * @up : 802.1p user priority bitmap
+ *
+ * Finds out the traffic class from the input user priority
+ * bitmap for FCoE.
+ *
+ * Returns : 0 on success otherwise returns 1 on error
+ */
+u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up)
+{
+ int i;
+ u32 up2tc;
+
+ /* valid user priority bitmap must not be 0 */
+ if (up) {
+ /* from user priority to the corresponding traffic class */
+ up2tc = IXGBE_READ_REG(&adapter->hw, IXGBE_RTTUP2TC);
+ for (i = 0; i < MAX_USER_PRIORITY; i++) {
+ if (up & (1 << i)) {
+ up2tc >>= (i * IXGBE_RTTUP2TC_UP_SHIFT);
+ up2tc &= (MAX_TRAFFIC_CLASS - 1);
+ adapter->fcoe.tc = (u8)up2tc;
+ return 0;
+ }
+ }
+ }
+
+ return 1;
+}
+#endif /* CONFIG_IXGBE_DCB */
diff --git a/drivers/net/ixgbe/ixgbe_fcoe.h b/drivers/net/ixgbe/ixgbe_fcoe.h
index c5b5002..b5dee7b 100644
--- a/drivers/net/ixgbe/ixgbe_fcoe.h
+++ b/drivers/net/ixgbe/ixgbe_fcoe.h
@@ -46,6 +46,9 @@
#define IXGBE_FCBUFF_MIN 4096 /* 4KB min */
#define IXGBE_FCOE_DDP_MAX 512 /* 9 bits xid */
+/* Default traffic class to use for FCoE */
+#define IXGBE_FCOE_DEFTC 3
+
/* fcerr */
#define IXGBE_FCERR_BADCRC 0x00100000
@@ -59,6 +62,7 @@ struct ixgbe_fcoe_ddp {
};
struct ixgbe_fcoe {
+ u8 tc;
spinlock_t lock;
struct pci_pool *pool;
struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX];
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 9738317..f4fc4ae 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -3801,6 +3801,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
adapter->ring_feature[RING_F_FCOE].indices = 0;
+ /* Default traffic class to use for FCoE */
+ adapter->fcoe.tc = IXGBE_FCOE_DEFTC;
#endif /* IXGBE_FCOE */
}
^ permalink raw reply related
* [net-next PATCH 11/12] dcbnl: Add implementations of dcbnl setapp/getapp commands
From: Jeff Kirsher @ 2009-08-14 22:44 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Implements the dcbnl netlink setapp/getapp pair. When a setapp/getapp
is received, dcbnl would just pass on to dcbnl_rtnl_op.setapp/getapp
that are supposed to be implemented by the low level drivers.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/dcb/dcbnl.c | 122 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 122 insertions(+), 0 deletions(-)
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 4046468..e0879bf 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -544,6 +544,120 @@ static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb,
return ret;
}
+static int dcbnl_getapp(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 *app_nest;
+ struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
+ u16 id;
+ u8 up, idtype;
+ int ret = -EINVAL;
+
+ if (!tb[DCB_ATTR_APP] || !netdev->dcbnl_ops->getapp)
+ goto out;
+
+ ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
+ dcbnl_app_nest);
+ if (ret)
+ goto out;
+
+ ret = -EINVAL;
+ /* all must be non-null */
+ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
+ (!app_tb[DCB_APP_ATTR_ID]))
+ goto out;
+
+ /* either by eth type or by socket number */
+ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
+ if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
+ (idtype != DCB_APP_IDTYPE_PORTNUM))
+ goto out;
+
+ id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
+ up = netdev->dcbnl_ops->getapp(netdev, idtype, id);
+
+ /* send this back */
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto 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_GAPP;
+
+ app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP);
+ ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype);
+ if (ret)
+ goto out_cancel;
+
+ ret = nla_put_u16(dcbnl_skb, DCB_APP_ATTR_ID, id);
+ if (ret)
+ goto out_cancel;
+
+ ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_PRIORITY, up);
+ if (ret)
+ goto out_cancel;
+
+ nla_nest_end(dcbnl_skb, app_nest);
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto nlmsg_failure;
+
+ goto out;
+
+out_cancel:
+ nla_nest_cancel(dcbnl_skb, app_nest);
+nlmsg_failure:
+ kfree_skb(dcbnl_skb);
+out:
+ return ret;
+}
+
+static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int 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)
+ goto out;
+
+ ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
+ dcbnl_app_nest);
+ if (ret)
+ goto out;
+
+ ret = -EINVAL;
+ /* all must be non-null */
+ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
+ (!app_tb[DCB_APP_ATTR_ID]) ||
+ (!app_tb[DCB_APP_ATTR_PRIORITY]))
+ goto out;
+
+ /* either by eth type or by socket number */
+ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
+ if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
+ (idtype != DCB_APP_IDTYPE_PORTNUM))
+ goto out;
+
+ 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);
+out:
+ return ret;
+}
+
static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
u32 pid, u32 seq, u16 flags, int dir)
{
@@ -1101,6 +1215,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_GAPP:
+ ret = dcbnl_getapp(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_SAPP:
+ ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
^ permalink raw reply related
* [net-next PATCH 10/12] dcbnl: Add netlink attributes for setapp/getapp to dcbnl
From: Jeff Kirsher @ 2009-08-14 22:44 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Add defines for dcbnl netlink attributes to support netlink message passing of
setapp/getapp in dcbnl.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/dcb/dcbnl.c | 8 ++++++++
1 files changed, 8 insertions(+), 0 deletions(-)
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 8379496..4046468 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -64,6 +64,7 @@ static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_CAP] = {.type = NLA_NESTED},
[DCB_ATTR_PFC_STATE] = {.type = NLA_U8},
[DCB_ATTR_BCN] = {.type = NLA_NESTED},
+ [DCB_ATTR_APP] = {.type = NLA_NESTED},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -158,6 +159,13 @@ static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = {
[DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG},
};
+/* DCB APP nested attributes. */
+static struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = {
+ [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8},
+ [DCB_APP_ATTR_ID] = {.type = NLA_U16},
+ [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8},
+};
+
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
u32 seq, u16 flags)
^ permalink raw reply related
* [net-next PATCH 09/12] dcbnl: Add support for setapp/getapp to netdev dcbnl_rtnl_ops
From: Jeff Kirsher @ 2009-08-14 22:44 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Adds support of dcbnl setapp/getapp to dcbnl_rtnl_ops in netdev to allow
LLDs to implement their corresponding dcbnl setapp/getapp ops to support
the IEEE 802.1Q DCBX setapp/getapp commands.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/net/dcbnl.h | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index 775cfc8..b36ac7e 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -48,6 +48,8 @@ struct dcbnl_rtnl_ops {
void (*setbcncfg)(struct net_device *, int, u32);
void (*getbcnrp)(struct net_device *, int, u8 *);
void (*setbcnrp)(struct net_device *, int, u8);
+ u8 (*setapp)(struct net_device *, u8, u16, u8);
+ u8 (*getapp)(struct net_device *, u8, u16);
};
#endif /* __NET_DCBNL_H__ */
^ permalink raw reply related
* [net-next PATCH 08/12] dcbnl: Add support for setapp/getapp commands to dcbnl
From: Jeff Kirsher @ 2009-08-14 22:43 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
This patch adds dcbnl command definitions to support setapp/getapp
functionality from the IEEE 802.1Qaz Data Center Bridging Capability
Exchange protocol (DCBX) specification. Section 3.3 defines the
application protocol and its 802.1p user priority in DCBX, which is
implemented here as a pair of setapp/getapp commands in the kernel
dcbnl for setting and retrieving the user priority for an given
application protocol. The protocol is identified by the combination of
an id and an idtype. Currently, when idtype is 0, the corresponding
id gives the ether type of this protocol, e.g., for FCoE, it will be
0x8906; when idtype is 1, then the corresponding id gives the TCP or
UDP port number.
For more information regarding DCBX spec., please refer to the following:
http://www.ieee802.org/1/files/public/docs2008/
az-wadekar-dcbx-capability-exchange-discovery-protocol-1108-v1.01.pdf
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/linux/dcbnl.h | 18 ++++++++++++++++++
1 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 7d2e100..b7cdbb4 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -50,6 +50,8 @@ struct dcbmsg {
* @DCB_CMD_SNUMTCS: set the number of traffic classes
* @DCB_CMD_GBCN: set backward congestion notification configuration
* @DCB_CMD_SBCN: get backward congestion notification configration.
+ * @DCB_CMD_GAPP: get application protocol configuration
+ * @DCB_CMD_SAPP: set application protocol configuration
*/
enum dcbnl_commands {
DCB_CMD_UNDEFINED,
@@ -80,6 +82,9 @@ enum dcbnl_commands {
DCB_CMD_BCN_GCFG,
DCB_CMD_BCN_SCFG,
+ DCB_CMD_GAPP,
+ DCB_CMD_SAPP,
+
__DCB_CMD_ENUM_MAX,
DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1,
};
@@ -114,6 +119,7 @@ enum dcbnl_attrs {
DCB_ATTR_CAP,
DCB_ATTR_NUMTCS,
DCB_ATTR_BCN,
+ DCB_ATTR_APP,
__DCB_ATTR_ENUM_MAX,
DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1,
@@ -338,5 +344,17 @@ enum dcb_general_attr_values {
DCB_ATTR_VALUE_UNDEFINED = 0xff
};
+#define DCB_APP_IDTYPE_ETHTYPE 0x00
+#define DCB_APP_IDTYPE_PORTNUM 0x01
+enum dcbnl_app_attrs {
+ DCB_APP_ATTR_UNDEFINED,
+
+ DCB_APP_ATTR_IDTYPE,
+ DCB_APP_ATTR_ID,
+ DCB_APP_ATTR_PRIORITY,
+
+ __DCB_APP_ATTR_ENUM_MAX,
+ DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1,
+};
#endif /* __LINUX_DCBNL_H__ */
^ permalink raw reply related
* [net-next PATCH 07/12] ixgbe: Add support for the net_device_ops.ndo_fcoe_control to 82599
From: Jeff Kirsher @ 2009-08-14 22:43 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Yi Zou, Peter P Waskiewicz Jr,
Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
This adds support to the net_device_ops.ndo_fcoe_control for 82599. This
consequently allows us to dynamically turn FCoE offload feature on or off
upon incoming calls to ndo_fcoe_control. When this happens, FCoE offload
features are enabled/disabled accordingly, and this is regardless of whether
DCB being turned on or not.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 1
drivers/net/ixgbe/ixgbe_dcb_nl.c | 33 ----------
drivers/net/ixgbe/ixgbe_fcoe.c | 120 ++++++++++++++++++++++++++++++++++++++
drivers/net/ixgbe/ixgbe_main.c | 1
4 files changed, 122 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 8f1f8ba..3c25524 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -485,6 +485,7 @@ extern int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter,
extern int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid,
struct scatterlist *sgl, unsigned int sgc);
extern int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid);
+extern int ixgbe_fcoe_control(struct net_device *netdev, u32 op);
#endif /* IXGBE_FCOE */
#endif /* _IXGBE_H_ */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 34bca45..e05c62a 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -139,23 +139,6 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
}
adapter->flags |= IXGBE_FLAG_DCB_ENABLED;
-#ifdef IXGBE_FCOE
- /* Turn on FCoE offload */
- if ((adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) &&
- (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED))) {
- adapter->flags |= IXGBE_FLAG_FCOE_ENABLED;
- adapter->ring_feature[RING_F_FCOE].indices =
- IXGBE_FCRETA_SIZE;
- netdev->features |= NETIF_F_FCOE_CRC;
- netdev->features |= NETIF_F_FSO;
- netdev->features |= NETIF_F_FCOE_MTU;
- netdev->vlan_features |= NETIF_F_FCOE_CRC;
- netdev->vlan_features |= NETIF_F_FSO;
- netdev->vlan_features |= NETIF_F_FCOE_MTU;
- netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1;
- netdev_features_change(netdev);
- }
-#endif /* IXGBE_FCOE */
ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
netdev->netdev_ops->ndo_open(netdev);
@@ -174,22 +157,6 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
if (adapter->hw.mac.type == ixgbe_mac_82599EB)
adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
-#ifdef IXGBE_FCOE
- /* Turn off FCoE offload */
- if (adapter->flags & (IXGBE_FLAG_FCOE_CAPABLE |
- IXGBE_FLAG_FCOE_ENABLED)) {
- adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
- adapter->ring_feature[RING_F_FCOE].indices = 0;
- netdev->features &= ~NETIF_F_FCOE_CRC;
- netdev->features &= ~NETIF_F_FSO;
- netdev->features &= ~NETIF_F_FCOE_MTU;
- netdev->vlan_features &= ~NETIF_F_FCOE_CRC;
- netdev->vlan_features &= ~NETIF_F_FSO;
- netdev->vlan_features &= ~NETIF_F_FCOE_MTU;
- netdev->fcoe_ddp_xid = 0;
- netdev_features_change(netdev);
- }
-#endif /* IXGBE_FCOE */
ixgbe_init_interrupt_scheme(adapter);
if (netif_running(netdev))
netdev->netdev_ops->ndo_open(netdev);
diff --git a/drivers/net/ixgbe/ixgbe_fcoe.c b/drivers/net/ixgbe/ixgbe_fcoe.c
index 28cf104..b67ed27 100644
--- a/drivers/net/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ixgbe/ixgbe_fcoe.c
@@ -554,3 +554,123 @@ void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter)
fcoe->pool = NULL;
}
}
+
+/**
+ * ixgbe_enable_fcoe - turn on FCoE offload feature
+ * @netdev: the corresponding netdev
+ *
+ * Turns on FCoE offload feature in 82599.
+ *
+ * Returns : 0 indicates success or -EINVAL on failure
+ */
+static int ixgbe_enable_fcoe(struct net_device *netdev)
+{
+ int rc = -EINVAL;
+ struct ixgbe_adapter *adapter = netdev_priv(netdev);
+
+ if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+ goto out_enable;
+
+ DPRINTK(DRV, INFO, "Enabling FCoE offload features.\n");
+ if (netif_running(netdev))
+ netdev->netdev_ops->ndo_stop(netdev);
+
+ ixgbe_clear_interrupt_scheme(adapter);
+
+ adapter->flags |= IXGBE_FLAG_FCOE_ENABLED;
+ adapter->ring_feature[RING_F_FCOE].indices = IXGBE_FCRETA_SIZE;
+ netdev->features |= NETIF_F_FCOE_CRC;
+ netdev->features |= NETIF_F_FSO;
+ netdev->features |= NETIF_F_FCOE_MTU;
+ netdev->vlan_features |= NETIF_F_FCOE_CRC;
+ netdev->vlan_features |= NETIF_F_FSO;
+ netdev->vlan_features |= NETIF_F_FCOE_MTU;
+ netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1;
+ netdev_features_change(netdev);
+
+ ixgbe_init_interrupt_scheme(adapter);
+
+ if (netif_running(netdev))
+ netdev->netdev_ops->ndo_open(netdev);
+ rc = 0;
+
+out_enable:
+ return rc;
+}
+
+/**
+ * ixgbe_disable_fcoe - turn off FCoE offload feature
+ * @netdev: the corresponding netdev
+ *
+ * Turns off FCoE offload feature in 82599.
+ *
+ * Returns : 0 indicates success or -EINVAL on failure
+ */
+static int ixgbe_disable_fcoe(struct net_device *netdev)
+{
+ int rc = -EINVAL;
+ struct ixgbe_adapter *adapter = netdev_priv(netdev);
+
+ if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
+ goto out_disable;
+
+ DPRINTK(DRV, INFO, "Disabling FCoE offload features.\n");
+ if (netif_running(netdev))
+ netdev->netdev_ops->ndo_stop(netdev);
+
+ ixgbe_clear_interrupt_scheme(adapter);
+
+ adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
+ adapter->ring_feature[RING_F_FCOE].indices = 0;
+ netdev->features &= ~NETIF_F_FCOE_CRC;
+ netdev->features &= ~NETIF_F_FSO;
+ netdev->features &= ~NETIF_F_FCOE_MTU;
+ netdev->vlan_features &= ~NETIF_F_FCOE_CRC;
+ netdev->vlan_features &= ~NETIF_F_FSO;
+ netdev->vlan_features &= ~NETIF_F_FCOE_MTU;
+ netdev->fcoe_ddp_xid = 0;
+ netdev_features_change(netdev);
+
+ ixgbe_cleanup_fcoe(adapter);
+
+ ixgbe_init_interrupt_scheme(adapter);
+ if (netif_running(netdev))
+ netdev->netdev_ops->ndo_open(netdev);
+ rc = 0;
+
+out_disable:
+ return rc;
+}
+
+/**
+ * ixgbe_fcoe_control - turn on or off FCoE offload feature
+ * @adapter : ixgbe adapter
+ * @ops : FCoE related command codes
+ *
+ * Supports op code NETDEV_FCOE_ENABLE to turn on FCoE offload
+ * features and op code NETDEV_FCOE_DISABLE to turn off FCoE
+ * offload features in 82599.
+ *
+ * Returns : 0 indicates success or -EINVAL on failure
+ */
+int ixgbe_fcoe_control(struct net_device *netdev, u32 op)
+{
+ int rc = -EINVAL;
+ struct ixgbe_adapter *adapter = netdev_priv(netdev);
+
+ if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE))
+ goto out;
+
+ switch (op) {
+ case NETDEV_FCOE_ENABLE:
+ rc = ixgbe_enable_fcoe(netdev);
+ break;
+ case NETDEV_FCOE_DISABLE:
+ rc = ixgbe_disable_fcoe(netdev);
+ break;
+ default:
+ break;
+ }
+out:
+ return rc;
+}
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index d69d277..9738317 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -5376,6 +5376,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
#ifdef IXGBE_FCOE
.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
+ .ndo_fcoe_control = ixgbe_fcoe_control,
#endif /* IXGBE_FCOE */
};
^ permalink raw reply related
* [net-next PATCH 06/12] vlan: Add support for net_devices_ops.ndo_fcoe_control to VLAN
From: Jeff Kirsher @ 2009-08-14 22:43 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo, Yi Zou, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
This adds implementation of the net_devices_ops.ndo_fcoe_control to the VLAN
driver. It checks if the real_dev has support for ndo_fcoe_control and pass on
to call the associated real_dev->netdevice_ops->ndo_fcoe_control.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/8021q/vlan_dev.c | 13 +++++++++++++
1 files changed, 13 insertions(+), 0 deletions(-)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 6e695ac..9a4ddf5 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -586,6 +586,17 @@ static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
return len;
}
+
+static int vlan_dev_fcoe_control(struct net_device *dev, u32 op)
+{
+ struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ const struct net_device_ops *ops = real_dev->netdev_ops;
+ int rc = -EINVAL;
+
+ if (ops->ndo_fcoe_control)
+ rc = ops->ndo_fcoe_control(real_dev, op);
+ return rc;
+}
#endif
static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
@@ -749,6 +760,7 @@ static const struct net_device_ops vlan_netdev_ops = {
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
.ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
+ .ndo_fcoe_control = vlan_dev_fcoe_control,
#endif
};
@@ -769,6 +781,7 @@ static const struct net_device_ops vlan_netdev_accel_ops = {
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
.ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
+ .ndo_fcoe_control = vlan_dev_fcoe_control,
#endif
};
^ permalink raw reply related
* [net-next PATCH 05/12] net: Add ndo_fcoe_control to net_device_ops
From: Jeff Kirsher @ 2009-08-14 22:42 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo, Yi Zou, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Add ndo_fcoe_control to net_device_ops so the corresponding HW can initialize
itself for FCoE traffic or clean up after FCoE traffic is done. This is
expected to be called by the kernel FCoE stack upon receiving a request for
creating an FCoE instance on the corresponding netdev interface. When
implemented by the actual HW, the HW driver check the op code to perform
corresponding initialization or clean up for FCoE. The initialization normally
includes allocating extra queues for FCoE, setting corresponding HW registers
for FCoE, indicating FCoE offload features via netdev, etc. The clean-up would
include releasing the resources allocated for FCoE.
Currently, there are two defined op codes as NETDEV_FCOE_DISABLE and _ENABLE,
for initialization and cleanup accordingly.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/linux/netdevice.h | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9192cdf..84c110b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -623,6 +623,10 @@ struct net_device_ops {
void (*ndo_poll_controller)(struct net_device *dev);
#endif
#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#define NETDEV_FCOE_DISABLE 0x0
+#define NETDEV_FCOE_ENABLE 0x1
+ int (*ndo_fcoe_control)(struct net_device *dev,
+ u32 op);
int (*ndo_fcoe_ddp_setup)(struct net_device *dev,
u16 xid,
struct scatterlist *sgl,
^ permalink raw reply related
* [net-next PATCH 04/12] ixgbe: Add support for NETIF_F_FCOE_MTU to 82599 devices
From: Jeff Kirsher @ 2009-08-14 22:42 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo, Yi Zou, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Enable netdev feature flag bit NETIF_F_FCOE_MTU for 82599 devices and enable
jumbo frame correspondingly when NETIF_F_FCOE_MTU is set.
Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe_dcb_nl.c | 4 ++++
drivers/net/ixgbe/ixgbe_main.c | 6 +++---
2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 116f12c..34bca45 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -148,8 +148,10 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
IXGBE_FCRETA_SIZE;
netdev->features |= NETIF_F_FCOE_CRC;
netdev->features |= NETIF_F_FSO;
+ netdev->features |= NETIF_F_FCOE_MTU;
netdev->vlan_features |= NETIF_F_FCOE_CRC;
netdev->vlan_features |= NETIF_F_FSO;
+ netdev->vlan_features |= NETIF_F_FCOE_MTU;
netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1;
netdev_features_change(netdev);
}
@@ -180,8 +182,10 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
adapter->ring_feature[RING_F_FCOE].indices = 0;
netdev->features &= ~NETIF_F_FCOE_CRC;
netdev->features &= ~NETIF_F_FSO;
+ netdev->features &= ~NETIF_F_FCOE_MTU;
netdev->vlan_features &= ~NETIF_F_FCOE_CRC;
netdev->vlan_features &= ~NETIF_F_FSO;
+ netdev->vlan_features &= ~NETIF_F_FCOE_MTU;
netdev->fcoe_ddp_xid = 0;
netdev_features_change(netdev);
}
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 8a8518d..d69d277 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -2026,7 +2026,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
else
hlreg0 |= IXGBE_HLREG0_JUMBOEN;
#ifdef IXGBE_FCOE
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+ if (netdev->features & NETIF_F_FCOE_MTU)
hlreg0 |= IXGBE_HLREG0_JUMBOEN;
#endif
IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0);
@@ -2057,7 +2057,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
rx_ring->flags |= IXGBE_RING_RX_PS_ENABLED;
#ifdef IXGBE_FCOE
- if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
+ if (netdev->features & NETIF_F_FCOE_MTU) {
struct ixgbe_ring_feature *f;
f = &adapter->ring_feature[RING_F_FCOE];
if ((i >= f->mask) && (i < f->mask + f->indices)) {
@@ -2609,7 +2609,7 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
#ifdef IXGBE_FCOE
/* adjust max frame to be able to do baby jumbo for FCoE */
- if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
+ if ((netdev->features & NETIF_F_FCOE_MTU) &&
(max_frame < IXGBE_FCOE_JUMBO_FRAME_SIZE))
max_frame = IXGBE_FCOE_JUMBO_FRAME_SIZE;
^ permalink raw reply related
* [net-next PATCH 03/12] net: Add NETIF_F_FCOE_MTU to indicate support for a different MTU for FCoE
From: Jeff Kirsher @ 2009-08-14 22:41 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo, Yi Zou, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Yi Zou <yi.zou@intel.com>
Add NETIF_F_FCOE_MTU to indicate that the NIC can support a secondary MTU for
converged traffic of LAN and Fiber Channel over Ethernet (FCoE). The MTU for
FCoE is 2158 = 14 (FCoE header) + 24 (FC header) + 2112 (FC max payload) +
4 (FC CRC) + 4 (FCoE trailer).
Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/linux/netdevice.h | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9f25ab2..9192cdf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -701,6 +701,7 @@ struct net_device
/* the GSO_MASK reserves bits 16 through 23 */
#define NETIF_F_FCOE_CRC (1 << 24) /* FCoE CRC32 */
#define NETIF_F_SCTP_CSUM (1 << 25) /* SCTP checksum offload */
+#define NETIF_F_FCOE_MTU (1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
/* Segmentation offload features */
#define NETIF_F_GSO_SHIFT 16
^ permalink raw reply related
* Re: [PATCH 0/9] sky2: version 1.24
From: David Miller @ 2009-08-14 22:41 UTC (permalink / raw)
To: shemminger; +Cc: netdev
In-Reply-To: <20090814151511.992669598@vyatta.com>
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Fri, 14 Aug 2009 08:15:11 -0700
> This is rework of some of Mike's patches, and additional
> improvement in the restart logic.
Patches themselves look good.
> Patch against current net-next-2.6.
Ummm... no, it isn't.
I merged net-2.6 into net-next-2.6 yesterday, which brought in various
sky2 fixes. This caused conflicts which I had to hand merge starting
in patch #6.
For example, in patch #6:
@@ -1498,10 +1498,9 @@ static int sky2_up(struct net_device *de
sky2_write32(hw, B0_IMSK, imask);
sky2_read32(hw, B0_IMSK);
- sky2_set_multicast(dev);
-
if (netif_msg_ifup(sky2))
printk(KERN_INFO PFX "%s: enabling interface\n", dev->name);
+
return 0;
err_out:
There is a netif_wake_queue() call right before the if (netif_msg_ifup)
Then, in patch #7:
@@ -2367,11 +2363,8 @@ static inline void sky2_tx_done(struct n
{
struct sky2_port *sky2 = netdev_priv(dev);
- if (netif_running(dev)) {
- netif_tx_lock(dev);
+ if (netif_running(dev))
sky2_tx_complete(sky2, last);
- netif_tx_unlock(dev);
- }
}
static inline void sky2_skb_rx(const struct sky2_port *sky2,
That if () test has an extra condition "&& !sky2->restarting",
I retained in when applying that patch.
Then, in patch #8:
@@ -2042,15 +2041,18 @@ struct sky2_port {
u8 fifo_lev;
} check;
-
dma_addr_t rx_le_map;
dma_addr_t tx_le_map;
+
u16 advertising; /* ADVERTISED_ bits */
- u16 speed; /* SPEED_1000, SPEED_100, ... */
- u8 autoneg; /* AUTONEG_ENABLE, AUTONEG_DISABLE */
- u8 duplex; /* DUPLEX_HALF, DUPLEX_FULL */
- u8 rx_csum;
- u8 wol;
+ u16 speed; /* SPEED_1000, SPEED_100, ... */
+ u8 wol; /* WAKE_ bits */
+ u8 duplex; /* DUPLEX_HALF, DUPLEX_FULL */
+ u16 flags;
+#define SKY2_FLAG_RX_CHECKSUM 0x0001
+#define SKY2_FLAG_AUTO_SPEED 0x0002
+#define SKY2_FLAG_AUTO_PAUSE 0x0004
+
enum flow_control flow_mode;
enum flow_control flow_status;
This is missing the "->restarting" member, I retained it while
applying this patch.
Even if whatever net-next-2.6 tree you patches against didn't have
those fixes, you should have anticipated them and known that I'd
have to end up sorting out the merge mess afterwards.
Anyways I pushed it all out, send me fixup patches if necessary.
^ permalink raw reply
* [net-next PATCH 02/12] ixgbe: updates vlan feature flags to enable FCoE offloads on vlan interface
From: Jeff Kirsher @ 2009-08-14 22:41 UTC (permalink / raw)
To: davem
Cc: netdev, linux-scsi, gospo, Vasu Dev, Yi Zou,
Peter P Waskiewicz Jr, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Vasu Dev <vasu.dev@intel.com>
Updates netdev->vlan_features for NETIF_F_FCOE_CRC and NETIF_F_FSO, so that
FCoE CRC and GSO offloads will get used for FCoE over ixgbe based vlan
interface.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Signed-off-by: Yi Zou <yi.zou@intel.com>
Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ixgbe/ixgbe_dcb_nl.c | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 1c72657..116f12c 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -148,7 +148,10 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
IXGBE_FCRETA_SIZE;
netdev->features |= NETIF_F_FCOE_CRC;
netdev->features |= NETIF_F_FSO;
+ netdev->vlan_features |= NETIF_F_FCOE_CRC;
+ netdev->vlan_features |= NETIF_F_FSO;
netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1;
+ netdev_features_change(netdev);
}
#endif /* IXGBE_FCOE */
ixgbe_init_interrupt_scheme(adapter);
@@ -177,7 +180,10 @@ static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state)
adapter->ring_feature[RING_F_FCOE].indices = 0;
netdev->features &= ~NETIF_F_FCOE_CRC;
netdev->features &= ~NETIF_F_FSO;
+ netdev->vlan_features &= ~NETIF_F_FCOE_CRC;
+ netdev->vlan_features &= ~NETIF_F_FSO;
netdev->fcoe_ddp_xid = 0;
+ netdev_features_change(netdev);
}
#endif /* IXGBE_FCOE */
ixgbe_init_interrupt_scheme(adapter);
^ permalink raw reply related
* [net-next PATCH 01/12] vlan: adds fcoe offload related net_device_ops and updates fcoe_ddp_xid field
From: Jeff Kirsher @ 2009-08-14 22:41 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo, Vasu Dev, Jeff Kirsher
In-Reply-To: <20090814223857.1640.26881.stgit@localhost.localdomain>
From: Vasu Dev <vasu.dev@intel.com>
Adds fcoe offload related net_device_ops functions vlan_dev_fcoe_ddp_setup
and vlan_dev_fcoe_ddp_done, their implementation simply calls real eth device
net_device_ops for FCoE DDP setup and done operations.
Updates VLAN netdev field value for fcoe_ddp_xid from real eth device netdev.
Above changes are required for fcoe DDP offload working on a VLAN interface.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/8021q/vlan.c | 3 +++
net/8021q/vlan_dev.c | 39 +++++++++++++++++++++++++++++++++++++++
2 files changed, 42 insertions(+), 0 deletions(-)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index a1f1630..e814794 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -391,6 +391,9 @@ static void vlan_transfer_features(struct net_device *dev,
vlandev->features &= ~dev->vlan_features;
vlandev->features |= dev->features & dev->vlan_features;
vlandev->gso_max_size = dev->gso_max_size;
+#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+ vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
+#endif
if (old_features != vlandev->features)
netdev_features_change(vlandev);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 96bad8f..6e695ac 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -561,6 +561,33 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
return err;
}
+#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
+ struct scatterlist *sgl, unsigned int sgc)
+{
+ struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ const struct net_device_ops *ops = real_dev->netdev_ops;
+ int rc = 0;
+
+ if (ops->ndo_fcoe_ddp_setup)
+ rc = ops->ndo_fcoe_ddp_setup(real_dev, xid, sgl, sgc);
+
+ return rc;
+}
+
+static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
+{
+ struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+ const struct net_device_ops *ops = real_dev->netdev_ops;
+ int len = 0;
+
+ if (ops->ndo_fcoe_ddp_done)
+ len = ops->ndo_fcoe_ddp_done(real_dev, xid);
+
+ return len;
+}
+#endif
+
static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
{
struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
@@ -635,6 +662,10 @@ static int vlan_dev_init(struct net_device *dev)
if (is_zero_ether_addr(dev->broadcast))
memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
+#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+ dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid;
+#endif
+
if (real_dev->features & NETIF_F_HW_VLAN_TX) {
dev->header_ops = real_dev->header_ops;
dev->hard_header_len = real_dev->hard_header_len;
@@ -715,6 +746,10 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_change_rx_flags = vlan_dev_change_rx_flags,
.ndo_do_ioctl = vlan_dev_ioctl,
.ndo_neigh_setup = vlan_dev_neigh_setup,
+#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+ .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
+ .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
+#endif
};
static const struct net_device_ops vlan_netdev_accel_ops = {
@@ -731,6 +766,10 @@ static const struct net_device_ops vlan_netdev_accel_ops = {
.ndo_change_rx_flags = vlan_dev_change_rx_flags,
.ndo_do_ioctl = vlan_dev_ioctl,
.ndo_neigh_setup = vlan_dev_neigh_setup,
+#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+ .ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
+ .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
+#endif
};
void vlan_setup(struct net_device *dev)
^ permalink raw reply related
* [net-next PATCH 00/12] ixgbe/vlan/DCB patch set
From: Jeff Kirsher @ 2009-08-14 22:40 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-scsi, gospo
Please merge net-2.6 then apply this set...
---
Vasu Dev (2):
ixgbe: updates vlan feature flags to enable FCoE offloads on vlan interface
vlan: adds fcoe offload related net_device_ops and updates fcoe_ddp_xid field
Yi Zou (10):
ixgbe: Add support for dcbnl_rtnl_ops.setapp/getapp
dcbnl: Add implementations of dcbnl setapp/getapp commands
dcbnl: Add netlink attributes for setapp/getapp to dcbnl
dcbnl: Add support for setapp/getapp to netdev dcbnl_rtnl_ops
dcbnl: Add support for setapp/getapp commands to dcbnl
ixgbe: Add support for the net_device_ops.ndo_fcoe_control to 82599
vlan: Add support for net_devices_ops.ndo_fcoe_control to VLAN
net: Add ndo_fcoe_control to net_device_ops
ixgbe: Add support for NETIF_F_FCOE_MTU to 82599 devices
net: Add NETIF_F_FCOE_MTU to indicate support for a different MTU for FCoE
drivers/net/ixgbe/ixgbe.h | 5 +
drivers/net/ixgbe/ixgbe_dcb_nl.c | 83 ++++++++++++-----
drivers/net/ixgbe/ixgbe_fcoe.c | 184 ++++++++++++++++++++++++++++++++++++++
drivers/net/ixgbe/ixgbe_fcoe.h | 4 +
drivers/net/ixgbe/ixgbe_main.c | 9 +-
include/linux/dcbnl.h | 18 ++++
include/linux/netdevice.h | 5 +
include/net/dcbnl.h | 2
net/8021q/vlan.c | 3 +
net/8021q/vlan_dev.c | 52 +++++++++++
net/dcb/dcbnl.c | 130 +++++++++++++++++++++++++++
11 files changed, 469 insertions(+), 26 deletions(-)
--
Cheers,
Jeff
^ permalink raw reply
* [RFC] bridge: prevent hairpin and STP problems?
From: Stephen Hemminger @ 2009-08-14 21:41 UTC (permalink / raw)
To: David Miller
Cc: anna.fischer, netdev, ptcongdon, evb, bridge, kaber, arnd,
mike.dickson, adobriyan, bridge
In-Reply-To: <20090813.162716.207478915.davem@davemloft.net>
Do we need to add this to block Spanning Tree from being enabled
with hairpin mode? I am not sure what the exact usage of hairpin
mode and if it is possible to create loops and get STP confusion.
For comment only, do not apply as is.
--- a/net/bridge/br_ioctl.c 2009-08-14 14:28:19.917690805 -0700
+++ b/net/bridge/br_ioctl.c 2009-08-14 14:29:54.078271361 -0700
@@ -259,8 +259,7 @@ static int old_dev_ioctl(struct net_devi
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- br_stp_set_enabled(br, args[1]);
- return 0;
+ return br_stp_set_enabled(br, args[1]);
case BRCTL_SET_BRIDGE_PRIORITY:
if (!capable(CAP_NET_ADMIN))
--- a/net/bridge/br_stp_if.c 2009-08-14 14:24:30.022315573 -0700
+++ b/net/bridge/br_stp_if.c 2009-08-14 14:35:25.819566113 -0700
@@ -160,17 +160,26 @@ static void br_stp_stop(struct net_bridg
br->stp_enabled = BR_NO_STP;
}
-void br_stp_set_enabled(struct net_bridge *br, unsigned long val)
+int br_stp_set_enabled(struct net_bridge *br, unsigned long val)
{
ASSERT_RTNL();
if (val) {
+ struct net_bridge_port *p;
+ list_for_each_entry_rcu(p, &br->port_list, list) {
+ if (p->flags & BR_HAIRPIN_MODE)
+ return -EINVAL;
+ }
+
+
if (br->stp_enabled == BR_NO_STP)
br_stp_start(br);
} else {
if (br->stp_enabled != BR_NO_STP)
br_stp_stop(br);
}
+
+ return 0;
}
/* called under bridge lock */
--- a/net/bridge/br_sysfs_br.c 2009-08-14 14:24:36.874256194 -0700
+++ b/net/bridge/br_sysfs_br.c 2009-08-14 14:33:26.025441102 -0700
@@ -164,6 +164,7 @@ static ssize_t store_stp_state(struct de
struct net_bridge *br = to_bridge(d);
char *endp;
unsigned long val;
+ int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -174,10 +175,11 @@ static ssize_t store_stp_state(struct de
if (!rtnl_trylock())
return restart_syscall();
- br_stp_set_enabled(br, val);
+
+ ret = br_stp_set_enabled(br, val);
rtnl_unlock();
- return len;
+ return (ret == 0) ? len : ret;
}
static DEVICE_ATTR(stp_state, S_IRUGO | S_IWUSR, show_stp_state,
store_stp_state);
--- a/net/bridge/br_sysfs_if.c 2009-08-14 14:24:36.888356879 -0700
+++ b/net/bridge/br_sysfs_if.c 2009-08-14 14:34:55.339272738 -0700
@@ -150,10 +150,13 @@ static ssize_t show_hairpin_mode(struct
}
static ssize_t store_hairpin_mode(struct net_bridge_port *p, unsigned long v)
{
- if (v)
+ if (!v)
+ p->flags &= ~BR_HAIRPIN_MODE;
+ else if (p->br->stp_enabled == BR_NO_STP)
p->flags |= BR_HAIRPIN_MODE;
else
- p->flags &= ~BR_HAIRPIN_MODE;
+ return -EINVAL;
+
return 0;
}
static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR,
--- a/net/bridge/br_private.h 2009-08-14 14:34:05.263278817 -0700
+++ b/net/bridge/br_private.h 2009-08-14 14:34:15.717297908 -0700
@@ -218,7 +218,7 @@ extern void br_become_designated_port(st
/* br_stp_if.c */
extern void br_stp_enable_bridge(struct net_bridge *br);
extern void br_stp_disable_bridge(struct net_bridge *br);
-extern void br_stp_set_enabled(struct net_bridge *br, unsigned long val);
+extern int br_stp_set_enabled(struct net_bridge *br, unsigned long val);
extern void br_stp_enable_port(struct net_bridge_port *p);
extern void br_stp_disable_port(struct net_bridge_port *p);
extern void br_stp_recalculate_bridge_id(struct net_bridge *br);
^ permalink raw reply
* Re: [PATCH] Speed-up pfifo_fast lookup using a bitmap
From: Jarek Poplawski @ 2009-08-14 21:36 UTC (permalink / raw)
To: Krishna Kumar; +Cc: kaber, netdev, davem, herbert
In-Reply-To: <20090814132458.27518.65144.sendpatchset@localhost.localdomain>
On Fri, Aug 14, 2009 at 06:54:58PM +0530, Krishna Kumar wrote:
> ďťżHi Jarek,
>
> Jarek Poplawski <jarkao2@gmail.com> wrote on 08/14/2009 04:31:27 PM:
>
> > Alas, private or public, these values are lower on average than
> > before, so I'm not sure the complexity (especially in reading) added
> > by this patch is worth it. So, I can only say it looks formally OK,
> > except the changelog and maybe 2 cosmetical suggestions below.
>
> Maybe the different test parameters result in smaller improvements.
> I agree with you - the first approach is very readable and probably
> preferable, while the second introduces a new structure and more
> complexity.
Actually, I meant the complexity added by any of these versions. If
you declare: "This helps in faster lookup for a skb when there are no
high priority skbs.", there is a question if less than 1% is enough.
> I am sending both these versions a last time, after fixing your
> comments in case someone can help decide if one or the other is
> better (sorry I forgot to run checkpatch couple of times, will try
> to remember next time).
I definitely can't see a reason to make this variable public, and
prefer the private (v2) version (which still lacks a changelog, btw).
Thanks,
Jarek P.
^ permalink raw reply
* Re: Receive side performance issue with multi-10-GigE and NUMA
From: Aviv Greenberg @ 2009-08-14 21:13 UTC (permalink / raw)
To: Andrew Gallatin; +Cc: Bill Fink, netdev
In-Reply-To: <4A859716.7040904@myri.com>
> There may be something in the chipset
shooting in the dark: when you lspci -vvv and check the MaxPayload and
MaxReadReq values for the myri devices - what are the values and are
they equal? Are they the same on all your platforms?
^ permalink raw reply
* Re: [net-next-2.6 PATCH] net/ethtool: Add support to the ethtool feature to flash firmware image from a specified file.
From: Ben Hutchings @ 2009-08-14 20:58 UTC (permalink / raw)
To: Ajit Khaparde; +Cc: davem, jgarzik, netdev
In-Reply-To: <20090814173314.GA26218@serverengines.com>
On Fri, 2009-08-14 at 23:03 +0530, Ajit Khaparde wrote:
> This patch adds support to flash a firmware image to a device using ethtool.
> The driver gets the filename of the firmware image and flashes this image
> using the request_firmware() path.
>
> Signed-off-by: Ajit Khaparde <ajitk@serverengines.com>
> ---
> include/linux/ethtool.h | 8 ++++++++
> net/core/ethtool.c | 17 +++++++++++++++++
> 2 files changed, 25 insertions(+), 0 deletions(-)
>
> diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
> index 90c4a36..243cdce 100644
> --- a/include/linux/ethtool.h
> +++ b/include/linux/ethtool.h
> @@ -362,6 +362,12 @@ struct ethtool_rxnfc {
> __u32 rule_locs[0];
> };
>
> +/* for passing firmware flashing related parameters */
> +struct ethtool_flash {
> + __u32 cmd;
> + __u8 *data;
There also needs to be some sort of identifier to distinguish different
flash regions.
[...]
> --- a/net/core/ethtool.c
> +++ b/net/core/ethtool.c
> @@ -898,6 +898,20 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr,
> return actor(dev, edata.data);
> }
>
> +static int ethtool_flash_device(struct net_device *dev, char __user *useraddr)
> +{
> + int err;
> + struct ethtool_flash efl;
> +
> + if (copy_from_user(&efl, useraddr, sizeof(efl)))
> + return -EFAULT;
[...]
This leaves efl.data as a user-space pointer, not a kernel-space
pointer. The string will then also need to be copied. It's simpler to
embed the string in the structure, though that means putting a limit on
the string length.
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: Receive side performance issue with multi-10-GigE and NUMA
From: Bill Fink @ 2009-08-14 20:44 UTC (permalink / raw)
To: Neil Horman; +Cc: Linux Network Developers, brice, gallatin
In-Reply-To: <20090808015612.GA17710@localhost.localdomain>
On Fri, 7 Aug 2009, Neil Horman wrote:
> On Fri, Aug 07, 2009 at 08:54:42PM -0400, Bill Fink wrote:
> > On Fri, 7 Aug 2009, Neil Horman wrote:
> >
> > > You're timing is impeccable! I just posted a patch for an ftrace module to help
> > > detect just these kind of conditions:
> > > http://marc.info/?l=linux-netdev&m=124967650218846&w=2
> > >
> > > Hope that helps you out
> > > Neil
> >
> > Thanks! It could be helpful. Do you have a pointer to documentation
> > on how to use it? And does it require the latest GIT kernel or could
> > it possibly be used with a 2.6.29.6 kernel?
> >
> > -Bill
>
> It should apply to 2.6.29.6 no problem (might take a little massaging, but not
> much).
It doesn't look like I can apply your patches to my 2.6.29.6 kernel.
For starters, there's no include/trace/events directory, so there's
no include/trace/events/skb.h. There is an include/trace/skb.h file,
but there's no TRACE_EVENT defined anywhere in the kernel.
I don't suppose it's as simple as defining (from include/linux/tracepoint.h
from Linus's GIT tree):
#define PARAMS(args...) args
#define TRACE_EVENT(name, proto, args, struct, assign, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
So do you still think it's reasonable to try applying your patches
to my 2.6.29.6 kernel, or should I get a newer kernel like 2.6.30.4
or 2.6.31-rc6?
-Thanks
-Bill
> No docs I'm afraid (sorry, I'm horrible about that)
>
> Using it is easy though:
>
> 1) Patch, build and boot the kernel (make sure to have
> CONFIG_SKB_SOURCES_TRACER, along with the other FTRACE requisite options)
>
> 2) mount -t debugfs nodev /sys/kernel/debug
>
> 3) cd /sys/kernel/debug/tracing
>
> 4) echo skb_sources > ./current_tracer
>
> 5) echo 1 > trace
>
> 6) cat ./trace
>
> Step 5 clears the trace buffer. Step 6 provides you a list list this
>
>
> PID ANID CNID RXQ CCPU LEN
>
>
> Where:
> PID - The process receiving an skb
> ANID - The node which the skb being received was allocated on
> CNID - The node which the process is running when it read this skb
> RQQ - The NIC receive queue that received this skb
> CCPU - The cpu the process was running on when it read the skb in question
> LEN - The length of the skb being received
>
> Each entry in the list denotes a unique skb (obviously), and with a clever awk
> script you can identify which nodes each process in your system is receiving
> frames from, so that you can use numactl or taskset to bias that process to run
> on the same nodes cpus.
>
> Note that step (6) wil show a larger list each time you cat that file (as trace
> records aren't removed during a read. Step 5 is what actually clears the trace
> buffer and resets the list length to zero.
>
> Hope that helps. Please feel free to email me if you have any questions.
^ permalink raw reply
* Re: Receive side performance issue with multi-10-GigE and NUMA
From: Bill Fink @ 2009-08-14 20:31 UTC (permalink / raw)
To: Bill Fink
Cc: Brandeburg, Jesse, Neil Horman, Andrew Gallatin, Brice Goglin,
Linux Network Developers, Yinghai Lu, jbarnes@virtuousgeek.org
In-Reply-To: <20090812003824.26c9c8fb.billfink@mindspring.com>
On Wed, 12 Aug 2009, Bill Fink wrote:
> On Tue, 11 Aug 2009, Brandeburg, Jesse wrote:
>
> > Bill Fink wrote:
> > > On Sat, 8 Aug 2009, Neil Horman wrote:
> > >
> > >> On Sat, Aug 08, 2009 at 02:21:36PM -0400, Andrew Gallatin wrote:
> > >>> Neil Horman wrote:
> > >>>> On Sat, Aug 08, 2009 at 07:08:20AM -0400, Andrew Gallatin wrote:
> > >>>>> Bill Fink wrote:
> > >>>>>> On Fri, 07 Aug 2009, Andrew Gallatin wrote:
> > >>>>>>
> > >>>>>>> Bill Fink wrote:
> > >>>>>>>
> > >>>>>>>> All sysfs local_cpus values are the same (00000000,000000ff),
> > >>>>>>>> so yes they are also wrong.
> >
> > bill, I recently helped Jesse Barnes push a patch that addresses this kind
> > of issue on CoreI7, the root cause was the numa_node variable was
> > initialized based on slot on AMD systems, but needed to be set to -1 by
> > default on systems with a uniform IOH to slot architecture.
> >
> > here is the commit ID:
> > http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git;a=commit;h=3c38
> > d674be519109696746192943a6d524019f7f
> >
> > I'm not sure it is in linus' tree yet, this link is to net-next
> >
> > Maybe see if it helps?
>
> It's worth a shot.
>
> Hopefully I can get a chance to build a new kernel tomorrow to check
> out some of the suggestions, like this one, the setting of ACPI_DEBUG,
> and the new ftrace module for checking NUMA affinity of skbs.
I applied this patch to my 2.6.29.6 kernel (from Fedora 11).
Now when I do:
find /sys -name numa_node -exec grep . {} /dev/null \;
the numa_node for _all_ PCI devices is -1.
When I do:
find /sys -name local_cpus -exec grep . {} /dev/null \;
I find that local_cpus is always 00000000,00000000.
Is that OK or should it be 00000000,000000ff (for my dual quad-core
Xeon 5580 system with no hyperthreading)?
Also, is it just not possible on this type of Intel Xeon system to
properly associate the PCI devices with the nearest NUMA node?
In any event, the patch didn't help (or hurt). The transmit
performance remained at ~100 Gbps while the receive performance
remained at 55 Gbps.
-Thanks
-Bill
^ permalink raw reply
* Re: [RFC] ipv6: Change %pI6 format to output compacted addresses?
From: David Miller @ 2009-08-14 20:12 UTC (permalink / raw)
To: jens; +Cc: joe, chuck.lever, brian.haley, netdev
In-Reply-To: <1250237739.16632.12.camel@fnki-nb00130>
From: Jens Rosenboom <jens@mcbone.net>
Date: Fri, 14 Aug 2009 10:15:39 +0200
> I wasn't sure whether "currently user visible stuff" would mean "user
> space interfaces" like sys/proc-fs, which the first quoted post asked
> about, or also kernel messages.
I'd say that kernel log messages are OK to tinker with, whereas procfs
and sysfs file contents are not.
^ permalink raw reply
* Re: AlacrityVM numbers updated for 31-rc4
From: Gregory Haskins @ 2009-08-14 19:50 UTC (permalink / raw)
To: Anthony Liguori
Cc: alacrityvm-devel, alacrityvm-users, linux-kernel@vger.kernel.org,
kvm@vger.kernel.org, Michael S. Tsirkin, netdev
In-Reply-To: <4A834E75.9060204@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1424 bytes --]
Gregory Haskins wrote:
> Anthony Liguori wrote:
>> Gregory Haskins wrote:
>>> I re-ran the numbers on 10GE against the actual alacrityvm v0.1 release
>>> available in git on kernel.org.
>>>
>>> I tried to include the newly announced "vhost" driver (Michael Tsirkin)
>>> for virtio acceleration, but ran into issues getting the patches to
>>> apply.
>>>
>>> For now, this includes native, virtio-u (virtio-userspace), and venet
>>> all running on 31-rc4. If I can resolve the issue with Michaels
>>> patches, I will add "virtio-k" (virtio-kernel) to the mix as well. For
>>> now, here are the results for 1500mtu:
>>>
>>> native: 7388Mb/s, 29.8us rtt (33505 tps udp-rr)
>>> venet: 3654Mb/s, 56.8us rtt (17600 tps udp-rr)
>>> virtio-u: 1955Mb/s, 4016.0us rtt ( 249 tps udp-rr)
>>>
I re-ran the numbers now that I have the HRT issue straighted out.
Native and virtio stayed level, venet recovered from the 3.6Gb/s
quagmire it was in, back up to ~4.5Gb/s.
native (hw): 7388Mb/s, 29.8us rtt (33500 tps udp-rr)
venet (alacrityvm): 4560Mb/s, 56.8us rtt (17600 tps udp-rr)
virtio-u (kvm): 2670Mb/s, 265.7us rtt ( 3764 tps udp-rr)
virtio-k (kvm): d-n-f
(still having problems getting vhost to run). Will try again next week.)
I have updated the graphs on the wiki:
http://developer.novell.com/wiki/index.php/AlacrityVM
Have a nice weekend, all.
-Greg
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 267 bytes --]
^ permalink raw reply
* Re: pull request: wireless-next-2.6 2009-08-14
From: David Miller @ 2009-08-14 19:29 UTC (permalink / raw)
To: linville; +Cc: linux-wireless, netdev
In-Reply-To: <20090814141315.GI2650@tuxdriver.com>
From: "John W. Linville" <linville@tuxdriver.com>
Date: Fri, 14 Aug 2009 10:13:15 -0400
> Yet another round of updates intended for 2.6.32...
>
> -- sdio support fo wl1251
> -- other wl1251 fixes
> -- new driver for wl1271
> -- some orinoco fixes
> -- some work on LP-PHY support for b43 (finally...hooray!)
> -- add new FIF_PSPOLL filter flag
> -- mesh mode fixes
> -- ath9k, ath5k, mac80211 updates, etc...
>
> Please let me know if there are problems!
Looks good, pulled, thanks!
^ permalink raw reply
* Re: pull request: wireless-2.6 2009-08-14
From: David Miller @ 2009-08-14 19:28 UTC (permalink / raw)
To: linville-2XuSBdqkA4R54TAoqtyWWQ
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20090814141224.GH2650-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
From: "John W. Linville" <linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org>
Date: Fri, 14 Aug 2009 10:12:24 -0400
> A couple more squeakers for 2.6.31...one avoids a panic related to
> 802.11n, the other avoids some memory corruption with rt2x00 devices.
Pulled, thanks John.
--
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
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