* [PATCH 22/27] net/dccp: Use memdup_user
From: Julia Lawall @ 2010-05-22 8:25 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, David S. Miller, dccp, netdev,
linux-kernel, kernel-janitor
From: Julia Lawall <julia@diku.dk>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
---
net/dccp/proto.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b03ecf6..f79bcef 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -473,14 +473,9 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type,
if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
return -EINVAL;
- val = kmalloc(optlen, GFP_KERNEL);
- if (val == NULL)
- return -ENOMEM;
-
- if (copy_from_user(val, optval, optlen)) {
- kfree(val);
- return -EFAULT;
- }
+ val = memdup_user(optval, optlen);
+ if (IS_ERR(val))
+ return PTR_ERR(val);
lock_sock(sk);
if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
^ permalink raw reply related
* [PATCH 7/27] drivers/net/wan: Use memdup_user
From: Julia Lawall @ 2010-05-22 8:20 UTC (permalink / raw)
To: Mike McLagan, netdev, linux-kernel, kernel-janitors
From: Julia Lawall <julia@diku.dk>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
---
drivers/net/wan/sdla.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index 43ae6f4..258efc2 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -1211,14 +1211,9 @@ static int sdla_xfer(struct net_device *dev, struct sdla_mem __user *info, int r
}
else
{
- temp = kmalloc(mem.len, GFP_KERNEL);
- if (!temp)
- return(-ENOMEM);
- if(copy_from_user(temp, mem.data, mem.len))
- {
- kfree(temp);
- return -EFAULT;
- }
+ temp = memdup_user(mem.data, mem.len);
+ if (IS_ERR(temp))
+ return PTR_ERR(temp);
sdla_write(dev, mem.addr, temp, mem.len);
kfree(temp);
}
^ permalink raw reply related
* [PATCH 6/27] drivers/net/cxgb3: Use memdup_user
From: Julia Lawall @ 2010-05-22 8:20 UTC (permalink / raw)
To: Divy Le Ray, netdev, linux-kernel, kernel-janitors
From: Julia Lawall <julia@diku.dk>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
---
drivers/net/cxgb3/cxgb3_main.c | 12 +++---------
1 file changed, 3 insertions(+), 9 deletions(-)
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index e3f1b85..066fd5b 100644
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -2311,15 +2311,9 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
if (copy_from_user(&t, useraddr, sizeof(t)))
return -EFAULT;
/* Check t.len sanity ? */
- fw_data = kmalloc(t.len, GFP_KERNEL);
- if (!fw_data)
- return -ENOMEM;
-
- if (copy_from_user
- (fw_data, useraddr + sizeof(t), t.len)) {
- kfree(fw_data);
- return -EFAULT;
- }
+ fw_data = memdup_user(useraddr + sizeof(t), t.len);
+ if (IS_ERR(fw_data))
+ return PTR_ERR(fw_data);
ret = t3_load_fw(adapter, fw_data, t.len);
kfree(fw_data);
^ permalink raw reply related
* [PATCH 2/27] drivers/net: Use memdup_user
From: Julia Lawall @ 2010-05-22 8:18 UTC (permalink / raw)
To: Paul Mackerras, linux-ppp, netdev, linux-kernel, kernel-janitors
From: Julia Lawall <julia@diku.dk>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
---
drivers/net/ppp_generic.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 5441688..da7943d 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -539,14 +539,9 @@ static int get_filter(void __user *arg, struct sock_filter **p)
}
len = uprog.len * sizeof(struct sock_filter);
- code = kmalloc(len, GFP_KERNEL);
- if (code == NULL)
- return -ENOMEM;
-
- if (copy_from_user(code, uprog.filter, len)) {
- kfree(code);
- return -EFAULT;
- }
+ code = memdup_user(uprog.filter, len);
+ if (IS_ERR(code))
+ return PTR_ERR(code);
err = sk_chk_filter(code, uprog.len);
if (err) {
^ permalink raw reply related
* [PATCH 1/27] net/can: Use memdup_user
From: Julia Lawall @ 2010-05-22 8:18 UTC (permalink / raw)
To: Oliver Hartkopp, Urs Thuermann, David S. Miller, socketcan-core,
netdev
From: Julia Lawall <julia@diku.dk>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
---
net/can/raw.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/net/can/raw.c b/net/can/raw.c
index da99cf1..ccfe633 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -436,14 +436,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
if (count > 1) {
/* filter does not fit into dfilter => alloc space */
- filter = kmalloc(optlen, GFP_KERNEL);
- if (!filter)
- return -ENOMEM;
-
- if (copy_from_user(filter, optval, optlen)) {
- kfree(filter);
- return -EFAULT;
- }
+ filter = memdup_user(optval, optlen);
+ if (IS_ERR(filter))
+ return PTR_ERR(filter);
} else if (count == 1) {
if (copy_from_user(&sfilter, optval, sizeof(sfilter)))
return -EFAULT;
^ permalink raw reply related
* Re: tc: RTM_GETQDISC causes kernel OOPS
From: Eric Dumazet @ 2010-05-22 7:18 UTC (permalink / raw)
To: Ben Pfaff; +Cc: Jamal Hadi Salim, netdev, Patrick McHardy
In-Reply-To: <20100521224243.GD10247@nicira.com>
Le vendredi 21 mai 2010 à 15:42 -0700, Ben Pfaff a écrit :
> Hi. While working on some library code for working with qdiscs and
> classes I came upon a kernel OOPS. Originally I came across it with a
> 2.6.26 kernel, but I can also reproduce it with unmodified v2.6.34 from
> kernel.org.
>
> At the end of this mail I'm appending both an example of the OOPS and a
> simple test program that reliably reproduces the problem for me when I
> invoke it with "lo" as argument. The program does not need to be run as
> root.
>
> After the OOPS, a lot of networking and other system functions stop
> working, so it seems to me a serious issue.
>
> The null pointer dereference that causes the OOPS is the dereference of
> the return value of qdisc_dev() in tc_fill_qdisc() in
> net/sched/sch_api.c line 1163:
>
> 1161 tcm->tcm__pad1 = 0;
> 1162 tcm->tcm__pad2 = 0;
> 1163 tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
> 1164 tcm->tcm_parent = clid;
> 1165 tcm->tcm_handle = q->handle;
>
> I am pretty sure about that, because if I add "WARN_ON(!qdisc_dev(q));"
> just before line 1163 then that warning triggers.
>
> Thanks,
Indeed, thanks for this very useful report !
We could add a check for TCQ_F_BUILTIN flag, or just make
qdisc_notify() checks consistent for both old and new qdisc
What other people thinks ?
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index fe35c1f..e454c73 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1210,7 +1210,7 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb,
if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0)
goto err_out;
}
- if (new) {
+ if (new && new->handle) {
if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0)
goto err_out;
}
^ permalink raw reply related
* Re: [PATCH] rtnetlink: Fix error handling in do_setlink()
From: Chris Wright @ 2010-05-22 6:52 UTC (permalink / raw)
To: David Howells; +Cc: netdev, Chris Wright, David S. Miller
In-Reply-To: <20100521122527.20442.77793.stgit@warthog.procyon.org.uk>
* David Howells (dhowells@redhat.com) wrote:
> Commit c02db8c6290bb992442fec1407643c94cc414375:
>
> Author: Chris Wright <chrisw@sous-sol.org>
> Date: Sun May 16 01:05:45 2010 -0700
> Subject: rtnetlink: make SR-IOV VF interface symmetric
>
> adds broken error handling to do_setlink() in net/core/rtnetlink.c. The
> problem is the following chunk of code:
>
> if (tb[IFLA_VFINFO_LIST]) {
> struct nlattr *attr;
> int rem;
> nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
> if (nla_type(attr) != IFLA_VF_INFO)
> ----> goto errout;
> err = do_setvfinfo(dev, attr);
> if (err < 0)
> goto errout;
> modified = 1;
> }
> }
>
> which can get to errout without setting err, resulting in the following error:
>
> net/core/rtnetlink.c: In function 'do_setlink':
> net/core/rtnetlink.c:904: warning: 'err' may be used uninitialized in this function
>
> Change the code to return -EINVAL in this case. Note that this might not be
> the appropriate error though.
>
> Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Chris Wright <chrisw@sous-sol.org>
Thank you David, that's correct. I have some other pending changes
here, so I don't mind collecting them together.
thanks,
-chris
^ permalink raw reply
* Re: VLANs, bonding redux: vlan state does not follow ethernet
From: George B. @ 2010-05-22 6:45 UTC (permalink / raw)
To: netdev
In-Reply-To: <AANLkTimxJHKjAEm7wMYObFn9U3Sc1WPRYUuFFIKwwAyD@mail.gmail.com>
On Fri, May 21, 2010 at 11:24 PM, George B. <georgeb@gmail.com> wrote:
> Using 2.6.34 I am trying to remove bottlenecks. Instead of bonding
> two ethernet interfaces and applying vlans to the bond, I am applying
> the vlans to the ethernet and bonding the vlans creating a separate
> bond interface for each vlan.
>
> The trouble now is that the bond interface does not see when the
> ethernet interface goes down. The vlan reports to the bonding driver
> that it is up when the ethernet it is connected to is down. This
> results in packet loss through the bond interface as the bond driver
> attempts to use that vlan.
>
> eth1 shows having no link:
>
> root@sandbox:/proc/net# ethtool eth1
> Settings for eth1:
> Supported ports: [ TP ]
> Supported link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> 1000baseT/Full
> Supports auto-negotiation: Yes
> Advertised link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> 1000baseT/Full
> Advertised pause frame use: No
> Advertised auto-negotiation: Yes
> Link partner advertised link modes: Not reported
> Link partner advertised pause frame use: No
> Link partner advertised auto-negotiation: No
> Speed: Unknown!
> Duplex: Unknown! (255)
> Port: Twisted Pair
> PHYAD: 1
> Transceiver: internal
> Auto-negotiation: on
> MDI-X: Unknown
> Supports Wake-on: pumbag
> Wake-on: g
> Current message level: 0x00000001 (1)
> Link detected: no
>
> bonding driver says eth1.99 reports MII status up:
>
> root@sandbox:/proc/net# cat bonding/bond0
> Ethernet Channel Bonding Driver: v3.6.0 (September 26, 2009)
>
> Bonding Mode: load balancing (round-robin)
> MII Status: up
> MII Polling Interval (ms): 0
> Up Delay (ms): 0
> Down Delay (ms): 0
>
> Slave Interface: eth0.99
> MII Status: up
> Link Failure Count: 0
> Permanent HW addr: 00:26:9e:1c:d3:3e
>
> Slave Interface: eth1.99
> MII Status: up
> Link Failure Count: 0
> Permanent HW addr: 00:26:9e:1c:d3:3f
>
> is there some parameter I can give that tells the vlan driver to
> follow the state of the interface it is attached to? Having a vlan
> that reports being up all the time even when its underlying interface
> is down is less than useful. It would seem intuitive that a vlan's
> state would follow that of the interface it is attached to.
>
> root@sandbox:/proc/net# cat vlan/eth0.99
> eth0.99 VID: 99 REORDER_HDR: 1 dev->priv_flags: 21
> total frames received 32
> total bytes received 4735
> Broadcast/Multicast Rcvd 0
>
> total frames transmitted 50
> total bytes transmitted 3852
> total headroom inc 0
> total encap on xmit 0
> Device: eth0
> INGRESS priority mappings: 0:0 1:0 2:0 3:0 4:0 5:0 6:0 7:0
> EGRESS priority mappings:
> root@sandbox:/proc/net# cat vlan/eth1.99
> eth1.99 VID: 99 REORDER_HDR: 1 dev->priv_flags: 21
> total frames received 0
> total bytes received 0
> Broadcast/Multicast Rcvd 0
>
> total frames transmitted 0
> total bytes transmitted 0
> total headroom inc 0
> total encap on xmit 0
> Device: eth1
> INGRESS priority mappings: 0:0 1:0 2:0 3:0 4:0 5:0 6:0 7:0
> EGRESS priority mappings:
>
> root@sandbox:/proc/net# ping 10.1.99.1
> PING 10.1.99.1 (10.1.99.1) 56(84) bytes of data.
> 64 bytes from 10.1.99.1: icmp_seq=2 ttl=255 time=0.299 ms
> 64 bytes from 10.1.99.1: icmp_seq=4 ttl=255 time=0.311 ms
> 64 bytes from 10.1.99.1: icmp_seq=6 ttl=255 time=0.325 ms
> 64 bytes from 10.1.99.1: icmp_seq=8 ttl=255 time=0.291 ms
> 64 bytes from 10.1.99.1: icmp_seq=10 ttl=255 time=0.308 ms
>
> George
>
But interestingly, mii-tool reports the correct result:
root@sandbox:/usr/src/linux-source-2.6.34/Documentation/networking#
mii-tool -v eth1.99
eth1.99: no link
product info: vendor 00:50:43, model 10 rev 0
basic mode: autonegotiation enabled
basic status: no link
capabilities: 1000baseT-FD 100baseTx-FD 100baseTx-HD 10baseT-FD 10baseT-HD
advertising: 100baseTx-FD 100baseTx-HD 10baseT-FD 10baseT-HD flow-control
^ permalink raw reply
* VLANs, bonding redux: vlan state does not follow ethernet
From: George B. @ 2010-05-22 6:24 UTC (permalink / raw)
To: netdev
Using 2.6.34 I am trying to remove bottlenecks. Instead of bonding
two ethernet interfaces and applying vlans to the bond, I am applying
the vlans to the ethernet and bonding the vlans creating a separate
bond interface for each vlan.
The trouble now is that the bond interface does not see when the
ethernet interface goes down. The vlan reports to the bonding driver
that it is up when the ethernet it is connected to is down. This
results in packet loss through the bond interface as the bond driver
attempts to use that vlan.
eth1 shows having no link:
root@sandbox:/proc/net# ethtool eth1
Settings for eth1:
Supported ports: [ TP ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Advertised pause frame use: No
Advertised auto-negotiation: Yes
Link partner advertised link modes: Not reported
Link partner advertised pause frame use: No
Link partner advertised auto-negotiation: No
Speed: Unknown!
Duplex: Unknown! (255)
Port: Twisted Pair
PHYAD: 1
Transceiver: internal
Auto-negotiation: on
MDI-X: Unknown
Supports Wake-on: pumbag
Wake-on: g
Current message level: 0x00000001 (1)
Link detected: no
bonding driver says eth1.99 reports MII status up:
root@sandbox:/proc/net# cat bonding/bond0
Ethernet Channel Bonding Driver: v3.6.0 (September 26, 2009)
Bonding Mode: load balancing (round-robin)
MII Status: up
MII Polling Interval (ms): 0
Up Delay (ms): 0
Down Delay (ms): 0
Slave Interface: eth0.99
MII Status: up
Link Failure Count: 0
Permanent HW addr: 00:26:9e:1c:d3:3e
Slave Interface: eth1.99
MII Status: up
Link Failure Count: 0
Permanent HW addr: 00:26:9e:1c:d3:3f
is there some parameter I can give that tells the vlan driver to
follow the state of the interface it is attached to? Having a vlan
that reports being up all the time even when its underlying interface
is down is less than useful. It would seem intuitive that a vlan's
state would follow that of the interface it is attached to.
root@sandbox:/proc/net# cat vlan/eth0.99
eth0.99 VID: 99 REORDER_HDR: 1 dev->priv_flags: 21
total frames received 32
total bytes received 4735
Broadcast/Multicast Rcvd 0
total frames transmitted 50
total bytes transmitted 3852
total headroom inc 0
total encap on xmit 0
Device: eth0
INGRESS priority mappings: 0:0 1:0 2:0 3:0 4:0 5:0 6:0 7:0
EGRESS priority mappings:
root@sandbox:/proc/net# cat vlan/eth1.99
eth1.99 VID: 99 REORDER_HDR: 1 dev->priv_flags: 21
total frames received 0
total bytes received 0
Broadcast/Multicast Rcvd 0
total frames transmitted 0
total bytes transmitted 0
total headroom inc 0
total encap on xmit 0
Device: eth1
INGRESS priority mappings: 0:0 1:0 2:0 3:0 4:0 5:0 6:0 7:0
EGRESS priority mappings:
root@sandbox:/proc/net# ping 10.1.99.1
PING 10.1.99.1 (10.1.99.1) 56(84) bytes of data.
64 bytes from 10.1.99.1: icmp_seq=2 ttl=255 time=0.299 ms
64 bytes from 10.1.99.1: icmp_seq=4 ttl=255 time=0.311 ms
64 bytes from 10.1.99.1: icmp_seq=6 ttl=255 time=0.325 ms
64 bytes from 10.1.99.1: icmp_seq=8 ttl=255 time=0.291 ms
64 bytes from 10.1.99.1: icmp_seq=10 ttl=255 time=0.308 ms
George
^ permalink raw reply
* cls_cgroup: Store classid in struct sock
From: Herbert Xu @ 2010-05-22 1:49 UTC (permalink / raw)
To: Neil Horman; +Cc: David Miller, eric.dumazet, bmb, tgraf, nhorman, netdev
In-Reply-To: <20100521164054.GB29521@hmsreliant.think-freely.org>
On Fri, May 21, 2010 at 12:40:54PM -0400, Neil Horman wrote:
>
> There may also be an issue with the setting of the classid (possible use of the
> wrong subsys id value when grabbing our cgroup_subsys_state), but I'm checking
> on that now.
Actually, I think it's because my patch mistook CONFIG_CGROUP
for CONFIG_CGROUPS.
Here is a fixed version (also includes a build fix on sk->classid).
cls_cgroup: Store classid in struct sock
Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread. This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.
Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.
In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK. This is currently
unclassified.
As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.
This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)
The value is set at socket creation time. So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.
For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.
In order to minimise risks, I have not made this the authoritative
classid. For now it is only used as a backup when we execute
with soft IRQs disabled. Once we're completely happy with its
semantics we can use it as the sole classid.
Footnote: I have rearranged the error path on cls_group module
creation. If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
new file mode 100644
index 0000000..f0e244e
--- /dev/null
+++ b/include/net/cls_cgroup.h
@@ -0,0 +1,63 @@
+/*
+ * cls_cgroup.h Control Group Classifier
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _NET_CLS_CGROUP_H
+#define _NET_CLS_CGROUP_H
+
+#include <linux/cgroup.h>
+#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
+
+struct cgroup_cls_state
+{
+ struct cgroup_subsys_state css;
+ u32 classid;
+};
+
+#ifdef CONFIG_CGROUPS
+#ifdef CONFIG_NET_CLS_CGROUP
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+ if (in_interrupt())
+ return 0;
+
+ return container_of(task_subsys_state(p, net_cls_subsys_id),
+ struct cgroup_cls_state, css).classid;
+}
+#else
+extern int net_cls_subsys_id;
+
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+ int id;
+ u32 classid;
+
+ if (in_interrupt())
+ return 0;
+
+ rcu_read_lock();
+ id = rcu_dereference(net_cls_subsys_id);
+ if (id >= 0)
+ classid = container_of(task_subsys_state(p, id),
+ struct cgroup_cls_state, css)->classid;
+ rcu_read_unlock();
+
+ return classid;
+}
+#endif
+#else
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+ return 0;
+}
+#endif
+#endif /* _NET_CLS_CGROUP_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 5697caf..d24f382 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -312,7 +312,7 @@ struct sock {
void *sk_security;
#endif
__u32 sk_mark;
- /* XXX 4 bytes hole on 64 bit */
+ u32 sk_classid;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk, int bytes);
void (*sk_write_space)(struct sock *sk);
@@ -1074,6 +1074,14 @@ extern void *sock_kmalloc(struct sock *sk, int size,
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);
+#ifdef CONFIG_CGROUPS
+extern void sock_update_classid(struct sock *sk);
+#else
+static inline void sock_update_classid(struct sock *sk)
+{
+}
+#endif
+
/*
* Functions to fill in entries in struct proto_ops when a protocol
* does not implement a particular function.
diff --git a/net/core/sock.c b/net/core/sock.c
index bf88a16..a05ae7f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -123,6 +123,7 @@
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
+#include <net/cls_cgroup.h>
#include <linux/filter.h>
@@ -217,6 +218,11 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
+#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+int net_cls_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_cls_subsys_id);
+#endif
+
static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
struct timeval tv;
@@ -1050,6 +1056,16 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
+#ifdef CONFIG_CGROUPS
+void sock_update_classid(struct sock *sk)
+{
+ u32 classid = task_cls_classid(current);
+
+ if (classid && classid != sk->sk_classid)
+ sk->sk_classid = classid;
+}
+#endif
+
/**
* sk_alloc - All socket objects are allocated here
* @net: the applicable net namespace
@@ -1073,6 +1089,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sock_lock_init(sk);
sock_net_set(sk, get_net(net));
atomic_set(&sk->sk_wmem_alloc, 1);
+
+ sock_update_classid(sk);
}
return sk;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 2211803..766124b 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -16,14 +16,11 @@
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/cgroup.h>
+#include <linux/rcupdate.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
-
-struct cgroup_cls_state
-{
- struct cgroup_subsys_state css;
- u32 classid;
-};
+#include <net/sock.h>
+#include <net/cls_cgroup.h>
static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
struct cgroup *cgrp);
@@ -112,6 +109,10 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
struct cls_cgroup_head *head = tp->root;
u32 classid;
+ rcu_read_lock();
+ classid = task_cls_state(current)->classid;
+ rcu_read_unlock();
+
/*
* Due to the nature of the classifier it is required to ignore all
* packets originating from softirq context as accessing `current'
@@ -122,12 +123,12 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
* calls by looking at the number of nested bh disable calls because
* softirqs always disables bh.
*/
- if (softirq_count() != SOFTIRQ_OFFSET)
- return -1;
-
- rcu_read_lock();
- classid = task_cls_state(current)->classid;
- rcu_read_unlock();
+ if (softirq_count() != SOFTIRQ_OFFSET) {
+ /* If there is an sk_classid we'll use that. */
+ if (!skb->sk)
+ return -1;
+ classid = skb->sk->sk_classid;
+ }
if (!classid)
return -1;
@@ -289,18 +290,35 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
static int __init init_cgroup_cls(void)
{
- int ret = register_tcf_proto_ops(&cls_cgroup_ops);
- if (ret)
- return ret;
+ int ret;
+
ret = cgroup_load_subsys(&net_cls_subsys);
if (ret)
- unregister_tcf_proto_ops(&cls_cgroup_ops);
+ goto out;
+
+#ifndef CONFIG_NET_CLS_CGROUP
+ /* We can't use rcu_assign_pointer because this is an int. */
+ smp_wmb();
+ net_cls_subsys_id = net_cls_subsys.subsys_id;
+#endif
+
+ ret = register_tcf_proto_ops(&cls_cgroup_ops);
+ if (ret)
+ cgroup_unload_subsys(&net_cls_subsys);
+
+out:
return ret;
}
static void __exit exit_cgroup_cls(void)
{
unregister_tcf_proto_ops(&cls_cgroup_ops);
+
+#ifndef CONFIG_NET_CLS_CGROUP
+ net_cls_subsys_id = -1;
+ synchronize_rcu();
+#endif
+
cgroup_unload_subsys(&net_cls_subsys);
}
diff --git a/net/socket.c b/net/socket.c
index f9f7d08..367d547 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -94,6 +94,7 @@
#include <net/compat.h>
#include <net/wext.h>
+#include <net/cls_cgroup.h>
#include <net/sock.h>
#include <linux/netfilter.h>
@@ -558,6 +559,8 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
struct sock_iocb *si = kiocb_to_siocb(iocb);
int err;
+ sock_update_classid(sock->sk);
+
si->sock = sock;
si->scm = NULL;
si->msg = msg;
@@ -684,6 +687,8 @@ static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
{
struct sock_iocb *si = kiocb_to_siocb(iocb);
+ sock_update_classid(sock->sk);
+
si->sock = sock;
si->scm = NULL;
si->msg = msg;
@@ -777,6 +782,8 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
if (unlikely(!sock->ops->splice_read))
return -EINVAL;
+ sock_update_classid(sock->sk);
+
return sock->ops->splice_read(sock, ppos, pipe, len, flags);
}
@@ -3069,6 +3076,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname,
int kernel_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags)
{
+ sock_update_classid(sock->sk);
+
if (sock->ops->sendpage)
return sock->ops->sendpage(sock, page, offset, size, flags);
Thanks,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply related
* [PATCH]: Fix warning in _hfcpci_softirq()
From: Prarit Bhargava @ 2010-05-22 0:33 UTC (permalink / raw)
To: netdev, isdn; +Cc: Prarit Bhargava
Fix warning:
drivers/isdn/hardware/mISDN/hfcpci.c: In function `hfcpci_softirq':
drivers/isdn/hardware/mISDN/hfcpci.c:2321: warning: ignoring return value of `driver_for_each_device', declared with attribute warn_unused_result
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 5940a2c..12484d7 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -2317,8 +2317,10 @@ _hfcpci_softirq(struct device *dev, void *arg)
static void
hfcpci_softirq(void *arg)
{
- (void) driver_for_each_device(&hfc_driver.driver, NULL, arg,
- _hfcpci_softirq);
+ int ret;
+
+ ret = driver_for_each_device(&hfc_driver.driver, NULL, arg,
+ _hfcpci_softirq);
/* if next event would be in the past ... */
if ((s32)(hfc_jiffies + tics - jiffies) <= 0)
^ permalink raw reply related
* tc: RTM_GETQDISC causes kernel OOPS
From: Ben Pfaff @ 2010-05-21 22:42 UTC (permalink / raw)
To: Jamal Hadi Salim; +Cc: netdev
Hi. While working on some library code for working with qdiscs and
classes I came upon a kernel OOPS. Originally I came across it with a
2.6.26 kernel, but I can also reproduce it with unmodified v2.6.34 from
kernel.org.
At the end of this mail I'm appending both an example of the OOPS and a
simple test program that reliably reproduces the problem for me when I
invoke it with "lo" as argument. The program does not need to be run as
root.
After the OOPS, a lot of networking and other system functions stop
working, so it seems to me a serious issue.
The null pointer dereference that causes the OOPS is the dereference of
the return value of qdisc_dev() in tc_fill_qdisc() in
net/sched/sch_api.c line 1163:
1161 tcm->tcm__pad1 = 0;
1162 tcm->tcm__pad2 = 0;
1163 tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
1164 tcm->tcm_parent = clid;
1165 tcm->tcm_handle = q->handle;
I am pretty sure about that, because if I add "WARN_ON(!qdisc_dev(q));"
just before line 1163 then that warning triggers.
Thanks,
Ben.
----------------------------------------------------------------------
BUG: unable to handle kernel NULL pointer dereference at 00000050
IP: [<c12280c0>] tc_fill_qdisc+0x68/0x1e5
*pde = 00000000
Oops: 0000 [#1] SMP
last sysfs file:
Modules linked in:
Pid: 600, comm: qdisc Not tainted 2.6.34 #16 /
EIP: 0060:[<c12280c0>] EFLAGS: 00010282 CPU: 0
EIP is at tc_fill_qdisc+0x68/0x1e5
EAX: 00000000 EBX: ffffffff ECX: 00000000 EDX: c7222070
ESI: c14576e0 EDI: c7115200 EBP: c7239ca0 ESP: c7239c3c
DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
Process qdisc (pid: 600, ti=c7239000 task=c720b700 task.ti=c7239000)
Stack:
00000024 00000014 00000000 c14323a0 c7222060 c7222060 c10a7abd 00001030
<0> 000000d0 c7222060 000000d0 c1228329 000000d0 00000fc4 000000d0 c7115200
<0> 000000d0 00000ec0 c7239cac c12104b1 00000ec0 c1457a98 c7115200 00000258
Call Trace:
[<c10a7abd>] ? __kmalloc_track_caller+0x122/0x131
[<c1228329>] ? qdisc_notify+0x2a/0xc8
[<c12104b1>] ? __alloc_skb+0x4e/0x115
[<c122838a>] ? qdisc_notify+0x8b/0xc8
[<c12287ea>] ? tc_get_qdisc+0x143/0x15d
[<c12286a7>] ? tc_get_qdisc+0x0/0x15d
[<c1220c28>] ? rtnetlink_rcv_msg+0x195/0x1af
[<c1220a93>] ? rtnetlink_rcv_msg+0x0/0x1af
[<c12329e2>] ? netlink_rcv_skb+0x30/0x75
[<c1220a8b>] ? rtnetlink_rcv+0x1e/0x26
[<c123281b>] ? netlink_unicast+0xc4/0x11a
[<c1232eda>] ? netlink_sendmsg+0x223/0x230
[<c120978c>] ? sock_sendmsg+0xa8/0xbf
[<c10514fc>] ? print_lock_contention_bug+0x14/0xd7
[<c101ebe4>] ? __wake_up+0x15/0x3b
[<c101ebe4>] ? __wake_up+0x15/0x3b
[<c101ec00>] ? __wake_up+0x31/0x3b
[<c10acda4>] ? fget_light+0x2d/0xaf
[<c109488d>] ? might_fault+0x47/0x81
[<c120acf9>] ? sys_sendto+0xa4/0xc0
[<c116b82c>] ? _copy_from_user+0x2e/0x108
[<c120ad92>] ? sys_connect+0x63/0x6e
[<c120ad2d>] ? sys_send+0x18/0x1a
[<c120aedb>] ? sys_socketcall+0xd4/0x1a5
[<c12ca931>] ? syscall_call+0x7/0xb
Code: 50 8b 55 08 89 f8 6a 14 ff 75 14 e8 49 fa ff ff 89 c2 83 c2 10 89 45 ac c6 42 01 00 66 c7 42 02 00 00 c6 40 10 00 8b 46 40 8b 00 <8b> 40 50 89 5a 0c 89 42 04 8b 46 20 89 42 08 8b 46 28 89 42 10
EIP: [<c12280c0>] tc_fill_qdisc+0x68/0x1e5 SS:ESP 0068:c7239c3c
CR2: 0000000000000050
---[ end trace 6fb85bbc66de8f42 ]---
----------------------------------------------------------------------
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <unistd.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_sched.h>
#include <net/if.h>
int
main(int argc, char *argv[])
{
struct {
struct nlmsghdr nlmsg;
struct tcmsg tcmsg;
} msg;
struct sockaddr_nl local, remote;
int ifindex;
int fd;
if (argc != 2) {
fprintf(stderr,
"usage: %s <netdev>\n"
"where <netdev> is a network device, e.g. \"lo\"\n",
argv[0]);
return EXIT_FAILURE;
}
/* Get ifindex. */
ifindex = if_nametoindex(argv[1]);
if (!ifindex) {
fprintf(stderr, "no network device named \"%s\"", argv[1]);
return EXIT_FAILURE;
}
/* Make rtnetlink socket. */
fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
if (fd < 0) {
perror("socket");
return EXIT_FAILURE;
}
/* Bind local address as our selected pid. */
memset(&local, 0, sizeof local);
local.nl_family = AF_NETLINK;
local.nl_pid = getpid();
if (bind(fd, (struct sockaddr *) &local, sizeof local) < 0) {
perror("bind");
return EXIT_FAILURE;
}
/* Bind remote address as the kernel (pid 0). */
memset(&remote, 0, sizeof remote);
remote.nl_family = AF_NETLINK;
remote.nl_pid = 0;
if (connect(fd, (struct sockaddr *) &remote, sizeof remote) < 0) {
perror("connect");
return EXIT_FAILURE;
}
/* Send "get" request. */
memset(&msg, 0, sizeof msg);
msg.nlmsg.nlmsg_len = sizeof msg;
msg.nlmsg.nlmsg_type = RTM_GETQDISC;
msg.nlmsg.nlmsg_flags = NLM_F_REQUEST | NLM_F_ECHO | NLM_F_ACK;
msg.nlmsg.nlmsg_seq = 1;
msg.nlmsg.nlmsg_pid = getpid();
msg.tcmsg.tcm_family = AF_UNSPEC;
msg.tcmsg.tcm_ifindex = ifindex;
msg.tcmsg.tcm_handle = 0;
msg.tcmsg.tcm_parent = TC_H_ROOT;
if (send(fd, &msg, sizeof msg, 0) < 0) {
perror("send");
return EXIT_FAILURE;
}
return 0;
}
^ permalink raw reply
* Re: [PATCH 1/4] IPv6: keep route for tentative address
From: Emil S Tantilov @ 2010-05-21 22:21 UTC (permalink / raw)
To: Stephen Hemminger, David S. Miller, NetDev; +Cc: Tantilov, Emil S
In-Reply-To: <EA929A9653AAE14F841771FB1DE5A1365FE4FCE12C@rrsmsx501.amr.corp.intel.com>
On Mon, Apr 12, 2010 at 1:17 PM, Tantilov, Emil S
<emil.s.tantilov@intel.com> wrote:
> Stephen Hemminger wrote:
>> Recent changes preserve IPv6 address when link goes down (good).
>> But would cause address to point to dead dst entry (bad).
>> The simplest fix is to just not delete route if address is
>> being held for later use.
>>
>> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
>>
>>
>> --- a/net/ipv6/addrconf.c 2010-04-11 12:19:37.938082190 -0700
>> +++ b/net/ipv6/addrconf.c 2010-04-11 12:25:05.349309074 -0700
>> @@ -4046,7 +4046,8 @@ static void __ipv6_ifa_notify(int event,
>> addrconf_leave_anycast(ifp);
>> addrconf_leave_solict(ifp->idev, &ifp->addr);
>> dst_hold(&ifp->rt->u.dst);
>> - if (ip6_del_rt(ifp->rt))
>> +
>> + if (ifp->dead && ip6_del_rt(ifp->rt))
>> dst_free(&ifp->rt->u.dst);
>> break;
>> }
>
> Stephen,
>
> With these series of patches (1-4) applied I am no longer seeing the
> hangs and warnings associated with ipv6. I ran few rounds of
> tests with resetting the interface and loading/unloading modules.
Looks like these patches did not make it into net-2.6 and the issue can be seen
in the latest stable 2.6.34.
Any chance that the patches can be pushed to 2.6.34-stable?
Thanks,
Emil
^ permalink raw reply
* Re: bug fix patch lost: git problem or just incorrect merge?
From: David Miller @ 2010-05-21 22:07 UTC (permalink / raw)
To: torvalds; +Cc: James.Bottomley, linux-kernel, netdev, linux-scsi
In-Reply-To: <alpine.LFD.2.00.1005210931010.4243@i5.linux-foundation.org>
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 21 May 2010 09:45:49 -0700 (PDT)
> One of the reasons I ask people to let me merge is that it results in
> cleaner history to not have criss-cross merges. And another is that I'm
> pretty good at it, and letting me make merges also means that I am more
> aware of problem spots.
That wasn't possible in this case.
This happened more than a week ago, as I needed to merge your tree into
net-2.6 to resolve a conflict there. That's what took in the iscsi
bug fix, and this is way before the merge window.
Then I needed to pull net-2.6 into net-next-2.6 to resolve conflicts
existing between those two trees.
And this is why I ended up having to do the merge :-)
>> Either way, of course, we need the patch back ...
>
> I'll fix it up.
Thanks Linus.
^ permalink raw reply
* Re: bug fix patch lost: git problem or just incorrect merge?
From: David Miller @ 2010-05-21 22:02 UTC (permalink / raw)
To: James.Bottomley; +Cc: torvalds, linux-kernel, netdev, linux-scsi
In-Reply-To: <1274456515.9022.14.camel@mulgrave.site>
From: James Bottomley <James.Bottomley@suse.de>
Date: Fri, 21 May 2010 10:41:55 -0500
> Is this a git problem ... or is it just a mismerge in the net tree?
Mismerge, because sk->sk_sleep() doesn't exist any more I mistakenly
updated the original line to do the sk_sleep() stuff.
Sorry about that.
^ permalink raw reply
* [PATCH] net-caif: drop redundant Kconfig entries
From: Mike Frysinger @ 2010-05-21 20:45 UTC (permalink / raw)
To: netdev, David S. Miller, Sjur Braendeland
There is already a submenu entry that is always displayed, so there is
no need to also show a dedicated CAIF comment.
Drop dead commented code while we're here, and change the submenu text
to better match the style everyone else is using.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
---
net/caif/Kconfig | 5 +----
1 files changed, 1 insertions(+), 4 deletions(-)
diff --git a/net/caif/Kconfig b/net/caif/Kconfig
index cd1daf6..ed65178 100644
--- a/net/caif/Kconfig
+++ b/net/caif/Kconfig
@@ -2,10 +2,8 @@
# CAIF net configurations
#
-#menu "CAIF Support"
-comment "CAIF Support"
menuconfig CAIF
- tristate "Enable CAIF support"
+ tristate "CAIF support"
select CRC_CCITT
default n
---help---
@@ -45,4 +43,3 @@ config CAIF_NETDEV
If unsure say Y.
endif
-#endmenu
--
1.7.1
^ permalink raw reply related
* ixgbe: macvlan on PF/VF when SRIOV is enabled
From: Shirley Ma @ 2010-05-21 20:30 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, kvm, netdev, e1000-devel
Hello Jeff,
macvlan doesn't work on PF when SRIOV is enabled. Creating macvlan has
been successful, but ping (icmp request) goes to VF interface not
PF/macvlan even arp entry is correct. I patched ixgbe driver, and
macvlan/PF has worked with the patch. But I am not sure whether it is
right since I don't have the HW spec. What I did for ixgbe driver was:
1. PF's rar index is 0, VMDQ index is adatper->num_vfs;
2. VF's rar is based on rar_used_count and mc_addr_in_rar_count, VMDQ
index is ;
3. PF's secondary addresses is PF's rar index + i, VMDQ index is
adapter->num_vfs.
Before I submit the patch, I want to understand the right index
assignment for both rar index and VMDQ index, when SRIOV enabled:
1. VMDQ index for PF is adapter->num_vfs, or 0? rar index is 0?
2. PF's secondary address rar index is based on
rar_used_count/mc_addr_in_rar_count?
2. VF's VPDQ index is based on vf number?
3. VF's rar index is vf + 1, or should be based on rar_used_count?
I am also working on macvlan on VF. The question here is whether macvlan
on VF should work or not? Looks like ixgbevf secondary addresses are not
in receiver address filter, so macvlan on VF doesn't work.
Thanks
Shirley
^ permalink raw reply
* [RFC PATCH] packet_mmap: expose hw packet timestamps to network packet capture utilities
From: Mcmillan, Scott A @ 2010-05-21 20:24 UTC (permalink / raw)
To: netdev@vger.kernel.org, davem@davemloft.net
Cc: tcpdump-workers@lists.tcpdump.org
This patch adds a setting, PACKET_TIMESTAMP, to specify the packet timestamp source that is exported to capture utilities like tcpdump by packet_mmap.
PACKET_TIMESTAMP accepts the same integer bit field as SO_TIMESTAMPING. However, only the SOF_TIMESTAMPING_SYS_HARDWARE
and SOF_TIMESTAMPING_RAW_HARDWARE values are currently recognized by PACKET_TIMESTAMP. SOF_TIMESTAMPING_SYS_HARDWARE takes precedence over SOF_TIMESTAMPING_RAW_HARDWARE if both bits are set.
If PACKET_TIMESTAMP is not set, a software timestamp generated inside the networking stack is used (the behavior before this setting was added).
I am concurrently submitting a patch to the tcpdump / libpcap maintainers adding support for this capability.
Thanks,
Scott
Signed-off-by: Scott McMillan <scott.a.mcmillan@intel.com>
--- a/include/linux/if_packet.h 2010-05-18 17:22:59.000000000 -0500
+++ b/include/linux/if_packet.h 2010-05-21 14:37:30.000000000 -0500
@@ -48,6 +48,7 @@
#define PACKET_LOSS 14
#define PACKET_VNET_HDR 15
#define PACKET_TX_TIMESTAMP 16
+#define PACKET_TIMESTAMP 17
struct tpacket_stats {
unsigned int tp_packets;
--- a/net/packet/af_packet.c 2010-05-18 17:21:48.000000000 -0500
+++ b/net/packet/af_packet.c 2010-05-21 14:48:41.000000000 -0500
@@ -83,6 +83,7 @@
#include <linux/if_vlan.h>
#include <linux/virtio_net.h>
#include <linux/errqueue.h>
+#include <linux/net_tstamp.h>
#ifdef CONFIG_INET
#include <net/inet_common.h>
@@ -202,6 +203,7 @@
unsigned int tp_hdrlen;
unsigned int tp_reserve;
unsigned int tp_loss:1;
+ unsigned int tp_tstamp;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
@@ -656,6 +658,7 @@
struct sk_buff *copy_skb = NULL;
struct timeval tv;
struct timespec ts;
+ struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
if (skb->pkt_type == PACKET_LOOPBACK)
goto drop;
@@ -737,7 +740,13 @@
h.h1->tp_snaplen = snaplen;
h.h1->tp_mac = macoff;
h.h1->tp_net = netoff;
- if (skb->tstamp.tv64)
+ if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
+ && shhwtstamps->syststamp.tv64)
+ tv = ktime_to_timeval(shhwtstamps->syststamp);
+ else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
+ && shhwtstamps->hwtstamp.tv64)
+ tv = ktime_to_timeval(shhwtstamps->hwtstamp);
+ else if (skb->tstamp.tv64)
tv = ktime_to_timeval(skb->tstamp);
else
do_gettimeofday(&tv);
@@ -750,7 +759,13 @@
h.h2->tp_snaplen = snaplen;
h.h2->tp_mac = macoff;
h.h2->tp_net = netoff;
- if (skb->tstamp.tv64)
+ if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
+ && shhwtstamps->syststamp.tv64)
+ ts = ktime_to_timespec(shhwtstamps->syststamp);
+ else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
+ && shhwtstamps->hwtstamp.tv64)
+ ts = ktime_to_timespec(shhwtstamps->hwtstamp);
+ else if (skb->tstamp.tv64)
ts = ktime_to_timespec(skb->tstamp);
else
getnstimeofday(&ts);
@@ -2027,6 +2042,18 @@
po->has_vnet_hdr = !!val;
return 0;
}
+ case PACKET_TIMESTAMP:
+ {
+ int val;
+
+ if (optlen != sizeof(val))
+ return -EINVAL;
+ if (copy_from_user(&val, optval, sizeof(val)))
+ return -EFAULT;
+
+ po->tp_tstamp = val;
+ return 0;
+ }
default:
return -ENOPROTOOPT;
}
@@ -2119,6 +2146,12 @@
val = po->tp_loss;
data = &val;
break;
+ case PACKET_TIMESTAMP:
+ if (len > sizeof(int))
+ len = sizeof(int);
+ val = po->tp_tstamp;
+ data = &val;
+ break;
default:
return -ENOPROTOOPT;
}
--- a/Documentation/networking/packet_mmap.txt 2010-05-18 17:24:18.000000000 -0500
+++ b/Documentation/networking/packet_mmap.txt 2010-05-21 14:39:48.000000000 -0500
@@ -493,6 +493,32 @@
pfd.events = POLLOUT;
retval = poll(&pfd, 1, timeout);
+-------------------------------------------------------------------------------
++ PACKET_TIMESTAMP
+-------------------------------------------------------------------------------
+
+The PACKET_TIMESTAMP setting determines the source of the timestamp in
+the packet meta information. If your NIC is capable of timestamping
+packets in hardware, you can request those hardware timestamps to used.
+Note: you may need to enable the generation of hardware timestamps with
+SIOCSHWTSTAMP.
+
+PACKET_TIMESTAMP accepts the same integer bit field as
+SO_TIMESTAMPING. However, only the SOF_TIMESTAMPING_SYS_HARDWARE
+and SOF_TIMESTAMPING_RAW_HARDWARE values are recognized by
+PACKET_TIMESTAMP. SOF_TIMESTAMPING_SYS_HARDWARE takes precedence over
+SOF_TIMESTAMPING_RAW_HARDWARE if both bits are set.
+
+ int req = 0;
+ req |= SOF_TIMESTAMPING_SYS_HARDWARE;
+ setsockopt(fd, SOL_PACKET, PACKET_TIMESTAMP, (void *) &req, sizeof(req))
+
+If PACKET_TIMESTAMP is not set, a software timestamp generated inside
+the networking stack is used (the behavior before this setting was added).
+
+See include/linux/net_tstamp.h and Documentation/networking/timestamping
+for more information on hardware timestamps.
+
--------------------------------------------------------------------------------
+ THANKS
--------------------------------------------------------------------------------
^ permalink raw reply
* RE: [PATCH] net: add additional lock to qdisc to increase throughput
From: Duyck, Alexander H @ 2010-05-21 20:04 UTC (permalink / raw)
To: Eric Dumazet, David Miller; +Cc: netdev@vger.kernel.org
In-Reply-To: <1274454480.2439.418.camel@edumazet-laptop>
Eric Dumazet wrote:
> Tests with following script gave a boost from ~50.000 pps to ~600.000
> pps on a dual quad core machine (E5450 @3.00GHz), tg3 driver.
> (A single netperf flow can reach ~800.000 pps on this platform)
>
> for j in `seq 0 3`; do
> for i in `seq 0 7`; do
> netperf -H 192.168.0.1 -t UDP_STREAM -l 60 -N -T $i -- -m 6 &
> done
> done
Running the same script with your patch my results went from 200Kpps to 1.2Mpps on a dual Xeon 5570.
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
^ permalink raw reply
* RE: ixgbe and SRIOV failure in driver?
From: Rose, Gregory V @ 2010-05-21 19:18 UTC (permalink / raw)
To: Fischer, Anna, e1000-devel@lists.sourceforge.net,
netdev@vger.kernel.org
In-Reply-To: <0199E0D51A61344794750DC57738F58E70B08A2A20@GVW1118EXC.americas.hpqcorp.net>
>-----Original Message-----
>From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org]
>On Behalf Of Fischer, Anna
>Sent: Friday, May 21, 2010 9:33 AM
>To: e1000-devel@lists.sourceforge.net; netdev@vger.kernel.org
>Subject: ixgbe and SRIOV failure in driver?
>
>I am running a system with 3 Intel NICs. Two of them are 82598 devices,
>and one is a SRIOV capable 82599.
>
>All devices use the ixgbe driver. What happens (I believe) now is that
>when the driver loads at first, it sees the 82598 first (because of its
>position in the PCI tree) and then it says "Device not IOV capable -
>switching off IOV."
>
>So then it switches into non-IOV mode, and I can never enable SRIOV on
>my 82599, because the driver does not enable it any more for further
>devices.
>
>So to get around this issue, I tried to use pciback.hide to hide the
>82598 devices from the OS. That way I was hoping that the driver would
>switch on SRIOV on my 82599. However, then I got a kernel panic on boot
>(see below).
>
>I am running Xen 4 and the Dom0 kernel is a 2.6.31 kernel.
The ixgbe driver included with the 2.6.31 kernel does not support SR-IOV.
Where did you get the driver that does? Please run ethtool -i <ethx> and
post the results.
- Greg Rose
Intel Corp.
Lan Access Division
^ permalink raw reply
* Re: [PATCH v2 2/2] phylib: Convert MDIO bitbang to new MDIO 45 format
From: Ben Hutchings @ 2010-05-21 18:55 UTC (permalink / raw)
To: Andy Fleming; +Cc: davem, netdev
In-Reply-To: <1274466711-24962-3-git-send-email-afleming@freescale.com>
On Fri, 2010-05-21 at 13:31 -0500, Andy Fleming wrote:
> Now that we've added somewhat more complete MDIO 45 support to the PHY
> Lib, convert the MDIO bitbang driver to use this new infrastructure.
>
> Signed-off-by: Andy Fleming <afleming@freescale.com>
> ---
> drivers/net/phy/mdio-bitbang.c | 29 +++++++++++++++--------------
> 1 files changed, 15 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
> index 2f6f02e..be7ae74 100644
> --- a/drivers/net/phy/mdio-bitbang.c
> +++ b/drivers/net/phy/mdio-bitbang.c
[...]
> @@ -157,11 +154,13 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int devad, int reg)
> struct mdiobb_ctrl *ctrl = bus->priv;
> int ret, i;
>
> - if (reg & MII_ADDR_C45) {
> - reg = mdiobb_cmd_addr(ctrl, phy, reg);
> - mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg);
> - } else
> + /* Clause 22 PHYs only use devad = 0, and Clause 45 only use nonzero */
> + if (devad == MDIO_DEVAD_NONE)
> mdiobb_cmd(ctrl, MDIO_READ, phy, reg);
> + else {
> + mdiobb_cmd_addr(ctrl, phy, devad, reg);
> + mdiobb_cmd(ctrl, MDIO_C45_READ, phy, devad);
> + }
[...]
This comment is now wrong.
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: [PATCH v2 1/2] phylib: Convert MDIO and PHY Lib drivers to support 10G
From: Ben Hutchings @ 2010-05-21 18:55 UTC (permalink / raw)
To: Andy Fleming; +Cc: davem, netdev
In-Reply-To: <1274466711-24962-2-git-send-email-afleming@freescale.com>
On Fri, 2010-05-21 at 13:31 -0500, Andy Fleming wrote:
[...]
> diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
> index 1a99bb2..c72ba85 100644
> --- a/drivers/net/phy/phy_device.c
> +++ b/drivers/net/phy/phy_device.c
[...]
> @@ -873,6 +941,36 @@ static int genphy_config_init(struct phy_device *phydev)
>
> return 0;
> }
> +
> +/* Replicate mdio45_probe */
> +int gen10g_config_init(struct phy_device *phydev)
> +{
> + int mmd, stat2, devs1, devs2;
> +
> + phydev->supported = phydev->advertising = SUPPORTED_10000baseT_Full;
[...]
Whyever are you assuming that?
> diff --git a/include/linux/phy.h b/include/linux/phy.h
> index 987e111..8fb1b52 100644
> --- a/include/linux/phy.h
> +++ b/include/linux/phy.h
[...]
> @@ -62,7 +63,8 @@ typedef enum {
> PHY_INTERFACE_MODE_RGMII_ID,
> PHY_INTERFACE_MODE_RGMII_RXID,
> PHY_INTERFACE_MODE_RGMII_TXID,
> - PHY_INTERFACE_MODE_RTBI
> + PHY_INTERFACE_MODE_RTBI,
> + PHY_INTERFACE_MODE_XGMII
> } phy_interface_t;
[...]
What about XAUI and XFI? I don't think anyone uses XGMII other than as
an on-chip interface.
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
* [PATCH v2 2/2] phylib: Convert MDIO bitbang to new MDIO 45 format
From: Andy Fleming @ 2010-05-21 18:31 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <1274466711-24962-2-git-send-email-afleming@freescale.com>
Now that we've added somewhat more complete MDIO 45 support to the PHY
Lib, convert the MDIO bitbang driver to use this new infrastructure.
Signed-off-by: Andy Fleming <afleming@freescale.com>
---
drivers/net/phy/mdio-bitbang.c | 29 +++++++++++++++--------------
1 files changed, 15 insertions(+), 14 deletions(-)
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index 2f6f02e..be7ae74 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -134,11 +134,10 @@ static void mdiobb_cmd(struct mdiobb_ctrl *ctrl, int op, u8 phy, u8 reg)
MII_ADDR_C45 into the address. Theoretically clause 45 and normal devices
can exist on the same bus. Normal devices should ignore the MDIO_ADDR
phase. */
-static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr)
+static void mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, int devad,
+ int reg)
{
- unsigned int dev_addr = (addr >> 16) & 0x1F;
- unsigned int reg = addr & 0xFFFF;
- mdiobb_cmd(ctrl, MDIO_C45_ADDR, phy, dev_addr);
+ mdiobb_cmd(ctrl, MDIO_C45_ADDR, phy, devad);
/* send the turnaround (10) */
mdiobb_send_bit(ctrl, 1);
@@ -148,8 +147,6 @@ static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr)
ctrl->ops->set_mdio_dir(ctrl, 0);
mdiobb_get_bit(ctrl);
-
- return dev_addr;
}
static int mdiobb_read(struct mii_bus *bus, int phy, int devad, int reg)
@@ -157,11 +154,13 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int devad, int reg)
struct mdiobb_ctrl *ctrl = bus->priv;
int ret, i;
- if (reg & MII_ADDR_C45) {
- reg = mdiobb_cmd_addr(ctrl, phy, reg);
- mdiobb_cmd(ctrl, MDIO_C45_READ, phy, reg);
- } else
+ /* Clause 22 PHYs only use devad = 0, and Clause 45 only use nonzero */
+ if (devad == MDIO_DEVAD_NONE)
mdiobb_cmd(ctrl, MDIO_READ, phy, reg);
+ else {
+ mdiobb_cmd_addr(ctrl, phy, devad, reg);
+ mdiobb_cmd(ctrl, MDIO_C45_READ, phy, devad);
+ }
ctrl->ops->set_mdio_dir(ctrl, 0);
@@ -186,11 +185,13 @@ static int mdiobb_write(struct mii_bus *bus, int phy, int devad, int reg,
{
struct mdiobb_ctrl *ctrl = bus->priv;
- if (reg & MII_ADDR_C45) {
- reg = mdiobb_cmd_addr(ctrl, phy, reg);
- mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, reg);
- } else
+ /* Clause 22 PHYs only use devad = 0, and Clause 45 only use nonzero */
+ if (devad == MDIO_DEVAD_NONE)
mdiobb_cmd(ctrl, MDIO_WRITE, phy, reg);
+ else {
+ mdiobb_cmd_addr(ctrl, phy, devad, reg);
+ mdiobb_cmd(ctrl, MDIO_C45_WRITE, phy, devad);
+ }
/* send the turnaround (10) */
mdiobb_send_bit(ctrl, 1);
--
1.6.5.2.g6ff9a
^ permalink raw reply related
* [PATCH v2 1/2] phylib: Convert MDIO and PHY Lib drivers to support 10G
From: Andy Fleming @ 2010-05-21 18:31 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <1274466711-24962-1-git-send-email-afleming@freescale.com>
10G MDIO is a totally different protocol (clause 45 of 802.3).
Supporting this new protocol requires a couple of changes:
* Add a new parameter to the mdiobus_read functions to specify the
"device address" inside the PHY.
* Add a phy45_read command which takes advantage of that new parameter
* Add a generic PHY driver for 10G PHYs
* Convert all of the existing drivers to use the new format
Signed-off-by: Andy Fleming <afleming@freescale.com>
---
Documentation/networking/phy.txt | 13 +-
arch/powerpc/platforms/pasemi/gpio_mdio.c | 6 +-
drivers/net/arm/ixp4xx_eth.c | 7 +-
drivers/net/au1000_eth.c | 7 +-
drivers/net/bcm63xx_enet.c | 4 +-
drivers/net/bfin_mac.c | 7 +-
drivers/net/cpmac.c | 4 +-
drivers/net/davinci_emac.c | 5 +-
drivers/net/dnet.c | 7 +-
drivers/net/ethoc.c | 5 +-
drivers/net/fec.c | 7 +-
drivers/net/fec_mpc52xx_phy.c | 7 +-
drivers/net/fs_enet/mii-fec.c | 6 +-
drivers/net/fsl_pq_mdio.c | 13 +-
drivers/net/fsl_pq_mdio.h | 11 +-
drivers/net/greth.c | 5 +-
drivers/net/ll_temac_mdio.c | 5 +-
drivers/net/macb.c | 7 +-
drivers/net/mv643xx_eth.c | 5 +-
drivers/net/phy/fixed.c | 5 +-
drivers/net/phy/icplus.c | 15 ++-
drivers/net/phy/mdio-bitbang.c | 5 +-
drivers/net/phy/mdio-octeon.c | 5 +-
drivers/net/phy/mdio_bus.c | 8 +-
drivers/net/phy/phy_device.c | 170 ++++++++++++++++++++++++++---
drivers/net/s6gmac.c | 5 +-
drivers/net/sb1250-mac.c | 14 ++-
drivers/net/smsc911x.c | 19 ++--
drivers/net/smsc9420.c | 9 +-
drivers/net/stmmac/stmmac_mdio.c | 9 +-
drivers/net/tc35815.c | 5 +-
drivers/net/tg3.c | 5 +-
drivers/net/xilinx_emaclite.c | 9 +-
include/linux/phy.h | 57 ++++++++--
34 files changed, 343 insertions(+), 128 deletions(-)
diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt
index 88bb71b..8729cac 100644
--- a/Documentation/networking/phy.txt
+++ b/Documentation/networking/phy.txt
@@ -40,13 +40,14 @@ The MDIO bus
1) read and write functions must be implemented. Their prototypes are:
- int write(struct mii_bus *bus, int mii_id, int regnum, u16 value);
- int read(struct mii_bus *bus, int mii_id, int regnum);
-
- mii_id is the address on the bus for the PHY, and regnum is the register
- number. These functions are guaranteed not to be called from interrupt
- time, so it is safe for them to block, waiting for an interrupt to signal
- the operation is complete
+ int write(struct mii_bus *bus, int addr, int devad, u16 regnum,
+ u16 value);
+ int read(struct mii_bus *bus, int addr, int devad, u16 regnum);
+
+ addr is the address on the bus for the PHY, devad is the address of the
+ internal device, and regnum is the register number. These functions are
+ guaranteed not to be called from interrupt time, so it is safe for them
+ to block, waiting for an interrupt to signal the operation is complete
2) A reset function is necessary. This is used to return the bus to an
initialized state.
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 0f881f6..ce9764c 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -124,7 +124,8 @@ static void bitbang_pre(struct mii_bus *bus, int read, u8 addr, u8 reg)
}
}
-static int gpio_mdio_read(struct mii_bus *bus, int phy_id, int location)
+static int gpio_mdio_read(struct mii_bus *bus, int phy_id, int devad,
+ int location)
{
u16 rdreg;
int ret, i;
@@ -163,7 +164,8 @@ static int gpio_mdio_read(struct mii_bus *bus, int phy_id, int location)
return ret;
}
-static int gpio_mdio_write(struct mii_bus *bus, int phy_id, int location, u16 val)
+static int gpio_mdio_write(struct mii_bus *bus, int phy_id, int devad,
+ int location, u16 val)
{
int i;
diff --git a/drivers/net/arm/ixp4xx_eth.c b/drivers/net/arm/ixp4xx_eth.c
index 24df032..51f1a72 100644
--- a/drivers/net/arm/ixp4xx_eth.c
+++ b/drivers/net/arm/ixp4xx_eth.c
@@ -298,7 +298,8 @@ static int ixp4xx_mdio_cmd(struct mii_bus *bus, int phy_id, int location,
((__raw_readl(&mdio_regs->mdio_status[1]) & 0xFF) << 8);
}
-static int ixp4xx_mdio_read(struct mii_bus *bus, int phy_id, int location)
+static int ixp4xx_mdio_read(struct mii_bus *bus, int phy_id, int devad,
+ int location)
{
unsigned long flags;
int ret;
@@ -313,8 +314,8 @@ static int ixp4xx_mdio_read(struct mii_bus *bus, int phy_id, int location)
return ret;
}
-static int ixp4xx_mdio_write(struct mii_bus *bus, int phy_id, int location,
- u16 val)
+static int ixp4xx_mdio_write(struct mii_bus *bus, int phy_id, int devad,
+ int location, u16 val)
{
unsigned long flags;
int ret;
diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c
index ece6128..d3cddb1 100644
--- a/drivers/net/au1000_eth.c
+++ b/drivers/net/au1000_eth.c
@@ -232,7 +232,8 @@ static void au1000_mdio_write(struct net_device *dev, int phy_addr,
*mii_control_reg = mii_control;
}
-static int au1000_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
+static int au1000_mdiobus_read(struct mii_bus *bus, int phy_addr, int devad,
+ int regnum)
{
/* WARNING: bus->phy_map[phy_addr].attached_dev == dev does
* _NOT_ hold (e.g. when PHY is accessed through other MAC's MII bus) */
@@ -243,8 +244,8 @@ static int au1000_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
return au1000_mdio_read(dev, phy_addr, regnum);
}
-static int au1000_mdiobus_write(struct mii_bus *bus, int phy_addr, int regnum,
- u16 value)
+static int au1000_mdiobus_write(struct mii_bus *bus, int phy_addr, int devad,
+ int regnum, u16 value)
{
struct net_device *const dev = bus->priv;
diff --git a/drivers/net/bcm63xx_enet.c b/drivers/net/bcm63xx_enet.c
index faf5add..152afa3 100644
--- a/drivers/net/bcm63xx_enet.c
+++ b/drivers/net/bcm63xx_enet.c
@@ -139,7 +139,7 @@ static int bcm_enet_mdio_write(struct bcm_enet_priv *priv, int mii_id,
* MII read callback from phylib
*/
static int bcm_enet_mdio_read_phylib(struct mii_bus *bus, int mii_id,
- int regnum)
+ int devad, int regnum)
{
return bcm_enet_mdio_read(bus->priv, mii_id, regnum);
}
@@ -148,7 +148,7 @@ static int bcm_enet_mdio_read_phylib(struct mii_bus *bus, int mii_id,
* MII write callback from phylib
*/
static int bcm_enet_mdio_write_phylib(struct mii_bus *bus, int mii_id,
- int regnum, u16 value)
+ int devad, int regnum, u16 value)
{
return bcm_enet_mdio_write(bus->priv, mii_id, regnum, value);
}
diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c
index 39a54ba..15ff21e 100644
--- a/drivers/net/bfin_mac.c
+++ b/drivers/net/bfin_mac.c
@@ -275,7 +275,8 @@ static int bfin_mdio_poll(void)
}
/* Read an off-chip register in a PHY through the MDC/MDIO port */
-static int bfin_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
+static int bfin_mdiobus_read(struct mii_bus *bus, int phy_addr,
+ int devad, int regnum)
{
int ret;
@@ -296,8 +297,8 @@ static int bfin_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
}
/* Write an off-chip register in a PHY through the MDC/MDIO port */
-static int bfin_mdiobus_write(struct mii_bus *bus, int phy_addr, int regnum,
- u16 value)
+static int bfin_mdiobus_write(struct mii_bus *bus, int phy_addr, int devad,
+ int regnum, u16 value)
{
int ret;
diff --git a/drivers/net/cpmac.c b/drivers/net/cpmac.c
index 3c58db5..eec4007 100644
--- a/drivers/net/cpmac.c
+++ b/drivers/net/cpmac.c
@@ -271,7 +271,7 @@ static void cpmac_dump_skb(struct net_device *dev, struct sk_buff *skb)
printk("\n");
}
-static int cpmac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+static int cpmac_mdio_read(struct mii_bus *bus, int phy_id, int devad, int reg)
{
u32 val;
@@ -285,7 +285,7 @@ static int cpmac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
}
static int cpmac_mdio_write(struct mii_bus *bus, int phy_id,
- int reg, u16 val)
+ int devad, int reg, u16 val)
{
while (cpmac_read(bus->priv, CPMAC_MDIO_ACCESS(0)) & MDIO_BUSY)
cpu_relax();
diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c
index 08e82b1..43c1023 100644
--- a/drivers/net/davinci_emac.c
+++ b/drivers/net/davinci_emac.c
@@ -2240,7 +2240,8 @@ void emac_poll_controller(struct net_device *ndev)
while ((emac_mdio_read((MDIO_USERACCESS(0))) &\
MDIO_USERACCESS_GO) != 0)
-static int emac_mii_read(struct mii_bus *bus, int phy_id, int phy_reg)
+static int emac_mii_read(struct mii_bus *bus, int phy_id, int devad,
+ int phy_reg)
{
unsigned int phy_data = 0;
unsigned int phy_control;
@@ -2263,7 +2264,7 @@ static int emac_mii_read(struct mii_bus *bus, int phy_id, int phy_reg)
}
static int emac_mii_write(struct mii_bus *bus, int phy_id,
- int phy_reg, u16 phy_data)
+ int devad, int phy_reg, u16 phy_data)
{
unsigned int control;
diff --git a/drivers/net/dnet.c b/drivers/net/dnet.c
index 8b0f50b..b1d26fd 100644
--- a/drivers/net/dnet.c
+++ b/drivers/net/dnet.c
@@ -99,7 +99,8 @@ static void __devinit dnet_get_hwaddr(struct dnet *bp)
memcpy(bp->dev->dev_addr, addr, sizeof(addr));
}
-static int dnet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+static int dnet_mdio_read(struct mii_bus *bus, int mii_id, int devad,
+ int regnum)
{
struct dnet *bp = bus->priv;
u16 value;
@@ -131,8 +132,8 @@ static int dnet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
return value;
}
-static int dnet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
- u16 value)
+static int dnet_mdio_write(struct mii_bus *bus, int mii_id, int devad,
+ int regnum, u16 value)
{
struct dnet *bp = bus->priv;
u16 tmp;
diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c
index 14cbde5..a2c6647 100644
--- a/drivers/net/ethoc.c
+++ b/drivers/net/ethoc.c
@@ -564,7 +564,7 @@ static int ethoc_poll(struct napi_struct *napi, int budget)
return work_done;
}
-static int ethoc_mdio_read(struct mii_bus *bus, int phy, int reg)
+static int ethoc_mdio_read(struct mii_bus *bus, int phy, int devad, int reg)
{
unsigned long timeout = jiffies + ETHOC_MII_TIMEOUT;
struct ethoc *priv = bus->priv;
@@ -587,7 +587,8 @@ static int ethoc_mdio_read(struct mii_bus *bus, int phy, int reg)
return -EBUSY;
}
-static int ethoc_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val)
+static int ethoc_mdio_write(struct mii_bus *bus, int phy, int devad,
+ int reg, u16 val)
{
unsigned long timeout = jiffies + ETHOC_MII_TIMEOUT;
struct ethoc *priv = bus->priv;
diff --git a/drivers/net/fec.c b/drivers/net/fec.c
index 42d9ac9..5286e88 100644
--- a/drivers/net/fec.c
+++ b/drivers/net/fec.c
@@ -609,7 +609,8 @@ spin_unlock:
/*
* NOTE: a MII transaction is during around 25 us, so polling it...
*/
-static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int devad,
+ int regnum)
{
struct fec_enet_private *fep = bus->priv;
int timeout = FEC_MII_TIMEOUT;
@@ -638,8 +639,8 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
}
-static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
- u16 value)
+static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int devad,
+ int regnum, u16 value)
{
struct fec_enet_private *fep = bus->priv;
int timeout = FEC_MII_TIMEOUT;
diff --git a/drivers/net/fec_mpc52xx_phy.c b/drivers/net/fec_mpc52xx_phy.c
index 7658a08..af52b5a 100644
--- a/drivers/net/fec_mpc52xx_phy.c
+++ b/drivers/net/fec_mpc52xx_phy.c
@@ -50,13 +50,14 @@ static int mpc52xx_fec_mdio_transfer(struct mii_bus *bus, int phy_id,
in_be32(&priv->regs->mii_data) & FEC_MII_DATA_DATAMSK : 0;
}
-static int mpc52xx_fec_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+static int mpc52xx_fec_mdio_read(struct mii_bus *bus, int phy_id, int devad,
+ int reg)
{
return mpc52xx_fec_mdio_transfer(bus, phy_id, reg, FEC_MII_READ_FRAME);
}
-static int mpc52xx_fec_mdio_write(struct mii_bus *bus, int phy_id, int reg,
- u16 data)
+static int mpc52xx_fec_mdio_write(struct mii_bus *bus, int phy_id, int devad,
+ int reg, u16 data)
{
return mpc52xx_fec_mdio_transfer(bus, phy_id, reg,
data | FEC_MII_WRITE_FRAME);
diff --git a/drivers/net/fs_enet/mii-fec.c b/drivers/net/fs_enet/mii-fec.c
index 5944b65..2d02356 100644
--- a/drivers/net/fs_enet/mii-fec.c
+++ b/drivers/net/fs_enet/mii-fec.c
@@ -49,7 +49,8 @@
#define FEC_MII_LOOPS 10000
-static int fs_enet_fec_mii_read(struct mii_bus *bus , int phy_id, int location)
+static int fs_enet_fec_mii_read(struct mii_bus *bus , int phy_id, int devad,
+ int location)
{
struct fec_info* fec = bus->priv;
struct fec __iomem *fecp = fec->fecp;
@@ -72,7 +73,8 @@ static int fs_enet_fec_mii_read(struct mii_bus *bus , int phy_id, int location)
return ret;
}
-static int fs_enet_fec_mii_write(struct mii_bus *bus, int phy_id, int location, u16 val)
+static int fs_enet_fec_mii_write(struct mii_bus *bus, int phy_id, int devad,
+ int location, u16 val)
{
struct fec_info* fec = bus->priv;
struct fec __iomem *fecp = fec->fecp;
diff --git a/drivers/net/fsl_pq_mdio.c b/drivers/net/fsl_pq_mdio.c
index ff028f5..1b66b23 100644
--- a/drivers/net/fsl_pq_mdio.c
+++ b/drivers/net/fsl_pq_mdio.c
@@ -61,7 +61,7 @@ struct fsl_pq_mdio_priv {
* controlling the external PHYs, for example.
*/
int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
- int regnum, u16 value)
+ int regnum, u16 value)
{
/* Set the PHY address and the register address we want to write */
out_be32(®s->miimadd, (mii_id << 8) | regnum);
@@ -86,8 +86,8 @@ int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
* and are always tied to the local mdio pins, which may not be the
* same as system mdio bus, used for controlling the external PHYs, for eg.
*/
-int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs,
- int mii_id, int regnum)
+int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id,
+ int regnum)
{
u16 value;
@@ -119,7 +119,8 @@ static struct fsl_pq_mdio __iomem *fsl_pq_mdio_get_regs(struct mii_bus *bus)
* Write value to the PHY at mii_id at register regnum,
* on the bus, waiting until the write is done before returning.
*/
-int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value)
+int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int devad, int regnum,
+ u16 value)
{
struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus);
@@ -131,7 +132,7 @@ int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value)
* Read the bus for PHY at addr mii_id, register regnum, and
* return the value. Clears miimcom first.
*/
-int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int devad, int regnum)
{
struct fsl_pq_mdio __iomem *regs = fsl_pq_mdio_get_regs(bus);
@@ -190,7 +191,7 @@ static int fsl_pq_mdio_find_free(struct mii_bus *new_bus)
for (i = PHY_MAX_ADDR; i > 0; i--) {
u32 phy_id;
- if (get_phy_id(new_bus, i, &phy_id))
+ if (get_phy_id(new_bus, i, MDIO_DEVAD_NONE, &phy_id))
return -1;
if (phy_id == 0xffffffff)
diff --git a/drivers/net/fsl_pq_mdio.h b/drivers/net/fsl_pq_mdio.h
index 1f7d865..48328eb 100644
--- a/drivers/net/fsl_pq_mdio.h
+++ b/drivers/net/fsl_pq_mdio.h
@@ -41,11 +41,14 @@ struct fsl_pq_mdio {
u8 res4[2728];
} __attribute__ ((packed));
-int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int regnum);
-int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value);
+
+int fsl_pq_mdio_read(struct mii_bus *bus, int mii_id, int devad, int regnum);
+int fsl_pq_mdio_write(struct mii_bus *bus, int mii_id, int devad, int regnum,
+ u16 value);
int fsl_pq_local_mdio_write(struct fsl_pq_mdio __iomem *regs, int mii_id,
- int regnum, u16 value);
-int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id, int regnum);
+ int regnum, u16 value);
+int fsl_pq_local_mdio_read(struct fsl_pq_mdio __iomem *regs, int mii_id,
+ int regnum);
int __init fsl_pq_mdio_init(void);
void fsl_pq_mdio_exit(void);
void fsl_pq_mdio_bus_name(char *name, struct device_node *np);
diff --git a/drivers/net/greth.c b/drivers/net/greth.c
index fd491e4..230ad75 100644
--- a/drivers/net/greth.c
+++ b/drivers/net/greth.c
@@ -1169,7 +1169,7 @@ static inline int wait_for_mdio(struct greth_private *greth)
return 1;
}
-static int greth_mdio_read(struct mii_bus *bus, int phy, int reg)
+static int greth_mdio_read(struct mii_bus *bus, int phy, int devad, int reg)
{
struct greth_private *greth = bus->priv;
int data;
@@ -1191,7 +1191,8 @@ static int greth_mdio_read(struct mii_bus *bus, int phy, int reg)
}
}
-static int greth_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val)
+static int greth_mdio_write(struct mii_bus *bus, int phy, int devad, int reg,
+ u16 val)
{
struct greth_private *greth = bus->priv;
diff --git a/drivers/net/ll_temac_mdio.c b/drivers/net/ll_temac_mdio.c
index 5ae28c9..c02d5a5 100644
--- a/drivers/net/ll_temac_mdio.c
+++ b/drivers/net/ll_temac_mdio.c
@@ -18,7 +18,7 @@
/* ---------------------------------------------------------------------
* MDIO Bus functions
*/
-static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+static int temac_mdio_read(struct mii_bus *bus, int phy_id, int devad, int reg)
{
struct temac_local *lp = bus->priv;
u32 rc;
@@ -37,7 +37,8 @@ static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
return rc;
}
-static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
+static int temac_mdio_write(struct mii_bus *bus, int phy_id, int devad, int reg,
+ u16 val)
{
struct temac_local *lp = bus->priv;
diff --git a/drivers/net/macb.c b/drivers/net/macb.c
index 40797fb..15c1b14 100644
--- a/drivers/net/macb.c
+++ b/drivers/net/macb.c
@@ -88,7 +88,8 @@ static void __init macb_get_hwaddr(struct macb *bp)
}
}
-static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+static int macb_mdio_read(struct mii_bus *bus, int mii_id, int devad,
+ int regnum)
{
struct macb *bp = bus->priv;
int value;
@@ -108,8 +109,8 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
return value;
}
-static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
- u16 value)
+static int macb_mdio_write(struct mii_bus *bus, int mii_id, int devad,
+ int regnum, u16 value)
{
struct macb *bp = bus->priv;
diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c
index e345ec8..93f4bf1 100644
--- a/drivers/net/mv643xx_eth.c
+++ b/drivers/net/mv643xx_eth.c
@@ -1111,7 +1111,7 @@ static int smi_wait_ready(struct mv643xx_eth_shared_private *msp)
return 0;
}
-static int smi_bus_read(struct mii_bus *bus, int addr, int reg)
+static int smi_bus_read(struct mii_bus *bus, int addr, int devad, int reg)
{
struct mv643xx_eth_shared_private *msp = bus->priv;
void __iomem *smi_reg = msp->base + SMI_REG;
@@ -1138,7 +1138,8 @@ static int smi_bus_read(struct mii_bus *bus, int addr, int reg)
return ret & 0xffff;
}
-static int smi_bus_write(struct mii_bus *bus, int addr, int reg, u16 val)
+static int smi_bus_write(struct mii_bus *bus, int addr, int devad, int reg,
+ u16 val)
{
struct mv643xx_eth_shared_private *msp = bus->priv;
void __iomem *smi_reg = msp->base + SMI_REG;
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index 1fa4d73..31f621e 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -115,7 +115,8 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
return 0;
}
-static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int reg_num)
+static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int devad,
+ int reg_num)
{
struct fixed_mdio_bus *fmb = bus->priv;
struct fixed_phy *fp;
@@ -139,7 +140,7 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int reg_num)
}
static int fixed_mdio_write(struct mii_bus *bus, int phy_id, int reg_num,
- u16 val)
+ int devad, u16 val)
{
return 0;
}
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index 439adaf..4b5b059 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -42,36 +42,41 @@ static int ip175c_config_init(struct phy_device *phydev)
if (full_reset_performed == 0) {
/* master reset */
- err = phydev->bus->write(phydev->bus, 30, 0, 0x175c);
+ err = phydev->bus->write(phydev->bus, 30, MDIO_DEVAD_NONE, 0,
+ 0x175c);
if (err < 0)
return err;
/* ensure no bus delays overlap reset period */
- err = phydev->bus->read(phydev->bus, 30, 0);
+ err = phydev->bus->read(phydev->bus, 30, MDIO_DEVAD_NONE, 0);
/* data sheet specifies reset period is 2 msec */
mdelay(2);
/* enable IP175C mode */
- err = phydev->bus->write(phydev->bus, 29, 31, 0x175c);
+ err = phydev->bus->write(phydev->bus, 29, MDIO_DEVAD_NONE, 31,
+ 0x175c);
if (err < 0)
return err;
/* Set MII0 speed and duplex (in PHY mode) */
- err = phydev->bus->write(phydev->bus, 29, 22, 0x420);
+ err = phydev->bus->write(phydev->bus, 29, MDIO_DEVAD_NONE, 22,
+ 0x420);
if (err < 0)
return err;
/* reset switch ports */
for (i = 0; i < 5; i++) {
err = phydev->bus->write(phydev->bus, i,
+ MDIO_DEVAD_NONE,
MII_BMCR, BMCR_RESET);
if (err < 0)
return err;
}
for (i = 0; i < 5; i++)
- err = phydev->bus->read(phydev->bus, i, MII_BMCR);
+ err = phydev->bus->read(phydev->bus, i, MDIO_DEVAD_NONE,
+ MII_BMCR);
mdelay(2);
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index 6539189..2f6f02e 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -152,7 +152,7 @@ static int mdiobb_cmd_addr(struct mdiobb_ctrl *ctrl, int phy, u32 addr)
return dev_addr;
}
-static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
+static int mdiobb_read(struct mii_bus *bus, int phy, int devad, int reg)
{
struct mdiobb_ctrl *ctrl = bus->priv;
int ret, i;
@@ -181,7 +181,8 @@ static int mdiobb_read(struct mii_bus *bus, int phy, int reg)
return ret;
}
-static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
+static int mdiobb_write(struct mii_bus *bus, int phy, int devad, int reg,
+ u16 val)
{
struct mdiobb_ctrl *ctrl = bus->priv;
diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/phy/mdio-octeon.c
index f443d43..021af21 100644
--- a/drivers/net/phy/mdio-octeon.c
+++ b/drivers/net/phy/mdio-octeon.c
@@ -24,7 +24,8 @@ struct octeon_mdiobus {
int phy_irq[PHY_MAX_ADDR];
};
-static int octeon_mdiobus_read(struct mii_bus *bus, int phy_id, int regnum)
+static int octeon_mdiobus_read(struct mii_bus *bus, int phy_id, int devad,
+ int regnum)
{
struct octeon_mdiobus *p = bus->priv;
union cvmx_smix_cmd smi_cmd;
@@ -52,7 +53,7 @@ static int octeon_mdiobus_read(struct mii_bus *bus, int phy_id, int regnum)
return -EIO;
}
-static int octeon_mdiobus_write(struct mii_bus *bus, int phy_id,
+static int octeon_mdiobus_write(struct mii_bus *bus, int phy_id, int devad
int regnum, u16 val)
{
struct octeon_mdiobus *p = bus->priv;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 6a6b819..5c7df03 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -208,14 +208,14 @@ EXPORT_SYMBOL(mdiobus_scan);
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
+int mdiobus_read(struct mii_bus *bus, int addr, int devad, u16 regnum)
{
int retval;
BUG_ON(in_interrupt());
mutex_lock(&bus->mdio_lock);
- retval = bus->read(bus, addr, regnum);
+ retval = bus->read(bus, addr, devad, regnum);
mutex_unlock(&bus->mdio_lock);
return retval;
@@ -233,14 +233,14 @@ EXPORT_SYMBOL(mdiobus_read);
* because the bus read/write functions may wait for an interrupt
* to conclude the operation.
*/
-int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
+int mdiobus_write(struct mii_bus *bus, int addr, int devad, u16 regnum, u16 val)
{
int err;
BUG_ON(in_interrupt());
mutex_lock(&bus->mdio_lock);
- err = bus->write(bus, addr, regnum, val);
+ err = bus->write(bus, addr, devad, regnum, val);
mutex_unlock(&bus->mdio_lock);
return err;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 1a99bb2..c72ba85 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -4,9 +4,11 @@
* Framework for finding and configuring PHYs.
* Also contains generic PHY driver
*
+ * 10G PHY Driver support mostly appropriated from drivers/net/mdio.c
+ *
* Author: Andy Fleming
*
- * Copyright (c) 2004 Freescale Semiconductor, Inc.
+ * Copyright (c) 2004-2006, 2008-2009 Freescale Semiconductor, Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
@@ -29,6 +31,7 @@
#include <linux/module.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
+#include <linux/mdio.h>
#include <linux/phy.h>
#include <asm/io.h>
@@ -51,6 +54,7 @@ static void phy_device_release(struct device *dev)
}
static struct phy_driver genphy_driver;
+static struct phy_driver gen10g_driver;
extern int mdio_bus_init(void);
extern void mdio_bus_exit(void);
@@ -204,13 +208,13 @@ EXPORT_SYMBOL(phy_device_create);
* Description: Reads the ID registers of the PHY at @addr on the
* @bus, stores it in @phy_id and returns zero on success.
*/
-int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id)
+int get_phy_id(struct mii_bus *bus, int addr, int devad, u32 *phy_id)
{
int phy_reg;
/* Grab the bits from PHYIR1, and put them
* in the upper half */
- phy_reg = bus->read(bus, addr, MII_PHYSID1);
+ phy_reg = bus->read(bus, addr, devad, MII_PHYSID1);
if (phy_reg < 0)
return -EIO;
@@ -218,7 +222,7 @@ int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id)
*phy_id = (phy_reg & 0xffff) << 16;
/* Grab the bits from PHYIR2, and put them in the lower half */
- phy_reg = bus->read(bus, addr, MII_PHYSID2);
+ phy_reg = bus->read(bus, addr, devad, MII_PHYSID2);
if (phy_reg < 0)
return -EIO;
@@ -239,21 +243,31 @@ EXPORT_SYMBOL(get_phy_id);
*/
struct phy_device * get_phy_device(struct mii_bus *bus, int addr)
{
- struct phy_device *dev = NULL;
- u32 phy_id;
+ u32 phy_id = 0x1fffffff;
+ int i;
int r;
- r = get_phy_id(bus, addr, &phy_id);
+ /* Try Standard (ie Clause 22) access */
+ r = get_phy_id(bus, addr, MDIO_DEVAD_NONE, &phy_id);
if (r)
return ERR_PTR(r);
- /* If the phy_id is mostly Fs, there is no device there */
- if ((phy_id & 0x1fffffff) == 0x1fffffff)
- return NULL;
+ /* If the PHY ID is mostly f's, we didn't find anything */
+ if ((phy_id & 0x1fffffff) != 0x1fffffff)
+ return phy_device_create(bus, addr, phy_id);
- dev = phy_device_create(bus, addr, phy_id);
+ /* Otherwise we have to try Clause 45 */
+ for (i = 1; i < 5; i++) {
+ r = get_phy_id(bus, addr, i, &phy_id);
+ if (r)
+ return ERR_PTR(r);
- return dev;
+ /* If the phy_id is mostly Fs, there is no device there */
+ if ((phy_id & 0x1fffffff) != 0x1fffffff)
+ break;
+ }
+
+ return phy_device_create(bus, addr, phy_id);
}
EXPORT_SYMBOL(get_phy_device);
@@ -430,8 +444,8 @@ int phy_init_hw(struct phy_device *phydev)
*
* Description: Called by drivers to attach to a particular PHY
* device. The phy_device is found, and properly hooked up
- * to the phy_driver. If no driver is attached, then the
- * genphy_driver is used. The phy_device is given a ptr to
+ * to the phy_driver. If no driver is attached, then a
+ * generic driver is used. The phy_device is given a ptr to
* the attaching device, and given a callback for link status
* change. The phy_device is returned to the attaching driver.
*/
@@ -444,7 +458,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
* exist, and we should use the genphy driver. */
if (NULL == d->driver) {
int err;
- d->driver = &genphy_driver.driver;
+ if (interface == PHY_INTERFACE_MODE_XGMII)
+ d->driver = &gen10g_driver.driver;
+ else
+ d->driver = &genphy_driver.driver;
err = d->driver->probe(d);
if (err >= 0)
@@ -521,6 +538,8 @@ void phy_detach(struct phy_device *phydev)
* real driver could be loaded */
if (phydev->dev.driver == &genphy_driver.driver)
device_release_driver(&phydev->dev);
+ else if (phydev->dev.driver == &gen10g_driver.driver)
+ device_release_driver(&phydev->dev);
}
EXPORT_SYMBOL(phy_detach);
@@ -603,6 +622,12 @@ int genphy_config_advert(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_config_advert);
+int gen10g_config_advert(struct phy_device *dev)
+{
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_config_advert);
+
/**
* genphy_setup_forced - configures/forces speed/duplex from @phydev
* @phydev: target phy_device struct
@@ -631,6 +656,10 @@ int genphy_setup_forced(struct phy_device *phydev)
return err;
}
+int gen10g_setup_forced(struct phy_device *phydev)
+{
+ return 0;
+}
/**
* genphy_restart_aneg - Enable and Restart Autonegotiation
@@ -656,6 +685,12 @@ int genphy_restart_aneg(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_restart_aneg);
+int gen10g_restart_aneg(struct phy_device *phydev)
+{
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_restart_aneg);
+
/**
* genphy_config_aneg - restart auto-negotiation or write BMCR
@@ -698,6 +733,12 @@ int genphy_config_aneg(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_config_aneg);
+int gen10g_config_aneg(struct phy_device *phydev)
+{
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_config_aneg);
+
/**
* genphy_update_link - update link status in @phydev
* @phydev: target phy_device struct
@@ -827,6 +868,33 @@ int genphy_read_status(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_read_status);
+int gen10g_read_status(struct phy_device *phydev)
+{
+ int devad, reg;
+ u32 mmd_mask = phydev->mmds;
+
+ phydev->link = 1;
+
+ /* For now just lie and say it's 10G all the time */
+ phydev->speed = 10000;
+ phydev->duplex = DUPLEX_FULL;
+
+ for (devad = 0; mmd_mask; devad++, mmd_mask = mmd_mask >> 1) {
+ if (!mmd_mask & 1)
+ continue;
+
+ /* Read twice because link state is latched and a
+ * read moves the current state into the register */
+ phy45_read(phydev, devad, MDIO_STAT1);
+ reg = phy45_read(phydev, devad, MDIO_STAT1);
+ if (reg < 0 || !(reg & MDIO_STAT1_LSTATUS))
+ phydev->link = 0;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_read_status);
+
static int genphy_config_init(struct phy_device *phydev)
{
int val;
@@ -873,6 +941,36 @@ static int genphy_config_init(struct phy_device *phydev)
return 0;
}
+
+/* Replicate mdio45_probe */
+int gen10g_config_init(struct phy_device *phydev)
+{
+ int mmd, stat2, devs1, devs2;
+
+ phydev->supported = phydev->advertising = SUPPORTED_10000baseT_Full;
+
+ /* Assume PHY must have at least one of PMA/PMD, WIS, PCS, PHY
+ * XS or DTE XS; give up if none is present. */
+ for (mmd = 1; mmd <= 5; mmd++) {
+ /* Is this MMD present? */
+ stat2 = phy45_read(phydev, mmd, MDIO_STAT2);
+ if (stat2 < 0 ||
+ (stat2 & MDIO_STAT2_DEVPRST) != MDIO_STAT2_DEVPRST_VAL)
+ continue;
+
+ /* It should tell us about all the other MMDs */
+ devs1 = phy45_read(phydev, mmd, MDIO_DEVS1);
+ devs2 = phy45_read(phydev, mmd, MDIO_DEVS2);
+ if (devs1 < 0 || devs2 < 0)
+ continue;
+
+ phydev->mmds = devs1 | (devs2 << 16);
+ return 0;
+ }
+
+ return -ENODEV;
+}
+
int genphy_suspend(struct phy_device *phydev)
{
int value;
@@ -888,6 +986,12 @@ int genphy_suspend(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_suspend);
+int gen10g_suspend(struct phy_device *phydev)
+{
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_suspend);
+
int genphy_resume(struct phy_device *phydev)
{
int value;
@@ -903,6 +1007,13 @@ int genphy_resume(struct phy_device *phydev)
}
EXPORT_SYMBOL(genphy_resume);
+int gen10g_resume(struct phy_device *phydev)
+{
+ return 0;
+}
+EXPORT_SYMBOL(gen10g_resume);
+
+
/**
* phy_probe - probe and init a PHY device
* @dev: device to probe and init
@@ -1013,7 +1124,20 @@ static struct phy_driver genphy_driver = {
.read_status = genphy_read_status,
.suspend = genphy_suspend,
.resume = genphy_resume,
- .driver = {.owner= THIS_MODULE, },
+ .driver = {.owner = THIS_MODULE, },
+};
+
+static struct phy_driver gen10g_driver = {
+ .phy_id = 0xffffffff,
+ .phy_id_mask = 0xffffffff,
+ .name = "Generic 10G PHY",
+ .config_init = gen10g_config_init,
+ .features = 0,
+ .config_aneg = gen10g_config_aneg,
+ .read_status = gen10g_read_status,
+ .suspend = gen10g_suspend,
+ .resume = gen10g_resume,
+ .driver = {.owner = THIS_MODULE, },
};
static int __init phy_init(void)
@@ -1026,13 +1150,25 @@ static int __init phy_init(void)
rc = phy_driver_register(&genphy_driver);
if (rc)
- mdio_bus_exit();
+ goto genphy_register_failed;
+
+ rc = phy_driver_register(&gen10g_driver);
+ if (rc)
+ goto gen10g_register_failed;
+
+ return rc;
+
+gen10g_register_failed:
+ phy_driver_unregister(&genphy_driver);
+genphy_register_failed:
+ mdio_bus_exit();
return rc;
}
static void __exit phy_exit(void)
{
+ phy_driver_unregister(&gen10g_driver);
phy_driver_unregister(&genphy_driver);
mdio_bus_exit();
}
diff --git a/drivers/net/s6gmac.c b/drivers/net/s6gmac.c
index a7ff8ea..7430211 100644
--- a/drivers/net/s6gmac.c
+++ b/drivers/net/s6gmac.c
@@ -661,7 +661,7 @@ static int s6mii_busy(struct s6gmac *pd, int tmo)
return 0;
}
-static int s6mii_read(struct mii_bus *bus, int phy_addr, int regnum)
+static int s6mii_read(struct mii_bus *bus, int phy_addr, int devad, int regnum)
{
struct s6gmac *pd = bus->priv;
s6mii_enable(pd);
@@ -677,7 +677,8 @@ static int s6mii_read(struct mii_bus *bus, int phy_addr, int regnum)
return (u16)readl(pd->reg + S6_GMAC_MACMIISTAT);
}
-static int s6mii_write(struct mii_bus *bus, int phy_addr, int regnum, u16 value)
+static int s6mii_write(struct mii_bus *bus, int phy_addr, int devad,
+ int regnum, u16 value)
{
struct s6gmac *pd = bus->priv;
s6mii_enable(pd);
diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c
index 1f3acc3..5168400 100644
--- a/drivers/net/sb1250-mac.c
+++ b/drivers/net/sb1250-mac.c
@@ -322,9 +322,10 @@ static int sbmac_mii_probe(struct net_device *dev);
static void sbmac_mii_sync(void __iomem *sbm_mdio);
static void sbmac_mii_senddata(void __iomem *sbm_mdio, unsigned int data,
int bitcnt);
-static int sbmac_mii_read(struct mii_bus *bus, int phyaddr, int regidx);
-static int sbmac_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
- u16 val);
+static int sbmac_mii_read(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx);
+static int sbmac_mii_write(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx, u16 val);
/**********************************************************************
@@ -434,7 +435,8 @@ static void sbmac_mii_senddata(void __iomem *sbm_mdio, unsigned int data,
* value read, or 0xffff if an error occurred.
********************************************************************* */
-static int sbmac_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
+static int sbmac_mii_read(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx)
{
struct sbmac_softc *sc = (struct sbmac_softc *)bus->priv;
void __iomem *sbm_mdio = sc->sbm_mdio;
@@ -527,8 +529,8 @@ static int sbmac_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
* 0 for success
********************************************************************* */
-static int sbmac_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
- u16 regval)
+static int sbmac_mii_write(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx, u16 regval)
{
struct sbmac_softc *sc = (struct sbmac_softc *)bus->priv;
void __iomem *sbm_mdio = sc->sbm_mdio;
diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c
index 89f35f9..4424da5 100644
--- a/drivers/net/smsc911x.c
+++ b/drivers/net/smsc911x.c
@@ -302,7 +302,8 @@ static void smsc911x_mac_write(struct smsc911x_data *pdata,
}
/* Get a phy register */
-static int smsc911x_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
+static int smsc911x_mii_read(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx)
{
struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv;
unsigned long flags;
@@ -339,8 +340,8 @@ out:
}
/* Set a phy register */
-static int smsc911x_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
- u16 val)
+static int smsc911x_mii_write(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx, u16 val)
{
struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv;
unsigned long flags;
@@ -570,11 +571,10 @@ static int smsc911x_phy_reset(struct smsc911x_data *pdata)
BUG_ON(!phy_dev->bus);
SMSC_TRACE(HW, "Performing PHY BCR Reset");
- smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, BMCR_RESET);
+ phy_write(phy_dev, MII_BMCR, BMCR_RESET);
do {
msleep(1);
- temp = smsc911x_mii_read(phy_dev->bus, phy_dev->addr,
- MII_BMCR);
+ temp = phy_read(phy_dev, MII_BMCR);
} while ((i--) && (temp & BMCR_RESET));
if (temp & BMCR_RESET) {
@@ -622,8 +622,7 @@ static int smsc911x_phy_loopbacktest(struct net_device *dev)
for (i = 0; i < 10; i++) {
/* Set PHY to 10/FD, no ANEG, and loopback mode */
- smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR,
- BMCR_LOOPBACK | BMCR_FULLDPLX);
+ phy_write(phy_dev, MII_BMCR, BMCR_LOOPBACK | BMCR_FULLDPLX);
/* Enable MAC tx/rx, FD */
spin_lock_irqsave(&pdata->mac_lock, flags);
@@ -651,7 +650,7 @@ static int smsc911x_phy_loopbacktest(struct net_device *dev)
spin_unlock_irqrestore(&pdata->mac_lock, flags);
/* Cancel PHY loopback mode */
- smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, 0);
+ phy_write(phy_dev, MII_BMCR, 0);
smsc911x_reg_write(pdata, TX_CFG, 0);
smsc911x_reg_write(pdata, RX_CFG, 0);
@@ -1615,7 +1614,7 @@ smsc911x_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs,
}
for (i = 0; i <= 31; i++)
- data[j++] = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, i);
+ data[j++] = phy_read(phy_dev, i);
}
static void smsc911x_eeprom_enable_access(struct smsc911x_data *pdata)
diff --git a/drivers/net/smsc9420.c b/drivers/net/smsc9420.c
index 6cdee6a..871a71e 100644
--- a/drivers/net/smsc9420.c
+++ b/drivers/net/smsc9420.c
@@ -127,7 +127,8 @@ static inline void smsc9420_pci_flush_write(struct smsc9420_pdata *pd)
smsc9420_reg_read(pd, ID_REV);
}
-static int smsc9420_mii_read(struct mii_bus *bus, int phyaddr, int regidx)
+static int smsc9420_mii_read(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx)
{
struct smsc9420_pdata *pd = (struct smsc9420_pdata *)bus->priv;
unsigned long flags;
@@ -164,8 +165,8 @@ out:
return reg;
}
-static int smsc9420_mii_write(struct mii_bus *bus, int phyaddr, int regidx,
- u16 val)
+static int smsc9420_mii_write(struct mii_bus *bus, int phyaddr, int devad,
+ int regidx, u16 val)
{
struct smsc9420_pdata *pd = (struct smsc9420_pdata *)bus->priv;
unsigned long flags;
@@ -328,7 +329,7 @@ smsc9420_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs,
return;
for (i = 0; i <= 31; i++)
- data[j++] = smsc9420_mii_read(phy_dev->bus, phy_dev->addr, i);
+ data[j++] = phy_read(phy_dev, i);
}
static void smsc9420_eeprom_enable_access(struct smsc9420_pdata *pd)
diff --git a/drivers/net/stmmac/stmmac_mdio.c b/drivers/net/stmmac/stmmac_mdio.c
index 40b2c79..dd0a89a 100644
--- a/drivers/net/stmmac/stmmac_mdio.c
+++ b/drivers/net/stmmac/stmmac_mdio.c
@@ -37,13 +37,15 @@
* stmmac_mdio_read
* @bus: points to the mii_bus structure
* @phyaddr: MII addr reg bits 15-11
+ * @devad: unused
* @phyreg: MII addr reg bits 10-6
* Description: it reads data from the MII register from within the phy device.
* For the 7111 GMAC, we must set the bit 0 in the MII address register while
* accessing the PHY registers.
* Fortunately, it seems this has no drawback for the 7109 MAC.
*/
-static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
+static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int devad,
+ int phyreg)
{
struct net_device *ndev = bus->priv;
struct stmmac_priv *priv = netdev_priv(ndev);
@@ -70,12 +72,13 @@ static int stmmac_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
* stmmac_mdio_write
* @bus: points to the mii_bus structure
* @phyaddr: MII addr reg bits 15-11
+ * @devad: unused
* @phyreg: MII addr reg bits 10-6
* @phydata: phy data
* Description: it writes the data into the MII register from within the device.
*/
-static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
- u16 phydata)
+static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int devad,
+ int phyreg, u16 phydata)
{
struct net_device *ndev = bus->priv;
struct stmmac_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/tc35815.c b/drivers/net/tc35815.c
index be08b75..b2a5e8c 100644
--- a/drivers/net/tc35815.c
+++ b/drivers/net/tc35815.c
@@ -500,7 +500,7 @@ static void panic_queues(struct net_device *dev);
static void tc35815_restart_work(struct work_struct *work);
-static int tc_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
+static int tc_mdio_read(struct mii_bus *bus, int mii_id, int devad, int regnum)
{
struct net_device *dev = bus->priv;
struct tc35815_regs __iomem *tr =
@@ -517,7 +517,8 @@ static int tc_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
return tc_readl(&tr->MD_Data) & 0xffff;
}
-static int tc_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 val)
+static int tc_mdio_write(struct mii_bus *bus, int mii_id, int devad,
+ int regnum, u16 val)
{
struct net_device *dev = bus->priv;
struct tc35815_regs __iomem *tr =
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 573054a..5c8a864 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -936,7 +936,7 @@ static int tg3_bmcr_reset(struct tg3 *tp)
return 0;
}
-static int tg3_mdio_read(struct mii_bus *bp, int mii_id, int reg)
+static int tg3_mdio_read(struct mii_bus *bp, int mii_id, int devad, int reg)
{
struct tg3 *tp = bp->priv;
u32 val;
@@ -951,7 +951,8 @@ static int tg3_mdio_read(struct mii_bus *bp, int mii_id, int reg)
return val;
}
-static int tg3_mdio_write(struct mii_bus *bp, int mii_id, int reg, u16 val)
+static int tg3_mdio_write(struct mii_bus *bp, int mii_id, int devad,
+ int reg, u16 val)
{
struct tg3 *tp = bp->priv;
u32 ret = 0;
diff --git a/drivers/net/xilinx_emaclite.c b/drivers/net/xilinx_emaclite.c
index a7db68d..653e493 100644
--- a/drivers/net/xilinx_emaclite.c
+++ b/drivers/net/xilinx_emaclite.c
@@ -738,6 +738,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
* xemaclite_mdio_read - Read from a given MII management register
* @bus: the mii_bus struct
* @phy_id: the phy address
+ * @devad: unused
* @reg: register number to read from
*
* This function waits till the device is ready to accept a new MDIO
@@ -746,7 +747,8 @@ static int xemaclite_mdio_wait(struct net_local *lp)
*
* Return: Value read from the MII management register
*/
-static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
+static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int devad,
+ int reg)
{
struct net_local *lp = bus->priv;
u32 ctrl_reg;
@@ -782,14 +784,15 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
* xemaclite_mdio_write - Write to a given MII management register
* @bus: the mii_bus struct
* @phy_id: the phy address
+ * @devad: unused
* @reg: register number to write to
* @val: value to write to the register number specified by reg
*
* This fucntion waits till the device is ready to accept a new MDIO
* request and then writes the val to the MDIO Write Data register.
*/
-static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
- u16 val)
+static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int devad,
+ int reg, u16 val)
{
struct net_local *lp = bus->priv;
u32 ctrl_reg;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 987e111..8fb1b52 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -6,7 +6,7 @@
*
* Author: Andy Fleming
*
- * Copyright (c) 2004 Freescale Semiconductor, Inc.
+ * Copyright (c) 2004-2009 Freescale Semiconductor, Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
@@ -22,6 +22,7 @@
#include <linux/device.h>
#include <linux/ethtool.h>
#include <linux/mii.h>
+#include <linux/mdio.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/mod_devicetable.h>
@@ -62,7 +63,8 @@ typedef enum {
PHY_INTERFACE_MODE_RGMII_ID,
PHY_INTERFACE_MODE_RGMII_RXID,
PHY_INTERFACE_MODE_RGMII_TXID,
- PHY_INTERFACE_MODE_RTBI
+ PHY_INTERFACE_MODE_RTBI,
+ PHY_INTERFACE_MODE_XGMII
} phy_interface_t;
@@ -94,8 +96,10 @@ struct mii_bus {
const char *name;
char id[MII_BUS_ID_SIZE];
void *priv;
- int (*read)(struct mii_bus *bus, int phy_id, int regnum);
- int (*write)(struct mii_bus *bus, int phy_id, int regnum, u16 val);
+ int (*read)(struct mii_bus *bus, int port_addr, int dev_addr,
+ int regnum);
+ int (*write)(struct mii_bus *bus, int port_addr, int dev_addr,
+ int regnum, u16 val);
int (*reset)(struct mii_bus *bus);
/*
@@ -132,8 +136,9 @@ int mdiobus_register(struct mii_bus *bus);
void mdiobus_unregister(struct mii_bus *bus);
void mdiobus_free(struct mii_bus *bus);
struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
-int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
-int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
+int mdiobus_read(struct mii_bus *bus, int addr, int devad, u16 regnum);
+int mdiobus_write(struct mii_bus *bus, int addr, int devad,
+ u16 regnum, u16 val);
#define PHY_INTERRUPT_DISABLED 0x0
@@ -303,6 +308,7 @@ struct phy_device {
/* See mii.h for more info */
u32 supported;
u32 advertising;
+ u32 mmds;
int autoneg;
@@ -429,7 +435,22 @@ struct phy_fixup {
*/
static inline int phy_read(struct phy_device *phydev, u32 regnum)
{
- return mdiobus_read(phydev->bus, phydev->addr, regnum);
+ return mdiobus_read(phydev->bus, phydev->addr, MDIO_DEVAD_NONE, regnum);
+}
+
+/**
+ * phy45_read - Convenience function for reading a given port/dev/reg address
+ * @phydev: The phy_device struct
+ * @devad: The device address to read
+ * @regnum: The register number to read
+ *
+ * NOTE: MUST NOT be called from interrupt context,
+ * because the bus read/write functions may wait for an interrupt
+ * to conclude the operation.
+ */
+static inline int phy45_read(struct phy_device *phydev, int devad, u16 regnum)
+{
+ return mdiobus_read(phydev->bus, phydev->addr, devad, regnum);
}
/**
@@ -444,10 +465,28 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum)
*/
static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val)
{
- return mdiobus_write(phydev->bus, phydev->addr, regnum, val);
+ return mdiobus_write(phydev->bus, phydev->addr, MDIO_DEVAD_NONE, regnum,
+ val);
+}
+
+/**
+ * phy45_write - Convenience function for writing a given port/dev/reg
+ * @phydev: the phy_device struct
+ * @devad: the device addr
+ * @regnum: register number to write
+ * @val: value to write to @regnum
+ *
+ * NOTE: MUST NOT be called from interrupt context,
+ * because the bus read/write functions may wait for an interrupt
+ * to conclude the operation.
+ */
+static inline int phy45_write(struct phy_device *phydev, u16 regnum,
+ int devad, u16 val)
+{
+ return mdiobus_write(phydev->bus, phydev->addr, devad, regnum, val);
}
-int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id);
+int get_phy_id(struct mii_bus *bus, int addr, int devad, u32 *phy_id);
struct phy_device* get_phy_device(struct mii_bus *bus, int addr);
int phy_device_register(struct phy_device *phy);
int phy_clear_interrupt(struct phy_device *phydev);
--
1.6.5.2.g6ff9a
^ permalink raw reply related
* [PATCH v2 0/2] phylib: Add support for MDIO clause 45
From: Andy Fleming @ 2010-05-21 18:31 UTC (permalink / raw)
To: davem; +Cc: netdev
MDIO Clause 45 adds a new argument for accessing PHY registers, so
that you need the PHY address, the "device" address, and the register
address (which can now be up to 65,535). It's best if, moving forward
we add this new device address argument to the MDIO read/write functions,
which means all of the current bus drivers need to be modified.
I opted not to modify the phy read/write functions mostly because all of the
existing code which calls those functions is correct as-is, and any code which
accesses the new 10G PHYs must do so in a fashion quite distinct from that
of accessing older PHYs (the registers are layed out differently, and the
initialization sequences are also quite different).
However, the MDIO buses are technically allowed to use both access mechanisms
on the same bus, so there's an advantage to adding support to all of the
current implementations.
Changes in v2:
Instead of using device address "0" to indicate a Clause 22 transaction, we
use Ben's suggestion of using MDIO_DEVAD_NONE. Also, modify the PHY
identification code to allow Clauses 22 and 45 to coexist on the same bus.
Andy Fleming (2):
phylib: Convert MDIO and PHY Lib drivers to support 10G
phylib: Convert MDIO bitbang to new MDIO 45 format
Documentation/networking/phy.txt | 13 +-
arch/powerpc/platforms/pasemi/gpio_mdio.c | 6 +-
drivers/net/arm/ixp4xx_eth.c | 7 +-
drivers/net/au1000_eth.c | 7 +-
drivers/net/bcm63xx_enet.c | 4 +-
drivers/net/bfin_mac.c | 7 +-
drivers/net/cpmac.c | 4 +-
drivers/net/davinci_emac.c | 5 +-
drivers/net/dnet.c | 7 +-
drivers/net/ethoc.c | 5 +-
drivers/net/fec.c | 7 +-
drivers/net/fec_mpc52xx_phy.c | 7 +-
drivers/net/fs_enet/mii-fec.c | 6 +-
drivers/net/fsl_pq_mdio.c | 13 +-
drivers/net/fsl_pq_mdio.h | 11 +-
drivers/net/greth.c | 5 +-
drivers/net/ll_temac_mdio.c | 5 +-
drivers/net/macb.c | 7 +-
drivers/net/mv643xx_eth.c | 5 +-
drivers/net/phy/fixed.c | 5 +-
drivers/net/phy/icplus.c | 15 ++-
drivers/net/phy/mdio-bitbang.c | 34 +++---
drivers/net/phy/mdio-octeon.c | 5 +-
drivers/net/phy/mdio_bus.c | 8 +-
drivers/net/phy/phy_device.c | 170 ++++++++++++++++++++++++++---
drivers/net/s6gmac.c | 5 +-
drivers/net/sb1250-mac.c | 14 ++-
drivers/net/smsc911x.c | 19 ++--
drivers/net/smsc9420.c | 9 +-
drivers/net/stmmac/stmmac_mdio.c | 9 +-
drivers/net/tc35815.c | 5 +-
drivers/net/tg3.c | 5 +-
drivers/net/xilinx_emaclite.c | 9 +-
include/linux/phy.h | 57 ++++++++--
34 files changed, 358 insertions(+), 142 deletions(-)
^ 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