* [net-next-2.6 PATCH] net: convert multiple drivers to use netdev_for_each_mc_addr, part7
From: Jiri Pirko @ 2010-03-01 15:09 UTC (permalink / raw)
To: netdev; +Cc: davem
In mlx4, using char * to store mc address in private structure instead.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
---
drivers/media/dvb/dvb-core/dvb_net.c | 6 +---
drivers/net/mlx4/en_netdev.c | 49 ++++++++++++++--------------------
drivers/net/mlx4/mlx4_en.h | 3 +-
drivers/s390/net/qeth_l2_main.c | 2 +-
net/bluetooth/bnep/netdev.c | 10 +++---
5 files changed, 29 insertions(+), 41 deletions(-)
diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c
index 441c064..dba1c84 100644
--- a/drivers/media/dvb/dvb-core/dvb_net.c
+++ b/drivers/media/dvb/dvb-core/dvb_net.c
@@ -1140,7 +1140,6 @@ static void wq_set_multicast_list (struct work_struct *work)
dprintk("%s: allmulti mode\n", dev->name);
priv->rx_mode = RX_MODE_ALL_MULTI;
} else if (!netdev_mc_empty(dev)) {
- int mci;
struct dev_mc_list *mc;
dprintk("%s: set_mc_list, %d entries\n",
@@ -1149,11 +1148,8 @@ static void wq_set_multicast_list (struct work_struct *work)
priv->rx_mode = RX_MODE_MULTI;
priv->multi_num = 0;
- for (mci = 0, mc=dev->mc_list;
- mci < netdev_mc_count(dev);
- mc = mc->next, mci++) {
+ netdev_for_each_mc_addr(mc, dev)
dvb_set_mc_filter(dev, mc);
- }
}
netif_addr_unlock_bh(dev);
diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c
index c48b0f4..7cd0933 100644
--- a/drivers/net/mlx4/en_netdev.c
+++ b/drivers/net/mlx4/en_netdev.c
@@ -160,39 +160,29 @@ static void mlx4_en_do_set_mac(struct work_struct *work)
static void mlx4_en_clear_list(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- struct dev_mc_list *plist = priv->mc_list;
- struct dev_mc_list *next;
- while (plist) {
- next = plist->next;
- kfree(plist);
- plist = next;
- }
- priv->mc_list = NULL;
+ kfree(priv->mc_addrs);
+ priv->mc_addrs_cnt = 0;
}
static void mlx4_en_cache_mclist(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct dev_mc_list *mclist;
- struct dev_mc_list *tmp;
- struct dev_mc_list *plist = NULL;
-
- for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
- tmp = kmalloc(sizeof(struct dev_mc_list), GFP_ATOMIC);
- if (!tmp) {
- en_err(priv, "failed to allocate multicast list\n");
- mlx4_en_clear_list(dev);
- return;
- }
- memcpy(tmp, mclist, sizeof(struct dev_mc_list));
- tmp->next = NULL;
- if (plist)
- plist->next = tmp;
- else
- priv->mc_list = tmp;
- plist = tmp;
+ char *mc_addrs;
+ int mc_addrs_cnt = netdev_mc_count(dev);
+ int i;
+
+ mc_addrs = kmalloc(mc_addrs_cnt * ETH_ALEN, GFP_ATOMIC);
+ if (!mc_addrs) {
+ en_err(priv, "failed to allocate multicast list\n");
+ return;
}
+ i = 0;
+ netdev_for_each_mc_addr(mclist, dev)
+ memcpy(mc_addrs + i++ * ETH_ALEN, mclist->dmi_addr, ETH_ALEN);
+ priv->mc_addrs = mc_addrs;
+ priv->mc_addrs_cnt = mc_addrs_cnt;
}
@@ -212,7 +202,6 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
mcast_task);
struct mlx4_en_dev *mdev = priv->mdev;
struct net_device *dev = priv->dev;
- struct dev_mc_list *mclist;
u64 mcast_addr = 0;
int err;
@@ -288,6 +277,8 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
if (err)
en_err(priv, "Failed disabling multicast filter\n");
} else {
+ int i;
+
err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
0, MLX4_MCAST_DISABLE);
if (err)
@@ -302,8 +293,9 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
netif_tx_lock_bh(dev);
mlx4_en_cache_mclist(dev);
netif_tx_unlock_bh(dev);
- for (mclist = priv->mc_list; mclist; mclist = mclist->next) {
- mcast_addr = mlx4_en_mac_to_u64(mclist->dmi_addr);
+ for (i = 0; i < priv->mc_addrs_cnt; i++) {
+ mcast_addr =
+ mlx4_en_mac_to_u64(priv->mc_addrs + i * ETH_ALEN);
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
mcast_addr, 0, MLX4_MCAST_CONFIG);
}
@@ -984,7 +976,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->flags = prof->flags;
priv->tx_ring_num = prof->tx_ring_num;
priv->rx_ring_num = prof->rx_ring_num;
- priv->mc_list = NULL;
priv->mac_index = -1;
priv->msg_enable = MLX4_EN_MSG_LEVEL;
spin_lock_init(&priv->stats_lock);
diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h
index 82c3ebc..b55e46c 100644
--- a/drivers/net/mlx4/mlx4_en.h
+++ b/drivers/net/mlx4/mlx4_en.h
@@ -492,7 +492,8 @@ struct mlx4_en_priv {
struct mlx4_en_perf_stats pstats;
struct mlx4_en_pkt_stats pkstats;
struct mlx4_en_port_stats port_stats;
- struct dev_mc_list *mc_list;
+ char *mc_addrs;
+ int mc_addrs_cnt;
struct mlx4_en_stat_out_mbox hw_stats;
};
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 51fde6f..d5bef49 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -619,7 +619,7 @@ static void qeth_l2_set_multicast_list(struct net_device *dev)
return;
qeth_l2_del_all_mc(card);
spin_lock_bh(&card->mclock);
- for (dm = dev->mc_list; dm; dm = dm->next)
+ netdev_for_each_mc_addr(dm, dev)
qeth_l2_add_mc(card, dm->da_addr, 0);
netdev_for_each_uc_addr(ha, dev)
diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c
index b6234b7..326ab45 100644
--- a/net/bluetooth/bnep/netdev.c
+++ b/net/bluetooth/bnep/netdev.c
@@ -87,7 +87,7 @@ static void bnep_net_set_mc_list(struct net_device *dev)
memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN);
r->len = htons(ETH_ALEN * 2);
} else {
- struct dev_mc_list *dmi = dev->mc_list;
+ struct dev_mc_list *dmi;
int i, len = skb->len;
if (dev->flags & IFF_BROADCAST) {
@@ -97,12 +97,12 @@ static void bnep_net_set_mc_list(struct net_device *dev)
/* FIXME: We should group addresses here. */
- for (i = 0;
- i < netdev_mc_count(dev) && i < BNEP_MAX_MULTICAST_FILTERS;
- i++) {
+ i = 0;
+ netdev_for_each_mc_addr(dmi, dev) {
+ if (i == BNEP_MAX_MULTICAST_FILTERS)
+ break;
memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN);
memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN);
- dmi = dmi->next;
}
r->len = htons(skb->len - len);
}
--
1.6.6
^ permalink raw reply related
* Re: [RFC][PATCH] af_unix: Add peer inode to /proc/net/unix
From: Kenan Kalajdzic @ 2010-03-01 15:09 UTC (permalink / raw)
To: Changli Gao; +Cc: davem, netdev
In-Reply-To: <412e6f7f1002282305i1d201d76h4085220f71fc76d0@mail.gmail.com>
On Mon, Mar 01, 2010 at 03:05:50PM +0800, Changli Gao wrote:
> If there are two read requests, the system maybe locked up. please use
> unix_state_double_lock()/unix_state_double_unlock(), instead. And the
Thanks for pointing this out. The corrected patch is provided at the end.
> file isn't consistent with the old one. You'd better use a column
> title "Peer" instead of "peer=".
As far as the column name is concerned, I avoided adding a new column, since
this would break userspace programs. Instead, I reused empty space provided
within the 'Path' column to add peer inode number for unbound sockets. This
makes it easy to match client and server sockets as well as unnamed socket
pairs created with socketpair(2).
Here is an example of using the peer inode information from /proc/net/unix
to find all local X-clients:
(1) Find all X-server sockets:
# strings /proc/net/unix | grep X11
e51ec8c0: 00000002 00000000 00010000 0001 01 12318 /tmp/.X11-unix/X0
d2ae98c0: 00000003 00000000 00000000 0001 03 16077 /tmp/.X11-unix/X0
d2b38e00: 00000003 00000000 00000000 0001 03 15858 /tmp/.X11-unix/X0
d2a3bc40: 00000003 00000000 00000000 0001 03 13828 /tmp/.X11-unix/X0
d2a3b1c0: 00000003 00000000 00000000 0001 03 13816 /tmp/.X11-unix/X0
d2909380: 00000003 00000000 00000000 0001 03 13802 /tmp/.X11-unix/X0
d299da80: 00000003 00000000 00000000 0001 03 13728 /tmp/.X11-unix/X0
d299d540: 00000003 00000000 00000000 0001 03 13722 /tmp/.X11-unix/X0
d293f380: 00000003 00000000 00000000 0001 03 13715 /tmp/.X11-unix/X0
d2957700: 00000003 00000000 00000000 0001 03 13644 /tmp/.X11-unix/X0
d291fa80: 00000003 00000000 00000000 0001 03 13585 /tmp/.X11-unix/X0
d290de00: 00000003 00000000 00000000 0001 03 13573 /tmp/.X11-unix/X0
d9fea700: 00000003 00000000 00000000 0001 03 13550 /tmp/.X11-unix/X0
d9fea000: 00000003 00000000 00000000 0001 03 13531 /tmp/.X11-unix/X0
d28b5e00: 00000003 00000000 00000000 0001 03 13465 /tmp/.X11-unix/X0
e541e540: 00000003 00000000 00000000 0001 03 13277 /tmp/.X11-unix/X0
d2898e00: 00000003 00000000 00000000 0001 03 13269 /tmp/.X11-unix/X0
e42ee000: 00000003 00000000 00000000 0001 03 12376 /tmp/.X11-unix/X0
(2) Using inode number of each of the listed X-server sockets, find the
corresponding peer socket. Here we make use of the fact that the peer
inode number is recorded within the 'Path' column of client sockets:
# strings /proc/net/unix | egrep 'peer=(12318|16077|15858|13828|13816|13802'\
> '|13728|13722|13715|13644|13585|13573|13550|13531|13465|13277|13269|12376)$'
d2ae9700: 00000003 00000000 00000000 0001 03 16076 peer=16077
d2b38c40: 00000003 00000000 00000000 0001 03 15857 peer=15858
d2a3ba80: 00000003 00000000 00000000 0001 03 13827 peer=13828
d2a3b000: 00000003 00000000 00000000 0001 03 13815 peer=13816
d29091c0: 00000003 00000000 00000000 0001 03 13801 peer=13802
d299d8c0: 00000003 00000000 00000000 0001 03 13727 peer=13728
d299d380: 00000003 00000000 00000000 0001 03 13721 peer=13722
d293fc40: 00000003 00000000 00000000 0001 03 13714 peer=13715
d29578c0: 00000003 00000000 00000000 0001 03 13643 peer=13644
d291f8c0: 00000003 00000000 00000000 0001 03 13584 peer=13585
d290dc40: 00000003 00000000 00000000 0001 03 13572 peer=13573
d9fea540: 00000003 00000000 00000000 0001 03 13549 peer=13550
d28a98c0: 00000003 00000000 00000000 0001 03 13530 peer=13531
d9fe5e00: 00000003 00000000 00000000 0001 03 13464 peer=13465
e541e700: 00000003 00000000 00000000 0001 03 13276 peer=13277
d28988c0: 00000003 00000000 00000000 0001 03 13268 peer=13269
e51ece00: 00000003 00000000 00000000 0001 03 12320 peer=12376
(3) Using the peer inode numbers, find the corresponding process(es)
through /proc/<PID>/fd/*:
# ls -l /proc/*/fd/* 2>/dev/null | egrep 'socket:.(16076|'\
> '15857|13827|13815|13801|13727|13721|13714|13643|13584|'\
> '13572|13549|13530|13464|13276|13268|12320)'
lr-x------ 1 root root 64 Mar 1 15:07 /proc/4101/fd/3 -> socket:[12320]
lrwx------ 1 root root 64 Mar 1 15:20 /proc/4243/fd/3 -> socket:[13276]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4311/fd/4 -> socket:[13268]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4323/fd/3 -> socket:[13464]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4338/fd/12 -> socket:[13530]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4342/fd/3 -> socket:[13549]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4344/fd/3 -> socket:[13572]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4351/fd/3 -> socket:[13584]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4353/fd/3 -> socket:[13643]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4371/fd/8 -> socket:[13721]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4374/fd/3 -> socket:[13727]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4387/fd/4 -> socket:[13827]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4389/fd/3 -> socket:[13815]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4393/fd/3 -> socket:[13801]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4401/fd/3 -> socket:[13714]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4477/fd/3 -> socket:[15857]
lrwx------ 1 root root 64 Mar 1 15:24 /proc/4488/fd/3 -> socket:[16076]
(4) Finally, use the PIDs obtained in previous step to get a readable
list of X-clients:
# ps -eo pid,args | awk '$1 ~ "^(4101|4243|4311|4323|4338|4342|'\
> '4344|4351|4353|4371|4374|4387|4389|4393|4401|4477|4488)$"'
4101 /usr/sbin/gdm-binary -nodaemon
4243 /usr/bin/gnome-session
4311 /usr/bin/dbus-launch --exit-with-session /etc/X11/xinit/Xclients
4323 /usr/libexec/gnome-settings-daemon
4338 metacity --sm-client-id=default1
4342 gnome-panel --sm-client-id default2
4344 nautilus --no-default-window --sm-client-id default3
4351 gnome-volume-manager --sm-client-id default5
4353 eggcups --sm-client-id default4
4371 ./escd --key_Inserted="/usr/bin/esc" --on_Signal="/usr/bin/esc"
4374 bt-applet --sm-disable
4387 /usr/bin/python -tt /usr/bin/puplet
4389 nm-applet --sm-disable
4393 pam-panel-icon --sm-client-id default0
4401 gnome-power-manager
4477 gnome-screensaver
4488 gnome-terminal
Signed-off-by: Kenan Kalajdzic <kenan@unix.ba>
---
net/unix/af_unix.c | 13 ++++++++++---
1 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index f255119..cee957a 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2157,9 +2157,14 @@ static int unix_seq_show(struct seq_file *seq, void *v)
seq_puts(seq, "Num RefCount Protocol Flags Type St "
"Inode Path\n");
else {
- struct sock *s = v;
+ struct sock *s = v, *peer;
struct unix_sock *u = unix_sk(s);
+
unix_state_lock(s);
+ peer = unix_peer(s);
+ unix_state_unlock(s);
+
+ unix_state_double_lock(s, peer);
seq_printf(seq, "%p: %08X %08X %08X %04X %02X %5lu",
s,
@@ -2186,8 +2191,10 @@ static int unix_seq_show(struct seq_file *seq, void *v)
}
for ( ; i < len; i++)
seq_putc(seq, u->addr->name->sun_path[i]);
- }
- unix_state_unlock(s);
+ } else if (peer)
+ seq_printf(seq, " peer=%lu", sock_i_ino(peer));
+
+ unix_state_double_unlock(s, peer);
seq_putc(seq, '\n');
}
--
1.6.4
^ permalink raw reply related
* [ANNOUNCE]: Release of iptables-1.4.7
From: Patrick McHardy @ 2010-03-01 15:20 UTC (permalink / raw)
To: Netfilter Development Mailinglist, Linux Netdev List,
netfilter-announce
[-- Attachment #1: Type: text/plain, Size: 519 bytes --]
The netfilter coreteam presents:
iptables version 1.4.7
the iptables release for the 2.6.33 kernel. Changes include:
- libipq is built as a shared library
- removal of some restrictions on interface names
- documentation updates
- code cleanups
See the changelog for more details.
Version 1.4.7 can be obtained from:
http://www.netfilter.org/projects/iptables/downloads.html
ftp://ftp.netfilter.org/pub/iptables/
git://git.netfilter.org/iptables.git
On behalf of the Netfilter Core Team.
Happy firewalling!
[-- Attachment #2: changes-iptables-1.4.7.txt --]
[-- Type: text/plain, Size: 552 bytes --]
Dmitry V. Levin (1):
libip4tc: Add static qualifier to dump_entry()
Jan Engelhardt (8):
libipq: build as shared library
recent: reorder cases in code (cosmetic cleanup)
doc: fix recent manpage to reflect actual supported syntax
doc: fix limit manpage to reflect actual supported syntax
doc: mention requirement of additional packages for ipset
policy: fix error message showing wrong option
includes: header updates
Lift restrictions on interface names
Patrick McHardy (1):
iptables 1.4.7
^ permalink raw reply
* Re: net: rtnetlink: support specifying device flags on device creation
From: Patrick McHardy @ 2010-03-01 15:24 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20100227.025128.186425822.davem@davemloft.net>
David Miller wrote:
> From: Patrick McHardy <kaber@trash.net>
> Date: Fri, 26 Feb 2010 17:34:49 +0100 (MET)
>
>> The following patches add support to specify the device flags (like UP) when
>> creating a new device through rtnl_link. This requires to surpress netlink
>> notifications until the device is fully configured in order to not confuse
>> userspace when changing the flags fails and registration has to be undone.
>> Once the device is configured, a single NEWLINK message with the full state
>> is sent.
>>
>> The individual patch changelogs describe the necessary changes in more detail.
>
> All applied, but two things:
>
> 1) This patch set was harder to review because there were no
> default initializations of the new enumeration you added
> to struct netdev.
>
> I know RTNL_LINK_INITIALIZED is probably zero by C enumeration
> rules, and the zeroing out of new netdev objects gives us this,
> but I only figured that out after some time.
>
> It deserved at least a commit message mention in patch #2.
Agreed. The reason to use the value 0 for RTNL_LINK_INITIALIZED
was that it avoids touching drivers that can register netdevices
through non rtnl_link paths, like bonding, ifb or dummy.
> 2) I would really appreciate you forming your patch postings
> properly. I have to edit them every single time
>
> You put the whole output of "git show" or "git format-patch" into
> your email body. That doesn't work, we don't want all of those
> commit ID etc. lines in there. It also causes every line of your
> commit messages to be indented by 4 spaces.
>
> Your email body should just contain the unindented commit message
> and the signoffs, then the patch itself.
>
> Your Subject lines are also not setup properly. Because the
> "net X/N:" thing isn't in [] brackets, it ends up in the
> commit message header lines when I feed your emails to
> "git am".
>
> All of this could be avoided if you used git send-email but
> I realize that a lot of people dislike that for one reason
> or another (myself included), but if you're going to compose
> the emails by hand you ought to make it look the same (syntax
> wise) as what git send-email would have emitted.
I'll either switch to git-send-email or make sure my script
works properly with git-am.
^ permalink raw reply
* call ((+2348056281072)) for your western union promo
From: WESTERNUNION PAY CENTER @ 2010-03-01 15:26 UTC (permalink / raw)
You have been awarded with the sum of $50,000 USD by our office, as one of our
customers who use Western Union in their daily business transaction.Please
provide Mr.Dominic Johnson with the following details listed below so that
your fund will be remited to you through Western Union.
1. Name:______
2. Address________
3. Country:_______
4. Phone Number____
5. Occupation:________
6. Sex:_________________
7. Age___________________
Mr.Dominic Johnson
Tel;+2348056281072
E-mail: w.unionclaim1@w.cn
^ permalink raw reply
* Re: [RFC PATCH]xfrm: fix perpetual bundles
From: Steffen Klassert @ 2010-03-01 15:33 UTC (permalink / raw)
To: jamal; +Cc: davem, kaber, herbert, yoshfuji, nakam, eric.dumazet, netdev
In-Reply-To: <1267366035.24915.24.camel@bigi>
Hi Jamal.
On Sun, Feb 28, 2010 at 09:07:15AM -0500, jamal wrote:
> Steffen,
>
> Did you try the simple patch i posted? After contemplating
> in the background i think it is the right thing to do.
> Ive also fixed IPV6 side the same way.
>
Yes, I did. Your patch works fine. As your solution is less
invasive we probaply should take your patches if nobody else
has an opinion on this.
Steffen
^ permalink raw reply
* Re: sparse checking prevented by "net: fix kmemcheck annotations"
From: Stefan Richter @ 2010-03-01 16:18 UTC (permalink / raw)
To: Eric Dumazet; +Cc: linux-kernel, David S. Miller, netdev
In-Reply-To: <1267448966.3039.22.camel@edumazet-laptop>
Eric Dumazet wrote:
> [PATCH] net: fix protocol sk_buff field
>
> Commit e992cd9b72a18 (kmemcheck: make bitfield annotations truly no-ops
> when disabled) allows us to revert a workaround we did in the past to
> not add holes in sk_buff structure.
>
> This patch partially reverts commit 14d18a81b5171
> (net: fix kmemcheck annotations) so that sparse doesnt complain:
>
> include/linux/skbuff.h:357:41: error: invalid bitfield specifier for
> type restricted __be16.
Great, very appreciated.
--
Stefan Richter
-=====-==-=- --== ----=
http://arcgraph.de/sr/
^ permalink raw reply
* Was: Re: [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking, Now: SWIOTLB dynamic allocation
From: Konrad Rzeszutek Wilk @ 2010-03-01 16:34 UTC (permalink / raw)
To: David Miller
Cc: fujita.tomonori, hancockrwd, bzolnier, linux-kernel, netdev,
linux-usb
In-Reply-To: <20100228.001628.48507956.davem@davemloft.net>
On Sun, Feb 28, 2010 at 12:16:28AM -0800, David Miller wrote:
> From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
> Date: Sun, 28 Feb 2010 03:38:19 +0900
>
> > When I proposed such approach (always use swiotlb) before, IIRC,
> > the objections were:
> >
> > - better to make allocation respect dma_mask. (I don't think that this
> > approach is possible since we don't know which device handles data
> > later when we allocate memory).
>
> And such objects might end up being processed by multiple devices with
> different DMA restrictions.
>
> > - swiotlb is not good for small systems since it allocates too much
> > memory (we can fix this though).
>
> Indeed.
What would be a good mechanism for this? Enumerating all of the PCI
devices to find out which ones are 32-bit and then allocate some chunk
of memory based on the amount of them? say, 1MB per card?
Or maybe a simpler one - figure out how many pages we have an allocate
based on some sliding rule (say, 8MB for under 512MB, 16MB between 512MB
and 2GB, and 32MB for 2GB to 4GB, and after that the full 64MB?)
^ permalink raw reply
* [RFC] Setting processor affinity for network queues
From: Ben Hutchings @ 2010-03-01 17:21 UTC (permalink / raw)
To: netdev
Cc: Peter P Waskiewicz Jr, Peter Zijlstra, Thomas Gleixner,
Tom Herbert, Stephen Hemminger, sf-linux-drivers
With multiqueue network hardware or Receive/Transmit Packet Steering
(RPS/XPS) we can spread out network processing across multiple
processors. The administrator should be able to control the number of
channels and the processor affinity of each.
By 'channel' I mean a bundle of:
- a wakeup (IRQ or IPI)
- a receive queue whose completions trigger the wakeup
- a transmit queue whose completions trigger the wakeup
- a NAPI instance scheduled by the wakeup, which handles the completions
Numbers of RX and TX queues used on a device do not have to match, but
ideally they should. For generality, you can subsitute 'a receive
and/or a transmit queue' above. At the hardware level the numbers of
queues could be different e.g. in the sfc driver a channel would be
associated with 1 hardware RX queue, 2 hardware TX queues (with and
without checksum offload) and 1 hardware event queue.
Currently we have a userspace interface for setting affinity of IRQs and
a convention for naming each channel's IRQ handler, but no such
interface for memory allocation. For RX buffers this should not be a
problem since they are normally allocated as older buffers are
completed, in the NAPI context. However, the DMA descriptor rings and
driver structures for a channel should also be allocated on the NUMA
node where NAPI processing is done. Currently this allocation takes
place when a net device is created or when it is opened, before an
administrator has any opportunity to configure affinity. Reallocation
will normally require a complete stop to network traffic (at least on
the affected queues) so it should not be done automatically when the
driver detects a change in IRQ affinity. There needs to be an explicit
mechanism for changing it.
Devices using RPS will not generally be able to implement NUMA affinity
for RX buffer allocation, but there will be a similar issue of processor
selection for IPIs and NUMA node affinity for driver structures. The
proposed interface for setting processor affinity should cover this, but
it is completely different from the IRQ affinity mechanism for hardware
multiqueue devices. That seems undesirable.
Therefore I propose that:
1. Channels (or NAPI instances) should be exposed in sysfs.
2. Channels will have processor affinity, exposed read/write in sysfs.
Changing this triggers the networking core and driver to reallocate
associated structures if the processor affinity moved between NUMA
nodes, and triggers the driver to set IRQ affinity.
3. The networking core will set the initial affinity for each channel.
There may be global settings to control this.
4. Drivers should not set IRQ affinity.
5. irqbalanced should not set IRQ affinity for multiqueue network
devices.
(Most of this has been proposed already, but I'm trying to bring it all
together.)
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: [RFC] Setting processor affinity for network queues
From: Tadepalli, Hari K @ 2010-03-01 17:43 UTC (permalink / raw)
To: Ben Hutchings, netdev
In-Reply-To: <1267464102.2092.136.camel@achroite.uk.solarflarecom.com>
>> From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org] On Behalf Of Ben Hutchings
>> Sent: Monday, March 01, 2010 10:22 AM
>> To: netdev
>> Cc: Waskiewicz Jr, Peter P; Peter Zijlstra; Thomas Gleixner; Tom Herbert; Stephen Hemminger; sf-linux-drivers
>> Subject: [RFC] Setting processor affinity for network queues
>>
>> Currently we have a userspace interface for setting affinity of IRQs and
>> a convention for naming each channel's IRQ handler, but no such
>> interface for memory allocation. For RX buffers this should not be a
>> problem since they are normally allocated as older buffers are
>> completed, in the NAPI context. However, the DMA descriptor rings and
>> driver structures for a channel should also be allocated on the NUMA
>> node where NAPI processing is done. Currently this allocation takes
>> place when a net device is created or when it is opened, before an
>> administrator has any opportunity to configure affinity. Reallocation
>> will normally require a complete stop to network traffic (at least on
>> the affected queues) so it should not be done automatically when the
>> driver detects a change in IRQ affinity
y. There needs to be an explicit
>> mechanism for changing it.
I have sought clarifications on this issue 2 weeks ago in the context of IxGbE:
http://marc.info/?l=linux-netdev&m=126638089307398&w=2
>> (i) tx_ring, rx_ring control structures of tx/rx rings:
>> tx_ring->tx_buffer_info = vmalloc_node(size, tx_ring->numa_node);
>>
>> (ii) descriptor rings in the DMA region: tx_ring->dma, rx_ring->dma
>> tx_ring->desc = pci_alloc_consistent(pdev, tx_ring->size, &tx_ring->dma);
>>
>> (iii) packet buffers:
>> struct sk_buff *skb = netdev_alloc_skb(adapter->netdev,bufsz);
The above memory allocation calls (sparing vmalloc_node()) conventionally used in a network driver allow for node awareness only at the physical device (pdev) level, where queues in a device do not have independent node-status. This is a serious setback to the benefits expected of recent developments for high throughput networking: RSS, 10/40GbE, NUMA & many cores on an SBC (single board computer or server). Cross node traffic, even in small proportions, is a retard on performance in the million packets/sec range.
I have hacked into some of the above, by using alloc_pages_node() & setting node_id explicitly when allocating for specific queues. But, look forward to a clean, 'hack-free' solution.
Thanks,
- Hari
__________________________________________
Embeedded Communications Group
Intel/ IAG, Chandler, AZ
^ permalink raw reply
* Re: [PATCH 1/1] bnx2x: Tx barriers and locks
From: Michael Chan @ 2010-03-01 17:59 UTC (permalink / raw)
To: Stanislaw Gruszka
Cc: Vladislav Zolotarov, netdev@vger.kernel.org, davem@davemloft.net,
Eilon Greenstein, Matthew Carlson
In-Reply-To: <20100301133339.GB2440@dhcp-lab-161.englab.brq.redhat.com>
On Mon, 2010-03-01 at 05:33 -0800, Stanislaw Gruszka wrote:
> On Sun, Feb 28, 2010 at 12:12:02PM +0200, Vladislav Zolotarov wrote:
> > --- a/drivers/net/bnx2x_main.c
> > +++ b/drivers/net/bnx2x_main.c
> > @@ -57,8 +57,8 @@
> > #include "bnx2x_init_ops.h"
> > #include "bnx2x_dump.h"
> >
> > -#define DRV_MODULE_VERSION "1.52.1-6"
> > -#define DRV_MODULE_RELDATE "2010/02/16"
> > +#define DRV_MODULE_VERSION "1.52.1-7"
> > +#define DRV_MODULE_RELDATE "2010/02/28"
> > #define BNX2X_BC_VER 0x040200
> >
> > #include <linux/firmware.h>
> > @@ -957,21 +957,34 @@ static int bnx2x_tx_int(struct bnx2x_fastpath *fp)
> > fp->tx_pkt_cons = sw_cons;
> > fp->tx_bd_cons = bd_cons;
> >
> > + /* Need to make the tx_bd_cons update visible to start_xmit()
> > + * before checking for netif_tx_queue_stopped(). Without the
> > + * memory barrier, there is a small possibility that
> > + * start_xmit() will miss it and cause the queue to be stopped
> > + * forever.
> > + */
> > + smp_wmb();
> > +
> > /* TBD need a thresh? */
> > if (unlikely(netif_tx_queue_stopped(txq))) {
> > -
> > - /* Need to make the tx_bd_cons update visible to start_xmit()
> > - * before checking for netif_tx_queue_stopped(). Without the
> > - * memory barrier, there is a small possibility that
> > - * start_xmit() will miss it and cause the queue to be stopped
> > - * forever.
> > + /* Taking tx_lock() is needed to prevent reenabling the queue
> > + * while it's empty. This could have happen if rx_action() gets
> > + * suspended in bnx2x_tx_int() after the condition before
> > + * netif_tx_wake_queue(), while tx_action (bnx2x_start_xmit()):
> > + *
> > + * stops the queue->sees fresh tx_bd_cons->releases the queue->
> > + * sends some packets consuming the whole queue again->
> > + * stops the queue
> > */
> > - smp_mb();
> > +
> > + __netif_tx_lock(txq, smp_processor_id());
> >
> > if ((netif_tx_queue_stopped(txq)) &&
> > (bp->state == BNX2X_STATE_OPEN) &&
> > (bnx2x_tx_avail(fp) >= MAX_SKB_FRAGS + 3))
> > netif_tx_wake_queue(txq);
> > +
> > + __netif_tx_unlock(txq);
> > }
> > return 0;
> > }
>
> There is still difference between what we have in bnx2x and bnx2/tg3
> regarding memory barriers in tx_poll/start_xmit code. Mainly we have
> smp_mb() in bnx2/tg3_tx_avail(), and in bnx2/tg3_tx_int() is smp_mb()
> not smp_wmb(). I do not see that bnx2x is wrong, but would like to know
> why there is a difference, maybe bnx2/tg3 should be changed?
>
The memory barrier in tx_int() is to make the tx index update happen
before the netif_tx_queue_stopped() check. The barrier is to prevent a
situation like this:
CPU0 CPU1
start_xmit()
if (tx_ring_full) {
tx_int()
if (!netif_tx_queue_stopped)
netif_tx_stop_queue()
if (!tx_ring_full)
update_tx_index
netif_tx_wake_queue()
}
The update_tx_index code is before the if statement in program order,
but the CPU and/or compiler can reorder it as shown above. smp_mb() will
prevent that. Will smp_wmb() prevent that as well?
^ permalink raw reply
* Re: [PATCH net-next-2.6] vhost: Restart tx poll when socket send queue is full
From: Shirley Ma @ 2010-02-26 3:09 UTC (permalink / raw)
To: Sridhar Samudrala; +Cc: Michael S. Tsirkin, David Miller, netdev
In-Reply-To: <1266946292.6364.6.camel@w-sridhar.beaverton.ibm.com>
This also fixes tx hung issue between guest and guest communication
through vhost.
Thanks
Shirley
^ permalink raw reply
* Re: [RFC][PATCH] ns: Syscalls for better namespace sharing control.
From: Eric W. Biederman @ 2010-03-01 19:24 UTC (permalink / raw)
To: Daniel Lezcano
Cc: Pavel Emelyanov, hadi, Patrick McHardy, Linux Netdev List,
containers, Netfilter Development Mailinglist, Ben Greear,
Serge Hallyn, Matt Helsley
In-Reply-To: <4B8AE8C1.1030305@free.fr>
Daniel Lezcano <daniel.lezcano@free.fr> writes:
>> Replacing struct pid is guaranteed to do all kinds of nasty things with
>> signal handling and the like, de_thread is nasty enough and you are talking
>> something worse. So if we can change pid namespaces without changing
>> the pid I am for it.
>
> I agree with all the points you and Pavel you talked about but I don't feel
> comfortable to have the current process to switch the pid namespace because of
> the process tree hierarchy (what will be the parent of the process when you
> enter the pid namespace for example). What is the difference with the sys_bindns
> or the sys_hijack, proposed a couple of years ago ?
I was not aiming at the general enter case. There is a very specific case
in networking where we only need a network namespace, not full blown containers
so I was seeing what could be done to handle the easy case.
The big idea is solving the namespace naming issues with bind mounts and file
descriptors. All of the rest is window dressing for that idea.
setns looks like the easy way but what is really needed for the network namespace
is a way to open sockets that are in a specified network namespace.
> I did a suggestion some weeks ago about a new syscall 'cloneat' where the child
> process becomes the child of the targeted process specified in the
> syscall. Maybe it would be interesting to replace the 'setns' by, or add, a
> cloneat' syscall with the file descriptor passed as parameter. The copy_process
> function shall not use the nsproxy of the caller but the one provided in the fd
> argument.
>
> The newly created process becomes the child of the process where we retrieve the
> namespace with nsfd and this one have to 'waitpid' it, (the caller of 'cloneat'
> can not wait it). It's a bit similar with the CLONE_PARENT flag, except the
> creation order is inverted (the father creates for the child).
>
> So when entering the container, we specify the pid 1 of the container which is
> usually a child reaper.
>
> Does it make sense ?
Essentially. I am not hugely interested in solving the general case
if it takes us off into tangents about pid namespace semantics.
I have just realized that while the original use case for having unix
domain sockets able to work across network namespaces was a little
weak, there are much better arguments. Operationally it is a game
changer. In the case where you don't need to support migration it
allows direct access to your X server and greatly simplifies the
design of a server designed to start processes in your container.
Eric
^ permalink raw reply
* [PATCH net-next-2.6] bridge: Fix build error when IGMP_SNOOPING is not enabled
From: Sridhar Samudrala @ 2010-03-01 19:53 UTC (permalink / raw)
To: Herbert Xu, David Miller; +Cc: netdev
Fix the following build error when IGMP_SNOOPING is not enabled.
In file included from net/bridge/br.c:24:
net/bridge/br_private.h: In function 'br_multicast_is_router':
net/bridge/br_private.h:361: error: 'struct net_bridge' has no member named 'multicast_router'
net/bridge/br_private.h:362: error: 'struct net_bridge' has no member named 'multicast_router'
net/bridge/br_private.h:363: error: 'struct net_bridge' has no member named 'multicast_router_timer'
Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 9191198..1cf2cef 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -302,6 +302,13 @@ extern int br_multicast_set_port_router(struct net_bridge_port *p,
unsigned long val);
extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
+
+static inline bool br_multicast_is_router(struct net_bridge *br)
+{
+ return br->multicast_router == 2 ||
+ (br->multicast_router == 1 &&
+ timer_pending(&br->multicast_router_timer));
+}
#else
static inline int br_multicast_rcv(struct net_bridge *br,
struct net_bridge_port *port,
@@ -354,14 +361,11 @@ static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
struct sk_buff *skb2)
{
}
-#endif
-
static inline bool br_multicast_is_router(struct net_bridge *br)
{
- return br->multicast_router == 2 ||
- (br->multicast_router == 1 &&
- timer_pending(&br->multicast_router_timer));
+ return 0;
}
+#endif
/* br_netfilter.c */
#ifdef CONFIG_BRIDGE_NETFILTER
^ permalink raw reply related
* HELLO
From: Rose Anderson @ 2010-03-01 20:23 UTC (permalink / raw)
HELLO
My name is Rose
i interested in you,i will also like to know you the more,and i want you to send an email to my email address so i can give you my picture for you to know whom i am Here is my email address (Rose_8v8@yahoo.com) i believe we can move from here!I am waiting for your mail to my email address above. Rose
(Remember the distance or color an age does not matter but love matters a lot in life
(Rose_8v8@yahoo.com)
^ permalink raw reply
* [PATCH] sis190: fix cable detect via link status poll
From: Jeff Garzik @ 2010-03-01 20:40 UTC (permalink / raw)
To: netdev
Some sis190 devices don't report LinkChange, so do polling for
link status.
Fixes http://bugzilla.kernel.org/show_bug.cgi?id=11926
Signed-off-by: Herton Ronaldo Krzesinski <herton@mandriva.com.br>
---
Alan Cox found this change languishing in bugzilla -- a problem with a
patch verified to fix the problem.
I updated the patch to apply to the most recent net-next kernel, but
have not received confirmation that my updated patch still fixes the
problem. -jgarzik
drivers/net/sis190.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/drivers/net/sis190.c b/drivers/net/sis190.c
index 80af4a4..760d9e8 100644
--- a/drivers/net/sis190.c
+++ b/drivers/net/sis190.c
@@ -285,6 +285,11 @@ struct sis190_private {
struct list_head first_phy;
u32 features;
u32 negotiated_lpa;
+ enum {
+ LNK_OFF,
+ LNK_ON,
+ LNK_AUTONEG,
+ } link_status;
};
struct sis190_phy {
@@ -750,6 +755,7 @@ static irqreturn_t sis190_interrupt(int irq, void *__dev)
if (status & LinkChange) {
netif_info(tp, intr, dev, "link change\n");
+ del_timer(&tp->timer);
schedule_work(&tp->phy_task);
}
@@ -922,12 +928,15 @@ static void sis190_phy_task(struct work_struct *work)
if (val & BMCR_RESET) {
// FIXME: needlessly high ? -- FR 02/07/2005
mod_timer(&tp->timer, jiffies + HZ/10);
- } else if (!(mdio_read_latched(ioaddr, phy_id, MII_BMSR) &
- BMSR_ANEGCOMPLETE)) {
+ goto out_unlock;
+ }
+
+ val = mdio_read_latched(ioaddr, phy_id, MII_BMSR);
+ if (!(val & BMSR_ANEGCOMPLETE) && tp->link_status != LNK_AUTONEG) {
netif_carrier_off(dev);
netif_warn(tp, link, dev, "auto-negotiating...\n");
- mod_timer(&tp->timer, jiffies + SIS190_PHY_TIMEOUT);
- } else {
+ tp->link_status = LNK_AUTONEG;
+ } else if ((val & BMSR_LSTATUS) && tp->link_status != LNK_ON) {
/* Rejoice ! */
struct {
int val;
@@ -1000,7 +1009,10 @@ static void sis190_phy_task(struct work_struct *work)
netif_info(tp, link, dev, "link on %s mode\n", p->msg);
netif_carrier_on(dev);
- }
+ tp->link_status = LNK_ON;
+ } else if (!(val & BMSR_LSTATUS) && tp->link_status != LNK_AUTONEG)
+ tp->link_status = LNK_OFF;
+ mod_timer(&tp->timer, jiffies + SIS190_PHY_TIMEOUT);
out_unlock:
rtnl_unlock();
@@ -1513,6 +1525,7 @@ static struct net_device * __devinit sis190_init_board(struct pci_dev *pdev)
tp->pci_dev = pdev;
tp->mmio_addr = ioaddr;
+ tp->link_status = LNK_OFF;
sis190_irq_mask_and_ack(ioaddr);
^ permalink raw reply related
* Re: [RFC] Setting processor affinity for network queues
From: Tom Herbert @ 2010-03-01 20:46 UTC (permalink / raw)
To: Ben Hutchings
Cc: netdev, Peter P Waskiewicz Jr, Peter Zijlstra, Thomas Gleixner,
Stephen Hemminger, sf-linux-drivers
In-Reply-To: <1267464102.2092.136.camel@achroite.uk.solarflarecom.com>
On Mon, Mar 1, 2010 at 9:21 AM, Ben Hutchings <bhutchings@solarflare.com> wrote:
> With multiqueue network hardware or Receive/Transmit Packet Steering
> (RPS/XPS) we can spread out network processing across multiple
> processors. The administrator should be able to control the number of
> channels and the processor affinity of each.
>
> By 'channel' I mean a bundle of:
> - a wakeup (IRQ or IPI)
> - a receive queue whose completions trigger the wakeup
> - a transmit queue whose completions trigger the wakeup
> - a NAPI instance scheduled by the wakeup, which handles the completions
>
Yes. Also in the receive side it is really cumbersome to do per NAPI
RPS settings without the receive napi instance not be exposed in
netif_rx. Maybe a reference to NAPI structure can be added in skb?
This could clean up RPS a lot.
Tom
> Numbers of RX and TX queues used on a device do not have to match, but
> ideally they should. For generality, you can subsitute 'a receive
> and/or a transmit queue' above. At the hardware level the numbers of
> queues could be different e.g. in the sfc driver a channel would be
> associated with 1 hardware RX queue, 2 hardware TX queues (with and
> without checksum offload) and 1 hardware event queue.
>
> Currently we have a userspace interface for setting affinity of IRQs and
> a convention for naming each channel's IRQ handler, but no such
> interface for memory allocation. For RX buffers this should not be a
> problem since they are normally allocated as older buffers are
> completed, in the NAPI context. However, the DMA descriptor rings and
> driver structures for a channel should also be allocated on the NUMA
> node where NAPI processing is done. Currently this allocation takes
> place when a net device is created or when it is opened, before an
> administrator has any opportunity to configure affinity. Reallocation
> will normally require a complete stop to network traffic (at least on
> the affected queues) so it should not be done automatically when the
> driver detects a change in IRQ affinity. There needs to be an explicit
> mechanism for changing it.
>
> Devices using RPS will not generally be able to implement NUMA affinity
> for RX buffer allocation, but there will be a similar issue of processor
> selection for IPIs and NUMA node affinity for driver structures. The
> proposed interface for setting processor affinity should cover this, but
> it is completely different from the IRQ affinity mechanism for hardware
> multiqueue devices. That seems undesirable.
>
> Therefore I propose that:
>
> 1. Channels (or NAPI instances) should be exposed in sysfs.
> 2. Channels will have processor affinity, exposed read/write in sysfs.
> Changing this triggers the networking core and driver to reallocate
> associated structures if the processor affinity moved between NUMA
> nodes, and triggers the driver to set IRQ affinity.
> 3. The networking core will set the initial affinity for each channel.
> There may be global settings to control this.
> 4. Drivers should not set IRQ affinity.
> 5. irqbalanced should not set IRQ affinity for multiqueue network
> devices.
>
> (Most of this has been proposed already, but I'm trying to bring it all
> together.)
>
> 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 net-next-2.6] bridge: Fix build error when IGMP_SNOOPING is not enabled
From: Randy Dunlap @ 2010-03-01 20:54 UTC (permalink / raw)
To: Sridhar Samudrala; +Cc: Herbert Xu, David Miller, netdev
In-Reply-To: <1267473184.31728.7.camel@w-sridhar.beaverton.ibm.com>
On 03/01/10 11:53, Sridhar Samudrala wrote:
> Fix the following build error when IGMP_SNOOPING is not enabled.
> In file included from net/bridge/br.c:24:
> net/bridge/br_private.h: In function 'br_multicast_is_router':
> net/bridge/br_private.h:361: error: 'struct net_bridge' has no member named 'multicast_router'
> net/bridge/br_private.h:362: error: 'struct net_bridge' has no member named 'multicast_router'
> net/bridge/br_private.h:363: error: 'struct net_bridge' has no member named 'multicast_router_timer'
>
> Signed-off-by: Sridhar Samudrala <sri@us.ibm.com>
>
> diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
> index 9191198..1cf2cef 100644
> --- a/net/bridge/br_private.h
> +++ b/net/bridge/br_private.h
> @@ -302,6 +302,13 @@ extern int br_multicast_set_port_router(struct net_bridge_port *p,
> unsigned long val);
> extern int br_multicast_toggle(struct net_bridge *br, unsigned long val);
> extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val);
> +
> +static inline bool br_multicast_is_router(struct net_bridge *br)
> +{
> + return br->multicast_router == 2 ||
> + (br->multicast_router == 1 &&
> + timer_pending(&br->multicast_router_timer));
> +}
> #else
> static inline int br_multicast_rcv(struct net_bridge *br,
> struct net_bridge_port *port,
> @@ -354,14 +361,11 @@ static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst,
> struct sk_buff *skb2)
> {
> }
> -#endif
> -
> static inline bool br_multicast_is_router(struct net_bridge *br)
> {
> - return br->multicast_router == 2 ||
> - (br->multicast_router == 1 &&
> - timer_pending(&br->multicast_router_timer));
> + return 0;
> }
> +#endif
>
> /* br_netfilter.c */
> #ifdef CONFIG_BRIDGE_NETFILTER
>
>
> --
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Thanks.
--
~Randy
^ permalink raw reply
* Re: linux-next: Tree for March 1 (bluetooth/hci_sysfs)
From: Randy Dunlap @ 2010-03-01 21:08 UTC (permalink / raw)
To: Stephen Rothwell
Cc: linux-next, LKML, Marcel Holtmann, linux-bluetooth, Netdev
In-Reply-To: <20100301210210.c6f465e6.sfr@canb.auug.org.au>
On 03/01/10 02:02, Stephen Rothwell wrote:
> Hi all,
>
> Changes since 20100226:
>
> We are seeing conflicts migrate from being between 2 trees in linux-next
> to be between a tree and Linus' tree as things start to get merged.
>
>
> The net tree gained a conflict against Linus' tree.
static ssize_t inquiry_cache_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
{
struct hci_dev *hdev = file->private_data;
struct inquiry_cache *cache = &hdev->inq_cache;
struct inquiry_entry *e;
char buf[4096]; // <<<<<<<<<<<<<<<<<<<<<<<<<<< huh? don't do that on stack.
int n = 0;
--
~Randy
^ permalink raw reply
* Re: Was: Re: [RFC PATCH] fix problems with NETIF_F_HIGHDMA in networking, Now: SWIOTLB dynamic allocation
From: Robert Hancock @ 2010-03-01 21:12 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk
Cc: David Miller, fujita.tomonori, bzolnier, linux-kernel, netdev,
linux-usb
In-Reply-To: <20100301163437.GE7881@phenom.dumpdata.com>
On Mon, Mar 1, 2010 at 10:34 AM, Konrad Rzeszutek Wilk
<konrad.wilk@oracle.com> wrote:
> On Sun, Feb 28, 2010 at 12:16:28AM -0800, David Miller wrote:
>> From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
>> Date: Sun, 28 Feb 2010 03:38:19 +0900
>>
>> > When I proposed such approach (always use swiotlb) before, IIRC,
>> > the objections were:
>> >
>> > - better to make allocation respect dma_mask. (I don't think that this
>> > approach is possible since we don't know which device handles data
>> > later when we allocate memory).
>>
>> And such objects might end up being processed by multiple devices with
>> different DMA restrictions.
>>
>> > - swiotlb is not good for small systems since it allocates too much
>> > memory (we can fix this though).
>>
>> Indeed.
>
> What would be a good mechanism for this? Enumerating all of the PCI
> devices to find out which ones are 32-bit and then allocate some chunk
> of memory based on the amount of them? say, 1MB per card?
>
> Or maybe a simpler one - figure out how many pages we have an allocate
> based on some sliding rule (say, 8MB for under 512MB, 16MB between 512MB
> and 2GB, and 32MB for 2GB to 4GB, and after that the full 64MB?)
Why do we need to allocate SWIOTLB if your highest memory address is
under 4GB? You can just disable it in that case, like x86_64 does.
^ permalink raw reply
* [PATCH net-next] drivers/net/e100.c: Use pr_<level> and netif_<level>
From: Joe Perches @ 2010-03-01 21:16 UTC (permalink / raw)
To: Jeff Kirsher
Cc: David Miller, netdev, Jesse Brandeburg, Bruce Allan, Alex Duyck,
PJ Waskiewicz, John Ronciak, Andrew Gallatin, Brice Goglin,
linux-kernel, e1000-devel
In-Reply-To: <9929d2391002231833j65008a1ev1d2297672a39a483@mail.gmail.com>
Convert DPRINTK, commonly used for debugging, to netif_<level>
Remove #define PFX
Use #define pr_fmt
Consistently use no periods for non-sentence logging messages
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/e100.c | 183 ++++++++++++++++++++++++++++------------------------
1 files changed, 98 insertions(+), 85 deletions(-)
diff --git a/drivers/net/e100.c b/drivers/net/e100.c
index a26ccab..c33d12a 100644
--- a/drivers/net/e100.c
+++ b/drivers/net/e100.c
@@ -147,6 +147,8 @@
* - add clean lowlevel I/O emulation for cards with MII-lacking PHYs
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/kernel.h>
@@ -174,7 +176,6 @@
#define DRV_VERSION "3.5.24-k2"DRV_EXT
#define DRV_DESCRIPTION "Intel(R) PRO/100 Network Driver"
#define DRV_COPYRIGHT "Copyright(c) 1999-2006 Intel Corporation"
-#define PFX DRV_NAME ": "
#define E100_WATCHDOG_PERIOD (2 * HZ)
#define E100_NAPI_WEIGHT 16
@@ -200,10 +201,6 @@ module_param(use_io, int, 0);
MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
MODULE_PARM_DESC(eeprom_bad_csum_allow, "Allow bad eeprom checksums");
MODULE_PARM_DESC(use_io, "Force use of i/o access mode");
-#define DPRINTK(nlevel, klevel, fmt, args...) \
- (void)((NETIF_MSG_##nlevel & nic->msg_enable) && \
- printk(KERN_##klevel PFX "%s: %s: " fmt, nic->netdev->name, \
- __func__ , ## args))
#define INTEL_8255X_ETHERNET_DEVICE(device_id, ich) {\
PCI_VENDOR_ID_INTEL, device_id, PCI_ANY_ID, PCI_ANY_ID, \
@@ -689,12 +686,13 @@ static int e100_self_test(struct nic *nic)
/* Check results of self-test */
if (nic->mem->selftest.result != 0) {
- DPRINTK(HW, ERR, "Self-test failed: result=0x%08X\n",
- nic->mem->selftest.result);
+ netif_err(nic, hw, nic->netdev,
+ "Self-test failed: result=0x%08X\n",
+ nic->mem->selftest.result);
return -ETIMEDOUT;
}
if (nic->mem->selftest.signature == 0) {
- DPRINTK(HW, ERR, "Self-test failed: timed out\n");
+ netif_err(nic, hw, nic->netdev, "Self-test failed: timed out\n");
return -ETIMEDOUT;
}
@@ -797,7 +795,7 @@ static int e100_eeprom_load(struct nic *nic)
/* The checksum, stored in the last word, is calculated such that
* the sum of words should be 0xBABA */
if (cpu_to_le16(0xBABA - checksum) != nic->eeprom[nic->eeprom_wc - 1]) {
- DPRINTK(PROBE, ERR, "EEPROM corrupted\n");
+ netif_err(nic, probe, nic->netdev, "EEPROM corrupted\n");
if (!eeprom_bad_csum_allow)
return -EAGAIN;
}
@@ -953,8 +951,7 @@ static u16 mdio_ctrl_hw(struct nic *nic, u32 addr, u32 dir, u32 reg, u16 data)
udelay(20);
}
if (unlikely(!i)) {
- printk("e100.mdio_ctrl(%s) won't go Ready\n",
- nic->netdev->name );
+ netdev_err(nic->netdev, "e100.mdio_ctrl won't go Ready\n");
spin_unlock_irqrestore(&nic->mdio_lock, flags);
return 0; /* No way to indicate timeout error */
}
@@ -966,9 +963,10 @@ static u16 mdio_ctrl_hw(struct nic *nic, u32 addr, u32 dir, u32 reg, u16 data)
break;
}
spin_unlock_irqrestore(&nic->mdio_lock, flags);
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data_in=0x%04X, data_out=0x%04X\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data, data_out);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data_in=0x%04X, data_out=0x%04X\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data, data_out);
return (u16)data_out;
}
@@ -1028,17 +1026,19 @@ static u16 mdio_ctrl_phy_mii_emulated(struct nic *nic,
return ADVERTISE_10HALF |
ADVERTISE_10FULL;
default:
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data);
return 0xFFFF;
}
} else {
switch (reg) {
default:
- DPRINTK(HW, DEBUG,
- "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
- dir == mdi_read ? "READ" : "WRITE", addr, reg, data);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "%s:addr=%d, reg=%d, data=0x%04X: unimplemented emulation!\n",
+ dir == mdi_read ? "READ" : "WRITE",
+ addr, reg, data);
return 0xFFFF;
}
}
@@ -1155,12 +1155,15 @@ static void e100_configure(struct nic *nic, struct cb *cb, struct sk_buff *skb)
}
}
- DPRINTK(HW, DEBUG, "[00-07]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]);
- DPRINTK(HW, DEBUG, "[08-15]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[8], c[9], c[10], c[11], c[12], c[13], c[14], c[15]);
- DPRINTK(HW, DEBUG, "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
- c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[00-07]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[08-15]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[8], c[9], c[10], c[11], c[12], c[13], c[14], c[15]);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n",
+ c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]);
}
/*************************************************************************
@@ -1253,16 +1256,18 @@ static const struct firmware *e100_request_firmware(struct nic *nic)
err = request_firmware(&fw, fw_name, &nic->pdev->dev);
if (err) {
- DPRINTK(PROBE, ERR, "Failed to load firmware \"%s\": %d\n",
- fw_name, err);
+ netif_err(nic, probe, nic->netdev,
+ "Failed to load firmware \"%s\": %d\n",
+ fw_name, err);
return ERR_PTR(err);
}
/* Firmware should be precisely UCODE_SIZE (words) plus three bytes
indicating the offsets for BUNDLESMALL, BUNDLEMAX, INTDELAY */
if (fw->size != UCODE_SIZE * 4 + 3) {
- DPRINTK(PROBE, ERR, "Firmware \"%s\" has wrong size %zu\n",
- fw_name, fw->size);
+ netif_err(nic, probe, nic->netdev,
+ "Firmware \"%s\" has wrong size %zu\n",
+ fw_name, fw->size);
release_firmware(fw);
return ERR_PTR(-EINVAL);
}
@@ -1274,9 +1279,9 @@ static const struct firmware *e100_request_firmware(struct nic *nic)
if (timer >= UCODE_SIZE || bundle >= UCODE_SIZE ||
min_size >= UCODE_SIZE) {
- DPRINTK(PROBE, ERR,
- "\"%s\" has bogus offset values (0x%x,0x%x,0x%x)\n",
- fw_name, timer, bundle, min_size);
+ netif_err(nic, probe, nic->netdev,
+ "\"%s\" has bogus offset values (0x%x,0x%x,0x%x)\n",
+ fw_name, timer, bundle, min_size);
release_firmware(fw);
return ERR_PTR(-EINVAL);
}
@@ -1328,7 +1333,8 @@ static inline int e100_load_ucode_wait(struct nic *nic)
return PTR_ERR(fw);
if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode)))
- DPRINTK(PROBE,ERR, "ucode cmd failed with error %d\n", err);
+ netif_err(nic, probe, nic->netdev,
+ "ucode cmd failed with error %d\n", err);
/* must restart cuc */
nic->cuc_cmd = cuc_start;
@@ -1348,7 +1354,7 @@ static inline int e100_load_ucode_wait(struct nic *nic)
/* if the command failed, or is not OK, notify and return */
if (!counter || !(cb->status & cpu_to_le16(cb_ok))) {
- DPRINTK(PROBE,ERR, "ucode load failed\n");
+ netif_err(nic, probe, nic->netdev, "ucode load failed\n");
err = -EPERM;
}
@@ -1386,8 +1392,8 @@ static int e100_phy_check_without_mii(struct nic *nic)
* media is sensed automatically based on how the link partner
* is configured. This is, in essence, manual configuration.
*/
- DPRINTK(PROBE, INFO,
- "found MII-less i82503 or 80c24 or other PHY\n");
+ netif_info(nic, probe, nic->netdev,
+ "found MII-less i82503 or 80c24 or other PHY\n");
nic->mdio_ctrl = mdio_ctrl_phy_mii_emulated;
nic->mii.phy_id = 0; /* is this ok for an MII-less PHY? */
@@ -1434,18 +1440,20 @@ static int e100_phy_init(struct nic *nic)
return 0; /* simply return and hope for the best */
else {
/* for unknown cases log a fatal error */
- DPRINTK(HW, ERR,
- "Failed to locate any known PHY, aborting.\n");
+ netif_err(nic, hw, nic->netdev,
+ "Failed to locate any known PHY, aborting\n");
return -EAGAIN;
}
} else
- DPRINTK(HW, DEBUG, "phy_addr = %d\n", nic->mii.phy_id);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "phy_addr = %d\n", nic->mii.phy_id);
/* Get phy ID */
id_lo = mdio_read(netdev, nic->mii.phy_id, MII_PHYSID1);
id_hi = mdio_read(netdev, nic->mii.phy_id, MII_PHYSID2);
nic->phy = (u32)id_hi << 16 | (u32)id_lo;
- DPRINTK(HW, DEBUG, "phy ID = 0x%08X\n", nic->phy);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "phy ID = 0x%08X\n", nic->phy);
/* Select the phy and isolate the rest */
for (addr = 0; addr < 32; addr++) {
@@ -1507,7 +1515,7 @@ static int e100_hw_init(struct nic *nic)
e100_hw_reset(nic);
- DPRINTK(HW, ERR, "e100_hw_init\n");
+ netif_err(nic, hw, nic->netdev, "e100_hw_init\n");
if (!in_interrupt() && (err = e100_self_test(nic)))
return err;
@@ -1555,8 +1563,9 @@ static void e100_set_multicast_list(struct net_device *netdev)
{
struct nic *nic = netdev_priv(netdev);
- DPRINTK(HW, DEBUG, "mc_count=%d, flags=0x%04X\n",
- netdev_mc_count(netdev), netdev->flags);
+ netif_printk(nic, hw, KERN_DEBUG, nic->netdev,
+ "mc_count=%d, flags=0x%04X\n",
+ netdev_mc_count(netdev), netdev->flags);
if (netdev->flags & IFF_PROMISC)
nic->flags |= promiscuous;
@@ -1629,7 +1638,8 @@ static void e100_update_stats(struct nic *nic)
if (e100_exec_cmd(nic, cuc_dump_reset, 0))
- DPRINTK(TX_ERR, DEBUG, "exec cuc_dump_reset failed\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "exec cuc_dump_reset failed\n");
}
static void e100_adjust_adaptive_ifs(struct nic *nic, int speed, int duplex)
@@ -1659,20 +1669,19 @@ static void e100_watchdog(unsigned long data)
struct nic *nic = (struct nic *)data;
struct ethtool_cmd cmd;
- DPRINTK(TIMER, DEBUG, "right now = %ld\n", jiffies);
+ netif_printk(nic, timer, KERN_DEBUG, nic->netdev,
+ "right now = %ld\n", jiffies);
/* mii library handles link maintenance tasks */
mii_ethtool_gset(&nic->mii, &cmd);
if (mii_link_ok(&nic->mii) && !netif_carrier_ok(nic->netdev)) {
- printk(KERN_INFO "e100: %s NIC Link is Up %s Mbps %s Duplex\n",
- nic->netdev->name,
- cmd.speed == SPEED_100 ? "100" : "10",
- cmd.duplex == DUPLEX_FULL ? "Full" : "Half");
+ netdev_info(nic->netdev, "NIC Link is Up %u Mbps %s Duplex\n",
+ cmd.speed == SPEED_100 ? 100 : 10,
+ cmd.duplex == DUPLEX_FULL ? "Full" : "Half");
} else if (!mii_link_ok(&nic->mii) && netif_carrier_ok(nic->netdev)) {
- printk(KERN_INFO "e100: %s NIC Link is Down\n",
- nic->netdev->name);
+ netdev_info(nic->netdev, "NIC Link is Down\n");
}
mii_check_link(&nic->mii);
@@ -1732,7 +1741,8 @@ static netdev_tx_t e100_xmit_frame(struct sk_buff *skb,
Issue a NOP command followed by a 1us delay before
issuing the Tx command. */
if (e100_exec_cmd(nic, cuc_nop, 0))
- DPRINTK(TX_ERR, DEBUG, "exec cuc_nop failed\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "exec cuc_nop failed\n");
udelay(1);
}
@@ -1741,12 +1751,14 @@ static netdev_tx_t e100_xmit_frame(struct sk_buff *skb,
switch (err) {
case -ENOSPC:
/* We queued the skb, but now we're out of space. */
- DPRINTK(TX_ERR, DEBUG, "No space for CB\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "No space for CB\n");
netif_stop_queue(netdev);
break;
case -ENOMEM:
/* This is a hard error - log it. */
- DPRINTK(TX_ERR, DEBUG, "Out of Tx resources, returning skb\n");
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "Out of Tx resources, returning skb\n");
netif_stop_queue(netdev);
return NETDEV_TX_BUSY;
}
@@ -1767,9 +1779,10 @@ static int e100_tx_clean(struct nic *nic)
for (cb = nic->cb_to_clean;
cb->status & cpu_to_le16(cb_complete);
cb = nic->cb_to_clean = cb->next) {
- DPRINTK(TX_DONE, DEBUG, "cb[%d]->status = 0x%04X\n",
- (int)(((void*)cb - (void*)nic->cbs)/sizeof(struct cb)),
- cb->status);
+ netif_printk(nic, tx_done, KERN_DEBUG, nic->netdev,
+ "cb[%d]->status = 0x%04X\n",
+ (int)(((void*)cb - (void*)nic->cbs)/sizeof(struct cb)),
+ cb->status);
if (likely(cb->skb != NULL)) {
dev->stats.tx_packets++;
@@ -1912,7 +1925,8 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx,
sizeof(struct rfd), PCI_DMA_BIDIRECTIONAL);
rfd_status = le16_to_cpu(rfd->status);
- DPRINTK(RX_STATUS, DEBUG, "status=0x%04X\n", rfd_status);
+ netif_printk(nic, rx_status, KERN_DEBUG, nic->netdev,
+ "status=0x%04X\n", rfd_status);
/* If data isn't ready, nothing to indicate */
if (unlikely(!(rfd_status & cb_complete))) {
@@ -2123,7 +2137,8 @@ static irqreturn_t e100_intr(int irq, void *dev_id)
struct nic *nic = netdev_priv(netdev);
u8 stat_ack = ioread8(&nic->csr->scb.stat_ack);
- DPRINTK(INTR, DEBUG, "stat_ack = 0x%02X\n", stat_ack);
+ netif_printk(nic, intr, KERN_DEBUG, nic->netdev,
+ "stat_ack = 0x%02X\n", stat_ack);
if (stat_ack == stat_ack_not_ours || /* Not our interrupt */
stat_ack == stat_ack_not_present) /* Hardware is ejected */
@@ -2263,8 +2278,8 @@ static void e100_tx_timeout_task(struct work_struct *work)
struct nic *nic = container_of(work, struct nic, tx_timeout_task);
struct net_device *netdev = nic->netdev;
- DPRINTK(TX_ERR, DEBUG, "scb.status=0x%02X\n",
- ioread8(&nic->csr->scb.status));
+ netif_printk(nic, tx_err, KERN_DEBUG, nic->netdev,
+ "scb.status=0x%02X\n", ioread8(&nic->csr->scb.status));
e100_down(netdev_priv(netdev));
e100_up(netdev_priv(netdev));
}
@@ -2526,8 +2541,8 @@ static int e100_set_ringparam(struct net_device *netdev,
rfds->count = min(rfds->count, rfds->max);
cbs->count = max(ring->tx_pending, cbs->min);
cbs->count = min(cbs->count, cbs->max);
- DPRINTK(DRV, INFO, "Ring Param settings: rx: %d, tx %d\n",
- rfds->count, cbs->count);
+ netif_info(nic, drv, nic->netdev, "Ring Param settings: rx: %d, tx %d\n",
+ rfds->count, cbs->count);
if (netif_running(netdev))
e100_up(nic);
@@ -2704,7 +2719,7 @@ static int e100_open(struct net_device *netdev)
netif_carrier_off(netdev);
if ((err = e100_up(nic)))
- DPRINTK(IFUP, ERR, "Cannot open interface, aborting.\n");
+ netif_err(nic, ifup, nic->netdev, "Cannot open interface, aborting\n");
return err;
}
@@ -2738,7 +2753,7 @@ static int __devinit e100_probe(struct pci_dev *pdev,
if (!(netdev = alloc_etherdev(sizeof(struct nic)))) {
if (((1 << debug) - 1) & NETIF_MSG_PROBE)
- printk(KERN_ERR PFX "Etherdev alloc failed, abort.\n");
+ pr_err("Etherdev alloc failed, aborting\n");
return -ENOMEM;
}
@@ -2756,35 +2771,34 @@ static int __devinit e100_probe(struct pci_dev *pdev,
pci_set_drvdata(pdev, netdev);
if ((err = pci_enable_device(pdev))) {
- DPRINTK(PROBE, ERR, "Cannot enable PCI device, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot enable PCI device, aborting\n");
goto err_out_free_dev;
}
if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
- DPRINTK(PROBE, ERR, "Cannot find proper PCI device "
- "base address, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot find proper PCI device base address, aborting\n");
err = -ENODEV;
goto err_out_disable_pdev;
}
if ((err = pci_request_regions(pdev, DRV_NAME))) {
- DPRINTK(PROBE, ERR, "Cannot obtain PCI resources, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot obtain PCI resources, aborting\n");
goto err_out_disable_pdev;
}
if ((err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
- DPRINTK(PROBE, ERR, "No usable DMA configuration, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "No usable DMA configuration, aborting\n");
goto err_out_free_res;
}
SET_NETDEV_DEV(netdev, &pdev->dev);
if (use_io)
- DPRINTK(PROBE, INFO, "using i/o access mode\n");
+ netif_info(nic, probe, nic->netdev, "using i/o access mode\n");
nic->csr = pci_iomap(pdev, (use_io ? 1 : 0), sizeof(struct csr));
if (!nic->csr) {
- DPRINTK(PROBE, ERR, "Cannot map device registers, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot map device registers, aborting\n");
err = -ENOMEM;
goto err_out_free_res;
}
@@ -2818,7 +2832,7 @@ static int __devinit e100_probe(struct pci_dev *pdev,
INIT_WORK(&nic->tx_timeout_task, e100_tx_timeout_task);
if ((err = e100_alloc(nic))) {
- DPRINTK(PROBE, ERR, "Cannot alloc driver memory, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot alloc driver memory, aborting\n");
goto err_out_iounmap;
}
@@ -2831,13 +2845,11 @@ static int __devinit e100_probe(struct pci_dev *pdev,
memcpy(netdev->perm_addr, nic->eeprom, ETH_ALEN);
if (!is_valid_ether_addr(netdev->perm_addr)) {
if (!eeprom_bad_csum_allow) {
- DPRINTK(PROBE, ERR, "Invalid MAC address from "
- "EEPROM, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Invalid MAC address from EEPROM, aborting\n");
err = -EAGAIN;
goto err_out_free;
} else {
- DPRINTK(PROBE, ERR, "Invalid MAC address from EEPROM, "
- "you MUST configure one.\n");
+ netif_err(nic, probe, nic->netdev, "Invalid MAC address from EEPROM, you MUST configure one.\n");
}
}
@@ -2853,7 +2865,7 @@ static int __devinit e100_probe(struct pci_dev *pdev,
strcpy(netdev->name, "eth%d");
if ((err = register_netdev(netdev))) {
- DPRINTK(PROBE, ERR, "Cannot register net device, aborting.\n");
+ netif_err(nic, probe, nic->netdev, "Cannot register net device, aborting\n");
goto err_out_free;
}
nic->cbs_pool = pci_pool_create(netdev->name,
@@ -2861,9 +2873,10 @@ static int __devinit e100_probe(struct pci_dev *pdev,
nic->params.cbs.count * sizeof(struct cb),
sizeof(u32),
0);
- DPRINTK(PROBE, INFO, "addr 0x%llx, irq %d, MAC addr %pM\n",
- (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0),
- pdev->irq, netdev->dev_addr);
+ netif_info(nic, probe, nic->netdev,
+ "addr 0x%llx, irq %d, MAC addr %pM\n",
+ (unsigned long long)pci_resource_start(pdev, use_io ? 1 : 0),
+ pdev->irq, netdev->dev_addr);
return 0;
@@ -3021,7 +3034,7 @@ static pci_ers_result_t e100_io_slot_reset(struct pci_dev *pdev)
struct nic *nic = netdev_priv(netdev);
if (pci_enable_device(pdev)) {
- printk(KERN_ERR "e100: Cannot re-enable PCI device after reset.\n");
+ pr_err("Cannot re-enable PCI device after reset\n");
return PCI_ERS_RESULT_DISCONNECT;
}
pci_set_master(pdev);
@@ -3080,8 +3093,8 @@ static struct pci_driver e100_driver = {
static int __init e100_init_module(void)
{
if (((1 << debug) - 1) & NETIF_MSG_DRV) {
- printk(KERN_INFO PFX "%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
- printk(KERN_INFO PFX "%s\n", DRV_COPYRIGHT);
+ pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION);
+ pr_info("%s\n", DRV_COPYRIGHT);
}
return pci_register_driver(&e100_driver);
}
^ permalink raw reply related
* Re: [RFC][PATCH] ns: Syscalls for better namespace sharing control.
From: Eric W. Biederman @ 2010-03-01 21:42 UTC (permalink / raw)
To: Daniel Lezcano
Cc: Pavel Emelyanov, hadi, Patrick McHardy, Linux Netdev List,
containers, Netfilter Development Mailinglist, Ben Greear,
Serge Hallyn, Matt Helsley
In-Reply-To: <4B8AE8C1.1030305@free.fr>
Daniel Lezcano <daniel.lezcano@free.fr> writes:
> I agree with all the points you and Pavel you talked about but I don't feel
> comfortable to have the current process to switch the pid namespace because of
> the process tree hierarchy (what will be the parent of the process when you
> enter the pid namespace for example). What is the difference with the sys_bindns
> or the sys_hijack, proposed a couple of years ago ?
I think what has changed is:
- We have mostly completed most of the namespace work.
- We have operational experience with the current namespaces.
- We have people not in the core containers group feeling the pain
of not having some of these features.
So I think we are at point where we can perhaps talk about these
things and finally solve some of these issues.
Clearly how to enter a container is on your and Pavel's mind as big
concerns. I am aiming a little lower.
I am of two mind about my patches. Right now they are a brilliant
proof of concept that we can name namespaces without needing a
namespace for the names of namespaces, and start to be a practical
solution to the join problem. At the same time, I'm not certain
I like a solution that requires yet more syscalls so I ask myself
is there not yet a simpler way.
Hopefully we can resolve something before the next merge window.
Eric
^ permalink raw reply
* Hospitals - 23,747 Hospital Administrators in over 7,145 Hospitals (full contact info no emails)
From: Everett litigate @ 2010-03-01 21:46 UTC (permalink / raw)
To: caniond, kay.hairclinic, good4seo, resume.cn, misecretservice
For details, samples and counts on our US listings please
email me at my other email address Dominic.Farris@fastlist.Co.CC
Forward email to rembox@fastlist.Co.CC to purge you from our records
^ permalink raw reply
* [RFC] ppp: Bridge Control Protocol
From: Stephen Hemminger @ 2010-03-01 22:59 UTC (permalink / raw)
To: David, "Miller <davem", Paul Mackerras
Cc: linux-ppp, bridge, netdev, dane
This is a port of an old patch to provide BCP support.
BCP allows bridging PPP tunnels, it useful to do bridging between
virtualized environments. Original patch was done by
Dan Eble but was for 2.4.21.
Note: still needs testing. Does anyone have hardware to make
sure this interoperates with other implementations?
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
---
drivers/net/Kconfig | 7
drivers/net/ppp_generic.c | 359 ++++++++++++++++++++++++++++++++++++++++++++--
include/linux/ppp_defs.h | 31 +++
3 files changed, 385 insertions(+), 12 deletions(-)
--- a/include/linux/ppp_defs.h 2009-12-26 13:40:48.000000000 -0800
+++ b/include/linux/ppp_defs.h 2010-03-01 14:50:10.973353622 -0800
@@ -70,15 +70,18 @@
#define PPP_IPX 0x2b /* IPX protocol */
#define PPP_VJC_COMP 0x2d /* VJ compressed TCP */
#define PPP_VJC_UNCOMP 0x2f /* VJ uncompressed TCP */
+#define PPP_BRIDGE 0x31 /* Bridged LAN traffic or BPDU */
#define PPP_MP 0x3d /* Multilink protocol */
#define PPP_IPV6 0x57 /* Internet Protocol Version 6 */
#define PPP_COMPFRAG 0xfb /* fragment compressed below bundle */
#define PPP_COMP 0xfd /* compressed packet */
+#define PPP_BPDU_IEEE 0x0201 /* IEEE 802.1 (D or G) bridge PDU */
#define PPP_MPLS_UC 0x0281 /* Multi Protocol Label Switching - Unicast */
#define PPP_MPLS_MC 0x0283 /* Multi Protocol Label Switching - Multicast */
#define PPP_IPCP 0x8021 /* IP Control Protocol */
#define PPP_ATCP 0x8029 /* AppleTalk Control Protocol */
#define PPP_IPXCP 0x802b /* IPX Control Protocol */
+#define PPP_BCP 0x8031 /* Bridging Control Protocol */
#define PPP_IPV6CP 0x8057 /* IPv6 Control Protocol */
#define PPP_CCPFRAG 0x80fb /* CCP at link level (below MP bundle) */
#define PPP_CCP 0x80fd /* Compression Control Protocol */
@@ -181,4 +184,32 @@ struct ppp_idle {
__kernel_time_t recv_idle; /* time since last NP packet received */
};
+/*
+ * Bridging Control Protocol (BCP)
+ */
+struct bcp_hdr {
+ u8 flags;
+ u8 mactype;
+ u8 padbyte; /* not used (present when "control" is also) */
+ u8 control; /* 802.4, 802.5, and FDDI only */
+};
+#define BCP_802_3_HDRLEN 2
+
+/*
+ * Fields in bcp_hdr flags.
+ */
+#define BCP_LAN_FCS 0x80 /* set when LAN FCS is present */
+#define BCP_ZERO_PAD 0x20 /* set to pad 802.3 to min size */
+#define BCP_PADS_MASK 0x0F /* 0-15 bytes padding before PPP FCS */
+
+/*
+ * Values for bcp_hdr mactype.
+ */
+#define BCP_MAC_802_3 0x01 /* 802.3 / Ethernet */
+#define BCP_MAC_802_4 0x02
+#define BCP_MAC_802_5_NC 0x03 /* with non-canonical address */
+#define BCP_MAC_FDDI_NC 0x04 /* with non-canonical address */
+#define BCP_MAC_802_5 0x0B /* with canonical address */
+#define BCP_MAC_FDDI 0x0C /* with canonical address */
+
#endif /* _PPP_DEFS_H_ */
--- a/drivers/net/ppp_generic.c 2010-02-17 09:31:54.707473382 -0800
+++ b/drivers/net/ppp_generic.c 2010-03-01 14:51:49.439297517 -0800
@@ -29,6 +29,7 @@
#include <linux/list.h>
#include <linux/idr.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/poll.h>
#include <linux/ppp_defs.h>
#include <linux/filter.h>
@@ -64,7 +65,9 @@
#define NP_AT 3 /* Appletalk protocol */
#define NP_MPLS_UC 4 /* MPLS unicast */
#define NP_MPLS_MC 5 /* MPLS multicast */
-#define NUM_NP 6 /* Number of NPs. */
+#define NP_BRIDGE 6 /* Bridged LAN packets */
+#define NP_BPDU_IEEE 7 /* IEEE 802.1 (D or G) bridge PDU */
+#define NUM_NP 8 /* Number of NPs. */
#define MPHDRLEN 6 /* multilink protocol header length */
#define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */
@@ -136,6 +139,9 @@ struct ppp {
unsigned pass_len, active_len;
#endif /* CONFIG_PPP_FILTER */
struct net *ppp_net; /* the net we belong to */
+#ifdef CONFIG_PPP_BCP
+ struct net_device *bcp; /* network device for bridging */
+#endif
};
/*
@@ -296,6 +302,10 @@ static inline int proto_to_npindex(int p
return NP_MPLS_UC;
case PPP_MPLS_MC:
return NP_MPLS_MC;
+ case PPP_BRIDGE:
+ return NP_BRIDGE;
+ case PPP_BPDU_IEEE:
+ return NP_BPDU_IEEE;
}
return -EINVAL;
}
@@ -308,6 +318,8 @@ static const int npindex_to_proto[NUM_NP
PPP_AT,
PPP_MPLS_UC,
PPP_MPLS_MC,
+ PPP_BRIDGE,
+ PPP_BPDU_IEEE,
};
/* Translates an ethertype into an NP index */
@@ -341,6 +353,13 @@ static const int npindex_to_ethertype[NU
ETH_P_MPLS_MC,
};
+/* IEEE 802.1D bridge PDU destination address */
+static const u8 ieee_8021d_dstaddr[ETH_ALEN] = { 1, 0x80, 0xC2, 0, 0, 0 };
+
+/* A few bytes that are present when and IEEE 802.1D bridge PDU is
+ * packed into an IEEE 802.3 frame. */
+static const u8 ieee_8021d_8023_hdr[] = { 0x42, 0x42, 0x03 };
+
/*
* Locking shorthand.
*/
@@ -732,7 +751,22 @@ static long ppp_ioctl(struct file *file,
if (copy_to_user(argp, &npi, sizeof(npi)))
break;
} else {
- ppp->npmode[i] = npi.mode;
+#ifdef CONFIG_PPP_BCP
+ if (i == NP_BRIDGE) {
+ if (npi.mode == NPMODE_PASS) {
+ err = ppp_create_bcp(ppp);
+ if (err < 0)
+ break;
+ ppp->npmode[i] = npi.mode;
+ } else {
+ ppp->npmode[NP_BRIDGE] = npi.mode;
+ ppp->npmode[NP_BPDU_IEEE] = npi.mode;
+ ppp_shutdown_bcp(ppp);
+ }
+ } else
+#endif
+ ppp->npmode[i] = npi.mode;
+
/* we may be able to transmit more packets now (??) */
netif_wake_queue(ppp->dev);
}
@@ -935,14 +969,15 @@ out:
/*
* Network interface unit routines.
*/
+
+/* Called by PPP and BCP transmission routines. */
static netdev_tx_t
-ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
+ppp_common_start_xmit(int npi, struct sk_buff *skb, struct net_device *dev)
{
struct ppp *ppp = netdev_priv(dev);
- int npi, proto;
+ int proto;
unsigned char *pp;
- npi = ethertype_to_npindex(ntohs(skb->protocol));
if (npi < 0)
goto outf;
@@ -980,6 +1015,14 @@ ppp_start_xmit(struct sk_buff *skb, stru
return NETDEV_TX_OK;
}
+static netdev_tx_t
+ppp_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ int npi = ethertype_to_npindex(ntohs(skb->protocol));
+
+ return ppp_common_start_xmit(npi, skb, dev);
+}
+
static int
ppp_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
@@ -1643,6 +1686,81 @@ ppp_receive_error(struct ppp *ppp)
slhc_toss(ppp->vj);
}
+#ifdef CONFIG_PPP_BCP
+/* Decapsulate a packet from BCP. */
+static struct sk_buff *bcp_decap(struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ const struct bcp_hdr *hdr;
+
+ /* Make sure that the data we examine are present. */
+ if (!pskb_may_pull(skb, BCP_802_3_HDRLEN))
+ goto drop;
+
+ /* Currently, only 802.3/Ethernet bridging is supported. */
+ hdr = (struct bcp_hdr *) skb->data;
+ if (hdr->mactype != BCP_MAC_802_3)
+ goto drop;
+
+ skb_pull(skb, BCP_802_3_HDRLEN);
+ skb->mac.raw = skb->data;
+
+ /* remove LAN FCS */
+ if (hdr->flags & BCP_LAN_FCS) {
+ if (skb->len < ETH_FCS_LEN)
+ goto drop;
+ skb_trim(skb, skb->len - ETH_FCS_LEN);
+ }
+
+ /* decompress "Tinygrams" */
+ if ((hdr->flags & BCP_ZERO_PAD) && skb_padto(skb, ETH_ZLEN))
+ return 0;
+
+ /* Parse the ethernet header. Because of the increased
+ * hard_header_len, eth_type_trans() skips too much, so push
+ * some back afterward.
+ */
+ skb->protocol = eth_type_trans(skb, dev);
+ skb_push(skb, dev->hard_header_len - ETH_HLEN);
+
+ return skb;
+
+ drop:
+ kfree_skb(skb);
+ return 0;
+}
+
+/* Decapsulate an IEEE 802.1 (D or G) PDU. */
+static struct sk_buff *bpdu_ieee_decap(struct sk_buff *skb)
+{
+ struct net_device *const dev = skb->dev;
+ struct ethhdr *eth;
+
+ if (skb_cow_head(skb, ETH_HLEN + sizeof(ieee_8021d_8023_hdr))) {
+ kfree_skb(skb);
+ return 0;
+ }
+
+ /* Prepend the 802.3 SAP and control byte. */
+ memcpy(skb_push(skb, sizeof(ieee_8021d_8023_hdr)),
+ ieee_8021d_8023_hdr, sizeof(ieee_8021d_8023_hdr));
+
+ /* Prepend an ethernet header. */
+ eth = skb_push(skb, ETH_HLEN);
+ memcpy(eth->h_dest, ieee_8021d_dstaddr, ETH_ALEN);
+ memset(eth->h_source, 0, ETH_ALEN);
+ eth->h_proto = htons(skb->len - ETH_HLEN);
+
+ /* Parse the ethernet header. Because of the increased
+ * hard_header_len, eth_type_trans() skips too much, so push
+ * some back afterward. */
+ skb->protocol = eth_type_trans(skb, dev);
+ skb_push(skb, dev->hard_header_len - ETH_HLEN);
+
+ return skb;
+}
+#endif
+
static void
ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
{
@@ -1734,6 +1852,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp,
} else {
/* network protocol frame - give it to the kernel */
+ struct net_device *rxdev;
#ifdef CONFIG_PPP_FILTER
/* check if the packet passes the pass and active filters */
@@ -1763,13 +1882,44 @@ ppp_receive_nonmp_frame(struct ppp *ppp,
#endif /* CONFIG_PPP_FILTER */
ppp->last_recv = jiffies;
- if ((ppp->dev->flags & IFF_UP) == 0 ||
- ppp->npmode[npi] != NPMODE_PASS) {
- kfree_skb(skb);
- } else {
- /* chop off protocol */
- skb_pull_rcsum(skb, 2);
- skb->dev = ppp->dev;
+#ifdef CONFIG_PPP_BCP
+ if (npi == NP_BRIDGE || npi == NP_BPDU_IEEE)
+ rxdev = ppp->bcp;
+ else
+#endif
+ rxdev = ppp->dev;
+
+ if (ppp->npmode[npi] != NPMODE_PASS ||
+ !rxdev || !(rxdev->flags & IFF_UP)) {
+ kfree_skb(skb);
+ return;
+ }
+
+ /* chop off protocol */
+ skb_pull_rcsum(skb, 2);
+ skb->dev = rxdev;
+
+ switch (npi) {
+#ifdef CONFIG_PPP_BCP
+ case NP_BRIDGE:
+ skb = bcp_decap(skb);
+ if (!skb) {
+ ++ppp->bcp->stats.rx_dropped;
+ goto dropped;
+ }
+ ++ppp->bcp->stats.rx_packets;
+ break;
+
+ case NP_BPDU_IEEE:
+ skb = bpdu_ieee_decap(skb);
+ if (!skb) {
+ ++ppp->bcp->stats.rx_dropped;
+ goto dropped;
+ }
+ ++ppp->bcp->stats.rx_packets;
+ break;
+#endif
+ default:
skb->protocol = htons(npindex_to_ethertype[npi]);
skb_reset_mac_header(skb);
netif_rx(skb);
@@ -2538,6 +2688,8 @@ ppp_create_interface(struct net *net, in
ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */
for (i = 0; i < NUM_NP; ++i)
ppp->npmode[i] = NPMODE_PASS;
+ ppp->npmode[NP_BRIDGE] = NPMODE_DROP;
+ ppp->npmode[NP_BPDU_IEEE] = NPMODE_DROP;
INIT_LIST_HEAD(&ppp->channels);
spin_lock_init(&ppp->rlock);
spin_lock_init(&ppp->wlock);
@@ -2880,6 +3032,189 @@ static void *unit_find(struct idr *p, in
return idr_find(p, n);
}
+#ifdef CONFIG_PPP_BCP
+static const struct net_device_ops bcp_netdev_ops = {
+ .ndo_start_xmit = bcp_start_xmit,
+ .ndo_change_mtu = bcp_net_change_mtu,
+ .ndo_set_mac_addr = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+};
+
+/*
+ * Create interface for bridging.
+ */
+static int ppp_create_bcp(struct ppp *ppp)
+{
+ struct net_device *dev;
+ int ret = -ENOMEM;
+
+ /* If it already exists, ignore the request. */
+ if (ppp->bcp)
+ return 0;
+
+ /* create a new BCP dev */
+ dev = alloc_etherdev(0);
+ if (!dev)
+ goto err;
+
+ dev->hard_header_len = ppp->dev->hard_header_len
+ + BCP_802_3_HDRLEN + ETH_HLEN;
+
+ /* ETH_FCS_LEN is not subtracted from the PPP MTU here because
+ * bcp_start_xmit() never adds the FCS. */
+ dev->mtu = ppp->dev->mtu - (BCP_802_3_HDRLEN + ETH_HLEN);
+
+ if (dev->mtu > ETH_DATA_LEN)
+ dev->mtu = ETH_DATA_LEN;
+
+ dev->netdev_ops = &bcp_netdev_ops;
+ dev->tx_queue_len = 0; /* let PPP device queue packets */
+
+ sprintf(dev->name, "bcp%d", ppp->file.index);
+
+ rtnl_lock();
+ ret = register_netdevice(dev);
+ if (ret == 0)
+ ppp->bcp = dev;
+ rtnl_unlock();
+
+ if (ret) {
+ pr_err("PPP: couldn't register device %s (%d)\n",
+ dev->name, ret);
+ free_netdev(dev);
+ }
+ err:
+ return ret;
+}
+
+/*
+ * Take down a bcp interface.
+ */
+static void ppp_shutdown_bcp(struct ppp *ppp)
+{
+ struct net_device *bcp;
+
+ bcp = ppp->bcp;
+ if (bcp) {
+ unregister_netdev(bcp);
+ ppp->bcp = 0;
+ free_netdev(bcp);
+ }
+}
+
+static int
+bcp_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+ return -EOPNOTSUPP;
+}
+
+static int
+bcp_net_change_mtu(struct net_device *dev, int new_mtu)
+{
+ /* MTU is negotiated by the PPP daemon and should not be changed. */
+ return -EOPNOTSUPP;
+}
+
+/* input: ethernet frame in non-shared skbuff
+ * output: bcp-encapsulated frame in non-shared and non-cloned skbuff
+ */
+static struct sk_buff *bcp_encap(struct sk_buff *skb, struct net_device *dev)
+{
+ struct bcp_hdr *bhdr;
+ int pad_len;
+
+ /* @todo Calculate FCS? NB: If you add this, be sure to
+ * change the MTU calculation in ppp_create_bcp() to account
+ * for it. */
+
+
+ /* Add a BCP header and pad to minimum frame size.
+ *
+ * Observations:
+ * - Headroom is usually adequate, because the kernel usually
+ * checks dev->hard_header_len; however, it is possible to
+ * be given a buffer that was originally allocated for another
+ * device. (I have not seen it during testing.)
+ * - It is not possible for a buffer to be shared, because
+ * bcp_start_xmit() calls skb_share_check().
+ * - I do not know when a buffer might be cloned; perhaps it
+ * is possible in a bridging application where the same
+ * packet needs to be transmitted to multiple interfaces.
+ */
+ if (skb_cow_head(skb, dev->hard_header_len)) {
+ kfree_skb(skb);
+ return 0;
+ }
+
+ bhdr = skb_push(skb, BCP_802_3_HDRLEN);
+ bhdr->flags = 0; /* no LAN FCS, not a tinygram */
+ bhdr->mactype = BCP_MAC_802_3; /* 802.3 / Ethernet */
+
+ /* There is currently no communication from pppd regarding the
+ * peer's Tinygram-Compression option. Therefore, we always
+ * pad short frames to minimum Ethernet size in case the peer
+ * does not support Tinygrams.
+ */
+ if (skb_padto(skb, ETH_ZLEN))
+ return 0;
+
+ return skb;
+}
+
+/* input: BPDU ethernet frame in non-shared skbuff
+ * output: naked BPDU in non-shared and non-cloned skbuff
+ */
+static struct sk_buff *bpdu_ieee_encap(struct sk_buff *skb)
+{
+ /* pull off the link header */
+ skb_pull(skb, ETH_HLEN + sizeof(ieee_8021d_8023_hdr));
+
+ return skb_unshare(skb, GFP_ATOMIC);
+}
+
+static int
+bcp_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct bcp_device *const bcp = dev_to_bcp(dev);
+ struct ppp *const ppp = bcp_to_ppp(bcp);
+ int npi;
+
+ /* make sure we can push/pull without side effects */
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ goto dropped;
+
+ /* When configured to encapsulate 802.1D bridge PDUs in the
+ * obsolete manner of RFC 1638, do it. Otherwise, send it
+ * like any other packet.
+ */
+ if ((ppp->npmode[NP_BPDU_IEEE] == NPMODE_PASS) &&
+ pskb_may_pull(skb, ETH_HLEN + sizeof(ieee_8021d_8023_hdr)) &&
+ compare_ether_addr(skb->data, ieee_8021d_dstaddr) == 0 &&
+ memcmp(skb->data + ETH_HLEN, ieee_8021d_8023_hdr,
+ sizeof(ieee_8021d_8023_hdr)) == 0) {
+ skb = bpdu_ieee_encap(skb, dev);
+ npi = NP_BPDU_IEEE;
+ } else {
+ skb = bcp_encap(skb, dev);
+ npi = NP_BRIDGE;
+ }
+
+ if (!skb)
+ goto dropped;
+
+ /* send packet through the PPP interface */
+ skb->dev = ppp->dev;
+ ++bcp->stats.tx_packets;
+
+ return ppp_common_start_xmit(npi, skb, skb->dev);
+
+ dropped:
+ ++bcp->stats.tx_dropped;
+ return 0;
+}
+#endif
+
/* Module/initialization stuff */
module_init(ppp_init);
--- a/drivers/net/Kconfig 2010-02-19 08:14:26.161558356 -0800
+++ b/drivers/net/Kconfig 2010-03-01 14:50:10.977353125 -0800
@@ -3166,6 +3166,13 @@ config PPPOL2TP
and session setup). One such daemon is OpenL2TP
(http://openl2tp.sourceforge.net/).
+config PPP_BCP
+ tristate "PPP over Bridge"
+ depends on EXPERIMENTAL && PPP && BRIDGE
+ help
+ Support for PPP over Ethernet Bridge by using the
+ Bridge Control Protocol (BCP) as defined in RFC 3185.
+
config SLIP
tristate "SLIP (serial line) support"
---help---
^ permalink raw reply
* [PATCH 0/5] ARC vmac ethernet driver.
From: Andreas Fenkart @ 2010-03-01 23:18 UTC (permalink / raw)
To: netdev; +Cc: amit.bhor, sameer.dhavale
In-Reply-To: <20100222.154010.149123575.davem@davemloft.net>
This is a resend of previous submission. It contains the following
changes:
* Removed arcvmac_fifo.h, moved content to arcvmac.h
* Replaced BUG_ON with WARN_ON
* Added missing Kconfig entry
^ 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