* [PATCH 9/13] unix_diag: Unix inode info NLA
From: Pavel Emelyanov @ 2011-12-15 12:45 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
Actually, the socket path if it's not anonymous doesn't give
a clue to which file the socket is bound to. Even if the path
is absolute, it can be unlinked and then new socket can be
bound to it.
With this NLA it's possible to check which file a particular
socket is really bound to.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
include/linux/unix_diag.h | 7 +++++++
net/unix/diag.c | 21 +++++++++++++++++++++
2 files changed, 28 insertions(+), 0 deletions(-)
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
index cc4df34..3e53adb 100644
--- a/include/linux/unix_diag.h
+++ b/include/linux/unix_diag.h
@@ -12,6 +12,7 @@ struct unix_diag_req {
};
#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
+#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
struct unix_diag_msg {
__u8 udiag_family;
@@ -25,8 +26,14 @@ struct unix_diag_msg {
enum {
UNIX_DIAG_NAME,
+ UNIX_DIAG_VFS,
UNIX_DIAG_MAX,
};
+struct unix_diag_vfs {
+ __u32 udiag_vfs_ino;
+ __u32 udiag_vfs_dev;
+};
+
#endif
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 161ce6c..83799ef 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -26,6 +26,23 @@ rtattr_failure:
return -EMSGSIZE;
}
+static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct dentry *dentry = unix_sk(sk)->dentry;
+ struct unix_diag_vfs *uv;
+
+ if (dentry) {
+ uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv));
+ uv->udiag_vfs_ino = dentry->d_inode->i_ino;
+ uv->udiag_vfs_dev = dentry->d_sb->s_dev;
+ }
+
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
u32 pid, u32 seq, u32 flags, int sk_ino)
{
@@ -48,6 +65,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
sk_diag_dump_name(sk, skb))
goto nlmsg_failure;
+ if ((req->udiag_show & UDIAG_SHOW_VFS) &&
+ sk_diag_dump_vfs(sk, skb))
+ goto nlmsg_failure;
+
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
--
1.5.5.6
^ permalink raw reply related
* [PATCH 10/13] unix_diag: Unix peer inode NLA
From: Pavel Emelyanov @ 2011-12-15 12:45 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
Report the peer socket inode ID as NLA. With this it's finally
possible to find out the other end of an interesting unix connection.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
include/linux/unix_diag.h | 2 ++
net/unix/diag.c | 24 ++++++++++++++++++++++++
2 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
index 3e53adb..2d74a86 100644
--- a/include/linux/unix_diag.h
+++ b/include/linux/unix_diag.h
@@ -13,6 +13,7 @@ struct unix_diag_req {
#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
+#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
struct unix_diag_msg {
__u8 udiag_family;
@@ -27,6 +28,7 @@ struct unix_diag_msg {
enum {
UNIX_DIAG_NAME,
UNIX_DIAG_VFS,
+ UNIX_DIAG_PEER,
UNIX_DIAG_MAX,
};
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 83799ef..0e0fda7 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -43,6 +43,26 @@ rtattr_failure:
return -EMSGSIZE;
}
+static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sock *peer;
+ int ino;
+
+ peer = unix_peer_get(sk);
+ if (peer) {
+ unix_state_lock(peer);
+ ino = sock_i_ino(peer);
+ unix_state_unlock(peer);
+ sock_put(peer);
+
+ RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino);
+ }
+
+ return 0;
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
u32 pid, u32 seq, u32 flags, int sk_ino)
{
@@ -69,6 +89,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
sk_diag_dump_vfs(sk, skb))
goto nlmsg_failure;
+ if ((req->udiag_show & UDIAG_SHOW_PEER) &&
+ sk_diag_dump_peer(sk, skb))
+ goto nlmsg_failure;
+
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
--
1.5.5.6
^ permalink raw reply related
* [PATCH 11/13] unix_diag: Pending connections IDs NLA
From: Pavel Emelyanov @ 2011-12-15 12:46 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
When establishing a unix connection on stream sockets the
server end receives an skb with socket in its receive queue.
Report who is waiting for these ends to be accepted for
listening sockets via NLA.
There's a lokcing issue with this -- the unix sk state lock is
required to access the peer, and it is taken under the listening
sk's queue lock. Strictly speaking the queue lock should be taken
inside the state lock, but since in this case these two sockets
are different it shouldn't lead to deadlock.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
include/linux/unix_diag.h | 2 ++
net/unix/diag.c | 39 +++++++++++++++++++++++++++++++++++++++
2 files changed, 41 insertions(+), 0 deletions(-)
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
index 2d74a86..03ffb7d 100644
--- a/include/linux/unix_diag.h
+++ b/include/linux/unix_diag.h
@@ -14,6 +14,7 @@ struct unix_diag_req {
#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
+#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
struct unix_diag_msg {
__u8 udiag_family;
@@ -29,6 +30,7 @@ enum {
UNIX_DIAG_NAME,
UNIX_DIAG_VFS,
UNIX_DIAG_PEER,
+ UNIX_DIAG_ICONS,
UNIX_DIAG_MAX,
};
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 0e0fda7..9d9e808 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -63,6 +63,41 @@ rtattr_failure:
return -EMSGSIZE;
}
+static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
+{
+ struct sk_buff *skb;
+ u32 *buf;
+ int i;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ spin_lock(&sk->sk_receive_queue.lock);
+ buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, sk->sk_receive_queue.qlen);
+ i = 0;
+ skb_queue_walk(&sk->sk_receive_queue, skb) {
+ struct sock *req, *peer;
+
+ req = skb->sk;
+ /*
+ * The state lock is outer for the same sk's
+ * queue lock. With the other's queue locked it's
+ * OK to lock the state.
+ */
+ unix_state_lock_nested(req);
+ peer = unix_sk(req)->peer;
+ if (peer)
+ buf[i++] = sock_i_ino(peer);
+ unix_state_unlock(req);
+ }
+ spin_unlock(&sk->sk_receive_queue.lock);
+ }
+
+ return 0;
+
+rtattr_failure:
+ spin_unlock(&sk->sk_receive_queue.lock);
+ return -EMSGSIZE;
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
u32 pid, u32 seq, u32 flags, int sk_ino)
{
@@ -93,6 +128,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
sk_diag_dump_peer(sk, skb))
goto nlmsg_failure;
+ if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
+ sk_diag_dump_icons(sk, skb))
+ goto nlmsg_failure;
+
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
--
1.5.5.6
^ permalink raw reply related
* [PATCH 12/13] unix_diag: Receive queue lenght NLA
From: Pavel Emelyanov @ 2011-12-15 12:46 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
include/linux/unix_diag.h | 2 ++
net/unix/diag.c | 13 +++++++++++++
2 files changed, 15 insertions(+), 0 deletions(-)
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
index 03ffb7d..3f7afb0 100644
--- a/include/linux/unix_diag.h
+++ b/include/linux/unix_diag.h
@@ -15,6 +15,7 @@ struct unix_diag_req {
#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
+#define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */
struct unix_diag_msg {
__u8 udiag_family;
@@ -31,6 +32,7 @@ enum {
UNIX_DIAG_VFS,
UNIX_DIAG_PEER,
UNIX_DIAG_ICONS,
+ UNIX_DIAG_RQLEN,
UNIX_DIAG_MAX,
};
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 9d9e808..53b4833 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -98,6 +98,15 @@ rtattr_failure:
return -EMSGSIZE;
}
+static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
+{
+ RTA_PUT_U32(nlskb, UNIX_DIAG_RQLEN, sk->sk_receive_queue.qlen);
+ return 0;
+
+rtattr_failure:
+ return -EMSGSIZE;
+}
+
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
u32 pid, u32 seq, u32 flags, int sk_ino)
{
@@ -132,6 +141,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
sk_diag_dump_icons(sk, skb))
goto nlmsg_failure;
+ if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
+ sk_diag_show_rqlen(sk, skb))
+ goto nlmsg_failure;
+
nlh->nlmsg_len = skb_tail_pointer(skb) - b;
return skb->len;
--
1.5.5.6
^ permalink raw reply related
* [PATCH 13/13] unix_diag: Write it into kbuild
From: Pavel Emelyanov @ 2011-12-15 12:46 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
net/unix/Kconfig | 7 +++++++
net/unix/Makefile | 3 +++
2 files changed, 10 insertions(+), 0 deletions(-)
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index 5a69733..52db53c 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -19,3 +19,10 @@ config UNIX
Say Y unless you know what you are doing.
+config UNIX_DIAG
+ tristate "UNIX: socket monitoring interface"
+ depends on UNIX
+ default UNIX
+ ---help---
+ Support for UNIX socket monitoring interface used by the ss tool.
+ If unsure, say Y.
diff --git a/net/unix/Makefile b/net/unix/Makefile
index b852a2b..b663c60 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -6,3 +6,6 @@ obj-$(CONFIG_UNIX) += unix.o
unix-y := af_unix.o garbage.o
unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o
+
+obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
+unix_diag-y := diag.o
--
1.5.5.6
^ permalink raw reply related
* [PATCH] iproute: Dump unix sockets via netlink
From: Pavel Emelyanov @ 2011-12-15 13:28 UTC (permalink / raw)
To: David Miller, Linux Netdev List
In-Reply-To: <4EE9EB2A.4040909@parallels.com>
Get the same info as from /proc file plus the peer inode.
Applies on top of new sock diag patch and udp diag patch.
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
---
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
new file mode 100644
index 0000000..3f7afb0
--- /dev/null
+++ b/include/linux/unix_diag.h
@@ -0,0 +1,45 @@
+#ifndef __UNIX_DIAG_H__
+#define __UNIX_DIAG_H__
+
+struct unix_diag_req {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u16 pad;
+ __u32 udiag_states;
+ __u32 udiag_ino;
+ __u32 udiag_show;
+ __u32 udiag_cookie[2];
+};
+
+#define UDIAG_SHOW_NAME 0x00000001 /* show name (not path) */
+#define UDIAG_SHOW_VFS 0x00000002 /* show VFS inode info */
+#define UDIAG_SHOW_PEER 0x00000004 /* show peer socket info */
+#define UDIAG_SHOW_ICONS 0x00000008 /* show pending connections */
+#define UDIAG_SHOW_RQLEN 0x00000010 /* show skb receive queue len */
+
+struct unix_diag_msg {
+ __u8 udiag_family;
+ __u8 udiag_type;
+ __u8 udiag_state;
+ __u8 pad;
+
+ __u32 udiag_ino;
+ __u32 udiag_cookie[2];
+};
+
+enum {
+ UNIX_DIAG_NAME,
+ UNIX_DIAG_VFS,
+ UNIX_DIAG_PEER,
+ UNIX_DIAG_ICONS,
+ UNIX_DIAG_RQLEN,
+
+ UNIX_DIAG_MAX,
+};
+
+struct unix_diag_vfs {
+ __u32 udiag_vfs_ino;
+ __u32 udiag_vfs_dev;
+};
+
+#endif
diff --git a/misc/ss.c b/misc/ss.c
index a5e232b..6f2995e 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -35,6 +35,7 @@
#include <netinet/tcp.h>
#include <linux/inet_diag.h>
+#include <linux/unix_diag.h>
int resolve_hosts = 0;
int resolve_services = 1;
@@ -2011,6 +2012,179 @@ void unix_list_print(struct unixstat *list, struct filter *f)
}
}
+static int unix_show_sock(struct nlmsghdr *nlh, struct filter *f)
+{
+ struct unix_diag_msg *r = NLMSG_DATA(nlh);
+ struct rtattr *tb[UNIX_DIAG_MAX+1];
+ char name[128];
+ int peer_ino;
+ int rqlen;
+
+ parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr*)(r+1),
+ nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+ if (netid_width)
+ printf("%-*s ", netid_width,
+ r->udiag_type == SOCK_STREAM ? "u_str" : "u_dgr");
+ if (state_width)
+ printf("%-*s ", state_width, sstate_name[r->udiag_state]);
+
+ if (tb[UNIX_DIAG_RQLEN])
+ rqlen = *(int *)RTA_DATA(tb[UNIX_DIAG_RQLEN]);
+ else
+ rqlen = 0;
+
+ printf("%-6d %-6d ", rqlen, 0);
+
+ if (tb[UNIX_DIAG_NAME]) {
+ int len = RTA_PAYLOAD(tb[UNIX_DIAG_NAME]);
+
+ memcpy(name, RTA_DATA(tb[UNIX_DIAG_NAME]), len);
+ name[len] = '\0';
+ if (name[0] == '\0')
+ name[0] = '@';
+ } else
+ sprintf(name, "*");
+
+ if (tb[UNIX_DIAG_PEER])
+ peer_ino = *(int *)RTA_DATA(tb[UNIX_DIAG_PEER]);
+ else
+ peer_ino = 0;
+
+ printf("%*s %-*d %*s %-*d",
+ addr_width, name,
+ serv_width, r->udiag_ino,
+ addr_width, "*", /* FIXME */
+ serv_width, peer_ino);
+
+ if (show_users) {
+ char ubuf[4096];
+ if (find_users(r->udiag_ino, ubuf, sizeof(ubuf)) > 0)
+ printf(" users:(%s)", ubuf);
+ }
+
+ printf("\n");
+
+ return 0;
+}
+
+static int unix_show_netlink(struct filter *f, FILE *dump_fp)
+{
+ int fd;
+ struct sockaddr_nl nladdr;
+ struct {
+ struct nlmsghdr nlh;
+ struct unix_diag_req r;
+ } req;
+ struct msghdr msg;
+ char buf[8192];
+ struct iovec iov[3];
+
+ if ((fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_INET_DIAG)) < 0)
+ return -1;
+
+ memset(&nladdr, 0, sizeof(nladdr));
+ nladdr.nl_family = AF_NETLINK;
+
+ req.nlh.nlmsg_len = sizeof(req);
+ req.nlh.nlmsg_type = SOCK_DIAG_BY_FAMILY;
+ req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+ req.nlh.nlmsg_pid = 0;
+ req.nlh.nlmsg_seq = 123456;
+ memset(&req.r, 0, sizeof(req.r));
+ req.r.sdiag_family = AF_UNIX;
+ req.r.sdiag_protocol = 0; /* ignored */
+ req.r.udiag_states = f->states;
+ req.r.udiag_show = UDIAG_SHOW_NAME | UDIAG_SHOW_PEER | UDIAG_SHOW_RQLEN;
+
+ iov[0] = (struct iovec){
+ .iov_base = &req,
+ .iov_len = sizeof(req)
+ };
+
+ msg = (struct msghdr) {
+ .msg_name = (void*)&nladdr,
+ .msg_namelen = sizeof(nladdr),
+ .msg_iov = iov,
+ .msg_iovlen = f->f ? 3 : 1,
+ };
+
+ if (sendmsg(fd, &msg, 0) < 0)
+ return -1;
+
+ iov[0] = (struct iovec){
+ .iov_base = buf,
+ .iov_len = sizeof(buf)
+ };
+
+ while (1) {
+ int status;
+ struct nlmsghdr *h;
+
+ msg = (struct msghdr) {
+ (void*)&nladdr, sizeof(nladdr),
+ iov, 1,
+ NULL, 0,
+ 0
+ };
+
+ status = recvmsg(fd, &msg, 0);
+
+ if (status < 0) {
+ if (errno == EINTR)
+ continue;
+ perror("OVERRUN");
+ continue;
+ }
+ if (status == 0) {
+ fprintf(stderr, "EOF on netlink\n");
+ return 0;
+ }
+
+ if (dump_fp)
+ fwrite(buf, 1, NLMSG_ALIGN(status), dump_fp);
+
+ h = (struct nlmsghdr*)buf;
+ while (NLMSG_OK(h, status)) {
+ int err;
+
+ if (/*h->nlmsg_pid != rth->local.nl_pid ||*/
+ h->nlmsg_seq != 123456)
+ goto skip_it;
+
+ if (h->nlmsg_type == NLMSG_DONE)
+ return 0;
+ if (h->nlmsg_type == NLMSG_ERROR) {
+ struct nlmsgerr *err = (struct nlmsgerr*)NLMSG_DATA(h);
+ if (h->nlmsg_len < NLMSG_LENGTH(sizeof(struct nlmsgerr))) {
+ fprintf(stderr, "ERROR truncated\n");
+ } else {
+ errno = -err->error;
+ perror("TCPDIAG answers");
+ }
+ return 0;
+ }
+ if (!dump_fp) {
+ err = unix_show_sock(h, f);
+ if (err < 0)
+ return err;
+ }
+
+skip_it:
+ h = NLMSG_NEXT(h, status);
+ }
+ if (msg.msg_flags & MSG_TRUNC) {
+ fprintf(stderr, "Message truncated\n");
+ continue;
+ }
+ if (status) {
+ fprintf(stderr, "!!!Remnant of size %d\n", status);
+ exit(1);
+ }
+ }
+ return 0;
+}
+
int unix_show(struct filter *f)
{
FILE *fp;
@@ -2020,6 +2194,10 @@ int unix_show(struct filter *f)
int cnt;
struct unixstat *list = NULL;
+ if (!getenv("PROC_NET_UNIX") && !getenv("PROC_ROOT")
+ && unix_show_netlink(f, NULL) == 0)
+ return 0;
+
if ((fp = net_unix_open()) == NULL)
return -1;
fgets(buf, sizeof(buf)-1, fp);
^ permalink raw reply related
* Re: linux-3.0.x regression with ipv4 routes having mtu
From: Steffen Klassert @ 2011-12-15 13:49 UTC (permalink / raw)
To: David Miller; +Cc: timo.teras, netdev
In-Reply-To: <20111214.125010.82857701285437834.davem@davemloft.net>
On Wed, Dec 14, 2011 at 12:50:10PM -0500, David Miller wrote:
> From: Timo Teräs <timo.teras@iki.fi>
> Date: Wed, 14 Dec 2011 17:54:16 +0200
>
> > So something is does not get updated here. This used to work though.
> > The current production boxes where I know this work is 2.6.38.8.
>
> We store the PMTU externally in inetpeer entries, Eric Dumazet
> fixed recently but that fix hasn't been submitted to -stable
> yet.
>
I think we still have at least two problems with pmtu handling.
One is that "ip route flush cache" flushes the routing cache
but not the cached metrics on the inetpeer.
Another problem might be that we ignore the user configured
fib_metrics in rt_init_metrics() if we have a cached metric
on the inetpeer.
I'll try to look at this a bit closer tomorrow.
^ permalink raw reply
* Re: [Linux-zigbee-devel] ieee802154: WARNING: at mm/page_alloc.c:2095
From: Sasha Levin @ 2011-12-15 14:13 UTC (permalink / raw)
To: Alexander Smirnov; +Cc: dbaryshkov, slapin, davem, netdev, linux-zigbee-devel
In-Reply-To: <CAJmB2rCa-tODD9vFBRRY+Qp3DKDJN6VBLurE=TEqPatGFJEH4g@mail.gmail.com>
On Thu, 2011-12-15 at 15:21 +0300, Alexander Smirnov wrote:
> first of all could you please specify:
> 1. What's the kernel do you use?
linux-next.
> 2. What's the config options are enabled in your kernel?
It's a testing kernel which is pretty close to being 'make
allyesconfig'. So if you're thinking about a specific feature - it's
probably '=y'.
> 3. What the HW do you use and what is the use case?
I actually don't have any special HW, this was part of a fuzzer test.
> 4. What you do to represent this error?
According to the fuzzer it's the result of calling sys_sendto() with a
pretty large numbrt in the length field.
--
Sasha.
^ permalink raw reply
* Re: kenel level packet capturing
From: Eduardo Panisset @ 2011-12-15 15:19 UTC (permalink / raw)
To: David Miller; +Cc: raviraj.j1991, netdev, netfilter-devel, netfilter
In-Reply-To: <20111214.110919.1286184647888114902.davem@davemloft.net>
Hi Raviraj,
You could be interested in taking a look at
"Documentation/networking/packet_mmap.txt" (this talks about mmap()'d
packet ring implementation for AF_PACKET).
Rgds,
Eduardo Panisset.
On Wed, Dec 14, 2011 at 2:09 PM, David Miller <davem@davemloft.net> wrote:
> From: raviraj joshi <raviraj.j1991@gmail.com>
> Date: Wed, 14 Dec 2011 16:16:01 +0530
>
>> On Wed, Dec 14, 2011 at 12:06 AM, David Miller <davem@davemloft.net> wrote:
>>> From: raviraj joshi <raviraj.j1991@gmail.com>
>>> Date: Tue, 13 Dec 2011 17:34:22 +0530
>>>
>>>> We have decided to use PF_RING(a kernel module to capture packets) for
>>>> the same due to the number of advantages.
>>>
>>> What "advantages"? The AF_PACKET socket layer already upstream in the
>>> kernel supports every relevant performance feature PF_RING does, and
>>> then some.
>> I refered to the document on "A Measurement Study of Packet Reception
>> using Linux"[1] which said pf_ring maintains
>> a ring buffer, so we dont have to issue a receive system call for each
>> packet in contrast to AF_PACKET which issues a system call for each
>> packet(pls correct me if i am wrong).
>
> AF_PACKET supports mmap()'d packet rings, and even supports variable
> packet lengths within those rings.
>
> AF_PACKET supports all the worthwhile performance features of PR_RING
> and it's upstream, stop kidding yourself.
>
> I'm really sick and tired of people saying PF_RING is better than
> what we have upstream, it really isn't.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net-next 2/2] igb: offer a PTP Hardware Clock instead of the timecompare method
From: Richard Cochran @ 2011-12-15 16:12 UTC (permalink / raw)
To: Jesse Brandeburg
Cc: netdev@vger.kernel.org, e1000-devel@lists.sourceforge.net,
Keller, Jacob E, Kirsher, Jeffrey T, Ronciak, John, John Stultz,
Thomas Gleixner, Wyborny, Carolyn
In-Reply-To: <1323901989.19702.12.camel@jbrandeb-mobl2>
On Wed, Dec 14, 2011 at 02:33:09PM -0800, Jesse Brandeburg wrote:
> On Mon, 2011-12-12 at 19:00 -0800, Richard Cochran wrote:
> > This commit removes the legacy timecompare code from the igb driver and
> > offers a tunable PHC instead.
> >
> > Signed-off-by: Richard Cochran <richardcochran@gmail.com>
>
> Richard, first, thanks for this work, I have some feedback and request
> you make a V2.
Thanks for your feedback, I'll will work your comments in.
Any chance of getting the driver tested on a 82576?
Thanks,
Richard
^ permalink raw reply
* Re: [PATCH 2/2] Explicitly call tcp creation and init from memcontrol.c
From: KAMEZAWA Hiroyuki @ 2011-12-15 16:13 UTC (permalink / raw)
To: Glauber Costa
Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, cgroups-u79uwXL29TY76Z2rM5mHXA,
Eric Dumazet, Stephen Rothwell
In-Reply-To: <1323941672-14324-3-git-send-email-glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
On Thu, 15 Dec 2011 13:34:32 +0400
Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org> wrote:
> Walking the proto_list holds a read_lock, which prevents us from doing
> allocations. Splitting the tcp create function into create + init is
> good, but it is not enough since create_files will do allocations as well
> (dentry ones, mostly).
>
> Since this does not involve any protocol state, I propose we call the tcp
> functions explicitly from memcontrol.c
>
> With this, we lose by now the ability of doing cgroup memcontrol for
> protocols that are loaded as modules. But at least the ones I have in mind
> won't really need it (tcp_ipv6 being the only one, but it uses the same data
> structures as tcp_ipv4). So I believe this to be the simpler solution to this
> problem.
>
> Signed-off-by: Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
> CC: Hiroyouki Kamezawa <kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
> CC: David S. Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
> CC: Eric Dumazet <eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> CC: Stephen Rothwell <sfr-3FnU+UHB4dNDw9hX6IcOSA@public.gmane.org>
Could you remake the patch onto the 'latest' linux-next ?
As Dave mentioned, some bandaids are already applied and this patch hunks.
Thanks,
-Kame
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 2/2] Explicitly call tcp creation and init from memcontrol.c
From: Glauber Costa @ 2011-12-15 16:18 UTC (permalink / raw)
To: KAMEZAWA Hiroyuki
Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, cgroups-u79uwXL29TY76Z2rM5mHXA,
Eric Dumazet, Stephen Rothwell
In-Reply-To: <20111216011316.8d58bc8f.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
On 12/15/2011 08:13 PM, KAMEZAWA Hiroyuki wrote:
> On Thu, 15 Dec 2011 13:34:32 +0400
> Glauber Costa<glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org> wrote:
>
>> Walking the proto_list holds a read_lock, which prevents us from doing
>> allocations. Splitting the tcp create function into create + init is
>> good, but it is not enough since create_files will do allocations as well
>> (dentry ones, mostly).
>>
>> Since this does not involve any protocol state, I propose we call the tcp
>> functions explicitly from memcontrol.c
>>
>> With this, we lose by now the ability of doing cgroup memcontrol for
>> protocols that are loaded as modules. But at least the ones I have in mind
>> won't really need it (tcp_ipv6 being the only one, but it uses the same data
>> structures as tcp_ipv4). So I believe this to be the simpler solution to this
>> problem.
>>
>> Signed-off-by: Glauber Costa<glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
>> CC: Hiroyouki Kamezawa<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
>> CC: David S. Miller<davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
>> CC: Eric Dumazet<eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
>> CC: Stephen Rothwell<sfr-3FnU+UHB4dNDw9hX6IcOSA@public.gmane.org>
>
> Could you remake the patch onto the 'latest' linux-next ?
> As Dave mentioned, some bandaids are already applied and this patch hunks.
Sure thing.
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net-next] be2net: Add support for Skyhawk cards
From: Ajit Khaparde @ 2011-12-15 16:31 UTC (permalink / raw)
To: davem; +Cc: netdev
Signed-off-by: Ajit Khaparde <ajit.khaparde@emulex.com>
---
drivers/net/ethernet/emulex/benet/be.h | 4 ++++
drivers/net/ethernet/emulex/benet/be_main.c | 2 ++
2 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index a3588fb..995198d 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -40,6 +40,7 @@
#define OC_NAME "Emulex OneConnect 10Gbps NIC"
#define OC_NAME_BE OC_NAME "(be3)"
#define OC_NAME_LANCER OC_NAME "(Lancer)"
+#define OC_NAME_SH OC_NAME "(Skyhawk)"
#define DRV_DESC "ServerEngines BladeEngine 10Gbps NIC Driver"
#define BE_VENDOR_ID 0x19a2
@@ -50,6 +51,7 @@
#define OC_DEVICE_ID2 0x710 /* Device Id for BE3 cards */
#define OC_DEVICE_ID3 0xe220 /* Device id for Lancer cards */
#define OC_DEVICE_ID4 0xe228 /* Device id for VF in Lancer */
+#define OC_DEVICE_ID5 0x720 /* Device Id for Skyhawk cards */
static inline char *nic_name(struct pci_dev *pdev)
{
@@ -63,6 +65,8 @@ static inline char *nic_name(struct pci_dev *pdev)
return OC_NAME_LANCER;
case BE_DEVICE_ID2:
return BE3_NAME;
+ case OC_DEVICE_ID5:
+ return OC_NAME_SH;
default:
return BE_NAME;
}
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 9b5304a..b145a49 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -42,6 +42,7 @@ static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
+ { PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
{ 0 }
};
MODULE_DEVICE_TABLE(pci, be_dev_ids);
@@ -3312,6 +3313,7 @@ static int be_dev_family_check(struct be_adapter *adapter)
break;
case BE_DEVICE_ID2:
case OC_DEVICE_ID2:
+ case OC_DEVICE_ID5:
adapter->generation = BE_GEN3;
break;
case OC_DEVICE_ID3:
--
1.7.5.4
^ permalink raw reply related
* Re: [PATCH net-next 2/2] igb: offer a PTP Hardware Clock instead of the timecompare method
From: Wyborny, Carolyn @ 2011-12-15 16:46 UTC (permalink / raw)
To: Richard Cochran, Brandeburg, Jesse
Cc: e1000-devel@lists.sourceforge.net, netdev@vger.kernel.org,
Ronciak, John, Stultz, Keller, Jacob E, Thomas Gleixner, John
In-Reply-To: <20111215161256.GA5176@cherladcori01>
>-----Original Message-----
>From: Richard Cochran [mailto:richardcochran@gmail.com]
>Sent: Thursday, December 15, 2011 8:13 AM
>To: Brandeburg, Jesse
>Cc: netdev@vger.kernel.org; e1000-devel@lists.sourceforge.net; Keller,
>Jacob E; Kirsher, Jeffrey T; Ronciak, John; John Stultz; Thomas
>Gleixner; Wyborny, Carolyn
>Subject: Re: [PATCH net-next 2/2] igb: offer a PTP Hardware Clock
>instead of the timecompare method
>
>On Wed, Dec 14, 2011 at 02:33:09PM -0800, Jesse Brandeburg wrote:
>> On Mon, 2011-12-12 at 19:00 -0800, Richard Cochran wrote:
>> > This commit removes the legacy timecompare code from the igb driver
>and
>> > offers a tunable PHC instead.
>> >
>> > Signed-off-by: Richard Cochran <richardcochran@gmail.com>
>>
>> Richard, first, thanks for this work, I have some feedback and request
>> you make a V2.
>
>Thanks for your feedback, I'll will work your comments in.
>
>Any chance of getting the driver tested on a 82576?
>
>Thanks,
>
>Richard
I will request this testing and let you know.
Thanks,
Carolyn
Carolyn Wyborny
Linux Development
LAN Access Division
Intel Corporation
------------------------------------------------------------------------------
10 Tips for Better Server Consolidation
Server virtualization is being driven by many needs.
But none more important than the need to reduce IT complexity
while improving strategic productivity. Learn More!
http://www.accelacomm.com/jaw/sdnl/114/51507609/
_______________________________________________
E1000-devel mailing list
E1000-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/e1000-devel
To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
^ permalink raw reply
* Re: drivers/net/usb/asix: bug in asix_get_wol
From: Grant Grundler @ 2011-12-15 16:48 UTC (permalink / raw)
To: Eugene, Allan Chou; +Cc: netdev, Freddy Xin
In-Reply-To: <CAKbEaOBnGAJuZiM5BRaR3RD6EzgB-mCVrC0v2AbnniFpx22m8A@mail.gmail.com>
On Tue, Dec 13, 2011 at 5:03 AM, Eugene <elubarsky@gmail.com> wrote:
> Hi Grant,
>
>
> The problem is that, as it's currently written, asix_get_wol always
> returns that wake-on-lan is disabled.
I think that was the intent.
Allan, can you please confirm?
thanks,
grant
>
>
> Cheers,
> Eugene
>
> On 12 December 2011 10:29, Grant Grundler <grundler@chromium.org> wrote:
>> [+freddy/allan @ ASIX]
>>
>> On Sat, Dec 10, 2011 at 5:02 PM, Eugene <elubarsky@gmail.com> wrote:
>>> Dear kernel devs,
>>>
>>> Thanks for the commit at
>>> http://git.kernel.org/?p=linux/kernel/git/next/linux-next.git;a=commitdiff;h=4ad1438f025ed8d1e4e95a796ca7f0ad5a22c378,
>>> It successfully stops my adapter from dying when wake-on-lan gets
>>> enabled.
>>
>> Hi Eugene!
>> thanks for the "it works!" report.
>>
>>> However, I've noticed that it has broken asix_get_wol - the
>>> lines
>>>
>>> if (opt & AX_MONITOR_LINK)
>>> wolinfo->wolopts |= WAKE_PHY;
>>> if (opt & AX_MONITOR_MAGIC)
>>> wolinfo->wolopts |= WAKE_MAGIC;
>>>
>>> have been accidentally removed.
>>
>> This wasn't by accident. This comment in the commit log perhaps
>> doesn't explain sufficiently:
>> | Remove MONITOR_MODE. In this mode, Received packets are not buffered when
>> | the remote wakeup is enabled.
>>
>>> The vendor driver has them, and I've
>>> successfully tested a kernel with these lines included. The change is
>>> too small for me to bother sending in a properly formatted patch...
>>
>> "Too small"? No such thing. :)
>>
>> cheers,
>> grant
^ permalink raw reply
* [PATCH] mlx4: Fix compile error when driver is comiled-in
From: Joerg Roedel @ 2011-12-15 16:48 UTC (permalink / raw)
To: David S. Miller, Yevgeny Petrilin; +Cc: netdev, linux-kernel, Stephen Rothwell
Hi,
Testing my iommu-configs against linux-next found a compile error for
allyesconfig. It only happens when the mlx4 driver is compiled into the
kernel and not as a module because these two static functions are also
used in another file. The attached patch fixes it.
>From b993c4448c2ce5447fd24e7d4fce02e633d3222e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <joerg.roedel@amd.com>
Date: Thu, 15 Dec 2011 17:30:33 +0100
Subject: [PATCH 1/2] mlx4: Fix compile error when driver is comiled-in
This patch fixes a compile error that occurs when the driver
is compile into the kernel and not as a module.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
drivers/net/ethernet/mellanox/mlx4/port.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 00a9547..88b52e5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -783,7 +783,7 @@ int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
return err;
}
-static int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
+int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx)
{
struct mlx4_cmd_mailbox *mailbox;
@@ -813,7 +813,7 @@ static int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
}
EXPORT_SYMBOL(mlx4_SET_PORT_general);
-static int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
+int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
u8 promisc)
{
struct mlx4_cmd_mailbox *mailbox;
--
1.7.5.4
--
AMD Operating System Research Center
Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach
General Managers: Alberto Bozzo, Andrew Bowd
Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632
^ permalink raw reply related
* [PATCH] phylib: update mdiobus_alloc() to allocate extra private space
From: Timur Tabi @ 2011-12-15 16:51 UTC (permalink / raw)
To: davem, afleming, netdev, linuxppc-dev
Augment mdiobus_alloc() to take a parameter indicating the number of extra
bytes to allocate for private data. Almost all callers of mdiobus_alloc()
separately allocate a private data structure. By allowing mdiobus_alloc()
to allocate extra memory, the two allocations can be merged into one.
This patch does not change any of the callers to actually take advantage
of this feature, however. That change can be made by the individual
maintainers at their leisure. For now, all callers ask for zero additional
bytes, which mimics the previous behavior.
Signed-off-by: Timur Tabi <timur@freescale.com>
---
arch/powerpc/platforms/pasemi/gpio_mdio.c | 2 +-
drivers/net/ethernet/adi/bfin_mac.c | 2 +-
drivers/net/ethernet/aeroflex/greth.c | 2 +-
drivers/net/ethernet/amd/au1000_eth.c | 2 +-
drivers/net/ethernet/broadcom/bcm63xx_enet.c | 2 +-
drivers/net/ethernet/broadcom/sb1250-mac.c | 2 +-
drivers/net/ethernet/broadcom/tg3.c | 2 +-
drivers/net/ethernet/cadence/macb.c | 2 +-
drivers/net/ethernet/dnet.c | 2 +-
drivers/net/ethernet/ethoc.c | 2 +-
drivers/net/ethernet/faraday/ftgmac100.c | 2 +-
drivers/net/ethernet/freescale/fec.c | 2 +-
drivers/net/ethernet/freescale/fec_mpc52xx_phy.c | 2 +-
drivers/net/ethernet/freescale/fs_enet/mii-fec.c | 2 +-
drivers/net/ethernet/freescale/fsl_pq_mdio.c | 2 +-
drivers/net/ethernet/lantiq_etop.c | 2 +-
drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +-
drivers/net/ethernet/marvell/pxa168_eth.c | 2 +-
drivers/net/ethernet/rdc/r6040.c | 2 +-
drivers/net/ethernet/s6gmac.c | 2 +-
drivers/net/ethernet/smsc/smsc911x.c | 2 +-
drivers/net/ethernet/smsc/smsc9420.c | 2 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 +-
drivers/net/ethernet/ti/cpmac.c | 2 +-
drivers/net/ethernet/ti/davinci_mdio.c | 2 +-
drivers/net/ethernet/toshiba/tc35815.c | 2 +-
drivers/net/ethernet/xilinx/ll_temac_mdio.c | 2 +-
drivers/net/ethernet/xilinx/xilinx_emaclite.c | 2 +-
drivers/net/ethernet/xscale/ixp4xx_eth.c | 2 +-
drivers/net/phy/fixed.c | 2 +-
drivers/net/phy/mdio-bitbang.c | 2 +-
drivers/net/phy/mdio-octeon.c | 2 +-
drivers/net/phy/mdio_bus.c | 20 +++++++++++++++++---
drivers/staging/et131x/et131x.c | 2 +-
include/linux/phy.h | 2 +-
net/dsa/dsa.c | 2 +-
36 files changed, 52 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c
index 9886296..754a57b 100644
--- a/arch/powerpc/platforms/pasemi/gpio_mdio.c
+++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c
@@ -230,7 +230,7 @@ static int __devinit gpio_mdio_probe(struct platform_device *ofdev)
if (!priv)
goto out;
- new_bus = mdiobus_alloc();
+ new_bus = mdiobus_alloc(0);
if (!new_bus)
goto out_free_priv;
diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
index b6d69c9..ea71758 100644
--- a/drivers/net/ethernet/adi/bfin_mac.c
+++ b/drivers/net/ethernet/adi/bfin_mac.c
@@ -1659,7 +1659,7 @@ static int __devinit bfin_mii_bus_probe(struct platform_device *pdev)
}
rc = -ENOMEM;
- miibus = mdiobus_alloc();
+ miibus = mdiobus_alloc(0);
if (miibus == NULL)
goto out_err_alloc;
miibus->read = bfin_mdiobus_read;
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index c885aa9..c6bc550 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1326,7 +1326,7 @@ static int greth_mdio_init(struct greth_private *greth)
int ret, phy;
unsigned long timeout;
- greth->mdio = mdiobus_alloc();
+ greth->mdio = mdiobus_alloc(0);
if (!greth->mdio) {
return -ENOMEM;
}
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index cc9262b..5c30544 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1159,7 +1159,7 @@ static int __devinit au1000_probe(struct platform_device *pdev)
goto err_mdiobus_alloc;
}
- aup->mii_bus = mdiobus_alloc();
+ aup->mii_bus = mdiobus_alloc(0);
if (aup->mii_bus == NULL) {
dev_err(&pdev->dev, "failed to allocate mdiobus structure\n");
err = -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index a11a8ad..c847801 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1715,7 +1715,7 @@ static int __devinit bcm_enet_probe(struct platform_device *pdev)
/* MII bus registration */
if (priv->has_phy) {
- priv->mii_bus = mdiobus_alloc();
+ priv->mii_bus = mdiobus_alloc(0);
if (!priv->mii_bus) {
ret = -ENOMEM;
goto out_uninit_hw;
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 8fa7abc..4ff830e 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -2252,7 +2252,7 @@ static int sbmac_init(struct platform_device *pldev, long long base)
/* This is needed for PASS2 for Rx H/W checksum feature */
sbmac_set_iphdr_offset(sc);
- sc->mii_bus = mdiobus_alloc();
+ sc->mii_bus = mdiobus_alloc(0);
if (sc->mii_bus == NULL) {
err = -ENOMEM;
goto uninit_ctx;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 1979151..6ce2c4c 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1323,7 +1323,7 @@ static int tg3_mdio_init(struct tg3 *tp)
if (!tg3_flag(tp, USE_PHYLIB) || tg3_flag(tp, MDIOBUS_INITED))
return 0;
- tp->mdio_bus = mdiobus_alloc();
+ tp->mdio_bus = mdiobus_alloc(0);
if (tp->mdio_bus == NULL)
return -ENOMEM;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index a437b46..dc3b09e 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -234,7 +234,7 @@ static int macb_mii_init(struct macb *bp)
/* Enable management port */
macb_writel(bp, NCR, MACB_BIT(MPE));
- bp->mii_bus = mdiobus_alloc();
+ bp->mii_bus = mdiobus_alloc(0);
if (bp->mii_bus == NULL) {
err = -ENOMEM;
goto err_out;
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index ce88c0f..04a55a4 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -316,7 +316,7 @@ static int dnet_mii_init(struct dnet *bp)
{
int err, i;
- bp->mii_bus = mdiobus_alloc();
+ bp->mii_bus = mdiobus_alloc(0);
if (bp->mii_bus == NULL)
return -ENOMEM;
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 60f0e78..9916475 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1056,7 +1056,7 @@ static int __devinit ethoc_probe(struct platform_device *pdev)
ethoc_set_mac_address(netdev, netdev->dev_addr);
/* register MII bus */
- priv->mdio = mdiobus_alloc();
+ priv->mdio = mdiobus_alloc(0);
if (!priv->mdio) {
ret = -ENOMEM;
goto free;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index fb5579a..19fc332 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1248,7 +1248,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
priv->irq = irq;
/* initialize mdio bus */
- priv->mii_bus = mdiobus_alloc();
+ priv->mii_bus = mdiobus_alloc(0);
if (!priv->mii_bus) {
err = -EIO;
goto err_alloc_mdiobus;
diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c
index 01ee9cc..ab1d39c 100644
--- a/drivers/net/ethernet/freescale/fec.c
+++ b/drivers/net/ethernet/freescale/fec.c
@@ -1066,7 +1066,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
fep->phy_speed <<= 1;
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
- fep->mii_bus = mdiobus_alloc();
+ fep->mii_bus = mdiobus_alloc(0);
if (fep->mii_bus == NULL) {
err = -ENOMEM;
goto err_out;
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
index 360a578..f5918c1 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx_phy.c
@@ -70,7 +70,7 @@ static int mpc52xx_fec_mdio_probe(struct platform_device *of)
struct resource res;
int err;
- bus = mdiobus_alloc();
+ bus = mdiobus_alloc(0);
if (bus == NULL)
return -ENOMEM;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 55bb867..74964ce 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -116,7 +116,7 @@ static int __devinit fs_enet_mdio_probe(struct platform_device *ofdev)
return -EINVAL;
get_bus_freq = match->data;
- new_bus = mdiobus_alloc();
+ new_bus = mdiobus_alloc(0);
if (!new_bus)
goto out;
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index f109602..332418a 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -266,7 +266,7 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev)
if (!priv)
return -ENOMEM;
- new_bus = mdiobus_alloc();
+ new_bus = mdiobus_alloc(0);
if (!new_bus) {
err = -ENOMEM;
goto err_free_priv;
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 0b3567a..94a6055 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -425,7 +425,7 @@ ltq_etop_mdio_init(struct net_device *dev)
int i;
int err;
- priv->mii_bus = mdiobus_alloc();
+ priv->mii_bus = mdiobus_alloc(0);
if (!priv->mii_bus) {
netdev_err(dev, "failed to allocate mii bus\n");
err = -ENOMEM;
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index e87847e..250e0cc 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2604,7 +2604,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev)
* Set up and register SMI bus.
*/
if (pd == NULL || pd->shared_smi == NULL) {
- msp->smi_bus = mdiobus_alloc();
+ msp->smi_bus = mdiobus_alloc(0);
if (msp->smi_bus == NULL)
goto out_unmap;
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 5ec409e..2dfb98a 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1543,7 +1543,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
pep->timeout.function = rxq_refill_timer_wrapper;
pep->timeout.data = (unsigned long)pep;
- pep->smi_bus = mdiobus_alloc();
+ pep->smi_bus = mdiobus_alloc(0);
if (pep->smi_bus == NULL) {
err = -ENOMEM;
goto err_base;
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 4bf68cf..4175e57 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -1176,7 +1176,7 @@ static int __devinit r6040_init_one(struct pci_dev *pdev,
netif_napi_add(dev, &lp->napi, r6040_poll, 64);
- lp->mii_bus = mdiobus_alloc();
+ lp->mii_bus = mdiobus_alloc(0);
if (!lp->mii_bus) {
dev_err(&pdev->dev, "mdiobus_alloc() failed\n");
err = -ENOMEM;
diff --git a/drivers/net/ethernet/s6gmac.c b/drivers/net/ethernet/s6gmac.c
index a7ff8ea..d8f11ef 100644
--- a/drivers/net/ethernet/s6gmac.c
+++ b/drivers/net/ethernet/s6gmac.c
@@ -994,7 +994,7 @@ static int __devinit s6gmac_probe(struct platform_device *pdev)
dev->name);
goto errdev;
}
- mb = mdiobus_alloc();
+ mb = mdiobus_alloc(0);
if (!mb) {
printk(KERN_ERR DRV_PRMT "error allocating mii bus\n");
goto errmii;
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 06d0df6..103297b 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -1037,7 +1037,7 @@ static int __devinit smsc911x_mii_init(struct platform_device *pdev,
struct smsc911x_data *pdata = netdev_priv(dev);
int err = -ENXIO, i;
- pdata->mii_bus = mdiobus_alloc();
+ pdata->mii_bus = mdiobus_alloc(0);
if (!pdata->mii_bus) {
err = -ENOMEM;
goto err_out_1;
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index a9efbdf..16738a1 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -1205,7 +1205,7 @@ static int smsc9420_mii_init(struct net_device *dev)
struct smsc9420_pdata *pd = netdev_priv(dev);
int err = -ENXIO, i;
- pd->mii_bus = mdiobus_alloc();
+ pd->mii_bus = mdiobus_alloc(0);
if (!pd->mii_bus) {
err = -ENOMEM;
goto err_out_1;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 9c3b9d5..5dc0396 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -144,7 +144,7 @@ int stmmac_mdio_register(struct net_device *ndev)
if (!mdio_bus_data)
return 0;
- new_bus = mdiobus_alloc();
+ new_bus = mdiobus_alloc(0);
if (new_bus == NULL)
return -ENOMEM;
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index aaac0c7..b13df3c 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -1227,7 +1227,7 @@ int __devinit cpmac_init(void)
u32 mask;
int i, res;
- cpmac_mii = mdiobus_alloc();
+ cpmac_mii = mdiobus_alloc(0);
if (cpmac_mii == NULL)
return -ENOMEM;
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 7615040..fffddef 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -300,7 +300,7 @@ static int __devinit davinci_mdio_probe(struct platform_device *pdev)
data->pdata = pdata ? (*pdata) : default_pdata;
- data->bus = mdiobus_alloc();
+ data->bus = mdiobus_alloc(0);
if (!data->bus) {
dev_err(dev, "failed to alloc mii bus\n");
ret = -ENOMEM;
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 71b785c..4538908 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -673,7 +673,7 @@ static int tc_mii_init(struct net_device *dev)
int err;
int i;
- lp->mii_bus = mdiobus_alloc();
+ lp->mii_bus = mdiobus_alloc(0);
if (lp->mii_bus == NULL) {
err = -ENOMEM;
goto err_out;
diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
index 8cf9d4f..7d0ebf5 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
@@ -81,7 +81,7 @@ int temac_mdio_setup(struct temac_local *lp, struct device_node *np)
temac_indirect_out32(lp, XTE_MC_OFFSET, 1 << 6 | clk_div);
mutex_unlock(&lp->indirect_mutex);
- bus = mdiobus_alloc();
+ bus = mdiobus_alloc(0);
if (!bus)
return -ENOMEM;
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index dca6541..4ecd7ac 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -861,7 +861,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
out_be32(lp->base_addr + XEL_MDIOCTRL_OFFSET,
XEL_MDIOCTRL_MDIOEN_MASK);
- bus = mdiobus_alloc();
+ bus = mdiobus_alloc(0);
if (!bus)
return -ENOMEM;
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index f45c85a..43b4892 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -509,7 +509,7 @@ static int ixp4xx_mdio_register(void)
{
int err;
- if (!(mdio_bus = mdiobus_alloc()))
+ if (!(mdio_bus = mdiobus_alloc(0)))
return -ENOMEM;
if (cpu_is_ixp43x()) {
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index 1fa4d73..18e838e 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -214,7 +214,7 @@ static int __init fixed_mdio_bus_init(void)
goto err_pdev;
}
- fmb->mii_bus = mdiobus_alloc();
+ fmb->mii_bus = mdiobus_alloc(0);
if (fmb->mii_bus == NULL) {
ret = -ENOMEM;
goto err_mdiobus_reg;
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index daec9b0..097cf50 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -214,7 +214,7 @@ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
{
struct mii_bus *bus;
- bus = mdiobus_alloc();
+ bus = mdiobus_alloc(0);
if (!bus)
return NULL;
diff --git a/drivers/net/phy/mdio-octeon.c b/drivers/net/phy/mdio-octeon.c
index bd12ba9..4c68668 100644
--- a/drivers/net/phy/mdio-octeon.c
+++ b/drivers/net/phy/mdio-octeon.c
@@ -99,7 +99,7 @@ static int __devinit octeon_mdiobus_probe(struct platform_device *pdev)
/* The platform_device id is our unit number. */
bus->unit = pdev->id;
- bus->mii_bus = mdiobus_alloc();
+ bus->mii_bus = mdiobus_alloc(0);
if (!bus->mii_bus)
goto err;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 6c58da2..e6fd35d 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -41,14 +41,28 @@
*
* Description: called by a bus driver to allocate an mii_bus
* structure to fill in.
+ *
+ * 'size' is an an extra amount of memory to allocate for private storage.
+ * If non-zero, then bus->priv is points to that memory.
*/
-struct mii_bus *mdiobus_alloc(void)
+struct mii_bus *mdiobus_alloc(size_t size)
{
struct mii_bus *bus;
+ size_t aligned_size = ALIGN(sizeof(*bus), NETDEV_ALIGN);
+ size_t alloc_size;
+
+ /* If we alloc extra space, it should be aligned */
+ if (size)
+ alloc_size = aligned_size + size;
+ else
+ alloc_size = sizeof(*bus);
- bus = kzalloc(sizeof(*bus), GFP_KERNEL);
- if (bus != NULL)
+ bus = kzalloc(alloc_size, GFP_KERNEL);
+ if (bus) {
bus->state = MDIOBUS_ALLOCATED;
+ if (size)
+ bus->priv = (void *)bus + aligned_size;
+ }
return bus;
}
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index 0c1c6ca..1f5a2f9 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -5396,7 +5396,7 @@ static int __devinit et131x_pci_setup(struct pci_dev *pdev,
et1310_disable_phy_coma(adapter);
/* Setup the mii_bus struct */
- adapter->mii_bus = mdiobus_alloc();
+ adapter->mii_bus = mdiobus_alloc(0);
if (!adapter->mii_bus) {
dev_err(&pdev->dev, "Alloc of mii_bus struct failed\n");
goto err_mem_free;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 79f337c..603153f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -129,7 +129,7 @@ struct mii_bus {
};
#define to_mii_bus(d) container_of(d, struct mii_bus, dev)
-struct mii_bus *mdiobus_alloc(void);
+struct mii_bus *mdiobus_alloc(size_t size);
int mdiobus_register(struct mii_bus *bus);
void mdiobus_unregister(struct mii_bus *bus);
void mdiobus_free(struct mii_bus *bus);
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 88e7c2f..dd0e270 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -154,7 +154,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index,
if (ret < 0)
goto out;
- ds->slave_mii_bus = mdiobus_alloc();
+ ds->slave_mii_bus = mdiobus_alloc(0);
if (ds->slave_mii_bus == NULL) {
ret = -ENOMEM;
goto out;
--
1.7.3.4
^ permalink raw reply related
* Re: [PATCH 2/2] Explicitly call tcp creation and init from memcontrol.c
From: David Miller @ 2011-12-15 16:57 UTC (permalink / raw)
To: kamezawa.hiroyu; +Cc: glommer, linux-kernel, netdev, cgroups, eric.dumazet, sfr
In-Reply-To: <20111216011316.8d58bc8f.kamezawa.hiroyu@jp.fujitsu.com>
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Fri, 16 Dec 2011 01:13:16 +0900
> Could you remake the patch onto the 'latest' linux-next ?
> As Dave mentioned, some bandaids are already applied and this patch hunks.
He was correct to submit this against net-next.
The bandaid in linux-next is temporary and Stephen will remove it
once we fix things properly in net-next.
^ permalink raw reply
* [PATCH 0/7] SUNRPC: register services with per-net rpcbind
From: Stanislav Kinsbursky @ 2011-12-15 16:59 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
This patch set makes service registered with per-net rpcbind and required for
making Lockd and NFSd services able to handle requests from and to different
network namespaces.
The following series consists of:
---
Stanislav Kinsbursky (7):
SUNRPC: create rpcbind client in passed network namespace context
SUNRPC: register rpcbind programs in passed network namespase context
SUNRPC: use proper network namespace in rpcbind RPCBPROC_GETADDR procedure
SUNRPC: parametrize local rpcbind clients creation with net ns
SUNRPC: pass network namespace to service registering routines
SUNRPC: register service on creation in current network namespace
SUNRPC: unregister service on creation in current network namespace
fs/nfsd/nfssvc.c | 4 +--
include/linux/sunrpc/clnt.h | 9 ++++--
include/linux/sunrpc/svc.h | 11 ++++----
net/sunrpc/rpcb_clnt.c | 29 +++++++++++---------
net/sunrpc/svc.c | 61 +++++++++++++++++++++++--------------------
net/sunrpc/svcsock.c | 3 +-
6 files changed, 63 insertions(+), 54 deletions(-)
--
Signature
^ permalink raw reply
* [PATCH 1/7] SUNRPC: create rpcbind client in passed network namespace context
From: Stanislav Kinsbursky @ 2011-12-15 16:59 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111215155252.2434.39434.stgit@localhost6.localdomain6>
Rpcbind clients are per network namespace.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
net/sunrpc/rpcb_clnt.c | 11 ++++++-----
1 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 46f5915..43eff03 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -344,11 +344,12 @@ out:
return result;
}
-static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
- size_t salen, int proto, u32 version)
+static struct rpc_clnt *rpcb_create(struct net *net, char *hostname,
+ struct sockaddr *srvaddr, size_t salen,
+ int proto, u32 version)
{
struct rpc_create_args args = {
- .net = &init_net,
+ .net = net,
.protocol = proto,
.address = srvaddr,
.addrsize = salen,
@@ -708,8 +709,8 @@ void rpcb_getport_async(struct rpc_task *task)
dprintk("RPC: %5u %s: trying rpcbind version %u\n",
task->tk_pid, __func__, bind_version);
- rpcb_clnt = rpcb_create(clnt->cl_server, sap, salen, xprt->prot,
- bind_version);
+ rpcb_clnt = rpcb_create(xprt->xprt_net, clnt->cl_server, sap, salen,
+ xprt->prot, bind_version);
if (IS_ERR(rpcb_clnt)) {
status = PTR_ERR(rpcb_clnt);
dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n",
^ permalink raw reply related
* Re: [PATCH 1/2] Move limit definitions outside CONFIG_INET
From: David Miller @ 2011-12-15 16:59 UTC (permalink / raw)
To: glommer-bzQdu9zFT3WakBO8gow8eQ
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, cgroups-u79uwXL29TY76Z2rM5mHXA,
kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A,
eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w, sfr-3FnU+UHB4dNDw9hX6IcOSA
In-Reply-To: <1323941672-14324-2-git-send-email-glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
From: Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
Date: Thu, 15 Dec 2011 13:34:31 +0400
> They need to be available for other protocols as well, since
> they are used in sock.c openly
>
> Signed-off-by: Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>
Applied.
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 2/7] SUNRPC: register rpcbind programs in passed network namespase context
From: Stanislav Kinsbursky @ 2011-12-15 16:59 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111215155252.2434.39434.stgit@localhost6.localdomain6>
Registering rpcbind program requires rpcbind clients, which are per network
namespace context.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
include/linux/sunrpc/clnt.h | 5 +++--
net/sunrpc/rpcb_clnt.c | 8 ++++----
net/sunrpc/svc.c | 10 +++++-----
3 files changed, 12 insertions(+), 11 deletions(-)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 53afa56..1e56469 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -138,8 +138,9 @@ void rpc_task_release_client(struct rpc_task *);
int rpcb_create_local(void);
void rpcb_put_local(void);
-int rpcb_register(u32, u32, int, unsigned short);
-int rpcb_v4_register(const u32 program, const u32 version,
+int rpcb_register(struct net *, u32, u32, int, unsigned short);
+int rpcb_v4_register(struct net *net, const u32 program,
+ const u32 version,
const struct sockaddr *address,
const char *netid);
void rpcb_getport_async(struct rpc_task *);
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 43eff03..ea87b0c 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -425,7 +425,7 @@ static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg)
* IN6ADDR_ANY (ie available for all AF_INET and AF_INET6
* addresses).
*/
-int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port)
+int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short port)
{
struct rpcbind_args map = {
.r_prog = prog,
@@ -436,7 +436,7 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port)
struct rpc_message msg = {
.rpc_argp = &map,
};
- struct sunrpc_net *sn = net_generic(&init_net, sunrpc_net_id);
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
dprintk("RPC: %sregistering (%u, %u, %d, %u) with local "
"rpcbind\n", (port ? "" : "un"),
@@ -563,7 +563,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn,
* service on any IPv4 address, but not on IPv6. The latter
* advertises the service on all IPv4 and IPv6 addresses.
*/
-int rpcb_v4_register(const u32 program, const u32 version,
+int rpcb_v4_register(struct net *net, const u32 program, const u32 version,
const struct sockaddr *address, const char *netid)
{
struct rpcbind_args map = {
@@ -575,7 +575,7 @@ int rpcb_v4_register(const u32 program, const u32 version,
struct rpc_message msg = {
.rpc_argp = &map,
};
- struct sunrpc_net *sn = net_generic(&init_net, sunrpc_net_id);
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
if (sn->rpcb_local_clnt4 == NULL)
return -EPROTONOSUPPORT;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 6e03888..e9c42ad 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -813,7 +813,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
return -ENOPROTOOPT;
}
- error = rpcb_v4_register(program, version,
+ error = rpcb_v4_register(&init_net, program, version,
(const struct sockaddr *)&sin, netid);
/*
@@ -821,7 +821,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
* registration request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
- error = rpcb_register(program, version, protocol, port);
+ error = rpcb_register(&init_net, program, version, protocol, port);
return error;
}
@@ -860,7 +860,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
return -ENOPROTOOPT;
}
- error = rpcb_v4_register(program, version,
+ error = rpcb_v4_register(&init_net, program, version,
(const struct sockaddr *)&sin6, netid);
/*
@@ -963,14 +963,14 @@ static void __svc_unregister(const u32 program, const u32 version,
{
int error;
- error = rpcb_v4_register(program, version, NULL, "");
+ error = rpcb_v4_register(&init_net, program, version, NULL, "");
/*
* User space didn't support rpcbind v4, so retry this
* request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
- error = rpcb_register(program, version, 0, 0);
+ error = rpcb_register(&init_net, program, version, 0, 0);
dprintk("svc: %s(%sv%u), error %d\n",
__func__, progname, version, error);
^ permalink raw reply related
* [PATCH 3/7] SUNRPC: use proper network namespace in rpcbind RPCBPROC_GETADDR procedure
From: Stanislav Kinsbursky @ 2011-12-15 17:00 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111215155252.2434.39434.stgit@localhost6.localdomain6>
Pass request socket network namespace to rpc_uaddr2sockaddr() instead of
hardcoded init_net, when decoding address in RPCBPROC_GETADDR procedure.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
net/sunrpc/rpcb_clnt.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index ea87b0c..d94f188 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -935,7 +935,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid,
task->tk_msg.rpc_proc->p_name, (char *)p);
- if (rpc_uaddr2sockaddr(&init_net, (char *)p, len, sap, sizeof(address)) == 0)
+ if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len,
+ sap, sizeof(address)) == 0)
goto out_fail;
rpcb->r_port = rpc_get_port(sap);
^ permalink raw reply related
* [PATCH 4/7] SUNRPC: parametrize local rpcbind clients creation with net ns
From: Stanislav Kinsbursky @ 2011-12-15 17:00 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111215155252.2434.39434.stgit@localhost6.localdomain6>
These client are per network namespace and thus can be created for different
network namespaces.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
include/linux/sunrpc/clnt.h | 4 ++--
net/sunrpc/rpcb_clnt.c | 7 +++----
net/sunrpc/svc.c | 4 ++--
3 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 1e56469..5748807 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -136,8 +136,8 @@ void rpc_shutdown_client(struct rpc_clnt *);
void rpc_release_client(struct rpc_clnt *);
void rpc_task_release_client(struct rpc_task *);
-int rpcb_create_local(void);
-void rpcb_put_local(void);
+int rpcb_create_local(struct net *);
+void rpcb_put_local(struct net *);
int rpcb_register(struct net *, u32, u32, int, unsigned short);
int rpcb_v4_register(struct net *net, const u32 program,
const u32 version,
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index d94f188..4ce3a8e 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -175,9 +175,9 @@ static int rpcb_get_local(struct net *net)
return cnt;
}
-void rpcb_put_local(void)
+void rpcb_put_local(struct net *net)
{
- struct sunrpc_net *sn = net_generic(&init_net, sunrpc_net_id);
+ struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
struct rpc_clnt *clnt = sn->rpcb_local_clnt;
struct rpc_clnt *clnt4 = sn->rpcb_local_clnt4;
int shutdown;
@@ -323,11 +323,10 @@ out:
* Returns zero on success, otherwise a negative errno value
* is returned.
*/
-int rpcb_create_local(void)
+int rpcb_create_local(struct net *net)
{
static DEFINE_MUTEX(rpcb_create_local_mutex);
int result = 0;
- struct net *net = &init_net;
if (rpcb_get_local(net))
return result;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index e9c42ad..03e9f04 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -370,7 +370,7 @@ static int svc_rpcb_setup(struct svc_serv *serv)
{
int err;
- err = rpcb_create_local();
+ err = rpcb_create_local(&init_net);
if (err)
return err;
@@ -382,7 +382,7 @@ static int svc_rpcb_setup(struct svc_serv *serv)
void svc_rpcb_cleanup(struct svc_serv *serv)
{
svc_unregister(serv);
- rpcb_put_local();
+ rpcb_put_local(&init_net);
}
EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
^ permalink raw reply related
* [PATCH 5/7] SUNRPC: pass network namespace to service registering routines
From: Stanislav Kinsbursky @ 2011-12-15 17:00 UTC (permalink / raw)
To: Trond.Myklebust
Cc: linux-nfs, xemul, neilb, netdev, linux-kernel, jbottomley,
bfields, davem, devel
In-Reply-To: <20111215155252.2434.39434.stgit@localhost6.localdomain6>
Lockd and NFSd services will handle requests from and to many network
nsamespaces. And thus have to be registered and unregistered per network
namespace.
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
---
include/linux/sunrpc/svc.h | 2 +-
net/sunrpc/svc.c | 42 +++++++++++++++++++++++-------------------
net/sunrpc/svcsock.c | 3 ++-
3 files changed, 26 insertions(+), 21 deletions(-)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 35b37b1..d3563c2 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -428,7 +428,7 @@ void svc_destroy(struct svc_serv *);
int svc_process(struct svc_rqst *);
int bc_svc_process(struct svc_serv *, struct rpc_rqst *,
struct svc_rqst *);
-int svc_register(const struct svc_serv *, const int,
+int svc_register(const struct svc_serv *, struct net *, const int,
const unsigned short, const unsigned short);
void svc_wake_up(struct svc_serv *);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 03e9f04..137475a 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -30,7 +30,7 @@
#define RPCDBG_FACILITY RPCDBG_SVCDSP
-static void svc_unregister(const struct svc_serv *serv);
+static void svc_unregister(const struct svc_serv *serv, struct net *net);
#define svc_serv_is_pooled(serv) ((serv)->sv_function)
@@ -375,13 +375,13 @@ static int svc_rpcb_setup(struct svc_serv *serv)
return err;
/* Remove any stale portmap registrations */
- svc_unregister(serv);
+ svc_unregister(serv, &init_net);
return 0;
}
void svc_rpcb_cleanup(struct svc_serv *serv)
{
- svc_unregister(serv);
+ svc_unregister(serv, &init_net);
rpcb_put_local(&init_net);
}
EXPORT_SYMBOL_GPL(svc_rpcb_cleanup);
@@ -790,7 +790,8 @@ EXPORT_SYMBOL_GPL(svc_exit_thread);
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
-static int __svc_rpcb_register4(const u32 program, const u32 version,
+static int __svc_rpcb_register4(struct net *net, const u32 program,
+ const u32 version,
const unsigned short protocol,
const unsigned short port)
{
@@ -813,7 +814,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
return -ENOPROTOOPT;
}
- error = rpcb_v4_register(&init_net, program, version,
+ error = rpcb_v4_register(net, program, version,
(const struct sockaddr *)&sin, netid);
/*
@@ -821,7 +822,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
* registration request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
- error = rpcb_register(&init_net, program, version, protocol, port);
+ error = rpcb_register(net, program, version, protocol, port);
return error;
}
@@ -837,7 +838,8 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
-static int __svc_rpcb_register6(const u32 program, const u32 version,
+static int __svc_rpcb_register6(struct net *net, const u32 program,
+ const u32 version,
const unsigned short protocol,
const unsigned short port)
{
@@ -860,7 +862,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
return -ENOPROTOOPT;
}
- error = rpcb_v4_register(&init_net, program, version,
+ error = rpcb_v4_register(net, program, version,
(const struct sockaddr *)&sin6, netid);
/*
@@ -880,7 +882,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
* Returns zero on success; a negative errno value is returned
* if any error occurs.
*/
-static int __svc_register(const char *progname,
+static int __svc_register(struct net *net, const char *progname,
const u32 program, const u32 version,
const int family,
const unsigned short protocol,
@@ -890,12 +892,12 @@ static int __svc_register(const char *progname,
switch (family) {
case PF_INET:
- error = __svc_rpcb_register4(program, version,
+ error = __svc_rpcb_register4(net, program, version,
protocol, port);
break;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
case PF_INET6:
- error = __svc_rpcb_register6(program, version,
+ error = __svc_rpcb_register6(net, program, version,
protocol, port);
#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
}
@@ -909,14 +911,16 @@ static int __svc_register(const char *progname,
/**
* svc_register - register an RPC service with the local portmapper
* @serv: svc_serv struct for the service to register
+ * @net: net namespace for the service to register
* @family: protocol family of service's listener socket
* @proto: transport protocol number to advertise
* @port: port to advertise
*
* Service is registered for any address in the passed-in protocol family
*/
-int svc_register(const struct svc_serv *serv, const int family,
- const unsigned short proto, const unsigned short port)
+int svc_register(const struct svc_serv *serv, struct net *net,
+ const int family, const unsigned short proto,
+ const unsigned short port)
{
struct svc_program *progp;
unsigned int i;
@@ -941,7 +945,7 @@ int svc_register(const struct svc_serv *serv, const int family,
if (progp->pg_vers[i]->vs_hidden)
continue;
- error = __svc_register(progp->pg_name, progp->pg_prog,
+ error = __svc_register(net, progp->pg_name, progp->pg_prog,
i, family, proto, port);
if (error < 0)
break;
@@ -958,19 +962,19 @@ int svc_register(const struct svc_serv *serv, const int family,
* any "inet6" entries anyway. So a PMAP_UNSET should be sufficient
* in this case to clear all existing entries for [program, version].
*/
-static void __svc_unregister(const u32 program, const u32 version,
+static void __svc_unregister(struct net *net, const u32 program, const u32 version,
const char *progname)
{
int error;
- error = rpcb_v4_register(&init_net, program, version, NULL, "");
+ error = rpcb_v4_register(net, program, version, NULL, "");
/*
* User space didn't support rpcbind v4, so retry this
* request with the legacy rpcbind v2 protocol.
*/
if (error == -EPROTONOSUPPORT)
- error = rpcb_register(&init_net, program, version, 0, 0);
+ error = rpcb_register(net, program, version, 0, 0);
dprintk("svc: %s(%sv%u), error %d\n",
__func__, progname, version, error);
@@ -984,7 +988,7 @@ static void __svc_unregister(const u32 program, const u32 version,
* The result of unregistration is reported via dprintk for those who want
* verification of the result, but is otherwise not important.
*/
-static void svc_unregister(const struct svc_serv *serv)
+static void svc_unregister(const struct svc_serv *serv, struct net *net)
{
struct svc_program *progp;
unsigned long flags;
@@ -1001,7 +1005,7 @@ static void svc_unregister(const struct svc_serv *serv)
dprintk("svc: attempting to unregister %sv%u\n",
progp->pg_name, i);
- __svc_unregister(progp->pg_prog, i, progp->pg_name);
+ __svc_unregister(net, progp->pg_prog, i, progp->pg_name);
}
}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 277909e..110735f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1409,7 +1409,8 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
/* Register socket with portmapper */
if (*errp >= 0 && pmap_register)
- *errp = svc_register(serv, inet->sk_family, inet->sk_protocol,
+ *errp = svc_register(serv, sock->sk->sk_net, inet->sk_family,
+ inet->sk_protocol,
ntohs(inet_sk(inet)->inet_sport));
if (*errp < 0) {
^ permalink raw reply related
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