kernel_optimize_test/fs/proc/proc_net.c

241 lines
4.5 KiB
C
Raw Normal View History

/*
* linux/fs/proc/net.c
*
* Copyright (C) 2007
*
* Author: Eric Biederman <ebiederm@xmission.com>
*
* proc net directory handling functions
*/
#include <asm/uaccess.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/smp_lock.h>
#include <linux/mount.h>
#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <linux/seq_file.h>
#include "internal.h"
static struct net *get_proc_net(const struct inode *inode)
{
return maybe_get_net(PDE_NET(PDE(inode)));
}
int seq_open_net(struct inode *ino, struct file *f,
const struct seq_operations *ops, int size)
{
struct net *net;
struct seq_net_private *p;
BUG_ON(size < sizeof(*p));
net = get_proc_net(ino);
if (net == NULL)
return -ENXIO;
p = __seq_open_private(f, ops, size);
if (p == NULL) {
put_net(net);
return -ENOMEM;
}
#ifdef CONFIG_NET_NS
p->net = net;
#endif
return 0;
}
EXPORT_SYMBOL_GPL(seq_open_net);
int single_open_net(struct inode *inode, struct file *file,
int (*show)(struct seq_file *, void *))
{
int err;
struct net *net;
err = -ENXIO;
net = get_proc_net(inode);
if (net == NULL)
goto err_net;
err = single_open(file, show, net);
if (err < 0)
goto err_open;
return 0;
err_open:
put_net(net);
err_net:
return err;
}
EXPORT_SYMBOL_GPL(single_open_net);
int seq_release_net(struct inode *ino, struct file *f)
{
struct seq_file *seq;
seq = f->private_data;
put_net(seq_file_net(seq));
seq_release_private(ino, f);
return 0;
}
EXPORT_SYMBOL_GPL(seq_release_net);
int single_release_net(struct inode *ino, struct file *f)
{
struct seq_file *seq = f->private_data;
put_net(seq->private);
return single_release(ino, f);
}
EXPORT_SYMBOL_GPL(single_release_net);
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
static struct net *get_proc_task_net(struct inode *dir)
{
struct task_struct *task;
struct nsproxy *ns;
struct net *net = NULL;
rcu_read_lock();
task = pid_task(proc_pid(dir), PIDTYPE_PID);
if (task != NULL) {
ns = task_nsproxy(task);
if (ns != NULL)
net = get_net(ns->net_ns);
}
rcu_read_unlock();
return net;
}
static struct dentry *proc_tgid_net_lookup(struct inode *dir,
struct dentry *dentry, struct nameidata *nd)
{
struct dentry *de;
struct net *net;
de = ERR_PTR(-ENOENT);
net = get_proc_task_net(dir);
if (net != NULL) {
de = proc_lookup_de(net->proc_net, dir, dentry);
put_net(net);
}
return de;
}
static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct net *net;
net = get_proc_task_net(inode);
generic_fillattr(inode, stat);
if (net != NULL) {
stat->nlink = net->proc_net->nlink;
put_net(net);
}
return 0;
}
const struct inode_operations proc_net_inode_operations = {
.lookup = proc_tgid_net_lookup,
.getattr = proc_tgid_net_getattr,
};
static int proc_tgid_net_readdir(struct file *filp, void *dirent,
filldir_t filldir)
{
int ret;
struct net *net;
ret = -EINVAL;
net = get_proc_task_net(filp->f_path.dentry->d_inode);
if (net != NULL) {
ret = proc_readdir_de(net->proc_net, filp, dirent, filldir);
put_net(net);
}
return ret;
}
const struct file_operations proc_net_operations = {
.read = generic_read_dir,
.readdir = proc_tgid_net_readdir,
};
struct proc_dir_entry *proc_net_fops_create(struct net *net,
const char *name, mode_t mode, const struct file_operations *fops)
{
proc: fix ->open'less usage due to ->proc_fops flip Typical PDE creation code looks like: pde = create_proc_entry("foo", 0, NULL); if (pde) pde->proc_fops = &foo_proc_fops; Notice that PDE is first created, only then ->proc_fops is set up to final value. This is a problem because right after creation a) PDE is fully visible in /proc , and b) ->proc_fops are proc_file_operations which do not have ->open callback. So, it's possible to ->read without ->open (see one class of oopses below). The fix is new API called proc_create() which makes sure ->proc_fops are set up before gluing PDE to main tree. Typical new code looks like: pde = proc_create("foo", 0, NULL, &foo_proc_fops); if (!pde) return -ENOMEM; Fix most networking users for a start. In the long run, create_proc_entry() for regular files will go. BUG: unable to handle kernel NULL pointer dereference at virtual address 00000024 printing eip: c1188c1b *pdpt = 000000002929e001 *pde = 0000000000000000 Oops: 0002 [#1] PREEMPT SMP DEBUG_PAGEALLOC last sysfs file: /sys/block/sda/sda1/dev Modules linked in: foo af_packet ipv6 cpufreq_ondemand loop serio_raw psmouse k8temp hwmon sr_mod cdrom Pid: 24679, comm: cat Not tainted (2.6.24-rc3-mm1 #2) EIP: 0060:[<c1188c1b>] EFLAGS: 00210002 CPU: 0 EIP is at mutex_lock_nested+0x75/0x25d EAX: 000006fe EBX: fffffffb ECX: 00001000 EDX: e9340570 ESI: 00000020 EDI: 00200246 EBP: e9340570 ESP: e8ea1ef8 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 Process cat (pid: 24679, ti=E8EA1000 task=E9340570 task.ti=E8EA1000) Stack: 00000000 c106f7ce e8ee05b4 00000000 00000001 458003d0 f6fb6f20 fffffffb 00000000 c106f7aa 00001000 c106f7ce 08ae9000 f6db53f0 00000020 00200246 00000000 00000002 00000000 00200246 00200246 e8ee05a0 fffffffb e8ee0550 Call Trace: [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c106f7ce>] seq_read+0x24/0x28a [<c106f7aa>] seq_read+0x0/0x28a [<c10818b8>] proc_reg_read+0x60/0x73 [<c1081858>] proc_reg_read+0x0/0x73 [<c105a34f>] vfs_read+0x6c/0x8b [<c105a6f3>] sys_read+0x3c/0x63 [<c10025f2>] sysenter_past_esp+0x5f/0xa5 [<c10697a7>] destroy_inode+0x24/0x33 ======================= INFO: lockdep is turned off. Code: 75 21 68 e1 1a 19 c1 68 87 00 00 00 68 b8 e8 1f c1 68 25 73 1f c1 e8 84 06 e9 ff e8 52 b8 e7 ff 83 c4 10 9c 5f fa e8 28 89 ea ff <f0> fe 4e 04 79 0a f3 90 80 7e 04 00 7e f8 eb f0 39 76 34 74 33 EIP: [<c1188c1b>] mutex_lock_nested+0x75/0x25d SS:ESP 0068:e8ea1ef8 [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:18:37 +08:00
return proc_create(name, mode, net->proc_net, fops);
}
EXPORT_SYMBOL_GPL(proc_net_fops_create);
void proc_net_remove(struct net *net, const char *name)
{
remove_proc_entry(name, net->proc_net);
}
EXPORT_SYMBOL_GPL(proc_net_remove);
static __net_init int proc_net_ns_init(struct net *net)
{
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
struct proc_dir_entry *netd, *net_statd;
int err;
err = -ENOMEM;
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
netd = kzalloc(sizeof(*netd), GFP_KERNEL);
if (!netd)
goto out;
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
netd->data = net;
netd->nlink = 2;
netd->name = "net";
netd->namelen = 3;
netd->parent = &proc_root;
err = -EEXIST;
net_statd = proc_net_mkdir(net, "stat", netd);
if (!net_statd)
goto free_net;
net->proc_net = netd;
net->proc_net_stat = net_statd;
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
return 0;
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
free_net:
kfree(netd);
out:
return err;
}
static __net_exit void proc_net_ns_exit(struct net *net)
{
remove_proc_entry("stat", net->proc_net);
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
kfree(net->proc_net);
}
static struct pernet_operations __net_initdata proc_net_ns_ops = {
.init = proc_net_ns_init,
.exit = proc_net_ns_exit,
};
int __init proc_net_init(void)
{
[NET]: Make /proc/net a symlink on /proc/self/net (v3) Current /proc/net is done with so called "shadows", but current implementation is broken and has little chances to get fixed. The problem is that dentries subtree of /proc/net directory has fancy revalidation rules to make processes living in different net namespaces see different entries in /proc/net subtree, but currently, tasks see in the /proc/net subdir the contents of any other namespace, depending on who opened the file first. The proposed fix is to turn /proc/net into a symlink, which points to /proc/self/net, which in turn shows what previously was in /proc/net - the network-related info, from the net namespace the appropriate task lives in. # ls -l /proc/net lrwxrwxrwx 1 root root 8 Mar 5 15:17 /proc/net -> self/net In other words - this behaves like /proc/mounts, but unlike "mounts", "net" is not a file, but a directory. Changes from v2: * Fixed discrepancy of /proc/net nlink count and selinux labeling screwup pointed out by Stephen. To get the correct nlink count the ->getattr callback for /proc/net is overridden to read one from the net->proc_net entry. To make selinux still work the net->proc_net entry is initialized properly, i.e. with the "net" name and the proc_net parent. Selinux fixes are Acked-by: Stephen Smalley <sds@tycho.nsa.gov> Changes from v1: * Fixed a task_struct leak in get_proc_task_net, pointed out by Paul. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-08 03:08:40 +08:00
proc_symlink("net", NULL, "self/net");
return register_pernet_subsys(&proc_net_ns_ops);
}