![Tejun Heo](/assets/img/avatar_default.png)
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
529 lines
12 KiB
C
529 lines
12 KiB
C
/* (C) 1999-2001 Paul `Rusty' Russell
|
|
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/netfilter.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/module.h>
|
|
#include <linux/skbuff.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/netdevice.h>
|
|
#include <net/net_namespace.h>
|
|
#ifdef CONFIG_SYSCTL
|
|
#include <linux/sysctl.h>
|
|
#endif
|
|
|
|
#include <net/netfilter/nf_conntrack.h>
|
|
#include <net/netfilter/nf_conntrack_core.h>
|
|
#include <net/netfilter/nf_conntrack_l3proto.h>
|
|
#include <net/netfilter/nf_conntrack_l4proto.h>
|
|
#include <net/netfilter/nf_conntrack_expect.h>
|
|
#include <net/netfilter/nf_conntrack_helper.h>
|
|
#include <net/netfilter/nf_conntrack_acct.h>
|
|
#include <net/netfilter/nf_conntrack_zones.h>
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
int
|
|
print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
|
|
const struct nf_conntrack_l3proto *l3proto,
|
|
const struct nf_conntrack_l4proto *l4proto)
|
|
{
|
|
return l3proto->print_tuple(s, tuple) || l4proto->print_tuple(s, tuple);
|
|
}
|
|
EXPORT_SYMBOL_GPL(print_tuple);
|
|
|
|
struct ct_iter_state {
|
|
struct seq_net_private p;
|
|
unsigned int bucket;
|
|
};
|
|
|
|
static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
|
|
{
|
|
struct net *net = seq_file_net(seq);
|
|
struct ct_iter_state *st = seq->private;
|
|
struct hlist_nulls_node *n;
|
|
|
|
for (st->bucket = 0;
|
|
st->bucket < net->ct.htable_size;
|
|
st->bucket++) {
|
|
n = rcu_dereference(net->ct.hash[st->bucket].first);
|
|
if (!is_a_nulls(n))
|
|
return n;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
|
|
struct hlist_nulls_node *head)
|
|
{
|
|
struct net *net = seq_file_net(seq);
|
|
struct ct_iter_state *st = seq->private;
|
|
|
|
head = rcu_dereference(head->next);
|
|
while (is_a_nulls(head)) {
|
|
if (likely(get_nulls_value(head) == st->bucket)) {
|
|
if (++st->bucket >= net->ct.htable_size)
|
|
return NULL;
|
|
}
|
|
head = rcu_dereference(net->ct.hash[st->bucket].first);
|
|
}
|
|
return head;
|
|
}
|
|
|
|
static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos)
|
|
{
|
|
struct hlist_nulls_node *head = ct_get_first(seq);
|
|
|
|
if (head)
|
|
while (pos && (head = ct_get_next(seq, head)))
|
|
pos--;
|
|
return pos ? NULL : head;
|
|
}
|
|
|
|
static void *ct_seq_start(struct seq_file *seq, loff_t *pos)
|
|
__acquires(RCU)
|
|
{
|
|
rcu_read_lock();
|
|
return ct_get_idx(seq, *pos);
|
|
}
|
|
|
|
static void *ct_seq_next(struct seq_file *s, void *v, loff_t *pos)
|
|
{
|
|
(*pos)++;
|
|
return ct_get_next(s, v);
|
|
}
|
|
|
|
static void ct_seq_stop(struct seq_file *s, void *v)
|
|
__releases(RCU)
|
|
{
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* return 0 on success, 1 in case of error */
|
|
static int ct_seq_show(struct seq_file *s, void *v)
|
|
{
|
|
struct nf_conntrack_tuple_hash *hash = v;
|
|
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
|
|
const struct nf_conntrack_l3proto *l3proto;
|
|
const struct nf_conntrack_l4proto *l4proto;
|
|
int ret = 0;
|
|
|
|
NF_CT_ASSERT(ct);
|
|
if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
|
|
return 0;
|
|
|
|
/* we only want to print DIR_ORIGINAL */
|
|
if (NF_CT_DIRECTION(hash))
|
|
goto release;
|
|
|
|
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
|
|
NF_CT_ASSERT(l3proto);
|
|
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
|
|
NF_CT_ASSERT(l4proto);
|
|
|
|
ret = -ENOSPC;
|
|
if (seq_printf(s, "%-8s %u %-8s %u %ld ",
|
|
l3proto->name, nf_ct_l3num(ct),
|
|
l4proto->name, nf_ct_protonum(ct),
|
|
timer_pending(&ct->timeout)
|
|
? (long)(ct->timeout.expires - jiffies)/HZ : 0) != 0)
|
|
goto release;
|
|
|
|
if (l4proto->print_conntrack && l4proto->print_conntrack(s, ct))
|
|
goto release;
|
|
|
|
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
|
|
l3proto, l4proto))
|
|
goto release;
|
|
|
|
if (seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL))
|
|
goto release;
|
|
|
|
if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
|
|
if (seq_printf(s, "[UNREPLIED] "))
|
|
goto release;
|
|
|
|
if (print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
|
|
l3proto, l4proto))
|
|
goto release;
|
|
|
|
if (seq_print_acct(s, ct, IP_CT_DIR_REPLY))
|
|
goto release;
|
|
|
|
if (test_bit(IPS_ASSURED_BIT, &ct->status))
|
|
if (seq_printf(s, "[ASSURED] "))
|
|
goto release;
|
|
|
|
#if defined(CONFIG_NF_CONNTRACK_MARK)
|
|
if (seq_printf(s, "mark=%u ", ct->mark))
|
|
goto release;
|
|
#endif
|
|
|
|
#ifdef CONFIG_NF_CONNTRACK_SECMARK
|
|
if (seq_printf(s, "secmark=%u ", ct->secmark))
|
|
goto release;
|
|
#endif
|
|
|
|
#ifdef CONFIG_NF_CONNTRACK_ZONES
|
|
if (seq_printf(s, "zone=%u ", nf_ct_zone(ct)))
|
|
goto release;
|
|
#endif
|
|
|
|
if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
|
|
goto release;
|
|
|
|
ret = 0;
|
|
release:
|
|
nf_ct_put(ct);
|
|
return 0;
|
|
}
|
|
|
|
static const struct seq_operations ct_seq_ops = {
|
|
.start = ct_seq_start,
|
|
.next = ct_seq_next,
|
|
.stop = ct_seq_stop,
|
|
.show = ct_seq_show
|
|
};
|
|
|
|
static int ct_open(struct inode *inode, struct file *file)
|
|
{
|
|
return seq_open_net(inode, file, &ct_seq_ops,
|
|
sizeof(struct ct_iter_state));
|
|
}
|
|
|
|
static const struct file_operations ct_file_ops = {
|
|
.owner = THIS_MODULE,
|
|
.open = ct_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = seq_release_net,
|
|
};
|
|
|
|
static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos)
|
|
{
|
|
struct net *net = seq_file_net(seq);
|
|
int cpu;
|
|
|
|
if (*pos == 0)
|
|
return SEQ_START_TOKEN;
|
|
|
|
for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) {
|
|
if (!cpu_possible(cpu))
|
|
continue;
|
|
*pos = cpu + 1;
|
|
return per_cpu_ptr(net->ct.stat, cpu);
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
|
|
{
|
|
struct net *net = seq_file_net(seq);
|
|
int cpu;
|
|
|
|
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
|
|
if (!cpu_possible(cpu))
|
|
continue;
|
|
*pos = cpu + 1;
|
|
return per_cpu_ptr(net->ct.stat, cpu);
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
static void ct_cpu_seq_stop(struct seq_file *seq, void *v)
|
|
{
|
|
}
|
|
|
|
static int ct_cpu_seq_show(struct seq_file *seq, void *v)
|
|
{
|
|
struct net *net = seq_file_net(seq);
|
|
unsigned int nr_conntracks = atomic_read(&net->ct.count);
|
|
const struct ip_conntrack_stat *st = v;
|
|
|
|
if (v == SEQ_START_TOKEN) {
|
|
seq_printf(seq, "entries searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete\n");
|
|
return 0;
|
|
}
|
|
|
|
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x "
|
|
"%08x %08x %08x %08x %08x %08x %08x %08x \n",
|
|
nr_conntracks,
|
|
st->searched,
|
|
st->found,
|
|
st->new,
|
|
st->invalid,
|
|
st->ignore,
|
|
st->delete,
|
|
st->delete_list,
|
|
st->insert,
|
|
st->insert_failed,
|
|
st->drop,
|
|
st->early_drop,
|
|
st->error,
|
|
|
|
st->expect_new,
|
|
st->expect_create,
|
|
st->expect_delete
|
|
);
|
|
return 0;
|
|
}
|
|
|
|
static const struct seq_operations ct_cpu_seq_ops = {
|
|
.start = ct_cpu_seq_start,
|
|
.next = ct_cpu_seq_next,
|
|
.stop = ct_cpu_seq_stop,
|
|
.show = ct_cpu_seq_show,
|
|
};
|
|
|
|
static int ct_cpu_seq_open(struct inode *inode, struct file *file)
|
|
{
|
|
return seq_open_net(inode, file, &ct_cpu_seq_ops,
|
|
sizeof(struct seq_net_private));
|
|
}
|
|
|
|
static const struct file_operations ct_cpu_seq_fops = {
|
|
.owner = THIS_MODULE,
|
|
.open = ct_cpu_seq_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = seq_release_net,
|
|
};
|
|
|
|
static int nf_conntrack_standalone_init_proc(struct net *net)
|
|
{
|
|
struct proc_dir_entry *pde;
|
|
|
|
pde = proc_net_fops_create(net, "nf_conntrack", 0440, &ct_file_ops);
|
|
if (!pde)
|
|
goto out_nf_conntrack;
|
|
|
|
pde = proc_create("nf_conntrack", S_IRUGO, net->proc_net_stat,
|
|
&ct_cpu_seq_fops);
|
|
if (!pde)
|
|
goto out_stat_nf_conntrack;
|
|
return 0;
|
|
|
|
out_stat_nf_conntrack:
|
|
proc_net_remove(net, "nf_conntrack");
|
|
out_nf_conntrack:
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void nf_conntrack_standalone_fini_proc(struct net *net)
|
|
{
|
|
remove_proc_entry("nf_conntrack", net->proc_net_stat);
|
|
proc_net_remove(net, "nf_conntrack");
|
|
}
|
|
#else
|
|
static int nf_conntrack_standalone_init_proc(struct net *net)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void nf_conntrack_standalone_fini_proc(struct net *net)
|
|
{
|
|
}
|
|
#endif /* CONFIG_PROC_FS */
|
|
|
|
/* Sysctl support */
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
/* Log invalid packets of a given protocol */
|
|
static int log_invalid_proto_min = 0;
|
|
static int log_invalid_proto_max = 255;
|
|
|
|
static struct ctl_table_header *nf_ct_netfilter_header;
|
|
|
|
static ctl_table nf_ct_sysctl_table[] = {
|
|
{
|
|
.procname = "nf_conntrack_max",
|
|
.data = &nf_conntrack_max,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{
|
|
.procname = "nf_conntrack_count",
|
|
.data = &init_net.ct.count,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0444,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{
|
|
.procname = "nf_conntrack_buckets",
|
|
.data = &init_net.ct.htable_size,
|
|
.maxlen = sizeof(unsigned int),
|
|
.mode = 0444,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{
|
|
.procname = "nf_conntrack_checksum",
|
|
.data = &init_net.ct.sysctl_checksum,
|
|
.maxlen = sizeof(unsigned int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{
|
|
.procname = "nf_conntrack_log_invalid",
|
|
.data = &init_net.ct.sysctl_log_invalid,
|
|
.maxlen = sizeof(unsigned int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec_minmax,
|
|
.extra1 = &log_invalid_proto_min,
|
|
.extra2 = &log_invalid_proto_max,
|
|
},
|
|
{
|
|
.procname = "nf_conntrack_expect_max",
|
|
.data = &nf_ct_expect_max,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{ }
|
|
};
|
|
|
|
#define NET_NF_CONNTRACK_MAX 2089
|
|
|
|
static ctl_table nf_ct_netfilter_table[] = {
|
|
{
|
|
.procname = "nf_conntrack_max",
|
|
.data = &nf_conntrack_max,
|
|
.maxlen = sizeof(int),
|
|
.mode = 0644,
|
|
.proc_handler = proc_dointvec,
|
|
},
|
|
{ }
|
|
};
|
|
|
|
static struct ctl_path nf_ct_path[] = {
|
|
{ .procname = "net", },
|
|
{ }
|
|
};
|
|
|
|
static int nf_conntrack_standalone_init_sysctl(struct net *net)
|
|
{
|
|
struct ctl_table *table;
|
|
|
|
if (net_eq(net, &init_net)) {
|
|
nf_ct_netfilter_header =
|
|
register_sysctl_paths(nf_ct_path, nf_ct_netfilter_table);
|
|
if (!nf_ct_netfilter_header)
|
|
goto out;
|
|
}
|
|
|
|
table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table),
|
|
GFP_KERNEL);
|
|
if (!table)
|
|
goto out_kmemdup;
|
|
|
|
table[1].data = &net->ct.count;
|
|
table[2].data = &net->ct.htable_size;
|
|
table[3].data = &net->ct.sysctl_checksum;
|
|
table[4].data = &net->ct.sysctl_log_invalid;
|
|
|
|
net->ct.sysctl_header = register_net_sysctl_table(net,
|
|
nf_net_netfilter_sysctl_path, table);
|
|
if (!net->ct.sysctl_header)
|
|
goto out_unregister_netfilter;
|
|
|
|
return 0;
|
|
|
|
out_unregister_netfilter:
|
|
kfree(table);
|
|
out_kmemdup:
|
|
if (net_eq(net, &init_net))
|
|
unregister_sysctl_table(nf_ct_netfilter_header);
|
|
out:
|
|
printk("nf_conntrack: can't register to sysctl.\n");
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void nf_conntrack_standalone_fini_sysctl(struct net *net)
|
|
{
|
|
struct ctl_table *table;
|
|
|
|
if (net_eq(net, &init_net))
|
|
unregister_sysctl_table(nf_ct_netfilter_header);
|
|
table = net->ct.sysctl_header->ctl_table_arg;
|
|
unregister_net_sysctl_table(net->ct.sysctl_header);
|
|
kfree(table);
|
|
}
|
|
#else
|
|
static int nf_conntrack_standalone_init_sysctl(struct net *net)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static void nf_conntrack_standalone_fini_sysctl(struct net *net)
|
|
{
|
|
}
|
|
#endif /* CONFIG_SYSCTL */
|
|
|
|
static int nf_conntrack_net_init(struct net *net)
|
|
{
|
|
int ret;
|
|
|
|
ret = nf_conntrack_init(net);
|
|
if (ret < 0)
|
|
goto out_init;
|
|
ret = nf_conntrack_standalone_init_proc(net);
|
|
if (ret < 0)
|
|
goto out_proc;
|
|
net->ct.sysctl_checksum = 1;
|
|
net->ct.sysctl_log_invalid = 0;
|
|
ret = nf_conntrack_standalone_init_sysctl(net);
|
|
if (ret < 0)
|
|
goto out_sysctl;
|
|
return 0;
|
|
|
|
out_sysctl:
|
|
nf_conntrack_standalone_fini_proc(net);
|
|
out_proc:
|
|
nf_conntrack_cleanup(net);
|
|
out_init:
|
|
return ret;
|
|
}
|
|
|
|
static void nf_conntrack_net_exit(struct net *net)
|
|
{
|
|
nf_conntrack_standalone_fini_sysctl(net);
|
|
nf_conntrack_standalone_fini_proc(net);
|
|
nf_conntrack_cleanup(net);
|
|
}
|
|
|
|
static struct pernet_operations nf_conntrack_net_ops = {
|
|
.init = nf_conntrack_net_init,
|
|
.exit = nf_conntrack_net_exit,
|
|
};
|
|
|
|
static int __init nf_conntrack_standalone_init(void)
|
|
{
|
|
return register_pernet_subsys(&nf_conntrack_net_ops);
|
|
}
|
|
|
|
static void __exit nf_conntrack_standalone_fini(void)
|
|
{
|
|
unregister_pernet_subsys(&nf_conntrack_net_ops);
|
|
}
|
|
|
|
module_init(nf_conntrack_standalone_init);
|
|
module_exit(nf_conntrack_standalone_fini);
|
|
|
|
/* Some modules need us, but don't depend directly on any symbol.
|
|
They should call this. */
|
|
void need_conntrack(void)
|
|
{
|
|
}
|
|
EXPORT_SYMBOL_GPL(need_conntrack);
|