2019-05-27 09:55:01 +03:00
// SPDX-License-Identifier: GPL-2.0-or-later
2005-04-17 02:20:36 +04:00
/*
* ip6_flowlabel . c IPv6 flowlabel manager .
*
* Authors : Alexey Kuznetsov , < kuznet @ ms2 . inr . ac . ru >
*/
2006-01-11 23:17:47 +03:00
# include <linux/capability.h>
2005-04-17 02:20:36 +04:00
# include <linux/errno.h>
# include <linux/types.h>
# include <linux/socket.h>
# include <linux/net.h>
# include <linux/netdevice.h>
# include <linux/in6.h>
# include <linux/proc_fs.h>
# include <linux/seq_file.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
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>
2010-03-24 11:04:11 +03:00
# include <linux/slab.h>
2011-07-15 19:47:34 +04:00
# include <linux/export.h>
2012-05-24 20:37:59 +04:00
# include <linux/pid_namespace.h>
2019-07-07 12:34:45 +03:00
# include <linux/jump_label_ratelimit.h>
2005-04-17 02:20:36 +04:00
2007-09-12 14:01:34 +04:00
# include <net/net_namespace.h>
2005-04-17 02:20:36 +04:00
# include <net/sock.h>
# include <net/ipv6.h>
# include <net/rawv6.h>
# include <net/transp_v6.h>
2016-12-24 22:46:01 +03:00
# include <linux/uaccess.h>
2005-04-17 02:20:36 +04:00
# define FL_MIN_LINGER 6 / * Minimal linger. It is set to 6sec specified
in old IPv6 RFC . Well , it was reasonable value .
*/
2013-11-07 20:53:13 +04:00
# define FL_MAX_LINGER 150 /* Maximal linger timeout */
2005-04-17 02:20:36 +04:00
/* FL hash table */
# define FL_MAX_PER_SOCK 32
# define FL_MAX_SIZE 4096
# define FL_HASH_MASK 255
# define FL_HASH(l) (ntohl(l)&FL_HASH_MASK)
static atomic_t fl_size = ATOMIC_INIT ( 0 ) ;
2013-01-30 13:27:47 +04:00
static struct ip6_flowlabel __rcu * fl_ht [ FL_HASH_MASK + 1 ] ;
2005-04-17 02:20:36 +04:00
2017-08-28 21:28:21 +03:00
static void ip6_fl_gc ( struct timer_list * unused ) ;
2017-10-05 02:27:04 +03:00
static DEFINE_TIMER ( ip6_fl_gc_timer , ip6_fl_gc ) ;
2005-04-17 02:20:36 +04:00
/* FL hash table lock: it protects only of GC */
2013-01-30 13:27:47 +04:00
static DEFINE_SPINLOCK ( ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
/* Big socket sock */
2013-01-30 13:27:52 +04:00
static DEFINE_SPINLOCK ( ip6_sk_fl_lock ) ;
2005-04-17 02:20:36 +04:00
2019-07-07 12:34:45 +03:00
DEFINE_STATIC_KEY_DEFERRED_FALSE ( ipv6_flowlabel_exclusive , HZ ) ;
EXPORT_SYMBOL ( ipv6_flowlabel_exclusive ) ;
2013-01-30 13:27:47 +04:00
# define for_each_fl_rcu(hash, fl) \
2013-02-07 19:52:40 +04:00
for ( fl = rcu_dereference_bh ( fl_ht [ ( hash ) ] ) ; \
2013-01-30 13:27:47 +04:00
fl ! = NULL ; \
2013-02-07 19:52:40 +04:00
fl = rcu_dereference_bh ( fl - > next ) )
2013-01-30 13:27:47 +04:00
# define for_each_fl_continue_rcu(fl) \
2013-02-07 19:52:40 +04:00
for ( fl = rcu_dereference_bh ( fl - > next ) ; \
2013-01-30 13:27:47 +04:00
fl ! = NULL ; \
2013-02-07 19:52:40 +04:00
fl = rcu_dereference_bh ( fl - > next ) )
2005-04-17 02:20:36 +04:00
2013-01-30 13:27:52 +04:00
# define for_each_sk_fl_rcu(np, sfl) \
for ( sfl = rcu_dereference_bh ( np - > ipv6_fl_list ) ; \
sfl ! = NULL ; \
sfl = rcu_dereference_bh ( sfl - > next ) )
2008-03-27 02:53:08 +03:00
static inline struct ip6_flowlabel * __fl_lookup ( struct net * net , __be32 label )
2005-04-17 02:20:36 +04:00
{
struct ip6_flowlabel * fl ;
2013-01-30 13:27:47 +04:00
for_each_fl_rcu ( FL_HASH ( label ) , fl ) {
2009-11-26 02:14:13 +03:00
if ( fl - > label = = label & & net_eq ( fl - > fl_net , net ) )
2005-04-17 02:20:36 +04:00
return fl ;
}
return NULL ;
}
2008-03-27 02:53:08 +03:00
static struct ip6_flowlabel * fl_lookup ( struct net * net , __be32 label )
2005-04-17 02:20:36 +04:00
{
struct ip6_flowlabel * fl ;
2013-01-30 13:27:47 +04:00
rcu_read_lock_bh ( ) ;
2008-03-27 02:53:08 +03:00
fl = __fl_lookup ( net , label ) ;
2013-01-30 13:27:47 +04:00
if ( fl & & ! atomic_inc_not_zero ( & fl - > users ) )
fl = NULL ;
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
return fl ;
}
2019-07-07 12:34:45 +03:00
static bool fl_shared_exclusive ( struct ip6_flowlabel * fl )
{
return fl - > share = = IPV6_FL_S_EXCL | |
fl - > share = = IPV6_FL_S_PROCESS | |
fl - > share = = IPV6_FL_S_USER ;
}
2019-04-28 02:49:06 +03:00
static void fl_free_rcu ( struct rcu_head * head )
{
struct ip6_flowlabel * fl = container_of ( head , struct ip6_flowlabel , rcu ) ;
if ( fl - > share = = IPV6_FL_S_PROCESS )
put_pid ( fl - > owner . pid ) ;
kfree ( fl - > opt ) ;
kfree ( fl ) ;
}
2005-04-17 02:20:36 +04:00
static void fl_free ( struct ip6_flowlabel * fl )
{
2019-07-07 12:34:45 +03:00
if ( ! fl )
return ;
if ( fl_shared_exclusive ( fl ) | | fl - > opt )
static_branch_slow_dec_deferred ( & ipv6_flowlabel_exclusive ) ;
call_rcu ( & fl - > rcu , fl_free_rcu ) ;
2005-04-17 02:20:36 +04:00
}
static void fl_release ( struct ip6_flowlabel * fl )
{
2013-01-30 13:27:47 +04:00
spin_lock_bh ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
fl - > lastuse = jiffies ;
if ( atomic_dec_and_test ( & fl - > users ) ) {
unsigned long ttd = fl - > lastuse + fl - > linger ;
if ( time_after ( ttd , fl - > expires ) )
fl - > expires = ttd ;
ttd = fl - > expires ;
if ( fl - > opt & & fl - > share = = IPV6_FL_S_EXCL ) {
struct ipv6_txoptions * opt = fl - > opt ;
fl - > opt = NULL ;
kfree ( opt ) ;
}
if ( ! timer_pending ( & ip6_fl_gc_timer ) | |
time_after ( ip6_fl_gc_timer . expires , ttd ) )
mod_timer ( & ip6_fl_gc_timer , ttd ) ;
}
2013-01-30 13:27:47 +04:00
spin_unlock_bh ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
}
2017-08-28 21:28:21 +03:00
static void ip6_fl_gc ( struct timer_list * unused )
2005-04-17 02:20:36 +04:00
{
int i ;
unsigned long now = jiffies ;
unsigned long sched = 0 ;
2013-01-30 13:27:47 +04:00
spin_lock ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
2014-08-25 00:53:10 +04:00
for ( i = 0 ; i < = FL_HASH_MASK ; i + + ) {
2013-03-07 08:20:32 +04:00
struct ip6_flowlabel * fl ;
struct ip6_flowlabel __rcu * * flp ;
2005-04-17 02:20:36 +04:00
flp = & fl_ht [ i ] ;
2013-01-30 13:27:47 +04:00
while ( ( fl = rcu_dereference_protected ( * flp ,
lockdep_is_held ( & ip6_fl_lock ) ) ) ! = NULL ) {
2005-04-17 02:20:36 +04:00
if ( atomic_read ( & fl - > users ) = = 0 ) {
unsigned long ttd = fl - > lastuse + fl - > linger ;
if ( time_after ( ttd , fl - > expires ) )
fl - > expires = ttd ;
ttd = fl - > expires ;
if ( time_after_eq ( now , ttd ) ) {
* flp = fl - > next ;
fl_free ( fl ) ;
atomic_dec ( & fl_size ) ;
continue ;
}
if ( ! sched | | time_before ( ttd , sched ) )
sched = ttd ;
}
flp = & fl - > next ;
}
}
if ( ! sched & & atomic_read ( & fl_size ) )
sched = now + FL_MAX_LINGER ;
if ( sched ) {
2008-03-27 02:53:08 +03:00
mod_timer ( & ip6_fl_gc_timer , sched ) ;
2005-04-17 02:20:36 +04:00
}
2013-01-30 13:27:47 +04:00
spin_unlock ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
}
2010-01-17 06:35:32 +03:00
static void __net_exit ip6_fl_purge ( struct net * net )
2008-03-27 02:53:08 +03:00
{
int i ;
2015-02-11 16:06:23 +03:00
spin_lock_bh ( & ip6_fl_lock ) ;
2008-03-27 02:53:08 +03:00
for ( i = 0 ; i < = FL_HASH_MASK ; i + + ) {
2013-03-07 08:20:32 +04:00
struct ip6_flowlabel * fl ;
struct ip6_flowlabel __rcu * * flp ;
2008-03-27 02:53:08 +03:00
flp = & fl_ht [ i ] ;
2013-01-30 13:27:47 +04:00
while ( ( fl = rcu_dereference_protected ( * flp ,
lockdep_is_held ( & ip6_fl_lock ) ) ) ! = NULL ) {
2009-11-26 02:14:13 +03:00
if ( net_eq ( fl - > fl_net , net ) & &
atomic_read ( & fl - > users ) = = 0 ) {
2008-03-27 02:53:08 +03:00
* flp = fl - > next ;
fl_free ( fl ) ;
atomic_dec ( & fl_size ) ;
continue ;
}
flp = & fl - > next ;
}
}
2015-02-11 16:06:23 +03:00
spin_unlock_bh ( & ip6_fl_lock ) ;
2008-03-27 02:53:08 +03:00
}
static struct ip6_flowlabel * fl_intern ( struct net * net ,
struct ip6_flowlabel * fl , __be32 label )
2005-04-17 02:20:36 +04:00
{
2007-10-18 16:18:56 +04:00
struct ip6_flowlabel * lfl ;
2005-04-17 02:20:36 +04:00
fl - > label = label & IPV6_FLOWLABEL_MASK ;
2013-01-30 13:27:47 +04:00
spin_lock_bh ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
if ( label = = 0 ) {
for ( ; ; ) {
2022-10-05 18:43:22 +03:00
fl - > label = htonl ( get_random_u32 ( ) ) & IPV6_FLOWLABEL_MASK ;
2005-04-17 02:20:36 +04:00
if ( fl - > label ) {
2008-03-27 02:53:08 +03:00
lfl = __fl_lookup ( net , fl - > label ) ;
2015-03-29 16:00:04 +03:00
if ( ! lfl )
2005-04-17 02:20:36 +04:00
break ;
}
}
2007-10-18 16:18:56 +04:00
} else {
/*
* we dropper the ip6_fl_lock , so this entry could reappear
* and we need to recheck with it .
*
* OTOH no need to search the active socket first , like it is
* done in ipv6_flowlabel_opt - sock is locked , so new entry
* with the same label can only appear on another sock
*/
2008-03-27 02:53:08 +03:00
lfl = __fl_lookup ( net , fl - > label ) ;
2015-03-29 16:00:05 +03:00
if ( lfl ) {
2007-10-18 16:18:56 +04:00
atomic_inc ( & lfl - > users ) ;
2013-01-30 13:27:47 +04:00
spin_unlock_bh ( & ip6_fl_lock ) ;
2007-10-18 16:18:56 +04:00
return lfl ;
}
2005-04-17 02:20:36 +04:00
}
fl - > lastuse = jiffies ;
fl - > next = fl_ht [ FL_HASH ( fl - > label ) ] ;
2013-01-30 13:27:47 +04:00
rcu_assign_pointer ( fl_ht [ FL_HASH ( fl - > label ) ] , fl ) ;
2005-04-17 02:20:36 +04:00
atomic_inc ( & fl_size ) ;
2013-01-30 13:27:47 +04:00
spin_unlock_bh ( & ip6_fl_lock ) ;
2007-10-18 16:18:56 +04:00
return NULL ;
2005-04-17 02:20:36 +04:00
}
/* Socket flowlabel lists */
2019-07-07 12:34:45 +03:00
struct ip6_flowlabel * __fl6_sock_lookup ( struct sock * sk , __be32 label )
2005-04-17 02:20:36 +04:00
{
struct ipv6_fl_socklist * sfl ;
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
label & = IPV6_FLOWLABEL_MASK ;
2013-01-30 13:27:52 +04:00
rcu_read_lock_bh ( ) ;
for_each_sk_fl_rcu ( np , sfl ) {
2005-04-17 02:20:36 +04:00
struct ip6_flowlabel * fl = sfl - > fl ;
2019-06-07 00:32:34 +03:00
if ( fl - > label = = label & & atomic_inc_not_zero ( & fl - > users ) ) {
2005-04-17 02:20:36 +04:00
fl - > lastuse = jiffies ;
2013-01-30 13:27:52 +04:00
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
return fl ;
}
}
2013-01-30 13:27:52 +04:00
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
return NULL ;
}
2019-07-07 12:34:45 +03:00
EXPORT_SYMBOL_GPL ( __fl6_sock_lookup ) ;
2005-12-14 10:23:20 +03:00
2005-04-17 02:20:36 +04:00
void fl6_free_socklist ( struct sock * sk )
{
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
struct ipv6_fl_socklist * sfl ;
2013-01-30 13:27:52 +04:00
if ( ! rcu_access_pointer ( np - > ipv6_fl_list ) )
2013-01-30 13:26:42 +04:00
return ;
2013-01-30 13:27:52 +04:00
spin_lock_bh ( & ip6_sk_fl_lock ) ;
while ( ( sfl = rcu_dereference_protected ( np - > ipv6_fl_list ,
lockdep_is_held ( & ip6_sk_fl_lock ) ) ) ! = NULL ) {
np - > ipv6_fl_list = sfl - > next ;
spin_unlock_bh ( & ip6_sk_fl_lock ) ;
2013-01-30 13:26:42 +04:00
2005-04-17 02:20:36 +04:00
fl_release ( sfl - > fl ) ;
2013-01-30 13:27:52 +04:00
kfree_rcu ( sfl , rcu ) ;
spin_lock_bh ( & ip6_sk_fl_lock ) ;
2005-04-17 02:20:36 +04:00
}
2013-01-30 13:27:52 +04:00
spin_unlock_bh ( & ip6_sk_fl_lock ) ;
2005-04-17 02:20:36 +04:00
}
/* Service routines */
/*
It is the only difficult place . flowlabel enforces equal headers
before and including routing header , however user may supply options
following rthdr .
*/
2014-08-25 00:53:10 +04:00
struct ipv6_txoptions * fl6_merge_options ( struct ipv6_txoptions * opt_space ,
struct ip6_flowlabel * fl ,
struct ipv6_txoptions * fopt )
2005-04-17 02:20:36 +04:00
{
2014-08-25 00:53:10 +04:00
struct ipv6_txoptions * fl_opt = fl - > opt ;
2007-02-09 17:24:49 +03:00
2015-03-29 16:00:04 +03:00
if ( ! fopt | | fopt - > opt_flen = = 0 )
2005-11-20 06:23:18 +03:00
return fl_opt ;
2007-02-09 17:24:49 +03:00
2015-03-29 16:00:05 +03:00
if ( fl_opt ) {
2005-04-17 02:20:36 +04:00
opt_space - > hopopt = fl_opt - > hopopt ;
2005-11-20 06:23:18 +03:00
opt_space - > dst0opt = fl_opt - > dst0opt ;
2005-04-17 02:20:36 +04:00
opt_space - > srcrt = fl_opt - > srcrt ;
opt_space - > opt_nflen = fl_opt - > opt_nflen ;
} else {
if ( fopt - > opt_nflen = = 0 )
return fopt ;
opt_space - > hopopt = NULL ;
opt_space - > dst0opt = NULL ;
opt_space - > srcrt = NULL ;
opt_space - > opt_nflen = 0 ;
}
opt_space - > dst1opt = fopt - > dst1opt ;
opt_space - > opt_flen = fopt - > opt_flen ;
2017-10-21 22:26:23 +03:00
opt_space - > tot_len = fopt - > tot_len ;
2005-04-17 02:20:36 +04:00
return opt_space ;
}
2012-04-30 01:48:53 +04:00
EXPORT_SYMBOL_GPL ( fl6_merge_options ) ;
2005-04-17 02:20:36 +04:00
static unsigned long check_linger ( unsigned long ttl )
{
if ( ttl < FL_MIN_LINGER )
return FL_MIN_LINGER * HZ ;
if ( ttl > FL_MAX_LINGER & & ! capable ( CAP_NET_ADMIN ) )
return 0 ;
return ttl * HZ ;
}
static int fl6_renew ( struct ip6_flowlabel * fl , unsigned long linger , unsigned long expires )
{
linger = check_linger ( linger ) ;
if ( ! linger )
return - EPERM ;
expires = check_linger ( expires ) ;
if ( ! expires )
return - EPERM ;
2013-11-07 20:53:14 +04:00
spin_lock_bh ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
fl - > lastuse = jiffies ;
if ( time_before ( fl - > linger , linger ) )
fl - > linger = linger ;
if ( time_before ( expires , fl - > linger ) )
expires = fl - > linger ;
if ( time_before ( fl - > expires , fl - > lastuse + expires ) )
fl - > expires = fl - > lastuse + expires ;
2013-11-07 20:53:14 +04:00
spin_unlock_bh ( & ip6_fl_lock ) ;
2005-04-17 02:20:36 +04:00
return 0 ;
}
static struct ip6_flowlabel *
2011-08-28 16:35:31 +04:00
fl_create ( struct net * net , struct sock * sk , struct in6_flowlabel_req * freq ,
2020-07-23 09:09:01 +03:00
sockptr_t optval , int optlen , int * err_p )
2005-04-17 02:20:36 +04:00
{
2009-02-06 11:49:55 +03:00
struct ip6_flowlabel * fl = NULL ;
2005-04-17 02:20:36 +04:00
int olen ;
int addr_type ;
int err ;
2009-02-06 11:49:55 +03:00
olen = optlen - CMSG_ALIGN ( sizeof ( * freq ) ) ;
err = - EINVAL ;
if ( olen > 64 * 1024 )
goto done ;
2005-04-17 02:20:36 +04:00
err = - ENOMEM ;
2006-03-21 10:01:32 +03:00
fl = kzalloc ( sizeof ( * fl ) , GFP_KERNEL ) ;
2015-03-29 16:00:04 +03:00
if ( ! fl )
2005-04-17 02:20:36 +04:00
goto done ;
if ( olen > 0 ) {
struct msghdr msg ;
2011-03-13 00:22:43 +03:00
struct flowi6 flowi6 ;
2016-05-03 07:40:07 +03:00
struct ipcm6_cookie ipc6 ;
2005-04-17 02:20:36 +04:00
err = - ENOMEM ;
fl - > opt = kmalloc ( sizeof ( * fl - > opt ) + olen , GFP_KERNEL ) ;
2015-03-29 16:00:04 +03:00
if ( ! fl - > opt )
2005-04-17 02:20:36 +04:00
goto done ;
memset ( fl - > opt , 0 , sizeof ( * fl - > opt ) ) ;
fl - > opt - > tot_len = sizeof ( * fl - > opt ) + olen ;
err = - EFAULT ;
2020-07-28 19:38:35 +03:00
if ( copy_from_sockptr_offset ( fl - > opt + 1 , optval ,
CMSG_ALIGN ( sizeof ( * freq ) ) , olen ) )
2005-04-17 02:20:36 +04:00
goto done ;
msg . msg_controllen = olen ;
2014-08-25 00:53:10 +04:00
msg . msg_control = ( void * ) ( fl - > opt + 1 ) ;
2011-03-13 00:22:43 +03:00
memset ( & flowi6 , 0 , sizeof ( flowi6 ) ) ;
2005-04-17 02:20:36 +04:00
2016-05-03 07:40:07 +03:00
ipc6 . opt = fl - > opt ;
2018-07-06 17:12:57 +03:00
err = ip6_datagram_send_ctl ( net , sk , & msg , & flowi6 , & ipc6 ) ;
2005-04-17 02:20:36 +04:00
if ( err )
goto done ;
err = - EINVAL ;
if ( fl - > opt - > opt_flen )
goto done ;
if ( fl - > opt - > opt_nflen = = 0 ) {
kfree ( fl - > opt ) ;
fl - > opt = NULL ;
}
}
2015-03-12 07:04:08 +03:00
fl - > fl_net = net ;
2005-04-17 02:20:36 +04:00
fl - > expires = jiffies ;
err = fl6_renew ( fl , freq - > flr_linger , freq - > flr_expires ) ;
if ( err )
goto done ;
fl - > share = freq - > flr_share ;
addr_type = ipv6_addr_type ( & freq - > flr_dst ) ;
2009-11-25 01:52:52 +03:00
if ( ( addr_type & IPV6_ADDR_MAPPED ) | |
addr_type = = IPV6_ADDR_ANY ) {
2006-10-31 05:56:06 +03:00
err = - EINVAL ;
2005-04-17 02:20:36 +04:00
goto done ;
2006-10-31 05:56:06 +03:00
}
2011-11-21 07:39:03 +04:00
fl - > dst = freq - > flr_dst ;
2005-04-17 02:20:36 +04:00
atomic_set ( & fl - > users , 1 ) ;
switch ( fl - > share ) {
case IPV6_FL_S_EXCL :
case IPV6_FL_S_ANY :
break ;
case IPV6_FL_S_PROCESS :
2012-05-24 20:37:59 +04:00
fl - > owner . pid = get_task_pid ( current , PIDTYPE_PID ) ;
2005-04-17 02:20:36 +04:00
break ;
case IPV6_FL_S_USER :
2012-05-24 20:37:59 +04:00
fl - > owner . uid = current_euid ( ) ;
2005-04-17 02:20:36 +04:00
break ;
default :
err = - EINVAL ;
goto done ;
}
2022-02-15 19:00:37 +03:00
if ( fl_shared_exclusive ( fl ) | | fl - > opt ) {
WRITE_ONCE ( sock_net ( sk ) - > ipv6 . flowlabel_has_excl , 1 ) ;
2019-07-10 16:40:11 +03:00
static_branch_deferred_inc ( & ipv6_flowlabel_exclusive ) ;
2022-02-15 19:00:37 +03:00
}
2005-04-17 02:20:36 +04:00
return fl ;
done :
2019-07-10 16:40:11 +03:00
if ( fl ) {
kfree ( fl - > opt ) ;
kfree ( fl ) ;
}
2005-04-17 02:20:36 +04:00
* err_p = err ;
return NULL ;
}
static int mem_check ( struct sock * sk )
{
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
struct ipv6_fl_socklist * sfl ;
int room = FL_MAX_SIZE - atomic_read ( & fl_size ) ;
int count = 0 ;
if ( room > FL_MAX_SIZE - FL_MAX_PER_SOCK )
return 0 ;
2013-11-08 22:26:21 +04:00
rcu_read_lock_bh ( ) ;
2013-01-30 13:27:52 +04:00
for_each_sk_fl_rcu ( np , sfl )
2005-04-17 02:20:36 +04:00
count + + ;
2013-11-08 22:26:21 +04:00
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
if ( room < = 0 | |
( ( count > = FL_MAX_PER_SOCK | |
2009-11-25 01:52:52 +03:00
( count > 0 & & room < FL_MAX_SIZE / 2 ) | | room < FL_MAX_SIZE / 4 ) & &
! capable ( CAP_NET_ADMIN ) ) )
2005-04-17 02:20:36 +04:00
return - ENOBUFS ;
return 0 ;
}
2007-10-18 16:14:58 +04:00
static inline void fl_link ( struct ipv6_pinfo * np , struct ipv6_fl_socklist * sfl ,
struct ip6_flowlabel * fl )
{
2013-01-30 13:27:52 +04:00
spin_lock_bh ( & ip6_sk_fl_lock ) ;
2007-10-18 16:14:58 +04:00
sfl - > fl = fl ;
sfl - > next = np - > ipv6_fl_list ;
2013-01-30 13:27:52 +04:00
rcu_assign_pointer ( np - > ipv6_fl_list , sfl ) ;
spin_unlock_bh ( & ip6_sk_fl_lock ) ;
2007-10-18 16:14:58 +04:00
}
2014-01-17 20:15:04 +04:00
int ipv6_flowlabel_opt_get ( struct sock * sk , struct in6_flowlabel_req * freq ,
int flags )
2013-11-07 20:53:12 +04:00
{
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
struct ipv6_fl_socklist * sfl ;
2014-01-17 20:15:04 +04:00
if ( flags & IPV6_FL_F_REMOTE ) {
freq - > flr_label = np - > rcv_flowinfo & IPV6_FLOWLABEL_MASK ;
return 0 ;
}
2014-01-17 20:15:03 +04:00
if ( np - > repflow ) {
freq - > flr_label = np - > flow_label ;
return 0 ;
}
2013-11-07 20:53:12 +04:00
rcu_read_lock_bh ( ) ;
for_each_sk_fl_rcu ( np , sfl ) {
if ( sfl - > fl - > label = = ( np - > flow_label & IPV6_FLOWLABEL_MASK ) ) {
spin_lock_bh ( & ip6_fl_lock ) ;
freq - > flr_label = sfl - > fl - > label ;
freq - > flr_dst = sfl - > fl - > dst ;
freq - > flr_share = sfl - > fl - > share ;
freq - > flr_expires = ( sfl - > fl - > expires - jiffies ) / HZ ;
freq - > flr_linger = sfl - > fl - > linger / HZ ;
spin_unlock_bh ( & ip6_fl_lock ) ;
rcu_read_unlock_bh ( ) ;
return 0 ;
}
}
rcu_read_unlock_bh ( ) ;
return - ENOENT ;
}
2020-07-23 09:09:00 +03:00
# define socklist_dereference(__sflp) \
rcu_dereference_protected ( __sflp , lockdep_is_held ( & ip6_sk_fl_lock ) )
static int ipv6_flowlabel_put ( struct sock * sk , struct in6_flowlabel_req * freq )
2005-04-17 02:20:36 +04:00
{
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
2013-03-07 08:20:32 +04:00
struct ipv6_fl_socklist __rcu * * sflp ;
2020-07-23 09:09:00 +03:00
struct ipv6_fl_socklist * sfl ;
2007-10-18 16:18:56 +04:00
2020-07-23 09:09:00 +03:00
if ( freq - > flr_flags & IPV6_FL_F_REFLECT ) {
if ( sk - > sk_protocol ! = IPPROTO_TCP )
return - ENOPROTOOPT ;
if ( ! np - > repflow )
return - ESRCH ;
np - > flow_label = 0 ;
np - > repflow = 0 ;
return 0 ;
}
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
spin_lock_bh ( & ip6_sk_fl_lock ) ;
for ( sflp = & np - > ipv6_fl_list ;
( sfl = socklist_dereference ( * sflp ) ) ! = NULL ;
sflp = & sfl - > next ) {
if ( sfl - > fl - > label = = freq - > flr_label )
goto found ;
}
spin_unlock_bh ( & ip6_sk_fl_lock ) ;
return - ESRCH ;
found :
if ( freq - > flr_label = = ( np - > flow_label & IPV6_FLOWLABEL_MASK ) )
np - > flow_label & = ~ IPV6_FLOWLABEL_MASK ;
* sflp = sfl - > next ;
spin_unlock_bh ( & ip6_sk_fl_lock ) ;
fl_release ( sfl - > fl ) ;
kfree_rcu ( sfl , rcu ) ;
return 0 ;
}
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
static int ipv6_flowlabel_renew ( struct sock * sk , struct in6_flowlabel_req * freq )
{
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
struct net * net = sock_net ( sk ) ;
struct ipv6_fl_socklist * sfl ;
int err ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
rcu_read_lock_bh ( ) ;
for_each_sk_fl_rcu ( np , sfl ) {
if ( sfl - > fl - > label = = freq - > flr_label ) {
err = fl6_renew ( sfl - > fl , freq - > flr_linger ,
freq - > flr_expires ) ;
rcu_read_unlock_bh ( ) ;
return err ;
2005-04-17 02:20:36 +04:00
}
2020-07-23 09:09:00 +03:00
}
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
if ( freq - > flr_share = = IPV6_FL_S_NONE & &
ns_capable ( net - > user_ns , CAP_NET_ADMIN ) ) {
struct ip6_flowlabel * fl = fl_lookup ( net , freq - > flr_label ) ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
if ( fl ) {
err = fl6_renew ( fl , freq - > flr_linger ,
freq - > flr_expires ) ;
fl_release ( fl ) ;
return err ;
2005-04-17 02:20:36 +04:00
}
2020-07-23 09:09:00 +03:00
}
return - ESRCH ;
}
2014-01-17 20:15:05 +04:00
2020-07-23 09:09:00 +03:00
static int ipv6_flowlabel_get ( struct sock * sk , struct in6_flowlabel_req * freq ,
2020-07-23 09:09:01 +03:00
sockptr_t optval , int optlen )
2020-07-23 09:09:00 +03:00
{
struct ipv6_fl_socklist * sfl , * sfl1 = NULL ;
struct ip6_flowlabel * fl , * fl1 = NULL ;
struct ipv6_pinfo * np = inet6_sk ( sk ) ;
struct net * net = sock_net ( sk ) ;
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
2020-08-06 06:13:21 +03:00
int err ;
2014-01-17 20:15:05 +04:00
2020-07-23 09:09:00 +03:00
if ( freq - > flr_flags & IPV6_FL_F_REFLECT ) {
if ( net - > ipv6 . sysctl . flowlabel_consistency ) {
net_info_ratelimited ( " Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable \n " ) ;
return - EPERM ;
2014-01-17 20:15:03 +04:00
}
2020-07-23 09:09:00 +03:00
if ( sk - > sk_protocol ! = IPPROTO_TCP )
return - ENOPROTOOPT ;
np - > repflow = 1 ;
return 0 ;
}
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
if ( freq - > flr_label & ~ IPV6_FLOWLABEL_MASK )
return - EINVAL ;
if ( net - > ipv6 . sysctl . flowlabel_state_ranges & &
( freq - > flr_label & IPV6_FLOWLABEL_STATELESS_FLAG ) )
return - ERANGE ;
ipv6: Flow label state ranges
This patch divides the IPv6 flow label space into two ranges:
0-7ffff is reserved for flow label manager, 80000-fffff will be
used for creating auto flow labels (per RFC6438). This only affects how
labels are set on transmit, it does not affect receive. This range split
can be disbaled by systcl.
Background:
IPv6 flow labels have been an unmitigated disappointment thus far
in the lifetime of IPv6. Support in HW devices to use them for ECMP
is lacking, and OSes don't turn them on by default. If we had these
we could get much better hashing in IPv6 networks without resorting
to DPI, possibly eliminating some of the motivations to to define new
encaps in UDP just for getting ECMP.
Unfortunately, the initial specfications of IPv6 did not clarify
how they are to be used. There has always been a vague concept that
these can be used for ECMP, flow hashing, etc. and we do now have a
good standard how to this in RFC6438. The problem is that flow labels
can be either stateful or stateless (as in RFC6438), and we are
presented with the possibility that a stateless label may collide
with a stateful one. Attempts to split the flow label space were
rejected in IETF. When we added support in Linux for RFC6438, we
could not turn on flow labels by default due to this conflict.
This patch splits the flow label space and should give us
a path to enabling auto flow labels by default for all IPv6 packets.
This is an API change so we need to consider compatibility with
existing deployment. The stateful range is chosen to be the lower
values in hopes that most uses would have chosen small numbers.
Once we resolve the stateless/stateful issue, we can proceed to
look at enabling RFC6438 flow labels by default (starting with
scaled testing).
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-30 01:33:21 +03:00
2020-07-23 09:09:00 +03:00
fl = fl_create ( net , sk , freq , optval , optlen , & err ) ;
if ( ! fl )
return err ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
sfl1 = kmalloc ( sizeof ( * sfl1 ) , GFP_KERNEL ) ;
if ( freq - > flr_label ) {
err = - EEXIST ;
rcu_read_lock_bh ( ) ;
for_each_sk_fl_rcu ( np , sfl ) {
if ( sfl - > fl - > label = = freq - > flr_label ) {
if ( freq - > flr_flags & IPV6_FL_F_EXCL ) {
rcu_read_unlock_bh ( ) ;
goto done ;
2005-04-17 02:20:36 +04:00
}
2020-07-23 09:09:00 +03:00
fl1 = sfl - > fl ;
if ( ! atomic_inc_not_zero ( & fl1 - > users ) )
fl1 = NULL ;
break ;
2005-04-17 02:20:36 +04:00
}
2020-07-23 09:09:00 +03:00
}
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
if ( ! fl1 )
fl1 = fl_lookup ( net , freq - > flr_label ) ;
if ( fl1 ) {
2007-10-18 16:18:56 +04:00
recheck :
2020-07-23 09:09:00 +03:00
err = - EEXIST ;
if ( freq - > flr_flags & IPV6_FL_F_EXCL )
goto release ;
err = - EPERM ;
if ( fl1 - > share = = IPV6_FL_S_EXCL | |
fl1 - > share ! = fl - > share | |
( ( fl1 - > share = = IPV6_FL_S_PROCESS ) & &
( fl1 - > owner . pid ! = fl - > owner . pid ) ) | |
( ( fl1 - > share = = IPV6_FL_S_USER ) & &
! uid_eq ( fl1 - > owner . uid , fl - > owner . uid ) ) )
goto release ;
err = - ENOMEM ;
if ( ! sfl1 )
goto release ;
if ( fl - > linger > fl1 - > linger )
fl1 - > linger = fl - > linger ;
if ( ( long ) ( fl - > expires - fl1 - > expires ) > 0 )
fl1 - > expires = fl - > expires ;
fl_link ( np , sfl1 , fl1 ) ;
fl_free ( fl ) ;
return 0 ;
2005-04-17 02:20:36 +04:00
release :
2020-07-23 09:09:00 +03:00
fl_release ( fl1 ) ;
2014-11-24 00:28:43 +03:00
goto done ;
2020-07-23 09:09:00 +03:00
}
}
err = - ENOENT ;
if ( ! ( freq - > flr_flags & IPV6_FL_F_CREATE ) )
goto done ;
2014-11-24 00:28:43 +03:00
2020-07-23 09:09:00 +03:00
err = - ENOMEM ;
if ( ! sfl1 )
goto done ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
err = mem_check ( sk ) ;
if ( err ! = 0 )
goto done ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
fl1 = fl_intern ( net , fl , freq - > flr_label ) ;
if ( fl1 )
goto recheck ;
2005-04-17 02:20:36 +04:00
2020-07-23 09:09:00 +03:00
if ( ! freq - > flr_label ) {
2020-07-28 19:38:35 +03:00
size_t offset = offsetof ( struct in6_flowlabel_req , flr_label ) ;
2005-04-17 02:20:36 +04:00
2020-07-28 19:38:35 +03:00
if ( copy_to_sockptr_offset ( optval , offset , & fl - > label ,
sizeof ( fl - > label ) ) ) {
2020-07-23 09:09:00 +03:00
/* Intentionally ignore fault. */
2005-05-30 07:28:01 +04:00
}
2005-04-17 02:20:36 +04:00
}
2020-07-23 09:09:00 +03:00
fl_link ( np , sfl1 , fl ) ;
return 0 ;
2005-04-17 02:20:36 +04:00
done :
fl_free ( fl ) ;
kfree ( sfl1 ) ;
return err ;
}
2020-07-23 09:09:01 +03:00
int ipv6_flowlabel_opt ( struct sock * sk , sockptr_t optval , int optlen )
2020-07-23 09:09:00 +03:00
{
struct in6_flowlabel_req freq ;
if ( optlen < sizeof ( freq ) )
return - EINVAL ;
2020-07-23 09:09:01 +03:00
if ( copy_from_sockptr ( & freq , optval , sizeof ( freq ) ) )
2020-07-23 09:09:00 +03:00
return - EFAULT ;
switch ( freq . flr_action ) {
case IPV6_FL_A_PUT :
return ipv6_flowlabel_put ( sk , & freq ) ;
case IPV6_FL_A_RENEW :
return ipv6_flowlabel_renew ( sk , & freq ) ;
case IPV6_FL_A_GET :
return ipv6_flowlabel_get ( sk , & freq , optval , optlen ) ;
default :
return - EINVAL ;
}
}
2005-04-17 02:20:36 +04:00
# ifdef CONFIG_PROC_FS
struct ip6fl_iter_state {
2008-03-27 02:53:30 +03:00
struct seq_net_private p ;
2012-05-24 20:37:59 +04:00
struct pid_namespace * pid_ns ;
2005-04-17 02:20:36 +04:00
int bucket ;
} ;
# define ip6fl_seq_private(seq) ((struct ip6fl_iter_state *)(seq)->private)
static struct ip6_flowlabel * ip6fl_get_first ( struct seq_file * seq )
{
struct ip6_flowlabel * fl = NULL ;
struct ip6fl_iter_state * state = ip6fl_seq_private ( seq ) ;
2008-03-27 02:53:30 +03:00
struct net * net = seq_file_net ( seq ) ;
2005-04-17 02:20:36 +04:00
for ( state - > bucket = 0 ; state - > bucket < = FL_HASH_MASK ; + + state - > bucket ) {
2013-01-30 13:27:47 +04:00
for_each_fl_rcu ( state - > bucket , fl ) {
if ( net_eq ( fl - > fl_net , net ) )
goto out ;
}
2005-04-17 02:20:36 +04:00
}
2013-01-30 13:27:47 +04:00
fl = NULL ;
out :
2005-04-17 02:20:36 +04:00
return fl ;
}
static struct ip6_flowlabel * ip6fl_get_next ( struct seq_file * seq , struct ip6_flowlabel * fl )
{
struct ip6fl_iter_state * state = ip6fl_seq_private ( seq ) ;
2008-03-27 02:53:30 +03:00
struct net * net = seq_file_net ( seq ) ;
2005-04-17 02:20:36 +04:00
2013-01-30 13:27:47 +04:00
for_each_fl_continue_rcu ( fl ) {
if ( net_eq ( fl - > fl_net , net ) )
goto out ;
}
2008-03-27 02:53:30 +03:00
try_again :
2013-01-30 13:27:47 +04:00
if ( + + state - > bucket < = FL_HASH_MASK ) {
for_each_fl_rcu ( state - > bucket , fl ) {
if ( net_eq ( fl - > fl_net , net ) )
goto out ;
}
goto try_again ;
2005-04-17 02:20:36 +04:00
}
2013-01-30 13:27:47 +04:00
fl = NULL ;
out :
2005-04-17 02:20:36 +04:00
return fl ;
}
static struct ip6_flowlabel * ip6fl_get_idx ( struct seq_file * seq , loff_t pos )
{
struct ip6_flowlabel * fl = ip6fl_get_first ( seq ) ;
if ( fl )
while ( pos & & ( fl = ip6fl_get_next ( seq , fl ) ) ! = NULL )
- - pos ;
return pos ? NULL : fl ;
}
static void * ip6fl_seq_start ( struct seq_file * seq , loff_t * pos )
2013-01-30 13:27:47 +04:00
__acquires ( RCU )
2005-04-17 02:20:36 +04:00
{
2018-04-11 11:01:30 +03:00
struct ip6fl_iter_state * state = ip6fl_seq_private ( seq ) ;
2020-05-18 21:07:38 +03:00
state - > pid_ns = proc_pid_ns ( file_inode ( seq - > file ) - > i_sb ) ;
2018-04-11 11:01:30 +03:00
2013-01-30 13:27:47 +04:00
rcu_read_lock_bh ( ) ;
2005-04-17 02:20:36 +04:00
return * pos ? ip6fl_get_idx ( seq , * pos - 1 ) : SEQ_START_TOKEN ;
}
static void * ip6fl_seq_next ( struct seq_file * seq , void * v , loff_t * pos )
{
struct ip6_flowlabel * fl ;
if ( v = = SEQ_START_TOKEN )
fl = ip6fl_get_first ( seq ) ;
else
fl = ip6fl_get_next ( seq , v ) ;
+ + * pos ;
return fl ;
}
static void ip6fl_seq_stop ( struct seq_file * seq , void * v )
2013-01-30 13:27:47 +04:00
__releases ( RCU )
2005-04-17 02:20:36 +04:00
{
2013-01-30 13:27:47 +04:00
rcu_read_unlock_bh ( ) ;
2005-04-17 02:20:36 +04:00
}
2006-10-31 11:43:44 +03:00
static int ip6fl_seq_show ( struct seq_file * seq , void * v )
2005-04-17 02:20:36 +04:00
{
2012-05-24 20:37:59 +04:00
struct ip6fl_iter_state * state = ip6fl_seq_private ( seq ) ;
2014-11-05 01:01:00 +03:00
if ( v = = SEQ_START_TOKEN ) {
2014-11-05 02:37:03 +03:00
seq_puts ( seq , " Label S Owner Users Linger Expires Dst Opt \n " ) ;
2014-11-05 01:01:00 +03:00
} else {
2006-10-31 11:43:44 +03:00
struct ip6_flowlabel * fl = v ;
2005-04-17 02:20:36 +04:00
seq_printf ( seq ,
2008-10-29 22:50:24 +03:00
" %05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d \n " ,
2012-04-15 09:58:06 +04:00
( unsigned int ) ntohl ( fl - > label ) ,
2005-04-17 02:20:36 +04:00
fl - > share ,
2012-05-24 20:37:59 +04:00
( ( fl - > share = = IPV6_FL_S_PROCESS ) ?
pid_nr_ns ( fl - > owner . pid , state - > pid_ns ) :
( ( fl - > share = = IPV6_FL_S_USER ) ?
from_kuid_munged ( seq_user_ns ( seq ) , fl - > owner . uid ) :
0 ) ) ,
2005-04-17 02:20:36 +04:00
atomic_read ( & fl - > users ) ,
fl - > linger / HZ ,
( long ) ( fl - > expires - jiffies ) / HZ ,
2008-10-29 02:05:40 +03:00
& fl - > dst ,
2005-04-17 02:20:36 +04:00
fl - > opt ? fl - > opt - > opt_nflen : 0 ) ;
}
return 0 ;
}
2007-07-11 10:07:31 +04:00
static const struct seq_operations ip6fl_seq_ops = {
2005-04-17 02:20:36 +04:00
. start = ip6fl_seq_start ,
. next = ip6fl_seq_next ,
. stop = ip6fl_seq_stop ,
. show = ip6fl_seq_show ,
} ;
2010-01-17 06:35:32 +03:00
static int __net_init ip6_flowlabel_proc_init ( struct net * net )
2007-12-11 13:23:18 +03:00
{
2018-04-10 20:42:55 +03:00
if ( ! proc_create_net ( " ip6_flowlabel " , 0444 , net - > proc_net ,
& ip6fl_seq_ops , sizeof ( struct ip6fl_iter_state ) ) )
2007-12-11 13:23:18 +03:00
return - ENOMEM ;
return 0 ;
}
2005-04-17 02:20:36 +04:00
2010-01-17 06:35:32 +03:00
static void __net_exit ip6_flowlabel_proc_fini ( struct net * net )
2005-04-17 02:20:36 +04:00
{
2013-02-18 05:34:56 +04:00
remove_proc_entry ( " ip6_flowlabel " , net - > proc_net ) ;
2007-12-11 13:23:18 +03:00
}
# else
static inline int ip6_flowlabel_proc_init ( struct net * net )
{
return 0 ;
}
static inline void ip6_flowlabel_proc_fini ( struct net * net )
{
}
2005-04-17 02:20:36 +04:00
# endif
2007-12-11 13:23:18 +03:00
2010-01-17 06:35:32 +03:00
static void __net_exit ip6_flowlabel_net_exit ( struct net * net )
2008-03-27 02:53:08 +03:00
{
ip6_fl_purge ( net ) ;
2008-03-27 02:53:30 +03:00
ip6_flowlabel_proc_fini ( net ) ;
2008-03-27 02:53:08 +03:00
}
static struct pernet_operations ip6_flowlabel_net_ops = {
2008-03-27 02:53:30 +03:00
. init = ip6_flowlabel_proc_init ,
2008-03-27 02:53:08 +03:00
. exit = ip6_flowlabel_net_exit ,
} ;
2007-12-11 13:23:18 +03:00
int ip6_flowlabel_init ( void )
{
2008-03-27 02:53:30 +03:00
return register_pernet_subsys ( & ip6_flowlabel_net_ops ) ;
2005-04-17 02:20:36 +04:00
}
void ip6_flowlabel_cleanup ( void )
{
2019-07-07 12:34:45 +03:00
static_key_deferred_flush ( & ipv6_flowlabel_exclusive ) ;
2005-04-17 02:20:36 +04:00
del_timer ( & ip6_fl_gc_timer ) ;
2008-03-27 02:53:08 +03:00
unregister_pernet_subsys ( & ip6_flowlabel_net_ops ) ;
2005-04-17 02:20:36 +04:00
}