2005-04-17 02:20:36 +04:00
/*
* net / sched / cls_u32 . c Ugly ( or Universal ) 32 bit key Packet Classifier .
*
* This program is free software ; you can redistribute it and / or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation ; either version
* 2 of the License , or ( at your option ) any later version .
*
* Authors : Alexey Kuznetsov , < kuznet @ ms2 . inr . ac . ru >
*
* The filters are packed to hash tables of key nodes
* with a set of 32 bit key / mask pairs at every node .
* Nodes reference next level hash tables etc .
*
* This scheme is the best universal classifier I managed to
* invent ; it is not super - fast , but it is not slow ( provided you
* program it correctly ) , and general enough . And its relative
* speed grows as the number of rules becomes larger .
*
* It seems that it represents the best middle point between
* speed and manageability both by human and by machine .
*
* It is especially useful for link sharing combined with QoS ;
* pure RSVP doesn ' t need such a general approach and can use
* much simpler ( and faster ) schemes , sort of cls_rsvp . c .
*
* JHS : We should remove the CONFIG_NET_CLS_IND from here
* eventually when the meta match extension is made available
*
* nfmark match added by Catalin ( ux aka Dino ) BOIE < catab at umbrella . ro >
*/
# include <linux/module.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>
2005-04-17 02:20:36 +04:00
# include <linux/types.h>
# include <linux/kernel.h>
# include <linux/string.h>
# include <linux/errno.h>
# include <linux/rtnetlink.h>
# include <linux/skbuff.h>
2007-07-03 09:49:07 +04:00
# include <net/netlink.h>
2005-04-17 02:20:36 +04:00
# include <net/act_api.h>
# include <net/pkt_cls.h>
struct tc_u_knode
{
struct tc_u_knode * next ;
u32 handle ;
struct tc_u_hnode * ht_up ;
struct tcf_exts exts ;
# ifdef CONFIG_NET_CLS_IND
char indev [ IFNAMSIZ ] ;
# endif
u8 fshift ;
struct tcf_result res ;
struct tc_u_hnode * ht_down ;
# ifdef CONFIG_CLS_U32_PERF
struct tc_u32_pcnt * pf ;
# endif
# ifdef CONFIG_CLS_U32_MARK
struct tc_u32_mark mark ;
# endif
struct tc_u32_sel sel ;
} ;
struct tc_u_hnode
{
struct tc_u_hnode * next ;
u32 handle ;
u32 prio ;
struct tc_u_common * tp_c ;
int refcnt ;
unsigned divisor ;
struct tc_u_knode * ht [ 1 ] ;
} ;
struct tc_u_common
{
struct tc_u_hnode * hlist ;
struct Qdisc * q ;
int refcnt ;
u32 hgenerator ;
} ;
2008-02-01 05:36:18 +03:00
static const struct tcf_ext_map u32_ext_map = {
2005-04-17 02:20:36 +04:00
. action = TCA_U32_ACT ,
. police = TCA_U32_POLICE
} ;
2008-03-18 08:46:46 +03:00
static __inline__ unsigned u32_hash_fold ( __be32 key , struct tc_u32_sel * sel , u8 fshift )
2005-04-17 02:20:36 +04:00
{
[PKT_SCHED] CLS_U32: Fix endianness problem with u32 classifier hash masks.
While trying to implement u32 hashes in my shaping machine I ran into
a possible bug in the u32 hash/bucket computing algorithm
(net/sched/cls_u32.c).
The problem occurs only with hash masks that extend over the octet
boundary, on little endian machines (where htonl() actually does
something).
Let's say that I would like to use 0x3fc0 as the hash mask. This means
8 contiguous "1" bits starting at b6. With such a mask, the expected
(and logical) behavior is to hash any address in, for instance,
192.168.0.0/26 in bucket 0, then any address in 192.168.0.64/26 in
bucket 1, then 192.168.0.128/26 in bucket 2 and so on.
This is exactly what would happen on a big endian machine, but on
little endian machines, what would actually happen with current
implementation is 0x3fc0 being reversed (into 0xc03f0000) by htonl()
in the userspace tool and then applied to 192.168.x.x in the u32
classifier. When shifting right by 16 bits (rank of first "1" bit in
the reversed mask) and applying the divisor mask (0xff for divisor
256), what would actually remain is 0x3f applied on the "168" octet of
the address.
One could say is this can be easily worked around by taking endianness
into account in userspace and supplying an appropriate mask (0xfc03)
that would be turned into contiguous "1" bits when reversed
(0x03fc0000). But the actual problem is the network address (inside
the packet) not being converted to host order, but used as a
host-order value when computing the bucket.
Let's say the network address is written as n31 n30 ... n0, with n0
being the least significant bit. When used directly (without any
conversion) on a little endian machine, it becomes n7 ... n0 n8 ..n15
etc in the machine's registers. Thus bits n7 and n8 would no longer be
adjacent and 192.168.64.0/26 and 192.168.128.0/26 would no longer be
consecutive.
The fix is to apply ntohl() on the hmask before computing fshift,
and in u32_hash_fold() convert the packet data to host order before
shifting down by fshift.
With helpful feedback from Jamal Hadi Salim and Jarek Poplawski.
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-07 12:20:12 +03:00
unsigned h = ntohl ( key & sel - > hmask ) > > fshift ;
2005-04-17 02:20:36 +04:00
return h ;
}
static int u32_classify ( struct sk_buff * skb , struct tcf_proto * tp , struct tcf_result * res )
{
struct {
struct tc_u_knode * knode ;
u8 * ptr ;
} stack [ TC_U32_MAXDEPTH ] ;
struct tc_u_hnode * ht = ( struct tc_u_hnode * ) tp - > root ;
2007-04-11 07:50:43 +04:00
u8 * ptr = skb_network_header ( skb ) ;
2005-04-17 02:20:36 +04:00
struct tc_u_knode * n ;
int sdepth = 0 ;
int off2 = 0 ;
int sel = 0 ;
# ifdef CONFIG_CLS_U32_PERF
int j ;
# endif
int i , r ;
next_ht :
n = ht - > ht [ sel ] ;
next_knode :
if ( n ) {
struct tc_u32_key * key = n - > sel . keys ;
# ifdef CONFIG_CLS_U32_PERF
n - > pf - > rcnt + = 1 ;
j = 0 ;
# endif
# ifdef CONFIG_CLS_U32_MARK
2006-11-10 02:19:14 +03:00
if ( ( skb - > mark & n - > mark . mask ) ! = n - > mark . val ) {
2005-04-17 02:20:36 +04:00
n = n - > next ;
goto next_knode ;
} else {
n - > mark . success + + ;
}
# endif
for ( i = n - > sel . nkeys ; i > 0 ; i - - , key + + ) {
2008-03-18 08:46:46 +03:00
if ( ( * ( __be32 * ) ( ptr + key - > off + ( off2 & key - > offmask ) ) ^ key - > val ) & key - > mask ) {
2005-04-17 02:20:36 +04:00
n = n - > next ;
goto next_knode ;
}
# ifdef CONFIG_CLS_U32_PERF
n - > pf - > kcnts [ j ] + = 1 ;
j + + ;
# endif
}
if ( n - > ht_down = = NULL ) {
check_terminal :
if ( n - > sel . flags & TC_U32_TERMINAL ) {
* res = n - > res ;
# ifdef CONFIG_NET_CLS_IND
if ( ! tcf_match_indev ( skb , n - > indev ) ) {
n = n - > next ;
goto next_knode ;
}
# endif
# ifdef CONFIG_CLS_U32_PERF
n - > pf - > rhit + = 1 ;
# endif
r = tcf_exts_exec ( skb , & n - > exts , res ) ;
if ( r < 0 ) {
n = n - > next ;
goto next_knode ;
}
return r ;
}
n = n - > next ;
goto next_knode ;
}
/* PUSH */
if ( sdepth > = TC_U32_MAXDEPTH )
goto deadloop ;
stack [ sdepth ] . knode = n ;
stack [ sdepth ] . ptr = ptr ;
sdepth + + ;
ht = n - > ht_down ;
sel = 0 ;
if ( ht - > divisor )
2008-03-18 08:46:46 +03:00
sel = ht - > divisor & u32_hash_fold ( * ( __be32 * ) ( ptr + n - > sel . hoff ) , & n - > sel , n - > fshift ) ;
2005-04-17 02:20:36 +04:00
if ( ! ( n - > sel . flags & ( TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT ) ) )
goto next_ht ;
if ( n - > sel . flags & ( TC_U32_OFFSET | TC_U32_VAROFFSET ) ) {
off2 = n - > sel . off + 3 ;
if ( n - > sel . flags & TC_U32_VAROFFSET )
2008-03-18 08:46:46 +03:00
off2 + = ntohs ( n - > sel . offmask & * ( __be16 * ) ( ptr + n - > sel . offoff ) ) > > n - > sel . offshift ;
2005-04-17 02:20:36 +04:00
off2 & = ~ 3 ;
}
if ( n - > sel . flags & TC_U32_EAT ) {
ptr + = off2 ;
off2 = 0 ;
}
2007-04-20 07:29:13 +04:00
if ( ptr < skb_tail_pointer ( skb ) )
2005-04-17 02:20:36 +04:00
goto next_ht ;
}
/* POP */
if ( sdepth - - ) {
n = stack [ sdepth ] . knode ;
ht = n - > ht_up ;
ptr = stack [ sdepth ] . ptr ;
goto check_terminal ;
}
return - 1 ;
deadloop :
if ( net_ratelimit ( ) )
2010-05-12 10:37:05 +04:00
printk ( KERN_WARNING " cls_u32: dead loop \n " ) ;
2005-04-17 02:20:36 +04:00
return - 1 ;
}
static __inline__ struct tc_u_hnode *
u32_lookup_ht ( struct tc_u_common * tp_c , u32 handle )
{
struct tc_u_hnode * ht ;
for ( ht = tp_c - > hlist ; ht ; ht = ht - > next )
if ( ht - > handle = = handle )
break ;
return ht ;
}
static __inline__ struct tc_u_knode *
u32_lookup_key ( struct tc_u_hnode * ht , u32 handle )
{
unsigned sel ;
struct tc_u_knode * n = NULL ;
sel = TC_U32_HASH ( handle ) ;
if ( sel > ht - > divisor )
goto out ;
for ( n = ht - > ht [ sel ] ; n ; n = n - > next )
if ( n - > handle = = handle )
break ;
out :
return n ;
}
static unsigned long u32_get ( struct tcf_proto * tp , u32 handle )
{
struct tc_u_hnode * ht ;
struct tc_u_common * tp_c = tp - > data ;
if ( TC_U32_HTID ( handle ) = = TC_U32_ROOT )
ht = tp - > root ;
else
ht = u32_lookup_ht ( tp_c , TC_U32_HTID ( handle ) ) ;
if ( ! ht )
return 0 ;
if ( TC_U32_KEY ( handle ) = = 0 )
return ( unsigned long ) ht ;
return ( unsigned long ) u32_lookup_key ( ht , handle ) ;
}
static void u32_put ( struct tcf_proto * tp , unsigned long f )
{
}
static u32 gen_new_htid ( struct tc_u_common * tp_c )
{
int i = 0x800 ;
do {
if ( + + tp_c - > hgenerator = = 0x7FF )
tp_c - > hgenerator = 1 ;
} while ( - - i > 0 & & u32_lookup_ht ( tp_c , ( tp_c - > hgenerator | 0x800 ) < < 20 ) ) ;
return i > 0 ? ( tp_c - > hgenerator | 0x800 ) < < 20 : 0 ;
}
static int u32_init ( struct tcf_proto * tp )
{
struct tc_u_hnode * root_ht ;
struct tc_u_common * tp_c ;
2008-07-19 07:54:17 +04:00
tp_c = tp - > q - > u32_node ;
2005-04-17 02:20:36 +04:00
2006-07-22 01:51:30 +04:00
root_ht = kzalloc ( sizeof ( * root_ht ) , GFP_KERNEL ) ;
2005-04-17 02:20:36 +04:00
if ( root_ht = = NULL )
return - ENOBUFS ;
root_ht - > divisor = 0 ;
root_ht - > refcnt + + ;
root_ht - > handle = tp_c ? gen_new_htid ( tp_c ) : 0x80000000 ;
root_ht - > prio = tp - > prio ;
if ( tp_c = = NULL ) {
2006-07-22 01:51:30 +04:00
tp_c = kzalloc ( sizeof ( * tp_c ) , GFP_KERNEL ) ;
2005-04-17 02:20:36 +04:00
if ( tp_c = = NULL ) {
kfree ( root_ht ) ;
return - ENOBUFS ;
}
tp_c - > q = tp - > q ;
2008-07-19 07:54:17 +04:00
tp - > q - > u32_node = tp_c ;
2005-04-17 02:20:36 +04:00
}
tp_c - > refcnt + + ;
root_ht - > next = tp_c - > hlist ;
tp_c - > hlist = root_ht ;
root_ht - > tp_c = tp_c ;
tp - > root = root_ht ;
tp - > data = tp_c ;
return 0 ;
}
static int u32_destroy_key ( struct tcf_proto * tp , struct tc_u_knode * n )
{
tcf_unbind_filter ( tp , & n - > res ) ;
tcf_exts_destroy ( tp , & n - > exts ) ;
if ( n - > ht_down )
n - > ht_down - > refcnt - - ;
# ifdef CONFIG_CLS_U32_PERF
2006-03-23 12:16:48 +03:00
kfree ( n - > pf ) ;
2005-04-17 02:20:36 +04:00
# endif
kfree ( n ) ;
return 0 ;
}
static int u32_delete_key ( struct tcf_proto * tp , struct tc_u_knode * key )
{
struct tc_u_knode * * kp ;
struct tc_u_hnode * ht = key - > ht_up ;
if ( ht ) {
for ( kp = & ht - > ht [ TC_U32_HASH ( key - > handle ) ] ; * kp ; kp = & ( * kp ) - > next ) {
if ( * kp = = key ) {
tcf_tree_lock ( tp ) ;
* kp = key - > next ;
tcf_tree_unlock ( tp ) ;
u32_destroy_key ( tp , key ) ;
return 0 ;
}
}
}
2008-07-26 08:43:18 +04:00
WARN_ON ( 1 ) ;
2005-04-17 02:20:36 +04:00
return 0 ;
}
static void u32_clear_hnode ( struct tcf_proto * tp , struct tc_u_hnode * ht )
{
struct tc_u_knode * n ;
unsigned h ;
for ( h = 0 ; h < = ht - > divisor ; h + + ) {
while ( ( n = ht - > ht [ h ] ) ! = NULL ) {
ht - > ht [ h ] = n - > next ;
u32_destroy_key ( tp , n ) ;
}
}
}
static int u32_destroy_hnode ( struct tcf_proto * tp , struct tc_u_hnode * ht )
{
struct tc_u_common * tp_c = tp - > data ;
struct tc_u_hnode * * hn ;
2008-07-26 08:43:18 +04:00
WARN_ON ( ht - > refcnt ) ;
2005-04-17 02:20:36 +04:00
u32_clear_hnode ( tp , ht ) ;
for ( hn = & tp_c - > hlist ; * hn ; hn = & ( * hn ) - > next ) {
if ( * hn = = ht ) {
* hn = ht - > next ;
kfree ( ht ) ;
return 0 ;
}
}
2008-07-26 08:43:18 +04:00
WARN_ON ( 1 ) ;
2005-04-17 02:20:36 +04:00
return - ENOENT ;
}
static void u32_destroy ( struct tcf_proto * tp )
{
struct tc_u_common * tp_c = tp - > data ;
2008-11-19 11:03:09 +03:00
struct tc_u_hnode * root_ht = tp - > root ;
2005-04-17 02:20:36 +04:00
2008-07-26 08:43:18 +04:00
WARN_ON ( root_ht = = NULL ) ;
2005-04-17 02:20:36 +04:00
if ( root_ht & & - - root_ht - > refcnt = = 0 )
u32_destroy_hnode ( tp , root_ht ) ;
if ( - - tp_c - > refcnt = = 0 ) {
struct tc_u_hnode * ht ;
2008-07-19 07:54:17 +04:00
tp - > q - > u32_node = NULL ;
2005-04-17 02:20:36 +04:00
2008-04-13 05:37:13 +04:00
for ( ht = tp_c - > hlist ; ht ; ht = ht - > next ) {
ht - > refcnt - - ;
2005-04-17 02:20:36 +04:00
u32_clear_hnode ( tp , ht ) ;
2008-04-13 05:37:13 +04:00
}
2005-04-17 02:20:36 +04:00
while ( ( ht = tp_c - > hlist ) ! = NULL ) {
tp_c - > hlist = ht - > next ;
2008-07-26 08:43:18 +04:00
WARN_ON ( ht - > refcnt ! = 0 ) ;
2005-04-17 02:20:36 +04:00
kfree ( ht ) ;
2007-04-21 04:09:22 +04:00
}
2005-04-17 02:20:36 +04:00
kfree ( tp_c ) ;
}
tp - > data = NULL ;
}
static int u32_delete ( struct tcf_proto * tp , unsigned long arg )
{
struct tc_u_hnode * ht = ( struct tc_u_hnode * ) arg ;
if ( ht = = NULL )
return 0 ;
if ( TC_U32_KEY ( ht - > handle ) )
return u32_delete_key ( tp , ( struct tc_u_knode * ) ht ) ;
if ( tp - > root = = ht )
return - EINVAL ;
2008-04-13 05:37:13 +04:00
if ( ht - > refcnt = = 1 ) {
ht - > refcnt - - ;
2005-04-17 02:20:36 +04:00
u32_destroy_hnode ( tp , ht ) ;
2008-04-13 05:37:13 +04:00
} else {
return - EBUSY ;
}
2005-04-17 02:20:36 +04:00
return 0 ;
}
static u32 gen_new_kid ( struct tc_u_hnode * ht , u32 handle )
{
struct tc_u_knode * n ;
unsigned i = 0x7FF ;
for ( n = ht - > ht [ TC_U32_HASH ( handle ) ] ; n ; n = n - > next )
if ( i < TC_U32_NODE ( n - > handle ) )
i = TC_U32_NODE ( n - > handle ) ;
i + + ;
return handle | ( i > 0xFFF ? 0xFFF : i ) ;
}
2008-01-24 07:36:12 +03:00
static const struct nla_policy u32_policy [ TCA_U32_MAX + 1 ] = {
[ TCA_U32_CLASSID ] = { . type = NLA_U32 } ,
[ TCA_U32_HASH ] = { . type = NLA_U32 } ,
[ TCA_U32_LINK ] = { . type = NLA_U32 } ,
[ TCA_U32_DIVISOR ] = { . type = NLA_U32 } ,
[ TCA_U32_SEL ] = { . len = sizeof ( struct tc_u32_sel ) } ,
[ TCA_U32_INDEV ] = { . type = NLA_STRING , . len = IFNAMSIZ } ,
[ TCA_U32_MARK ] = { . len = sizeof ( struct tc_u32_mark ) } ,
} ;
2005-04-17 02:20:36 +04:00
static int u32_set_parms ( struct tcf_proto * tp , unsigned long base ,
struct tc_u_hnode * ht ,
2008-01-23 09:11:33 +03:00
struct tc_u_knode * n , struct nlattr * * tb ,
struct nlattr * est )
2005-04-17 02:20:36 +04:00
{
int err ;
struct tcf_exts e ;
err = tcf_exts_validate ( tp , tb , est , & e , & u32_ext_map ) ;
if ( err < 0 )
return err ;
err = - EINVAL ;
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_LINK ] ) {
2008-01-24 07:35:03 +03:00
u32 handle = nla_get_u32 ( tb [ TCA_U32_LINK ] ) ;
2008-11-19 11:03:09 +03:00
struct tc_u_hnode * ht_down = NULL , * ht_old ;
2005-04-17 02:20:36 +04:00
if ( TC_U32_KEY ( handle ) )
goto errout ;
if ( handle ) {
ht_down = u32_lookup_ht ( ht - > tp_c , handle ) ;
if ( ht_down = = NULL )
goto errout ;
ht_down - > refcnt + + ;
}
tcf_tree_lock ( tp ) ;
2008-11-19 11:03:09 +03:00
ht_old = n - > ht_down ;
n - > ht_down = ht_down ;
2005-04-17 02:20:36 +04:00
tcf_tree_unlock ( tp ) ;
2008-11-19 11:03:09 +03:00
if ( ht_old )
ht_old - > refcnt - - ;
2005-04-17 02:20:36 +04:00
}
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_CLASSID ] ) {
2008-01-24 07:35:03 +03:00
n - > res . classid = nla_get_u32 ( tb [ TCA_U32_CLASSID ] ) ;
2005-04-17 02:20:36 +04:00
tcf_bind_filter ( tp , & n - > res , base ) ;
}
# ifdef CONFIG_NET_CLS_IND
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_INDEV ] ) {
err = tcf_change_indev ( tp , n - > indev , tb [ TCA_U32_INDEV ] ) ;
2005-04-17 02:20:36 +04:00
if ( err < 0 )
goto errout ;
}
# endif
tcf_exts_change ( tp , & n - > exts , & e ) ;
return 0 ;
errout :
tcf_exts_destroy ( tp , & e ) ;
return err ;
}
static int u32_change ( struct tcf_proto * tp , unsigned long base , u32 handle ,
2008-01-23 09:11:33 +03:00
struct nlattr * * tca ,
2005-04-17 02:20:36 +04:00
unsigned long * arg )
{
struct tc_u_common * tp_c = tp - > data ;
struct tc_u_hnode * ht ;
struct tc_u_knode * n ;
struct tc_u32_sel * s ;
2008-01-23 09:11:33 +03:00
struct nlattr * opt = tca [ TCA_OPTIONS ] ;
struct nlattr * tb [ TCA_U32_MAX + 1 ] ;
2005-04-17 02:20:36 +04:00
u32 htid ;
int err ;
if ( opt = = NULL )
return handle ? - EINVAL : 0 ;
2008-01-24 07:36:12 +03:00
err = nla_parse_nested ( tb , TCA_U32_MAX , opt , u32_policy ) ;
2008-01-24 07:33:32 +03:00
if ( err < 0 )
return err ;
2005-04-17 02:20:36 +04:00
if ( ( n = ( struct tc_u_knode * ) * arg ) ! = NULL ) {
if ( TC_U32_KEY ( n - > handle ) = = 0 )
return - EINVAL ;
2008-01-23 09:11:33 +03:00
return u32_set_parms ( tp , base , n - > ht_up , n , tb , tca [ TCA_RATE ] ) ;
2005-04-17 02:20:36 +04:00
}
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_DIVISOR ] ) {
2008-01-24 07:35:03 +03:00
unsigned divisor = nla_get_u32 ( tb [ TCA_U32_DIVISOR ] ) ;
2005-04-17 02:20:36 +04:00
if ( - - divisor > 0x100 )
return - EINVAL ;
if ( TC_U32_KEY ( handle ) )
return - EINVAL ;
if ( handle = = 0 ) {
handle = gen_new_htid ( tp - > data ) ;
if ( handle = = 0 )
return - ENOMEM ;
}
2006-07-22 01:51:30 +04:00
ht = kzalloc ( sizeof ( * ht ) + divisor * sizeof ( void * ) , GFP_KERNEL ) ;
2005-04-17 02:20:36 +04:00
if ( ht = = NULL )
return - ENOBUFS ;
ht - > tp_c = tp_c ;
2008-04-13 05:37:13 +04:00
ht - > refcnt = 1 ;
2005-04-17 02:20:36 +04:00
ht - > divisor = divisor ;
ht - > handle = handle ;
ht - > prio = tp - > prio ;
ht - > next = tp_c - > hlist ;
tp_c - > hlist = ht ;
* arg = ( unsigned long ) ht ;
return 0 ;
}
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_HASH ] ) {
2008-01-24 07:35:03 +03:00
htid = nla_get_u32 ( tb [ TCA_U32_HASH ] ) ;
2005-04-17 02:20:36 +04:00
if ( TC_U32_HTID ( htid ) = = TC_U32_ROOT ) {
ht = tp - > root ;
htid = ht - > handle ;
} else {
ht = u32_lookup_ht ( tp - > data , TC_U32_HTID ( htid ) ) ;
if ( ht = = NULL )
return - EINVAL ;
}
} else {
ht = tp - > root ;
htid = ht - > handle ;
}
if ( ht - > divisor < TC_U32_HASH ( htid ) )
return - EINVAL ;
if ( handle ) {
if ( TC_U32_HTID ( handle ) & & TC_U32_HTID ( handle ^ htid ) )
return - EINVAL ;
handle = htid | TC_U32_NODE ( handle ) ;
} else
handle = gen_new_kid ( ht , htid ) ;
2008-01-24 07:36:12 +03:00
if ( tb [ TCA_U32_SEL ] = = NULL )
2005-04-17 02:20:36 +04:00
return - EINVAL ;
2008-01-23 09:11:33 +03:00
s = nla_data ( tb [ TCA_U32_SEL ] ) ;
2005-04-17 02:20:36 +04:00
2006-07-22 01:51:30 +04:00
n = kzalloc ( sizeof ( * n ) + s - > nkeys * sizeof ( struct tc_u32_key ) , GFP_KERNEL ) ;
2005-04-17 02:20:36 +04:00
if ( n = = NULL )
return - ENOBUFS ;
# ifdef CONFIG_CLS_U32_PERF
2006-07-22 01:51:30 +04:00
n - > pf = kzalloc ( sizeof ( struct tc_u32_pcnt ) + s - > nkeys * sizeof ( u64 ) , GFP_KERNEL ) ;
2005-04-17 02:20:36 +04:00
if ( n - > pf = = NULL ) {
kfree ( n ) ;
return - ENOBUFS ;
}
# endif
memcpy ( & n - > sel , s , sizeof ( * s ) + s - > nkeys * sizeof ( struct tc_u32_key ) ) ;
n - > ht_up = ht ;
n - > handle = handle ;
2007-11-11 08:54:50 +03:00
n - > fshift = s - > hmask ? ffs ( ntohl ( s - > hmask ) ) - 1 : 0 ;
2005-04-17 02:20:36 +04:00
# ifdef CONFIG_CLS_U32_MARK
2008-01-23 09:11:33 +03:00
if ( tb [ TCA_U32_MARK ] ) {
2005-04-17 02:20:36 +04:00
struct tc_u32_mark * mark ;
2008-01-23 09:11:33 +03:00
mark = nla_data ( tb [ TCA_U32_MARK ] ) ;
2005-04-17 02:20:36 +04:00
memcpy ( & n - > mark , mark , sizeof ( struct tc_u32_mark ) ) ;
n - > mark . success = 0 ;
}
# endif
2008-01-23 09:11:33 +03:00
err = u32_set_parms ( tp , base , ht , n , tb , tca [ TCA_RATE ] ) ;
2005-04-17 02:20:36 +04:00
if ( err = = 0 ) {
struct tc_u_knode * * ins ;
for ( ins = & ht - > ht [ TC_U32_HASH ( handle ) ] ; * ins ; ins = & ( * ins ) - > next )
if ( TC_U32_NODE ( handle ) < TC_U32_NODE ( ( * ins ) - > handle ) )
break ;
n - > next = * ins ;
2009-01-06 05:14:19 +03:00
tcf_tree_lock ( tp ) ;
2005-04-17 02:20:36 +04:00
* ins = n ;
2009-01-06 05:14:19 +03:00
tcf_tree_unlock ( tp ) ;
2005-04-17 02:20:36 +04:00
* arg = ( unsigned long ) n ;
return 0 ;
}
# ifdef CONFIG_CLS_U32_PERF
2006-03-23 12:16:48 +03:00
kfree ( n - > pf ) ;
2005-04-17 02:20:36 +04:00
# endif
kfree ( n ) ;
return err ;
}
static void u32_walk ( struct tcf_proto * tp , struct tcf_walker * arg )
{
struct tc_u_common * tp_c = tp - > data ;
struct tc_u_hnode * ht ;
struct tc_u_knode * n ;
unsigned h ;
if ( arg - > stop )
return ;
for ( ht = tp_c - > hlist ; ht ; ht = ht - > next ) {
if ( ht - > prio ! = tp - > prio )
continue ;
if ( arg - > count > = arg - > skip ) {
if ( arg - > fn ( tp , ( unsigned long ) ht , arg ) < 0 ) {
arg - > stop = 1 ;
return ;
}
}
arg - > count + + ;
for ( h = 0 ; h < = ht - > divisor ; h + + ) {
for ( n = ht - > ht [ h ] ; n ; n = n - > next ) {
if ( arg - > count < arg - > skip ) {
arg - > count + + ;
continue ;
}
if ( arg - > fn ( tp , ( unsigned long ) n , arg ) < 0 ) {
arg - > stop = 1 ;
return ;
}
arg - > count + + ;
}
}
}
}
static int u32_dump ( struct tcf_proto * tp , unsigned long fh ,
struct sk_buff * skb , struct tcmsg * t )
{
struct tc_u_knode * n = ( struct tc_u_knode * ) fh ;
2008-01-24 07:34:11 +03:00
struct nlattr * nest ;
2005-04-17 02:20:36 +04:00
if ( n = = NULL )
return skb - > len ;
t - > tcm_handle = n - > handle ;
2008-01-24 07:34:11 +03:00
nest = nla_nest_start ( skb , TCA_OPTIONS ) ;
if ( nest = = NULL )
goto nla_put_failure ;
2005-04-17 02:20:36 +04:00
if ( TC_U32_KEY ( n - > handle ) = = 0 ) {
struct tc_u_hnode * ht = ( struct tc_u_hnode * ) fh ;
u32 divisor = ht - > divisor + 1 ;
2008-01-24 07:34:48 +03:00
NLA_PUT_U32 ( skb , TCA_U32_DIVISOR , divisor ) ;
2005-04-17 02:20:36 +04:00
} else {
2008-01-23 09:11:33 +03:00
NLA_PUT ( skb , TCA_U32_SEL ,
2005-04-17 02:20:36 +04:00
sizeof ( n - > sel ) + n - > sel . nkeys * sizeof ( struct tc_u32_key ) ,
& n - > sel ) ;
if ( n - > ht_up ) {
u32 htid = n - > handle & 0xFFFFF000 ;
2008-01-24 07:34:48 +03:00
NLA_PUT_U32 ( skb , TCA_U32_HASH , htid ) ;
2005-04-17 02:20:36 +04:00
}
if ( n - > res . classid )
2008-01-24 07:34:48 +03:00
NLA_PUT_U32 ( skb , TCA_U32_CLASSID , n - > res . classid ) ;
2005-04-17 02:20:36 +04:00
if ( n - > ht_down )
2008-01-24 07:34:48 +03:00
NLA_PUT_U32 ( skb , TCA_U32_LINK , n - > ht_down - > handle ) ;
2005-04-17 02:20:36 +04:00
# ifdef CONFIG_CLS_U32_MARK
if ( n - > mark . val | | n - > mark . mask )
2008-01-23 09:11:33 +03:00
NLA_PUT ( skb , TCA_U32_MARK , sizeof ( n - > mark ) , & n - > mark ) ;
2005-04-17 02:20:36 +04:00
# endif
if ( tcf_exts_dump ( skb , & n - > exts , & u32_ext_map ) < 0 )
2008-01-23 09:11:33 +03:00
goto nla_put_failure ;
2005-04-17 02:20:36 +04:00
# ifdef CONFIG_NET_CLS_IND
if ( strlen ( n - > indev ) )
2008-01-24 07:34:28 +03:00
NLA_PUT_STRING ( skb , TCA_U32_INDEV , n - > indev ) ;
2005-04-17 02:20:36 +04:00
# endif
# ifdef CONFIG_CLS_U32_PERF
2008-01-23 09:11:33 +03:00
NLA_PUT ( skb , TCA_U32_PCNT ,
2005-04-17 02:20:36 +04:00
sizeof ( struct tc_u32_pcnt ) + n - > sel . nkeys * sizeof ( u64 ) ,
n - > pf ) ;
# endif
}
2008-01-24 07:34:11 +03:00
nla_nest_end ( skb , nest ) ;
2005-04-17 02:20:36 +04:00
if ( TC_U32_KEY ( n - > handle ) )
if ( tcf_exts_dump_stats ( skb , & n - > exts , & u32_ext_map ) < 0 )
2008-01-23 09:11:33 +03:00
goto nla_put_failure ;
2005-04-17 02:20:36 +04:00
return skb - > len ;
2008-01-23 09:11:33 +03:00
nla_put_failure :
2008-01-24 07:34:11 +03:00
nla_nest_cancel ( skb , nest ) ;
2005-04-17 02:20:36 +04:00
return - 1 ;
}
2008-01-23 09:10:42 +03:00
static struct tcf_proto_ops cls_u32_ops __read_mostly = {
2005-04-17 02:20:36 +04:00
. kind = " u32 " ,
. classify = u32_classify ,
. init = u32_init ,
. destroy = u32_destroy ,
. get = u32_get ,
. put = u32_put ,
. change = u32_change ,
. delete = u32_delete ,
. walk = u32_walk ,
. dump = u32_dump ,
. owner = THIS_MODULE ,
} ;
static int __init init_u32 ( void )
{
2010-05-12 10:37:05 +04:00
pr_info ( " u32 classifier \n " ) ;
2005-04-17 02:20:36 +04:00
# ifdef CONFIG_CLS_U32_PERF
2010-05-12 10:37:05 +04:00
pr_info ( " Performance counters on \n " ) ;
2005-04-17 02:20:36 +04:00
# endif
# ifdef CONFIG_NET_CLS_IND
2010-05-12 10:37:05 +04:00
pr_info ( " input device check on \n " ) ;
2005-04-17 02:20:36 +04:00
# endif
# ifdef CONFIG_NET_CLS_ACT
2010-05-12 10:37:05 +04:00
pr_info ( " Actions configured \n " ) ;
2005-04-17 02:20:36 +04:00
# endif
return register_tcf_proto_ops ( & cls_u32_ops ) ;
}
2007-02-09 17:25:16 +03:00
static void __exit exit_u32 ( void )
2005-04-17 02:20:36 +04:00
{
unregister_tcf_proto_ops ( & cls_u32_ops ) ;
}
module_init ( init_u32 )
module_exit ( exit_u32 )
MODULE_LICENSE ( " GPL " ) ;