linux/net/ipv6/addrlabel.c

594 lines
14 KiB
C
Raw Normal View History

/*
* IPv6 Address Label subsystem
* for the IPv6 "Default" Source Address Selection
*
* Copyright (C)2007 USAGI/WIDE Project
*/
/*
* Author:
* YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org>
*/
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/rcupdate.h>
#include <linux/in6.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 08:04:11 +00:00
#include <linux/slab.h>
#include <net/addrconf.h>
#include <linux/if_addrlabel.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/refcount.h>
#if 0
#define ADDRLABEL(x...) printk(x)
#else
#define ADDRLABEL(x...) do { ; } while (0)
#endif
/*
* Policy Table
*/
struct ip6addrlbl_entry {
struct in6_addr prefix;
int prefixlen;
int ifindex;
int addrtype;
u32 label;
struct hlist_node list;
refcount_t refcnt;
struct rcu_head rcu;
};
/*
* Default policy table (RFC6724 + extensions)
*
* prefix addr_type label
* -------------------------------------------------------------------------
* ::1/128 LOOPBACK 0
* ::/0 N/A 1
* 2002::/16 N/A 2
* ::/96 COMPATv4 3
* ::ffff:0:0/96 V4MAPPED 4
* fc00::/7 N/A 5 ULA (RFC 4193)
* 2001::/32 N/A 6 Teredo (RFC 4380)
* 2001:10::/28 N/A 7 ORCHID (RFC 4843)
* fec0::/10 N/A 11 Site-local
* (deprecated by RFC3879)
* 3ffe::/16 N/A 12 6bone
*
* Note: 0xffffffff is used if we do not have any policies.
* Note: Labels for ULA and 6to4 are different from labels listed in RFC6724.
*/
#define IPV6_ADDR_LABEL_DEFAULT 0xffffffffUL
static const __net_initconst struct ip6addrlbl_init_table
{
const struct in6_addr *prefix;
int prefixlen;
u32 label;
} ip6addrlbl_init_table[] = {
{ /* ::/0 */
.prefix = &in6addr_any,
.label = 1,
}, { /* fc00::/7 */
.prefix = &(struct in6_addr){ { { 0xfc } } } ,
.prefixlen = 7,
.label = 5,
}, { /* fec0::/10 */
.prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } },
.prefixlen = 10,
.label = 11,
}, { /* 2002::/16 */
.prefix = &(struct in6_addr){ { { 0x20, 0x02 } } },
.prefixlen = 16,
.label = 2,
}, { /* 3ffe::/16 */
.prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } },
.prefixlen = 16,
.label = 12,
}, { /* 2001::/32 */
.prefix = &(struct in6_addr){ { { 0x20, 0x01 } } },
.prefixlen = 32,
.label = 6,
}, { /* 2001:10::/28 */
.prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } },
.prefixlen = 28,
.label = 7,
}, { /* ::ffff:0:0 */
.prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } },
.prefixlen = 96,
.label = 4,
}, { /* ::/96 */
.prefix = &in6addr_any,
.prefixlen = 96,
.label = 3,
}, { /* ::1/128 */
.prefix = &in6addr_loopback,
.prefixlen = 128,
.label = 0,
}
};
/* Object management */
static inline void ip6addrlbl_free(struct ip6addrlbl_entry *p)
{
kfree(p);
}
static void ip6addrlbl_free_rcu(struct rcu_head *h)
{
ip6addrlbl_free(container_of(h, struct ip6addrlbl_entry, rcu));
}
static bool ip6addrlbl_hold(struct ip6addrlbl_entry *p)
{
return refcount_inc_not_zero(&p->refcnt);
}
static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p)
{
if (refcount_dec_and_test(&p->refcnt))
call_rcu(&p->rcu, ip6addrlbl_free_rcu);
}
/* Find label */
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p,
const struct in6_addr *addr,
int addrtype, int ifindex)
{
if (p->ifindex && p->ifindex != ifindex)
return false;
if (p->addrtype && p->addrtype != addrtype)
return false;
if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen))
return false;
return true;
}
static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net,
const struct in6_addr *addr,
int type, int ifindex)
{
struct ip6addrlbl_entry *p;
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
if (__ip6addrlbl_match(p, addr, type, ifindex))
return p;
}
return NULL;
}
u32 ipv6_addr_label(struct net *net,
const struct in6_addr *addr, int type, int ifindex)
{
u32 label;
struct ip6addrlbl_entry *p;
type &= IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK;
rcu_read_lock();
p = __ipv6_addr_label(net, addr, type, ifindex);
label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT;
rcu_read_unlock();
ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n",
__func__, addr, type, ifindex, label);
return label;
}
/* allocate one entry */
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix,
int prefixlen, int ifindex,
u32 label)
{
struct ip6addrlbl_entry *newp;
int addrtype;
ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n",
__func__, prefix, prefixlen, ifindex, (unsigned int)label);
addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK);
switch (addrtype) {
case IPV6_ADDR_MAPPED:
if (prefixlen > 96)
return ERR_PTR(-EINVAL);
if (prefixlen < 96)
addrtype = 0;
break;
case IPV6_ADDR_COMPATv4:
if (prefixlen != 96)
addrtype = 0;
break;
case IPV6_ADDR_LOOPBACK:
if (prefixlen != 128)
addrtype = 0;
break;
}
newp = kmalloc(sizeof(*newp), GFP_KERNEL);
if (!newp)
return ERR_PTR(-ENOMEM);
ipv6_addr_prefix(&newp->prefix, prefix, prefixlen);
newp->prefixlen = prefixlen;
newp->ifindex = ifindex;
newp->addrtype = addrtype;
newp->label = label;
INIT_HLIST_NODE(&newp->list);
refcount_set(&newp->refcnt, 1);
return newp;
}
/* add a label */
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp,
int replace)
{
struct ip6addrlbl_entry *last = NULL, *p = NULL;
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
struct hlist_node *n;
int ret = 0;
ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp,
replace);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
if (p->prefixlen == newp->prefixlen &&
p->ifindex == newp->ifindex &&
ipv6_addr_equal(&p->prefix, &newp->prefix)) {
if (!replace) {
ret = -EEXIST;
goto out;
}
hlist_replace_rcu(&p->list, &newp->list);
ip6addrlbl_put(p);
goto out;
} else if ((p->prefixlen == newp->prefixlen && !p->ifindex) ||
(p->prefixlen < newp->prefixlen)) {
hlist_add_before_rcu(&newp->list, &p->list);
goto out;
}
last = p;
}
if (last)
hlist_add_behind_rcu(&newp->list, &last->list);
else
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head);
out:
if (!ret)
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
net->ipv6.ip6addrlbl_table.seq++;
return ret;
}
/* add a label */
static int ip6addrlbl_add(struct net *net,
const struct in6_addr *prefix, int prefixlen,
int ifindex, u32 label, int replace)
{
struct ip6addrlbl_entry *newp;
int ret = 0;
ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n",
__func__, prefix, prefixlen, ifindex, (unsigned int)label,
replace);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label);
if (IS_ERR(newp))
return PTR_ERR(newp);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_lock(&net->ipv6.ip6addrlbl_table.lock);
ret = __ip6addrlbl_add(net, newp, replace);
spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
if (ret)
ip6addrlbl_free(newp);
return ret;
}
/* remove a label */
static int __ip6addrlbl_del(struct net *net,
const struct in6_addr *prefix, int prefixlen,
int ifindex)
{
struct ip6addrlbl_entry *p = NULL;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *n;
int ret = -ESRCH;
ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n",
__func__, prefix, prefixlen, ifindex);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
if (p->prefixlen == prefixlen &&
p->ifindex == ifindex &&
ipv6_addr_equal(&p->prefix, prefix)) {
hlist_del_rcu(&p->list);
ip6addrlbl_put(p);
ret = 0;
break;
}
}
return ret;
}
static int ip6addrlbl_del(struct net *net,
const struct in6_addr *prefix, int prefixlen,
int ifindex)
{
struct in6_addr prefix_buf;
int ret;
ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n",
__func__, prefix, prefixlen, ifindex);
ipv6_addr_prefix(&prefix_buf, prefix, prefixlen);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_lock(&net->ipv6.ip6addrlbl_table.lock);
ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
return ret;
}
/* add default label */
static int __net_init ip6addrlbl_net_init(struct net *net)
{
int err = 0;
int i;
ADDRLABEL(KERN_DEBUG "%s\n", __func__);
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_lock_init(&net->ipv6.ip6addrlbl_table.lock);
INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);
for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
int ret = ip6addrlbl_add(net,
ip6addrlbl_init_table[i].prefix,
ip6addrlbl_init_table[i].prefixlen,
0,
ip6addrlbl_init_table[i].label, 0);
/* XXX: should we free all rules when we catch an error? */
if (ret && (!err || err != -ENOMEM))
err = ret;
}
return err;
}
static void __net_exit ip6addrlbl_net_exit(struct net *net)
{
struct ip6addrlbl_entry *p = NULL;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *n;
/* Remove all labels belonging to the exiting net */
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_lock(&net->ipv6.ip6addrlbl_table.lock);
hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
hlist_del_rcu(&p->list);
ip6addrlbl_put(p);
}
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
spin_unlock(&net->ipv6.ip6addrlbl_table.lock);
}
static struct pernet_operations ipv6_addr_label_ops = {
.init = ip6addrlbl_net_init,
.exit = ip6addrlbl_net_exit,
};
int __init ipv6_addr_label_init(void)
{
return register_pernet_subsys(&ipv6_addr_label_ops);
}
void ipv6_addr_label_cleanup(void)
{
unregister_pernet_subsys(&ipv6_addr_label_ops);
}
static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
[IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), },
[IFAL_LABEL] = { .len = sizeof(u32), },
};
static bool addrlbl_ifindex_exists(struct net *net, int ifindex)
{
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_index_rcu(net, ifindex);
rcu_read_unlock();
return dev != NULL;
}
static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct ifaddrlblmsg *ifal;
struct nlattr *tb[IFAL_MAX+1];
struct in6_addr *pfx;
u32 label;
int err = 0;
err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
extack);
if (err < 0)
return err;
ifal = nlmsg_data(nlh);
if (ifal->ifal_family != AF_INET6 ||
ifal->ifal_prefixlen > 128)
return -EINVAL;
if (!tb[IFAL_ADDRESS])
return -EINVAL;
pfx = nla_data(tb[IFAL_ADDRESS]);
if (!tb[IFAL_LABEL])
return -EINVAL;
label = nla_get_u32(tb[IFAL_LABEL]);
if (label == IPV6_ADDR_LABEL_DEFAULT)
return -EINVAL;
switch (nlh->nlmsg_type) {
case RTM_NEWADDRLABEL:
if (ifal->ifal_index &&
!addrlbl_ifindex_exists(net, ifal->ifal_index))
return -EINVAL;
err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen,
ifal->ifal_index, label,
nlh->nlmsg_flags & NLM_F_REPLACE);
break;
case RTM_DELADDRLABEL:
err = ip6addrlbl_del(net, pfx, ifal->ifal_prefixlen,
ifal->ifal_index);
break;
default:
err = -EOPNOTSUPP;
}
return err;
}
static void ip6addrlbl_putmsg(struct nlmsghdr *nlh,
int prefixlen, int ifindex, u32 lseq)
{
struct ifaddrlblmsg *ifal = nlmsg_data(nlh);
ifal->ifal_family = AF_INET6;
ifal->ifal_prefixlen = prefixlen;
ifal->ifal_flags = 0;
ifal->ifal_index = ifindex;
ifal->ifal_seq = lseq;
};
static int ip6addrlbl_fill(struct sk_buff *skb,
struct ip6addrlbl_entry *p,
u32 lseq,
u32 portid, u32 seq, int event,
unsigned int flags)
{
struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event,
sizeof(struct ifaddrlblmsg), flags);
if (!nlh)
return -EMSGSIZE;
ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq);
if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 ||
nla_put_u32(skb, IFAL_LABEL, p->label) < 0) {
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
nlmsg_end(skb, nlh);
return 0;
}
static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct ip6addrlbl_entry *p;
int idx = 0, s_idx = cb->args[0];
int err;
rcu_read_lock();
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
if (idx >= s_idx) {
err = ip6addrlbl_fill(skb, p,
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
net->ipv6.ip6addrlbl_table.seq,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWADDRLABEL,
NLM_F_MULTI);
netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-16 21:09:00 +00:00
if (err < 0)
break;
}
idx++;
}
rcu_read_unlock();
cb->args[0] = idx;
return skb->len;
}
static inline int ip6addrlbl_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg))
+ nla_total_size(16) /* IFAL_ADDRESS */
+ nla_total_size(4); /* IFAL_LABEL */
}
static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(in_skb->sk);
struct ifaddrlblmsg *ifal;
struct nlattr *tb[IFAL_MAX+1];
struct in6_addr *addr;
u32 lseq;
int err = 0;
struct ip6addrlbl_entry *p;
struct sk_buff *skb;
err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
extack);
if (err < 0)
return err;
ifal = nlmsg_data(nlh);
if (ifal->ifal_family != AF_INET6 ||
ifal->ifal_prefixlen != 128)
return -EINVAL;
if (ifal->ifal_index &&
!addrlbl_ifindex_exists(net, ifal->ifal_index))
return -EINVAL;
if (!tb[IFAL_ADDRESS])
return -EINVAL;
addr = nla_data(tb[IFAL_ADDRESS]);
rcu_read_lock();
p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index);
if (p && !ip6addrlbl_hold(p))
p = NULL;
ipv6: addrlabel: per netns list Having a global list of labels do not scale to thousands of netns in the cloud era. This causes quadratic behavior on netns creation and deletion. This is time having a per netns list of ~10 labels. Tested: $ time perf record (for f in `seq 1 3000` ; do ip netns add tast$f; done) [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 3.637 MB perf.data (~158898 samples) ] real 0m20.837s # instead of 0m24.227s user 0m0.328s sys 0m20.338s # instead of 0m23.753s 16.17% ip [kernel.kallsyms] [k] netlink_broadcast_filtered 12.30% ip [kernel.kallsyms] [k] netlink_has_listeners 6.76% ip [kernel.kallsyms] [k] _raw_spin_lock_irqsave 5.78% ip [kernel.kallsyms] [k] memset_erms 5.77% ip [kernel.kallsyms] [k] kobject_uevent_env 5.18% ip [kernel.kallsyms] [k] refcount_sub_and_test 4.96% ip [kernel.kallsyms] [k] _raw_read_lock 3.82% ip [kernel.kallsyms] [k] refcount_inc_not_zero 3.33% ip [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore 2.11% ip [kernel.kallsyms] [k] unmap_page_range 1.77% ip [kernel.kallsyms] [k] __wake_up 1.69% ip [kernel.kallsyms] [k] strlen 1.17% ip [kernel.kallsyms] [k] __wake_up_common 1.09% ip [kernel.kallsyms] [k] insert_header 1.04% ip [kernel.kallsyms] [k] page_remove_rmap 1.01% ip [kernel.kallsyms] [k] consume_skb 0.98% ip [kernel.kallsyms] [k] netlink_trim 0.51% ip [kernel.kallsyms] [k] kernfs_link_sibling 0.51% ip [kernel.kallsyms] [k] filemap_map_pages 0.46% ip [kernel.kallsyms] [k] memcpy_erms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 23:27:06 +00:00
lseq = net->ipv6.ip6addrlbl_table.seq;
rcu_read_unlock();
if (!p) {
err = -ESRCH;
goto out;
}
skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL);
if (!skb) {
ip6addrlbl_put(p);
return -ENOBUFS;
}
err = ip6addrlbl_fill(skb, p, lseq,
NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
RTM_NEWADDRLABEL, 0);
ip6addrlbl_put(p);
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto out;
}
err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
out:
return err;
}
void __init ipv6_addr_label_rtnl_register(void)
{
__rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel,
NULL, RTNL_FLAG_DOIT_UNLOCKED);
__rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel,
NULL, RTNL_FLAG_DOIT_UNLOCKED);
__rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get,
ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED);
}