linux/net/ipv6/ip6_flowlabel.c

888 lines
20 KiB
C
Raw Normal View History

/*
* ip6_flowlabel.c IPv6 flowlabel manager.
*
* 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>
*/
#include <linux/capability.h>
#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 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/pid_namespace.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <linux/uaccess.h>
#define FL_MIN_LINGER 6 /* Minimal linger. It is set to 6sec specified
in old IPv6 RFC. Well, it was reasonable value.
*/
#define FL_MAX_LINGER 150 /* Maximal linger timeout */
/* 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);
static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1];
static void ip6_fl_gc(struct timer_list *unused);
timer: Remove expires and data arguments from DEFINE_TIMER Drop the arguments from the macro and adjust all callers with the following script: perl -pi -e 's/DEFINE_TIMER\((.*), 0, 0\);/DEFINE_TIMER($1);/g;' \ $(git grep DEFINE_TIMER | cut -d: -f1 | sort -u | grep -v timer.h) Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> # for m68k parts Acked-by: Guenter Roeck <linux@roeck-us.net> # for watchdog parts Acked-by: David S. Miller <davem@davemloft.net> # for networking parts Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Kalle Valo <kvalo@codeaurora.org> # for wireless parts Acked-by: Arnd Bergmann <arnd@arndb.de> Cc: linux-mips@linux-mips.org Cc: Petr Mladek <pmladek@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Kalle Valo <kvalo@qca.qualcomm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com> Cc: Wim Van Sebroeck <wim@iguana.be> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ursula Braun <ubraun@linux.vnet.ibm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Harish Patil <harish.patil@cavium.com> Cc: Stephen Boyd <sboyd@codeaurora.org> Cc: Michael Reed <mdr@sgi.com> Cc: Manish Chopra <manish.chopra@cavium.com> Cc: Len Brown <len.brown@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Julian Wiedmann <jwi@linux.vnet.ibm.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Mark Gross <mark.gross@intel.com> Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Guenter Roeck <linux@roeck-us.net> Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee <sudipm.mukherjee@gmail.com> Link: https://lkml.kernel.org/r/1507159627-127660-11-git-send-email-keescook@chromium.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2017-10-04 23:27:04 +00:00
static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc);
/* FL hash table lock: it protects only of GC */
static DEFINE_SPINLOCK(ip6_fl_lock);
/* Big socket sock */
static DEFINE_SPINLOCK(ip6_sk_fl_lock);
#define for_each_fl_rcu(hash, fl) \
for (fl = rcu_dereference_bh(fl_ht[(hash)]); \
fl != NULL; \
fl = rcu_dereference_bh(fl->next))
#define for_each_fl_continue_rcu(fl) \
for (fl = rcu_dereference_bh(fl->next); \
fl != NULL; \
fl = rcu_dereference_bh(fl->next))
#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))
static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label)
{
struct ip6_flowlabel *fl;
for_each_fl_rcu(FL_HASH(label), fl) {
if (fl->label == label && net_eq(fl->fl_net, net))
return fl;
}
return NULL;
}
static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
{
struct ip6_flowlabel *fl;
rcu_read_lock_bh();
fl = __fl_lookup(net, label);
if (fl && !atomic_inc_not_zero(&fl->users))
fl = NULL;
rcu_read_unlock_bh();
return fl;
}
static void fl_free(struct ip6_flowlabel *fl)
{
if (fl) {
if (fl->share == IPV6_FL_S_PROCESS)
put_pid(fl->owner.pid);
kfree(fl->opt);
kfree_rcu(fl, rcu);
}
}
static void fl_release(struct ip6_flowlabel *fl)
{
spin_lock_bh(&ip6_fl_lock);
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);
}
spin_unlock_bh(&ip6_fl_lock);
}
static void ip6_fl_gc(struct timer_list *unused)
{
int i;
unsigned long now = jiffies;
unsigned long sched = 0;
spin_lock(&ip6_fl_lock);
for (i = 0; i <= FL_HASH_MASK; i++) {
struct ip6_flowlabel *fl;
struct ip6_flowlabel __rcu **flp;
flp = &fl_ht[i];
while ((fl = rcu_dereference_protected(*flp,
lockdep_is_held(&ip6_fl_lock))) != NULL) {
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) {
mod_timer(&ip6_fl_gc_timer, sched);
}
spin_unlock(&ip6_fl_lock);
}
static void __net_exit ip6_fl_purge(struct net *net)
{
int i;
ipv6: fix possible deadlock in ip6_fl_purge / ip6_fl_gc Use spin_lock_bh in ip6_fl_purge() to prevent following potentially deadlock scenario between ip6_fl_purge() and ip6_fl_gc() timer. ================================= [ INFO: inconsistent lock state ] 3.19.0 #1 Not tainted --------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. swapper/5/0 [HC0[0]:SC1[1]:HE1:SE0] takes: (ip6_fl_lock){+.?...}, at: [<ffffffff8171155d>] ip6_fl_gc+0x2d/0x180 {SOFTIRQ-ON-W} state was registered at: [<ffffffff810ee9a0>] __lock_acquire+0x4a0/0x10b0 [<ffffffff810efd54>] lock_acquire+0xc4/0x2b0 [<ffffffff81751d2d>] _raw_spin_lock+0x3d/0x80 [<ffffffff81711798>] ip6_flowlabel_net_exit+0x28/0x110 [<ffffffff815f9759>] ops_exit_list.isra.1+0x39/0x60 [<ffffffff815fa320>] cleanup_net+0x100/0x1e0 [<ffffffff810ad80a>] process_one_work+0x20a/0x830 [<ffffffff810adf4b>] worker_thread+0x11b/0x460 [<ffffffff810b42f4>] kthread+0x104/0x120 [<ffffffff81752bfc>] ret_from_fork+0x7c/0xb0 irq event stamp: 84640 hardirqs last enabled at (84640): [<ffffffff81752080>] _raw_spin_unlock_irq+0x30/0x50 hardirqs last disabled at (84639): [<ffffffff81751eff>] _raw_spin_lock_irq+0x1f/0x80 softirqs last enabled at (84628): [<ffffffff81091ad1>] _local_bh_enable+0x21/0x50 softirqs last disabled at (84629): [<ffffffff81093b7d>] irq_exit+0x12d/0x150 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ip6_fl_lock); <Interrupt> lock(ip6_fl_lock); *** DEADLOCK *** Signed-off-by: Jan Stancek <jstancek@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-11 13:06:23 +00:00
spin_lock_bh(&ip6_fl_lock);
for (i = 0; i <= FL_HASH_MASK; i++) {
struct ip6_flowlabel *fl;
struct ip6_flowlabel __rcu **flp;
flp = &fl_ht[i];
while ((fl = rcu_dereference_protected(*flp,
lockdep_is_held(&ip6_fl_lock))) != NULL) {
if (net_eq(fl->fl_net, net) &&
atomic_read(&fl->users) == 0) {
*flp = fl->next;
fl_free(fl);
atomic_dec(&fl_size);
continue;
}
flp = &fl->next;
}
}
ipv6: fix possible deadlock in ip6_fl_purge / ip6_fl_gc Use spin_lock_bh in ip6_fl_purge() to prevent following potentially deadlock scenario between ip6_fl_purge() and ip6_fl_gc() timer. ================================= [ INFO: inconsistent lock state ] 3.19.0 #1 Not tainted --------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. swapper/5/0 [HC0[0]:SC1[1]:HE1:SE0] takes: (ip6_fl_lock){+.?...}, at: [<ffffffff8171155d>] ip6_fl_gc+0x2d/0x180 {SOFTIRQ-ON-W} state was registered at: [<ffffffff810ee9a0>] __lock_acquire+0x4a0/0x10b0 [<ffffffff810efd54>] lock_acquire+0xc4/0x2b0 [<ffffffff81751d2d>] _raw_spin_lock+0x3d/0x80 [<ffffffff81711798>] ip6_flowlabel_net_exit+0x28/0x110 [<ffffffff815f9759>] ops_exit_list.isra.1+0x39/0x60 [<ffffffff815fa320>] cleanup_net+0x100/0x1e0 [<ffffffff810ad80a>] process_one_work+0x20a/0x830 [<ffffffff810adf4b>] worker_thread+0x11b/0x460 [<ffffffff810b42f4>] kthread+0x104/0x120 [<ffffffff81752bfc>] ret_from_fork+0x7c/0xb0 irq event stamp: 84640 hardirqs last enabled at (84640): [<ffffffff81752080>] _raw_spin_unlock_irq+0x30/0x50 hardirqs last disabled at (84639): [<ffffffff81751eff>] _raw_spin_lock_irq+0x1f/0x80 softirqs last enabled at (84628): [<ffffffff81091ad1>] _local_bh_enable+0x21/0x50 softirqs last disabled at (84629): [<ffffffff81093b7d>] irq_exit+0x12d/0x150 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(ip6_fl_lock); <Interrupt> lock(ip6_fl_lock); *** DEADLOCK *** Signed-off-by: Jan Stancek <jstancek@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-11 13:06:23 +00:00
spin_unlock_bh(&ip6_fl_lock);
}
static struct ip6_flowlabel *fl_intern(struct net *net,
struct ip6_flowlabel *fl, __be32 label)
{
struct ip6_flowlabel *lfl;
fl->label = label & IPV6_FLOWLABEL_MASK;
spin_lock_bh(&ip6_fl_lock);
if (label == 0) {
for (;;) {
fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK;
if (fl->label) {
lfl = __fl_lookup(net, fl->label);
if (!lfl)
break;
}
}
} 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
*/
lfl = __fl_lookup(net, fl->label);
if (lfl) {
atomic_inc(&lfl->users);
spin_unlock_bh(&ip6_fl_lock);
return lfl;
}
}
fl->lastuse = jiffies;
fl->next = fl_ht[FL_HASH(fl->label)];
rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl);
atomic_inc(&fl_size);
spin_unlock_bh(&ip6_fl_lock);
return NULL;
}
/* Socket flowlabel lists */
struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label)
{
struct ipv6_fl_socklist *sfl;
struct ipv6_pinfo *np = inet6_sk(sk);
label &= IPV6_FLOWLABEL_MASK;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl) {
struct ip6_flowlabel *fl = sfl->fl;
if (fl->label == label) {
fl->lastuse = jiffies;
atomic_inc(&fl->users);
rcu_read_unlock_bh();
return fl;
}
}
rcu_read_unlock_bh();
return NULL;
}
EXPORT_SYMBOL_GPL(fl6_sock_lookup);
void fl6_free_socklist(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_fl_socklist *sfl;
if (!rcu_access_pointer(np->ipv6_fl_list))
return;
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);
fl_release(sfl->fl);
kfree_rcu(sfl, rcu);
spin_lock_bh(&ip6_sk_fl_lock);
}
spin_unlock_bh(&ip6_sk_fl_lock);
}
/* Service routines */
/*
It is the only difficult place. flowlabel enforces equal headers
before and including routing header, however user may supply options
following rthdr.
*/
struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space,
struct ip6_flowlabel *fl,
struct ipv6_txoptions *fopt)
{
struct ipv6_txoptions *fl_opt = fl->opt;
if (!fopt || fopt->opt_flen == 0)
return fl_opt;
if (fl_opt) {
opt_space->hopopt = fl_opt->hopopt;
opt_space->dst0opt = fl_opt->dst0opt;
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;
ipv6: flowlabel: do not leave opt->tot_len with garbage When syzkaller team brought us a C repro for the crash [1] that had been reported many times in the past, I finally could find the root cause. If FlowLabel info is merged by fl6_merge_options(), we leave part of the opt_space storage provided by udp/raw/l2tp with random value in opt_space.tot_len, unless a control message was provided at sendmsg() time. Then ip6_setup_cork() would use this random value to perform a kzalloc() call. Undefined behavior and crashes. Fix is to properly set tot_len in fl6_merge_options() At the same time, we can also avoid consuming memory and cpu cycles to clear it, if every option is copied via a kmemdup(). This is the change in ip6_setup_cork(). [1] kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 6613 Comm: syz-executor0 Not tainted 4.14.0-rc4+ #127 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801cb64a100 task.stack: ffff8801cc350000 RIP: 0010:ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168 RSP: 0018:ffff8801cc357550 EFLAGS: 00010203 RAX: dffffc0000000000 RBX: ffff8801cc357748 RCX: 0000000000000010 RDX: 0000000000000002 RSI: ffffffff842bd1d9 RDI: 0000000000000014 RBP: ffff8801cc357620 R08: ffff8801cb17f380 R09: ffff8801cc357b10 R10: ffff8801cb64a100 R11: 0000000000000000 R12: ffff8801cc357ab0 R13: ffff8801cc357b10 R14: 0000000000000000 R15: ffff8801c3bbf0c0 FS: 00007f9c5c459700(0000) GS:ffff8801db200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020324000 CR3: 00000001d1cf2000 CR4: 00000000001406f0 DR0: 0000000020001010 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600 Call Trace: ip6_make_skb+0x282/0x530 net/ipv6/ip6_output.c:1729 udpv6_sendmsg+0x2769/0x3380 net/ipv6/udp.c:1340 inet_sendmsg+0x11f/0x5e0 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 [inline] sock_sendmsg+0xca/0x110 net/socket.c:643 SYSC_sendto+0x358/0x5a0 net/socket.c:1750 SyS_sendto+0x40/0x50 net/socket.c:1718 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x4520a9 RSP: 002b:00007f9c5c458c08 EFLAGS: 00000216 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 00000000004520a9 RDX: 0000000000000001 RSI: 0000000020fd1000 RDI: 0000000000000016 RBP: 0000000000000086 R08: 0000000020e0afe4 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000216 R12: 00000000004bb1ee R13: 00000000ffffffff R14: 0000000000000016 R15: 0000000000000029 Code: e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 ea 0f 00 00 48 8d 79 04 48 b8 00 00 00 00 00 fc ff df 45 8b 74 24 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 RIP: ip6_setup_cork+0x274/0x15c0 net/ipv6/ip6_output.c:1168 RSP: ffff8801cc357550 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-21 19:26:23 +00:00
opt_space->tot_len = fopt->tot_len;
return opt_space;
}
EXPORT_SYMBOL_GPL(fl6_merge_options);
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;
spin_lock_bh(&ip6_fl_lock);
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;
spin_unlock_bh(&ip6_fl_lock);
return 0;
}
static struct ip6_flowlabel *
fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
char __user *optval, int optlen, int *err_p)
{
struct ip6_flowlabel *fl = NULL;
int olen;
int addr_type;
int err;
olen = optlen - CMSG_ALIGN(sizeof(*freq));
err = -EINVAL;
if (olen > 64 * 1024)
goto done;
err = -ENOMEM;
fl = kzalloc(sizeof(*fl), GFP_KERNEL);
if (!fl)
goto done;
if (olen > 0) {
struct msghdr msg;
struct flowi6 flowi6;
struct sockcm_cookie sockc_junk;
struct ipcm6_cookie ipc6;
err = -ENOMEM;
fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL);
if (!fl->opt)
goto done;
memset(fl->opt, 0, sizeof(*fl->opt));
fl->opt->tot_len = sizeof(*fl->opt) + olen;
err = -EFAULT;
if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen))
goto done;
msg.msg_controllen = olen;
msg.msg_control = (void *)(fl->opt+1);
memset(&flowi6, 0, sizeof(flowi6));
ipc6.opt = fl->opt;
err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6, &sockc_junk);
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;
}
}
fl->fl_net = net;
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);
if ((addr_type & IPV6_ADDR_MAPPED) ||
addr_type == IPV6_ADDR_ANY) {
err = -EINVAL;
goto done;
}
fl->dst = freq->flr_dst;
atomic_set(&fl->users, 1);
switch (fl->share) {
case IPV6_FL_S_EXCL:
case IPV6_FL_S_ANY:
break;
case IPV6_FL_S_PROCESS:
fl->owner.pid = get_task_pid(current, PIDTYPE_PID);
break;
case IPV6_FL_S_USER:
fl->owner.uid = current_euid();
break;
default:
err = -EINVAL;
goto done;
}
return fl;
done:
fl_free(fl);
*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;
rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl)
count++;
rcu_read_unlock_bh();
if (room <= 0 ||
((count >= FL_MAX_PER_SOCK ||
(count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) &&
!capable(CAP_NET_ADMIN)))
return -ENOBUFS;
return 0;
}
static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl,
struct ip6_flowlabel *fl)
{
spin_lock_bh(&ip6_sk_fl_lock);
sfl->fl = fl;
sfl->next = np->ipv6_fl_list;
rcu_assign_pointer(np->ipv6_fl_list, sfl);
spin_unlock_bh(&ip6_sk_fl_lock);
}
int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq,
int flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_fl_socklist *sfl;
if (flags & IPV6_FL_F_REMOTE) {
freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK;
return 0;
}
if (np->repflow) {
freq->flr_label = np->flow_label;
return 0;
}
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;
}
int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen)
{
int uninitialized_var(err);
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_flowlabel_req freq;
struct ipv6_fl_socklist *sfl1 = NULL;
struct ipv6_fl_socklist *sfl;
struct ipv6_fl_socklist __rcu **sflp;
struct ip6_flowlabel *fl, *fl1 = NULL;
if (optlen < sizeof(freq))
return -EINVAL;
if (copy_from_user(&freq, optval, sizeof(freq)))
return -EFAULT;
switch (freq.flr_action) {
case IPV6_FL_A_PUT:
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;
}
spin_lock_bh(&ip6_sk_fl_lock);
for (sflp = &np->ipv6_fl_list;
(sfl = rcu_dereference_protected(*sflp,
lockdep_is_held(&ip6_sk_fl_lock))) != NULL;
sflp = &sfl->next) {
if (sfl->fl->label == freq.flr_label) {
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;
}
}
spin_unlock_bh(&ip6_sk_fl_lock);
return -ESRCH;
case IPV6_FL_A_RENEW:
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;
}
}
rcu_read_unlock_bh();
net: Allow userns root to control ipv6 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow the SIOCSIFADDR ioctl to add ipv6 addresses. Allow the SIOCDIFADDR ioctl to delete ipv6 addresses. Allow the SIOCADDRT ioctl to add ipv6 routes. Allow the SIOCDELRT ioctl to delete ipv6 routes. Allow creation of ipv6 raw sockets. Allow setting the IPV6_JOIN_ANYCAST socket option. Allow setting the IPV6_FL_A_RENEW parameter of the IPV6_FLOWLABEL_MGR socket option. Allow setting the IPV6_TRANSPARENT socket option. Allow setting the IPV6_HOPOPTS socket option. Allow setting the IPV6_RTHDRDSTOPTS socket option. Allow setting the IPV6_DSTOPTS socket option. Allow setting the IPV6_IPSEC_POLICY socket option. Allow setting the IPV6_XFRM_POLICY socket option. Allow sending packets with the IPV6_2292HOPOPTS control message. Allow sending packets with the IPV6_2292DSTOPTS control message. Allow sending packets with the IPV6_RTHDRDSTOPTS control message. Allow setting the multicast routing socket options on non multicast routing sockets. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, and SIOCDELTUNNEL ioctls for setting up, changing and deleting tunnels over ipv6. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, SIOCDELTUNNEL ioctls for setting up, changing and deleting ipv6 over ipv4 tunnels. Allow the SIOCADDPRL, SIOCDELPRL, SIOCCHGPRL ioctls for adding, deleting, and changing the potential router list for ISATAP tunnels. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 03:03:06 +00:00
if (freq.flr_share == IPV6_FL_S_NONE &&
ns_capable(net->user_ns, CAP_NET_ADMIN)) {
fl = fl_lookup(net, freq.flr_label);
if (fl) {
err = fl6_renew(fl, freq.flr_linger, freq.flr_expires);
fl_release(fl);
return err;
}
}
return -ESRCH;
case IPV6_FL_A_GET:
if (freq.flr_flags & IPV6_FL_F_REFLECT) {
struct net *net = sock_net(sk);
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;
}
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
np->repflow = 1;
return 0;
}
if (freq.flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
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>
2015-04-29 22:33:21 +00:00
if (net->ipv6.sysctl.flowlabel_state_ranges &&
(freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
return -ERANGE;
fl = fl_create(net, sk, &freq, optval, optlen, &err);
if (!fl)
return err;
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;
}
fl1 = sfl->fl;
atomic_inc(&fl1->users);
break;
}
}
rcu_read_unlock_bh();
if (!fl1)
fl1 = fl_lookup(net, freq.flr_label);
if (fl1) {
recheck:
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;
release:
fl_release(fl1);
goto done;
}
}
err = -ENOENT;
if (!(freq.flr_flags&IPV6_FL_F_CREATE))
goto done;
err = -ENOMEM;
if (!sfl1)
goto done;
err = mem_check(sk);
if (err != 0)
goto done;
fl1 = fl_intern(net, fl, freq.flr_label);
if (fl1)
goto recheck;
if (!freq.flr_label) {
if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label,
&fl->label, sizeof(fl->label))) {
/* Intentionally ignore fault. */
}
}
fl_link(np, sfl1, fl);
return 0;
default:
return -EINVAL;
}
done:
fl_free(fl);
kfree(sfl1);
return err;
}
#ifdef CONFIG_PROC_FS
struct ip6fl_iter_state {
struct seq_net_private p;
struct pid_namespace *pid_ns;
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);
struct net *net = seq_file_net(seq);
for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) {
for_each_fl_rcu(state->bucket, fl) {
if (net_eq(fl->fl_net, net))
goto out;
}
}
fl = NULL;
out:
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);
struct net *net = seq_file_net(seq);
for_each_fl_continue_rcu(fl) {
if (net_eq(fl->fl_net, net))
goto out;
}
try_again:
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;
}
fl = NULL;
out:
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)
__acquires(RCU)
{
rcu_read_lock_bh();
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)
__releases(RCU)
{
rcu_read_unlock_bh();
}
static int ip6fl_seq_show(struct seq_file *seq, void *v)
{
struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
if (v == SEQ_START_TOKEN) {
seq_puts(seq, "Label S Owner Users Linger Expires Dst Opt\n");
} else {
struct ip6_flowlabel *fl = v;
seq_printf(seq,
"%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n",
(unsigned int)ntohl(fl->label),
fl->share,
((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)),
atomic_read(&fl->users),
fl->linger/HZ,
(long)(fl->expires - jiffies)/HZ,
&fl->dst,
fl->opt ? fl->opt->opt_nflen : 0);
}
return 0;
}
static const struct seq_operations ip6fl_seq_ops = {
.start = ip6fl_seq_start,
.next = ip6fl_seq_next,
.stop = ip6fl_seq_stop,
.show = ip6fl_seq_show,
};
static int ip6fl_seq_open(struct inode *inode, struct file *file)
{
struct seq_file *seq;
struct ip6fl_iter_state *state;
int err;
err = seq_open_net(inode, file, &ip6fl_seq_ops,
sizeof(struct ip6fl_iter_state));
if (!err) {
seq = file->private_data;
state = ip6fl_seq_private(seq);
rcu_read_lock();
state->pid_ns = get_pid_ns(task_active_pid_ns(current));
rcu_read_unlock();
}
return err;
}
static int ip6fl_seq_release(struct inode *inode, struct file *file)
{
struct seq_file *seq = file->private_data;
struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
put_pid_ns(state->pid_ns);
return seq_release_net(inode, file);
}
static const struct file_operations ip6fl_seq_fops = {
.open = ip6fl_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = ip6fl_seq_release,
};
static int __net_init ip6_flowlabel_proc_init(struct net *net)
{
if (!proc_create("ip6_flowlabel", S_IRUGO, net->proc_net,
&ip6fl_seq_fops))
return -ENOMEM;
return 0;
}
static void __net_exit ip6_flowlabel_proc_fini(struct net *net)
{
remove_proc_entry("ip6_flowlabel", net->proc_net);
}
#else
static inline int ip6_flowlabel_proc_init(struct net *net)
{
return 0;
}
static inline void ip6_flowlabel_proc_fini(struct net *net)
{
}
#endif
static void __net_exit ip6_flowlabel_net_exit(struct net *net)
{
ip6_fl_purge(net);
ip6_flowlabel_proc_fini(net);
}
static struct pernet_operations ip6_flowlabel_net_ops = {
.init = ip6_flowlabel_proc_init,
.exit = ip6_flowlabel_net_exit,
};
int ip6_flowlabel_init(void)
{
return register_pernet_subsys(&ip6_flowlabel_net_ops);
}
void ip6_flowlabel_cleanup(void)
{
del_timer(&ip6_fl_gc_timer);
unregister_pernet_subsys(&ip6_flowlabel_net_ops);
}