linux/net/ipv6/ip6_flowlabel.c

910 lines
20 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* ip6_flowlabel.c IPv6 flowlabel manager.
*
* 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 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/pid_namespace.h>
#include <linux/jump_label_ratelimit.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>
2017-10-05 02:27:04 +03:00
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_STATIC_KEY_DEFERRED_FALSE(ipv6_flowlabel_exclusive, HZ);
EXPORT_SYMBOL(ipv6_flowlabel_exclusive);
#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 bool fl_shared_exclusive(struct ip6_flowlabel *fl)
{
return fl->share == IPV6_FL_S_EXCL ||
fl->share == IPV6_FL_S_PROCESS ||
fl->share == IPV6_FL_S_USER;
}
ipv6/flowlabel: wait rcu grace period before put_pid() syzbot was able to catch a use-after-free read in pid_nr_ns() [1] ip6fl_seq_show() seems to use RCU protection, dereferencing fl->owner.pid but fl_free() releases fl->owner.pid before rcu grace period is started. [1] BUG: KASAN: use-after-free in pid_nr_ns+0x128/0x140 kernel/pid.c:407 Read of size 4 at addr ffff888094012a04 by task syz-executor.0/18087 CPU: 0 PID: 18087 Comm: syz-executor.0 Not tainted 5.1.0-rc6+ #89 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:131 pid_nr_ns+0x128/0x140 kernel/pid.c:407 ip6fl_seq_show+0x2f8/0x4f0 net/ipv6/ip6_flowlabel.c:794 seq_read+0xad3/0x1130 fs/seq_file.c:268 proc_reg_read+0x1fe/0x2c0 fs/proc/inode.c:227 do_loop_readv_writev fs/read_write.c:701 [inline] do_loop_readv_writev fs/read_write.c:688 [inline] do_iter_read+0x4a9/0x660 fs/read_write.c:922 vfs_readv+0xf0/0x160 fs/read_write.c:984 kernel_readv fs/splice.c:358 [inline] default_file_splice_read+0x475/0x890 fs/splice.c:413 do_splice_to+0x12a/0x190 fs/splice.c:876 splice_direct_to_actor+0x2d2/0x970 fs/splice.c:953 do_splice_direct+0x1da/0x2a0 fs/splice.c:1062 do_sendfile+0x597/0xd00 fs/read_write.c:1443 __do_sys_sendfile64 fs/read_write.c:1498 [inline] __se_sys_sendfile64 fs/read_write.c:1490 [inline] __x64_sys_sendfile64+0x15a/0x220 fs/read_write.c:1490 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458da9 Code: ad b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b8 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f300d24bc78 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000000458da9 RDX: 00000000200000c0 RSI: 0000000000000008 RDI: 0000000000000007 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000005a R11: 0000000000000246 R12: 00007f300d24c6d4 R13: 00000000004c5fa3 R14: 00000000004da748 R15: 00000000ffffffff Allocated by task 17543: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_kmalloc mm/kasan/common.c:497 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:470 kasan_slab_alloc+0xf/0x20 mm/kasan/common.c:505 slab_post_alloc_hook mm/slab.h:437 [inline] slab_alloc mm/slab.c:3393 [inline] kmem_cache_alloc+0x11a/0x6f0 mm/slab.c:3555 alloc_pid+0x55/0x8f0 kernel/pid.c:168 copy_process.part.0+0x3b08/0x7980 kernel/fork.c:1932 copy_process kernel/fork.c:1709 [inline] _do_fork+0x257/0xfd0 kernel/fork.c:2226 __do_sys_clone kernel/fork.c:2333 [inline] __se_sys_clone kernel/fork.c:2327 [inline] __x64_sys_clone+0xbf/0x150 kernel/fork.c:2327 do_syscall_64+0x103/0x610 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 7789: save_stack+0x45/0xd0 mm/kasan/common.c:75 set_track mm/kasan/common.c:87 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:459 kasan_slab_free+0xe/0x10 mm/kasan/common.c:467 __cache_free mm/slab.c:3499 [inline] kmem_cache_free+0x86/0x260 mm/slab.c:3765 put_pid.part.0+0x111/0x150 kernel/pid.c:111 put_pid+0x20/0x30 kernel/pid.c:105 fl_free+0xbe/0xe0 net/ipv6/ip6_flowlabel.c:102 ip6_fl_gc+0x295/0x3e0 net/ipv6/ip6_flowlabel.c:152 call_timer_fn+0x190/0x720 kernel/time/timer.c:1325 expire_timers kernel/time/timer.c:1362 [inline] __run_timers kernel/time/timer.c:1681 [inline] __run_timers kernel/time/timer.c:1649 [inline] run_timer_softirq+0x652/0x1700 kernel/time/timer.c:1694 __do_softirq+0x266/0x95a kernel/softirq.c:293 The buggy address belongs to the object at ffff888094012a00 which belongs to the cache pid_2 of size 88 The buggy address is located 4 bytes inside of 88-byte region [ffff888094012a00, ffff888094012a58) The buggy address belongs to the page: page:ffffea0002500480 count:1 mapcount:0 mapping:ffff88809a483080 index:0xffff888094012980 flags: 0x1fffc0000000200(slab) raw: 01fffc0000000200 ffffea00018a3508 ffffea0002524a88 ffff88809a483080 raw: ffff888094012980 ffff888094012000 000000010000001b 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888094012900: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff888094012980: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc >ffff888094012a00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ^ ffff888094012a80: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff888094012b00: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc Fixes: 4f82f45730c6 ("net ip6 flowlabel: Make owner a union of struct pid * and kuid_t") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-28 02:49:06 +03:00
static void fl_free_rcu(struct rcu_head *head)
{
struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
if (fl->share == IPV6_FL_S_PROCESS)
put_pid(fl->owner.pid);
kfree(fl->opt);
kfree(fl);
}
static void fl_free(struct ip6_flowlabel *fl)
{
if (!fl)
return;
if (fl_shared_exclusive(fl) || fl->opt)
static_branch_slow_dec_deferred(&ipv6_flowlabel_exclusive);
call_rcu(&fl->rcu, fl_free_rcu);
}
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 16:06:23 +03:00
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 16:06:23 +03:00
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(get_random_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 && atomic_inc_not_zero(&fl->users)) {
fl->lastuse = jiffies;
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 22:26:23 +03:00
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,
sockptr_t 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 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_sockptr_offset(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);
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;
}
if (fl_shared_exclusive(fl) || fl->opt) {
WRITE_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl, 1);
ipv6: fix static key imbalance in fl_create() fl_create() should call static_branch_deferred_inc() only in case of success. Also we should not call fl_free() in error path, as this could cause a static key imbalance. jump label: negative count! WARNING: CPU: 0 PID: 15907 at kernel/jump_label.c:221 static_key_slow_try_dec kernel/jump_label.c:221 [inline] WARNING: CPU: 0 PID: 15907 at kernel/jump_label.c:221 static_key_slow_try_dec+0x1ab/0x1d0 kernel/jump_label.c:206 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 15907 Comm: syz-executor.2 Not tainted 5.2.0-rc6+ #62 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 panic+0x2cb/0x744 kernel/panic.c:219 __warn.cold+0x20/0x4d kernel/panic.c:576 report_bug+0x263/0x2b0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:179 [inline] fixup_bug arch/x86/kernel/traps.c:174 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:986 RIP: 0010:static_key_slow_try_dec kernel/jump_label.c:221 [inline] RIP: 0010:static_key_slow_try_dec+0x1ab/0x1d0 kernel/jump_label.c:206 Code: c0 e8 e9 3e e5 ff 83 fb 01 0f 85 32 ff ff ff e8 5b 3d e5 ff 45 31 ff eb a0 e8 51 3d e5 ff 48 c7 c7 40 99 92 87 e8 13 75 b7 ff <0f> 0b eb 8b 4c 89 e7 e8 a9 c0 1e 00 e9 de fe ff ff e8 bf 6d b7 ff RSP: 0018:ffff88805f9c7450 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 0000000000000000 RDX: 000000000000e3e1 RSI: ffffffff815adb06 RDI: ffffed100bf38e7c RBP: ffff88805f9c74e0 R08: ffff88806acf0700 R09: ffffed1015d060a9 R10: ffffed1015d060a8 R11: ffff8880ae830547 R12: ffffffff89832ce0 R13: ffff88805f9c74b8 R14: 1ffff1100bf38e8b R15: 00000000ffffff01 __static_key_slow_dec_deferred+0x65/0x110 kernel/jump_label.c:272 fl_free+0xa9/0xe0 net/ipv6/ip6_flowlabel.c:121 fl_create+0x6af/0x9f0 net/ipv6/ip6_flowlabel.c:457 ipv6_flowlabel_opt+0x80e/0x2730 net/ipv6/ip6_flowlabel.c:624 do_ipv6_setsockopt.isra.0+0x2119/0x4100 net/ipv6/ipv6_sockglue.c:825 ipv6_setsockopt+0xf6/0x170 net/ipv6/ipv6_sockglue.c:944 tcp_setsockopt net/ipv4/tcp.c:3131 [inline] tcp_setsockopt+0x8f/0xe0 net/ipv4/tcp.c:3125 sock_common_setsockopt+0x94/0xd0 net/core/sock.c:3130 __sys_setsockopt+0x253/0x4b0 net/socket.c:2080 __do_sys_setsockopt net/socket.c:2096 [inline] __se_sys_setsockopt net/socket.c:2093 [inline] __x64_sys_setsockopt+0xbe/0x150 net/socket.c:2093 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4597c9 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2670556c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00000000004597c9 RDX: 0000000000000020 RSI: 0000000000000029 RDI: 0000000000000003 RBP: 000000000075bfc8 R08: 000000000000fdf7 R09: 0000000000000000 R10: 0000000020000000 R11: 0000000000000246 R12: 00007f26705576d4 R13: 00000000004cec00 R14: 00000000004dd520 R15: 00000000ffffffff Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Willem de Bruijn <willemb@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-10 16:40:11 +03:00
static_branch_deferred_inc(&ipv6_flowlabel_exclusive);
}
return fl;
done:
ipv6: fix static key imbalance in fl_create() fl_create() should call static_branch_deferred_inc() only in case of success. Also we should not call fl_free() in error path, as this could cause a static key imbalance. jump label: negative count! WARNING: CPU: 0 PID: 15907 at kernel/jump_label.c:221 static_key_slow_try_dec kernel/jump_label.c:221 [inline] WARNING: CPU: 0 PID: 15907 at kernel/jump_label.c:221 static_key_slow_try_dec+0x1ab/0x1d0 kernel/jump_label.c:206 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 15907 Comm: syz-executor.2 Not tainted 5.2.0-rc6+ #62 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 panic+0x2cb/0x744 kernel/panic.c:219 __warn.cold+0x20/0x4d kernel/panic.c:576 report_bug+0x263/0x2b0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:179 [inline] fixup_bug arch/x86/kernel/traps.c:174 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:272 do_invalid_op+0x37/0x50 arch/x86/kernel/traps.c:291 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:986 RIP: 0010:static_key_slow_try_dec kernel/jump_label.c:221 [inline] RIP: 0010:static_key_slow_try_dec+0x1ab/0x1d0 kernel/jump_label.c:206 Code: c0 e8 e9 3e e5 ff 83 fb 01 0f 85 32 ff ff ff e8 5b 3d e5 ff 45 31 ff eb a0 e8 51 3d e5 ff 48 c7 c7 40 99 92 87 e8 13 75 b7 ff <0f> 0b eb 8b 4c 89 e7 e8 a9 c0 1e 00 e9 de fe ff ff e8 bf 6d b7 ff RSP: 0018:ffff88805f9c7450 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 0000000000000000 RDX: 000000000000e3e1 RSI: ffffffff815adb06 RDI: ffffed100bf38e7c RBP: ffff88805f9c74e0 R08: ffff88806acf0700 R09: ffffed1015d060a9 R10: ffffed1015d060a8 R11: ffff8880ae830547 R12: ffffffff89832ce0 R13: ffff88805f9c74b8 R14: 1ffff1100bf38e8b R15: 00000000ffffff01 __static_key_slow_dec_deferred+0x65/0x110 kernel/jump_label.c:272 fl_free+0xa9/0xe0 net/ipv6/ip6_flowlabel.c:121 fl_create+0x6af/0x9f0 net/ipv6/ip6_flowlabel.c:457 ipv6_flowlabel_opt+0x80e/0x2730 net/ipv6/ip6_flowlabel.c:624 do_ipv6_setsockopt.isra.0+0x2119/0x4100 net/ipv6/ipv6_sockglue.c:825 ipv6_setsockopt+0xf6/0x170 net/ipv6/ipv6_sockglue.c:944 tcp_setsockopt net/ipv4/tcp.c:3131 [inline] tcp_setsockopt+0x8f/0xe0 net/ipv4/tcp.c:3125 sock_common_setsockopt+0x94/0xd0 net/core/sock.c:3130 __sys_setsockopt+0x253/0x4b0 net/socket.c:2080 __do_sys_setsockopt net/socket.c:2096 [inline] __se_sys_setsockopt net/socket.c:2093 [inline] __x64_sys_setsockopt+0xbe/0x150 net/socket.c:2093 do_syscall_64+0xfd/0x680 arch/x86/entry/common.c:301 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4597c9 Code: fd b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 cb b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f2670556c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00000000004597c9 RDX: 0000000000000020 RSI: 0000000000000029 RDI: 0000000000000003 RBP: 000000000075bfc8 R08: 000000000000fdf7 R09: 0000000000000000 R10: 0000000020000000 R11: 0000000000000246 R12: 00007f26705576d4 R13: 00000000004cec00 R14: 00000000004dd520 R15: 00000000ffffffff Kernel Offset: disabled Rebooting in 86400 seconds.. Fixes: 59c820b2317f ("ipv6: elide flowlabel check if no exclusive leases exist") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Willem de Bruijn <willemb@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-10 16:40:11 +03:00
if (fl) {
kfree(fl->opt);
kfree(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;
}
#define socklist_dereference(__sflp) \
rcu_dereference_protected(__sflp, lockdep_is_held(&ip6_sk_fl_lock))
static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6_fl_socklist __rcu **sflp;
struct ipv6_fl_socklist *sfl;
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 = socklist_dereference(*sflp)) != NULL;
sflp = &sfl->next) {
if (sfl->fl->label == freq->flr_label)
goto found;
}
spin_unlock_bh(&ip6_sk_fl_lock);
return -ESRCH;
found:
if (freq->flr_label == (np->flow_label & IPV6_FLOWLABEL_MASK))
np->flow_label &= ~IPV6_FLOWLABEL_MASK;
*sflp = sfl->next;
spin_unlock_bh(&ip6_sk_fl_lock);
fl_release(sfl->fl);
kfree_rcu(sfl, rcu);
return 0;
}
static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
struct ipv6_fl_socklist *sfl;
int err;
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();
if (freq->flr_share == IPV6_FL_S_NONE &&
ns_capable(net->user_ns, CAP_NET_ADMIN)) {
struct ip6_flowlabel *fl = fl_lookup(net, freq->flr_label);
if (fl) {
err = fl6_renew(fl, freq->flr_linger,
freq->flr_expires);
fl_release(fl);
return err;
}
}
return -ESRCH;
}
static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq,
sockptr_t optval, int optlen)
{
struct ipv6_fl_socklist *sfl, *sfl1 = NULL;
struct ip6_flowlabel *fl, *fl1 = NULL;
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from David Miller: 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan. 2) Support UDP segmentation in code TSO code, from Eric Dumazet. 3) Allow flashing different flash images in cxgb4 driver, from Vishal Kulkarni. 4) Add drop frames counter and flow status to tc flower offloading, from Po Liu. 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni. 6) Various new indirect call avoidance, from Eric Dumazet and Brian Vazquez. 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from Yonghong Song. 8) Support querying and setting hardware address of a port function via devlink, use this in mlx5, from Parav Pandit. 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson. 10) Switch qca8k driver over to phylink, from Jonathan McDowell. 11) In bpftool, show list of processes holding BPF FD references to maps, programs, links, and btf objects. From Andrii Nakryiko. 12) Several conversions over to generic power management, from Vaibhav Gupta. 13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry Yakunin. 14) Various https url conversions, from Alexander A. Klimov. 15) Timestamping and PHC support for mscc PHY driver, from Antoine Tenart. 16) Support bpf iterating over tcp and udp sockets, from Yonghong Song. 17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov. 18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan. 19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several drivers. From Luc Van Oostenryck. 20) XDP support for xen-netfront, from Denis Kirjanov. 21) Support receive buffer autotuning in MPTCP, from Florian Westphal. 22) Support EF100 chip in sfc driver, from Edward Cree. 23) Add XDP support to mvpp2 driver, from Matteo Croce. 24) Support MPTCP in sock_diag, from Paolo Abeni. 25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic infrastructure, from Jakub Kicinski. 26) Several pci_ --> dma_ API conversions, from Christophe JAILLET. 27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel. 28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki. 29) Refactor a lot of networking socket option handling code in order to avoid set_fs() calls, from Christoph Hellwig. 30) Add rfc4884 support to icmp code, from Willem de Bruijn. 31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei. 32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin. 33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin. 34) Support TCP syncookies in MPTCP, from Flowian Westphal. 35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano Brivio. * git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits) net: thunderx: initialize VF's mailbox mutex before first usage usb: hso: remove bogus check for EINPROGRESS usb: hso: no complaint about kmalloc failure hso: fix bailout in error case of probe ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM selftests/net: relax cpu affinity requirement in msg_zerocopy test mptcp: be careful on subflow creation selftests: rtnetlink: make kci_test_encap() return sub-test result selftests: rtnetlink: correct the final return value for the test net: dsa: sja1105: use detected device id instead of DT one on mismatch tipc: set ub->ifindex for local ipv6 address ipv6: add ipv6_dev_find() net: openvswitch: silence suspicious RCU usage warning Revert "vxlan: fix tos value before xmit" ptp: only allow phase values lower than 1 period farsync: switch from 'pci_' to 'dma_' API wan: wanxl: switch from 'pci_' to 'dma_' API hv_netvsc: do not use VF device if link is down dpaa2-eth: Fix passing zero to 'PTR_ERR' warning net: macb: Properly handle phylink on at91sam9x ...
2020-08-06 06:13:21 +03:00
int err;
if (freq->flr_flags & IPV6_FL_F_REFLECT) {
if (net->ipv6.sysctl.flowlabel_consistency) {
net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n");
return -EPERM;
}
if (sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
np->repflow = 1;
return 0;
}
if (freq->flr_label & ~IPV6_FLOWLABEL_MASK)
return -EINVAL;
if (net->ipv6.sysctl.flowlabel_state_ranges &&
(freq->flr_label & IPV6_FLOWLABEL_STATELESS_FLAG))
return -ERANGE;
ipv6: Flow label state ranges This patch divides the IPv6 flow label space into two ranges: 0-7ffff is reserved for flow label manager, 80000-fffff will be used for creating auto flow labels (per RFC6438). This only affects how labels are set on transmit, it does not affect receive. This range split can be disbaled by systcl. Background: IPv6 flow labels have been an unmitigated disappointment thus far in the lifetime of IPv6. Support in HW devices to use them for ECMP is lacking, and OSes don't turn them on by default. If we had these we could get much better hashing in IPv6 networks without resorting to DPI, possibly eliminating some of the motivations to to define new encaps in UDP just for getting ECMP. Unfortunately, the initial specfications of IPv6 did not clarify how they are to be used. There has always been a vague concept that these can be used for ECMP, flow hashing, etc. and we do now have a good standard how to this in RFC6438. The problem is that flow labels can be either stateful or stateless (as in RFC6438), and we are presented with the possibility that a stateless label may collide with a stateful one. Attempts to split the flow label space were rejected in IETF. When we added support in Linux for RFC6438, we could not turn on flow labels by default due to this conflict. This patch splits the flow label space and should give us a path to enabling auto flow labels by default for all IPv6 packets. This is an API change so we need to consider compatibility with existing deployment. The stateful range is chosen to be the lower values in hopes that most uses would have chosen small numbers. Once we resolve the stateless/stateful issue, we can proceed to look at enabling RFC6438 flow labels by default (starting with scaled testing). Signed-off-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-30 01:33:21 +03:00
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;
if (!atomic_inc_not_zero(&fl1->users))
fl1 = NULL;
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) {
size_t offset = offsetof(struct in6_flowlabel_req, flr_label);
if (copy_to_sockptr_offset(optval, offset, &fl->label,
sizeof(fl->label))) {
/* Intentionally ignore fault. */
}
}
fl_link(np, sfl1, fl);
return 0;
done:
fl_free(fl);
kfree(sfl1);
return err;
}
int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen)
{
struct in6_flowlabel_req freq;
if (optlen < sizeof(freq))
return -EINVAL;
if (copy_from_sockptr(&freq, optval, sizeof(freq)))
return -EFAULT;
switch (freq.flr_action) {
case IPV6_FL_A_PUT:
return ipv6_flowlabel_put(sk, &freq);
case IPV6_FL_A_RENEW:
return ipv6_flowlabel_renew(sk, &freq);
case IPV6_FL_A_GET:
return ipv6_flowlabel_get(sk, &freq, optval, optlen);
default:
return -EINVAL;
}
}
#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)
{
struct ip6fl_iter_state *state = ip6fl_seq_private(seq);
state->pid_ns = proc_pid_ns(file_inode(seq->file)->i_sb);
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 __net_init ip6_flowlabel_proc_init(struct net *net)
{
if (!proc_create_net("ip6_flowlabel", 0444, net->proc_net,
&ip6fl_seq_ops, sizeof(struct ip6fl_iter_state)))
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)
{
static_key_deferred_flush(&ipv6_flowlabel_exclusive);
del_timer(&ip6_fl_gc_timer);
unregister_pernet_subsys(&ip6_flowlabel_net_ops);
}