linux/kernel/ucount.c

240 lines
5.5 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/hash.h>
headers: untangle kmemleak.h from mm.h Currently <linux/slab.h> #includes <linux/kmemleak.h> for no obvious reason. It looks like it's only a convenience, so remove kmemleak.h from slab.h and add <linux/kmemleak.h> to any users of kmemleak_* that don't already #include it. Also remove <linux/kmemleak.h> from source files that do not use it. This is tested on i386 allmodconfig and x86_64 allmodconfig. It would be good to run it through the 0day bot for other $ARCHes. I have neither the horsepower nor the storage space for the other $ARCHes. Update: This patch has been extensively build-tested by both the 0day bot & kisskb/ozlabs build farms. Both of them reported 2 build failures for which patches are included here (in v2). [ slab.h is the second most used header file after module.h; kernel.h is right there with slab.h. There could be some minor error in the counting due to some #includes having comments after them and I didn't combine all of those. ] [akpm@linux-foundation.org: security/keys/big_key.c needs vmalloc.h, per sfr] Link: http://lkml.kernel.org/r/e4309f98-3749-93e1-4bb7-d9501a39d015@infradead.org Link: http://kisskb.ellerman.id.au/kisskb/head/13396/ Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Reviewed-by: Ingo Molnar <mingo@kernel.org> Reported-by: Michael Ellerman <mpe@ellerman.id.au> [2 build failures] Reported-by: Fengguang Wu <fengguang.wu@intel.com> [2 build failures] Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Wei Yongjun <weiyongjun1@huawei.com> Cc: Luis R. Rodriguez <mcgrof@kernel.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mimi Zohar <zohar@linux.vnet.ibm.com> Cc: John Johansen <john.johansen@canonical.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-05 23:25:34 +00:00
#include <linux/kmemleak.h>
#include <linux/user_namespace.h>
#define UCOUNTS_HASHTABLE_BITS 10
static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
static DEFINE_SPINLOCK(ucounts_lock);
#define ucounts_hashfn(ns, uid) \
hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \
UCOUNTS_HASHTABLE_BITS)
#define ucounts_hashentry(ns, uid) \
(ucounts_hashtable + ucounts_hashfn(ns, uid))
#ifdef CONFIG_SYSCTL
static struct ctl_table_set *
set_lookup(struct ctl_table_root *root)
{
return &current_user_ns()->set;
}
static int set_is_seen(struct ctl_table_set *set)
{
return &current_user_ns()->set == set;
}
static int set_permissions(struct ctl_table_header *head,
struct ctl_table *table)
{
struct user_namespace *user_ns =
container_of(head->set, struct user_namespace, set);
int mode;
/* Allow users with CAP_SYS_RESOURCE unrestrained access */
if (ns_capable(user_ns, CAP_SYS_RESOURCE))
mode = (table->mode & S_IRWXU) >> 6;
else
/* Allow all others at most read-only access */
mode = table->mode & S_IROTH;
return (mode << 6) | (mode << 3) | mode;
}
static struct ctl_table_root set_root = {
.lookup = set_lookup,
.permissions = set_permissions,
};
#define UCOUNT_ENTRY(name) \
{ \
.procname = name, \
.maxlen = sizeof(int), \
.mode = 0644, \
.proc_handler = proc_dointvec_minmax, \
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-18 22:58:50 +00:00
.extra1 = SYSCTL_ZERO, \
.extra2 = SYSCTL_INT_MAX, \
}
static struct ctl_table user_table[] = {
UCOUNT_ENTRY("max_user_namespaces"),
UCOUNT_ENTRY("max_pid_namespaces"),
UCOUNT_ENTRY("max_uts_namespaces"),
UCOUNT_ENTRY("max_ipc_namespaces"),
UCOUNT_ENTRY("max_net_namespaces"),
UCOUNT_ENTRY("max_mnt_namespaces"),
UCOUNT_ENTRY("max_cgroup_namespaces"),
#ifdef CONFIG_INOTIFY_USER
UCOUNT_ENTRY("max_inotify_instances"),
UCOUNT_ENTRY("max_inotify_watches"),
#endif
{ }
};
#endif /* CONFIG_SYSCTL */
bool setup_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
setup_sysctl_set(&ns->set, &set_root, set_is_seen);
tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL);
if (tbl) {
int i;
for (i = 0; i < UCOUNT_COUNTS; i++) {
tbl[i].data = &ns->ucount_max[i];
}
ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl);
}
if (!ns->sysctls) {
kfree(tbl);
retire_sysctl_set(&ns->set);
return false;
}
#endif
return true;
}
void retire_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
tbl = ns->sysctls->ctl_table_arg;
unregister_sysctl_table(ns->sysctls);
retire_sysctl_set(&ns->set);
kfree(tbl);
#endif
}
static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent)
{
struct ucounts *ucounts;
hlist_for_each_entry(ucounts, hashent, node) {
if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns))
return ucounts;
}
return NULL;
}
static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
{
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov <dvyukov@google.com> reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [<ffff2000081678c8>] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [<ffff2000081c82d8>] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [<ffff2000081c97a8>] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [<ffff200008167c28>] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [<ffff200008481850>] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [<ffff200008487298>] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [<ffff200009bd6674>] mnt_init+0x258/0x384 fs/namespace.c:3251 > [<ffff200009bd60bc>] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [<ffff200009bb1114>] start_kernel+0x414/0x460 init/main.c:648 > [<ffff200009bb01e8>] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [<ffff200008210414>] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [<ffff20000820fe80>] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [<ffff20000811b4c4>] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [<ffff20000811c994>] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > <Interrupt> > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [<ffff200008210390>] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [<ffff20000808fa60>] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [<ffff20000808fec0>] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [<ffff2000088a99e0>] dump_stack+0x110/0x168 > [<ffff2000082fa2b4>] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [<ffff2000081c89ec>] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [<ffff2000081c9a60>] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [<ffff2000081678c8>] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [<ffff200008168364>] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [<ffff200008293dc8>] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [<ffff2000082103d8>] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [<ffff2000080821dc>] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [<ffff20000811c994>] irq_exit+0x264/0x308 kernel/softirq.c:405 > [<ffff2000081ecc28>] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [<ffff200008081c80>] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [<ffff2000080837f8>] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [<ffff20000820a47c>] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [<ffff2000081bcbfc>] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [<ffff2000081bd1cc>] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [<ffff200008099f8c>] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov <dvyukov@google.com> Tested-by: Dmitry Vyukov <dvyukov@google.com> Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-20 13:21:35 +00:00
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (!ucounts) {
userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov <dvyukov@google.com> reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [<ffff2000081678c8>] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [<ffff2000081c82d8>] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [<ffff2000081c97a8>] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [<ffff200008167c28>] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [<ffff200008481850>] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [<ffff200008487298>] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [<ffff200009bd6674>] mnt_init+0x258/0x384 fs/namespace.c:3251 > [<ffff200009bd60bc>] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [<ffff200009bb1114>] start_kernel+0x414/0x460 init/main.c:648 > [<ffff200009bb01e8>] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [<ffff200008210414>] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [<ffff20000820fe80>] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [<ffff20000811b4c4>] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [<ffff20000811c994>] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > <Interrupt> > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [<ffff200008210390>] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [<ffff20000808fa60>] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [<ffff20000808fec0>] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [<ffff2000088a99e0>] dump_stack+0x110/0x168 > [<ffff2000082fa2b4>] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [<ffff2000081c89ec>] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [<ffff2000081c9a60>] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [<ffff2000081678c8>] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [<ffff200008168364>] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [<ffff200008293dc8>] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [<ffff2000082103d8>] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [<ffff2000080821dc>] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [<ffff20000811c994>] irq_exit+0x264/0x308 kernel/softirq.c:405 > [<ffff2000081ecc28>] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [<ffff200008081c80>] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [<ffff2000080837f8>] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [<ffff20000820a47c>] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [<ffff2000081bcbfc>] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [<ffff2000081bd1cc>] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [<ffff200008099f8c>] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov <dvyukov@google.com> Tested-by: Dmitry Vyukov <dvyukov@google.com> Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-20 13:21:35 +00:00
spin_unlock_irq(&ucounts_lock);
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return NULL;
new->ns = ns;
new->uid = uid;
new->count = 0;
userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov <dvyukov@google.com> reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [<ffff2000081678c8>] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [<ffff2000081c82d8>] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [<ffff2000081c97a8>] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [<ffff200008167c28>] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [<ffff200008481850>] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [<ffff200008487298>] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [<ffff200009bd6674>] mnt_init+0x258/0x384 fs/namespace.c:3251 > [<ffff200009bd60bc>] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [<ffff200009bb1114>] start_kernel+0x414/0x460 init/main.c:648 > [<ffff200009bb01e8>] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [<ffff200008210414>] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [<ffff20000820fe80>] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [<ffff20000811b4c4>] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [<ffff20000811c994>] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > <Interrupt> > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [<ffff200008210390>] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [<ffff20000808fa60>] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [<ffff20000808fec0>] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [<ffff2000088a99e0>] dump_stack+0x110/0x168 > [<ffff2000082fa2b4>] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [<ffff2000081c89ec>] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [<ffff2000081c9a60>] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [<ffff2000081678c8>] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [<ffff200008168364>] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [<ffff200008293dc8>] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [<ffff2000082103d8>] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [<ffff2000080821dc>] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [<ffff20000811c994>] irq_exit+0x264/0x308 kernel/softirq.c:405 > [<ffff2000081ecc28>] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [<ffff200008081c80>] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [<ffff2000080837f8>] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [<ffff20000820a47c>] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [<ffff2000081bcbfc>] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [<ffff2000081bd1cc>] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [<ffff200008099f8c>] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov <dvyukov@google.com> Tested-by: Dmitry Vyukov <dvyukov@google.com> Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-20 13:21:35 +00:00
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (ucounts) {
kfree(new);
} else {
hlist_add_head(&new->node, hashent);
ucounts = new;
}
}
if (ucounts->count == INT_MAX)
ucounts = NULL;
else
ucounts->count += 1;
userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov <dvyukov@google.com> reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [<ffff2000081678c8>] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [<ffff2000081c82d8>] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [<ffff2000081c97a8>] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [<ffff200008167c28>] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [<ffff200008481850>] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [<ffff200008487298>] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [<ffff200009bd6674>] mnt_init+0x258/0x384 fs/namespace.c:3251 > [<ffff200009bd60bc>] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [<ffff200009bb1114>] start_kernel+0x414/0x460 init/main.c:648 > [<ffff200009bb01e8>] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [<ffff200008210414>] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [<ffff20000820fe80>] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [<ffff20000811b4c4>] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [<ffff20000811c994>] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > <Interrupt> > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [<ffff200008210390>] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [<ffff20000808fa60>] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [<ffff20000808fec0>] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [<ffff2000088a99e0>] dump_stack+0x110/0x168 > [<ffff2000082fa2b4>] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [<ffff2000081c89ec>] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [<ffff2000081c9a60>] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [<ffff2000081678c8>] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [<ffff200008168364>] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [<ffff200008293dc8>] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [<ffff2000082103d8>] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [<ffff2000080821dc>] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [<ffff20000811c994>] irq_exit+0x264/0x308 kernel/softirq.c:405 > [<ffff2000081ecc28>] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [<ffff200008081c80>] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [<ffff2000080837f8>] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [<ffff20000820a47c>] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [<ffff2000081bcbfc>] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [<ffff2000081bd1cc>] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [<ffff200008099f8c>] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov <dvyukov@google.com> Tested-by: Dmitry Vyukov <dvyukov@google.com> Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-20 13:21:35 +00:00
spin_unlock_irq(&ucounts_lock);
return ucounts;
}
static void put_ucounts(struct ucounts *ucounts)
{
userns: Make ucounts lock irq-safe The ucounts_lock is being used to protect various ucounts lifecycle management functionalities. However, those services can also be invoked when a pidns is being freed in an RCU callback (e.g. softirq context). This can lead to deadlocks. There were already efforts trying to prevent similar deadlocks in add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock"), however they just moved the context from hardirq to softrq. Fix this issue once and for all by explictly making the lock disable irqs altogether. Dmitry Vyukov <dvyukov@google.com> reported: > I've got the following deadlock report while running syzkaller fuzzer > on eec0d3d065bfcdf9cd5f56dd2a36b94d12d32297 of linux-next (on odroid > device if it matters): > > ================================= > [ INFO: inconsistent lock state ] > 4.10.0-rc3-next-20170112-xc2-dirty #6 Not tainted > --------------------------------- > inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. > swapper/2/0 [HC0[0]:SC1[1]:HE1:SE0] takes: > (ucounts_lock){+.?...}, at: [< inline >] spin_lock > ./include/linux/spinlock.h:302 > (ucounts_lock){+.?...}, at: [<ffff2000081678c8>] > put_ucounts+0x60/0x138 kernel/ucount.c:162 > {SOFTIRQ-ON-W} state was registered at: > [<ffff2000081c82d8>] mark_lock+0x220/0xb60 kernel/locking/lockdep.c:3054 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2941 > [<ffff2000081c97a8>] __lock_acquire+0x388/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [< inline >] get_ucounts kernel/ucount.c:131 > [<ffff200008167c28>] inc_ucount+0x80/0x6c8 kernel/ucount.c:189 > [< inline >] inc_mnt_namespaces fs/namespace.c:2818 > [<ffff200008481850>] alloc_mnt_ns+0x78/0x3a8 fs/namespace.c:2849 > [<ffff200008487298>] create_mnt_ns+0x28/0x200 fs/namespace.c:2959 > [< inline >] init_mount_tree fs/namespace.c:3199 > [<ffff200009bd6674>] mnt_init+0x258/0x384 fs/namespace.c:3251 > [<ffff200009bd60bc>] vfs_caches_init+0x6c/0x80 fs/dcache.c:3626 > [<ffff200009bb1114>] start_kernel+0x414/0x460 init/main.c:648 > [<ffff200009bb01e8>] __primary_switched+0x6c/0x70 arch/arm64/kernel/head.S:456 > irq event stamp: 2316924 > hardirqs last enabled at (2316924): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2911 > hardirqs last enabled at (2316924): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last enabled at (2316924): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last enabled at (2316924): [<ffff200008210414>] > rcu_process_callbacks+0x7a4/0xc28 kernel/rcu/tree.c:3166 > hardirqs last disabled at (2316923): [< inline >] rcu_do_batch > kernel/rcu/tree.c:2900 > hardirqs last disabled at (2316923): [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > hardirqs last disabled at (2316923): [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > hardirqs last disabled at (2316923): [<ffff20000820fe80>] > rcu_process_callbacks+0x210/0xc28 kernel/rcu/tree.c:3166 > softirqs last enabled at (2316912): [<ffff20000811b4c4>] > _local_bh_enable+0x4c/0x80 kernel/softirq.c:155 > softirqs last disabled at (2316913): [< inline >] > do_softirq_own_stack ./include/linux/interrupt.h:488 > softirqs last disabled at (2316913): [< inline >] > invoke_softirq kernel/softirq.c:371 > softirqs last disabled at (2316913): [<ffff20000811c994>] > irq_exit+0x264/0x308 kernel/softirq.c:405 > > other info that might help us debug this: > Possible unsafe locking scenario: > > CPU0 > ---- > lock(ucounts_lock); > <Interrupt> > lock(ucounts_lock); > > *** DEADLOCK *** > > 1 lock held by swapper/2/0: > #0: (rcu_callback){......}, at: [< inline >] __rcu_reclaim > kernel/rcu/rcu.h:108 > #0: (rcu_callback){......}, at: [< inline >] rcu_do_batch > kernel/rcu/tree.c:2919 > #0: (rcu_callback){......}, at: [< inline >] > invoke_rcu_callbacks kernel/rcu/tree.c:3182 > #0: (rcu_callback){......}, at: [< inline >] > __rcu_process_callbacks kernel/rcu/tree.c:3149 > #0: (rcu_callback){......}, at: [<ffff200008210390>] > rcu_process_callbacks+0x720/0xc28 kernel/rcu/tree.c:3166 > > stack backtrace: > CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.10.0-rc3-next-20170112-xc2-dirty #6 > Hardware name: Hardkernel ODROID-C2 (DT) > Call trace: > [<ffff20000808fa60>] dump_backtrace+0x0/0x440 arch/arm64/kernel/traps.c:500 > [<ffff20000808fec0>] show_stack+0x20/0x30 arch/arm64/kernel/traps.c:225 > [<ffff2000088a99e0>] dump_stack+0x110/0x168 > [<ffff2000082fa2b4>] print_usage_bug.part.27+0x49c/0x4bc > kernel/locking/lockdep.c:2387 > [< inline >] print_usage_bug kernel/locking/lockdep.c:2357 > [< inline >] valid_state kernel/locking/lockdep.c:2400 > [< inline >] mark_lock_irq kernel/locking/lockdep.c:2617 > [<ffff2000081c89ec>] mark_lock+0x934/0xb60 kernel/locking/lockdep.c:3065 > [< inline >] mark_irqflags kernel/locking/lockdep.c:2923 > [<ffff2000081c9a60>] __lock_acquire+0x640/0x3260 kernel/locking/lockdep.c:3295 > [<ffff2000081cce24>] lock_acquire+0xa4/0x138 kernel/locking/lockdep.c:3753 > [< inline >] __raw_spin_lock ./include/linux/spinlock_api_smp.h:144 > [<ffff200009798128>] _raw_spin_lock+0x90/0xd0 kernel/locking/spinlock.c:151 > [< inline >] spin_lock ./include/linux/spinlock.h:302 > [<ffff2000081678c8>] put_ucounts+0x60/0x138 kernel/ucount.c:162 > [<ffff200008168364>] dec_ucount+0xf4/0x158 kernel/ucount.c:214 > [< inline >] dec_pid_namespaces kernel/pid_namespace.c:89 > [<ffff200008293dc8>] delayed_free_pidns+0x40/0xe0 kernel/pid_namespace.c:156 > [< inline >] __rcu_reclaim kernel/rcu/rcu.h:118 > [< inline >] rcu_do_batch kernel/rcu/tree.c:2919 > [< inline >] invoke_rcu_callbacks kernel/rcu/tree.c:3182 > [< inline >] __rcu_process_callbacks kernel/rcu/tree.c:3149 > [<ffff2000082103d8>] rcu_process_callbacks+0x768/0xc28 kernel/rcu/tree.c:3166 > [<ffff2000080821dc>] __do_softirq+0x324/0x6e0 kernel/softirq.c:284 > [< inline >] do_softirq_own_stack ./include/linux/interrupt.h:488 > [< inline >] invoke_softirq kernel/softirq.c:371 > [<ffff20000811c994>] irq_exit+0x264/0x308 kernel/softirq.c:405 > [<ffff2000081ecc28>] __handle_domain_irq+0xc0/0x150 kernel/irq/irqdesc.c:636 > [<ffff200008081c80>] gic_handle_irq+0x68/0xd8 > Exception stack(0xffff8000648e7dd0 to 0xffff8000648e7f00) > 7dc0: ffff8000648d4b3c 0000000000000007 > 7de0: 0000000000000000 1ffff0000c91a967 1ffff0000c91a967 1ffff0000c91a967 > 7e00: ffff20000a4b6b68 0000000000000001 0000000000000007 0000000000000001 > 7e20: 1fffe4000149ae90 ffff200009d35000 0000000000000000 0000000000000002 > 7e40: 0000000000000000 0000000000000000 0000000002624a1a 0000000000000000 > 7e60: 0000000000000000 ffff200009cbcd88 000060006d2ed000 0000000000000140 > 7e80: ffff200009cff000 ffff200009cb6000 ffff200009cc2020 ffff200009d2159d > 7ea0: 0000000000000000 ffff8000648d4380 0000000000000000 ffff8000648e7f00 > 7ec0: ffff20000820a478 ffff8000648e7f00 ffff20000820a47c 0000000010000145 > 7ee0: 0000000000000140 dfff200000000000 ffffffffffffffff ffff20000820a478 > [<ffff2000080837f8>] el1_irq+0xb8/0x130 arch/arm64/kernel/entry.S:486 > [< inline >] arch_local_irq_restore > ./arch/arm64/include/asm/irqflags.h:81 > [<ffff20000820a47c>] rcu_idle_exit+0x64/0xa8 kernel/rcu/tree.c:1030 > [< inline >] cpuidle_idle_call kernel/sched/idle.c:200 > [<ffff2000081bcbfc>] do_idle+0x1dc/0x2d0 kernel/sched/idle.c:243 > [<ffff2000081bd1cc>] cpu_startup_entry+0x24/0x28 kernel/sched/idle.c:345 > [<ffff200008099f8c>] secondary_start_kernel+0x2cc/0x358 > arch/arm64/kernel/smp.c:276 > [<000000000279f1a4>] 0x279f1a4 Reported-by: Dmitry Vyukov <dvyukov@google.com> Tested-by: Dmitry Vyukov <dvyukov@google.com> Fixes: add7c65ca426 ("pid: fix lockdep deadlock warning due to ucount_lock") Fixes: f333c700c610 ("pidns: Add a limit on the number of pid namespaces") Cc: stable@vger.kernel.org Link: https://www.spinics.net/lists/kernel/msg2426637.html Signed-off-by: Nikolay Borisov <n.borisov.lkml@gmail.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2017-01-20 13:21:35 +00:00
unsigned long flags;
spin_lock_irqsave(&ucounts_lock, flags);
ucounts->count -= 1;
if (!ucounts->count)
hlist_del_init(&ucounts->node);
else
ucounts = NULL;
spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
}
static inline bool atomic_inc_below(atomic_t *v, int u)
{
int c, old;
c = atomic_read(v);
for (;;) {
if (unlikely(c >= u))
return false;
old = atomic_cmpxchg(v, c, c+1);
if (likely(old == c))
return true;
c = old;
}
}
struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
enum ucount_type type)
{
struct ucounts *ucounts, *iter, *bad;
struct user_namespace *tns;
ucounts = get_ucounts(ns, uid);
for (iter = ucounts; iter; iter = tns->ucounts) {
int max;
tns = iter->ns;
max = READ_ONCE(tns->ucount_max[type]);
if (!atomic_inc_below(&iter->ucount[type], max))
goto fail;
}
return ucounts;
fail:
bad = iter;
for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
atomic_dec(&iter->ucount[type]);
put_ucounts(ucounts);
return NULL;
}
void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
{
struct ucounts *iter;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
int dec = atomic_dec_if_positive(&iter->ucount[type]);
WARN_ON_ONCE(dec < 0);
}
put_ucounts(ucounts);
}
static __init int user_namespace_sysctl_init(void)
{
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *user_header;
static struct ctl_table empty[1];
/*
* It is necessary to register the user directory in the
* default set so that registrations in the child sets work
* properly.
*/
user_header = register_sysctl("user", empty);
kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
return 0;
}
subsys_initcall(user_namespace_sysctl_init);