From a7dc19b8652c862d5b7c4d2339bd3c428bd29c4a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 7 Mar 2013 15:09:24 +0000 Subject: clockevents: Don't allow dummy broadcast timers Currently tick_check_broadcast_device doesn't reject clock_event_devices with CLOCK_EVT_FEAT_DUMMY, and may select them in preference to real hardware if they have a higher rating value. In this situation, the dummy timer is responsible for broadcasting to itself, and the core clockevents code may attempt to call non-existent callbacks for programming the dummy, eventually leading to a panic. This patch makes tick_check_broadcast_device always reject dummy timers, preventing this problem. Signed-off-by: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Cc: Jon Medhurst (Tixy) Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- kernel/time/tick-broadcast.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 2fb8cb88df8d..7f32fe0e52cd 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -67,7 +67,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) */ int tick_check_broadcast_device(struct clock_event_device *dev) { - if ((tick_broadcast_device.evtdev && + if ((dev->features & CLOCK_EVT_FEAT_DUMMY) || + (tick_broadcast_device.evtdev && tick_broadcast_device.evtdev->rating >= dev->rating) || (dev->features & CLOCK_EVT_FEAT_C3STOP)) return 0; -- cgit v1.3-18-gd494 From eb2834285cf172856cd12f66892fc7467935ebed Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 8 Mar 2013 15:18:28 -0800 Subject: workqueue: fix possible pool stall bug in wq_unbind_fn() Since multiple pools per cpu have been introduced, wq_unbind_fn() has a subtle bug which may theoretically stall work item processing. The problem is two-fold. * wq_unbind_fn() depends on the worker executing wq_unbind_fn() itself to start unbound chain execution, which works fine when there was only single pool. With multiple pools, only the pool which is running wq_unbind_fn() - the highpri one - is guaranteed to have such kick-off. The other pool could stall when its busy workers block. * The current code is setting WORKER_UNBIND / POOL_DISASSOCIATED of the two pools in succession without initiating work execution inbetween. Because setting the flags requires grabbing assoc_mutex which is held while new workers are created, this could lead to stalls if a pool's manager is waiting for the previous pool's work items to release memory. This is almost purely theoretical tho. Update wq_unbind_fn() such that it sets WORKER_UNBIND / POOL_DISASSOCIATED, goes over schedule() and explicitly kicks off execution for a pool and then moves on to the next one. tj: Updated comments and description. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org --- kernel/workqueue.c | 44 +++++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 81f2457811eb..604801b91cba 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3446,28 +3446,34 @@ static void wq_unbind_fn(struct work_struct *work) spin_unlock_irq(&pool->lock); mutex_unlock(&pool->assoc_mutex); - } - /* - * Call schedule() so that we cross rq->lock and thus can guarantee - * sched callbacks see the %WORKER_UNBOUND flag. This is necessary - * as scheduler callbacks may be invoked from other cpus. - */ - schedule(); + /* + * Call schedule() so that we cross rq->lock and thus can + * guarantee sched callbacks see the %WORKER_UNBOUND flag. + * This is necessary as scheduler callbacks may be invoked + * from other cpus. + */ + schedule(); - /* - * Sched callbacks are disabled now. Zap nr_running. After this, - * nr_running stays zero and need_more_worker() and keep_working() - * are always true as long as the worklist is not empty. Pools on - * @cpu now behave as unbound (in terms of concurrency management) - * pools which are served by workers tied to the CPU. - * - * On return from this function, the current worker would trigger - * unbound chain execution of pending work items if other workers - * didn't already. - */ - for_each_std_worker_pool(pool, cpu) + /* + * Sched callbacks are disabled now. Zap nr_running. + * After this, nr_running stays zero and need_more_worker() + * and keep_working() are always true as long as the + * worklist is not empty. This pool now behaves as an + * unbound (in terms of concurrency management) pool which + * are served by workers tied to the pool. + */ atomic_set(&pool->nr_running, 0); + + /* + * With concurrency management just turned off, a busy + * worker blocking could lead to lengthy stalls. Kick off + * unbound chain execution of currently pending work items. + */ + spin_lock_irq(&pool->lock); + wake_up_worker(pool); + spin_unlock_irq(&pool->lock); + } } /* -- cgit v1.3-18-gd494 From dc72c32e1fd872a9a4fdfe645283c9dcd68e556d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 22 Mar 2013 15:04:39 -0700 Subject: printk: Provide a wake_up_klogd() off-case wake_up_klogd() is useless when CONFIG_PRINTK=n because neither printk() nor printk_sched() are in use and there are actually no waiter on log_wait waitqueue. It should be a stub in this case for users like bust_spinlocks(). Otherwise this results in this warning when CONFIG_PRINTK=n and CONFIG_IRQ_WORK=n: kernel/built-in.o In function `wake_up_klogd': (.text.wake_up_klogd+0xb4): undefined reference to `irq_work_queue' To fix this, provide an off-case for wake_up_klogd() when CONFIG_PRINTK=n. There is much more from console_unlock() and other console related code in printk.c that should be moved under CONFIG_PRINTK. But for now, focus on a minimal fix as we passed the merged window already. [akpm@linux-foundation.org: include printk.h in bust_spinlocks.c] Signed-off-by: Frederic Weisbecker Reported-by: James Hogan Cc: James Hogan Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - include/linux/printk.h | 6 ++++ kernel/printk.c | 80 ++++++++++++++++++++++++-------------------------- lib/bust_spinlocks.c | 3 +- 4 files changed, 46 insertions(+), 44 deletions(-) (limited to 'kernel') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 80d36874689b..79fdd80a42d4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -390,7 +390,6 @@ extern struct pid *session_of_pgrp(struct pid *pgrp); unsigned long int_sqrt(unsigned long); extern void bust_spinlocks(int yes); -extern void wake_up_klogd(void); extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ extern int panic_timeout; extern int panic_on_oops; diff --git a/include/linux/printk.h b/include/linux/printk.h index 1249a54d17e0..822171fcb1c8 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -134,6 +134,8 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; +extern void wake_up_klogd(void); + void log_buf_kexec_setup(void); void __init setup_log_buf(int early); #else @@ -162,6 +164,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, return false; } +static inline void wake_up_klogd(void) +{ +} + static inline void log_buf_kexec_setup(void) { } diff --git a/kernel/printk.c b/kernel/printk.c index 0b31715f335a..abbdd9e2ac82 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */ #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */ -DECLARE_WAIT_QUEUE_HEAD(log_wait); - int console_printk[4] = { DEFAULT_CONSOLE_LOGLEVEL, /* console_loglevel */ DEFAULT_MESSAGE_LOGLEVEL, /* default_message_loglevel */ @@ -224,6 +222,7 @@ struct log { static DEFINE_RAW_SPINLOCK(logbuf_lock); #ifdef CONFIG_PRINTK +DECLARE_WAIT_QUEUE_HEAD(log_wait); /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static u32 syslog_idx; @@ -1957,45 +1956,6 @@ int is_console_locked(void) return console_locked; } -/* - * Delayed printk version, for scheduler-internal messages: - */ -#define PRINTK_BUF_SIZE 512 - -#define PRINTK_PENDING_WAKEUP 0x01 -#define PRINTK_PENDING_SCHED 0x02 - -static DEFINE_PER_CPU(int, printk_pending); -static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); - -static void wake_up_klogd_work_func(struct irq_work *irq_work) -{ - int pending = __this_cpu_xchg(printk_pending, 0); - - if (pending & PRINTK_PENDING_SCHED) { - char *buf = __get_cpu_var(printk_sched_buf); - printk(KERN_WARNING "[sched_delayed] %s", buf); - } - - if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible(&log_wait); -} - -static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { - .func = wake_up_klogd_work_func, - .flags = IRQ_WORK_LAZY, -}; - -void wake_up_klogd(void) -{ - preempt_disable(); - if (waitqueue_active(&log_wait)) { - this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); - irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); - } - preempt_enable(); -} - static void console_cont_flush(char *text, size_t size) { unsigned long flags; @@ -2458,6 +2418,44 @@ static int __init printk_late_init(void) late_initcall(printk_late_init); #if defined CONFIG_PRINTK +/* + * Delayed printk version, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + +static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); + +static void wake_up_klogd_work_func(struct irq_work *irq_work) +{ + int pending = __this_cpu_xchg(printk_pending, 0); + + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); +} + +static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { + .func = wake_up_klogd_work_func, + .flags = IRQ_WORK_LAZY, +}; + +void wake_up_klogd(void) +{ + preempt_disable(); + if (waitqueue_active(&log_wait)) { + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); + irq_work_queue(&__get_cpu_var(wake_up_klogd_work)); + } + preempt_enable(); +} int printk_sched(const char *fmt, ...) { diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c index 9681d54b95d1..f8e0e5367398 100644 --- a/lib/bust_spinlocks.c +++ b/lib/bust_spinlocks.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes) wake_up_klogd(); } } - - -- cgit v1.3-18-gd494 From 2ca067efd82939dfd87827d29d36a265823a4c2f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 22 Mar 2013 15:04:41 -0700 Subject: poweroff: change orderly_poweroff() to use schedule_work() David said: Commit 6c0c0d4d1080 ("poweroff: fix bug in orderly_poweroff()") apparently fixes one bug in orderly_poweroff(), but introduces another. The comments on orderly_poweroff() claim it can be called from any context - and indeed we call it from interrupt context in arch/powerpc/platforms/pseries/ras.c for example. But since that commit this is no longer safe, since call_usermodehelper_fns() is not safe in interrupt context without the UMH_NO_WAIT option. orderly_poweroff() can be used from any context but UMH_WAIT_EXEC is sleepable. Move the "force" logic into __orderly_poweroff() and change orderly_poweroff() to use the global poweroff_work which simply calls __orderly_poweroff(). While at it, remove the unneeded "int argc" and change argv_split() to use GFP_KERNEL. We use the global "bool poweroff_force" to pass the argument, this can obviously affect the previous request if it is pending/running. So we only allow the "false => true" transition assuming that the pending "true" should succeed anyway. If schedule_work() fails after that we know that work->func() was not called yet, it must see the new value. This means that orderly_poweroff() becomes async even if we do not run the command and always succeeds, schedule_work() can only fail if the work is already pending. We can export __orderly_poweroff() and change the non-atomic callers which want the old semantics. Signed-off-by: Oleg Nesterov Reported-by: Benjamin Herrenschmidt Reported-by: David Gibson Cc: Lucas De Marchi Cc: Feng Hong Cc: Kees Cook Cc: Serge Hallyn Cc: "Eric W. Biederman" Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 57 ++++++++++++++++++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 25 deletions(-) (limited to 'kernel') diff --git a/kernel/sys.c b/kernel/sys.c index 81f56445fba9..39c9c4a2949f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2185,9 +2185,8 @@ SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; -static int __orderly_poweroff(void) +static int __orderly_poweroff(bool force) { - int argc; char **argv; static char *envp[] = { "HOME=/", @@ -2196,20 +2195,40 @@ static int __orderly_poweroff(void) }; int ret; - argv = argv_split(GFP_ATOMIC, poweroff_cmd, &argc); - if (argv == NULL) { + argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL); + if (argv) { + ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + argv_free(argv); + } else { printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n", - __func__, poweroff_cmd); - return -ENOMEM; + __func__, poweroff_cmd); + ret = -ENOMEM; } - ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC, - NULL, NULL, NULL); - argv_free(argv); + if (ret && force) { + printk(KERN_WARNING "Failed to start orderly shutdown: " + "forcing the issue\n"); + /* + * I guess this should try to kick off some daemon to sync and + * poweroff asap. Or not even bother syncing if we're doing an + * emergency shutdown? + */ + emergency_sync(); + kernel_power_off(); + } return ret; } +static bool poweroff_force; + +static void poweroff_work_func(struct work_struct *work) +{ + __orderly_poweroff(poweroff_force); +} + +static DECLARE_WORK(poweroff_work, poweroff_work_func); + /** * orderly_poweroff - Trigger an orderly system poweroff * @force: force poweroff if command execution fails @@ -2219,21 +2238,9 @@ static int __orderly_poweroff(void) */ int orderly_poweroff(bool force) { - int ret = __orderly_poweroff(); - - if (ret && force) { - printk(KERN_WARNING "Failed to start orderly shutdown: " - "forcing the issue\n"); - - /* - * I guess this should try to kick off some daemon to sync and - * poweroff asap. Or not even bother syncing if we're doing an - * emergency shutdown? - */ - emergency_sync(); - kernel_power_off(); - } - - return ret; + if (force) /* do not override the pending "true" */ + poweroff_force = true; + schedule_work(&poweroff_work); + return 0; } EXPORT_SYMBOL_GPL(orderly_poweroff); -- cgit v1.3-18-gd494 From 751c644b95bb48aaa8825f0c66abbcc184d92051 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Mar 2013 02:27:11 -0700 Subject: pid: Handle the exit of a multi-threaded init. When a multi-threaded init exits and the initial thread is not the last thread to exit the initial thread hangs around as a zombie until the last thread exits. In that case zap_pid_ns_processes needs to wait until there are only 2 hashed pids in the pid namespace not one. v2. Replace thread_pid_vnr(me) == 1 with the test thread_group_leader(me) as suggested by Oleg. Cc: stable@vger.kernel.org Cc: Oleg Nesterov Reported-by: Caj Larsson Signed-off-by: "Eric W. Biederman" --- kernel/pid_namespace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index c1c3dc1c6023..bea15bdf82b0 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -181,6 +181,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) int nr; int rc; struct task_struct *task, *me = current; + int init_pids = thread_group_leader(me) ? 1 : 2; /* Don't allow any more processes into the pid namespace */ disable_pid_allocation(pid_ns); @@ -230,7 +231,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) */ for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - if (pid_ns->nr_hashed == 1) + if (pid_ns->nr_hashed == init_pids) break; schedule(); } -- cgit v1.3-18-gd494 From 3151527ee007b73a0ebd296010f1c0454a919c7d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 15 Mar 2013 01:45:51 -0700 Subject: userns: Don't allow creation if the user is chrooted Guarantee that the policy of which files may be access that is established by setting the root directory will not be violated by user namespaces by verifying that the root directory points to the root of the mount namespace at the time of user namespace creation. Changing the root is a privileged operation, and as a matter of policy it serves to limit unprivileged processes to files below the current root directory. For reasons of simplicity and comprehensibility the privilege to change the root directory is gated solely on the CAP_SYS_CHROOT capability in the user namespace. Therefore when creating a user namespace we must ensure that the policy of which files may be access can not be violated by changing the root directory. Anyone who runs a processes in a chroot and would like to use user namespace can setup the same view of filesystems with a mount namespace instead. With this result that this is not a practical limitation for using user namespaces. Cc: stable@vger.kernel.org Acked-by: Serge Hallyn Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 24 ++++++++++++++++++++++++ include/linux/fs_struct.h | 2 ++ kernel/user_namespace.c | 9 +++++++++ 3 files changed, 35 insertions(+) (limited to 'kernel') diff --git a/fs/namespace.c b/fs/namespace.c index 50ca17d3cb45..a3035223d421 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2732,6 +2732,30 @@ bool our_mnt(struct vfsmount *mnt) return check_mnt(real_mount(mnt)); } +bool current_chrooted(void) +{ + /* Does the current process have a non-standard root */ + struct path ns_root; + struct path fs_root; + bool chrooted; + + /* Find the namespace root */ + ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; + ns_root.dentry = ns_root.mnt->mnt_root; + path_get(&ns_root); + while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) + ; + + get_fs_root(current->fs, &fs_root); + + chrooted = !path_equal(&fs_root, &ns_root); + + path_put(&fs_root); + path_put(&ns_root); + + return chrooted; +} + static void *mntns_get(struct task_struct *task) { struct mnt_namespace *ns = NULL; diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 729eded4b24f..2b93a9a5a1e6 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -50,4 +50,6 @@ static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root, spin_unlock(&fs->lock); } +extern bool current_chrooted(void); + #endif /* _LINUX_FS_STRUCT_H */ diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index b14f4d342043..0f1e42884577 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -61,6 +61,15 @@ int create_user_ns(struct cred *new) kgid_t group = new->egid; int ret; + /* + * Verify that we can not violate the policy of which files + * may be accessed that is specified by the root directory, + * by verifing that the root directory is at the root of the + * mount namespace which allows all files to be accessed. + */ + if (current_chrooted()) + return -EPERM; + /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. -- cgit v1.3-18-gd494 From 87a8ebd637dafc255070f503909a053cf0d98d3f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 24 Mar 2013 14:28:27 -0700 Subject: userns: Restrict when proc and sysfs can be mounted Only allow unprivileged mounts of proc and sysfs if they are already mounted when the user namespace is created. proc and sysfs are interesting because they have content that is per namespace, and so fresh mounts are needed when new namespaces are created while at the same time proc and sysfs have content that is shared between every instance. Respect the policy of who may see the shared content of proc and sysfs by only allowing new mounts if there was an existing mount at the time the user namespace was created. In practice there are only two interesting cases: proc and sysfs are mounted at their usual places, proc and sysfs are not mounted at all (some form of mount namespace jail). Cc: stable@vger.kernel.org Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- fs/namespace.c | 21 +++++++++++++++++++++ fs/proc/root.c | 4 ++++ fs/sysfs/mount.c | 4 ++++ include/linux/user_namespace.h | 4 ++++ kernel/user.c | 2 ++ kernel/user_namespace.c | 2 ++ 6 files changed, 37 insertions(+) (limited to 'kernel') diff --git a/fs/namespace.c b/fs/namespace.c index 968d4c5eae03..d581e45c0a9f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2763,6 +2763,27 @@ bool current_chrooted(void) return chrooted; } +void update_mnt_policy(struct user_namespace *userns) +{ + struct mnt_namespace *ns = current->nsproxy->mnt_ns; + struct mount *mnt; + + down_read(&namespace_sem); + list_for_each_entry(mnt, &ns->list, mnt_list) { + switch (mnt->mnt.mnt_sb->s_magic) { + case SYSFS_MAGIC: + userns->may_mount_sysfs = true; + break; + case PROC_SUPER_MAGIC: + userns->may_mount_proc = true; + break; + } + if (userns->may_mount_sysfs && userns->may_mount_proc) + break; + } + up_read(&namespace_sem); +} + static void *mntns_get(struct task_struct *task) { struct mnt_namespace *ns = NULL; diff --git a/fs/proc/root.c b/fs/proc/root.c index c6e9fac26bac..9c7fab1d23f0 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, } else { ns = task_active_pid_ns(current); options = data; + + if (!current_user_ns()->may_mount_proc) + return ERR_PTR(-EPERM); } sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 8d924b5ec733..afd83273e6ce 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "sysfs.h" @@ -111,6 +112,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, struct super_block *sb; int error; + if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs) + return ERR_PTR(-EPERM); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 4ce009324933..b6b215f13b45 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -26,6 +26,8 @@ struct user_namespace { kuid_t owner; kgid_t group; unsigned int proc_inum; + bool may_mount_sysfs; + bool may_mount_proc; }; extern struct user_namespace init_user_ns; @@ -82,4 +84,6 @@ static inline void put_user_ns(struct user_namespace *ns) #endif +void update_mnt_policy(struct user_namespace *userns); + #endif /* _LINUX_USER_H */ diff --git a/kernel/user.c b/kernel/user.c index e81978e8c03b..8e635a18ab52 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,6 +51,8 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, + .may_mount_sysfs = true, + .may_mount_proc = true, }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 0f1e42884577..a54f26f82eb2 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -96,6 +96,8 @@ int create_user_ns(struct cred *new) set_cred_user_ns(new, ns); + update_mnt_policy(ns); + return 0; } -- cgit v1.3-18-gd494 From dbf520a9d7d4d5ba28d2947be11e34099a5e3e20 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Sun, 31 Mar 2013 00:04:40 +0000 Subject: Revert "lockdep: check that no locks held at freeze time" This reverts commit 6aa9707099c4b25700940eb3d016f16c4434360d. Commit 6aa9707099c4 ("lockdep: check that no locks held at freeze time") causes problems with NFS root filesystems. The failures were noticed on OMAP2 and 3 boards during kernel init: [ BUG: swapper/0/1 still has locks held! ] 3.9.0-rc3-00344-ga937536 #1 Not tainted ------------------------------------- 1 lock held by swapper/0/1: #0: (&type->s_umount_key#13/1){+.+.+.}, at: [] sget+0x248/0x574 stack backtrace: rpc_wait_bit_killable __wait_on_bit out_of_line_wait_on_bit __rpc_execute rpc_run_task rpc_call_sync nfs_proc_get_root nfs_get_root nfs_fs_mount_common nfs_try_mount nfs_fs_mount mount_fs vfs_kern_mount do_mount sys_mount do_mount_root mount_root prepare_namespace kernel_init_freeable kernel_init Although the rootfs mounts, the system is unstable. Here's a transcript from a PM test: http://www.pwsan.com/omap/testlogs/test_v3.9-rc3/20130317194234/pm/37xxevm/37xxevm_log.txt Here's what the test log should look like: http://www.pwsan.com/omap/testlogs/test_v3.8/20130218214403/pm/37xxevm/37xxevm_log.txt Mailing list discussion is here: http://lkml.org/lkml/2013/3/4/221 Deal with this for v3.9 by reverting the problem commit, until folks can figure out the right long-term course of action. Signed-off-by: Paul Walmsley Cc: Mandeep Singh Baines Cc: Jeff Layton Cc: Shawn Guo Cc: Cc: Fengguang Wu Cc: Trond Myklebust Cc: Ingo Molnar Cc: Ben Chan Cc: Oleg Nesterov Cc: Tejun Heo Cc: Rafael J. Wysocki Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debug_locks.h | 4 ++-- include/linux/freezer.h | 3 --- kernel/exit.c | 2 +- kernel/lockdep.c | 17 +++++++++-------- 4 files changed, 12 insertions(+), 14 deletions(-) (limited to 'kernel') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index a975de1ff59f..3bd46f766751 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -51,7 +51,7 @@ struct task_struct; extern void debug_show_all_locks(void); extern void debug_show_held_locks(struct task_struct *task); extern void debug_check_no_locks_freed(const void *from, unsigned long len); -extern void debug_check_no_locks_held(void); +extern void debug_check_no_locks_held(struct task_struct *task); #else static inline void debug_show_all_locks(void) { @@ -67,7 +67,7 @@ debug_check_no_locks_freed(const void *from, unsigned long len) } static inline void -debug_check_no_locks_held(void) +debug_check_no_locks_held(struct task_struct *task) { } #endif diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 043a5cf8b5ba..e70df40d84f6 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -3,7 +3,6 @@ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED -#include #include #include #include @@ -49,8 +48,6 @@ extern void thaw_kernel_threads(void); static inline bool try_to_freeze(void) { - if (!(current->flags & PF_NOFREEZE)) - debug_check_no_locks_held(); might_sleep(); if (likely(!freezing(current))) return false; diff --git a/kernel/exit.c b/kernel/exit.c index 51e485ca9935..60bc027c61c3 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -835,7 +835,7 @@ void do_exit(long code) /* * Make sure we are holding no locks: */ - debug_check_no_locks_held(); + debug_check_no_locks_held(tsk); /* * We can do this unlocked here. The futex code uses this flag * just to verify whether the pi state cleanup has been done diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 259db207b5d9..8a0efac4f99d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -4088,7 +4088,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len) } EXPORT_SYMBOL_GPL(debug_check_no_locks_freed); -static void print_held_locks_bug(void) +static void print_held_locks_bug(struct task_struct *curr) { if (!debug_locks_off()) return; @@ -4097,21 +4097,22 @@ static void print_held_locks_bug(void) printk("\n"); printk("=====================================\n"); - printk("[ BUG: %s/%d still has locks held! ]\n", - current->comm, task_pid_nr(current)); + printk("[ BUG: lock held at task exit time! ]\n"); print_kernel_ident(); printk("-------------------------------------\n"); - lockdep_print_held_locks(current); + printk("%s/%d is exiting with locks still held!\n", + curr->comm, task_pid_nr(curr)); + lockdep_print_held_locks(curr); + printk("\nstack backtrace:\n"); dump_stack(); } -void debug_check_no_locks_held(void) +void debug_check_no_locks_held(struct task_struct *task) { - if (unlikely(current->lockdep_depth > 0)) - print_held_locks_bug(); + if (unlikely(task->lockdep_depth > 0)) + print_held_locks_bug(task); } -EXPORT_SYMBOL_GPL(debug_check_no_locks_held); void debug_show_all_locks(void) { -- cgit v1.3-18-gd494