From a288eecce5253cc1565d400a52b9b476a157e040 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:37 +0200 Subject: ptrace: kill trivial tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following trivial tracehooks. * Ones testing whether task is ptraced. Replace with ->ptrace test. tracehook_expect_breakpoints() tracehook_consider_ignored_signal() tracehook_consider_fatal_signal() * ptrace_event() wrappers. Call directly. tracehook_report_exec() tracehook_report_exit() tracehook_report_vfork_done() * ptrace_release_task() wrapper. Call directly. tracehook_finish_release_task() * noop tracehook_prepare_release_task() tracehook_report_death() This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: Martin Schwidefsky Signed-off-by: Oleg Nesterov --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..d4f0dff9d617 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1527,7 +1527,7 @@ long do_fork(unsigned long clone_flags, freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - tracehook_report_vfork_done(p, nr); + ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); } } else { nr = PTR_ERR(p); -- cgit v1.2.3 From 4b9d33e6d83cc05a8005a8f9a8b9677fa0f53626 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:38 +0200 Subject: ptrace: kill clone/exec tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following clone and exec related tracehooks. tracehook_prepare_clone() tracehook_finish_clone() tracehook_report_clone() tracehook_report_clone_complete() tracehook_unsafe_exec() The changes are mostly trivial - logic is moved to the caller and comments are merged and adjusted appropriately. The only exception is in check_unsafe_exec() where LSM_UNSAFE_PTRACE* are OR'd to bprm->unsafe instead of setting it, which produces the same result as the field is always zero on entry. It also tests p->ptrace instead of (p->ptrace & PT_PTRACED) for consistency, which also gives the same result. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Oleg Nesterov --- fs/exec.c | 7 ++- include/linux/tracehook.h | 121 ---------------------------------------------- kernel/fork.c | 41 ++++++++++++---- 3 files changed, 38 insertions(+), 131 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/exec.c b/fs/exec.c index b37030d0a50b..8dca45b0dae8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1224,7 +1224,12 @@ int check_unsafe_exec(struct linux_binprm *bprm) unsigned n_fs; int res = 0; - bprm->unsafe = tracehook_unsafe_exec(p); + if (p->ptrace) { + if (p->ptrace & PT_PTRACE_CAP) + bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; + else + bprm->unsafe |= LSM_UNSAFE_PTRACE; + } n_fs = 1; spin_lock(&p->fs->lock); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 8b06d4f2b814..bcc4ca762aee 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -129,27 +129,6 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) ptrace_report_syscall(regs); } -/** - * tracehook_unsafe_exec - check for exec declared unsafe due to tracing - * @task: current task doing exec - * - * Return %LSM_UNSAFE_* bits applied to an exec because of tracing. - * - * @task->signal->cred_guard_mutex is held by the caller through the do_execve(). - */ -static inline int tracehook_unsafe_exec(struct task_struct *task) -{ - int unsafe = 0; - int ptrace = task->ptrace; - if (ptrace & PT_PTRACED) { - if (ptrace & PT_PTRACE_CAP) - unsafe |= LSM_UNSAFE_PTRACE_CAP; - else - unsafe |= LSM_UNSAFE_PTRACE; - } - return unsafe; -} - /** * tracehook_tracer_task - return the task that is tracing the given task * @tsk: task to consider @@ -168,106 +147,6 @@ static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk) return NULL; } -/** - * tracehook_prepare_clone - prepare for new child to be cloned - * @clone_flags: %CLONE_* flags from clone/fork/vfork system call - * - * This is called before a new user task is to be cloned. - * Its return value will be passed to tracehook_finish_clone(). - * - * Called with no locks held. - */ -static inline int tracehook_prepare_clone(unsigned clone_flags) -{ - int event = 0; - - if (clone_flags & CLONE_UNTRACED) - return 0; - - if (clone_flags & CLONE_VFORK) - event = PTRACE_EVENT_VFORK; - else if ((clone_flags & CSIGNAL) != SIGCHLD) - event = PTRACE_EVENT_CLONE; - else - event = PTRACE_EVENT_FORK; - - return ptrace_event_enabled(current, event) ? event : 0; -} - -/** - * tracehook_finish_clone - new child created and being attached - * @child: new child task - * @clone_flags: %CLONE_* flags from clone/fork/vfork system call - * @trace: return value from tracehook_prepare_clone() - * - * This is called immediately after adding @child to its parent's children list. - * The @trace value is that returned by tracehook_prepare_clone(). - * - * Called with current's siglock and write_lock_irq(&tasklist_lock) held. - */ -static inline void tracehook_finish_clone(struct task_struct *child, - unsigned long clone_flags, int trace) -{ - ptrace_init_task(child, (clone_flags & CLONE_PTRACE) || trace); -} - -/** - * tracehook_report_clone - in parent, new child is about to start running - * @regs: parent's user register state - * @clone_flags: flags from parent's system call - * @pid: new child's PID in the parent's namespace - * @child: new child task - * - * Called after a child is set up, but before it has been started running. - * This is not a good place to block, because the child has not started - * yet. Suspend the child here if desired, and then block in - * tracehook_report_clone_complete(). This must prevent the child from - * self-reaping if tracehook_report_clone_complete() uses the @child - * pointer; otherwise it might have died and been released by the time - * tracehook_report_clone_complete() is called. - * - * Called with no locks held, but the child cannot run until this returns. - */ -static inline void tracehook_report_clone(struct pt_regs *regs, - unsigned long clone_flags, - pid_t pid, struct task_struct *child) -{ - if (unlikely(child->ptrace)) { - /* - * It doesn't matter who attached/attaching to this - * task, the pending SIGSTOP is right in any case. - */ - sigaddset(&child->pending.signal, SIGSTOP); - set_tsk_thread_flag(child, TIF_SIGPENDING); - } -} - -/** - * tracehook_report_clone_complete - new child is running - * @trace: return value from tracehook_prepare_clone() - * @regs: parent's user register state - * @clone_flags: flags from parent's system call - * @pid: new child's PID in the parent's namespace - * @child: child task, already running - * - * This is called just after the child has started running. This is - * just before the clone/fork syscall returns, or blocks for vfork - * child completion if @clone_flags has the %CLONE_VFORK bit set. - * The @child pointer may be invalid if a self-reaping child died and - * tracehook_report_clone() took no action to prevent it from self-reaping. - * - * Called with no locks held. - */ -static inline void tracehook_report_clone_complete(int trace, - struct pt_regs *regs, - unsigned long clone_flags, - pid_t pid, - struct task_struct *child) -{ - if (unlikely(trace)) - ptrace_event(trace, pid); -} - /** * tracehook_signal_handler - signal handler setup is complete * @sig: number of signal being delivered diff --git a/kernel/fork.c b/kernel/fork.c index d4f0dff9d617..3c72a5b321a7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1340,7 +1340,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (likely(p->pid)) { - tracehook_finish_clone(p, clone_flags, trace); + ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); if (thread_group_leader(p)) { if (is_child_reaper(pid)) @@ -1481,10 +1481,22 @@ long do_fork(unsigned long clone_flags, } /* - * When called from kernel_thread, don't do user tracing stuff. + * Determine whether and which event to report to ptracer. When + * called from kernel_thread or CLONE_UNTRACED is explicitly + * requested, no event is reported; otherwise, report if the event + * for the type of forking is enabled. */ - if (likely(user_mode(regs))) - trace = tracehook_prepare_clone(clone_flags); + if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) { + if (clone_flags & CLONE_VFORK) + trace = PTRACE_EVENT_VFORK; + else if ((clone_flags & CSIGNAL) != SIGCHLD) + trace = PTRACE_EVENT_CLONE; + else + trace = PTRACE_EVENT_FORK; + + if (likely(!ptrace_event_enabled(current, trace))) + trace = 0; + } p = copy_process(clone_flags, stack_start, regs, stack_size, child_tidptr, NULL, trace); @@ -1508,20 +1520,31 @@ long do_fork(unsigned long clone_flags, } audit_finish_fork(p); - tracehook_report_clone(regs, clone_flags, nr, p); + + /* + * Child is ready but hasn't started running yet. Queue + * SIGSTOP if it's gonna be ptraced - it doesn't matter who + * attached/attaching to this task, the pending SIGSTOP is + * right in any case. + */ + if (unlikely(p->ptrace)) { + sigaddset(&p->pending.signal, SIGSTOP); + set_tsk_thread_flag(p, TIF_SIGPENDING); + } /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that - * hasn't gotten to tracehook_report_clone() yet. Now we - * clear it and set the child going. + * hasn't finished SIGSTOP raising yet. Now we clear it + * and set the child going. */ p->flags &= ~PF_STARTING; wake_up_new_task(p); - tracehook_report_clone_complete(trace, regs, - clone_flags, nr, p); + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event(trace, nr); if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); -- cgit v1.2.3 From 732375c6a5a4cc825b676c922d547aba96b8ce15 Mon Sep 17 00:00:00 2001 From: Dima Zavin Date: Thu, 7 Jul 2011 17:27:59 -0700 Subject: plist: Remove the need to supply locks to plist heads This was legacy code brought over from the RT tree and is no longer necessary. Signed-off-by: Dima Zavin Acked-by: Thomas Gleixner Cc: Daniel Walker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Andi Kleen Cc: Lai Jiangshan Link: http://lkml.kernel.org/r/1310084879-10351-2-git-send-email-dima@android.com Signed-off-by: Ingo Molnar --- include/linux/plist.h | 55 +++---------------------------------------------- include/linux/rtmutex.h | 4 ++-- kernel/fork.c | 2 +- kernel/futex.c | 2 +- kernel/pm_qos_params.c | 6 +++--- kernel/rtmutex.c | 2 +- kernel/sched.c | 4 ++-- lib/plist.c | 7 +------ 8 files changed, 14 insertions(+), 68 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/plist.h b/include/linux/plist.h index c9b9f322c8d8..aa0fb390bd29 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -77,14 +77,9 @@ #include #include -#include struct plist_head { struct list_head node_list; -#ifdef CONFIG_DEBUG_PI_LIST - raw_spinlock_t *rawlock; - spinlock_t *spinlock; -#endif }; struct plist_node { @@ -93,37 +88,13 @@ struct plist_node { struct list_head node_list; }; -#ifdef CONFIG_DEBUG_PI_LIST -# define PLIST_HEAD_LOCK_INIT(_lock) .spinlock = _lock -# define PLIST_HEAD_LOCK_INIT_RAW(_lock) .rawlock = _lock -#else -# define PLIST_HEAD_LOCK_INIT(_lock) -# define PLIST_HEAD_LOCK_INIT_RAW(_lock) -#endif - -#define _PLIST_HEAD_INIT(head) \ - .node_list = LIST_HEAD_INIT((head).node_list) - /** * PLIST_HEAD_INIT - static struct plist_head initializer * @head: struct plist_head variable name - * @_lock: lock to initialize for this list - */ -#define PLIST_HEAD_INIT(head, _lock) \ -{ \ - _PLIST_HEAD_INIT(head), \ - PLIST_HEAD_LOCK_INIT(&(_lock)) \ -} - -/** - * PLIST_HEAD_INIT_RAW - static struct plist_head initializer - * @head: struct plist_head variable name - * @_lock: lock to initialize for this list */ -#define PLIST_HEAD_INIT_RAW(head, _lock) \ +#define PLIST_HEAD_INIT(head) \ { \ - _PLIST_HEAD_INIT(head), \ - PLIST_HEAD_LOCK_INIT_RAW(&(_lock)) \ + .node_list = LIST_HEAD_INIT((head).node_list) \ } /** @@ -141,31 +112,11 @@ struct plist_node { /** * plist_head_init - dynamic struct plist_head initializer * @head: &struct plist_head pointer - * @lock: spinlock protecting the list (debugging) */ static inline void -plist_head_init(struct plist_head *head, spinlock_t *lock) +plist_head_init(struct plist_head *head) { INIT_LIST_HEAD(&head->node_list); -#ifdef CONFIG_DEBUG_PI_LIST - head->spinlock = lock; - head->rawlock = NULL; -#endif -} - -/** - * plist_head_init_raw - dynamic struct plist_head initializer - * @head: &struct plist_head pointer - * @lock: raw_spinlock protecting the list (debugging) - */ -static inline void -plist_head_init_raw(struct plist_head *head, raw_spinlock_t *lock) -{ - INIT_LIST_HEAD(&head->node_list); -#ifdef CONFIG_DEBUG_PI_LIST - head->rawlock = lock; - head->spinlock = NULL; -#endif } /** diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 8d522ffeda33..de17134244f3 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -66,7 +66,7 @@ struct hrtimer_sleeper; #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .wait_list = PLIST_HEAD_INIT_RAW(mutexname.wait_list, mutexname.wait_lock) \ + , .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \ , .owner = NULL \ __DEBUG_RT_MUTEX_INITIALIZER(mutexname)} @@ -100,7 +100,7 @@ extern void rt_mutex_unlock(struct rt_mutex *lock); #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ - .pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters, tsk.pi_lock), \ + .pi_waiters = PLIST_HEAD_INIT(tsk.pi_waiters), \ INIT_RT_MUTEX_DEBUG(tsk) #else # define INIT_RT_MUTEXES(tsk) diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..7517a53d50e3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1013,7 +1013,7 @@ static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES - plist_head_init_raw(&p->pi_waiters, &p->pi_lock); + plist_head_init(&p->pi_waiters); p->pi_blocked_on = NULL; #endif } diff --git a/kernel/futex.c b/kernel/futex.c index fe28dc282eae..3fbc76cbb9aa 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2697,7 +2697,7 @@ static int __init futex_init(void) futex_cmpxchg_enabled = 1; for (i = 0; i < ARRAY_SIZE(futex_queues); i++) { - plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock); + plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 6824ca7d4d0c..37f05d0f0793 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -74,7 +74,7 @@ static DEFINE_SPINLOCK(pm_qos_lock); static struct pm_qos_object null_pm_qos; static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); static struct pm_qos_object cpu_dma_pm_qos = { - .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests), .notifiers = &cpu_dma_lat_notifier, .name = "cpu_dma_latency", .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, @@ -84,7 +84,7 @@ static struct pm_qos_object cpu_dma_pm_qos = { static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); static struct pm_qos_object network_lat_pm_qos = { - .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests), .notifiers = &network_lat_notifier, .name = "network_latency", .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, @@ -95,7 +95,7 @@ static struct pm_qos_object network_lat_pm_qos = { static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); static struct pm_qos_object network_throughput_pm_qos = { - .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests), .notifiers = &network_throughput_notifier, .name = "network_throughput", .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index ab449117aaf2..255e1662acdb 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -890,7 +890,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name) { lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); - plist_head_init_raw(&lock->wait_list, &lock->wait_lock); + plist_head_init(&lock->wait_list); debug_rt_mutex_init(lock, name); } diff --git a/kernel/sched.c b/kernel/sched.c index 3f2e502d609b..71bc127e96ba 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -7781,7 +7781,7 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) #ifdef CONFIG_SMP rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; - plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); + plist_head_init(&rt_rq->pushable_tasks); #endif rt_rq->rt_time = 0; @@ -7986,7 +7986,7 @@ void __init sched_init(void) #endif #ifdef CONFIG_RT_MUTEXES - plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); + plist_head_init(&init_task.pi_waiters); #endif /* diff --git a/lib/plist.c b/lib/plist.c index 0ae7e6431726..a0a4da489c22 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -56,11 +56,6 @@ static void plist_check_list(struct list_head *top) static void plist_check_head(struct plist_head *head) { - WARN_ON(head != &test_head && !head->rawlock && !head->spinlock); - if (head->rawlock) - WARN_ON_SMP(!raw_spin_is_locked(head->rawlock)); - if (head->spinlock) - WARN_ON_SMP(!spin_is_locked(head->spinlock)); if (!plist_head_empty(head)) plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); @@ -180,7 +175,7 @@ static int __init plist_test(void) unsigned int r = local_clock(); printk(KERN_INFO "start plist test\n"); - plist_head_init(&test_head, NULL); + plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) plist_node_init(test_node + i, 0); -- cgit v1.2.3 From 4aede84b33d6beb401136a3deca0651ae07c5e99 Mon Sep 17 00:00:00 2001 From: Justin TerAvest Date: Tue, 12 Jul 2011 08:31:45 +0200 Subject: fixlet: Remove fs_excl from struct task. fs_excl is a poor man's priority inheritance for filesystems to hint to the block layer that an operation is important. It was never clearly specified, not widely adopted, and will not prevent starvation in many cases (like across cgroups). fs_excl was introduced with the time sliced CFQ IO scheduler, to indicate when a process held FS exclusive resources and thus needed a boost. It doesn't cover all file systems, and it was never fully complete. Lets kill it. Signed-off-by: Justin TerAvest Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 28 +--------------------------- fs/reiserfs/journal.c | 13 ------------- fs/super.c | 4 ---- include/linux/fs.h | 4 ---- include/linux/init_task.h | 1 - include/linux/sched.h | 1 - kernel/exit.c | 1 - kernel/fork.c | 1 - 8 files changed, 1 insertion(+), 52 deletions(-) (limited to 'kernel/fork.c') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 762bd509b71b..d8b108737b72 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -134,7 +134,7 @@ struct cfq_queue { /* io prio of this group */ unsigned short ioprio, org_ioprio; - unsigned short ioprio_class, org_ioprio_class; + unsigned short ioprio_class; pid_t pid; @@ -2869,7 +2869,6 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) * elevate the priority of this queue */ cfqq->org_ioprio = cfqq->ioprio; - cfqq->org_ioprio_class = cfqq->ioprio_class; cfq_clear_cfqq_prio_changed(cfqq); } @@ -3593,30 +3592,6 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfq_schedule_dispatch(cfqd); } -/* - * we temporarily boost lower priority queues if they are holding fs exclusive - * resources. they are boosted to normal prio (CLASS_BE/4) - */ -static void cfq_prio_boost(struct cfq_queue *cfqq) -{ - if (has_fs_excl()) { - /* - * boost idle prio on transactions that would lock out other - * users of the filesystem - */ - if (cfq_class_idle(cfqq)) - cfqq->ioprio_class = IOPRIO_CLASS_BE; - if (cfqq->ioprio > IOPRIO_NORM) - cfqq->ioprio = IOPRIO_NORM; - } else { - /* - * unboost the queue (if needed) - */ - cfqq->ioprio_class = cfqq->org_ioprio_class; - cfqq->ioprio = cfqq->org_ioprio; - } -} - static inline int __cfq_may_queue(struct cfq_queue *cfqq) { if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) { @@ -3647,7 +3622,6 @@ static int cfq_may_queue(struct request_queue *q, int rw) cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { cfq_init_prio_data(cfqq, cic->ioc); - cfq_prio_boost(cfqq); return __cfq_may_queue(cfqq); } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index c5e82ece7c6c..a159ba5a35e7 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -678,23 +678,19 @@ struct buffer_chunk { static void write_chunk(struct buffer_chunk *chunk) { int i; - get_fs_excl(); for (i = 0; i < chunk->nr; i++) { submit_logged_buffer(chunk->bh[i]); } chunk->nr = 0; - put_fs_excl(); } static void write_ordered_chunk(struct buffer_chunk *chunk) { int i; - get_fs_excl(); for (i = 0; i < chunk->nr; i++) { submit_ordered_buffer(chunk->bh[i]); } chunk->nr = 0; - put_fs_excl(); } static int add_to_chunk(struct buffer_chunk *chunk, struct buffer_head *bh, @@ -986,8 +982,6 @@ static int flush_commit_list(struct super_block *s, return 0; } - get_fs_excl(); - /* before we can put our commit blocks on disk, we have to make sure everyone older than ** us is on disk too */ @@ -1145,7 +1139,6 @@ static int flush_commit_list(struct super_block *s, if (retval) reiserfs_abort(s, retval, "Journal write error in %s", __func__); - put_fs_excl(); return retval; } @@ -1374,8 +1367,6 @@ static int flush_journal_list(struct super_block *s, return 0; } - get_fs_excl(); - /* if all the work is already done, get out of here */ if (atomic_read(&(jl->j_nonzerolen)) <= 0 && atomic_read(&(jl->j_commit_left)) <= 0) { @@ -1597,7 +1588,6 @@ static int flush_journal_list(struct super_block *s, put_journal_list(s, jl); if (flushall) mutex_unlock(&journal->j_flush_mutex); - put_fs_excl(); return err; } @@ -3108,7 +3098,6 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th, th->t_trans_id = journal->j_trans_id; unlock_journal(sb); INIT_LIST_HEAD(&th->t_list); - get_fs_excl(); return 0; out_fail: @@ -3964,7 +3953,6 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, flush = flags & FLUSH_ALL; wait_on_commit = flags & WAIT; - put_fs_excl(); current->journal_info = th->t_handle_save; reiserfs_check_lock_depth(sb, "journal end"); if (journal->j_len == 0) { @@ -4316,4 +4304,3 @@ void reiserfs_abort_journal(struct super_block *sb, int errno) dump_stack(); #endif } - diff --git a/fs/super.c b/fs/super.c index ab3d672db0de..cf12ba50973b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -245,13 +245,11 @@ static int grab_super(struct super_block *s) __releases(sb_lock) */ void lock_super(struct super_block * sb) { - get_fs_excl(); mutex_lock(&sb->s_lock); } void unlock_super(struct super_block * sb) { - put_fs_excl(); mutex_unlock(&sb->s_lock); } @@ -280,7 +278,6 @@ void generic_shutdown_super(struct super_block *sb) if (sb->s_root) { shrink_dcache_for_umount(sb); sync_filesystem(sb); - get_fs_excl(); sb->s_flags &= ~MS_ACTIVE; fsnotify_unmount_inodes(&sb->s_inodes); @@ -295,7 +292,6 @@ void generic_shutdown_super(struct super_block *sb) "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); } - put_fs_excl(); } spin_lock(&sb_lock); /* should be initialized for __put_super_and_need_restart() */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e73e2e9ae33..f6c866c287b5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1453,10 +1453,6 @@ enum { #define vfs_check_frozen(sb, level) \ wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) -#define get_fs_excl() atomic_inc(¤t->fs_excl) -#define put_fs_excl() atomic_dec(¤t->fs_excl) -#define has_fs_excl() atomic_read(¤t->fs_excl) - /* * until VFS tracks user namespaces for inodes, just make all files * belong to init_user_ns diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 580f70c02391..d14e058aaeed 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -176,7 +176,6 @@ extern struct cred init_cred; .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ .journal_info = NULL, \ .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ - .fs_excl = ATOMIC_INIT(0), \ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ diff --git a/include/linux/sched.h b/include/linux/sched.h index a837b20ba190..22f54249cde1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1503,7 +1503,6 @@ struct task_struct { short il_next; short pref_node_fork; #endif - atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; /* diff --git a/kernel/exit.c b/kernel/exit.c index f2b321bae440..b412df45ea6c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -906,7 +906,6 @@ NORET_TYPE void do_exit(long code) profile_task_exit(tsk); - WARN_ON(atomic_read(&tsk->fs_excl)); WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..30a0e8607223 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -291,7 +291,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) /* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); - atomic_set(&tsk->fs_excl, 0); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif -- cgit v1.2.3 From dcace06cc29df927a74a6bc0e57b9bef87704377 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Jul 2011 19:13:54 +0200 Subject: ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task() If the new child is traced, do_fork() adds the pending SIGSTOP. It assumes that either it is traced because of auto-attach or the tracer attached later, in both cases sigaddset/set_thread_flag is correct even if SIGSTOP is already pending. Now that we have PTRACE_SEIZE this is no longer right in the latter case. If the tracer does PTRACE_SEIZE after copy_process() makes the child visible the queued SIGSTOP is wrong. We could check PT_SEIZED bit and change ptrace_attach() to set both PT_PTRACED and PT_SEIZED bits simultaneously but see the next patch, we need to know whether this child was auto-attached or not anyway. So this patch simply moves this code to ptrace_init_task(), this way we can never race with ptrace_attach(). Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- include/linux/ptrace.h | 3 +++ kernel/fork.c | 12 ------------ 2 files changed, 3 insertions(+), 12 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index fd8669fc339f..9b5d2c901d06 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -227,6 +227,9 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; __ptrace_link(child, current->parent); + + sigaddset(&child->pending.signal, SIGSTOP); + set_tsk_thread_flag(child, TIF_SIGPENDING); } } diff --git a/kernel/fork.c b/kernel/fork.c index 3c72a5b321a7..4d4117e01504 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -1521,17 +1520,6 @@ long do_fork(unsigned long clone_flags, audit_finish_fork(p); - /* - * Child is ready but hasn't started running yet. Queue - * SIGSTOP if it's gonna be ptraced - it doesn't matter who - * attached/attaching to this task, the pending SIGSTOP is - * right in any case. - */ - if (unlikely(p->ptrace)) { - sigaddset(&p->pending.signal, SIGSTOP); - set_tsk_thread_flag(p, TIF_SIGPENDING); - } - /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that -- cgit v1.2.3 From 6657719390cd05be45f4e3b501d8bb46889c0a19 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 28 Jun 2011 15:41:10 -0400 Subject: make sure that nsproxy_cache is initialized early enough Signed-off-by: Al Viro --- include/linux/nsproxy.h | 1 + kernel/fork.c | 1 + kernel/nsproxy.c | 4 +--- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 50d20aba57d3..cc37a55ad004 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -68,6 +68,7 @@ void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); void free_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct fs_struct *); +int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..31fa13e63b70 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1574,6 +1574,7 @@ void __init proc_caches_init(void) SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); + nsproxy_cache_init(); } /* diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index d6a00f3de15d..9aeab4b98c64 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -271,10 +271,8 @@ out: return err; } -static int __init nsproxy_cache_init(void) +int __init nsproxy_cache_init(void) { nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC); return 0; } - -module_init(nsproxy_cache_init); -- cgit v1.2.3 From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 1 + include/linux/nodemask.h | 13 +++++++++++++ kernel/cpuset.c | 8 ++++++++ kernel/fork.c | 4 ++++ lib/bitmap.c | 2 +- mm/mempolicy.c | 16 ++++++++++++++++ 6 files changed, 43 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0bf0005..3bac44cce142 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -144,6 +144,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index dba35e413371..7afc36334d52 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -66,6 +66,8 @@ * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * + * int node_random(mask) Random node with set bit in mask + * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * @@ -430,6 +432,7 @@ static inline void node_set_offline(int nid) node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } + #else static inline int node_state(int node, enum node_states state) @@ -460,6 +463,16 @@ static inline int num_node_state(enum node_states state) #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) + +#endif + +#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) +extern int node_random(const nodemask_t *maskp); +#else +static inline int node_random(const nodemask_t *mask) +{ + return 0; +} #endif #define node_online_map node_states[N_ONLINE] diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9c9b7545c810..f8bc977ccbbe 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2460,11 +2460,19 @@ static int cpuset_spread_node(int *rotor) int cpuset_mem_spread_node(void) { + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } diff --git a/kernel/fork.c b/kernel/fork.c index 17bf7c8d6511..e33177edb3bf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1173,6 +1173,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; +#endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW diff --git a/lib/bitmap.c b/lib/bitmap.c index 3f3b68199d74..37ef4b048795 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -756,7 +756,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits) * * The bit positions 0 through @bits are valid positions in @buf. */ -static int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits) +int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits) { int pos = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e7fb9d25c54e..8b57173c1dd5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -93,6 +93,7 @@ #include #include +#include #include "internal.h" @@ -1645,6 +1646,21 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } +/* + * Return the bit number of a random bit set in the nodemask. + * (returns -1 if nodemask is empty) + */ +int node_random(const nodemask_t *maskp) +{ + int w, bit = -1; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +} + #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) -- cgit v1.2.3 From fb0a685cb95a0267a96153af2f72486f27be5847 Mon Sep 17 00:00:00 2001 From: Daniel Rebelo de Oliveira Date: Tue, 26 Jul 2011 16:08:39 -0700 Subject: kernel/fork.c: fix a few coding style issues Signed-off-by: Daniel Rebelo de Oliveira Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 83 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 35 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index e33177edb3bf..e7ceaca89609 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -80,7 +80,7 @@ * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ -int nr_threads; /* The idle threads do not count.. */ +int nr_threads; /* The idle threads do not count.. */ int max_threads; /* tunable limit on nr_threads */ @@ -232,7 +232,7 @@ void __init fork_init(unsigned long mempages) /* * we need to allow at least 20 threads to boot a system */ - if(max_threads < 20) + if (max_threads < 20) max_threads = 20; init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; @@ -268,7 +268,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; } - err = arch_dup_task_struct(tsk, orig); + err = arch_dup_task_struct(tsk, orig); if (err) goto out; @@ -288,8 +288,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->stack_canary = get_random_int(); #endif - /* One for us, one for whoever does the "release_task()" (usually parent) */ - atomic_set(&tsk->usage,2); + /* + * One for us, one for whoever does the "release_task()" (usually + * parent) + */ + atomic_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif @@ -437,7 +440,7 @@ fail_nomem: goto out; } -static inline int mm_alloc_pgd(struct mm_struct * mm) +static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) @@ -445,7 +448,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm) return 0; } -static inline void mm_free_pgd(struct mm_struct * mm) +static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } @@ -482,7 +485,7 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -513,9 +516,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) /* * Allocate and initialize an mm_struct. */ -struct mm_struct * mm_alloc(void) +struct mm_struct *mm_alloc(void) { - struct mm_struct * mm; + struct mm_struct *mm; mm = allocate_mm(); if (!mm) @@ -583,7 +586,7 @@ void added_exe_file_vma(struct mm_struct *mm) void removed_exe_file_vma(struct mm_struct *mm) { mm->num_exe_file_vmas--; - if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + if ((mm->num_exe_file_vmas == 0) && mm->exe_file) { fput(mm->exe_file); mm->exe_file = NULL; } @@ -775,9 +778,9 @@ fail_nocontext: return NULL; } -static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) +static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { - struct mm_struct * mm, *oldmm; + struct mm_struct *mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; @@ -844,7 +847,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; @@ -1166,11 +1169,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); - if (IS_ERR(p->mempolicy)) { - retval = PTR_ERR(p->mempolicy); - p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; - } + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup_cgroup; + } mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_CPUSETS @@ -1216,25 +1219,33 @@ static struct task_struct *copy_process(unsigned long clone_flags, retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; - - if ((retval = audit_alloc(p))) + retval = audit_alloc(p); + if (retval) goto bad_fork_cleanup_policy; /* copy all the process information */ - if ((retval = copy_semundo(clone_flags, p))) + retval = copy_semundo(clone_flags, p); + if (retval) goto bad_fork_cleanup_audit; - if ((retval = copy_files(clone_flags, p))) + retval = copy_files(clone_flags, p); + if (retval) goto bad_fork_cleanup_semundo; - if ((retval = copy_fs(clone_flags, p))) + retval = copy_fs(clone_flags, p); + if (retval) goto bad_fork_cleanup_files; - if ((retval = copy_sighand(clone_flags, p))) + retval = copy_sighand(clone_flags, p); + if (retval) goto bad_fork_cleanup_fs; - if ((retval = copy_signal(clone_flags, p))) + retval = copy_signal(clone_flags, p); + if (retval) goto bad_fork_cleanup_sighand; - if ((retval = copy_mm(clone_flags, p))) + retval = copy_mm(clone_flags, p); + if (retval) goto bad_fork_cleanup_signal; - if ((retval = copy_namespaces(clone_flags, p))) + retval = copy_namespaces(clone_flags, p); + if (retval) goto bad_fork_cleanup_mm; - if ((retval = copy_io(clone_flags, p))) + retval = copy_io(clone_flags, p); + if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) @@ -1256,7 +1267,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, /* * Clear TID on mm_release()? */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1324,7 +1335,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). - */ + */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); @@ -1685,12 +1696,14 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; - if ((err = unshare_fs(unshare_flags, &new_fs))) + err = unshare_fs(unshare_flags, &new_fs); + if (err) goto bad_unshare_out; - if ((err = unshare_fd(unshare_flags, &new_fd))) + err = unshare_fd(unshare_flags, &new_fd); + if (err) goto bad_unshare_cleanup_fs; - if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, - new_fs))) + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs); + if (err) goto bad_unshare_cleanup_fd; if (new_fs || new_fd || do_sysvsem || new_nsproxy) { -- cgit v1.2.3