The patch titled Subject: task_work_add: generic process-context callbacks has been removed from the -mm tree. Its filename was task_work_add-generic-process-context-callbacks.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ From: Oleg Nesterov <oleg@xxxxxxxxxx> Subject: task_work_add: generic process-context callbacks Provide a simple mechanism that allows running code in the (nonatomic) context of the arbitrary task. The caller does task_work_add(task, task_work) and this task executes task_work->func() either from do_notify_resume() or from do_exit(). The callback can rely on PF_EXITING to detect the latter case. "struct task_work" can be embedded in another struct, still it has "void *data" to handle the most common/simple case. This allows us to kill the ->replacement_session_keyring hack, and potentially this can have more users. Performance-wise, this adds 2 "unlikely(!hlist_empty())" checks into tracehook_notify_resume() and do_exit(). But at the same time we can remove the "replacement_session_keyring != NULL" checks from arch/*/signal.c and exit_creds(). Note: task_work_add/task_work_run abuses ->pi_lock. This is only because this lock is already used by lookup_pi_state() to synchronize with do_exit() setting PF_EXITING. Fortunately the scope of this lock in task_work.c is really tiny, and the code is unlikely anyway. Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx> Acked-by: David Howells <dhowells@xxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: Richard Kuo <rkuo@xxxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Cc: Alexander Gordeev <agordeev@xxxxxxxxxx> Cc: Chris Zankel <chris@xxxxxxxxxx> Cc: David Smith <dsmith@xxxxxxxxxx> Cc: "Frank Ch. Eigler" <fche@xxxxxxxxxx> Cc: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx> Cc: Larry Woodman <lwoodman@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/sched.h | 2 include/linux/task_work.h | 33 ++++++++++++++ include/linux/tracehook.h | 13 ++++- kernel/Makefile | 2 kernel/exit.c | 5 +- kernel/fork.c | 2 kernel/task_work.c | 84 ++++++++++++++++++++++++++++++++++++ 7 files changed, 137 insertions(+), 4 deletions(-) diff -puN include/linux/sched.h~task_work_add-generic-process-context-callbacks include/linux/sched.h --- a/include/linux/sched.h~task_work_add-generic-process-context-callbacks +++ a/include/linux/sched.h @@ -1415,6 +1415,8 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; + struct hlist_head task_works; + struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL uid_t loginuid; diff -puN /dev/null include/linux/task_work.h --- /dev/null +++ a/include/linux/task_work.h @@ -0,0 +1,33 @@ +#ifndef _LINUX_TASK_WORK_H +#define _LINUX_TASK_WORK_H + +#include <linux/list.h> +#include <linux/sched.h> + +struct task_work; +typedef void (*task_work_func_t)(struct task_work *); + +struct task_work { + struct hlist_node hlist; + task_work_func_t func; + void *data; +}; + +static inline void +init_task_work(struct task_work *twork, task_work_func_t func, void *data) +{ + twork->func = func; + twork->data = data; +} + +int task_work_add(struct task_struct *task, struct task_work *twork, bool); +struct task_work *task_work_cancel(struct task_struct *, task_work_func_t); +void task_work_run(void); + +static inline void exit_task_work(struct task_struct *task) +{ + if (unlikely(!hlist_empty(&task->task_works))) + task_work_run(); +} + +#endif /* _LINUX_TASK_WORK_H */ diff -puN include/linux/tracehook.h~task_work_add-generic-process-context-callbacks include/linux/tracehook.h --- a/include/linux/tracehook.h~task_work_add-generic-process-context-callbacks +++ a/include/linux/tracehook.h @@ -49,6 +49,7 @@ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> +#include <linux/task_work.h> struct linux_binprm; /* @@ -153,7 +154,6 @@ static inline void tracehook_signal_hand ptrace_notify(SIGTRAP); } -#ifdef TIF_NOTIFY_RESUME /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() @@ -165,8 +165,10 @@ static inline void tracehook_signal_hand */ static inline void set_notify_resume(struct task_struct *task) { +#ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); +#endif } /** @@ -184,7 +186,14 @@ static inline void set_notify_resume(str */ static inline void tracehook_notify_resume(struct pt_regs *regs) { + /* + * The caller just cleared TIF_NOTIFY_RESUME. This barrier + * pairs with task_work_add()->set_notify_resume() after + * hlist_add_head(task->task_works); + */ + smp_mb__after_clear_bit(); + if (unlikely(!hlist_empty(¤t->task_works))) + task_work_run(); } -#endif /* TIF_NOTIFY_RESUME */ #endif /* <linux/tracehook.h> */ diff -puN kernel/Makefile~task_work_add-generic-process-context-callbacks kernel/Makefile --- a/kernel/Makefile~task_work_add-generic-process-context-callbacks +++ a/kernel/Makefile @@ -5,7 +5,7 @@ obj-y = fork.o exec_domain.o panic.o printk.o \ cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ - signal.o sys.o kmod.o workqueue.o pid.o \ + signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ diff -puN kernel/exit.c~task_work_add-generic-process-context-callbacks kernel/exit.c --- a/kernel/exit.c~task_work_add-generic-process-context-callbacks +++ a/kernel/exit.c @@ -946,11 +946,14 @@ void do_exit(long code) exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against - * an exiting task cleaning up the robust pi futexes. + * an exiting task cleaning up the robust pi futexes, and in + * task_work_add() to avoid the race with exit_task_work(). */ smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); + exit_task_work(tsk); + exit_irq_thread(); if (unlikely(in_atomic())) diff -puN kernel/fork.c~task_work_add-generic-process-context-callbacks kernel/fork.c --- a/kernel/fork.c~task_work_add-generic-process-context-callbacks +++ a/kernel/fork.c @@ -1420,6 +1420,8 @@ static struct task_struct *copy_process( */ p->group_leader = p; + INIT_HLIST_HEAD(&p->task_works); + /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible * on the tasklist. */ diff -puN /dev/null kernel/task_work.c --- /dev/null +++ a/kernel/task_work.c @@ -0,0 +1,84 @@ +#include <linux/spinlock.h> +#include <linux/task_work.h> +#include <linux/tracehook.h> + +int +task_work_add(struct task_struct *task, struct task_work *twork, bool notify) +{ + unsigned long flags; + int err = -ESRCH; + +#ifndef TIF_NOTIFY_RESUME + if (notify) + return -ENOTSUPP; +#endif + /* + * We must not insert the new work if the task has already passed + * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait() + * and check PF_EXITING under pi_lock. + */ + raw_spin_lock_irqsave(&task->pi_lock, flags); + if (likely(!(task->flags & PF_EXITING))) { + hlist_add_head(&twork->hlist, &task->task_works); + err = 0; + } + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */ + if (likely(!err) && notify) + set_notify_resume(task); + return err; +} + +struct task_work * +task_work_cancel(struct task_struct *task, task_work_func_t func) +{ + unsigned long flags; + struct task_work *twork; + struct hlist_node *pos; + + raw_spin_lock_irqsave(&task->pi_lock, flags); + hlist_for_each_entry(twork, pos, &task->task_works, hlist) { + if (twork->func == func) { + hlist_del(&twork->hlist); + goto found; + } + } + twork = NULL; + found: + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + return twork; +} + +void task_work_run(void) +{ + struct task_struct *task = current; + struct hlist_head task_works; + struct hlist_node *pos; + + raw_spin_lock_irq(&task->pi_lock); + hlist_move_list(&task->task_works, &task_works); + raw_spin_unlock_irq(&task->pi_lock); + + if (unlikely(hlist_empty(&task_works))) + return; + /* + * We use hlist to save the space in task_struct, but we want fifo. + * Find the last entry, the list should be short, then process them + * in reverse order. + */ + for (pos = task_works.first; pos->next; pos = pos->next) + ; + + for (;;) { + struct hlist_node **pprev = pos->pprev; + struct task_work *twork = container_of(pos, struct task_work, + hlist); + twork->func(twork); + + if (pprev == &task_works.first) + break; + pos = container_of(pprev, struct hlist_node, next); + } +} _ Patches currently in -mm which might be from oleg@xxxxxxxxxx are origin.patch linux-next.patch mm-fork-fix-overflow-in-vma-length-when-copying-mmap-on-clone.patch mm-correctly-synchronize-rss-counters-at-exit-exec.patch kmod-unexport-call_usermodehelper_freeinfo.patch kmod-convert-two-call-sites-to-call_usermodehelper_fns.patch kmod-move-call_usermodehelper_fns-to-c-file-and-unexport-all-its-helpers.patch cred-remove-task_is_dead-from-__task_cred-validation.patch stack-usage-add-pid-to-warning-printk-in-check_stack_usage.patch proc-clean-up-proc-pid-environ-handling.patch proc-remove-mm_for_maps.patch proc-use-mm_access-instead-of-ptrace_may_access.patch proc-use-is_err_or_null.patch fork-call-complete_vfork_done-after-clearing-child_tid-and-flushing-rss-counters.patch cpu-introduce-clear_tasks_mm_cpumask-helper.patch arm-use-clear_tasks_mm_cpumask.patch powerpc-use-clear_tasks_mm_cpumask.patch sh-use-clear_tasks_mm_cpumask.patch blackfin-a-couple-of-task-mm-handling-fixes.patch blackfin-fix-possible-deadlock-in-decode_address.patch um-should-hold-tasklist_lock-while-traversing-processes.patch um-fix-possible-race-on-task-mm.patch um-properly-check-all-process-threads-for-a-live-mm.patch pidns-use-task_active_pid_ns-in-do_notify_parent.patch pidns-make-killed-children-autoreap.patch pidns-guarantee-that-the-pidns-init-will-be-the-last-pidns-process-reaped-v2.patch pidns-guarantee-that-the-pidns-init-will-be-the-last-pidns-process-reaped-v2-fix.patch aio-vfs-cleanup-of-rw_copy_check_uvector-and-compat_rw_copy_check_uvector.patch sysctl-make-kernelns_last_pid-control-being-checkpoint_restore-dependent.patch fs-proc-introduce-proc-pid-task-tid-children-entry-v9.patch fs-proc-introduce-proc-pid-task-tid-children-entry-v9-fix.patch c-r-prctl-add-ability-to-set-new-mm_struct-exe_file.patch c-r-prctl-add-ability-to-set-new-mm_struct-exe_file-update-after-mm-num_exe_file_vmas-removal.patch c-r-prctl-add-ability-to-get-clear_tid_address.patch c-r-prctl-drop-vma-flags-test-on-pr_set_mm_-stack-data-assignment.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html