From 05cfb614ddbf3181540ce09d44d96486f8ba8d6a Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Sun, 26 Mar 2006 01:38:12 -0800 Subject: [PATCH] hrtimers: remove data field The nanosleep cleanup allows to remove the data field of hrtimer. The callback function can use container_of() to get it's own data. Since the hrtimer structure is anyway embedded in other structures, this adds no overhead. Signed-off-by: Roman Zippel Signed-off-by: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index e0054c1b9a09..036d14d2bf90 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -402,6 +402,7 @@ struct signal_struct { /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; + struct task_struct *tsk; ktime_t it_real_incr; /* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */ -- cgit v1.2.2 From 0771dfefc9e538f077d0b43b6dec19a5a67d0e70 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:22 -0800 Subject: [PATCH] lightweight robust futexes: core Add the core infrastructure for robust futexes: structure definitions, the new syscalls and the do_exit() based cleanup mechanism. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner Signed-off-by: Arjan van de Ven Acked-by: Ulrich Drepper Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 036d14d2bf90..fd4848f2d750 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -35,6 +35,7 @@ #include #include #include +#include #include /* For AT_VECTOR_SIZE */ @@ -872,6 +873,8 @@ struct task_struct { int cpuset_mems_generation; int cpuset_mem_spread_rotor; #endif + struct robust_list_head __user *robust_list; + atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; }; -- cgit v1.2.2 From 34f192c6527f20c47ccec239e7d51a27691b93fc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Mar 2006 01:16:24 -0800 Subject: [PATCH] lightweight robust futexes: compat 32-bit syscall compatibility support. (This patch also moves all futex related compat functionality into kernel/futex_compat.c.) Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner Signed-off-by: Arjan van de Ven Acked-by: Ulrich Drepper Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index fd4848f2d750..20b4f0372e44 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -874,6 +874,9 @@ struct task_struct { int cpuset_mem_spread_rotor; #endif struct robust_list_head __user *robust_list; +#ifdef CONFIG_COMPAT + struct compat_robust_list_head __user *compat_robust_list; +#endif atomic_t fs_excl; /* holding fs exclusive resources */ struct rcu_head rcu; -- cgit v1.2.2 From 6c99c5cb94319a601b5ec5ee31c331f84755dd74 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 28 Mar 2006 16:11:00 -0800 Subject: [PATCH] Remove dead kill_sl prototype from sched.h The kill_sl function doesn't exist in the kernel so a prototype is completely unnecessary. Signed-off-by: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 20b4f0372e44..5f5ab98bbb6b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1101,7 +1101,6 @@ extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); extern void zap_other_threads(struct task_struct *p); extern int kill_pg(pid_t, int, int); -extern int kill_sl(pid_t, int, int); extern int kill_proc(pid_t, int, int); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); -- cgit v1.2.2 From 8fafabd86f1b75ed3cc6a6ffbe6c3e53e3d8457d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:05 -0800 Subject: [PATCH] remove add_parent()'s parent argument add_parent(p, parent) is always called with parent == p->parent, and it makes no sense to do it differently. This patch removes this argument. No changes in affected .o files. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5f5ab98bbb6b..b4b14c32b28a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1184,7 +1184,7 @@ extern void wait_task_inactive(task_t * p); #endif #define remove_parent(p) list_del_init(&(p)->sibling) -#define add_parent(p, parent) list_add_tail(&(p)->sibling,&(parent)->children) +#define add_parent(p) list_add_tail(&(p)->sibling,&(p)->parent->children) #define REMOVE_LINKS(p) do { \ if (thread_group_leader(p)) \ @@ -1195,7 +1195,7 @@ extern void wait_task_inactive(task_t * p); #define SET_LINKS(p) do { \ if (thread_group_leader(p)) \ list_add_tail(&(p)->tasks,&init_task.tasks); \ - add_parent(p, (p)->parent); \ + add_parent(p); \ } while (0) #define next_task(p) list_entry((p)->tasks.next, struct task_struct, tasks) -- cgit v1.2.2 From c97d98931ac52ef110b62d9b75c6a6f2bfbc1898 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:06 -0800 Subject: [PATCH] kill SET_LINKS/REMOVE_LINKS Both SET_LINKS() and SET_LINKS/REMOVE_LINKS() have exactly one caller, and these callers already check thread_group_leader(). This patch kills theese macros, they mix two different things: setting process's parent and registering it in init_task.tasks list. Callers are updated to do these actions by hand. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b4b14c32b28a..1f16fb1fea22 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1186,18 +1186,6 @@ extern void wait_task_inactive(task_t * p); #define remove_parent(p) list_del_init(&(p)->sibling) #define add_parent(p) list_add_tail(&(p)->sibling,&(p)->parent->children) -#define REMOVE_LINKS(p) do { \ - if (thread_group_leader(p)) \ - list_del_init(&(p)->tasks); \ - remove_parent(p); \ - } while (0) - -#define SET_LINKS(p) do { \ - if (thread_group_leader(p)) \ - list_add_tail(&(p)->tasks,&init_task.tasks); \ - add_parent(p); \ - } while (0) - #define next_task(p) list_entry((p)->tasks.next, struct task_struct, tasks) #define prev_task(p) list_entry((p)->tasks.prev, struct task_struct, tasks) -- cgit v1.2.2 From 73b9ebfe126a4a886ee46cbab637374d7024668a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:07 -0800 Subject: [PATCH] pidhash: don't count idle threads fork_idle() does unhash_process() just after copy_process(). Contrary, boot_cpu's idle thread explicitely registers itself for each pid_type with nr = 0. copy_process() already checks p->pid != 0 before process_counts++, I think we can just skip attach_pid() calls and job control inits for idle threads and kill unhash_process(). We don't need to cleanup ->proc_dentry in fork_idle() because with this patch idle threads are never hashed in kernel/pid.c:pid_hash[]. We don't need to hash pid == 0 in pidmap_init(). free_pidmap() is never called with pid == 0 arg, so it will never be reused. So it is still possible to use pid == 0 in any PIDTYPE_xxx namespace from kernel/pid.c's POV. However with this patch we don't hash pid == 0 for PIDTYPE_PID case. We still have have PIDTYPE_PGID/PIDTYPE_SID entries with pid == 0: /sbin/init and kernel threads which don't call daemonize(). Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1f16fb1fea22..ddc0df7f8bf5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1214,8 +1214,6 @@ static inline int thread_group_empty(task_t *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) -extern void unhash_process(struct task_struct *p); - /* * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also -- cgit v1.2.2 From aa1757f90bea3f598b6e5d04d922a6a60200f1da Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:12 -0800 Subject: [PATCH] convert sighand_cache to use SLAB_DESTROY_BY_RCU This patch borrows a clever Hugh's 'struct anon_vma' trick. Without tasklist_lock held we can't trust task->sighand until we locked it and re-checked that it is still the same. But this means we don't need to defer 'kmem_cache_free(sighand)'. We can return the memory to slab immediately, all we need is to be sure that sighand->siglock can't dissapear inside rcu protected section. To do so we need to initialize ->siglock inside ctor function, SLAB_DESTROY_BY_RCU does the rest. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index ddc0df7f8bf5..bbcfc873bd98 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -355,16 +355,8 @@ struct sighand_struct { atomic_t count; struct k_sigaction action[_NSIG]; spinlock_t siglock; - struct rcu_head rcu; }; -extern void sighand_free_cb(struct rcu_head *rhp); - -static inline void sighand_free(struct sighand_struct *sp) -{ - call_rcu(&sp->rcu, sighand_free_cb); -} - /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always -- cgit v1.2.2 From f63ee72e0fb82e504a0489490babc7612c7cd6c2 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:13 -0800 Subject: [PATCH] introduce lock_task_sighand() helper Add lock_task_sighand() helper and converts group_send_sig_info() to use it. Hopefully we will have more users soon. This patch also removes '!sighand->count' and '!p->usage' checks, I think they both are bogus, racy and unneeded (but probably it makes sense to restore them as BUG_ON()s). ->sighand is cleared and it's ->count is decremented in release_task() with sighand->siglock held, so it is a bug to have '!p->usage || !->count' after we already locked and verified it is the same. On the other hand, an already dead task without ->sighand can have a non-zero ->usage due to ptrace, for example. If we read the stale value of ->sighand we must see the change after spin_lock(), because that change was done while holding that same old ->sighand.siglock. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index bbcfc873bd98..ca1fd31aae97 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1225,6 +1225,15 @@ static inline void task_unlock(struct task_struct *p) spin_unlock(&p->alloc_lock); } +extern struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags); + +static inline void unlock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); +} + #ifndef __HAVE_THREAD_FUNCTIONS #define task_thread_info(task) (task)->thread_info -- cgit v1.2.2 From 7001510d0cbf51ad202dd2d0744f54104285cbb9 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:14 -0800 Subject: [PATCH] copy_process: cleanup bad_fork_cleanup_sighand The only caller of exit_sighand(tsk) is copy_process's error path. We can call __exit_sighand() directly and kill exit_sighand(). This 'tsk' was not yet registered in pid_hash[] or init_task.tasks, it has no external references, nobody can see it, and IF (clone_flags & CLONE_SIGHAND) At least 'current' has a reference to ->sighand, this means atomic_dec_and_test(sighand->count) can't be true. ELSE Nobody can see this ->sighand, this means we can free it without any locking. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Acked-by: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index ca1fd31aae97..69c2a1e1529e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1151,7 +1151,6 @@ extern void exit_thread(void); extern void exit_files(struct task_struct *); extern void exit_signal(struct task_struct *); extern void __exit_signal(struct task_struct *); -extern void exit_sighand(struct task_struct *); extern void __exit_sighand(struct task_struct *); extern void exit_itimers(struct signal_struct *); -- cgit v1.2.2 From 6b3934ef52712ece50605dfc72e55d00c580831a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:16 -0800 Subject: [PATCH] copy_process: cleanup bad_fork_cleanup_signal __exit_signal() does important cleanups atomically under ->siglock. It is also called from copy_process's error path. This is not good, for example we can't move __unhash_process() under ->siglock for that reason. We should not mix these 2 paths, just look at ugly 'if (p->sighand)' under 'bad_fork_cleanup_sighand:' label. For copy_process() case it is sufficient to just backout copy_signal(), nothing more. Again, nobody can see this task yet. For CLONE_THREAD case we just decrement signal->count, otherwise nobody can see this ->signal and we can free it lockless. This patch assumes it is safe to do exit_thread_group_keys() without tasklist_lock. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Acked-by: David Howells Signed-off-by: Adrian Bunk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 69c2a1e1529e..7dd430b697aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1149,7 +1149,7 @@ extern void flush_thread(void); extern void exit_thread(void); extern void exit_files(struct task_struct *); -extern void exit_signal(struct task_struct *); +extern void __cleanup_signal(struct signal_struct *); extern void __exit_signal(struct task_struct *); extern void __exit_sighand(struct task_struct *); extern void exit_itimers(struct signal_struct *); -- cgit v1.2.2 From c81addc9d3a0ebff2155e0cd86f90820ab97147e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:17 -0800 Subject: [PATCH] rename __exit_sighand to cleanup_sighand Cosmetic, rename __exit_sighand to cleanup_sighand and move it close to copy_sighand(). This matches copy_signal/cleanup_signal naming, and I think it is easier to follow. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Acked-by: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7dd430b697aa..921148277da9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1150,8 +1150,8 @@ extern void exit_thread(void); extern void exit_files(struct task_struct *); extern void __cleanup_signal(struct signal_struct *); +extern void cleanup_sighand(struct task_struct *); extern void __exit_signal(struct task_struct *); -extern void __exit_sighand(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern NORET_TYPE void do_group_exit(int); -- cgit v1.2.2 From 6a14c5c9da0b4c34b5be783403c54f0396fcfe77 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:18 -0800 Subject: [PATCH] move __exit_signal() to kernel/exit.c __exit_signal() is private to release_task() now. I think it is better to make it static in kernel/exit.c and export flush_sigqueue() instead - this function is much more simple and straightforward. Signed-off-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 921148277da9..a913fca9e70d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1151,7 +1151,6 @@ extern void exit_thread(void); extern void exit_files(struct task_struct *); extern void __cleanup_signal(struct signal_struct *); extern void cleanup_sighand(struct task_struct *); -extern void __exit_signal(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern NORET_TYPE void do_group_exit(int); -- cgit v1.2.2 From 47e65328a7b1cdfc4e3102e50d60faf94ebba7d3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:25 -0800 Subject: [PATCH] pids: kill PIDTYPE_TGID This patch kills PIDTYPE_TGID pid_type thus saving one hash table in kernel/pid.c and speeding up subthreads create/destroy a bit. It is also a preparation for the further tref/pids rework. This patch adds 'struct list_head thread_group' to 'struct task_struct' instead. We don't detach group leader from PIDTYPE_PID namespace until another thread inherits it's ->pid == ->tgid, so we are safe wrt premature free_pidmap(->tgid) call. Currently there are no users of find_task_by_pid_type(PIDTYPE_TGID). Should the need arise, we can use find_task_by_pid()->group_leader. Signed-off-by: Oleg Nesterov Acked-By: Eric Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index a913fca9e70d..99855f694ebd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -752,6 +752,7 @@ struct task_struct { /* PID/PID hash table linkage. */ struct pid pids[PIDTYPE_MAX]; + struct list_head thread_group; struct completion *vfork_done; /* for vfork() */ int __user *set_child_tid; /* CLONE_CHILD_SETTID */ @@ -1192,13 +1193,17 @@ extern void wait_task_inactive(task_t * p); #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) -extern task_t * FASTCALL(next_thread(const task_t *p)); - #define thread_group_leader(p) (p->pid == p->tgid) +static inline task_t *next_thread(task_t *p) +{ + return list_entry(rcu_dereference(p->thread_group.next), + task_t, thread_group); +} + static inline int thread_group_empty(task_t *p) { - return list_empty(&p->pids[PIDTYPE_TGID].pid_list); + return list_empty(&p->thread_group); } #define delay_group_leader(p) \ -- cgit v1.2.2 From a7e5328a06a2beee3a2bbfaf87ce2a7bbe937de1 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:27 -0800 Subject: [PATCH] cleanup __exit_signal->cleanup_sighand path Move 'tsk->sighand = NULL' from cleanup_sighand() to __exit_signal(). This makes the exit path more understandable and allows us to do cleanup_sighand() outside of ->siglock protected section. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 99855f694ebd..d04186d8cc68 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1151,7 +1151,7 @@ extern void exit_thread(void); extern void exit_files(struct task_struct *); extern void __cleanup_signal(struct signal_struct *); -extern void cleanup_sighand(struct task_struct *); +extern void __cleanup_sighand(struct sighand_struct *); extern void exit_itimers(struct signal_struct *); extern NORET_TYPE void do_group_exit(int); -- cgit v1.2.2