- 18 Jun, 2009 40 commits
-
-
Oleg Nesterov authored
Based on Eric's patch which in turn was based on my patch. kthread_stop() has the nasty problems: - it runs unpredictably long with the global semaphore held. - it deadlocks if kthread itself does kthread_stop() before it obeys the kthread_should_stop() request. - it is not useable if kthread exits on its own, see for example the ugly "wait_to_die:" hack in migration_thread() - it is not possible to just tell kthread it should stop, we must always wait for its exit. With this patch kthread() allocates all neccesary data (struct kthread) on its own stack, globals kthread_stop_xxx are deleted. ->vfork_done is used as a pointer into "struct kthread", this means kthread_stop() can easily wait for kthread's exit. Signed-off-by:
Oleg Nesterov <oleg@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Vitaliy Gusev <vgusev@openvz.org Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Oleg Nesterov authored
We use two completions two create the kernel thread, this is a bit ugly. kthread() wakes up create_kthread() via ->started, then create_kthread() wakes up the caller kthread_create() via ->done. But kthread() does not need to wait for kthread(), it can just return. Instead kthread() itself can wake up the caller of kthread_create(). Kill kthread_create_info->started, ->done is enough. This improves the scalability a bit and sijmplifies the code. The only problem if kernel_thread() fails, in that case create_kthread() must do complete(&create->done). Signed-off-by:
-
Richard Kennedy authored
Reorder struct wait_opts to remove 8 bytes of alignment padding on 64 bit builds. Signed-off-by:
Richard Kennedy <richard@rsk.demon.co.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Roland McGrath <roland@redhat.com> Signed-off-by:
-
Oleg Nesterov authored
do_wait: current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); ... search for the task to reap ... In theory, the ->state changing can leak into the critical section. Since the child can change its status under read_lock(tasklist) in parallel (finish_stop/ptrace_stop), we can miss the wakeup if __wake_up_parent() sees us in TASK_RUNNING state. Add the barrier. Also, use __set_current_state() to set TASK_RUNNING. Signed-off-by:
Roland McGrath <roland@redhat.com> Signed-off-by:
-
Oleg Nesterov authored
do_wait() does BUG_ON(tsk->signal != current->signal), this looks like a raher obsolete check. At least, I don't think do_wait() is the best place to verify that all threads have the same ->signal. Remove it. Also, change the code to use while_each_thread(). Signed-off-by:
-
Oleg Nesterov authored
Now that we don't pass &retval down to other helpers we can simplify the code more. - kill tsk_result, just use retval - add the "notask" label right after the main loop, and s/got end/goto notask/ after the fastpath pid check. This way we don't need to initialize retval before this check and the code becomes a bit more clean, if this pid has no attached tasks we should just skip the list search. Signed-off-by:
-
Oleg Nesterov authored
Introduce "struct wait_opts" which holds the parameters for misc helpers in do_wait() pathes. This adds 13 lines to kernel/exit.c, but saves 256 bytes from .o and imho makes the code much more readable. This patch temporary uglifies rusage/siginfo code a little bit, will be addressed by further cleanups. Signed-off-by:
Ingo Molnar <mingo@elte.hu> Acked-by:
-
Oleg Nesterov authored
No functional changes, preparation for the next patch. ptrace_do_wait() adds WUNTRACED to options for wait_task_stopped() which should always accept the stopped tracee, even if do_wait() was called without WUNTRACED. Change wait_task_stopped() to check "ptrace || WUNTRACED" instead. This makes the code more explicit, and "int options" argument becomes const in do_wait() pathes. Signed-off-by:
-
Oleg Nesterov authored
In theory it is not safe to dereference ->parent/real_parent without tasklist or rcu lock, we can race with re-parenting. Signed-off-by:
-
Oleg Nesterov authored
The forked child can have TIF_SIGPENDING if it was copied from parent's ti->flags. But this is harmless and actually almost never happens, because copy_process() can't succeed if signal_pending() == T. Signed-off-by:
-
Oleg Nesterov authored
There is no reason for thread_group_cputime() in wait_task_zombie(), there must be no other threads. This call was previously needed to collect the per-cpu data which we do not have any longer. Signed-off-by:
-
Oleg Nesterov authored
Change ptrace_getsiginfo/ptrace_setsiginfo to use lock_task_sighand() without tasklist_lock. Perhaps it makes sense to make a single helper with "bool rw" argument. Signed-off-by:
-
Oleg Nesterov authored
If the non-traced sub-thread calls do_notify_parent_cldstop(), we send the notification to group_leader->real_parent and we report group_leader's pid. But, if group_leader is traced we use the wrong ->parent->nsproxy->pid_ns, the tracer and parent can live in different namespaces. Change the code to use "parent" instead of tsk->parent. Signed-off-by:
Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by:
-
Oleg Nesterov authored
Change wait_task_zombie() to use ->real_parent instead of ->parent. We could even use current afaics, but ->real_parent is more clean. We know that the child is not ptrace_reparented() and thus they are equal. But we should avoid using task_struct->parent, we are going to remove it. Signed-off-by:
-
Oleg Nesterov authored
- Use rcu_read_lock() instead of tasklist_lock to find/get the task in ptrace_get_task_struct(). - Make it static, it has no callers outside of ptrace.c. - The comment doesn't match the reality, this helper does not do any checks. Beacuse it is really trivial and static I removed the whole comment. Signed-off-by:
-
Oleg Nesterov authored
Remove the "Nasty, nasty" lock dance in ptrace_attach()/ptrace_traceme() - from now task_lock() has nothing to do with ptrace at all. With the recent changes nobody uses task_lock() to serialize with ptrace, but in fact it was never needed and it was never used consistently. However ptrace_attach() calls __ptrace_may_access() and needs task_lock() to pin task->mm for get_dumpable(). But we can call __ptrace_may_access() before we take tasklist_lock, ->cred_exec_mutex protects us against do_execve() path which can change creds and MMF_DUMP* flags. (ugly, but we can't use ptrace_may_access() because it hides the error code, so we have to take task_lock() and use __ptrace_may_access()). NOTE: this change assumes that LSM hooks, security_ptrace_may_access() and security_ptrace_traceme(), can be called without task_lock() held. Signed-off-by:
-
Oleg Nesterov authored
ptrace_attach() and ptrace_traceme() are the last functions which look as if the untraced task can have task->ptrace != 0, this must not be possible. Change the code to just check ->ptrace != 0 and s/|=/=/ to set PT_PTRACED. Also, a couple of trivial whitespace cleanups in ptrace_attach(). And move ptrace_traceme() up near ptrace_attach() to keep them close to each other. Signed-off-by:
-
Oleg Nesterov authored
- Add PF_KTHREAD check to prevent attaching to the kernel thread with a borrowed ->mm. With or without this change we can race with daemonize() which can set PF_KTHREAD or clear ->mm after ptrace_attach() does the check, but this doesn't matter because reparent_to_kthreadd() does ptrace_unlink(). - Kill "!task->mm" check. We don't really care about ->mm != NULL, and the task can call exit_mm() right after we drop task_lock(). What we need is to make sure we can't attach after exit_notify(), check task->exit_state != 0 instead. Also, move the "already traced" check down for cosmetic reasons. Signed-off-by:
-
Oleg Nesterov authored
No functional changes. - Nobody except ptrace.c & co should use ptrace flags directly, we have task_ptrace() for that. - No need to specially check PT_PTRACED, we must not have other PT_ bits set without PT_PTRACED. And no need to know this flag exists. Signed-off-by:
-
Oleg Nesterov authored
tracehook_unsafe_exec() doesn't need task_lock(), remove the old comment. Signed-off-by:
-
Oleg Nesterov authored
"Search in the siblings" should use ->real_parent, not ->parent. If the task is traced then ->parent == tracer, while the task's parent is always ->real_parent. Signed-off-by:
-
Oleg Nesterov authored
m32r: PTRACE_SINGLESTEP sets PT_DTRACE, it is never used except cleared after do_execve(). Signed-off-by:
Hirokazu Takata <takata@linux-m32r.org> Acked-by:
-
Oleg Nesterov authored
m68k sets PT_DTRACE in trap_c() but never uses it. Signed-off-by:
Geert Uytterhoeven <geert@linux-m68k.org> Acked-by:
Greg Ungerer <gerg@snapgear.com> Cc: Roman Zippel <zippel@linux-m68k.org> Acked-by:
-
Oleg Nesterov authored
avr32, mn10300, parisc, s390, sh, xtensa: They never set PT_DTRACE, but clear it after do_execve(). Signed-off-by:
Kyle McMartin <kyle@mcmartin.ca> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: Matthew Wilcox <matthew@wil.cx> Acked-by:
Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Acked-by:
Paul Mundt <lethal@linux-sh.org> Acked-by:
Chris Zankel <chris@zankel.net> Acked-by:
Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Signed-off-by:
-
Oleg Nesterov authored
h8300 defines PT_DTRACE for asm but never uses it. DEFINE(PT_PTRACED, PT_PTRACED) seems to be unused too. Signed-off-by:
Yoshinori Sato <ysato@users.sourceforge.jp> Acked-by:
-
Oleg Nesterov authored
allow_signal() checks ->mm == NULL. Not sure why. Perhaps to make sure current is the kernel thread. But this helper must not be used unless we are the kernel thread, kill this check. Also, document the fact that the CLONE_SIGHAND kthread must not use allow_signal(), unless the caller really wants to change the parent's ->sighand->action as well. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
Try to fix memcg's lru rotation sanity: make memcg use the same logic as the global LRU does. Now, at __isolate_lru_page() retruns -EBUSY, the page is rotated to the tail of LRU in global LRU's isolate LRU pages. But in memcg, it's not handled. This makes memcg do the same behavior as global LRU and rotate LRU in the page is busy. Signed-off-by:
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by:
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by:
-
Daisuke Nishimura authored
We don't have an interface to reset mem.limit or memsw.limit now. This patch allows to reset mem.limit or memsw.limit when they are being set to -1. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
A user can set memcg.limit_in_bytes == memcg.memsw.limit_in_bytes when the user just want to limit the total size of applications, in other words, not very interested in memory usage itself. In this case, swap-out will be done only by global-LRU. But, under current implementation, memory.limit_in_bytes is checked at first and try_to_free_page() may do swap-out. But, that swap-out is useless for memsw.limit_in_bytes and the thread may hit limit again. This patch tries to fix the current behavior at memory.limit == memsw.limit case. And documentation is updated to explain the behavior of this special case. Signed-off-by:
-
KAMEZAWA Hiroyuki authored
This patch fixes mis-accounting of swap usage in memcg. In the current implementation, memcg's swap account is uncharged only when swap is completely freed. But there are several cases where swap cannot be freed cleanly. For handling that, this patch changes that memcg uncharges swap account when swap has no references other than cache. By this, memcg's swap entry accounting can be fully synchronous with the application's behavior. This patch also changes memcg's hooks for swap-out. Signed-off-by:
Balbir Singh <balbir@in.ibm.com> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by:
-
Li Zefan authored
This forward declaration seems pointless. Signed-off-by:
Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by:
-
Li Zefan authored
We don't need to check do_swap_account in the case that the function which checks do_swap_account will never get called if do_swap_account == 0. Signed-off-by:
-
Daisuke Nishimura authored
mem_cgroup_cache_charge_swapin() isn't used any more, so remove no-op definition of it in header file. Signed-off-by:
-
Balbir Singh authored
Add file RSS tracking per memory cgroup We currently don't track file RSS, the RSS we report is actually anon RSS. All the file mapped pages, come in through the page cache and get accounted there. This patch adds support for accounting file RSS pages. It should 1. Help improve the metrics reported by the memory resource controller 2. Will form the basis for a future shared memory accounting heuristic that has been proposed by Kamezawa. Unfortunately, we cannot rename the existing "rss" keyword used in memory.stat to "anon_rss". We however, add "mapped_file" data and hope to educate the end user through documentation. [hugh.dickins@tiscali.co.uk: fix mem_cgroup_update_mapped_file_stat oops] Signed-off-by:
Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by:
Hugh Dickins <hugh.dickins@tiscali.co.uk> Signed-off-by:
-
Li Zefan authored
While walking through the whitelist, if the DEV_ALL item is found, no more check is needed. Signed-off-by:
Serge Hallyn <serue@us.ibm.com> Signed-off-by:
-
Li Zefan authored
The 'noprefix' option was introduced for backwards-compatibility of cpuset, but actually it can be used when mounting other subsystems. This results in possibility of name collision, and now the collision can really happen, because we have 'stat' file in both memory and cpuacct subsystem: # mount -t cgroup -o noprefix,memory,cpuacct xxx /mnt Cgroup will happily mount the 2 subsystems, but only 'stat' file of memory subsys can be seen. We don't want users to use nopreifx, and also want to avoid name collision, so we change to allow noprefix only if mounting just the cpuset subsystem. [akpm@linux-foundation.org: fix shift for cpuset_subsys_id >= 32] Signed-off-by:
Dhaval Giani <dhaval@linux.vnet.ibm.com> Signed-off-by:
-
Randy Dunlap authored
Fix some cgroup messages to read better. Update MAINTAINERS to include mm/*cgroup* files. Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Cc: Paul Menage <menage@google.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by:
-
Jaswinder Singh Rajput authored
Currently cn_test_want_notify() has no user. So add an ifdef and a comment which tells us to not remove it. Signed-off-by:
Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Acked-by:
Evgeniy Polyakov <zbr@ioremap.net> Signed-off-by:
-
Jose Luis Perez Diez authored
Perl is used on the kernel Makefile to generate documentation, firmwares in c source form, sources, graphs, and some headers and this fact is undocumented. [akpm@linux-foundation.org: 80-columns, please] Signed-off-by:
Jose Luis Perez Diez <jluis@escomposlinux.org> Cc: Sam Ravnborg <sam@ravnborg.org> Signed-off-by:
-
Jeff Mahoney authored
Several code paths in reiserfs have a construct like: if (is_direntry_le_ih(ih = B_N_PITEM_HEAD(src, item_num))) ... which, in addition to being ugly, end up causing compiler warnings with gcc 4.4.0. Previous compilers didn't issue a warning. fs/reiserfs/do_balan.c:1273: warning: operation on `aux_ih' may be undefined fs/reiserfs/lbalance.c:393: warning: operation on `ih' may be undefined fs/reiserfs/lbalance.c:421: warning: operation on `ih' may be undefined fs/reiserfs/lbalance.c:777: warning: operation on `ih' may be undefined I believe this is due to the ih being passed to macros which evaluate the argument more than once. This is old code and we haven't seen any problems with it, but this patch eliminates the warnings. It converts the multiple evaluation macros to static inlines and does a preassignment for the cases that were causing the warnings because that code is just ugly. Reported-by:
Chris Mason <mason@oracle.com> Signed-off-by:
Jeff Mahoney <jeffm@suse.com> Signed-off-by:
-
