- 19 Oct, 2007 40 commits
-
-
Paul Jackson authored
Add a new per-cpuset flag called 'sched_load_balance'. When enabled in a cpuset (the default value) it tells the kernel scheduler that the scheduler should provide the normal load balancing on the CPUs in that cpuset, sometimes moving tasks from one CPU to a second CPU if the second CPU is less loaded and if that task is allowed to run there. When disabled (write "0" to the file) then it tells the kernel scheduler that load balancing is not required for the CPUs in that cpuset. Now even if this flag is disabled for some cpuset, the kernel may still have to load balance some or all the CPUs in that cpuset, if some overlapping cpuset has its sched_load_balance flag enabled. If there are some CPUs that are not in any cpuset whose sched_load_balance flag is enabled, the kernel scheduler will not load balance tasks to those CPUs. Moreover the kernel will partition the 'sched domains' (non-overlapping sets of CPUs over which load balancing is attempted) into the finest granularity partition that it can find, while still keeping any two CPUs that are in the same shed_load_balance enabled cpuset in the same element of the partition. This serves two purposes: 1) It provides a mechanism for real time isolation of some CPUs, and 2) it can be used to improve performance on systems with many CPUs by supporting configurations in which load balancing is not done across all CPUs at once, but rather only done in several smaller disjoint sets of CPUs. This mechanism replaces the earlier overloading of the per-cpuset flag 'cpu_exclusive', which overloading was removed in an earlier patch: cpuset-remove-sched-domain-hooks-from-cpusets See further the Documentation and comments in the code itself. [akpm@linux-foundation.org: don't be weird] Signed-off-by:Paul Jackson <pj@sgi.com> Acked-by:
Ingo Molnar <mingo@elte.hu> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Pavel Emelyanov authored
Since these are expanded into call to pid_nr_ns() anyway, it's OK to move the whole routine out-of-line. This is a cheap way to save ~100 bytes from vmlinux. Together with the previous two patches, it saves half-a-kilo from the vmlinux. Un-inline other (currently inlined) functions must be done with additional performance testing. Signed-off-by:
Pavel Emelyanov <xemul@openvz.org> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Paul Menage <menage@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by:
-
Pavel Emelyanov authored
The find_pid/_vpid/_pid_ns functions are used to find the struct pid by its id, depending on whic id - global or virtual - is used. The find_vpid() is a macro that pushes the current->nsproxy->pid_ns on the stack to call another function - find_pid_ns(). It turned out, that this dereference together with the push itself cause the kernel text size to grow too much. Move all these out-of-line. Together with the previous patch this saves a bit less that 400 bytes from .text section. Signed-off-by:
-
Pavel Emelyanov authored
With pid namespaces this field is now dangerous to use explicitly, so hide it behind the helpers. Also the pid and pgrp fields o task_struct and signal_struct are to be deprecated. Unfortunately this patch cannot be sent right now as this leads to tons of warnings, so start isolating them, and deprecate later. Actually the p->tgid == pid has to be changed to has_group_leader_pid(), but Oleg pointed out that in case of posix cpu timers this is the same, and thread_group_leader() is more preferable. Signed-off-by:
Oleg Nesterov <oleg@tv-sign.ru> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by:
-
Pavel Emelyanov authored
Since we've switched from using pid->nr to pid->upids->nr some fields on struct pid are no longer needed Signed-off-by:
-
Pavel Emelyanov authored
The find_task_by_something is a set of macros are used to find task by pid depending on what kind of pid is proposed - global or virtual one. All of them are wrappers above the most generic one - find_task_by_pid_type_ns() - and just substitute some args for it. It turned out, that dereferencing the current->nsproxy->pid_ns construction and pushing one more argument on the stack inline cause kernel text size to grow. This patch moves all this stuff out-of-line into kernel/pid.c. Together with the next patch it saves a bit less than 400 bytes from the .text section. Signed-off-by:
-
Pavel Emelyanov authored
This is the largest patch in the set. Make all (I hope) the places where the pid is shown to or get from user operate on the virtual pids. The idea is: - all in-kernel data structures must store either struct pid itself or the pid's global nr, obtained with pid_nr() call; - when seeking the task from kernel code with the stored id one should use find_task_by_pid() call that works with global pids; - when showing pid's numerical value to the user the virtual one should be used, but however when one shows task's pid outside this task's namespace the global one is to be used; - when getting the pid from userspace one need to consider this as the virtual one and use appropriate task/pid-searching functions. [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: nuther build fix] [akpm@linux-foundation.org: yet nuther build fix] [akpm@linux-foundation.org: remove unneeded casts] Signed-off-by:
Alexey Dobriyan <adobriyan@openvz.org> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Paul Menage <menage@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by:
-
Sukadev Bhattiprolu authored
Terminate all processes in a namespace when the reaper of the namespace is exiting. We do this by walking the pidmap of the namespace and sending SIGKILL to all processes. Signed-off-by:
Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by:
-
Sukadev Bhattiprolu authored
Only the global-init process must be special - any other cgroup-init process must be killable to prevent run-away processes in the system. TODO: Ideally we should allow killing the cgroup-init only from parent cgroup and prevent it being killed from within the cgroup. But that is a more complex change and will be addressed by a follow-on patch. For now allow the cgroup-init to be terminated by any process with sufficient privileges. Signed-off-by:
-
Sukadev Bhattiprolu authored
This will help fixing memory leaks due to bad reference counting. Signed-off-by:
-
Pavel Emelyanov authored
The namespace's proc_mnt must be kern_mount-ed to make this pointer always valid, independently of whether the user space mounted the proc or not. This solves raced in proc_flush_task, etc. with the proc_mnt switching from NULL to not-NULL. The initialization is done after the init's pid is created and hashed to make proc_get_sb() finr it and get for root inode. Sice the namespace holds the vfsmnt, vfsmnt holds the superblock and the superblock holds the namespace we must explicitly break this circle to destroy all the stuff. This is done after the init of the namespace dies. Running a few steps forward - when init exits it will kill all its children, so no proc_mnt will be needed after its death. Signed-off-by:
-
Pavel Emelyanov authored
This means that proc_flush_task_mnt() is to be called for many proc mounts and with different ids, depending on the namespace this pid is to be flushed from. Signed-off-by:
-
Pavel Emelyanov authored
When clone() is invoked with CLONE_NEWPID, create a new pid namespace and then create a new struct pid for the new process. Allocate pid_t's for the new process in the new pid namespace and all ancestor pid namespaces. Make the newly cloned process the session and process group leader. Since the active pid namespace is special and expected to be the first entry in pid->upid_list, preserve the order of pid namespaces. The size of 'struct pid' is dependent on the the number of pid namespaces the process exists in, so we use multiple pid-caches'. Only one pid cache is created during system startup and this used by processes that exist only in init_pid_ns. When a process clones its pid namespace, we create additional pid caches as necessary and use the pid cache to allocate 'struct pids' for that depth. Note, that with this patch the newly created namespace won't work, since the rest of the kernel still uses global pids, but this is to be fixed soon. Init pid namespace still works. [oleg@tv-sign.ru: merge fix] Signed-off-by:
-
Pavel Emelyanov authored
* remove pid.h from pid_namespaces.h; * rework is_(cgroup|global)_init; * optimize (get|put)_pid_ns for init_pid_ns; * declare task_child_reaper to return actual reaper. Signed-off-by:
-
Pavel Emelyanov authored
Each pid namespace have to be visible through its own proc mount. Thus we need to have per-namespace proc trees with their own superblocks. We cannot easily show different pid namespace via one global proc tree, since each pid refers to different tasks in different namespaces. E.g. pid 1 refers to the init task in the initial namespace and to some other task when seeing from another namespace. Moreover - pid, exisintg in one namespace may not exist in the other. This approach has one move advantage is that the tasks from the init namespace can see what tasks live in another namespace by reading entries from another proc tree. Signed-off-by:
-
Pavel Emelyanov authored
When we create new namespace we will need to allocate the struct pid, that will have one extra struct upid in array, comparing to the parent. Thus we need to know the new namespace (if any) in alloc_pid() to init this struct upid properly, so move the alloc_pid() call lower in copy_process(). Signed-off-by:
-
Pavel Emelyanov authored
When searching the task by numerical id on may need to find it using global pid (as it is done now in kernel) or by its virtual id, e.g. when sending a signal to a task from one namespace the sender will specify the task's virtual id and we should find the task by this value. [akpm@linux-foundation.org: fix gfs2 linkage] Signed-off-by:
-
Pavel Emelyanov authored
When showing pid to user or getting the pid numerical id for in-kernel use the value of this id may differ depending on the namespace. This set of helpers is used to get the global pid nr, the virtual (i.e. seen by task in its namespace) nr and the nr as it is seen from the specified namespace. Signed-off-by:
-
Pavel Emelyanov authored
Each struct upid element of struct pid has to be initialized properly, i.e. its nr mst be allocated from appropriate pidmap and ns set to appropriate namespace. When allocating a new pid, we need to know the namespace this pid will live in, so the additional argument is added to alloc_pid(). On the other hand, the rest of the kernel still uses the pid->nr and pid->pid_chain fields, so these ones are still initialized, but this will be removed soon. Signed-off-by:
-
Pavel Emelyanov authored
Each namespace has a parent and is characterized by its "level". Level is the number of the namespace generation. E.g. init namespace has level 0, after cloning new one it will have level 1, the next one - 2 and so on and so forth. This level is not explicitly limited. True hierarchy must have some way to find each namespace's children, but it is not used in the patches, so this ability is not added (yet). Signed-off-by:
-
Sukadev Bhattiprolu authored
Since task will be visible from different pid namespaces each of them have to be addressed by multiple pids. struct upid is to store the information about which id refers to which namespace. The constuciton looks like this. Each struct pid carried the reference counter and the list of tasks attached to this pid. At its end it has a variable length array of struct upid-s. Each struct upid has a numerical id (pid itself), pointer to the namespace, this ID is valid in and is hashed into a pid_hash for searching the pids. The nr and pid_chain fields are kept in struct pid for a while to make kernel still work (no patch initialize the upids yet), but it will be removed at the end of this series when we switch to upids completely. Signed-off-by:
-
Pavel Emelyanov authored
The first part is trivial - we just make the proc_flush_task() to operate on arbitrary vfsmount with arbitrary ids and pass the pid and global proc_mnt to it. The other change is more tricky: I moved the proc_flush_task() call in release_task() higher to address the following problem. When flushing task from many proc trees we need to know the set of ids (not just one pid) to find the dentries' names to flush. Thus we need to pass the task's pid to proc_flush_task() as struct pid is the only object that can provide all the pid numbers. But after __exit_signal() task has detached all his pids and this information is lost. This creates a tiny gap for proc_pid_lookup() to bring some dentries back to tree and keep them in hash (since pids are still alive before __exit_signal()) till the next shrink, but since proc_flush_task() does not provide a 100% guarantee that the dentries will be flushed, this is OK to do so. Signed-off-by:
-
Pavel Emelyanov authored
This flag tells the .get_sb callback that this is a kern_mount() call so that it can trust *data pointer to be valid in-kernel one. If this flag is passed from the user process, it is cleared since the *data pointer is not a valid kernel object. Running a few steps forward - this will be needed for proc to create the superblock and store a valid pid namespace on it during the namespace creation. The reason, why the namespace cannot live without proc mount is described in the appropriate patch. Signed-off-by:
-
Pavel Emelyanov authored
Make task release its namespaces after it has reparented all his children to child_reaper, but before it notifies its parent about its death. The reason to release namespaces after reparenting is that when task exits it may send a signal to its parent (SIGCHLD), but if the parent has already exited its namespaces there will be no way to decide what pid to dever to him - parent can be from different namespace. The reason to release namespace before notifying the parent it that when task sends a SIGCHLD to parent it can call wait() on this taks and release it. But releasing the mnt namespace implies dropping of all the mounts in the mnt namespace and NFS expects the task to have valid sighand pointer. Thanks to Oleg for pointing out some races that can apear and helping with patches and fixes. Signed-off-by:
-
Oleg Nesterov authored
A pid namespace is a "view" of a particular set of tasks on the system. They work in a similar way to filesystem namespaces. A file (or a process) can be accessed in multiple namespaces, but it may have a different name in each. In a filesystem, this name might be /etc/passwd in one namespace, but /chroot/etc/passwd in another. For processes, a process may have pid 1234 in one namespace, but be pid 1 in another. This allows new pid namespaces to have basically arbitrary pids, and not have to worry about what pids exist in other namespaces. This is essential for checkpoint/restart where a restarted process's pid might collide with an existing process on the system's pid. In this particular implementation, pid namespaces have a parent-child relationship, just like processes. A process in a pid namespace may see all of the processes in the same namespace, as well as all of the processes in all of the namespaces which are children of its namespace. Processes may not, however, see others which are in their parent's namespace, but not in their own. The same goes for sibling namespaces. The know issue to be solved in the nearest future is signal handling in the namespace boundary. That is, currently the namespace's init is treated like an ordinary task that can be killed from within an namespace. Ideally, the signal handling by the namespace's init should have two sides: when signaling the init from its namespace, the init should look like a real init task, i.e. receive only those signals, that is explicitly wants to; when signaling the init from one of the parent namespaces, init should look like an ordinary task, i.e. receive any signal, only taking the general permissions into account. The pid namespace was developed by Pavel Emlyanov and Sukadev Bhattiprolu and we eventually came to almost the same implementation, which differed in some details. This set is based on Pavel's patches, but it includes comments and patches that from Sukadev. Many thanks to Oleg, who reviewed the patches, pointed out many BUGs and made valuable advises on how to make this set cleaner. This patch: We have to call exit_task_namespaces() only after the exiting task has reparented all his children and is sure that no other threads will reparent theirs for it. Why this is needed is explained in appropriate patch. This one only reworks the forget_original_parent() so that after calling this a task cannot be/become parent of any other task. We check PF_EXITING instead of ->exit_state while choosing the new parent. Note that tasklits_lock acts as a barrier, everyone who takes tasklist after us (when forget_original_parent() drops it) must see PF_EXITING. The other changes are just cleanups. They just move some code from exit_notify to forget_original_parent(). It is a bit silly to declare ptrace_dead in exit_notify(), take tasklist, pass ptrace_dead to forget_original_parent(), unlock-lock-unlock tasklist, and then use ptrace_dead. Signed-off-by:
-
Daniel Walker authored
Signed-off-by:
Daniel Walker <dwalker@mvista.com> Signed-off-by:
-
Matthias Kaehlcke authored
mm/oom_kill.c: Convert list_for_each to list_for_each_entry in oom_kill_process() Signed-off-by:
Matthias Kaehlcke <matthias.kaehlcke@gmail.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by:
-
Matthias Kaehlcke authored
kernel/time/clocksource.c: Convert list_for_each to list_for_each_entry in clocksource_resume(), sysfs_override_clocksource() and show_available_clocksources() Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by:
-
Matthias Kaehlcke authored
kernel/exit.c: Convert list_for_each(_safe) to list_for_each_entry(_safe) in forget_original_parent(), exit_notify() and do_wait() Signed-off-by:
-
Matthias Kaehlcke authored
fs/super.c: use list_for_each_entry() instead of list_for_each() in sget() [akpm@linux-foundation.org: clean up some crap while we're there] Signed-off-by:
-
Matthias Kaehlcke authored
fs/eventpoll.c: use list_for_each_entry() instead of list_for_each() in ep_poll_safewake() Signed-off-by:
-
Matthias Kaehlcke authored
fs/file_table.c: use list_for_each_entry() instead of list_for_each() in fs_may_remount_ro() Signed-off-by:
-
Johannes Berg authored
In the following scenario: code path 1: my_function() -> lock(L1); ...; flush_workqueue(); ... code path 2: run_workqueue() -> my_work() -> ...; lock(L1); ... you can get a deadlock when my_work() is queued or running but my_function() has acquired L1 already. This patch adds a pseudo-lock to each workqueue to make lockdep warn about this scenario. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
Johannes Berg <johannes@sipsolutions.net> Acked-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by:
-
Pavel Emelyanov authored
When someone wants to deal with some other taks's namespaces it has to lock the task and then to get the desired namespace if the one exists. This is slow on read-only paths and may be impossible in some cases. E.g. Oleg recently noticed a race between unshare() and the (sent for review in cgroups) pid namespaces - when the task notifies the parent it has to know the parent's namespace, but taking the task_lock() is impossible there - the code is under write locked tasklist lock. On the other hand switching the namespace on task (daemonize) and releasing the namespace (after the last task exit) is rather rare operation and we can sacrifice its speed to solve the issues above. The access to other task namespaces is proposed to be performed like this: rcu_read_lock(); nsproxy = task_nsproxy(tsk); if (nsproxy != NULL) { / * * work with the namespaces here * e.g. get the reference on one of them * / } / * * NULL task_nsproxy() means that this task is * almost dead (zombie) * / rcu_read_unlock(); This patch has passed the review by Eric and Oleg :) and, of course, tested. [clg@fr.ibm.com: fix unshare()] [ebiederm@xmission.com: Update get_net_ns_by_pid] Signed-off-by:Eric W. Biederman <ebiederm@xmission.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Serge Hallyn <serue@us.ibm.com> Signed-off-by:
Cedric Le Goater <clg@fr.ibm.com> Signed-off-by:
-
Sukadev Bhattiprolu authored
Move alloc_pid() into copy_process(). This will keep all pid and pid namespace code together and simplify error handling when we support multiple pid namespaces. Signed-off-by:
-
Serge E. Hallyn authored
is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by:Serge E. Hallyn <serue@us.ibm.com> Signed-off-by:
-
Sukadev Bhattiprolu authored
Use task_pid() to get leader's 'struct pid' and avoid the find_pid(). Signed-off-by:
-
Sukadev Bhattiprolu authored
Rename the child_reaper() function to task_child_reaper() to be similar to other task_* functions and to distinguish the function from 'struct pid_namspace.child_reaper'. Signed-off-by:
-
Sukadev Bhattiprolu authored
With multiple pid namespaces, a process is known by some pid_t in every ancestor pid namespace. Every time the process forks, the child process also gets a pid_t in every ancestor pid namespace. While a process is visible in >=1 pid namespaces, it can see pid_t's in only one pid namespace. We call this pid namespace it's "active pid namespace", and it is always the youngest pid namespace in which the process is known. This patch defines and uses a wrapper to find the active pid namespace of a process. The implementation of the wrapper will be changed in when support for multiple pid namespaces are added. Changelog: 2.6.22-rc4-mm2-pidns1: - [Pavel Emelianov, Alexey Dobriyan] Back out the change to use task_active_pid_ns() in child_reaper() since task->nsproxy can be NULL during task exit (so child_reaper() continues to use init_pid_ns). to implement child_reaper() since init_pid_ns.child_reaper to implement child_reaper() since tsk->nsproxy can be NULL during exit. 2.6.21-rc6-mm1: - Rename task_pid_ns() to task_active_pid_ns() to reflect that a process can have multiple pid namespaces. Signed-off-by:
-
Pavel Emelianov authored
Add kmem_cache to pid_namespace to allocate pids from. Since both implementations expand the struct pid to carry more numerical values each namespace should have separate cache to store pids of different sizes. Each kmem cache is name "pid_<NR>", where <NR> is the number of numerical ids on the pid. Different namespaces with same level of nesting will have same caches. This patch has two FIXMEs that are to be fixed after we reach the consensus about the struct pid itself. The first one is that the namespace to free the pid from in free_pid() must be taken from pid. Now the init_pid_ns is used. The second FIXME is about the cache allocation. When we do know how long the object will be then we'll have to calculate this size in create_pid_cachep. Right now the sizeof(struct pid) value is used. [akpm@linux-foundation.org: coding-style repair] Signed-off-by:
-
