From 967fc04671feea4dbf780c9e55a0bc8fcf68a14e Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Mon, 29 Dec 2008 09:39:52 -0500 Subject: sched: add sched_class->needs_post_schedule() member We currently run class->post_schedule() outside of the rq->lock, which means that we need to test for the need to post_schedule outside of the lock to avoid a forced reacquistion. This is currently not a problem as we only look at rq->rt.overloaded. However, we want to enhance this going forward to look at more state to reduce the need to post_schedule to a bare minimum set. Therefore, we introduce a new member-func called needs_post_schedule() which tests for the post_schedule condtion without actually performing the work. Therefore it is safe to call this function before the rq->lock is released, because we are guaranteed not to drop the lock at an intermediate point (such as what post_schedule() may do). We will use this later in the series [ rostedt: removed paranoid BUG_ON ] Signed-off-by: Gregory Haskins --- 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 e5f928a079e8..836a86c32a65 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1012,6 +1012,7 @@ struct sched_class { struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); + int (*needs_post_schedule) (struct rq *this_rq); void (*post_schedule) (struct rq *this_rq); void (*task_wake_up) (struct rq *this_rq, struct task_struct *task); -- cgit v1.2.2 From 917b627d4d981dc614519d7b34ea31a976b14e12 Mon Sep 17 00:00:00 2001 From: Gregory Haskins Date: Mon, 29 Dec 2008 09:39:53 -0500 Subject: sched: create "pushable_tasks" list to limit pushing to one attempt The RT scheduler employs a "push/pull" design to actively balance tasks within the system (on a per disjoint cpuset basis). When a task is awoken, it is immediately determined if there are any lower priority cpus which should be preempted. This is opposed to the way normal SCHED_OTHER tasks behave, which will wait for a periodic rebalancing operation to occur before spreading out load. When a particular RQ has more than 1 active RT task, it is said to be in an "overloaded" state. Once this occurs, the system enters the active balancing mode, where it will try to push the task away, or persuade a different cpu to pull it over. The system will stay in this state until the system falls back below the <= 1 queued RT task per RQ. However, the current implementation suffers from a limitation in the push logic. Once overloaded, all tasks (other than current) on the RQ are analyzed on every push operation, even if it was previously unpushable (due to affinity, etc). Whats more, the operation stops at the first task that is unpushable and will not look at items lower in the queue. This causes two problems: 1) We can have the same tasks analyzed over and over again during each push, which extends out the fast path in the scheduler for no gain. Consider a RQ that has dozens of tasks that are bound to a core. Each one of those tasks will be encountered and skipped for each push operation while they are queued. 2) There may be lower-priority tasks under the unpushable task that could have been successfully pushed, but will never be considered until either the unpushable task is cleared, or a pull operation succeeds. The net result is a potential latency source for mid priority tasks. This patch aims to rectify these two conditions by introducing a new priority sorted list: "pushable_tasks". A task is added to the list each time a task is activated or preempted. It is removed from the list any time it is deactivated, made current, or fails to push. This works because a task only needs to be attempted to push once. After an initial failure to push, the other cpus will eventually try to pull the task when the conditions are proper. This also solves the problem that we don't completely analyze all tasks due to encountering an unpushable tasks. Now every task will have a push attempted (when appropriate). This reduces latency both by shorting the critical section of the rq->lock for certain workloads, and by making sure the algorithm considers all eligible tasks in the system. [ rostedt: added a couple more BUG_ONs ] Signed-off-by: Gregory Haskins Acked-by: Steven Rostedt --- 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 836a86c32a65..440cabb2d432 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1179,6 +1179,7 @@ struct task_struct { #endif struct list_head tasks; + struct plist_node pushable_tasks; struct mm_struct *mm, *active_mm; -- cgit v1.2.2 From 41719b03091911028116155deddc5eedf8c45e37 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 14 Jan 2009 15:36:26 +0100 Subject: mutex: preemption fixes The problem is that dropping the spinlock right before schedule is a voluntary preemption point and can cause a schedule, right after which we schedule again. Fix this inefficiency by keeping preemption disabled until we schedule, do this by explicity disabling preemption and providing a schedule() variant that assumes preemption is already disabled. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- 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 4cae9b81a1f8..9f0b372cfa6f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -328,6 +328,7 @@ extern signed long schedule_timeout(signed long timeout); extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); +asmlinkage void __schedule(void); asmlinkage void schedule(void); struct nsproxy; -- cgit v1.2.2 From 0d66bf6d3514b35eb6897629059443132992dbd7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 12 Jan 2009 14:01:47 +0100 Subject: mutex: implement adaptive spinning Change mutex contention behaviour such that it will sometimes busy wait on acquisition - moving its behaviour closer to that of spinlocks. This concept got ported to mainline from the -rt tree, where it was originally implemented for rtmutexes by Steven Rostedt, based on work by Gregory Haskins. Testing with Ingo's test-mutex application (http://lkml.org/lkml/2006/1/8/50) gave a 345% boost for VFS scalability on my testbox: # ./test-mutex-shm V 16 10 | grep "^avg ops" avg ops/sec: 296604 # ./test-mutex-shm V 16 10 | grep "^avg ops" avg ops/sec: 85870 The key criteria for the busy wait is that the lock owner has to be running on a (different) cpu. The idea is that as long as the owner is running, there is a fair chance it'll release the lock soon, and thus we'll be better off spinning instead of blocking/scheduling. Since regular mutexes (as opposed to rtmutexes) do not atomically track the owner, we add the owner in a non-atomic fashion and deal with the races in the slowpath. Furthermore, to ease the testing of the performance impact of this new code, there is means to disable this behaviour runtime (without having to reboot the system), when scheduler debugging is enabled (CONFIG_SCHED_DEBUG=y), by issuing the following command: # echo NO_OWNER_SPIN > /debug/sched_features This command re-enables spinning again (this is also the default): # echo OWNER_SPIN > /debug/sched_features Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- 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 9f0b372cfa6f..c34b137cd1e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -330,6 +330,7 @@ extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void __schedule(void); asmlinkage void schedule(void); +extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner); struct nsproxy; struct user_namespace; -- cgit v1.2.2 From 831451ac4e44d3a20b581ce726ef1d1144373f7d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 14 Jan 2009 12:39:18 +0100 Subject: sched: introduce avg_wakeup Introduce a new avg_wakeup statistic. avg_wakeup is a measure of how frequently a task wakes up other tasks, it represents the average time between wakeups, with a limit of avg_runtime for when it doesn't wake up anybody. Signed-off-by: Peter Zijlstra Signed-off-by: Mike Galbraith Signed-off-by: Ingo Molnar --- 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 4cae9b81a1f8..daf4e07bc978 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1046,6 +1046,9 @@ struct sched_entity { u64 exec_max; u64 slice_max; + u64 start_runtime; + u64 avg_wakeup; + u64 nr_migrations; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; -- cgit v1.2.2 From 34cb61359b503d7aff6447acb037a5efd6ce93b2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 16 Jan 2009 13:36:06 +0100 Subject: sched: fix !CONFIG_SCHEDSTATS build failure Stephen Rothwell reported this linux-next build failure with !CONFIG_SCHEDSTATS: | In file included from kernel/sched.c:1703: | kernel/sched_fair.c: In function 'adaptive_gran': | kernel/sched_fair.c:1324: error: 'struct sched_entity' has no member named 'avg_wakeup' The start_runtime and avg_wakeup metrics are now not just for statistics, but also for scheduling - so they always need to be available. (Also move out the nr_migrations fields - for future perfcounters usage.) Reported-by: Stephen Rothwell Signed-off-by: Ingo Molnar --- include/linux/sched.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index daf4e07bc978..5d56b54350a5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1031,6 +1031,10 @@ struct sched_entity { u64 last_wakeup; u64 avg_overlap; + u64 start_runtime; + u64 avg_wakeup; + u64 nr_migrations; + #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; @@ -1046,10 +1050,6 @@ struct sched_entity { u64 exec_max; u64 slice_max; - u64 start_runtime; - u64 avg_wakeup; - - u64 nr_migrations; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; -- cgit v1.2.2 From 7e49fcce1bdadd723ae6a0b3b324c4daced61563 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 22 Jan 2009 19:01:40 -0500 Subject: trace, lockdep: manual preempt count adding for local_bh_disable Impact: fix to preempt trace triggering lockdep check_flag failure In local_bh_disable, the use of add_preempt_count causes the preempt tracer to start recording the time preemption is off. But because it already modified the preempt_count to show softirqs disabled, and before it called the lockdep code to handle this, it causes a state that lockdep can not handle. The preempt tracer will reset the ring buffer on start of a trace, and the ring buffer reset code does a spin_lock_irqsave. This calls into lockdep and lockdep will fail when it detects the invalid state of having softirqs disabled but the internal current->softirqs_enabled is still set. The fix is to manually add the SOFTIRQ_OFFSET to preempt count and call the preempt tracer code outside the lockdep critical area. Thanks to Peter Zijlstra for suggesting this solution. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4cae9b81a1f8..33085b88f87b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -137,6 +137,8 @@ extern unsigned long nr_uninterruptible(void); extern unsigned long nr_active(void); extern unsigned long nr_iowait(void); +extern unsigned long get_parent_ip(unsigned long addr); + struct seq_file; struct cfs_rq; struct task_group; -- cgit v1.2.2 From f9ce1f1cda8b73a36f47e424975a9dfa78b7840c Mon Sep 17 00:00:00 2001 From: Kentaro Takeda Date: Thu, 5 Feb 2009 17:18:11 +0900 Subject: Add in_execve flag into task_struct. This patch allows LSM modules to determine whether current process is in an execve operation or not so that they can behave differently while an execve operation is in progress. This patch is needed by TOMOYO. Please see another patch titled "LSM adapter functions." for backgrounds. Signed-off-by: Tetsuo Handa Signed-off-by: David Howells Signed-off-by: James Morris --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2127e959e0f4..397c20cfb6a5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1158,6 +1158,8 @@ struct task_struct { /* ??? */ unsigned int personality; unsigned did_exec:1; + unsigned in_execve:1; /* Tell the LSMs that the process is doing an + * execve */ pid_t pid; pid_t tgid; -- cgit v1.2.2 From cf40bd16fdad42c053040bcd3988f5fdedbb6c57 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 21 Jan 2009 08:12:39 +0100 Subject: lockdep: annotate reclaim context (__GFP_NOFS) Here is another version, with the incremental patch rolled up, and added reclaim context annotation to kswapd, and allocation tracing to slab allocators (which may only ever reach the page allocator in rare cases, so it is good to put annotations here too). Haven't tested this version as such, but it should be getting closer to merge worthy ;) -- After noticing some code in mm/filemap.c accidentally perform a __GFP_FS allocation when it should not have been, I thought it might be a good idea to try to catch this kind of thing with lockdep. I coded up a little idea that seems to work. Unfortunately the system has to actually be in __GFP_FS page reclaim, then take the lock, before it will mark it. But at least that might still be some orders of magnitude more common (and more debuggable) than an actual deadlock condition, so we have some improvement I hope (the concept is no less complete than discovery of a lock's interrupt contexts). I guess we could even do the same thing with __GFP_IO (normal reclaim), and even GFP_NOIO locks too... but filesystems will have the most locks and fiddly code paths, so let's start there and see how it goes. It *seems* to work. I did a quick test. ================================= [ INFO: inconsistent lock state ] 2.6.28-rc6-00007-ged31348-dirty #26 --------------------------------- inconsistent {in-reclaim-W} -> {ov-reclaim-W} usage. modprobe/8526 [HC0[0]:SC0[0]:HE1:SE1] takes: (testlock){--..}, at: [] brd_init+0x55/0x216 [brd] {in-reclaim-W} state was registered at: [] __lock_acquire+0x75b/0x1a60 [] lock_acquire+0x91/0xc0 [] mutex_lock_nested+0xb1/0x310 [] brd_init+0x2b/0x216 [brd] [] _stext+0x3b/0x170 [] sys_init_module+0xaf/0x1e0 [] system_call_fastpath+0x16/0x1b [] 0xffffffffffffffff irq event stamp: 3929 hardirqs last enabled at (3929): [] mutex_lock_nested+0x285/0x310 hardirqs last disabled at (3928): [] mutex_lock_nested+0x59/0x310 softirqs last enabled at (3732): [] sk_filter+0x83/0xe0 softirqs last disabled at (3730): [] sk_filter+0x16/0xe0 other info that might help us debug this: 1 lock held by modprobe/8526: #0: (testlock){--..}, at: [] brd_init+0x55/0x216 [brd] stack backtrace: Pid: 8526, comm: modprobe Not tainted 2.6.28-rc6-00007-ged31348-dirty #26 Call Trace: [] print_usage_bug+0x193/0x1d0 [] mark_lock+0xaf0/0xca0 [] mark_held_locks+0x55/0xc0 [] ? brd_init+0x0/0x216 [brd] [] trace_reclaim_fs+0x2a/0x60 [] __alloc_pages_internal+0x475/0x580 [] ? mutex_lock_nested+0x26e/0x310 [] ? brd_init+0x0/0x216 [brd] [] brd_init+0x6a/0x216 [brd] [] ? brd_init+0x0/0x216 [brd] [] _stext+0x3b/0x170 [] ? mutex_unlock+0x9/0x10 [] ? __mutex_unlock_slowpath+0x10d/0x180 [] ? trace_hardirqs_on_caller+0x12c/0x190 [] sys_init_module+0xaf/0x1e0 [] system_call_fastpath+0x16/0x1b Signed-off-by: Nick Piggin Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- 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 4efb552aca47..b00a77f4999e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1313,6 +1313,7 @@ struct task_struct { int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; + gfp_t lockdep_reclaim_gfp; #endif /* journalling filesystem info */ -- cgit v1.2.2 From b342501cd31e5546d0c9ca8ceff5ded1832f9e5b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 26 Feb 2009 20:20:29 +0100 Subject: sched: allow architectures to specify sched_clock_stable Allow CONFIG_HAVE_UNSTABLE_SCHED_CLOCK architectures to still specify that their sched_clock() implementation is reliable. This will be used by x86 to switch on a faster sched_clock_cpu() implementation on certain CPU types. Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8981e52c714f..a063d19b7a7d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1670,6 +1670,16 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) return set_cpus_allowed_ptr(p, &new_mask); } +/* + * Architectures can set this to 1 if they have specified + * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig, + * but then during bootup it turns out that sched_clock() + * is reliable after all: + */ +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +extern int sched_clock_stable; +#endif + extern unsigned long long sched_clock(void); extern void sched_clock_init(void); -- cgit v1.2.2 From 76e6eee03353f01bfca707d4dbb1f10a4ee27dc0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 12 Mar 2009 14:35:43 -0600 Subject: cpumask: tsk_cpumask for accessing the struct task_struct's cpus_allowed. This allows us to change the representation (to a dangling bitmap or cpumask_var_t) without breaking all the callers: they can use tsk_cpumask() now and won't see a difference as the changes roll into linux-next. Signed-off-by: Rusty Russell --- 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 8c216e057c94..011db2f4c94c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1419,6 +1419,9 @@ struct task_struct { #endif }; +/* Future-safe accessor for struct task_struct's cpus_allowed. */ +#define tsk_cpumask(tsk) (&(tsk)->cpus_allowed) + /* * Priority of a process goes from 0..MAX_PRIO-1, valid RT * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH -- cgit v1.2.2 From 8aef2d2856158a36c295a8d1288281e4839bff13 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 24 Mar 2009 01:10:15 -0400 Subject: function-graph: ignore times across schedule Impact: more accurate timings The current method of function graph tracing does not take into account the time spent when a task is not running. This shows functions that call schedule have increased costs: 3) + 18.664 us | } ------------------------------------------ 3) -0 => kblockd-123 ------------------------------------------ 3) | finish_task_switch() { 3) 1.441 us | _spin_unlock_irq(); 3) 3.966 us | } 3) ! 2959.433 us | } 3) ! 2961.465 us | } This patch uses the tracepoint in the scheduling context switch to account for time that has elapsed while a task is scheduled out. Now we see: ------------------------------------------ 3) -0 => edac-po-1067 ------------------------------------------ 3) | finish_task_switch() { 3) 0.685 us | _spin_unlock_irq(); 3) 2.331 us | } 3) + 41.439 us | } 3) + 42.663 us | } Signed-off-by: Steven Rostedt --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 89cd308cc7a5..471e36d30123 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1409,6 +1409,8 @@ struct task_struct { int curr_ret_stack; /* Stack of return addresses for return function tracing */ struct ftrace_ret_stack *ret_stack; + /* time stamp for last schedule */ + unsigned long long ftrace_timestamp; /* * Number of functions that haven't been traced * because of depth overrun. -- cgit v1.2.2 From 5ad4e53bd5406ee214ddc5a41f03f779b8b2d526 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:50:06 -0400 Subject: Get rid of indirect include of fs_struct.h Don't pull it in sched.h; very few files actually need it and those can include directly. sched.h itself only needs forward declaration of struct fs_struct; Signed-off-by: Al Viro --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29df6374d2de..b4e065ea0de1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -68,7 +68,7 @@ struct sched_param { #include #include #include -#include +#include #include #include #include @@ -97,6 +97,7 @@ struct futex_pi_state; struct robust_list_head; struct bio; struct bts_tracer; +struct fs_struct; /* * List of flags we want to share for kernel threads, -- cgit v1.2.2 From 9de1581e75ba9d7979766d4ab6d56f0f2d87f7c6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 31 Mar 2009 15:19:29 -0700 Subject: get_mm_hiwater_xxx: trivial, s/define/inline/ Andrew pointed out get_mm_hiwater_xxx() evaluate "mm" argument thrice/twice, make them inline. Signed-off-by: Oleg Nesterov Cc: Hugh Dickins Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29df6374d2de..481fad3a9b42 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -391,8 +391,15 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); (mm)->hiwater_vm = (mm)->total_vm; \ } while (0) -#define get_mm_hiwater_rss(mm) max((mm)->hiwater_rss, get_mm_rss(mm)) -#define get_mm_hiwater_vm(mm) max((mm)->hiwater_vm, (mm)->total_vm) +static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) +{ + return max(mm->hiwater_rss, get_mm_rss(mm)); +} + +static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) +{ + return max(mm->hiwater_vm, mm->total_vm); +} extern void set_dumpable(struct mm_struct *mm, int value); extern int get_dumpable(struct mm_struct *mm); -- cgit v1.2.2 From 6f2c55b843836d26528c56a0968689accaedbc67 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 2 Apr 2009 16:56:59 -0700 Subject: Simplify copy_thread() First argument unused since 2.3.11. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Alexey Dobriyan Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 481fad3a9b42..9186f8c5d5f2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1975,7 +1975,8 @@ extern void mm_release(struct task_struct *, struct mm_struct *); /* Allocate a new mm structure and copy contents from tsk->mm */ extern struct mm_struct *dup_mm(struct task_struct *tsk); -extern int copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *); +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *, struct pt_regs *); extern void flush_thread(void); extern void exit_thread(void); -- cgit v1.2.2 From 39c626ae47c469abdfd30c6e42eff884931380d6 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:18 -0700 Subject: forget_original_parent: split out the un-ptrace part By discussion with Roland. - Rename ptrace_exit() to exit_ptrace(), and change it to do all the necessary work with ->ptraced list by its own. - Move this code from exit.c to ptrace.c - Update the comment in ptrace_detach() to explain the rechecking of the child->ptrace. Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: "Metzger, Markus T" Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9186f8c5d5f2..b47c94e7560b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2061,6 +2061,11 @@ static inline int thread_group_empty(struct task_struct *p) #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) +static inline int task_detached(struct task_struct *p) +{ + return p->exit_signal == -1; +} + /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also -- cgit v1.2.2 From 6dda81f4384b94930826eded254d8c16f89a9248 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:35 -0700 Subject: pids: document task_pgrp/task_session is not safe without tasklist/rcu Even if task == current, it is not safe to dereference the result of task_pgrp/task_session. We can race with another thread which changes the special pid via setpgid/setsid. Document this. The next 2 patches give an example of the unsafe usage, we have more bad users. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index b47c94e7560b..722dd313bf8a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1489,6 +1489,11 @@ static inline struct pid *task_tgid(struct task_struct *task) return task->group_leader->pids[PIDTYPE_PID].pid; } +/* + * Without tasklist or rcu lock it is not safe to dereference + * the result of task_pgrp/task_session even if task == current, + * we can race with another thread doing sys_setsid/sys_setpgid. + */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->group_leader->pids[PIDTYPE_PGID].pid; -- cgit v1.2.2 From 52ee2dfdd4f51cf422ea6a96a0846dc94244aa37 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:38 -0700 Subject: pids: refactor vnr/nr_ns helpers to make them safe Inho, the safety rules for vnr/nr_ns helpers are horrible and buggy. task_pid_nr_ns(task) needs rcu/tasklist depending on task == current. As for "special" pids, vnr/nr_ns helpers always need rcu. However, if task != current, they are unsafe even under rcu lock, we can't trust task->group_leader without the special checks. And almost every helper has a callsite which needs a fix. Also, it is a bit annoying that the implementations of, say, task_pgrp_vnr() and task_pgrp_nr_ns() are not "symmetrical". This patch introduces the new helper, __task_pid_nr_ns(), which is always safe to use, and turns all other helpers into the trivial wrappers. After this I'll send another patch which converts task_tgid_xxx() as well, they're are a bit special. Signed-off-by: Oleg Nesterov Cc: Louis Rilling Cc: "Eric W. Biederman" Cc: Pavel Emelyanov Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 722dd313bf8a..49df878a0cad 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1519,17 +1519,23 @@ struct pid_namespace; * * see also pid_nr() etc in include/linux/pid.h */ +pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, + struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } -pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pid_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); +} static inline pid_t task_pid_vnr(struct task_struct *tsk) { - return pid_vnr(task_pid(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } @@ -1551,11 +1557,15 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return tsk->signal->__pgrp; } -pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); +} static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { - return pid_vnr(task_pgrp(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } @@ -1564,14 +1574,17 @@ static inline pid_t task_session_nr(struct task_struct *tsk) return tsk->signal->__session; } -pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); +static inline pid_t task_session_nr_ns(struct task_struct *tsk, + struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); +} static inline pid_t task_session_vnr(struct task_struct *tsk) { - return pid_vnr(task_session(tsk)); + return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. -- cgit v1.2.2 From 1b0f7ffd0ea27cd3a0b9ca04e3df9522048c32a3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 2 Apr 2009 16:58:39 -0700 Subject: pids: kill signal_struct-> __pgrp/__session and friends We are wasting 2 words in signal_struct without any reason to implement task_pgrp_nr() and task_session_nr(). task_session_nr() has no callers since 2e2ba22ea4fd4bb85f0fa37c521066db6775cbef, we can remove it. task_pgrp_nr() is still (I believe wrongly) used in fs/autofsX and fs/coda. This patch reimplements task_pgrp_nr() via task_pgrp_nr_ns(), and kills __pgrp/__session and the related helpers. The change in drivers/char/tty_io.c is cosmetic, but hopefully makes sense anyway. Signed-off-by: Oleg Nesterov Acked-by: Alan Cox [tty parts] Cc: Cedric Le Goater Cc: Dave Hansen Cc: Eric Biederman Cc: Pavel Emelyanov Cc: Serge Hallyn Cc: Sukadev Bhattiprolu Cc: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 43 ++++++------------------------------------- 1 file changed, 6 insertions(+), 37 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 49df878a0cad..206ac003e8c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -547,25 +547,8 @@ struct signal_struct { struct list_head cpu_timers[3]; - /* job control IDs */ - - /* - * pgrp and session fields are deprecated. - * use the task_session_Xnr and task_pgrp_Xnr routines below - */ - - union { - pid_t pgrp __deprecated; - pid_t __pgrp; - }; - struct pid *tty_old_pgrp; - union { - pid_t session __deprecated; - pid_t __session; - }; - /* boolean value for session group leader */ int leader; @@ -1469,16 +1452,6 @@ static inline int rt_task(struct task_struct *p) return rt_prio(p->prio); } -static inline void set_task_session(struct task_struct *tsk, pid_t session) -{ - tsk->signal->__session = session; -} - -static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp) -{ - tsk->signal->__pgrp = pgrp; -} - static inline struct pid *task_pid(struct task_struct *task) { return task->pids[PIDTYPE_PID].pid; @@ -1552,11 +1525,6 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk) } -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return tsk->signal->__pgrp; -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1569,11 +1537,6 @@ static inline pid_t task_pgrp_vnr(struct task_struct *tsk) } -static inline pid_t task_session_nr(struct task_struct *tsk) -{ - return tsk->signal->__session; -} - static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { @@ -1585,6 +1548,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +/* obsolete, do not use */ +static inline pid_t task_pgrp_nr(struct task_struct *tsk) +{ + return task_pgrp_nr_ns(tsk, &init_pid_ns); +} + /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. -- cgit v1.2.2