summaryrefslogtreecommitdiff
path: root/kernel
AgeCommit message (Collapse)Author
2008-09-14timers: fix itimer/many thread hangFrank Mayhar
Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar <fmayhar@google.com> Cc: Roland McGrath <roland@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-13cpuset: avoid changing cpuset's cpus when -errno returnedLi Zefan
After the patch: commit 0b2f630a28d53b5a2082a5275bc3334b10373508 Author: Miao Xie <miaox@cn.fujitsu.com> Date: Fri Jul 25 01:47:21 2008 -0700 cpusets: restructure the function update_cpumask() and update_nodemask() It might happen that 'echo 0 > /cpuset/sub/cpus' returned failure but 'cpus' has been changed, because cpus was changed before calling heap_init() which may return -ENOMEM. This patch restores the orginal behavior. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Paul Jackson <pj@sgi.com> Cc: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-09clockevents: remove WARN_ON which was used to gather informationThomas Gleixner
The issue of the endless reprogramming loop due to a too small min_delta_ns was fixed with the previous updates of the clock events code, but we had no information about the spread of this problem. I added a WARN_ON to get automated information via kerneloops.org and to get some direct reports, which allowed me to analyse the affected machines. The WARN_ON has served its purpose and would be annoying for a release kernel. Remove it and just keep the information about the increase of the min_delta_ns value. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-09-08Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: arch_reinit_sched_domains() must destroy domains to force rebuild sched, cpuset: rework sched domains and CPU hotplug handling (v4)
2008-09-06Merge branch 'timers-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: clocksource, acpi_pm.c: check for monotonicity clocksource, acpi_pm.c: use proper read function also in errata mode ntp: fix calculation of the next jiffie to trigger RTC sync x86: HPET: read back compare register before reading counter x86: HPET fix moronic 32/64bit thinko clockevents: broadcast fixup possible waiters HPET: make minimum reprogramming delta useful clockevents: prevent endless loop lockup clockevents: prevent multiple init/shutdown clockevents: enforce reprogram in oneshot setup clockevents: prevent endless loop in periodic broadcast handler clockevents: prevent clockevent event_handler ending up handler_noop
2008-09-06Merge branch 'sched/cpuset' into sched/urgentIngo Molnar
2008-09-06sched: arch_reinit_sched_domains() must destroy domains to force rebuildMax Krasnyansky
What I realized recently is that calling rebuild_sched_domains() in arch_reinit_sched_domains() by itself is not enough when cpusets are enabled. partition_sched_domains() code is trying to avoid unnecessary domain rebuilds and will not actually rebuild anything if new domain masks match the old ones. What this means is that doing echo 1 > /sys/devices/system/cpu/sched_mc_power_savings on a system with cpusets enabled will not take affect untill something changes in the cpuset setup (ie new sets created or deleted). This patch fixes restore correct behaviour where domains must be rebuilt in order to enable MC powersaving flags. Test on quad-core Core2 box with both CONFIG_CPUSETS and !CONFIG_CPUSETS. Also tested on dual-core Core2 laptop. Lockdep is happy and things are working as expected. Signed-off-by: Max Krasnyansky <maxk@qualcomm.com> Tested-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-06ntp: fix calculation of the next jiffie to trigger RTC syncMaciej W. Rozycki
We have a bug in the calculation of the next jiffie to trigger the RTC synchronisation. The aim here is to run sync_cmos_clock() as close as possible to the middle of a second. Which means we want this function to be called less than or equal to half a jiffie away from when now.tv_nsec equals 5e8 (500000000). If this is not the case for a given call to the function, for this purpose instead of updating the RTC we calculate the offset in nanoseconds to the next point in time where now.tv_nsec will be equal 5e8. The calculated offset is then converted to jiffies as these are the unit used by the timer. Hovewer timespec_to_jiffies() used here uses a ceil()-type rounding mode, where the resulting value is rounded up. As a result the range of now.tv_nsec when the timer will trigger is from 5e8 to 5e8 + TICK_NSEC rather than the desired 5e8 - TICK_NSEC / 2 to 5e8 + TICK_NSEC / 2. As a result if for example sync_cmos_clock() happens to be called at the time when now.tv_nsec is between 5e8 + TICK_NSEC / 2 and 5e8 to 5e8 + TICK_NSEC, it will simply be rescheduled HZ jiffies later, falling in the same range of now.tv_nsec again. Similarly for cases offsetted by an integer multiple of TICK_NSEC. This change addresses the problem by subtracting TICK_NSEC / 2 from the nanosecond offset to the next point in time where now.tv_nsec will be equal 5e8, effectively shifting the following rounding in timespec_to_jiffies() so that it produces a rounded-to-nearest result. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-06clockevents: broadcast fixup possible waitersThomas Gleixner
Until the C1E patches arrived there where no users of periodic broadcast before switching to oneshot mode. Now we need to trigger a possible waiter for a periodic broadcast when switching to oneshot mode. Otherwise we can starve them for ever. Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-09-05sched: fix process time monotonicityBalbir Singh
Spencer reported a problem where utime and stime were going negative despite the fixes in commit b27f03d4bdc145a09fb7b0c0e004b29f1ee555fa. The suspected reason for the problem is that signal_struct maintains it's own utime and stime (of exited tasks), these are not updated using the new task_utime() routine, hence sig->utime can go backwards and cause the same problem to occur (sig->utime, adds tsk->utime and not task_utime()). This patch fixes the problem TODO: using max(task->prev_utime, derived utime) works for now, but a more generic solution is to implement cputime_max() and use the cputime_gt() function for comparison. Reported-by: spencer@bluehost.com Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05sched_clock: fix NOHZ interactionPeter Zijlstra
If HLT stops the TSC, we'll fail to account idle time, thereby inflating the actual process times. Fix this by re-calibrating the clock against GTOD when leaving nohz mode. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Avi Kivity <avi@qumranet.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05clockevents: prevent endless loop lockupThomas Gleixner
The C1E/HPET bug reports on AMDX2/RS690 systems where tracked down to a too small value of the HPET minumum delta for programming an event. The clockevents code needs to enforce an interrupt event on the clock event device in some cases. The enforcement code was stupid and naive, as it just added the minimum delta to the current time and tried to reprogram the device. When the minimum delta is too small, then this loops forever. Add a sanity check. Allow reprogramming to fail 3 times, then print a warning and double the minimum delta value to make sure, that this does not happen again. Use the same function for both tick-oneshot and tick-broadcast code. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05clockevents: prevent multiple init/shutdownThomas Gleixner
While chasing the C1E/HPET bugreports I went through the clock events code inch by inch and found that the broadcast device can be initialized and shutdown multiple times. Multiple shutdowns are not critical, but useless waste of time. Multiple initializations are simply broken. Another CPU might have the device in use already after the first initialization and the second init could just render it unusable again. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05clockevents: enforce reprogram in oneshot setupThomas Gleixner
In tick_oneshot_setup we program the device to the given next_event, but we do not check the return value. We need to make sure that the device is programmed enforced so the interrupt handler engine starts working. Split out the reprogramming function from tick_program_event() and call it with the device, which was handed in to tick_setup_oneshot(). Set the force argument, so the devices is firing an interrupt. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05clockevents: prevent endless loop in periodic broadcast handlerThomas Gleixner
The reprogramming of the periodic broadcast handler was broken, when the first programming returned -ETIME. The clockevents code stores the new expiry value in the clock events device next_event field only when the programming time has not been elapsed yet. The loop in question calculates the new expiry value from the next_event value and therefor never increases. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-05clockevents: prevent clockevent event_handler ending up handler_noopVenkatesh Pallipadi
There is a ordering related problem with clockevents code, due to which clockevents_register_device() called after tickless/highres switch will not work. The new clockevent ends up with clockevents_handle_noop as event handler, resulting in no timer activity. The problematic path seems to be * old device already has hrtimer_interrupt as the event_handler * new clockevent device registers with a higher rating * tick_check_new_device() is called * clockevents_exchange_device() gets called * old->event_handler is set to clockevents_handle_noop * tick_setup_device() is called for the new device * which sets new->event_handler using the old->event_handler which is noop. Change the ordering so that new device inherits the proper handler. This does not have any issue in normal case as most likely all the clockevent devices are setup before the highres switch. But, can potentially be affecting some corner case where HPET force detect happens after the highres switch. This was a problem with HPET in MSI mode code that we have been experimenting with. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-04forgotten refcount on sysctl root tableAl Viro
We should've set refcount on the root sysctl table; otherwise we'll blow up the first time we get down to zero dynamically registered sysctl tables. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Tested-by: James Bottomley <James.Bottomley@HansenPartnership.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-02pm_qos_requirement might sleepJohn Kacur
Make PM_QOS and CPU_IDLE play nicer when run with the RT-Preempt kernel. The purpose of the patch is to remove the spin_lock around the read in the function pm_qos_requirement - since spinlocks can sleep in -rt and this function is called from idle. CPU_IDLE polls the target_value's of some of the pm_qos parameters from the idle loop causing sleeping locking warnings. Changing the target_value to an atomic avoids this issue. Remove the spinlock in pm_qos_requirement by making target_value an atomic type. Signed-off-by: mark gross <mgross@linux.intel.com> Signed-off-by: John Kacur <jkacur@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-02pid_ns: (BUG 11391) change ->child_reaper when init->group_leader exitsOleg Nesterov
We don't change pid_ns->child_reaper when the main thread of the subnamespace init exits. As Robert Rex <robert.rex@exasol.com> pointed out this is wrong. Yes, the re-parenting itself works correctly, but if the reparented task exits it needs ->parent->nsproxy->pid_ns in do_notify_parent(), and if the main thread is zombie its ->nsproxy was already cleared by exit_task_namespaces(). Introduce the new function, find_new_reaper(), which finds the new ->parent for the re-parenting and changes ->child_reaper if needed. Kill the now unneeded exit_child_reaper(). Also move the changing of ->child_reaper from zap_pid_ns_processes() to find_new_reaper(), this consolidates the games with ->child_reaper and makes it stable under tasklist_lock. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=11391 Reported-by: Robert Rex <robert.rex@exasol.com> Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Acked-by: Serge Hallyn <serue@us.ibm.com> Acked-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-02pid_ns: zap_pid_ns_processes: fix the ->child_reaper changingOleg Nesterov
zap_pid_ns_processes() sets pid_ns->child_reaper = NULL, this is wrong. Yes, we have already killed all tasks in this namespace, and sys_wait4() doesn't see any child. But this doesn't mean ->children list is empty, we may have EXIT_DEAD tasks which are not visible to do_wait(). In that case the subsequent forget_original_parent() will crash the kernel because it will try to re-parent these tasks to the NULL reaper. Even if there are no childs, it is not good that forget_original_parent() uses reaper == NULL. Change the code to set ->child_reaper = init_pid_ns.child_reaper instead. We could use pid_ns->parent->child_reaper as well, I think this does not really matter. These EXIT_DEAD tasks are not visible to the new ->parent after re-parenting, they will silently do release_task() eventually. Note that we must change ->child_reaper, otherwise forget_original_parent() will use reaper == father, and in that case we will hit the (correct) BUG_ON(!list_empty(&father->children)). Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Acked-by: Serge Hallyn <serue@us.ibm.com> Acked-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Acked-by: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-02Merge branch 'audit.b57' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current * 'audit.b57' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current: [PATCH] audit: Moved variable declaration to beginning of function
2008-09-02softlockup: minor cleanup, don't check task->state twiceOleg Nesterov
The recent commit 16d9679f33caf7e683471647d1472bfe133d858 changed check_hung_task() to filter out the TASK_KILLABLE tasks. We can move this check to the caller which has to test t->state anyway. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Acked-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-02kernel/resource.c: fix new kernel-doc warningRandy Dunlap
Fix kernel-doc warning for new function: Warning(linux-2.6.27-rc5-git2//kernel/resource.c:448): No description found for parameter 'root' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-01[PATCH] audit: Moved variable declaration to beginning of functionCordelia
got rid of compilation warning: ISO C90 forbids mixed declarations and code Signed-off-by: Cordelia Sam <cordesam@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-08-29Resource handling: add 'insert_resource_expand_to_fit()' functionLinus Torvalds
Not used anywhere yet, but this complements the existing plain 'insert_resource()' functionality with a version that can expand the resource we are adding in order to fix up any conflicts it has with existing resources. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-29Don't trigger softlockup detector on network fs blocked tasksAndi Kleen
Pulling the ethernet cable on a 2.6.27-rc system with NFS mounts currently leads to an ongoing flood of soft lockup detector backtraces for all tasks blocked on the NFS mounts when the hickup takes longer than 120s. I don't think NFS problems should be all that noisy. Luckily there's a reasonably easy way to distingush this case. Don't report task softlockup warnings for tasks in TASK_KILLABLE state, which is used by the network file systems. I believe this patch is a 2.6.27 candidate. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-28Merge branch 'core-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: exit signals: use of uninitialized field notify_count lockdep: fix invalid list_del_rcu in zap_class lockstat: repair erronous contention statistics lockstat: fix numerical output rounding error
2008-08-28Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: rt-bandwidth accounting fix sched: fix sched_rt_rq_enqueue() resched idle
2008-08-28Merge branch 'x86-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: update defconfigs x86: msr: fix bogus return values from rdmsr_safe/wrmsr_safe x86: cpuid: correct return value on partial operations x86: msr: correct return value on partial operations x86: cpuid: propagate error from smp_call_function_single() x86: msr: propagate errors from smp_call_function_single() smp: have smp_call_function_single() detect invalid CPUs
2008-08-28ftrace: disable tracing for hibernationRafael J. Wysocki
In accordance with commit f42ac38c59e0a03d6da0c24a63fb211393f484b0 ("ftrace: disable tracing for suspend to ram"), disable tracing around the suspend code in hibernation code paths. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-28sched: rt-bandwidth accounting fixPeter Zijlstra
It fixes an accounting bug where we would continue accumulating runtime even though the bandwidth control is disabled. This would lead to very long throttle periods once bandwidth control gets turned on again. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-28sched: fix sched_rt_rq_enqueue() resched idleJohn Blackwood
When sysctl_sched_rt_runtime is set to something other than -1 and the CONFIG_RT_GROUP_SCHED kernel parameter is NOT enabled, we get into a state where we see one or more CPUs idling forvever even though there are real-time tasks in their rt runqueue that are able to run (no longer throttled). The sequence is: - A real-time task is running when the timer sets the rt runqueue to throttled, and the rt task is resched_task()ed and switched out, and idle is switched in since there are no non-rt tasks to run on that cpu. - Eventually the do_sched_rt_period_timer() runs and un-throttles the rt runqueue, but we just exit the timer interrupt and go back to executing the idle task in the idle loop forever. If we change the sched_rt_rq_enqueue() routine to use some of the code from the CONFIG_RT_GROUP_SCHED enabled version of this same routine and resched_task() the currently executing task (idle in our case) if it is a lower priority task than the higher rt task in the now un-throttled runqueue, the problem is no longer observed. Signed-off-by: John Blackwood <john.blackwood@ccur.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-27ftrace: disable tracing for suspend to ramSteven Rostedt
I've been painstakingly debugging the issue with suspend to ram and ftraced. The 2.6.28 code does not have this issue, but since the mcount recording is not going to be in 27, this must be solved for the ftrace daemon version. The resume from suspend to ram would reboot because it was triple faulting. Debugging further, I found that calling the mcount function itself was not an issue, but it would fault when it incremented preempt_count. preempt_count is on the tasks info structure that is on the low memory address of the task's stack. For some reason, it could not write to it. Resuming out of suspend to ram does quite a lot of funny tricks to get to work, so it is not surprising at all that simply doing a preempt_disable() would cause a fault. Thanks to Rafael for suggesting to add a "while (1);" to find the place in resuming that is causing the fault. I would place the loop somewhere in the code, compile and reboot and see if it would either reboot (hit the fault) or simply hang (hit the loop). Doing this over and over again, I narrowed it down that it was happening in enable_nonboot_cpus. At this point, I found that it is easier to simply disable tracing around the suspend code, instead of searching for the particular function that can not handle doing a preempt_disable. This patch disables the tracer as it suspends and reenables it on resume. I tested this patch on my Laptop, and it can resume fine with the patch. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Acked-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-27exit signals: use of uninitialized field notify_countSteve VanDeBogart
task->signal->notify_count is only initialized if task->signal->group_exit_task is not NULL. Reorder a conditional so that uninitialised memory is not used. Found by Valgrind. Signed-off-by: Steve VanDeBogart <vandebo-lkml@nerdbox.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-27lockdep: fix invalid list_del_rcu in zap_classZhu Yi
The problem is found during iwlagn driver testing on v2.6.27-rc4-176-gb8e6c91 kernel, but it turns out to be a lockdep bug. In our testing, we frequently load and unload the iwlagn driver (>50 times). Then the MAX_STACK_TRACE_ENTRIES is reached (expected behaviour?). The error message with the call trace is as below. BUG: MAX_STACK_TRACE_ENTRIES too low! turning off the locking correctness validator. Pid: 4895, comm: iwlagn Not tainted 2.6.27-rc4 #13 Call Trace: [<ffffffff81014aa1>] save_stack_trace+0x22/0x3e [<ffffffff8105390a>] save_trace+0x8b/0x91 [<ffffffff81054e60>] mark_lock+0x1b0/0x8fa [<ffffffff81056f71>] __lock_acquire+0x5b9/0x716 [<ffffffffa00d818a>] ieee80211_sta_work+0x0/0x6ea [mac80211] [<ffffffff81057120>] lock_acquire+0x52/0x6b [<ffffffff81045f0e>] run_workqueue+0x97/0x1ed [<ffffffff81045f5e>] run_workqueue+0xe7/0x1ed [<ffffffff81045f0e>] run_workqueue+0x97/0x1ed [<ffffffff81046ae4>] worker_thread+0xd8/0xe3 [<ffffffff81049503>] autoremove_wake_function+0x0/0x2e [<ffffffff81046a0c>] worker_thread+0x0/0xe3 [<ffffffff810493ec>] kthread+0x47/0x73 [<ffffffff8128e3ab>] trace_hardirqs_on_thunk+0x3a/0x3f [<ffffffff8100cea9>] child_rip+0xa/0x11 [<ffffffff8100c4df>] restore_args+0x0/0x30 [<ffffffff810316e1>] finish_task_switch+0x0/0xcc [<ffffffff810493a5>] kthread+0x0/0x73 [<ffffffff8100ce9f>] child_rip+0x0/0x11 Although the above is harmless, when the ilwagn module is removed later lockdep will trigger a kernel oops as below. BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: [<ffffffff810531e1>] zap_class+0x24/0x82 PGD 73128067 PUD 7448c067 PMD 0 Oops: 0002 [1] SMP CPU 0 Modules linked in: rfcomm l2cap bluetooth autofs4 sunrpc nf_conntrack_ipv6 xt_state nf_conntrack xt_tcpudp ip6t_ipv6header ip6t_REJECT ip6table_filter ip6_tables x_tables ipv6 cpufreq_ondemand acpi_cpufreq dm_mirror dm_log dm_multipath dm_mod snd_hda_intel sr_mod snd_seq_dummy snd_seq_oss snd_seq_midi_event battery snd_seq snd_seq_device cdrom button snd_pcm_oss snd_mixer_oss snd_pcm snd_timer snd_page_alloc e1000e snd_hwdep sg iTCO_wdt iTCO_vendor_support ac pcspkr i2c_i801 i2c_core snd soundcore video output ata_piix ata_generic libata sd_mod scsi_mod ext3 jbd mbcache uhci_hcd ohci_hcd ehci_hcd [last unloaded: mac80211] Pid: 4941, comm: modprobe Not tainted 2.6.27-rc4 #10 RIP: 0010:[<ffffffff810531e1>] [<ffffffff810531e1>] zap_class+0x24/0x82 RSP: 0000:ffff88007bcb3eb0 EFLAGS: 00010046 RAX: 0000000000068ee8 RBX: ffffffff8192a0a0 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000001dfb RDI: ffffffff816e70b0 RBP: ffffffffa00cd000 R08: ffffffff816818f8 R09: ffff88007c923558 R10: ffffe20002ad2408 R11: ffffffff811028ec R12: ffffffff8192a0a0 R13: 000000000002bd90 R14: 0000000000000000 R15: 0000000000000296 FS: 00007f9d1cee56f0(0000) GS:ffffffff814a58c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000008 CR3: 0000000073047000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process modprobe (pid: 4941, threadinfo ffff88007bcb2000, task ffff8800758d1fc0) Stack: ffffffff81057376 0000000000000000 ffffffffa00f7b00 0000000000000000 0000000000000080 0000000000618278 00007fff24f16720 0000000000000000 ffffffff8105d37a ffffffffa00f7b00 ffffffff8105d591 313132303863616d Call Trace: [<ffffffff81057376>] ? lockdep_free_key_range+0x61/0xf5 [<ffffffff8105d37a>] ? free_module+0xd4/0xe4 [<ffffffff8105d591>] ? sys_delete_module+0x1de/0x1f9 [<ffffffff8106dbfa>] ? audit_syscall_entry+0x12d/0x160 [<ffffffff8100be2b>] ? system_call_fastpath+0x16/0x1b Code: b2 00 01 00 00 00 c3 31 f6 49 c7 c0 10 8a 61 81 eb 32 49 39 38 75 26 48 98 48 6b c0 38 48 8b 90 08 8a 61 81 48 8b 88 00 8a 61 81 <48> 89 51 08 48 89 0a 48 c7 80 08 8a 61 81 00 02 20 00 48 ff c6 RIP [<ffffffff810531e1>] zap_class+0x24/0x82 RSP <ffff88007bcb3eb0> CR2: 0000000000000008 ---[ end trace a1297e0c4abb0f2e ]--- The root cause for this oops is in add_lock_to_list() when save_trace() fails due to MAX_STACK_TRACE_ENTRIES is reached, entry->class is assigned but entry is never added into any lock list. This makes the list_del_rcu() in zap_class() oops later when the module is unloaded. This patch fixes the problem by assigning entry->class after save_trace() returns success. Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-26lockstat: repair erronous contention statisticsJoe Korty
Fix bad contention counting in /proc/lock_stat. /proc/lockstat tries to gather per-ip contention statistics per-lock. This was failing due to a garbage per-ip index selector being used. Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-26lockstat: fix numerical output rounding errorJoe Korty
Fix rounding error in /proc/lock_stat numerical output. On occasion the two digit fractional part contains the three digit value '100'. This is due to a bug in the rounding algorithm which pushes values in the range '95..99' to '100' rather than to '00' + an increment to the integer part. For example, - 123456.100 old display + 123457.00 new display Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-25smp: have smp_call_function_single() detect invalid CPUsH. Peter Anvin
Have smp_call_function_single() return invalid CPU indicies and return -ENXIO. This function is already executed inside a get_cpu()..put_cpu() which locks out CPU removal, so rather than having the higher layers doing another layer of locking to guard against unplugged CPUs do the test here. Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2008-08-25Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched_clock: fix cpu_clock()
2008-08-25[module] Don't let gcc inline load_module()Linus Torvalds
'load_module()' is a complex function that contains all the ELF section logic, and inlining it is utterly insane. But gcc will do it, simply because there is only one call-site. As a result, all the stack space that is allocated for all the work to load the module will still be active when we actually call the module init sequence, and the deep call chain makes stack overflows happen. And stack overflows are really hard to debug, because they not only corrupt random pages below the stack, but also corrupt the thread_info structure that is allocated under the stack. In this case, Alan Brunelle reported some crazy oopses at bootup, after loading the processor module that ends up doing complex ACPI stuff and has quite a deep callchain. This should fix it, and is the sane thing to do regardless. Cc: Alan D. Brunelle <Alan.Brunelle@hp.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-25sched_clock: fix cpu_clock()Peter Zijlstra
This patch fixes 3 issues: a) it removes the dependency on jiffies, because jiffies are incremented by a single CPU, and the tick is not synchronized between CPUs. Therefore relying on it to calculate a window to clip whacky TSC values doesn't work as it can drift around. So instead use [GTOD, GTOD+TICK_NSEC) as the window. b) __update_sched_clock() did (roughly speaking): delta = sched_clock() - scd->tick_raw; clock += delta; Which gives exponential growth, instead of linear. c) allows the sched_clock_cpu() value to warp the u64 without breaking. the results are more reliable sched_clock() deltas: before after sched_clock cpu_clock: 15750 51312 51488 cpu_clock: 59719 51052 50947 cpu_clock: 15879 51249 51061 cpu_clock: 1 50933 51198 cpu_clock: 1 50931 51039 cpu_clock: 1 51093 50981 cpu_clock: 1 51043 51040 cpu_clock: 1 50959 50938 cpu_clock: 1 50981 51011 cpu_clock: 1 51364 51212 cpu_clock: 1 51219 51273 cpu_clock: 1 51389 51048 cpu_clock: 1 51285 51611 cpu_clock: 1 50964 51137 cpu_clock: 1 50973 50968 cpu_clock: 1 50967 50972 cpu_clock: 1 58910 58485 cpu_clock: 1 51082 51025 cpu_clock: 1 50957 50958 cpu_clock: 1 50958 50957 cpu_clock: 1006128 51128 50971 cpu_clock: 1 51107 51155 cpu_clock: 1 51371 51081 cpu_clock: 1 51104 51365 cpu_clock: 1 51363 51309 cpu_clock: 1 51107 51160 cpu_clock: 1 51139 51100 cpu_clock: 1 51216 51136 cpu_clock: 1 51207 51215 cpu_clock: 1 51087 51263 cpu_clock: 1 51249 51177 cpu_clock: 1 51519 51412 cpu_clock: 1 51416 51255 cpu_clock: 1 51591 51594 cpu_clock: 1 50966 51374 cpu_clock: 1 50966 50966 cpu_clock: 1 51291 50948 cpu_clock: 1 50973 50867 cpu_clock: 1 50970 50970 cpu_clock: 998306 50970 50971 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 50971 50971 cpu_clock: 1 50970 50970 cpu_clock: 1 51351 50970 cpu_clock: 1 50970 51352 cpu_clock: 1 50971 50970 cpu_clock: 1 50970 50970 cpu_clock: 1 51321 50971 cpu_clock: 1 50974 51324 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-23removed unused #include <linux/version.h>'sAdrian Bunk
This patch lets the files using linux/version.h match the files that #include it. Signed-off-by: Adrian Bunk <bunk@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-22Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: enable LB_BIAS by default
2008-08-22Merge branch 'core-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: rcu: fix synchronize_rcu() so that kernel-doc works
2008-08-21nohz: fix wrong event handler after online an offlined cpuMiao Xie
On the tickless system(CONFIG_NO_HZ=y and CONFIG_HIGH_RES_TIMERS=n), after I made an offlined cpu online, I found this cpu's event handler was tick_handle_periodic, not tick_nohz_handler. After debuging, I found this bug was caused by the wrong tick mode. the tick mode is not changed to NOHZ_MODE_INACTIVE when the cpu is offline. This patch fixes this bug. Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-21rcu: fix synchronize_rcu() so that kernel-doc worksRandy Dunlap
Fix RCU's synchronize_rcu() so that it looks like a C function, enabling it to be recognized as a function with kernel-doc annotation. Warning(linux-2.6.26-git11//kernel/rcupdate.c:81): No description found for parameter 'synchronize_rcu' Warning(linux-2.6.26-git11//kernel/rcupdate.c:81): No description found for parameter 'call_rcu' [akpm@linux-foundation.org: fix comment] Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-21sched: enable LB_BIAS by defaultPeter Zijlstra
Yanmin reported a significant regression on his 16-core machine due to: commit 93b75217df39e6d75889cc6f8050343286aff4a5 Author: Peter Zijlstra <a.p.zijlstra@chello.nl> Date: Fri Jun 27 13:41:33 2008 +0200 Flip back to the old behaviour. Reported-by: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-20fix setpriority(PRIO_PGRP) thread iterator breakageKen Chen
When user calls sys_setpriority(PRIO_PGRP ...) on a NPTL style multi-LWP process, only the task leader of the process is affected, all other sibling LWP threads didn't receive the setting. The problem was that the iterator used in sys_setpriority() only iteartes over one task for each process, ignoring all other sibling thread. Introduce a new macro do_each_pid_thread / while_each_pid_thread to walk each thread of a process. Convert 4 call sites in {set/get}priority and ioprio_{set/get}. Signed-off-by: Ken Chen <kenchen@google.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Roland McGrath <roland@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-19tracehook: fix SA_NOCLDWAITRoland McGrath
I outwitted myself again in commit 2b2a1ff64afbadac842bbc58c5166962cf4f7664, and broke the SA_NOCLDWAIT behavior so it leaks zombies. This fixes it. Reported-by: Andi Kleen <andi@firstfloor.org> Signed-off-by: Roland McGrath <roland@redhat.com>
2008-08-18lockdep: fix spurious 'inconsistent lock state' warningDmitry Baryshkov
Since f82b217e3513fe3af342c0f3ee1494e86250c21c lockdep can output spurious warnings related to hwirqs due to hardirq_off shrinkage from int to bit-sized flag. Guard it with double negation to fix the warning. Signed-off-by: Dmitry Baryshkov <dbaryshkov@gmail.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>