linux/kernel, branch v2.6.13-rc7

[PATCH] cpu_exclusive sched domains on partial nodes temp fix

2005-08-24T03:02:52Z

This keeps the kernel/cpuset.c routine update_cpu_domains() from invoking the sched.c routine partition_sched_domains() if the cpuset in question doesn't fall on node boundaries. I have boot tested this on an SN2, and with the help of a couple of ad hoc printk's, determined that it does indeed avoid calling the partition_sched_domains() routine on partial nodes. I did not directly verify that this avoids setting up bogus sched domains or avoids the oops that Hawkes saw. This patch imposes a silent artificial constraint on which cpusets can be used to define dynamic sched domains. This patch should allow proceeding with this new feature in 2.6.13 for the configurations in which it is useful (node alligned sched domains) while avoiding trying to setup sched domains in the less useful cases that can cause the kernel corruption and oops. Signed-off-by: Paul Jackson Acked-by: Ingo Molnar Acked-by: Dinakar Guniguntala Acked-by: John Hawkes Signed-off-by: Linus Torvalds

[PATCH] preempt race in getppid

2005-08-23T18:44:29Z

With CONFIG_PREEMPT && !CONFIG_SMP, it's possible for sys_getppid to return a bogus value if the parent's task_struct gets reallocated after current->group_leader->real_parent is read: asmlinkage long sys_getppid(void) { int pid; struct task_struct *me = current; struct task_struct *parent; parent = me->group_leader->real_parent; RACE HERE => for (;;) { pid = parent->tgid; #ifdef CONFIG_SMP { struct task_struct *old = parent; /* * Make sure we read the pid before re-reading the * parent pointer: */ smp_rmb(); parent = me->group_leader->real_parent; if (old != parent) continue; } #endif break; } return pid; } If the process gets preempted at the indicated point, the parent process can go ahead and call exit() and then get wait()'d on to reap its task_struct. When the preempted process gets resumed, it will not do any further checks of the parent pointer on !CONFIG_SMP: it will read the bad pid and return. So, the same algorithm used when SMP is enabled should be used when preempt is enabled, which will recheck ->real_parent in this case. Signed-off-by: David Meybohm Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

[PATCH] Make RLIMIT_NICE ranges consistent with getpriority(2)

2005-08-18T19:53:58Z

As suggested by Michael Kerrisk , make RLIMIT_NICE consistent with getpriority before it becomes available in released glibc. Signed-off-by: Matt Mackall Acked-by: Ingo Molnar Acked-by: Chris Wright Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

[PATCH] NPTL signal delivery deadlock fix

2005-08-17T19:52:04Z

This bug is quite subtle and only happens in a very interesting situation where a real-time threaded process is in the middle of a coredump when someone whacks it with a SIGKILL. However, this deadlock leaves the system pretty hosed and you have to reboot to recover. Not good for real-time priority-preemption applications like our telephony application, with 90+ real-time (SCHED_FIFO and SCHED_RR) processes, many of them multi-threaded, interacting with each other for high volume call processing. Acked-by: Roland McGrath Signed-off-by: Linus Torvalds

[PATCH] remove name length check in a workqueue

2005-08-10T18:55:19Z

We have a chek in there to make sure that the name won't overflow task_struct.comm[], but it's triggering for scsi with lots of HBAs, only scsi is using single-threaded workqueues which don't append the "/%d" anyway. All too hard. Just kill the BUG_ON. Cc: Ingo Molnar Signed-off-by: Andrew Morton [ kthread_create() uses vsnprintf() and limits the thing, so no actual overflow can actually happen regardless ] Signed-off-by: Linus Torvalds

[PATCH] cpuset release ABBA deadlock fix

2005-08-09T19:08:22Z

Fix possible cpuset_sem ABBA deadlock if 'notify_on_release' set. For a particular usage pattern, creating and destroying cpusets fairly frequently using notify_on_release, on a very large system, this deadlock can be seen every few days. If you are not using the cpuset notify_on_release feature, you will never see this deadlock. The existing code, on task exit (or cpuset deletion) did: get cpuset_sem if cpuset marked notify_on_release and is ready to release: compute cpuset path relative to /dev/cpuset mount point call_usermodehelper() forks /sbin/cpuset_release_agent with path drop cpuset_sem Unfortunately, the fork in call_usermodehelper can allocate memory, and allocating memory can require cpuset_sem, if the mems_generation values changed in the interim. This results in an ABBA deadlock, trying to obtain cpuset_sem when it is already held by the current task. To fix this, I put the cpuset path (which must be computed while holding cpuset_sem) in a temporary buffer, to be used in the call_usermodehelper call of /sbin/cpuset_release_agent only _after_ dropping cpuset_sem. So the new logic is: get cpuset_sem if cpuset marked notify_on_release and is ready to release: compute cpuset path relative to /dev/cpuset mount point stash path in kmalloc'd buffer drop cpuset_sem call_usermodehelper() forks /sbin/cpuset_release_agent with path free path The sharp eyed reader might notice that this patch does not contain any calls to kmalloc. The existing code in the check_for_release() routine was already kmalloc'ing a buffer to hold the cpuset path. In the old code, it just held the buffer for a few lines, over the cpuset_release_agent() call that in turn invoked call_usermodehelper(). In the new code, with the application of this patch, it returns that buffer via the new char **ppathbuf parameter, for later use and freeing in cpuset_release_agent(), which is called after cpuset_sem is dropped. Whereas the old code has just one call to cpuset_release_agent(), right in the check_for_release() routine, the new code has three calls to cpuset_release_agent(), from the various places that a cpuset can be released. This patch has been build and booted on SN2, and passed a stress test that previously hit the deadlock within a few seconds. Signed-off-by: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

[PATCH] revert "timer exit cleanup"

2005-08-04T23:57:49Z

Revert this June 17 patch: it broke persistence of timers across execve(). Cc: Roland McGrath Cc: george anzinger Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

[PATCH] Remove suspend() calls from shutdown path

2005-08-04T15:20:47Z

This removes the calls to device_suspend() from the shutdown path that were added sometime during 2.6.13-rc*. They aren't working properly on a number of configs (I got reports from both ppc powerbook users and x86 users) causing the system to not shutdown anymore. I think it isn't the right approach at the moment anyway. We have already a shutdown() callback for the drivers that actually care about shutdown and the suspend() code isn't yet in a good enough shape to be so much generalized. Also, the semantics of suspend and shutdown are slightly different on a number of setups and the way this was patched in provides little way for drivers to cleanly differenciate. It should have been at least a different message. For 2.6.13, I think we should revert to 2.6.12 behaviour and have a working suspend back. Signed-off-by: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds

[PATCH] Module per-cpu alignment cannot always be met

2005-08-02T04:38:01Z

The module code assumes noone will ever ask for a per-cpu area more than SMP_CACHE_BYTES aligned. However, as these cases show, gcc asks sometimes asks for 32-byte alignment for the per-cpu section on a module, and if CONFIG_X86_L1_CACHE_SHIFT is 4, we hit that BUG_ON(). This is obviously an unusual combination, as there have been few reports, but better to warn than die. See: http://www.ussg.iu.edu/hypermail/linux/kernel/0409.0/0768.html And more recently: http://bugs.gentoo.org/show_bug.cgi?id=97006 Signed-off-by: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

[PATCH] remove sys_set_zone_reclaim()

2005-08-01T17:03:56Z

This removes sys_set_zone_reclaim() for now. While i'm sure Martin is trying to solve a real problem, we must not hard-code an incomplete and insufficient approach into a syscall, because syscalls are pretty much for eternity. I am quite strongly convinced that this syscall must not hit v2.6.13 in its current form. Firstly, the syscall lacks basic syscall design: e.g. it allows the global setting of VM policy for unprivileged users. (!) [ Imagine an Oracle installation and a SAP installation on the same NUMA box fighting over the 'optimal' setting for this flag. What will they do? Will they try to set the flag to their own preferred value every second or so? ] Secondly, it was added based on a single datapoint from Martin: http://marc.theaimsgroup.com/?l=linux-mm&m=111763597218177&w=2 where Martin characterizes the numbers the following way: ' Run-to-run variability for "make -j" is huge, so these numbers aren't terribly useful except to see that with reclaim the benchmark still finishes in a reasonable amount of time. ' in other words: the fundamental problem has likely not been solved, only a tendential move into the right direction has been observed, and a handful of numbers were picked out of a set of hugely variable results, without showing the variability data. How much variance is there run-to-run? I'd really suggest to first walk the walk and see what's needed to get stable & predictable kernel compilation numbers on that NUMA box, before adding random syscalls to tune a particular aspect of the VM ... which approach might not even matter once the whole picture has been analyzed and understood! The third, most important point is that the syscall exposes VM tuning internals in a completely unstructured way. What sense does it make to have a _GLOBAL_ per-node setting for 'should we go to another node for reclaim'? If then it might make sense to do this per-app, via numalib or so. The change is minimalistic in that it doesnt remove the syscall and the underlying infrastructure changes, only the user-visible changes. We could perhaps add a CAP_SYS_ADMIN-only sysctl for this hack, a'ka /proc/sys/vm/swappiness, but even that looks quite counterproductive when the generic approach is that we are trying to reduce the number of external factors in the VM balance picture. Signed-off-by: Ingo Molnar Signed-off-by: Linus Torvalds