aboutsummaryrefslogtreecommitdiff
path: root/kernel
AgeCommit message (Collapse)Author
2009-06-20Merge branch 'perfcounters-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits) perfcounter: Handle some IO return values perf_counter: Push perf_sample_data through the swcounter code perf_counter tools: Define and use our own u64, s64 etc. definitions perf_counter: Close race in perf_lock_task_context() perf_counter, x86: Improve interactions with fast-gup perf_counter: Simplify and fix task migration counting perf_counter tools: Add a data file header perf_counter: Update userspace callchain sampling uses perf_counter: Make callchain samples extensible perf report: Filter to parent set by default perf_counter tools: Handle lost events perf_counter: Add event overlow handling fs: Provide empty .set_page_dirty() aop for anon inodes perf_counter: tools: Makefile tweaks for 64-bit powerpc perf_counter: powerpc: Add processor back-end for MPC7450 family perf_counter: powerpc: Make powerpc perf_counter code safe for 32-bit kernels perf_counter: powerpc: Change how processor-specific back-ends get selected perf_counter: powerpc: Use unsigned long for register and constraint values perf_counter: powerpc: Enable use of software counters on 32-bit powerpc perf_counter tools: Add and use isprint() ...
2009-06-20Merge 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: Fix out of scope variable access in sched_slice() sched: Hide runqueues from direct refer at source code level sched: Remove unneeded __ref tag sched, x86: Fix cpufreq + sched_clock() TSC scaling
2009-06-20Merge branch 'tracing-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (24 commits) tracing/urgent: warn in case of ftrace_start_up inbalance tracing/urgent: fix unbalanced ftrace_start_up function-graph: add stack frame test function-graph: disable when both x86_32 and optimize for size are configured ring-buffer: have benchmark test print to trace buffer ring-buffer: do not grab locks in nmi ring-buffer: add locks around rb_per_cpu_empty ring-buffer: check for less than two in size allocation ring-buffer: remove useless compile check for buffer_page size ring-buffer: remove useless warn on check ring-buffer: use BUF_PAGE_HDR_SIZE in calculating index tracing: update sample event documentation tracing/filters: fix race between filter setting and module unload tracing/filters: free filter_string in destroy_preds() ring-buffer: use commit counters for commit pointer accounting ring-buffer: remove unused variable ring-buffer: have benchmark test handle discarded events ring-buffer: prevent adding write in discarded area tracing/filters: strloc should be unsigned short tracing/filters: operand can be negative ... Fix up kmemcheck-induced conflict in kernel/trace/ring_buffer.c manually
2009-06-20Merge 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: NOHZ: Properly feed cpufreq ondemand governor
2009-06-20Merge branch 'tip/tracing/urgent-1' of ↵Ingo Molnar
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/urgent
2009-06-20Merge branch 'tip/tracing/urgent' of ↵Ingo Molnar
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/urgent
2009-06-20perf_counter: Push perf_sample_data through the swcounter codePeter Zijlstra
Push the perf_sample_data further outwards to the swcounter interface, to abstract it away some more. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-20tracing/urgent: warn in case of ftrace_start_up inbalanceFrederic Weisbecker
Prevent from further ftrace_start_up inbalances so that we avoid future nop patching omissions with dynamic ftrace. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2009-06-20tracing/urgent: fix unbalanced ftrace_start_upFrederic Weisbecker
Perfcounter reports the following stats for a wide system profiling: # # (2364 samples) # # Overhead Symbol # ........ ...... # 15.40% [k] mwait_idle_with_hints 8.29% [k] read_hpet 5.75% [k] ftrace_caller 3.60% [k] ftrace_call [...] This snapshot has been taken while neither the function tracer nor the function graph tracer was running. With dynamic ftrace, such results show a wrong ftrace behaviour because all calls to ftrace_caller or ftrace_graph_caller (the patched calls to mcount) are supposed to be patched into nop if none of those tracers are running. The problem occurs after the first run of the function tracer. Once we launch it a second time, the callsites will never be nopped back, unless you set custom filters. For example it happens during the self tests at boot time. The function tracer selftest runs, and then the dynamic tracing is tested too. After that, the callsites are left un-nopped. This is because the reset callback of the function tracer tries to unregister two ftrace callbacks in once: the common function tracer and the function tracer with stack backtrace, regardless of which one is currently in use. It then creates an unbalance on ftrace_start_up value which is expected to be zero when the last ftrace callback is unregistered. When it reaches zero, the FTRACE_DISABLE_CALLS is set on the next ftrace command, triggering the patching into nop. But since it becomes unbalanced, ie becomes lower than zero, if the kernel functions are patched again (as in every further function tracer runs), they won't ever be nopped back. Note that ftrace_call and ftrace_graph_call are still patched back to ftrace_stub in the off case, but not the callers of ftrace_call and ftrace_graph_caller. It means that the tracing is well deactivated but we waste a useless call into every kernel function. This patch just unregisters the right ftrace_ops for the function tracer on its reset callback and ignores the other one which is not registered, fixing the unbalance. The problem also happens is .30 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: stable@kernel.org
2009-06-19ptrace: wait_task_zombie: do not account traced sub-threadsOleg Nesterov
The bug is ancient. If we trace the sub-thread of our natural child and this sub-thread exits, we update parent->signal->cxxx fields. But we should not do this until the whole thread-group exits, otherwise we account this thread (and all other live threads) twice. Add the task_detached() check. No need to check thread_group_empty(), wait_consider_task()->delay_group_leader() already did this. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Roland McGrath <roland@redhat.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Vitaly Mayatskikh <vmayatsk@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-19perf_counter: Close race in perf_lock_task_context()Peter Zijlstra
perf_lock_task_context() is buggy because it can return a dead context. the RCU read lock in perf_lock_task_context() only guarantees the memory won't get freed, it doesn't guarantee the object is valid (in our case refcount > 0). Therefore we can return a locked object that can get freed the moment we release the rcu read lock. perf_pin_task_context() then increases the refcount and does an unlock on freed memory. That increased refcount will cause a double free, in case it started out with 0. Ammend this by including the get_ctx() functionality in perf_lock_task_context() (all users already did this later anyway), and return a NULL context when the found one is already dead. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-19perf_counter: Simplify and fix task migration countingPeter Zijlstra
The task migrations counter was causing rare and hard to decypher memory corruptions under load. After a day of debugging and bisection we found that the problem was introduced with: 3f731ca: perf_counter: Fix cpu migration counter Turning them off fixes the crashes. Incidentally, the whole perf_counter_task_migration() logic can be done simpler as well, by injecting a proper sw-counter event. This cleanup also fixed the crashes. The precise failure mode is not completely clear yet, but we are clearly not unhappy about having a fix ;-) Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-18function-graph: add stack frame testSteven Rostedt
In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18function-graph: disable when both x86_32 and optimize for size are configuredSteven Rostedt
On x86_32, when optimize for size is set, gcc may align the frame pointer and make a copy of the the return address inside the stack frame. The return address that is located in the stack frame may not be the one used to return to the calling function. This will break the function graph tracer. The function graph tracer replaces the return address with a jump to a hook function that can trace the exit of the function. If it only replaces a copy, then the hook will not be called when the function returns. Worse yet, when the parent function returns, the function graph tracer will return back to the location of the child function which will easily crash the kernel with weird results. To see the problem, when i386 is compiled with -Os we get: c106be03: 57 push %edi c106be04: 8d 7c 24 08 lea 0x8(%esp),%edi c106be08: 83 e4 e0 and $0xffffffe0,%esp c106be0b: ff 77 fc pushl 0xfffffffc(%edi) c106be0e: 55 push %ebp c106be0f: 89 e5 mov %esp,%ebp c106be11: 57 push %edi c106be12: 56 push %esi c106be13: 53 push %ebx c106be14: 81 ec 8c 00 00 00 sub $0x8c,%esp c106be1a: e8 f5 57 fb ff call c1021614 <mcount> When it is compiled with -O2 instead we get: c10896f0: 55 push %ebp c10896f1: 89 e5 mov %esp,%ebp c10896f3: 83 ec 28 sub $0x28,%esp c10896f6: 89 5d f4 mov %ebx,0xfffffff4(%ebp) c10896f9: 89 75 f8 mov %esi,0xfffffff8(%ebp) c10896fc: 89 7d fc mov %edi,0xfffffffc(%ebp) c10896ff: e8 d0 08 fa ff call c1029fd4 <mcount> The compile with -Os will align the stack pointer then set up the frame pointer (%ebp), and it copies the return address back into the stack frame. The change to the return address in mcount is done to the copy and not the real place holder of the return address. Then compile with -O2 sets up the frame pointer first, this makes the change to the return address by mcount affect where the function will jump on exit. Reported-by: Jake Edge <jake@lwn.net> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-18gcov: enable GCOV_PROFILE_ALL for x86_64Peter Oberparleiter
Enable gcov profiling of the entire kernel on x86_64. Required changes include disabling profiling for: * arch/kernel/acpi/realmode and arch/kernel/boot/compressed: not linked to main kernel * arch/vdso, arch/kernel/vsyscall_64 and arch/kernel/hpet: profiling causes segfaults during boot (incompatible context) Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Li Wei <W.Li@Sun.COM> Cc: Michael Ellerman <michaele@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Heiko Carstens <heicars2@linux.vnet.ibm.com> Cc: Martin Schwidefsky <mschwid2@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: WANG Cong <xiyou.wangcong@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18gcov: add gcov profiling infrastructurePeter Oberparleiter
Enable the use of GCC's coverage testing tool gcov [1] with the Linux kernel. gcov may be useful for: * debugging (has this code been reached at all?) * test improvement (how do I change my test to cover these lines?) * minimizing kernel configurations (do I need this option if the associated code is never run?) The profiling patch incorporates the following changes: * change kbuild to include profiling flags * provide functions needed by profiling code * present profiling data as files in debugfs Note that on some architectures, enabling gcc's profiling option "-fprofile-arcs" for the entire kernel may trigger compile/link/ run-time problems, some of which are caused by toolchain bugs and others which require adjustment of architecture code. For this reason profiling the entire kernel is initially restricted to those architectures for which it is known to work without changes. This restriction can be lifted once an architecture has been tested and found compatible with gcc's profiling. Profiling of single files or directories is still available on all platforms (see config help text). [1] http://gcc.gnu.org/onlinedocs/gcc/Gcov.html Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Li Wei <W.Li@Sun.COM> Cc: Michael Ellerman <michaele@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Heiko Carstens <heicars2@linux.vnet.ibm.com> Cc: Martin Schwidefsky <mschwid2@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: WANG Cong <xiyou.wangcong@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18kernel: constructor supportPeter Oberparleiter
Call constructors (gcc-generated initcall-like functions) during kernel start and module load. Constructors are e.g. used for gcov data initialization. Disable constructor support for usermode Linux to prevent conflicts with host glibc. Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Acked-by: WANG Cong <xiyou.wangcong@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Li Wei <W.Li@Sun.COM> Cc: Michael Ellerman <michaele@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Heiko Carstens <heicars2@linux.vnet.ibm.com> Cc: Martin Schwidefsky <mschwid2@linux.vnet.ibm.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18nsproxy: extract create_nsproxy()Alexey Dobriyan
clone_nsproxy() does useless copying of old nsproxy -- every pointer will be rewritten to new ns or to old ns. Remove copying, rename clone_nsproxy(), create_nsproxy() will be used by C/R code to create fresh nsproxy on restart. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18utsns: extract creeate_uts_ns()Alexey Dobriyan
create_uts_ns() will be used by C/R to create fresh uts_ns. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18pidns: rewrite copy_pid_ns()Alexey Dobriyan
copy_pid_ns() is a perfect example of a case where unwinding leads to more code and makes it less clear. Watch the diffstat. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Reviewed-by: Serge Hallyn <serue@us.ibm.com> Acked-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18pidns: make create_pid_namespace() accept parent pidnsAlexey Dobriyan
create_pid_namespace() creates everything, but caller has to assign parent pidns by hand, which is unnatural. At the moment of call new ->level has to be taken from somewhere and parent pidns is already available. Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Serge Hallyn <serue@us.ibm.com> Acked-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18pids: clean up find_task_by_pid variantsChristoph Hellwig
find_task_by_pid_type_ns is only used to implement find_task_by_vpid and find_task_by_pid_ns, but both of them pass PIDTYPE_PID as first argument. So just fold find_task_by_pid_type_ns into find_task_by_pid_ns and use find_task_by_pid_ns to implement find_task_by_vpid. While we're at it also remove the exports for find_task_by_pid_ns and find_task_by_vpid - we don't have any modular callers left as the only modular caller of he old pre pid namespace find_task_by_pid (gfs2) was switched to pid_task which operates on a struct pid pointer instead of a pid_t. Given the confusion about pid_t values vs namespace that's generally the better option anyway and I think we're better of restricting modules to do it that way. Signed-off-by: Christoph Hellwig <hch@lst.de> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18sysctl.c: remove unused variableSukanto Ghosh
Remoce the unused variable 'val' from __do_proc_dointvec() The integer has been declared and used as 'val = -val' and there is no reference to it anywhere. Signed-off-by: Sukanto Ghosh <sukanto.cse.iitb@gmail.com> Cc: Jaswinder Singh Rajput <jaswinder@kernel.org> Cc: Sukanto Ghosh <sukanto.cse.iitb@gmail.com> Cc: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18kthreads: simplify migration_thread() exit pathOleg Nesterov
Now that kthread_stop() can be used even if the task has already exited, we can kill the "wait_to_die:" loop in migration_thread(). But we must pin rq->migration_thread after creation. Actually, I don't think CPU_UP_CANCELED or CPU_DEAD should wait for ->migration_thread exit. Perhaps we can simplify this code a bit more. migration_call() can set ->should_stop and forget about this thread. But we need a new helper in kthred.c for that. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Vitaliy Gusev <vgusev@openvz.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18kthreads: rework kthread_stop()Oleg Nesterov
Based on Eric's patch which in turn was based on my patch. kthread_stop() has the nasty problems: - it runs unpredictably long with the global semaphore held. - it deadlocks if kthread itself does kthread_stop() before it obeys the kthread_should_stop() request. - it is not useable if kthread exits on its own, see for example the ugly "wait_to_die:" hack in migration_thread() - it is not possible to just tell kthread it should stop, we must always wait for its exit. With this patch kthread() allocates all neccesary data (struct kthread) on its own stack, globals kthread_stop_xxx are deleted. ->vfork_done is used as a pointer into "struct kthread", this means kthread_stop() can easily wait for kthread's exit. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Vitaliy Gusev <vgusev@openvz.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18kthreads: simplify the startup synchronizationOleg Nesterov
We use two completions two create the kernel thread, this is a bit ugly. kthread() wakes up create_kthread() via ->started, then create_kthread() wakes up the caller kthread_create() via ->done. But kthread() does not need to wait for kthread(), it can just return. Instead kthread() itself can wake up the caller of kthread_create(). Kill kthread_create_info->started, ->done is enough. This improves the scalability a bit and sijmplifies the code. The only problem if kernel_thread() fails, in that case create_kthread() must do complete(&create->done). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Vitaliy Gusev <vgusev@openvz.org Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18mm: exit.c reorder wait_opts to remove padding on 64 bit buildsRichard Kennedy
Reorder struct wait_opts to remove 8 bytes of alignment padding on 64 bit builds. Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18do_wait: fix the theoretical race with stop/trace/contOleg Nesterov
do_wait: current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); ... search for the task to reap ... In theory, the ->state changing can leak into the critical section. Since the child can change its status under read_lock(tasklist) in parallel (finish_stop/ptrace_stop), we can miss the wakeup if __wake_up_parent() sees us in TASK_RUNNING state. Add the barrier. Also, use __set_current_state() to set TASK_RUNNING. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18do_wait: kill the old BUG_ON, use while_each_thread()Oleg Nesterov
do_wait() does BUG_ON(tsk->signal != current->signal), this looks like a raher obsolete check. At least, I don't think do_wait() is the best place to verify that all threads have the same ->signal. Remove it. Also, change the code to use while_each_thread(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18do_wait: simplify retval/tsk_result/notask_error messOleg Nesterov
Now that we don't pass &retval down to other helpers we can simplify the code more. - kill tsk_result, just use retval - add the "notask" label right after the main loop, and s/got end/goto notask/ after the fastpath pid check. This way we don't need to initialize retval before this check and the code becomes a bit more clean, if this pid has no attached tasks we should just skip the list search. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18introduce "struct wait_opts" to simplify do_wait() patchesOleg Nesterov
Introduce "struct wait_opts" which holds the parameters for misc helpers in do_wait() pathes. This adds 13 lines to kernel/exit.c, but saves 256 bytes from .o and imho makes the code much more readable. This patch temporary uglifies rusage/siginfo code a little bit, will be addressed by further cleanups. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reviewed-by: Ingo Molnar <mingo@elte.hu> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18shift "ptrace implies WUNTRACED" from ptrace_do_wait() to wait_task_stopped()Oleg Nesterov
No functional changes, preparation for the next patch. ptrace_do_wait() adds WUNTRACED to options for wait_task_stopped() which should always accept the stopped tracee, even if do_wait() was called without WUNTRACED. Change wait_task_stopped() to check "ptrace || WUNTRACED" instead. This makes the code more explicit, and "int options" argument becomes const in do_wait() pathes. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18copy_process(): remove the unneeded clear_tsk_thread_flag(TIF_SIGPENDING)Oleg Nesterov
The forked child can have TIF_SIGPENDING if it was copied from parent's ti->flags. But this is harmless and actually almost never happens, because copy_process() can't succeed if signal_pending() == T. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18wait_task_zombie: do not use thread_group_cputime()Oleg Nesterov
There is no reason for thread_group_cputime() in wait_task_zombie(), there must be no other threads. This call was previously needed to collect the per-cpu data which we do not have any longer. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Roland McGrath <roland@redhat.com> Cc: Stanislaw Gruszka <sgruszka@redhat.com> Cc: Vitaly Mayatskikh <vmayatsk@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: don't take tasklist to get/set ->last_siginfoOleg Nesterov
Change ptrace_getsiginfo/ptrace_setsiginfo to use lock_task_sighand() without tasklist_lock. Perhaps it makes sense to make a single helper with "bool rw" argument. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: do_notify_parent_cldstop: fix the wrong ->nsproxy usageOleg Nesterov
If the non-traced sub-thread calls do_notify_parent_cldstop(), we send the notification to group_leader->real_parent and we report group_leader's pid. But, if group_leader is traced we use the wrong ->parent->nsproxy->pid_ns, the tracer and parent can live in different namespaces. Change the code to use "parent" instead of tsk->parent. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> 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>
2009-06-18ptrace: wait_task_zombie: s/->parent/->real_parent/Oleg Nesterov
Change wait_task_zombie() to use ->real_parent instead of ->parent. We could even use current afaics, but ->real_parent is more clean. We know that the child is not ptrace_reparented() and thus they are equal. But we should avoid using task_struct->parent, we are going to remove it. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace_get_task_struct: s/tasklist/rcu/, make it staticOleg Nesterov
- Use rcu_read_lock() instead of tasklist_lock to find/get the task in ptrace_get_task_struct(). - Make it static, it has no callers outside of ptrace.c. - The comment doesn't match the reality, this helper does not do any checks. Beacuse it is really trivial and static I removed the whole comment. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: do not use task_lock() for attachOleg Nesterov
Remove the "Nasty, nasty" lock dance in ptrace_attach()/ptrace_traceme() - from now task_lock() has nothing to do with ptrace at all. With the recent changes nobody uses task_lock() to serialize with ptrace, but in fact it was never needed and it was never used consistently. However ptrace_attach() calls __ptrace_may_access() and needs task_lock() to pin task->mm for get_dumpable(). But we can call __ptrace_may_access() before we take tasklist_lock, ->cred_exec_mutex protects us against do_execve() path which can change creds and MMF_DUMP* flags. (ugly, but we can't use ptrace_may_access() because it hides the error code, so we have to take task_lock() and use __ptrace_may_access()). NOTE: this change assumes that LSM hooks, security_ptrace_may_access() and security_ptrace_traceme(), can be called without task_lock() held. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: cleanup check/set of PT_PTRACED during attachOleg Nesterov
ptrace_attach() and ptrace_traceme() are the last functions which look as if the untraced task can have task->ptrace != 0, this must not be possible. Change the code to just check ->ptrace != 0 and s/|=/=/ to set PT_PTRACED. Also, a couple of trivial whitespace cleanups in ptrace_attach(). And move ptrace_traceme() up near ptrace_attach() to keep them close to each other. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: ptrace_attach: check PF_KTHREAD + exit_state instead of ->mmOleg Nesterov
- Add PF_KTHREAD check to prevent attaching to the kernel thread with a borrowed ->mm. With or without this change we can race with daemonize() which can set PF_KTHREAD or clear ->mm after ptrace_attach() does the check, but this doesn't matter because reparent_to_kthreadd() does ptrace_unlink(). - Kill "!task->mm" check. We don't really care about ->mm != NULL, and the task can call exit_mm() right after we drop task_lock(). What we need is to make sure we can't attach after exit_notify(), check task->exit_state != 0 instead. Also, move the "already traced" check down for cosmetic reasons. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Chris Wright <chrisw@sous-sol.org> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: do not use task->ptrace directly in core kernelOleg Nesterov
No functional changes. - Nobody except ptrace.c & co should use ptrace flags directly, we have task_ptrace() for that. - No need to specially check PT_PTRACED, we must not have other PT_ bits set without PT_PTRACED. And no need to know this flag exists. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18ptrace: mm_need_new_owner: use ->real_parent to search in the siblingsOleg Nesterov
"Search in the siblings" should use ->real_parent, not ->parent. If the task is traced then ->parent == tracer, while the task's parent is always ->real_parent. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18allow_signal: kill the bogus ->mm check, add a note about CLONE_SIGHANDOleg Nesterov
allow_signal() checks ->mm == NULL. Not sure why. Perhaps to make sure current is the kernel thread. But this helper must not be used unless we are the kernel thread, kill this check. Also, document the fact that the CLONE_SIGHAND kthread must not use allow_signal(), unless the caller really wants to change the parent's ->sighand->action as well. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Acked-by: Roland McGrath <roland@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18memcg: add interface to reset limitsDaisuke Nishimura
We don't have an interface to reset mem.limit or memsw.limit now. This patch allows to reset mem.limit or memsw.limit when they are being set to -1. Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com> Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18cgroups: forbid noprefix if mounting more than just cpuset subsystemLi Zefan
The 'noprefix' option was introduced for backwards-compatibility of cpuset, but actually it can be used when mounting other subsystems. This results in possibility of name collision, and now the collision can really happen, because we have 'stat' file in both memory and cpuacct subsystem: # mount -t cgroup -o noprefix,memory,cpuacct xxx /mnt Cgroup will happily mount the 2 subsystems, but only 'stat' file of memory subsys can be seen. We don't want users to use nopreifx, and also want to avoid name collision, so we change to allow noprefix only if mounting just the cpuset subsystem. [akpm@linux-foundation.org: fix shift for cpuset_subsys_id >= 32] Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Paul Menage <menage@google.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18softirq: introduce statistics for softirqKeika Kobayashi
Statistics for softirq doesn't exist. It will be helpful like statistics for interrupts. This patch introduces counting the number of softirq, which will be exported in /proc/softirqs. When softirq handler consumes much CPU time, /proc/stat is like the following. $ while :; do cat /proc/stat | head -n1 ; sleep 10 ; done cpu 88 0 408 739665 583 28 2 0 0 cpu 450 0 1090 740970 594 28 1294 0 0 ^^^^ softirq In such a situation, /proc/softirqs shows us which softirq handler is invoked. We can see the increase rate of softirqs. <before> $ cat /proc/softirqs CPU0 CPU1 CPU2 CPU3 HI 0 0 0 0 TIMER 462850 462805 462782 462718 NET_TX 0 0 0 365 NET_RX 2472 2 2 40 BLOCK 0 0 381 1164 TASKLET 0 0 0 224 SCHED 462654 462689 462698 462427 RCU 3046 2423 3367 3173 <after> $ cat /proc/softirqs CPU0 CPU1 CPU2 CPU3 HI 0 0 0 0 TIMER 463361 465077 465056 464991 NET_TX 53 0 1 365 NET_RX 3757 2 2 40 BLOCK 0 0 398 1170 TASKLET 0 0 0 224 SCHED 463074 464318 464612 463330 RCU 3505 2948 3947 3673 When CPU TIME of softirq is high, the rates of increase is the following. TIMER : 220/sec : CPU1-3 NET_TX : 5/sec : CPU0 NET_RX : 120/sec : CPU0 SCHED : 40-200/sec : all CPU RCU : 45-58/sec : all CPU The rates of increase in an idle mode is the following. TIMER : 250/sec SCHED : 250/sec RCU : 2/sec It seems many softirqs for receiving packets and rcu are invoked. This gives us help for checking system. Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp> Reviewed-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Eric Dumazet <dada1@cosmosbay.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-18perf_counter: Add event overlow handlingPeter Zijlstra
Alternative method of mmap() data output handling that provides better overflow management and a more reliable data stream. Unlike the previous method, that didn't have any user->kernel feedback and relied on userspace keeping up, this method relies on userspace writing its last read position into the control page. It will ensure new output doesn't overwrite not-yet read events, new events for which there is no space left are lost and the overflow counter is incremented, providing exact event loss numbers. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-17ring-buffer: have benchmark test print to trace bufferSteven Rostedt
Currently the output of the ring buffer benchmark/test prints to the console. This test runs for ten seconds every ten seconds and ouputs the result after every iteration. This needlessly fills up the logs. This patch makes the ring buffer benchmark/test print to the ftrace buffer using trace_printk. To view the test results, you must examine the debug/tracing/trace file. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-17ring-buffer: do not grab locks in nmiSteven Rostedt
If ftrace_dump_on_oops is set, and an NMI detects a lockup, then it will need to read from the ring buffer. But the read side of the ring buffer still takes locks. This patch adds a check on the read side that if it is in an NMI, then it will disable the ring buffer and not take any locks. Reads can still happen on a disabled ring buffer. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>