An error occurred fetching the project authors.
- 20 Aug, 2010 8 commits
-
-
Paul E. McKenney authored
The CONFIG_PREEMPT_RCU kernel configuration parameter was recently re-introduced, but as an indication of the type of RCU (preemptible vs. non-preemptible) instead of as selecting a given implementation. This commit uses CONFIG_PREEMPT_RCU to combine duplicate code from include/linux/rcutiny.h and include/linux/rcutree.h into include/linux/rcupdate.h. This commit also combines a few other pieces of duplicate code that have accumulated. Signed-off-by:Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
Paul E. McKenney authored
Combine the duplicate definitions of ULONG_CMP_GE(), ULONG_CMP_LT(), and rcu_preempt_depth() into include/linux/rcupdate.h. Signed-off-by: -
Paul E. McKenney authored
The comment says that blocking is illegal in rcu_read_lock()-style RCU read-side critical sections, which is no longer entirely true given preemptible RCU. This commit provides a fix. Suggested-by:
David Miller <davem@davemloft.net> Signed-off-by:
-
Paul E. McKenney authored
Implement a small-memory-footprint uniprocessor-only implementation of preemptible RCU. This implementation uses but a single blocked-tasks list rather than the combinatorial number used per leaf rcu_node by TREE_PREEMPT_RCU, which reduces memory consumption and greatly simplifies processing. This version also takes advantage of uniprocessor execution to accelerate grace periods in the case where there are no readers. The general design is otherwise broadly similar to that of TREE_PREEMPT_RCU. This implementation is a step towards having RCU implementation driven off of the SMP and PREEMPT kernel configuration variables, which can happen once this implementation has accumulated sufficient experience. Removed ACCESS_ONCE() from __rcu_read_unlock() and added barrier() as suggested by Steve Rostedt in order to avoid the compiler-reordering issue noted by Mathieu Desnoyers (http://lkml.org/lkml/2010/8/16/183). As can be seen below, CONFIG_TINY_PREEMPT_RCU represents almost 5Kbyte savings compared to CONFIG_TREE_PREEMPT_RCU. Of course, for non-real-time workloads, CONFIG_TINY_RCU is even better. CONFIG_TREE_PREEMPT_RCU text data bss dec filename 13 0 0 13 kernel/rcupdate.o 6170 825 28 7023 kernel/rcutree.o ---- 7026 Total CONFIG_TINY_PREEMPT_RCU text data bss dec filename 13 0 0 13 kernel/rcupdate.o 2081 81 8 2170 kernel/rcutiny.o ---- 2183 Total CONFIG_TINY_RCU (non-preemptible) text data bss dec filename 13 0 0 13 kernel/rcupdate.o 719 25 0 744 kernel/rcutiny.o --- 757 Total Requested-by:
Loïc Minier <loic.minier@canonical.com> Signed-off-by:
-
Mathieu Desnoyers authored
RCU heads really don't need to be initialized. Their state before call_rcu() really does not matter. We need to keep init/destroy_rcu_head_on_stack() though, since we want debugobjects to be able to keep track of these objects. Signed-off-by:
Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by:
Mathieu Desnoyers <mathieu.desnoyers@efficios.com> CC: David S. Miller <davem@davemloft.net> CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> CC: akpm@linux-foundation.org CC: mingo@elte.hu CC: laijs@cn.fujitsu.com CC: dipankar@in.ibm.com CC: josh@joshtriplett.org CC: dvhltc@us.ibm.com CC: niv@us.ibm.com CC: tglx@linutronix.de CC: peterz@infradead.org CC: rostedt@goodmis.org CC: Valdis.Kletnieks@vt.edu CC: dhowells@redhat.com CC: eric.dumazet@gmail.com CC: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by:
Josh Triplett <josh@joshtriplett.org>
-
Paul E. McKenney authored
Make it explicit that new RCU read-side critical sections that start after call_rcu() and synchronize_rcu() start might still be running after the end of the relevant grace period. Signed-off-by:
-
Tetsuo Handa authored
find_task_by_vpid() says "Must be called under rcu_read_lock().". But due to commit 3120438a "rcu: Disable lockdep checking in RCU list-traversal primitives", we are currently unable to catch "find_task_by_vpid() with tasklist_lock held but RCU lock not held" errors due to the RCU-lockdep checks being suppressed in the RCU variants of the struct list_head traversals. This commit therefore places an explicit check for being in an RCU read-side critical section in find_task_by_pid_ns(). =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- kernel/pid.c:386 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 1 1 lock held by rc.sysinit/1102: #0: (tasklist_lock){.+.+..}, at: [<c1048340>] sys_setpgid+0x40/0x160 stack backtrace: Pid: 1102, comm: rc.sysinit Not tainted 2.6.35-rc3-dirty #1 Call Trace: [<c105e714>] lockdep_rcu_dereference+0x94/0xb0 [<c104b4cd>] find_task_by_pid_ns+0x6d/0x70 [<c104b4e8>] find_task_by_vpid+0x18/0x20 [<c1048347>] sys_setpgid+0x47/0x160 [<c1002b50>] sysenter_do_call+0x12/0x36 Commit updated to use a new rcu_lockdep_assert() exported API rather than the old internal __do_rcu_dereference(). Signed-off-by:
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by:
-
Paul E. McKenney authored
This commit provides definitions for the __rcu annotation defined earlier. This annotation permits sparse to check for correct use of RCU-protected pointers. If a pointer that is annotated with __rcu is accessed directly (as opposed to via rcu_dereference(), rcu_assign_pointer(), or one of their variants), sparse can be made to complain. To enable such complaints, use the new default-disabled CONFIG_SPARSE_RCU_POINTER kernel configuration option. Please note that these sparse complaints are intended to be a debugging aid, -not- a code-style-enforcement mechanism. There are special rcu_dereference_protected() and rcu_access_pointer() accessors for use when RCU read-side protection is not required, for example, when no other CPU has access to the data structure in question or while the current CPU hold the update-side lock. This patch also updates a number of docbook comments that were showing their age. Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
- 14 Jun, 2010 2 commits
-
-
Paul E. McKenney authored
The sparse RCU-pointer checking relies on type magic that dereferences the pointer in question. This does not work if the pointer is in fact an array index. This commit therefore supplies a new RCU API that omits the sparse checking to continue to support rcu_dereference() on integers. Signed-off-by: -
Mathieu Desnoyers authored
Helps finding racy users of call_rcu(), which results in hangs because list entries are overwritten and/or skipped. Changelog since v4: - Bissectability is now OK - Now generate a WARN_ON_ONCE() for non-initialized rcu_head passed to call_rcu(). Statically initialized objects are detected with object_is_static(). - Rename rcu_head_init_on_stack to init_rcu_head_on_stack. - Remove init_rcu_head() completely. Changelog since v3: - Include comments from Lai Jiangshan This new patch version is based on the debugobjects with the newly introduced "active state" tracker. Non-initialized entries are all considered as "statically initialized". An activation fixup (triggered by call_rcu()) takes care of performing the debug object initialization without issuing any warning. Since we cannot increase the size of struct rcu_head, I don't see much room to put an identifier for statically initialized rcu_head structures. So for now, we have to live without "activation without explicit init" detection. But the main purpose of this debug option is to detect double-activations (double call_rcu() use of a rcu_head before the callback is executed), which is correctly addressed here. This also detects potential internal RCU callback corruption, which would cause the callbacks to be executed twice. Signed-off-by:
Lai Jiangshan <laijs@cn.fujitsu.com>
-
- 10 May, 2010 6 commits
-
-
Mathieu Desnoyers authored
PEM: o Would it be possible to make this bisectable as follows? a. Insert a new patch after current patch 4/6 that defines destroy_rcu_head_on_stack(), init_rcu_head_on_stack(), and init_rcu_head() with their !CONFIG_DEBUG_OBJECTS_RCU_HEAD definitions. This patch performs this transition. Signed-off-by: -
Paul E. McKenney authored
TINY_RCU does not need rcu_scheduler_active unless CONFIG_DEBUG_LOCK_ALLOC. So conditionally compile rcu_scheduler_active in order to slim down rcutiny a bit more. Also gets rid of an EXPORT_SYMBOL_GPL, which is responsible for most of the slimming. Signed-off-by: -
Paul E. McKenney authored
Because synchronize_rcu_bh() is identical to synchronize_sched(), make the former a static inline invoking the latter, saving the overhead of an EXPORT_SYMBOL_GPL() and the duplicate code. Signed-off-by: -
Paul E. McKenney authored
The rcu_scheduler_active check has been wrapped into the new debug_lockdep_rcu_enabled() function, so update the comments to reflect this new reality. Signed-off-by: -
Paul E. McKenney authored
It is CONFIG_DEBUG_LOCK_ALLOC rather than CONFIG_PROVE_LOCKING, so fix it. Signed-off-by: -
Lai Jiangshan authored
There is no need to disable lockdep after an RCU lockdep splat, so remove the debug_lockdeps_off() from lockdep_rcu_dereference(). To avoid repeated lockdep splats, use a static variable in the inlined rcu_dereference_check() and rcu_dereference_protected() macros so that a given instance splats only once, but so that multiple instances can be detected per boot. This is controlled by a new config variable CONFIG_PROVE_RCU_REPEATEDLY, which is disabled by default. This provides the normal lockdep behavior by default, but permits people who want to find multiple RCU-lockdep splats per boot to easily do so. Requested-by:
Eric Paris <eparis@redhat.com> Signed-off-by:
-
- 06 May, 2010 1 commit
-
-
Paul E. McKenney authored
Some RCU-lockdep splat repairs need to know whether they are running in a single-threaded process. Unfortunately, the thread_group_empty() primitive is defined in sched.h, and can induce #include hell. This commit therefore introduces a rcu_my_thread_group_empty() wrapper that is defined in rcupdate.c, thus avoiding the need to include sched.h everywhere. Signed-off-by:
-
- 19 Apr, 2010 1 commit
-
-
Paul E. McKenney authored
The lockdep facility temporarily disables lockdep checking by incrementing the current->lockdep_recursion variable. Such disabling happens in NMIs and in other situations where lockdep might expect to recurse on itself. This patch therefore checks current->lockdep_recursion, disabling RCU lockdep splats when this variable is non-zero. In addition, this patch removes the "likely()", as suggested by Lai Jiangshan. Reported-by:
Frederic Weisbecker <fweisbec@gmail.com> Reported-by:
Ingo Molnar <mingo@elte.hu>
-
- 14 Apr, 2010 2 commits
-
-
David Howells authored
Better explain the condition parameter of rcu_dereference_check() that describes the conditions under which the dereference is permitted to take place (and incorporate Yong Zhang's suggestion). This condition is only checked under lockdep proving. Signed-off-by:
David Howells <dhowells@redhat.com> Signed-off-by:
-
Paul E. McKenney authored
This patch adds variants of rcu_dereference() that handle situations where the RCU-protected data structure cannot change, perhaps due to our holding the update-side lock, or where the RCU-protected pointer is only to be fetched, not dereferenced. These are needed due to some performance concerns with using rcu_dereference() where it is not required, aside from the need for lockdep/sparse checking. The new rcu_access_pointer() primitive is for the case where the pointer is be fetch and not dereferenced. This primitive may be used without protection, RCU or otherwise, due to the fact that it uses ACCESS_ONCE(). The new rcu_dereference_protected() primitive is for the case where updates are prevented, for example, due to holding the update-side lock. This primitive does neither ACCESS_ONCE() nor smp_read_barrier_depends(), so can only be used when updates are somehow prevented. Suggested-by:
-
- 18 Mar, 2010 1 commit
-
-
Lai Jiangshan authored
It is documented that local_irq_disable() also delimits RCU_SCHED read-site critical sections. See the document of synchronize_sched() or Documentation/RCU/whatisRCU.txt. So we have to test irqs_disabled() in rcu_read_lock_sched_held(). Otherwise rcu-lockdep brings incorrect complaint. Signed-off-by:
-
- 16 Mar, 2010 1 commit
-
-
Paul E. McKenney authored
Disabling BH can stand in for rcu_read_lock_bh(), and this patch updates rcu_read_lock_bh_held() to allow for this. In order to avoid include-file hell, this function is moved out of line to kernel/rcupdate.c. This fixes a false positive RCU warning. Reported-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
-
- 12 Mar, 2010 1 commit
-
-
Dave Young authored
Extern declarations in sysctl.c should be moved to their own header file, and then include them in relavant .c files. Move rcutorture_runnable extern declaration to linux/rcupdate.h Signed-off-by:
Dave Young <hidave.darkstar@gmail.com> Acked-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
- 04 Mar, 2010 2 commits
-
-
Paul E. McKenney authored
RCU is used during very early boot, before RCU and lockdep have been initialized. So make the underlying primitives (rcu_read_lock_held(), rcu_read_lock_bh_held(), rcu_read_lock_sched_held(), and rcu_dereference_check()) check for early boot via the rcu_scheduler_active flag. This will suppress false positives. Also introduce a debug_lockdep_rcu_enabled() static inline helper function, which tags the CONTINUE_PROVE_RCU case as likely(), as suggested by Ingo Molnar. Signed-off-by:
-
Paul E. McKenney authored
The rcu_read_lock_sched_held() needs to unconditionally return the value "1" in a !PREEMPT kernel, because under !PREEMPT, -all- kernel code is implicitly preempt-disabled. This patch makes this happen. Signed-off-by:
-
- 27 Feb, 2010 1 commit
-
-
Paul E. McKenney authored
Before the scheduler starts, all tasks are non-preemptible by definition. So, during that time, rcu_read_lock_sched_held() needs to always return "true". This patch makes that be so for RCU_PROVE_LOCKING=n. Signed-off-by:
-
- 26 Feb, 2010 1 commit
-
-
Paul E. McKenney authored
Before the scheduler starts, all tasks are non-preemptible by definition. So, during that time, rcu_read_lock_sched_held() needs to always return "true". This patch makes that be so. Signed-off-by:
-
- 25 Feb, 2010 3 commits
-
-
Paul E. McKenney authored
Make rcu_dereference_check() print the list of held locks in addition to the stack dump to ease debugging. Signed-off-by:
-
Paul E. McKenney authored
Make rcu_dereference() check for being in an RCU read-side critical section, and create rcu_dereference_bh(), rcu_dereference_sched(), and srcu_dereference() to check for the other flavors of RCU. Also create rcu_dereference_raw() to avoid checking, and make rcu_dereference_check() use rcu_dereference_raw(). Acked-by:
-
Paul E. McKenney authored
Inspection is proving insufficient to catch all RCU misuses, which is understandable given that rcu_dereference() might be protected by any of four different flavors of RCU (RCU, RCU-bh, RCU-sched, and SRCU), and might also/instead be protected by any of a number of locking primitives. It is therefore time to enlist the aid of lockdep. This set of patches is inspired by earlier work by Peter Zijlstra and Thomas Gleixner, and takes the following approach: o Set up separate lockdep classes for RCU, RCU-bh, and RCU-sched. o Set up separate lockdep classes for each instance of SRCU. o Create primitives that check for being in an RCU read-side critical section. These return exact answers if lockdep is fully enabled, but if unsure, report being in an RCU read-side critical section. (We want to avoid false positives!) The primitives are: For RCU: rcu_read_lock_held(void) For RCU-bh: rcu_read_lock_bh_held(void) For RCU-sched: rcu_read_lock_sched_held(void) For SRCU: srcu_read_lock_held(struct srcu_struct *sp) o Add rcu_dereference_check(), which takes a second argument in which one places a boolean expression based on the above primitives and/or lockdep_is_held(). o A new kernel configuration parameter, CONFIG_PROVE_RCU, enables rcu_dereference_check(). This depends on CONFIG_PROVE_LOCKING, and should be quite helpful during the transition period while CONFIG_PROVE_RCU-unaware patches are in flight. The existing rcu_dereference() primitive does no checking, but upcoming patches will change that. Signed-off-by:
-
- 22 Nov, 2009 1 commit
-
-
Paul E. McKenney authored
Remove #ifdefs from kernel/rcupdate.c and include/linux/rcupdate.h by moving code to include/linux/rcutiny.h, include/linux/rcutree.h, and kernel/rcutree.c. Also remove some definitions that are no longer used. Signed-off-by:
-
- 27 Oct, 2009 1 commit
-
-
Paul E. McKenney authored
Some compilers are happy with "#elif CONFIG_RCU_TINY", while others strongly prefer "#elif defined(CONFIG_RCU_TINY)". Change to the latter to make more compilers happy. Signed-off-by:
-
- 26 Oct, 2009 1 commit
-
-
Paul E. McKenney authored
This patch is a version of RCU designed for !SMP provided for a small-footprint RCU implementation. In particular, the implementation of synchronize_rcu() is extremely lightweight and high performance. It passes rcutorture testing in each of the four relevant configurations (combinations of NO_HZ and PREEMPT) on x86. This saves about 1K bytes compared to old Classic RCU (which is no longer in mainline), and more than three kilobytes compared to Hierarchical RCU (updated to 2.6.30): CONFIG_TREE_RCU: text data bss dec filename 183 4 0 187 kernel/rcupdate.o 2783 520 36 3339 kernel/rcutree.o 3526 Total (vs 4565 for v7) CONFIG_TREE_PREEMPT_RCU: text data bss dec filename 263 4 0 267 kernel/rcupdate.o 4594 776 52 5422 kernel/rcutree.o 5689 Total (6155 for v7) CONFIG_TINY_RCU: text data bss dec filename 96 4 0 100 kernel/rcupdate.o 734 24 0 758 kernel/rcutiny.o 858 Total (vs 848 for v7) The above is for x86. Your mileage may vary on other platforms. Further compression is possible, but is being procrastinated. Changes from v7 (http://lkml.org/lkml/2009/10/9/388) o Apply Lai Jiangshan's review comments (aside from might_sleep() in synchronize_sched(), which is covered by SMP builds). o Fix up expedited primitives. Changes from v6 (http://lkml.org/lkml/2009/9/23/293). o Forward ported to put it into the 2.6.33 stream. o Added lockdep support. o Make lightweight rcu_barrier. Changes from v5 (http://lkml.org/lkml/2009/6/23/12). o Ported to latest pre-2.6.32 merge window kernel. - Renamed rcu_qsctr_inc() to rcu_sched_qs(). - Renamed rcu_bh_qsctr_inc() to rcu_bh_qs(). - Provided trivial rcu_cpu_notify(). - Provided trivial exit_rcu(). - Provided trivial rcu_needs_cpu(). - Fixed up the rcu_*_enter/exit() functions in linux/hardirq.h. o Removed the dependence on EMBEDDED, with a view to making TINY_RCU default for !SMP at some time in the future. o Added (trivial) support for expedited grace periods. Changes from v4 (http://lkml.org/lkml/2009/5/2/91) include: o Squeeze the size down a bit further by removing the ->completed field from struct rcu_ctrlblk. o This permits synchronize_rcu() to become the empty function. Previous concerns about rcutorture were unfounded, as rcutorture correctly handles a constant value from rcu_batches_completed() and rcu_batches_completed_bh(). Changes from v3 (http://lkml.org/lkml/2009/3/29/221) include: o Changed rcu_batches_completed(), rcu_batches_completed_bh() rcu_enter_nohz(), rcu_exit_nohz(), rcu_nmi_enter(), and rcu_nmi_exit(), to be static inlines, as suggested by David Howells. Doing this saves about 100 bytes from rcutiny.o. (The numbers between v3 and this v4 of the patch are not directly comparable, since they are against different versions of Linux.) Changes from v2 (http://lkml.org/lkml/2009/2/3/333) include: o Fix whitespace issues. o Change short-circuit "||" operator to instead be "+" in order to fix performance bug noted by "kraai" on LWN. (http://lwn.net/Articles/324348/) Changes from v1 (http://lkml.org/lkml/2009/1/13/440) include: o This version depends on EMBEDDED as well as !SMP, as suggested by Ingo. o Updated rcu_needs_cpu() to unconditionally return zero, permitting the CPU to enter dynticks-idle mode at any time. This works because callbacks can be invoked upon entry to dynticks-idle mode. o Paul is now OK with this being included, based on a poll at the Kernel Miniconf at linux.conf.au, where about ten people said that they cared about saving 900 bytes on single-CPU systems. o Applies to both mainline and tip/core/rcu. Signed-off-by:
-
- 05 Oct, 2009 1 commit
-
-
Paul E. McKenney authored
Whitespace fixes, updated comments, and trivial code movement. o Fix whitespace error in RCU_HEAD_INIT() o Move "So where is rcu_write_lock()" comment so that it does not come between the rcu_read_unlock() header comment and the rcu_read_unlock() definition. o Move the module_param statements for blimit, qhimark, and qlowmark to immediately follow the corresponding definitions. o In __rcu_offline_cpu(), move the assignment to rdp_me inside the "if" statement, given that rdp_me is not used outside of that "if" statement. Signed-off-by:
-
- 23 Sep, 2009 1 commit
-
-
Paul E. McKenney authored
These issues identified during an old-fashioned face-to-face code review extending over many hours. o Add comments for tricky parts of code, and correct comments that have passed their sell-by date. o Get rid of the vestiges of rcu_init_sched(), which is no longer needed now that PREEMPT_RCU is gone. o Move the #include of rcutree_plugin.h to the end of rcutree.c, which means that, rather than having a random collection of forward declarations, the new set of forward declarations document the set of plugins. The new home for this #include also allows __rcu_init_preempt() to move into rcutree_plugin.h. o Fix rcu_preempt_check_callbacks() to be static. Suggested-by:
-
- 19 Sep, 2009 1 commit
-
-
Paul E. McKenney authored
Fix a number of whitespace ^Ierrors in the include/linux/rcu* and the kernel/rcu* files. Signed-off-by:
-
- 17 Sep, 2009 1 commit
-
-
Paul E. McKenney authored
The redirection of synchronize_sched() to synchronize_rcu() was appropriate for TREE_RCU, but not for TREE_PREEMPT_RCU. Fix this by creating an underlying synchronize_sched(). TREE_RCU then redirects synchronize_rcu() to synchronize_sched(), while TREE_PREEMPT_RCU has its own version of synchronize_rcu(). Signed-off-by:
-
- 26 Aug, 2009 1 commit
-
-
Paul E. McKenney authored
The lockdep annotations rcu_read_acquire() and rcu_read_release() might lead to infinite looping if called from lockdep. So this patch removes them. Formal repost of http://lkml.org/lkml/2009/8/25/309 on the strength of Lai Jiangshan's review. Suggested-by:
Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Reviewed-by:
-
- 24 Aug, 2009 1 commit
-
-
Paul E. McKenney authored
Both rcu_read_lock_sched_notrace() and rcu_read_unlock_sched_notrace() are used by ftrace, and thus need to be marked "notrace". Unfortunately, my naive assumption that gcc would see the inner "notrace" does not hold. Kudos to Lai Jiangshan for noting this. Reported-by:
-
- 23 Aug, 2009 1 commit
-
-
Paul E. McKenney authored
Now that CONFIG_TREE_PREEMPT_RCU is in place, there is no further need for CONFIG_PREEMPT_RCU. Remove it, along with whatever subtle bugs it may (or may not) contain. Signed-off-by:
-
