From 39d997b514e12d5aff0dca206eb8996b3957927e Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 21 Dec 2009 16:20:16 -0800 Subject: x86, core: Optimize hweight32() Optimize hweight32 by using the same technique in hweight64. The proof of this technique can be found in the commit log for f9b4192923fa6e38331e88214b1fe5fc21583fcc ("bitops: hweight() speedup"). The userspace benchmark on x86_32 showed 20% speedup with bitmap_weight() which uses hweight32 to count bits for each unsigned long on 32bit architectures. int main(void) { #define SZ (1024 * 1024 * 512) static DECLARE_BITMAP(bitmap, SZ) = { [0 ... 100] = 1, }; return bitmap_weight(bitmap, SZ); } Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Cc: Linus Torvalds LKML-Reference: <1258603932-4590-1-git-send-email-akinobu.mita@gmail.com> [ only x86 sets ARCH_HAS_FAST_MULTIPLIER so we do this via the x86 tree] Signed-off-by: Ingo Molnar --- lib/hweight.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'lib') diff --git a/lib/hweight.c b/lib/hweight.c index 389424ecb129..63ee4eb1228d 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -11,11 +11,18 @@ unsigned int hweight32(unsigned int w) { +#ifdef ARCH_HAS_FAST_MULTIPLIER + w -= (w >> 1) & 0x55555555; + w = (w & 0x33333333) + ((w >> 2) & 0x33333333); + w = (w + (w >> 4)) & 0x0f0f0f0f; + return (w * 0x01010101) >> 24; +#else unsigned int res = w - ((w >> 1) & 0x55555555); res = (res & 0x33333333) + ((res >> 2) & 0x33333333); res = (res + (res >> 4)) & 0x0F0F0F0F; res = res + (res >> 8); return (res + (res >> 16)) & 0x000000FF; +#endif } EXPORT_SYMBOL(hweight32); -- cgit v1.2.3 From 4c54005ca438a8b46dd542b497d4f0dc2ca375e8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 14 Jan 2010 16:10:57 -0800 Subject: rcu: 1Q2010 update for RCU documentation Add expedited functions. Review documentation and update obsolete verbiage. Also fix the advice for the RCU CPU-stall kernel configuration parameter, and document RCU CPU-stall warnings. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <12635142581866-git-send-email-> Signed-off-by: Ingo Molnar --- Documentation/RCU/00-INDEX | 8 +- Documentation/RCU/RTFP.txt | 58 +++++++- Documentation/RCU/checklist.txt | 200 ++++++++++++++++----------- Documentation/RCU/rcu.txt | 48 +------ Documentation/RCU/stallwarn.txt | 58 ++++++++ Documentation/RCU/torture.txt | 12 ++ Documentation/RCU/whatisRCU.txt | 3 +- Documentation/filesystems/dentry-locking.txt | 3 +- lib/Kconfig.debug | 4 +- 9 files changed, 258 insertions(+), 136 deletions(-) create mode 100644 Documentation/RCU/stallwarn.txt (limited to 'lib') diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 9bb62f7b89c3..0a27ea9621fa 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -8,14 +8,18 @@ listRCU.txt - Using RCU to Protect Read-Mostly Linked Lists NMI-RCU.txt - Using RCU to Protect Dynamic NMI Handlers +rcubarrier.txt + - RCU and Unloadable Modules +rculist_nulls.txt + - RCU list primitives for use with SLAB_DESTROY_BY_RCU rcuref.txt - Reference-count design for elements of lists/arrays protected by RCU rcu.txt - RCU Concepts -rcubarrier.txt - - Unloading modules that use RCU callbacks RTFP.txt - List of RCU papers (bibliography) going back to 1980. +stallwarn.txt + - RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR) torture.txt - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST) trace.txt diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index d2b85237c76e..5051209e6835 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -25,10 +25,10 @@ to be referencing the data structure. However, this mechanism was not optimized for modern computer systems, which is not surprising given that these overheads were not so expensive in the mid-80s. Nonetheless, passive serialization appears to be the first deferred-destruction -mechanism to be used in production. Furthermore, the relevant patent has -lapsed, so this approach may be used in non-GPL software, if desired. -(In contrast, use of RCU is permitted only in software licensed under -GPL. Sorry!!!) +mechanism to be used in production. Furthermore, the relevant patent +has lapsed, so this approach may be used in non-GPL software, if desired. +(In contrast, implementation of RCU is permitted only in software licensed +under either GPL or LGPL. Sorry!!!) In 1990, Pugh [Pugh90] noted that explicitly tracking which threads were reading a given data structure permitted deferred free to operate @@ -150,6 +150,18 @@ preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally, PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI]. +2008 saw a journal paper on real-time RCU [DinakarGuniguntala2008IBMSysJ], +a history of how Linux changed RCU more than RCU changed Linux +[PaulEMcKenney2008RCUOSR], and a design overview of hierarchical RCU +[PaulEMcKenney2008HierarchicalRCU]. + +2009 introduced user-level RCU algorithms [PaulEMcKenney2009MaliciousURCU], +which Mathieu Desnoyers is now maintaining [MathieuDesnoyers2009URCU] +[MathieuDesnoyersPhD]. TINY_RCU [PaulEMcKenney2009BloatWatchRCU] made +its appearance, as did expedited RCU [PaulEMcKenney2009expeditedRCU]. +The problem of resizeable RCU-protected hash tables may now be on a path +to a solution [JoshTriplett2009RPHash]. + Bibtex Entries @article{Kung80 @@ -730,6 +742,11 @@ Revised: " } +# +# "What is RCU?" LWN series. +# +######################################################################## + @article{DinakarGuniguntala2008IBMSysJ ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole" ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}" @@ -820,3 +837,36 @@ Revised: Uniprocessor assumptions allow simplified RCU implementation. " } + +@unpublished{PaulEMcKenney2009expeditedRCU +,Author="Paul E. McKenney" +,Title="[{PATCH} -tip 0/3] expedited 'big hammer' {RCU} grace periods" +,month="June" +,day="25" +,year="2009" +,note="Available: +\url{http://lkml.org/lkml/2009/6/25/306} +[Viewed August 16, 2009]" +,annotation=" + First posting of expedited RCU to be accepted into -tip. +" +} + +@unpublished{JoshTriplett2009RPHash +,Author="Josh Triplett" +,Title="Scalable concurrent hash tables via relativistic programming" +,month="September" +,year="2009" +,note="Linux Plumbers Conference presentation" +,annotation=" + RP fun with hash tables. +" +} + +@phdthesis{MathieuDesnoyersPhD +, title = "Low-impact Operating System Tracing" +, author = "Mathieu Desnoyers" +, school = "Ecole Polytechnique de Montr\'{e}al" +, month = "December" +, year = 2009 +} diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 51525a30e8b4..767cf06a4276 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -8,13 +8,12 @@ would cause. This list is based on experiences reviewing such patches over a rather long period of time, but improvements are always welcome! 0. Is RCU being applied to a read-mostly situation? If the data - structure is updated more than about 10% of the time, then - you should strongly consider some other approach, unless - detailed performance measurements show that RCU is nonetheless - the right tool for the job. Yes, you might think of RCU - as simply cutting overhead off of the readers and imposing it - on the writers. That is exactly why normal uses of RCU will - do much more reading than updating. + structure is updated more than about 10% of the time, then you + should strongly consider some other approach, unless detailed + performance measurements show that RCU is nonetheless the right + tool for the job. Yes, RCU does reduce read-side overhead by + increasing write-side overhead, which is exactly why normal uses + of RCU will do much more reading than updating. Another exception is where performance is not an issue, and RCU provides a simpler implementation. An example of this situation @@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome! If you choose #b, be prepared to describe how you have handled memory barriers on weakly ordered machines (pretty much all of - them -- even x86 allows reads to be reordered), and be prepared - to explain why this added complexity is worthwhile. If you - choose #c, be prepared to explain how this single task does not - become a major bottleneck on big multiprocessor machines (for - example, if the task is updating information relating to itself - that other tasks can read, there by definition can be no - bottleneck). + them -- even x86 allows later loads to be reordered to precede + earlier stores), and be prepared to explain why this added + complexity is worthwhile. If you choose #c, be prepared to + explain how this single task does not become a major bottleneck on + big multiprocessor machines (for example, if the task is updating + information relating to itself that other tasks can read, there + by definition can be no bottleneck). 2. Do the RCU read-side critical sections make proper use of rcu_read_lock() and friends? These primitives are needed @@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome! actuarial risk of your kernel. As a rough rule of thumb, any dereference of an RCU-protected - pointer must be covered by rcu_read_lock() or rcu_read_lock_bh() - or by the appropriate update-side lock. + pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(), + rcu_read_lock_sched(), or by the appropriate update-side lock. + Disabling of preemption can serve as rcu_read_lock_sched(), but + is less readable. 3. Does the update code tolerate concurrent accesses? @@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome! of ways to handle this concurrency, depending on the situation: a. Use the RCU variants of the list and hlist update - primitives to add, remove, and replace elements on an - RCU-protected list. Alternatively, use the RCU-protected - trees that have been added to the Linux kernel. + primitives to add, remove, and replace elements on + an RCU-protected list. Alternatively, use the other + RCU-protected data structures that have been added to + the Linux kernel. This is almost always the best approach. b. Proceed as in (a) above, but also maintain per-element locks (that are acquired by both readers and writers) that guard per-element state. Of course, fields that - the readers refrain from accessing can be guarded by the - update-side lock. + the readers refrain from accessing can be guarded by + some other lock acquired only by updaters, if desired. This works quite well, also. c. Make updates appear atomic to readers. For example, - pointer updates to properly aligned fields will appear - atomic, as will individual atomic primitives. Operations - performed under a lock and sequences of multiple atomic - primitives will -not- appear to be atomic. + pointer updates to properly aligned fields will + appear atomic, as will individual atomic primitives. + Sequences of perations performed under a lock will -not- + appear to be atomic to RCU readers, nor will sequences + of multiple atomic primitives. This can work, but is starting to get a bit tricky. @@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome! a new structure containing updated values. 4. Weakly ordered CPUs pose special challenges. Almost all CPUs - are weakly ordered -- even i386 CPUs allow reads to be reordered. - RCU code must take all of the following measures to prevent - memory-corruption problems: + are weakly ordered -- even x86 CPUs allow later loads to be + reordered to precede earlier stores. RCU code must take all of + the following measures to prevent memory-corruption problems: a. Readers must maintain proper ordering of their memory accesses. The rcu_dereference() primitive ensures that @@ -113,14 +116,21 @@ over a rather long period of time, but improvements are always welcome! The rcu_dereference() primitive is also an excellent documentation aid, letting the person reading the code know exactly which pointers are protected by RCU. - - The rcu_dereference() primitive is used by the various - "_rcu()" list-traversal primitives, such as the - list_for_each_entry_rcu(). Note that it is perfectly - legal (if redundant) for update-side code to use - rcu_dereference() and the "_rcu()" list-traversal - primitives. This is particularly useful in code - that is common to readers and updaters. + Please note that compilers can also reorder code, and + they are becoming increasingly aggressive about doing + just that. The rcu_dereference() primitive therefore + also prevents destructive compiler optimizations. + + The rcu_dereference() primitive is used by the + various "_rcu()" list-traversal primitives, such + as the list_for_each_entry_rcu(). Note that it is + perfectly legal (if redundant) for update-side code to + use rcu_dereference() and the "_rcu()" list-traversal + primitives. This is particularly useful in code that + is common to readers and updaters. However, neither + rcu_dereference() nor the "_rcu()" list-traversal + primitives can substitute for a good concurrency design + coordinating among multiple updaters. b. If the list macros are being used, the list_add_tail_rcu() and list_add_rcu() primitives must be used in order @@ -135,11 +145,14 @@ over a rather long period of time, but improvements are always welcome! readers. Similarly, if the hlist macros are being used, the hlist_del_rcu() primitive is required. - The list_replace_rcu() primitive may be used to - replace an old structure with a new one in an - RCU-protected list. + The list_replace_rcu() and hlist_replace_rcu() primitives + may be used to replace an old structure with a new one + in their respective types of RCU-protected lists. + + d. Rules similar to (4b) and (4c) apply to the "hlist_nulls" + type of RCU-protected linked lists. - d. Updates must ensure that initialization of a given + e. Updates must ensure that initialization of a given structure happens before pointers to that structure are publicized. Use the rcu_assign_pointer() primitive when publicizing a pointer to a structure that can @@ -151,16 +164,31 @@ over a rather long period of time, but improvements are always welcome! it cannot block. 6. Since synchronize_rcu() can block, it cannot be called from - any sort of irq context. Ditto for synchronize_sched() and - synchronize_srcu(). - -7. If the updater uses call_rcu(), then the corresponding readers - must use rcu_read_lock() and rcu_read_unlock(). If the updater - uses call_rcu_bh(), then the corresponding readers must use - rcu_read_lock_bh() and rcu_read_unlock_bh(). If the updater - uses call_rcu_sched(), then the corresponding readers must - disable preemption. Mixing things up will result in confusion - and broken kernels. + any sort of irq context. The same rule applies for + synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(), + synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(), + synchronize_sched_expedite(), and synchronize_srcu_expedited(). + + The expedited forms of these primitives have the same semantics + as the non-expedited forms, but expediting is both expensive + and unfriendly to real-time workloads. Use of the expedited + primitives should be restricted to rare configuration-change + operations that would not normally be undertaken while a real-time + workload is running. + +7. If the updater uses call_rcu() or synchronize_rcu(), then the + corresponding readers must use rcu_read_lock() and + rcu_read_unlock(). If the updater uses call_rcu_bh() or + synchronize_rcu_bh(), then the corresponding readers must + use rcu_read_lock_bh() and rcu_read_unlock_bh(). If the + updater uses call_rcu_sched() or synchronize_sched(), then + the corresponding readers must disable preemption, possibly + by calling rcu_read_lock_sched() and rcu_read_unlock_sched(). + If the updater uses synchronize_srcu(), the the corresponding + readers must use srcu_read_lock() and srcu_read_unlock(), + and with the same srcu_struct. The rules for the expedited + primitives are the same as for their non-expedited counterparts. + Mixing things up will result in confusion and broken kernels. One exception to this rule: rcu_read_lock() and rcu_read_unlock() may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh() @@ -212,6 +240,8 @@ over a rather long period of time, but improvements are always welcome! e. Periodically invoke synchronize_rcu(), permitting a limited number of updates per grace period. + The same cautions apply to call_rcu_bh() and call_rcu_sched(). + 9. All RCU list-traversal primitives, which include rcu_dereference(), list_for_each_entry_rcu(), list_for_each_continue_rcu(), and list_for_each_safe_rcu(), @@ -229,7 +259,8 @@ over a rather long period of time, but improvements are always welcome! 10. Conversely, if you are in an RCU read-side critical section, and you don't hold the appropriate update-side lock, you -must- use the "_rcu()" variants of the list macros. Failing to do so - will break Alpha and confuse people reading your code. + will break Alpha, cause aggressive compilers to generate bad code, + and confuse people trying to read your code. 11. Note that synchronize_rcu() -only- guarantees to wait until all currently executing rcu_read_lock()-protected RCU read-side @@ -239,15 +270,21 @@ over a rather long period of time, but improvements are always welcome! rcu_read_lock()-protected read-side critical sections, do -not- use synchronize_rcu(). - If you want to wait for some of these other things, you might - instead need to use synchronize_irq() or synchronize_sched(). + Similarly, disabling preemption is not an acceptable substitute + for rcu_read_lock(). Code that attempts to use preemption + disabling where it should be using rcu_read_lock() will break + in real-time kernel builds. + + If you want to wait for interrupt handlers, NMI handlers, and + code under the influence of preempt_disable(), you instead + need to use synchronize_irq() or synchronize_sched(). 12. Any lock acquired by an RCU callback must be acquired elsewhere with softirq disabled, e.g., via spin_lock_irqsave(), spin_lock_bh(), etc. Failing to disable irq on a given - acquisition of that lock will result in deadlock as soon as the - RCU callback happens to interrupt that acquisition's critical - section. + acquisition of that lock will result in deadlock as soon as + the RCU softirq handler happens to run your RCU callback while + interrupting that acquisition's critical section. 13. RCU callbacks can be and are executed in parallel. In many cases, the callback code simply wrappers around kfree(), so that this @@ -265,29 +302,30 @@ over a rather long period of time, but improvements are always welcome! not the case, a self-spawning RCU callback would prevent the victim CPU from ever going offline.) -14. SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu()) - may only be invoked from process context. Unlike other forms of - RCU, it -is- permissible to block in an SRCU read-side critical - section (demarked by srcu_read_lock() and srcu_read_unlock()), - hence the "SRCU": "sleepable RCU". Please note that if you - don't need to sleep in read-side critical sections, you should - be using RCU rather than SRCU, because RCU is almost always - faster and easier to use than is SRCU. +14. SRCU (srcu_read_lock(), srcu_read_unlock(), synchronize_srcu(), + and synchronize_srcu_expedited()) may only be invoked from + process context. Unlike other forms of RCU, it -is- permissible + to block in an SRCU read-side critical section (demarked by + srcu_read_lock() and srcu_read_unlock()), hence the "SRCU": + "sleepable RCU". Please note that if you don't need to sleep + in read-side critical sections, you should be using RCU rather + than SRCU, because RCU is almost always faster and easier to + use than is SRCU. Also unlike other forms of RCU, explicit initialization and cleanup is required via init_srcu_struct() and cleanup_srcu_struct(). These are passed a "struct srcu_struct" that defines the scope of a given SRCU domain. Once initialized, the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock() - and synchronize_srcu(). A given synchronize_srcu() waits only - for SRCU read-side critical sections governed by srcu_read_lock() - and srcu_read_unlock() calls that have been passd the same - srcu_struct. This property is what makes sleeping read-side - critical sections tolerable -- a given subsystem delays only - its own updates, not those of other subsystems using SRCU. - Therefore, SRCU is less prone to OOM the system than RCU would - be if RCU's read-side critical sections were permitted to - sleep. + synchronize_srcu(), and synchronize_srcu_expedited(). A given + synchronize_srcu() waits only for SRCU read-side critical + sections governed by srcu_read_lock() and srcu_read_unlock() + calls that have been passed the same srcu_struct. This property + is what makes sleeping read-side critical sections tolerable -- + a given subsystem delays only its own updates, not those of other + subsystems using SRCU. Therefore, SRCU is less prone to OOM the + system than RCU would be if RCU's read-side critical sections + were permitted to sleep. The ability to sleep in read-side critical sections does not come for free. First, corresponding srcu_read_lock() and @@ -311,12 +349,12 @@ over a rather long period of time, but improvements are always welcome! destructive operation, and -only- -then- invoke call_rcu(), synchronize_rcu(), or friends. - Because these primitives only wait for pre-existing readers, - it is the caller's responsibility to guarantee safety to - any subsequent readers. + Because these primitives only wait for pre-existing readers, it + is the caller's responsibility to guarantee that any subsequent + readers will execute safely. -16. The various RCU read-side primitives do -not- contain memory - barriers. The CPU (and in some cases, the compiler) is free - to reorder code into and out of RCU read-side critical sections. - It is the responsibility of the RCU update-side primitives to - deal with this. +16. The various RCU read-side primitives do -not- necessarily contain + memory barriers. You should therefore plan for the CPU + and the compiler to freely reorder code into and out of RCU + read-side critical sections. It is the responsibility of the + RCU update-side primitives to deal with this. diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt index 2a23523ce471..31852705b586 100644 --- a/Documentation/RCU/rcu.txt +++ b/Documentation/RCU/rcu.txt @@ -75,6 +75,8 @@ o I hear that RCU is patented? What is with that? search for the string "Patent" in RTFP.txt to find them. Of these, one was allowed to lapse by the assignee, and the others have been contributed to the Linux kernel under GPL. + There are now also LGPL implementations of user-level RCU + available (http://lttng.org/?q=node/18). o I hear that RCU needs work in order to support realtime kernels? @@ -91,48 +93,4 @@ o Where can I find more information on RCU? o What are all these files in this directory? - - NMI-RCU.txt - - Describes how to use RCU to implement dynamic - NMI handlers, which can be revectored on the fly, - without rebooting. - - RTFP.txt - - List of RCU-related publications and web sites. - - UP.txt - - Discussion of RCU usage in UP kernels. - - arrayRCU.txt - - Describes how to use RCU to protect arrays, with - resizeable arrays whose elements reference other - data structures being of the most interest. - - checklist.txt - - Lists things to check for when inspecting code that - uses RCU. - - listRCU.txt - - Describes how to use RCU to protect linked lists. - This is the simplest and most common use of RCU - in the Linux kernel. - - rcu.txt - - You are reading it! - - rcuref.txt - - Describes how to combine use of reference counts - with RCU. - - whatisRCU.txt - - Overview of how the RCU implementation works. Along - the way, presents a conceptual view of RCU. + See 00-INDEX for the list. diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt new file mode 100644 index 000000000000..1423d2570d78 --- /dev/null +++ b/Documentation/RCU/stallwarn.txt @@ -0,0 +1,58 @@ +Using RCU's CPU Stall Detector + +The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables +RCU's CPU stall detector, which detects conditions that unduly delay +RCU grace periods. The stall detector's idea of what constitutes +"unduly delayed" is controlled by a pair of C preprocessor macros: + +RCU_SECONDS_TILL_STALL_CHECK + + This macro defines the period of time that RCU will wait from + the beginning of a grace period until it issues an RCU CPU + stall warning. It is normally ten seconds. + +RCU_SECONDS_TILL_STALL_RECHECK + + This macro defines the period of time that RCU will wait after + issuing a stall warning until it issues another stall warning. + It is normally set to thirty seconds. + +RCU_STALL_RAT_DELAY + + The CPU stall detector tries to make the offending CPU rat on itself, + as this often gives better-quality stack traces. However, if + the offending CPU does not detect its own stall in the number + of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will + complain. This is normally set to two jiffies. + +The following problems can result in an RCU CPU stall warning: + +o A CPU looping in an RCU read-side critical section. + +o A CPU looping with interrupts disabled. + +o A CPU looping with preemption disabled. + +o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel + without invoking schedule(). + +o A bug in the RCU implementation. + +o A hardware failure. This is quite unlikely, but has occurred + at least once in a former life. A CPU failed in a running system, + becoming unresponsive, but not causing an immediate crash. + This resulted in a series of RCU CPU stall warnings, eventually + leading the realization that the CPU had failed. + +The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning. +SRCU does not do so directly, but its calls to synchronize_sched() will +result in RCU-sched detecting any CPU stalls that might be occurring. + +To diagnose the cause of the stall, inspect the stack traces. The offending +function will usually be near the top of the stack. If you have a series +of stall warnings from a single extended stall, comparing the stack traces +can often help determine where the stall is occurring, which will usually +be in the function nearest the top of the stack that stays the same from +trace to trace. + +RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 9dba3bb90e60..0e50bc2aa1e2 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -30,6 +30,18 @@ MODULE PARAMETERS This module has the following parameters: +fqs_duration Duration (in microseconds) of artificially induced bursts + of force_quiescent_state() invocations. In RCU + implementations having force_quiescent_state(), these + bursts help force races between forcing a given grace + period and that grace period ending on its own. + +fqs_holdoff Holdoff time (in microseconds) between consecutive calls + to force_quiescent_state() within a burst. + +fqs_stutter Wait time (in seconds) between consecutive bursts + of calls to force_quiescent_state(). + irqreaders Says to invoke RCU readers from irq level. This is currently done via timers. Defaults to "1" for variants of RCU that permit this. (Or, more accurately, variants of RCU that do diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index d542ca243b80..469a58b2e67e 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -327,7 +327,8 @@ a. synchronize_rcu() rcu_read_lock() / rcu_read_unlock() b. call_rcu_bh() rcu_read_lock_bh() / rcu_read_unlock_bh() -c. synchronize_sched() preempt_disable() / preempt_enable() +c. synchronize_sched() rcu_read_lock_sched() / rcu_read_unlock_sched() + preempt_disable() / preempt_enable() local_irq_save() / local_irq_restore() hardirq enter / hardirq exit NMI enter / NMI exit diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt index 4c0c575a4012..79334ed5daa7 100644 --- a/Documentation/filesystems/dentry-locking.txt +++ b/Documentation/filesystems/dentry-locking.txt @@ -62,7 +62,8 @@ changes are : 2. Insertion of a dentry into the hash table is done using hlist_add_head_rcu() which take care of ordering the writes - the writes to the dentry must be visible before the dentry is - inserted. This works in conjunction with hlist_for_each_rcu() while + inserted. This works in conjunction with hlist_for_each_rcu(), + which has since been replaced by hlist_for_each_entry_rcu(), while walking the hash chain. The only requirement is that all initialization to the dentry must be done before hlist_add_head_rcu() since we don't have dcache_lock protection diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..6bf97d176326 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -765,9 +765,9 @@ config RCU_CPU_STALL_DETECTOR CPUs are delaying the current grace period, but only when the grace period extends for excessive time periods. - Say Y if you want RCU to perform such checks. + Say N if you want to disable such checks. - Say N if you are unsure. + Say Y if you are unsure. config KPROBES_SANITY_TEST bool "Kprobes sanity tests" -- cgit v1.2.3 From 660e2acad81c19b404f7d7d06e57a6d5e6ce7426 Mon Sep 17 00:00:00 2001 From: Chris Smith Date: Wed, 27 Jan 2010 22:03:11 +0900 Subject: sh: kmemleak support. Enables support for kmemleak on sh. Signed-off-by: Chris Smith Signed-off-by: Paul Mundt --- arch/sh/kernel/vmlinux.lds.S | 6 +++--- lib/Kconfig.debug | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 93e9b25a1811..f0bc6b886eed 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -50,12 +50,12 @@ SECTIONS } = 0x0009 EXCEPTION_TABLE(16) - NOTES + + _sdata = .; RO_DATA(PAGE_SIZE) RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) - - _edata = .; /* End of data section */ + _edata = .; DWARF_EH_FRAME diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..d62e3cdab357 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -355,7 +355,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390) + (X86 || ARM || PPC || S390 || SUPERH) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3 From 24551f64d47af9539a7f324343bffeea09d9dcfa Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 12 Jan 2010 21:25:24 +0000 Subject: lmb: Add lmb_free() We can free memory allocated with lmb_alloc() by removing it from the list of reserved LMBs. Rework lmb_remove() to allow that possibility and add lmb_free() which exploits it. BenH: Removed some useless parenthesis Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- include/linux/lmb.h | 1 + lib/lmb.c | 13 +++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/include/linux/lmb.h b/include/linux/lmb.h index ef82b8fcbddb..f3d14333ebed 100644 --- a/include/linux/lmb.h +++ b/include/linux/lmb.h @@ -42,6 +42,7 @@ extern void __init lmb_init(void); extern void __init lmb_analyze(void); extern long lmb_add(u64 base, u64 size); extern long lmb_remove(u64 base, u64 size); +extern long __init lmb_free(u64 base, u64 size); extern long __init lmb_reserve(u64 base, u64 size); extern u64 __init lmb_alloc_nid(u64 size, u64 align, int nid, u64 (*nid_range)(u64, u64, int *)); diff --git a/lib/lmb.c b/lib/lmb.c index 9cee17142b2c..b1fc52606524 100644 --- a/lib/lmb.c +++ b/lib/lmb.c @@ -205,9 +205,8 @@ long lmb_add(u64 base, u64 size) } -long lmb_remove(u64 base, u64 size) +static long __lmb_remove(struct lmb_region *rgn, u64 base, u64 size) { - struct lmb_region *rgn = &(lmb.memory); u64 rgnbegin, rgnend; u64 end = base + size; int i; @@ -254,6 +253,16 @@ long lmb_remove(u64 base, u64 size) return lmb_add_region(rgn, end, rgnend - end); } +long lmb_remove(u64 base, u64 size) +{ + return __lmb_remove(&lmb.memory, base, size); +} + +long __init lmb_free(u64 base, u64 size) +{ + return __lmb_remove(&lmb.reserved, base, size); +} + long __init lmb_reserve(u64 base, u64 size) { struct lmb_region *_rgn = &lmb.reserved; -- cgit v1.2.3 From d2e7276b6b5e4bc2148891a056d5862c5314342d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Feb 2010 12:44:19 -0800 Subject: idr: fix a critical misallocation bug, take#2 This is retry of reverted 859ddf09743a8cc680af33f7259ccd0fd36bfe9d ("idr: fix a critical misallocation bug") which contained two bugs. * pa[idp->layers] should be cleared even if it's not used by sub_alloc() because it's used by mark idr_mark_full(). * The original condition check also assigned pa[l] to p which the new code didn't do thus leaving p pointing at the wrong layer. Both problems have been fixed and the idr code has received good amount testing using userland testing setup where simple bitmap allocator is run parallel to verify the result of idr allocation. The bug this patch fixes is caused by sub_alloc() optimization path bypassing out-of-room condition check and restarting allocation loop with starting value higher than maximum allowed value. For detailed description, please read commit message of 859ddf09. Signed-off-by: Tejun Heo Based-on-patch-from: Eric Paris Reported-by: Eric Paris Tested-by: Stefan Lippers-Hollmann Tested-by: Serge Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/idr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/idr.c b/lib/idr.c index 1cac726c44bc..0dc782216d4b 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -156,10 +156,12 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa) id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1; /* if already at the top layer, we need to grow */ - if (!(p = pa[l])) { + if (id >= 1 << (idp->layers * IDR_BITS)) { *starting_id = id; return IDR_NEED_TO_GROW; } + p = pa[l]; + BUG_ON(!p); /* If we need to go up one layer, continue the * loop; otherwise, restart from the top. -- cgit v1.2.3 From 632ee200130899252508c478ad0e808222573fbc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:45 -0800 Subject: rcu: Introduce lockdep-based checking to RCU read-side primitives 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: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1266887105-1528-1-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- include/linux/rcupdate.h | 126 +++++++++++++++++++++++++++++++++++++++++++---- include/linux/srcu.h | 87 +++++++++++++++++++++++++++++++- kernel/rcupdate.c | 10 ++++ kernel/rcutorture.c | 12 ++++- kernel/srcu.c | 50 ++++++++++++------- lib/Kconfig.debug | 12 +++++ lib/debug_locks.c | 1 + 7 files changed, 267 insertions(+), 31 deletions(-) (limited to 'lib') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 24440f4bf476..e3d37efe2703 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -78,14 +78,120 @@ extern void rcu_init(void); } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC + extern struct lockdep_map rcu_lock_map; -# define rcu_read_acquire() \ - lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_acquire() \ + lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) # define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) -#else -# define rcu_read_acquire() do { } while (0) -# define rcu_read_release() do { } while (0) -#endif + +extern struct lockdep_map rcu_bh_lock_map; +# define rcu_read_acquire_bh() \ + lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_) + +extern struct lockdep_map rcu_sched_lock_map; +# define rcu_read_acquire_sched() \ + lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define rcu_read_release_sched() \ + lock_release(&rcu_sched_lock_map, 1, _THIS_IP_) + +/** + * rcu_read_lock_held - might we be in RCU read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in + * an RCU read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an RCU read-side critical section unless it can + * prove otherwise. + */ +static inline int rcu_read_lock_held(void) +{ + if (debug_locks) + return lock_is_held(&rcu_lock_map); + return 1; +} + +/** + * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in + * an RCU-bh read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an RCU-bh read-side critical section unless it can + * prove otherwise. + */ +static inline int rcu_read_lock_bh_held(void) +{ + if (debug_locks) + return lock_is_held(&rcu_bh_lock_map); + return 1; +} + +/** + * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an + * RCU-sched read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an RCU-sched read-side critical section unless it + * can prove otherwise. Note that disabling of preemption (including + * disabling irqs) counts as an RCU-sched read-side critical section. + */ +static inline int rcu_read_lock_sched_held(void) +{ + int lockdep_opinion = 0; + + if (debug_locks) + lockdep_opinion = lock_is_held(&rcu_sched_lock_map); + return lockdep_opinion || preempt_count() != 0; +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +# define rcu_read_acquire() do { } while (0) +# define rcu_read_release() do { } while (0) +# define rcu_read_acquire_bh() do { } while (0) +# define rcu_read_release_bh() do { } while (0) +# define rcu_read_acquire_sched() do { } while (0) +# define rcu_read_release_sched() do { } while (0) + +static inline int rcu_read_lock_held(void) +{ + return 1; +} + +static inline int rcu_read_lock_bh_held(void) +{ + return 1; +} + +static inline int rcu_read_lock_sched_held(void) +{ + return preempt_count() != 0; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +#ifdef CONFIG_PROVE_RCU + +/** + * rcu_dereference_check - rcu_dereference with debug checking + * + * Do an rcu_dereference(), but check that the context is correct. + * For example, rcu_dereference_check(gp, rcu_read_lock_held()) to + * ensure that the rcu_dereference_check() executes within an RCU + * read-side critical section. It is also possible to check for + * locks being held, for example, by using lockdep_is_held(). + */ +#define rcu_dereference_check(p, c) \ + ({ \ + if (debug_locks) \ + WARN_ON_ONCE(!(c)); \ + rcu_dereference(p); \ + }) + +#else /* #ifdef CONFIG_PROVE_RCU */ + +#define rcu_dereference_check(p, c) rcu_dereference(p) + +#endif /* #else #ifdef CONFIG_PROVE_RCU */ /** * rcu_read_lock - mark the beginning of an RCU read-side critical section. @@ -160,7 +266,7 @@ static inline void rcu_read_lock_bh(void) { __rcu_read_lock_bh(); __acquire(RCU_BH); - rcu_read_acquire(); + rcu_read_acquire_bh(); } /* @@ -170,7 +276,7 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { - rcu_read_release(); + rcu_read_release_bh(); __release(RCU_BH); __rcu_read_unlock_bh(); } @@ -188,7 +294,7 @@ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); - rcu_read_acquire(); + rcu_read_acquire_sched(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -205,7 +311,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { - rcu_read_release(); + rcu_read_release_sched(); __release(RCU_SCHED); preempt_enable(); } diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 4765d97dcafb..adbe1670b366 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -35,6 +35,9 @@ struct srcu_struct { int completed; struct srcu_struct_array *per_cpu_ref; struct mutex mutex; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map dep_map; +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; #ifndef CONFIG_PREEMPT @@ -43,12 +46,92 @@ struct srcu_struct { #define srcu_barrier() #endif /* #else #ifndef CONFIG_PREEMPT */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +int __init_srcu_struct(struct srcu_struct *sp, const char *name, + struct lock_class_key *key); + +#define init_srcu_struct(sp) \ +({ \ + static struct lock_class_key __srcu_key; \ + \ + __init_srcu_struct((sp), #sp, &__srcu_key); \ +}) + +# define srcu_read_acquire(sp) \ + lock_acquire(&(sp)->dep_map, 0, 0, 2, 1, NULL, _THIS_IP_) +# define srcu_read_release(sp) \ + lock_release(&(sp)->dep_map, 1, _THIS_IP_) + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + int init_srcu_struct(struct srcu_struct *sp); + +# define srcu_read_acquire(sp) do { } while (0) +# define srcu_read_release(sp) do { } while (0) + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + void cleanup_srcu_struct(struct srcu_struct *sp); -int srcu_read_lock(struct srcu_struct *sp) __acquires(sp); -void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); +int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); +void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); long srcu_batches_completed(struct srcu_struct *sp); +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/** + * srcu_read_lock_held - might we be in SRCU read-side critical section? + * + * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in + * an SRCU read-side critical section. In absence of CONFIG_PROVE_LOCKING, + * this assumes we are in an SRCU read-side critical section unless it can + * prove otherwise. + */ +static inline int srcu_read_lock_held(struct srcu_struct *sp) +{ + if (debug_locks) + return lock_is_held(&sp->dep_map); + return 1; +} + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +static inline int srcu_read_lock_held(struct srcu_struct *sp) +{ + return 1; +} + +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + +/** + * srcu_read_lock - register a new reader for an SRCU-protected structure. + * @sp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section. Note that SRCU read-side + * critical sections may be nested. + */ +static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) +{ + int retval = __srcu_read_lock(sp); + + srcu_read_acquire(sp); + return retval; +} + +/** + * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. + * @sp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock(). + * + * Exit an SRCU read-side critical section. + */ +static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) + __releases(sp) +{ + srcu_read_release(sp); + __srcu_read_unlock(sp, idx); +} + #endif diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 9b7fd4723878..033cb55c26df 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -50,6 +50,16 @@ static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key); EXPORT_SYMBOL_GPL(rcu_lock_map); + +static struct lock_class_key rcu_bh_lock_key; +struct lockdep_map rcu_bh_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key); +EXPORT_SYMBOL_GPL(rcu_bh_lock_map); + +static struct lock_class_key rcu_sched_lock_key; +struct lockdep_map rcu_sched_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key); +EXPORT_SYMBOL_GPL(rcu_sched_lock_map); #endif /* diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index adda92bfafac..5f43f30fcd1d 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -796,7 +796,11 @@ static void rcu_torture_timer(unsigned long unused) idx = cur_ops->readlock(); completed = cur_ops->completed(); - p = rcu_dereference(rcu_torture_current); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_held() || + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); @@ -853,7 +857,11 @@ rcu_torture_reader(void *arg) } idx = cur_ops->readlock(); completed = cur_ops->completed(); - p = rcu_dereference(rcu_torture_current); + p = rcu_dereference_check(rcu_torture_current, + rcu_read_lock_held() || + rcu_read_lock_bh_held() || + rcu_read_lock_sched_held() || + srcu_read_lock_held(&srcu_ctl)); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); diff --git a/kernel/srcu.c b/kernel/srcu.c index 31b275b9c112..bde4295774c8 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -34,6 +34,30 @@ #include #include +static int init_srcu_struct_fields(struct srcu_struct *sp) +{ + sp->completed = 0; + mutex_init(&sp->mutex); + sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); + return sp->per_cpu_ref ? 0 : -ENOMEM; +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +int __init_srcu_struct(struct srcu_struct *sp, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* Don't re-initialize a lock while it is held. */ + debug_check_no_locks_freed((void *)sp, sizeof(*sp)); + lockdep_init_map(&sp->dep_map, name, key, 0); +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + return init_srcu_struct_fields(sp); +} +EXPORT_SYMBOL_GPL(__init_srcu_struct); + +#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /** * init_srcu_struct - initialize a sleep-RCU structure * @sp: structure to initialize. @@ -44,13 +68,12 @@ */ int init_srcu_struct(struct srcu_struct *sp) { - sp->completed = 0; - mutex_init(&sp->mutex); - sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); - return (sp->per_cpu_ref ? 0 : -ENOMEM); + return init_srcu_struct_fields(sp); } EXPORT_SYMBOL_GPL(init_srcu_struct); +#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + /* * srcu_readers_active_idx -- returns approximate number of readers * active on the specified rank of per-CPU counters. @@ -100,15 +123,12 @@ void cleanup_srcu_struct(struct srcu_struct *sp) } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); -/** - * srcu_read_lock - register a new reader for an SRCU-protected structure. - * @sp: srcu_struct in which to register the new reader. - * +/* * Counts the new reader in the appropriate per-CPU element of the * srcu_struct. Must be called from process context. * Returns an index that must be passed to the matching srcu_read_unlock(). */ -int srcu_read_lock(struct srcu_struct *sp) +int __srcu_read_lock(struct srcu_struct *sp) { int idx; @@ -120,26 +140,22 @@ int srcu_read_lock(struct srcu_struct *sp) preempt_enable(); return idx; } -EXPORT_SYMBOL_GPL(srcu_read_lock); +EXPORT_SYMBOL_GPL(__srcu_read_lock); -/** - * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. - * @sp: srcu_struct in which to unregister the old reader. - * @idx: return value from corresponding srcu_read_lock(). - * +/* * Removes the count for the old reader from the appropriate per-CPU * element of the srcu_struct. Note that this may well be a different * CPU than that which was incremented by the corresponding srcu_read_lock(). * Must be called from process context. */ -void srcu_read_unlock(struct srcu_struct *sp, int idx) +void __srcu_read_unlock(struct srcu_struct *sp, int idx) { preempt_disable(); srcu_barrier(); /* ensure compiler won't misorder critical section. */ per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--; preempt_enable(); } -EXPORT_SYMBOL_GPL(srcu_read_unlock); +EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6bf97d176326..6af20a8a0a54 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -499,6 +499,18 @@ config PROVE_LOCKING For more details, see Documentation/lockdep-design.txt. +config PROVE_RCU + bool "RCU debugging: prove RCU correctness" + depends on PROVE_LOCKING + default n + help + This feature enables lockdep extensions that check for correct + use of RCU APIs. This is currently under development. Say Y + if you want to debug RCU usage or help work on the PROVE_RCU + feature. + + Say N if you are unsure. + config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT diff --git a/lib/debug_locks.c b/lib/debug_locks.c index bc3b11731b9c..5bf0020b9248 100644 --- a/lib/debug_locks.c +++ b/lib/debug_locks.c @@ -23,6 +23,7 @@ * shut up after that. */ int debug_locks = 1; +EXPORT_SYMBOL_GPL(debug_locks); /* * The locking-testsuite uses to get a -- cgit v1.2.3 From 2676a58c980b7ef076cc9bbff3fd8c9d2d5417ea Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:54 -0800 Subject: radix-tree: Disable RCU lockdep checking in radix tree Because the radix tree is used with many different locking designs, we cannot do any effective checking without changing the radix-tree APIs. It might make sense to do this later, but only if the RCU lockdep checking proves itself sufficiently valuable. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1266887105-1528-10-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- lib/radix-tree.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'lib') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 92cdd9936e3d..6b9670d6bbf9 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -364,7 +364,7 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root, unsigned int height, shift; struct radix_tree_node *node, **slot; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (node == NULL) return NULL; @@ -384,7 +384,7 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root, do { slot = (struct radix_tree_node **) (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK)); - node = rcu_dereference(*slot); + node = rcu_dereference_raw(*slot); if (node == NULL) return NULL; @@ -568,7 +568,7 @@ int radix_tree_tag_get(struct radix_tree_root *root, if (!root_tag_get(root, tag)) return 0; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (node == NULL) return 0; @@ -602,7 +602,7 @@ int radix_tree_tag_get(struct radix_tree_root *root, BUG_ON(ret && saw_unset_tag); return !!ret; } - node = rcu_dereference(node->slots[offset]); + node = rcu_dereference_raw(node->slots[offset]); shift -= RADIX_TREE_MAP_SHIFT; height--; } @@ -711,7 +711,7 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index, } shift -= RADIX_TREE_MAP_SHIFT; - slot = rcu_dereference(slot->slots[i]); + slot = rcu_dereference_raw(slot->slots[i]); if (slot == NULL) goto out; } @@ -758,7 +758,7 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned long cur_index = first_index; unsigned int ret; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (!node) return 0; @@ -787,7 +787,7 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, slot = *(((void ***)results)[ret + i]); if (!slot) continue; - results[ret + nr_found] = rcu_dereference(slot); + results[ret + nr_found] = rcu_dereference_raw(slot); nr_found++; } ret += nr_found; @@ -826,7 +826,7 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long cur_index = first_index; unsigned int ret; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (!node) return 0; @@ -915,7 +915,7 @@ __lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index, } } shift -= RADIX_TREE_MAP_SHIFT; - slot = rcu_dereference(slot->slots[i]); + slot = rcu_dereference_raw(slot->slots[i]); if (slot == NULL) break; } @@ -951,7 +951,7 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, if (!root_tag_get(root, tag)) return 0; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (!node) return 0; @@ -980,7 +980,7 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, slot = *(((void ***)results)[ret + i]); if (!slot) continue; - results[ret + nr_found] = rcu_dereference(slot); + results[ret + nr_found] = rcu_dereference_raw(slot); nr_found++; } ret += nr_found; @@ -1020,7 +1020,7 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, if (!root_tag_get(root, tag)) return 0; - node = rcu_dereference(root->rnode); + node = rcu_dereference_raw(root->rnode); if (!node) return 0; -- cgit v1.2.3 From 96be753af91fc9d582450a84722f6a6721d218ad Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:04:55 -0800 Subject: idr: Apply lockdep-based diagnostics to rcu_dereference() uses Because idr can be used with any of a number of locks or with any flavor of RCU, just disable the lockdep-based diagnostics. If idr needs diagnostics, the check expression will need to be passed into the relevant idr primitives as an additional argument. Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1266887105-1528-11-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- lib/idr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/idr.c b/lib/idr.c index 0dc782216d4b..2eb1dca03681 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -504,7 +504,7 @@ void *idr_find(struct idr *idp, int id) int n; struct idr_layer *p; - p = rcu_dereference(idp->top); + p = rcu_dereference_raw(idp->top); if (!p) return NULL; n = (p->layer+1) * IDR_BITS; @@ -519,7 +519,7 @@ void *idr_find(struct idr *idp, int id) while (n > 0 && p) { n -= IDR_BITS; BUG_ON(n != p->layer*IDR_BITS); - p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]); + p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]); } return((void *)p); } @@ -552,7 +552,7 @@ int idr_for_each(struct idr *idp, struct idr_layer **paa = &pa[0]; n = idp->layers * IDR_BITS; - p = rcu_dereference(idp->top); + p = rcu_dereference_raw(idp->top); max = 1 << n; id = 0; @@ -560,7 +560,7 @@ int idr_for_each(struct idr *idp, while (n > 0 && p) { n -= IDR_BITS; *paa++ = p; - p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]); + p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]); } if (p) { -- cgit v1.2.3 From 1ed509a225008c9e8c0644fbd22168e09a7383a0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 Feb 2010 17:05:05 -0800 Subject: rcu: Add RCU_CPU_STALL_VERBOSE to dump detailed per-task information When RCU detects a grace-period stall, it currently just prints out the PID of any tasks doing the stalling. This patch adds RCU_CPU_STALL_VERBOSE, which enables the more-verbose reporting from sched_show_task(). Suggested-by: Thomas Gleixner Signed-off-by: Paul E. McKenney Cc: laijs@cn.fujitsu.com Cc: dipankar@in.ibm.com Cc: mathieu.desnoyers@polymtl.ca Cc: josh@joshtriplett.org Cc: dvhltc@us.ibm.com Cc: niv@us.ibm.com Cc: peterz@infradead.org Cc: rostedt@goodmis.org Cc: Valdis.Kletnieks@vt.edu Cc: dhowells@redhat.com LKML-Reference: <1266887105-1528-21-git-send-email-paulmck@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar --- kernel/rcutree.c | 4 ++++ kernel/rcutree.h | 1 + kernel/rcutree_plugin.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 12 ++++++++++++ 4 files changed, 69 insertions(+) (limited to 'lib') diff --git a/kernel/rcutree.c b/kernel/rcutree.c index b07be37d2aa3..525d39810616 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -489,6 +489,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp) smp_processor_id(), (long)(jiffies - rsp->gp_start)); trigger_all_cpu_backtrace(); + /* If so configured, complain about tasks blocking the grace period. */ + + rcu_print_detail_task_stall(rsp); + force_quiescent_state(rsp, 0); /* Kick them all. */ } diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 6a82c34ce669..2ceb08388582 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -352,6 +352,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +static void rcu_print_detail_task_stall(struct rcu_state *rsp); static void rcu_print_task_stall(struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index aecfe37e0117..3516de7091a1 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -312,6 +312,50 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock); #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +#ifdef CONFIG_RCU_CPU_STALL_VERBOSE + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period on the specified rcu_node structure. + */ +static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ + unsigned long flags; + struct list_head *lp; + int phase; + struct task_struct *t; + + if (rcu_preempted_readers(rnp)) { + raw_spin_lock_irqsave(&rnp->lock, flags); + phase = rnp->gpnum & 0x1; + lp = &rnp->blocked_tasks[phase]; + list_for_each_entry(t, lp, rcu_node_entry) + sched_show_task(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +/* + * Dump detailed information for all tasks blocking the current RCU + * grace period. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ + struct rcu_node *rnp = rcu_get_root(rsp); + + rcu_print_detail_task_stall_rnp(rnp); + rcu_for_each_leaf_node(rsp, rnp) + rcu_print_detail_task_stall_rnp(rnp); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ + +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ + /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -760,6 +804,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) #ifdef CONFIG_RCU_CPU_STALL_DETECTOR +/* + * Because preemptable RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections. + */ +static void rcu_print_detail_task_stall(struct rcu_state *rsp) +{ +} + /* * Because preemptable RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6af20a8a0a54..4cdab452bfe2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -781,6 +781,18 @@ config RCU_CPU_STALL_DETECTOR Say Y if you are unsure. +config RCU_CPU_STALL_VERBOSE + bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR" + depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU + default n + help + This option causes RCU to printk detailed per-task information + for any tasks that are stalling the current RCU grace period. + + Say N if you are unsure. + + Say Y if you want to enable such checks. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL -- cgit v1.2.3