diff options
169 files changed, 4771 insertions, 4627 deletions
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt index c43460dade0f..7c1dfb19fc40 100644 --- a/Documentation/RCU/RTFP.txt +++ b/Documentation/RCU/RTFP.txt @@ -1,9 +1,10 @@ -Read the F-ing Papers! +Read the Fscking Papers! This document describes RCU-related publications, and is followed by the corresponding bibtex entries. A number of the publications may -be found at http://www.rdrop.com/users/paulmck/RCU/. +be found at http://www.rdrop.com/users/paulmck/RCU/. For others, browsers +and search engines will usually find what you are looking for. The first thing resembling RCU was published in 1980, when Kung and Lehman [Kung80] recommended use of a garbage collector to defer destruction @@ -160,7 +161,26 @@ 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]. +to a solution [JoshTriplett2009RPHash]. A few academic researchers are now +using RCU to solve their parallel problems [HariKannan2009DynamicAnalysisRCU]. + +2010 produced a simpler preemptible-RCU implementation +based on TREE_RCU [PaulEMcKenney2010SimpleOptRCU], lockdep-RCU +[PaulEMcKenney2010LockdepRCU], another resizeable RCU-protected hash +table [HerbertXu2010RCUResizeHash] (this one consuming more memory, +but allowing arbitrary changes in hash function, as required for DoS +avoidance in the networking code), realization of the 2009 RCU-protected +hash table with atomic node move [JoshTriplett2010RPHash], an update on +the RCU API [PaulEMcKenney2010RCUAPI]. + +2011 marked the inclusion of Nick Piggin's fully lockless dentry search +[LinusTorvalds2011Linux2:6:38:rc1:NPigginVFS], an RCU-protected red-black +tree using software transactional memory to protect concurrent updates +(strange, but true!) [PhilHoward2011RCUTMRBTree], yet another variant of +RCU-protected resizeable hash tables [Triplett:2011:RPHash], the 3.0 RCU +trainwreck [PaulEMcKenney2011RCU3.0trainwreck], and Neil Brown's "Meet the +Lockers" LWN article [NeilBrown2011MeetTheLockers]. + Bibtex Entries @@ -173,6 +193,14 @@ Bibtex Entries ,volume="5" ,number="3" ,pages="354-382" +,note="Available: +\url{http://portal.acm.org/citation.cfm?id=320619&dl=GUIDE,} +[Viewed December 3, 2007]" +,annotation={ + Use garbage collector to clean up data after everyone is done with it. + . + Oldest use of something vaguely resembling RCU that I have found. +} } @techreport{Manber82 @@ -184,6 +212,31 @@ Bibtex Entries ,number="82-01-01" ,month="January" ,pages="28" +,annotation={ + . + Superseded by Manber84. + . + Describes concurrent AVL tree implementation. Uses a + garbage-collection mechanism to handle concurrent use and deletion + of nodes in the tree, but lacks the summary-of-execution-history + concept of read-copy locking. + . + Keeps full list of processes that were active when a given + node was to be deleted, and waits until all such processes have + -terminated- before allowing this node to be reused. This is + not described in great detail -- one could imagine using process + IDs for this if the ID space was large enough that overlapping + never occurred. + . + This restriction makes this algorithm unsuitable for use in + systems comprised of long-lived processes. It also produces + completely unacceptable overhead in systems with large numbers + of processes. Finally, it is specific to AVL trees. + . + Cites Kung80, so not an independent invention, but the first + RCU-like usage that does not rely on an automatic garbage + collector. +} } @article{Manber84 @@ -195,6 +248,74 @@ Bibtex Entries ,volume="9" ,number="3" ,pages="439-455" +,annotation={ + Describes concurrent AVL tree implementation. Uses a + garbage-collection mechanism to handle concurrent use and deletion + of nodes in the tree, but lacks the summary-of-execution-history + concept of read-copy locking. + . + Keeps full list of processes that were active when a given + node was to be deleted, and waits until all such processes have + -terminated- before allowing this node to be reused. This is + not described in great detail -- one could imagine using process + IDs for this if the ID space was large enough that overlapping + never occurred. + . + This restriction makes this algorithm unsuitable for use in + systems comprised of long-lived processes. It also produces + completely unacceptable overhead in systems with large numbers + of processes. Finally, it is specific to AVL trees. +} +} + +@Conference{RichardRashid87a +,Author="Richard Rashid and Avadis Tevanian and Michael Young and +David Golub and Robert Baron and David Black and William Bolosky and +Jonathan Chew" +,Title="Machine-Independent Virtual Memory Management for Paged +Uniprocessor and Multiprocessor Architectures" +,Booktitle="{2\textsuperscript{nd} Symposium on Architectural Support +for Programming Languages and Operating Systems}" +,Publisher="Association for Computing Machinery" +,Month="October" +,Year="1987" +,pages="31-39" +,Address="Palo Alto, CA" +,note="Available: +\url{http://www.cse.ucsc.edu/~randal/221/rashid-machvm.pdf} +[Viewed February 17, 2005]" +,annotation={ + Describes lazy TLB flush, where one waits for each CPU to pass + through a scheduling-clock interrupt before reusing a given range + of virtual address. Does not describe how one determines that + all CPUs have in fact taken such an interrupt, though there are + no shortage of straightforward methods for accomplishing this. + . + Note that it does not make sense to just wait a fixed amount of + time, since a given CPU might have interrupts disabled for an + extended amount of time. +} +} + +@article{BarbaraLiskov1988ArgusCACM +,author = {Barbara Liskov} +,title = {Distributed programming in {Argus}} +,journal = {Commun. ACM} +,volume = {31} +,number = {3} +,year = {1988} +,issn = {0001-0782} +,pages = {300--312} +,doi = {http://doi.acm.org/10.1145/42392.42399} +,publisher = {ACM} +,address = {New York, NY, USA} +,annotation= { + At the top of page 307: "Conflicts with deposits and withdrawals + are necessary if the reported total is to be up to date. They + could be avoided by having total return a sum that is slightly + out of date." Relies on semantics -- approximate numerical + values sometimes OK. +} } @techreport{Hennessy89 @@ -216,6 +337,13 @@ Bibtex Entries ,year="1990" ,number="CS-TR-2222.1" ,month="June" +,annotation={ + Concurrent access to skip lists. Has both weak and strong search. + Uses concept of ``garbage queue'', but has no real way of cleaning + the garbage efficiently. + . + Appears to be an independent invention of an RCU-like mechanism. +} } @Book{Adams91 @@ -223,20 +351,15 @@ Bibtex Entries ,title="Concurrent Programming, Principles, and Practices" ,Publisher="Benjamin Cummins" ,Year="1991" +,annotation={ + Has a few paragraphs describing ``chaotic relaxation'', a + numerical analysis technique that allows multiprocessors to + avoid synchronization overhead by using possibly-stale data. + . + Seems like this is descended from yet another independent + invention of RCU-like function -- but this is restricted + in that reclamation is not necessary. } - -@phdthesis{HMassalinPhD -,author="H. Massalin" -,title="Synthesis: An Efficient Implementation of Fundamental Operating -System Services" -,school="Columbia University" -,address="New York, NY" -,year="1992" -,annotation=" - Mondo optimizing compiler. - Wait-free stuff. - Good advice: defer work to avoid synchronization. -" } @unpublished{Jacobson93 @@ -244,7 +367,13 @@ System Services" ,title="Avoid Read-Side Locking Via Delayed Free" ,year="1993" ,month="September" -,note="Verbal discussion" +,note="private communication" +,annotation={ + Use fixed time delay to approximate grace period. Very simple, + but subject to random memory corruption under heavy load. + . + Independent invention of RCU-like mechanism. +} } @Conference{AjuJohn95 @@ -256,6 +385,17 @@ System Services" ,Year="1995" ,pages="11-23" ,Address="New Orleans, LA" +,note="Available: +\url{https://www.usenix.org/publications/library/proceedings/neworl/full_papers/john.a} +[Viewed October 1, 2010]" +,annotation={ + Age vnodes out of the cache, and have a fixed time set by a kernel + parameter. Not clear that all races were in fact correctly handled. + Used a 20-minute time by default, which would most definitely not + be suitable during DoS attacks or virus scans. + . + Apparently independent invention of RCU-like mechanism. +} } @conference{Pu95a, @@ -301,31 +441,47 @@ Utilizing Execution History and Thread Monitoring" ,institution="US Patent and Trademark Office" ,address="Washington, DC" ,year="1995" -,number="US Patent 5,442,758 (contributed under GPL)" +,number="US Patent 5,442,758" ,month="August" +,annotation={ + Describes the parallel RCU infrastructure. Includes NUMA aspect + (structure of bitmap can reflect bus structure of computer system). + . + Another independent invention of an RCU-like mechanism, but the + "real" RCU this time! +} } @techreport{Slingwine97 ,author="John D. Slingwine and Paul E. McKenney" -,title="Method for maintaining data coherency using thread -activity summaries in a multicomputer system" +,title="Method for Maintaining Data Coherency Using Thread Activity +Summaries in a Multicomputer System" ,institution="US Patent and Trademark Office" ,address="Washington, DC" ,year="1997" -,number="US Patent 5,608,893 (contributed under GPL)" +,number="US Patent 5,608,893" ,month="March" +,pages="19" +,annotation={ + Describes use of RCU to synchronize data between a pair of + SMP/NUMA computer systems. +} } @techreport{Slingwine98 ,author="John D. Slingwine and Paul E. McKenney" -,title="Apparatus and method for achieving reduced overhead -mutual exclusion and maintaining coherency in a multiprocessor -system utilizing execution history and thread monitoring" +,title="Apparatus and Method for Achieving Reduced Overhead Mutual +Exclusion and Maintaining Coherency in a Multiprocessor System +Utilizing Execution History and Thread Monitoring" ,institution="US Patent and Trademark Office" ,address="Washington, DC" ,year="1998" -,number="US Patent 5,727,209 (contributed under GPL)" +,number="US Patent 5,727,209" ,month="March" +,annotation={ + Describes doing an atomic update by copying the data item and + then substituting it into the data structure. +} } @Conference{McKenney98 @@ -337,6 +493,15 @@ Problems" ,Year="1998" ,pages="509-518" ,Address="Las Vegas, NV" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/rclockpdcsproof.pdf} +[Viewed December 3, 2007]" +,annotation={ + Describes and analyzes RCU mechanism in DYNIX/ptx. Describes + application to linked list update and log-buffer flushing. + Defines 'quiescent state'. Includes both measured and analytic + evaluation. +} } @Conference{Gamsa99 @@ -349,18 +514,76 @@ Operating System Design and Implementation}" ,Year="1999" ,pages="87-100" ,Address="New Orleans, LA" +,note="Available: +\url{http://www.usenix.org/events/osdi99/full_papers/gamsa/gamsa.pdf} +[Viewed August 30, 2006]" +,annotation={ + Use of RCU-like facility in K42/Tornado. Another independent + invention of RCU. + See especially pages 7-9 (Section 5). +} +} + +@unpublished{RustyRussell2000a +,Author="Rusty Russell" +,Title="Re: modular net drivers" +,month="June" +,year="2000" +,day="23" +,note="Available: +\url{http://oss.sgi.com/projects/netdev/archive/2000-06/msg00250.html} +[Viewed April 10, 2006]" +,annotation={ + Proto-RCU proposal from Phil Rumpf and Rusty Russell. + Yet another independent invention of RCU. + Outline of algorithm to unload modules... + . + Appeared on net-dev mailing list. +} +} + +@unpublished{RustyRussell2000b +,Author="Rusty Russell" +,Title="Re: modular net drivers" +,month="June" +,year="2000" +,day="24" +,note="Available: +\url{http://oss.sgi.com/projects/netdev/archive/2000-06/msg00254.html} +[Viewed April 10, 2006]" +,annotation={ + Proto-RCU proposal from Phil Rumpf and Rusty Russell. + . + Appeared on net-dev mailing list. +} +} + +@unpublished{McKenney01b +,Author="Paul E. McKenney and Dipankar Sarma" +,Title="Read-Copy Update Mutual Exclusion in {Linux}" +,month="February" +,year="2001" +,note="Available: +\url{http://lse.sourceforge.net/locking/rcu/rcupdate_doc.html} +[Viewed October 18, 2004]" +,annotation={ + Prototypical Linux documentation for RCU. +} } @techreport{Slingwine01 ,author="John D. Slingwine and Paul E. McKenney" -,title="Apparatus and method for achieving reduced overhead -mutual exclusion and maintaining coherency in a multiprocessor -system utilizing execution history and thread monitoring" +,title="Apparatus and Method for Achieving Reduced Overhead Mutual +Exclusion and Maintaining Coherency in a Multiprocessor System +Utilizing Execution History and Thread Monitoring" ,institution="US Patent and Trademark Office" ,address="Washington, DC" ,year="2001" -,number="US Patent 5,219,690 (contributed under GPL)" +,number="US Patent 6,219,690" ,month="April" +,annotation={ + 'Change in mode' aspect of RCU. Can be thought of as a lazy barrier. +} } @Conference{McKenney01a @@ -372,14 +595,61 @@ Orran Krieger and Rusty Russell and Dipankar Sarma and Maneesh Soni" ,Year="2001" ,note="Available: \url{http://www.linuxsymposium.org/2001/abstracts/readcopy.php} -\url{http://www.rdrop.com/users/paulmck/rclock/rclock_OLS.2001.05.01c.pdf} +\url{http://www.rdrop.com/users/paulmck/RCU/rclock_OLS.2001.05.01c.pdf} [Viewed June 23, 2004]" -annotation=" -Described RCU, and presented some patches implementing and using it in -the Linux kernel. +,annotation={ + Described RCU, and presented some patches implementing and using + it in the Linux kernel. +} +} + +@unpublished{McKenney01f +,Author="Paul E. McKenney" +,Title="{RFC:} patch to allow lock-free traversal of lists with insertion" +,month="October" +,year="2001" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100259266316456&w=2} +[Viewed June 23, 2004]" +,annotation=" + Memory-barrier and Alpha thread. 100 messages, not too bad... +" +} + +@unpublished{Spraul01 +,Author="Manfred Spraul" +,Title="Re: {RFC:} patch to allow lock-free traversal of lists with insertion" +,month="October" +,year="2001" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100264675012867&w=2} +[Viewed June 23, 2004]" +,annotation=" + Suggested burying memory barriers in Linux's list-manipulation + primitives. " } +@unpublished{LinusTorvalds2001a +,Author="Linus Torvalds" +,Title="{Re:} {[Lse-tech]} {Re:} {RFC:} patch to allow lock-free traversal of lists with insertion" +,month="October" +,year="2001" +,note="Available: +\url{http://lkml.org/lkml/2001/10/13/105} +[Viewed August 21, 2004]" +} + +@unpublished{Blanchard02a +,Author="Anton Blanchard" +,Title="some RCU dcache and ratcache results" +,month="March" +,year="2002" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=101637107412972&w=2} +[Viewed October 18, 2004]" +} + @Conference{Linder02a ,Author="Hanna Linder and Dipankar Sarma and Maneesh Soni" ,Title="Scalability of the Directory Entry Cache" @@ -387,6 +657,10 @@ the Linux kernel. ,Month="June" ,Year="2002" ,pages="289-300" +,annotation=" + Measured scalability of Linux 2.4 kernel's directory-entry cache + (dcache), and measured some scalability enhancements. +" } @Conference{McKenney02a @@ -400,49 +674,76 @@ Andrea Arcangeli and Andi Kleen and Orran Krieger and Rusty Russell" ,note="Available: \url{http://www.linux.org.uk/~ajh/ols2002_proceedings.pdf.gz} [Viewed June 23, 2004]" +,annotation=" + Presented and compared a number of RCU implementations for the + Linux kernel. +" } -@conference{Michael02a -,author="Maged M. Michael" -,title="Safe Memory Reclamation for Dynamic Lock-Free Objects Using Atomic -Reads and Writes" -,Year="2002" -,Month="August" -,booktitle="{Proceedings of the 21\textsuperscript{st} Annual ACM -Symposium on Principles of Distributed Computing}" -,pages="21-30" +@unpublished{Sarma02a +,Author="Dipankar Sarma" +,Title="specweb99: dcache scalability results" +,month="July" +,year="2002" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=102645767914212&w=2} +[Viewed June 23, 2004]" ,annotation=" - Each thread keeps an array of pointers to items that it is - currently referencing. Sort of an inside-out garbage collection - mechanism, but one that requires the accessing code to explicitly - state its needs. Also requires read-side memory barriers on - most architectures. + Compare fastwalk and RCU for dcache. RCU won. " } -@conference{Michael02b -,author="Maged M. Michael" -,title="High Performance Dynamic Lock-Free Hash Tables and List-Based Sets" -,Year="2002" -,Month="August" -,booktitle="{Proceedings of the 14\textsuperscript{th} Annual ACM -Symposium on Parallel -Algorithms and Architecture}" -,pages="73-82" +@unpublished{Barbieri02 +,Author="Luca Barbieri" +,Title="Re: {[PATCH]} Initial support for struct {vfs\_cred}" +,month="August" +,year="2002" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103082050621241&w=2} +[Viewed: June 23, 2004]" ,annotation=" - Like the title says... + Suggested RCU for vfs\_shared\_cred. " } -@InProceedings{HerlihyLM02 -,author={Maurice Herlihy and Victor Luchangco and Mark Moir} -,title="The Repeat Offender Problem: A Mechanism for Supporting Dynamic-Sized, -Lock-Free Data Structures" -,booktitle={Proceedings of 16\textsuperscript{th} International -Symposium on Distributed Computing} -,year=2002 +@unpublished{Dickins02a +,author="Hugh Dickins" +,title="Use RCU for System-V IPC" +,year="2002" +,month="October" +,note="private communication" +} + +@unpublished{Sarma02b +,Author="Dipankar Sarma" +,Title="Some dcache\_rcu benchmark numbers" ,month="October" -,pages="339-353" +,year="2002" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103462075416638&w=2} +[Viewed June 23, 2004]" +,annotation=" + Performance of dcache RCU on kernbench for 16x NUMA-Q and 1x, + 2x, and 4x systems. RCU does no harm, and helps on 16x. +" +} + +@unpublished{LinusTorvalds2003a +,Author="Linus Torvalds" +,Title="Re: {[PATCH]} small fixes in brlock.h" +,month="March" +,year="2003" +,note="Available: +\url{http://lkml.org/lkml/2003/3/9/205} +[Viewed March 13, 2006]" +,annotation=" + Linus suggests replacing brlock with RCU and/or seqlocks: + . + 'It's entirely possible that the current user could be replaced + by RCU and/or seqlocks, and we could get rid of brlocks entirely.' + . + Steve Hemminger responds by replacing them with RCU. +" } @article{Appavoo03a @@ -457,6 +758,20 @@ B. Rosenburg and M. Stumm and J. Xenidis" ,volume="42" ,number="1" ,pages="60-76" +,annotation=" + Use of RCU to enable hot-swapping for autonomic behavior in K42. +" +} + +@unpublished{Seigh03 +,author="Joseph W. {Seigh II}" +,title="Read Copy Update" +,Year="2003" +,Month="March" +,note="email correspondence" +,annotation=" + Described the relationship of the VM/XA passive serialization to RCU. +" } @Conference{Arcangeli03 @@ -470,6 +785,27 @@ Dipankar Sarma" ,year="2003" ,month="June" ,pages="297-310" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/rcu.FREENIX.2003.06.14.pdf} +[Viewed November 21, 2007]" +,annotation=" + Compared updated RCU implementations for the Linux kernel, and + described System V IPC use of RCU, including order-of-magnitude + performance improvements. +" +} + +@Conference{Soules03a +,Author="Craig A. N. Soules and Jonathan Appavoo and Kevin Hui and +Dilma {Da Silva} and Gregory R. Ganger and Orran Krieger and +Michael Stumm and Robert W. Wisniewski and Marc Auslander and +Michal Ostrowski and Bryan Rosenburg and Jimi Xenidis" +,Title="System Support for Online Reconfiguration" +,Booktitle="Proceedings of the 2003 USENIX Annual Technical Conference" +,Publisher="USENIX Association" +,year="2003" +,month="June" +,pages="141-154" } @article{McKenney03a @@ -481,6 +817,22 @@ Dipankar Sarma" ,volume="1" ,number="114" ,pages="18-26" +,note="Available: +\url{http://www.linuxjournal.com/article/6993} +[Viewed November 14, 2007]" +,annotation=" + Reader-friendly intro to RCU, with the infamous old-man-and-brat + cartoon. +" +} + +@unpublished{Sarma03a +,Author="Dipankar Sarma" +,Title="RCU low latency patches" +,month="December" +,year="2003" +,note="Message ID: [email protected]" +,annotation="dipankar/ct.2004.03.27/RCUll.2003.12.22.patch" } @techreport{Friedberg03a @@ -489,9 +841,14 @@ Dipankar Sarma" ,institution="US Patent and Trademark Office" ,address="Washington, DC" ,year="2003" -,number="US Patent 6,662,184 (contributed under GPL)" +,number="US Patent 6,662,184" ,month="December" ,pages="112" +,annotation=" + Applies RCU to a wildcard-search Patricia tree in order to permit + synchronization-free lookup. RCU is used to retain removed nodes + for a grace period before freeing them. +" } @article{McKenney04a @@ -503,6 +860,12 @@ Dipankar Sarma" ,volume="1" ,number="118" ,pages="38-46" +,note="Available: +\url{http://www.linuxjournal.com/node/7124} +[Viewed December 26, 2010]" +,annotation=" + Reader friendly intro to dcache and RCU. +" } @Conference{McKenney04b @@ -514,8 +877,83 @@ Dipankar Sarma" ,Address="Adelaide, Australia" ,note="Available: \url{http://www.linux.org.au/conf/2004/abstracts.html#90} -\url{http://www.rdrop.com/users/paulmck/rclock/lockperf.2004.01.17a.pdf} +\url{http://www.rdrop.com/users/paulmck/RCU/lockperf.2004.01.17a.pdf} [Viewed June 23, 2004]" +,annotation=" + Compares performance of RCU to that of other locking primitives + over a number of CPUs (x86, Opteron, Itanium, and PPC). +" +} + +@unpublished{Sarma04a +,Author="Dipankar Sarma" +,Title="{[PATCH]} {RCU} for low latency (experimental)" +,month="March" +,year="2004" +,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108003746402892&w=2}" +,annotation="Head of thread: dipankar/2004.03.23/rcu-low-lat.1.patch" +} + +@unpublished{Sarma04b +,Author="Dipankar Sarma" +,Title="Re: {[PATCH]} {RCU} for low latency (experimental)" +,month="March" +,year="2004" +,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108016474829546&w=2}" +,annotation="dipankar/rcuth.2004.03.24/rcu-throttle.patch" +} + +@unpublished{Spraul04a +,Author="Manfred Spraul" +,Title="[RFC] 0/5 rcu lock update" +,month="May" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108546407726602&w=2} +[Viewed June 23, 2004]" +,annotation=" + Hierarchical-bitmap patch for RCU infrastructure. +" +} + +@unpublished{Steiner04a +,Author="Jack Steiner" +,Title="Re: [Lse-tech] [RFC, PATCH] 1/5 rcu lock update: +Add per-cpu batch counter" +,month="May" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108551764515332&w=2} +[Viewed June 23, 2004]" +,annotation={ + RCU runs reasonably on a 512-CPU SGI using Manfred Spraul's patches, + which may be found at: + https://lkml.org/lkml/2004/5/20/49 (split vars into cachelines) + https://lkml.org/lkml/2004/5/22/114 (cpu_quiet() patch) + https://lkml.org/lkml/2004/5/25/24 (0/5) + https://lkml.org/lkml/2004/5/25/23 (1/5) + https://lkml.org/lkml/2004/5/25/265 (works for Jack) + https://lkml.org/lkml/2004/5/25/20 (2/5) + https://lkml.org/lkml/2004/5/25/22 (3/5) + https://lkml.org/lkml/2004/5/25/19 (4/5) + https://lkml.org/lkml/2004/5/25/21 (5/5) +} +} + +@Conference{Sarma04c +,Author="Dipankar Sarma and Paul E. McKenney" +,Title="Making {RCU} Safe for Deep Sub-Millisecond Response +Realtime Applications" +,Booktitle="Proceedings of the 2004 USENIX Annual Technical Conference +(FREENIX Track)" +,Publisher="USENIX Association" +,year="2004" +,month="June" +,pages="182-191" +,annotation=" + Describes and compares a number of modifications to the Linux RCU + implementation that make it friendly to realtime applications. +" } @phdthesis{PaulEdwardMcKenneyPhD @@ -529,17 +967,118 @@ Oregon Health and Sciences University" ,note="Available: \url{http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf} [Viewed October 15, 2004]" +,annotation=" + Describes RCU implementations and presents design patterns + corresponding to common uses of RCU in several operating-system + kernels. +" } -@Conference{Sarma04c -,Author="Dipankar Sarma and Paul E. McKenney" -,Title="Making RCU Safe for Deep Sub-Millisecond Response Realtime Applications" -,Booktitle="Proceedings of the 2004 USENIX Annual Technical Conference -(FREENIX Track)" -,Publisher="USENIX Association" +@unpublished{PaulEMcKenney2004rcu:dereference +,Author="Dipankar Sarma" +,Title="{Re: RCU : Abstracted RCU dereferencing [5/5]}" +,month="August" ,year="2004" -,month="June" -,pages="182-191" +,note="Available: +\url{http://lkml.org/lkml/2004/8/6/237} +[Viewed June 8, 2010]" +,annotation=" + Introduce rcu_dereference(). +" +} + +@unpublished{JimHouston04a +,Author="Jim Houston" +,Title="{[RFC\&PATCH] Alternative {RCU} implementation}" +,month="August" +,year="2004" +,note="Available: +\url{http://lkml.org/lkml/2004/8/30/87} +[Viewed February 17, 2005]" +,annotation=" + Uses active code in rcu_read_lock() and rcu_read_unlock() to + make RCU happen, allowing RCU to function on CPUs that do not + receive a scheduling-clock interrupt. +" +} + +@unpublished{TomHart04a +,Author="Thomas E. Hart" +,Title="Master's Thesis: Applying Lock-free Techniques to the {Linux} Kernel" +,month="October" +,year="2004" +,note="Available: +\url{http://www.cs.toronto.edu/~tomhart/masters_thesis.html} +[Viewed October 15, 2004]" +,annotation=" + Proposes comparing RCU to lock-free methods for the Linux kernel. +" +} + +@unpublished{Vaddagiri04a +,Author="Srivatsa Vaddagiri" +,Title="Subject: [RFC] Use RCU for tcp\_ehash lookup" +,month="October" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?t=109395731700004&r=1&w=2} +[Viewed October 18, 2004]" +,annotation=" + Srivatsa's RCU patch for tcp_ehash lookup. +" +} + +@unpublished{Thirumalai04a +,Author="Ravikiran Thirumalai" +,Title="Subject: [patchset] Lockfree fd lookup 0 of 5" +,month="October" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?t=109144217400003&r=1&w=2} +[Viewed October 18, 2004]" +,annotation=" + Ravikiran's lockfree FD patch. +" +} + +@unpublished{Thirumalai04b +,Author="Ravikiran Thirumalai" +,Title="Subject: Re: [patchset] Lockfree fd lookup 0 of 5" +,month="October" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=109152521410459&w=2} +[Viewed October 18, 2004]" +,annotation=" + Ravikiran's lockfree FD patch. +" +} + +@unpublished{PaulEMcKenney2004rcu:assign:pointer +,Author="Paul E. McKenney" +,Title="{[PATCH 1/3] RCU: \url{rcu_assign_pointer()} removal of memory barriers}" +,month="October" +,year="2004" +,note="Available: +\url{http://lkml.org/lkml/2004/10/23/241} +[Viewed June 8, 2010]" +,annotation=" + Introduce rcu_assign_pointer(). +" +} + +@unpublished{JamesMorris04a +,Author="James Morris" +,Title="{[PATCH 2/3] SELinux} scalability - convert {AVC} to {RCU}" +,day="15" +,month="November" +,year="2004" +,note="Available: +\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=110054979416004&w=2} +[Viewed December 10, 2004]" +,annotation=" + James Morris posts Kaigai Kohei's patch to LKML. +" } @unpublished{JamesMorris04b @@ -550,6 +1089,85 @@ Oregon Health and Sciences University" ,note="Available: \url{http://www.livejournal.com/users/james_morris/2153.html} [Viewed December 10, 2004]" +,annotation=" + RCU helps SELinux performance. ;-) Made LWN. +" +} + +@unpublished{PaulMcKenney2005RCUSemantics +,Author="Paul E. McKenney and Jonathan Walpole" +,Title="{RCU} Semantics: A First Attempt" +,month="January" +,year="2005" +,day="30" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/rcu-semantics.2005.01.30a.pdf} +[Viewed December 6, 2009]" +,annotation=" + Early derivation of RCU semantics. +" +} + +@unpublished{PaulMcKenney2005e +,Author="Paul E. McKenney" +,Title="Real-Time Preemption and {RCU}" +,month="March" +,year="2005" +,day="17" +,note="Available: +\url{http://lkml.org/lkml/2005/3/17/199} +[Viewed September 5, 2005]" +,annotation=" + First posting showing how RCU can be safely adapted for + preemptable RCU read side critical sections. +" +} + +@unpublished{EsbenNeilsen2005a +,Author="Esben Neilsen" +,Title="Re: Real-Time Preemption and {RCU}" +,month="March" +,year="2005" +,day="18" +,note="Available: +\url{http://lkml.org/lkml/2005/3/18/122} +[Viewed March 30, 2006]" +,annotation=" + Esben Neilsen suggests read-side suppression of grace-period + processing for crude-but-workable realtime RCU. The downside + is indefinite grace periods...But this is OK for experimentation + and testing. +" +} + +@unpublished{TomHart05a +,Author="Thomas E. Hart and Paul E. McKenney and Angela Demke Brown" +,Title="Efficient Memory Reclamation is Necessary for Fast Lock-Free +Data Structures" +,month="March" +,year="2005" +,note="Available: +\url{ftp://ftp.cs.toronto.edu/csrg-technical-reports/515/} +[Viewed March 4, 2005]" +,annotation=" + Comparison of RCU, QBSR, and EBSR. RCU wins for read-mostly + workloads. ;-) +" +} + +@unpublished{JonCorbet2005DeprecateSyncKernel +,Author="Jonathan Corbet" +,Title="API change: synchronize_kernel() deprecated" +,month="May" +,day="3" +,year="2005" +,note="Available: +\url{http://lwn.net/Articles/134484/} +[Viewed May 3, 2005]" +,annotation=" + Jon Corbet describes deprecation of synchronize_kernel() + in favor of synchronize_rcu() and synchronize_sched(). +" } @unpublished{PaulMcKenney05a @@ -568,7 +1186,7 @@ Oregon Health and Sciences University" @conference{PaulMcKenney05b ,Author="Paul E. McKenney and Dipankar Sarma" -,Title="Towards Hard Realtime Response from the Linux Kernel on SMP Hardware" +,Title="Towards Hard Realtime Response from the {Linux} Kernel on {SMP} Hardware" ,Booktitle="linux.conf.au 2005" ,month="April" ,year="2005" @@ -578,6 +1196,103 @@ Oregon Health and Sciences University" [Viewed May 13, 2005]" ,annotation=" Realtime turns into making RCU yet more realtime friendly. + http://lca2005.linux.org.au/Papers/Paul%20McKenney/Towards%20Hard%20Realtime%20Response%20from%20the%20Linux%20Kernel/LKS.2005.04.22a.pdf +" +} + +@unpublished{PaulEMcKenneyHomePage +,Author="Paul E. McKenney" +,Title="{Paul} {E.} {McKenney}" +,month="May" +,year="2005" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/} +[Viewed May 25, 2005]" +,annotation=" + Paul McKenney's home page. +" +} + +@unpublished{PaulEMcKenneyRCUPage +,Author="Paul E. McKenney" +,Title="Read-Copy Update {(RCU)}" +,month="May" +,year="2005" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU} +[Viewed May 25, 2005]" +,annotation=" + Paul McKenney's RCU page. +" +} + +@unpublished{JosephSeigh2005a +,Author="Joseph Seigh" +,Title="{RCU}+{SMR} (hazard pointers)" +,month="July" +,year="2005" +,note="Personal communication" +,annotation=" + Joe Seigh announcing his atomic-ptr-plus project. + http://sourceforge.net/projects/atomic-ptr-plus/ +" +} + +@unpublished{JosephSeigh2005b +,Author="Joseph Seigh" +,Title="Lock-free synchronization primitives" +,month="July" +,day="6" +,year="2005" +,note="Available: +\url{http://sourceforge.net/projects/atomic-ptr-plus/} +[Viewed August 8, 2005]" +,annotation=" + Joe Seigh's atomic-ptr-plus project. +" +} + +@unpublished{PaulMcKenney2005c +,Author="Paul E.McKenney" +,Title="{[RFC,PATCH] RCU} and {CONFIG\_PREEMPT\_RT} sane patch" +,month="August" +,day="1" +,year="2005" +,note="Available: +\url{http://lkml.org/lkml/2005/8/1/155} +[Viewed March 14, 2006]" +,annotation=" + First operating counter-based realtime RCU patch posted to LKML. +" +} + +@unpublished{PaulMcKenney2005d +,Author="Paul E. McKenney" +,Title="Re: [Fwd: Re: [patch] Real-Time Preemption, -RT-2.6.13-rc4-V0.7.52-01]" +,month="August" +,day="8" +,year="2005" +,note="Available: +\url{http://lkml.org/lkml/2005/8/8/108} +[Viewed March 14, 2006]" +,annotation=" + First operating counter-based realtime RCU patch posted to LKML, + but fixed so that various unusual combinations of configuration + parameters all function properly. +" +} + +@unpublished{PaulMcKenney2005rcutorture +,Author="Paul E. McKenney" +,Title="{[PATCH]} {RCU} torture testing" +,month="October" +,day="1" +,year="2005" +,note="Available: +\url{http://lkml.org/lkml/2005/10/1/70} +[Viewed March 14, 2006]" +,annotation=" + First rcutorture patch. " } @@ -591,22 +1306,39 @@ Distributed Processing Symposium" ,year="2006" ,day="25-29" ,address="Rhodes, Greece" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/hart_ipdps06.pdf} +[Viewed April 28, 2008]" +,annotation=" + Compares QSBR, HPBR, EBR, and lock-free reference counting. + http://www.cs.toronto.edu/~tomhart/perflab/ipdps06.tgz +" +} + +@unpublished{NickPiggin2006radixtree +,Author="Nick Piggin" +,Title="[patch 3/3] radix-tree: {RCU} lockless readside" +,month="June" +,day="20" +,year="2006" +,note="Available: +\url{http://lkml.org/lkml/2006/6/20/238} +[Viewed March 25, 2008]" ,annotation=" - Compares QSBR (AKA "classic RCU"), HPBR, EBR, and lock-free - reference counting. + RCU-protected radix tree. " } @Conference{PaulEMcKenney2006b ,Author="Paul E. McKenney and Dipankar Sarma and Ingo Molnar and Suparna Bhattacharya" -,Title="Extending RCU for Realtime and Embedded Workloads" +,Title="Extending {RCU} for Realtime and Embedded Workloads" ,Booktitle="{Ottawa Linux Symposium}" ,Month="July" ,Year="2006" ,pages="v2 123-138" ,note="Available: -\url{http://www.linuxsymposium.org/2006/index_2006.php} +\url{http://www.linuxsymposium.org/2006/view_abstract.php?content_key=184} \url{http://www.rdrop.com/users/paulmck/RCU/OLSrtRCU.2006.08.11a.pdf} [Viewed January 1, 2007]" ,annotation=" @@ -614,6 +1346,37 @@ Suparna Bhattacharya" " } +@unpublished{WikipediaRCU +,Author="Paul E. McKenney and Chris Purcell and Algae and Ben Schumin and +Gaius Cornelius and Qwertyus and Neil Conway and Sbw and Blainster and +Canis Rufus and Zoicon5 and Anome and Hal Eisen" +,Title="Read-Copy Update" +,month="July" +,day="8" +,year="2006" +,note="Available: +\url{http://en.wikipedia.org/wiki/Read-copy-update} +[Viewed August 21, 2006]" +,annotation=" + Wikipedia RCU page as of July 8 2006. +" +} + +@Conference{NickPiggin2006LocklessPageCache +,Author="Nick Piggin" +,Title="A Lockless Pagecache in Linux---Introduction, Progress, Performance" +,Booktitle="{Ottawa Linux Symposium}" +,Month="July" +,Year="2006" +,pages="v2 249-254" +,note="Available: +\url{http://www.linuxsymposium.org/2006/view_abstract.php?content_key=184} +[Viewed January 11, 2009]" +,annotation=" + Uses RCU-protected radix tree for a lockless page cache. +" +} + @unpublished{PaulEMcKenney2006c ,Author="Paul E. McKenney" ,Title="Sleepable {RCU}" @@ -637,29 +1400,301 @@ Revised: ,day="18" ,year="2006" ,note="Available: -\url{http://www.nada.kth.se/~snilsson/public/papers/trash/trash.pdf} -[Viewed February 24, 2007]" +\url{http://www.nada.kth.se/~snilsson/publications/TRASH/trash.pdf} +[Viewed March 4, 2011]" ,annotation=" RCU-protected dynamic trie-hash combination. " } -@unpublished{ThomasEHart2007a -,Author="Thomas E. Hart and Paul E. McKenney and Angela Demke Brown and Jonathan Walpole" -,Title="Performance of memory reclamation for lockless synchronization" -,journal="J. Parallel Distrib. Comput." +@unpublished{ChristophHellwig2006RCU2SRCU +,Author="Christoph Hellwig" +,Title="Re: {[-mm PATCH 1/4]} {RCU}: split classic rcu" +,month="September" +,day="28" +,year="2006" +,note="Available: +\url{http://lkml.org/lkml/2006/9/28/160} +[Viewed March 27, 2008]" +} + +@unpublished{PaulEMcKenneyRCUusagePage +,Author="Paul E. McKenney" +,Title="{RCU} {Linux} Usage" +,month="October" +,year="2006" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/linuxusage.html} +[Viewed January 14, 2007]" +,annotation=" + Paul McKenney's RCU page showing graphs plotting Linux-kernel + usage of RCU. +" +} + +@unpublished{PaulEMcKenneyRCUusageRawDataPage +,Author="Paul E. McKenney" +,Title="Read-Copy Update {(RCU)} Usage in {Linux} Kernel" +,month="October" +,year="2006" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html} +[Viewed January 14, 2007]" +,annotation=" + Paul McKenney's RCU page showing Linux usage of RCU in tabular + form, with links to corresponding cscope databases. +" +} + +@unpublished{GauthamShenoy2006RCUrwlock +,Author="Gautham R. Shenoy" +,Title="[PATCH 4/5] lock\_cpu\_hotplug: Redesign - Lightweight implementation of lock\_cpu\_hotplug" +,month="October" +,year="2006" +,day=26 +,note="Available: +\url{http://lkml.org/lkml/2006/10/26/73} +[Viewed January 26, 2009]" +,annotation=" + RCU-based reader-writer lock that allows readers to proceed with + no memory barriers or atomic instruction in absence of writers. + If writer do show up, readers must of course wait as required by + the semantics of reader-writer locking. This is a recursive + lock. +" +} + +@unpublished{JensAxboe2006SlowSRCU +,Author="Jens Axboe" +,Title="Re: [patch] cpufreq: mark \url{cpufreq_tsc()} as +\url{core_initcall_sync}" +,month="November" +,year="2006" +,day=17 +,note="Available: +\url{http://lkml.org/lkml/2006/11/17/56} +[Viewed May 28, 2007]" +,annotation=" + SRCU's grace periods are too slow for Jens, even after a + factor-of-three speedup. + Sped-up version of SRCU at http://lkml.org/lkml/2006/11/17/359. +" +} + +@unpublished{OlegNesterov2006QRCU +,Author="Oleg Nesterov" +,Title="Re: [patch] cpufreq: mark {\tt cpufreq\_tsc()} as +{\tt core\_initcall\_sync}" +,month="November" +,year="2006" +,day=19 +,note="Available: +\url{http://lkml.org/lkml/2006/11/19/69} +[Viewed May 28, 2007]" +,annotation=" + First cut of QRCU. Expanded/corrected versions followed. + Used to be OlegNesterov2007QRCU, now time-corrected. +" +} + +@unpublished{OlegNesterov2006aQRCU +,Author="Oleg Nesterov" +,Title="Re: [RFC, PATCH 1/2] qrcu: {"quick"} srcu implementation" +,month="November" +,year="2006" +,day=30 +,note="Available: +\url{http://lkml.org/lkml/2006/11/29/330} +[Viewed November 26, 2008]" +,annotation=" + Expanded/corrected version of QRCU. + Used to be OlegNesterov2007aQRCU, now time-corrected. +" +} + +@unpublished{EvgeniyPolyakov2006RCUslowdown +,Author="Evgeniy Polyakov" +,Title="Badness in postponing work" +,month="December" +,year="2006" +,day=05 +,note="Available: +\url{http://www.ioremap.net/node/41} +[Viewed October 28, 2008]" +,annotation=" + Using RCU as a pure delay leads to a 2.5x slowdown in skbs in + the Linux kernel. +" +} + +@inproceedings{ChrisMatthews2006ClusteredObjectsRCU +,author = {Matthews, Chris and Coady, Yvonne and Appavoo, Jonathan} +,title = {Portability events: a programming model for scalable system infrastructures} +,booktitle = {PLOS '06: Proceedings of the 3rd workshop on Programming languages and operating systems} +,year = {2006} +,isbn = {1-59593-577-0} +,pages = {11} +,location = {San Jose, California} +,doi = {http://doi.acm.org/10.1145/1215995.1216006} +,publisher = {ACM} +,address = {New York, NY, USA} +,annotation={ + Uses K42's RCU-like functionality to manage clustered-object + lifetimes. +}} + +@article{DilmaDaSilva2006K42 +,author = {Silva, Dilma Da and Krieger, Orran and Wisniewski, Robert W. and Waterland, Amos and Tam, David and Baumann, Andrew} +,title = {K42: an infrastructure for operating system research} +,journal = {SIGOPS Oper. Syst. Rev.} +,volume = {40} +,number = {2} +,year = {2006} +,issn = {0163-5980} +,pages = {34--42} +,doi = {http://doi.acm.org/10.1145/1131322.1131333} +,publisher = {ACM} +,address = {New York, NY, USA} +,annotation={ + Describes relationship of K42 generations to RCU. +}} + +# CoreyMinyard2007list_splice_rcu +@unpublished{CoreyMinyard2007list:splice:rcu +,Author="Corey Minyard and Paul E. McKenney" +,Title="{[PATCH]} add an {RCU} version of list splicing" +,month="January" +,year="2007" +,day=3 +,note="Available: +\url{http://lkml.org/lkml/2007/1/3/112} +[Viewed May 28, 2007]" +,annotation=" + Patch for list_splice_rcu(). +" +} + +@unpublished{PaulEMcKenney2007rcubarrier +,Author="Paul E. McKenney" +,Title="{RCU} and Unloadable Modules" +,month="January" +,day="14" +,year="2007" +,note="Available: +\url{http://lwn.net/Articles/217484/} +[Viewed November 22, 2007]" +,annotation=" + LWN article introducing the rcu_barrier() primitive. +" +} + +@unpublished{PeterZijlstra2007SyncBarrier +,Author="Peter Zijlstra and Ingo Molnar" +,Title="{[PATCH 3/7]} barrier: a scalable synchonisation barrier" +,month="January" +,year="2007" +,day=28 +,note="Available: +\url{http://lkml.org/lkml/2007/1/28/34} +[Viewed March 27, 2008]" +,annotation=" + RCU-like implementation for frequent updaters and rare readers(!). + Subsumed into QRCU. Maybe... +" +} + +@unpublished{PaulEMcKenney2007BoostRCU +,Author="Paul E. McKenney" +,Title="Priority-Boosting {RCU} Read-Side Critical Sections" +,month="February" +,day="5" +,year="2007" +,note="Available: +\url{http://lwn.net/Articles/220677/} +Revised: +\url{http://www.rdrop.com/users/paulmck/RCU/RCUbooststate.2007.04.16a.pdf} +[Viewed September 7, 2007]" +,annotation=" + LWN article introducing RCU priority boosting. +" +} + +@unpublished{PaulMcKenney2007QRCUpatch +,Author="Paul E. McKenney" +,Title="{[PATCH]} {QRCU} with lockless fastpath" +,month="February" +,year="2007" +,day=24 +,note="Available: +\url{http://lkml.org/lkml/2007/2/25/18} +[Viewed March 27, 2008]" +,annotation=" + Patch for QRCU supplying lock-free fast path. +" +} + +@article{JonathanAppavoo2007K42RCU +,author = {Appavoo, Jonathan and Silva, Dilma Da and Krieger, Orran and Auslander, Marc and Ostrowski, Michal and Rosenburg, Bryan and Waterland, Amos and Wisniewski, Robert W. and Xenidis, Jimi and Stumm, Michael and Soares, Livio} +,title = {Experience distributing objects in an SMMP OS} +,journal = {ACM Trans. Comput. Syst.} +,volume = {25} +,number = {3} +,year = {2007} +,issn = {0734-2071} +,pages = {6/1--6/52} +,doi = {http://doi.acm.org/10.1145/1275517.1275518} +,publisher = {ACM} +,address = {New York, NY, USA} +,annotation={ + Role of RCU in K42. +}} + +@conference{RobertOlsson2007Trash +,Author="Robert Olsson and Stefan Nilsson" +,Title="{TRASH}: A dynamic {LC}-trie and hash data structure" +,booktitle="Workshop on High Performance Switching and Routing (HPSR'07)" +,month="May" +,year="2007" +,note="Available: +\url{http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4281239} +[Viewed October 1, 2010]" +,annotation=" + RCU-protected dynamic trie-hash combination. +" +} + +@conference{PeterZijlstra2007ConcurrentPagecacheRCU +,Author="Peter Zijlstra" +,Title="Concurrent Pagecache" +,Booktitle="Linux Symposium" +,month="June" ,year="2007" -,note="To appear in J. Parallel Distrib. Comput. - \url{doi=10.1016/j.jpdc.2007.04.010}" +,address="Ottawa, Canada" +,note="Available: +\url{http://ols.108.redhat.com/2007/Reprints/zijlstra-Reprint.pdf} +[Viewed April 14, 2008]" +,annotation=" + Page-cache modifications permitting RCU readers and concurrent + updates. +" +} + +@unpublished{PaulEMcKenney2007whatisRCU +,Author="Paul E. McKenney" +,Title="What is {RCU}?" +,year="2007" +,month="07" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/whatisRCU.html} +[Viewed July 6, 2007]" ,annotation={ - Compares QSBR (AKA "classic RCU"), HPBR, EBR, and lock-free - reference counting. Journal version of ThomasEHart2006a. + Describes RCU in Linux kernel. } } @unpublished{PaulEMcKenney2007QRCUspin ,Author="Paul E. McKenney" -,Title="Using Promela and Spin to verify parallel algorithms" +,Title="Using {Promela} and {Spin} to verify parallel algorithms" ,month="August" ,day="1" ,year="2007" @@ -669,6 +1704,50 @@ Revised: ,annotation=" LWN article describing Promela and spin, and also using Oleg Nesterov's QRCU as an example (with Paul McKenney's fastpath). + Merged patch at: http://lkml.org/lkml/2007/2/25/18 +" +} + +@unpublished{PaulEMcKenney2007WG21DDOatomics +,Author="Paul E. McKenney and Hans-J. Boehm and Lawrence Crowl" +,Title="C++ Data-Dependency Ordering: Atomics and Memory Model" +,month="August" +,day="3" +,year="2007" +,note="Preprint: +\url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2664.htm} +[Viewed December 7, 2009]" +,annotation=" + RCU for C++, parts 1 and 2. +" +} + +@unpublished{PaulEMcKenney2007WG21DDOannotation +,Author="Paul E. McKenney and Lawrence Crowl" +,Title="C++ Data-Dependency Ordering: Function Annotation" +,month="September" +,day="18" +,year="2008" +,note="Preprint: +\url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2782.htm} +[Viewed December 7, 2009]" +,annotation=" + RCU for C++, part 2, updated many times. +" +} + +@unpublished{PaulEMcKenney2007PreemptibleRCUPatch +,Author="Paul E. McKenney" +,Title="[PATCH RFC 0/9] {RCU}: Preemptible {RCU}" +,month="September" +,day="10" +,year="2007" +,note="Available: +\url{http://lkml.org/lkml/2007/9/10/213} +[Viewed October 25, 2007]" +,annotation=" + Final patch for preemptable RCU to -rt. (Later patches were + to mainline, eventually incorporated.) " } @@ -686,10 +1765,46 @@ Revised: " } +@article{ThomasEHart2007a +,Author="Thomas E. Hart and Paul E. McKenney and Angela Demke Brown and Jonathan Walpole" +,Title="Performance of memory reclamation for lockless synchronization" +,journal="J. Parallel Distrib. Comput." +,volume={67} +,number="12" +,year="2007" +,issn="0743-7315" +,pages="1270--1285" +,doi="http://dx.doi.org/10.1016/j.jpdc.2007.04.010" +,publisher="Academic Press, Inc." +,address="Orlando, FL, USA" +,annotation={ + Compares QSBR, HPBR, EBR, and lock-free reference counting. + Journal version of ThomasEHart2006a. +} +} + +@unpublished{MathieuDesnoyers2007call:rcu:schedNeeded +,Author="Mathieu Desnoyers" +,Title="Re: [patch 1/2] {Linux} Kernel Markers - Support Multiple Probes" +,month="December" +,day="20" +,year="2007" +,note="Available: +\url{http://lkml.org/lkml/2007/12/20/244} +[Viewed March 27, 2008]" +,annotation=" + Request for call_rcu_sched() and rcu_barrier_sched(). +" +} + + ######################################################################## # # "What is RCU?" LWN series. # +# http://lwn.net/Articles/262464/ (What is RCU, Fundamentally?) +# http://lwn.net/Articles/263130/ (What is RCU's Usage?) +# http://lwn.net/Articles/264090/ (What is RCU's API?) @unpublished{PaulEMcKenney2007WhatIsRCUFundamentally ,Author="Paul E. McKenney and Jonathan Walpole" @@ -723,7 +1838,7 @@ Revised: 3. RCU is a Bulk Reference-Counting Mechanism 4. RCU is a Poor Man's Garbage Collector 5. RCU is a Way of Providing Existence Guarantees - 6. RCU is a Way of Waiting for Things to Finish + 6. RCU is a Way of Waiting for Things to Finish " } @@ -747,20 +1862,96 @@ Revised: # ######################################################################## + +@unpublished{SteveRostedt2008dyntickRCUpatch +,Author="Steven Rostedt and Paul E. McKenney" +,Title="{[PATCH]} add support for dynamic ticks and preempt rcu" +,month="January" +,day="29" +,year="2008" +,note="Available: +\url{http://lkml.org/lkml/2008/1/29/208} +[Viewed March 27, 2008]" +,annotation=" + Patch that prevents preemptible RCU from unnecessarily waking + up dynticks-idle CPUs. +" +} + +@unpublished{PaulEMcKenney2008LKMLDependencyOrdering +,Author="Paul E. McKenney" +,Title="Re: [PATCH 02/22 -v7] Add basic support for gcc profiler instrumentation" +,month="February" +,day="1" +,year="2008" +,note="Available: +\url{http://lkml.org/lkml/2008/2/2/255} +[Viewed October 18, 2008]" +,annotation=" + Explanation of compilers violating dependency ordering. +" +} + +@Conference{PaulEMcKenney2008Beijing +,Author="Paul E. McKenney" +,Title="Introducing Technology Into {Linux} Or: +Introducing your technology Into {Linux} will require introducing a +lot of {Linux} into your technology!!!" +,Booktitle="2008 Linux Developer Symposium - China" +,Publisher="OSS China" +,Month="February" +,Year="2008" +,Address="Beijing, China" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/TechIntroLinux.2008.02.19a.pdf} +[Viewed August 12, 2008]" +} + +@unpublished{PaulEMcKenney2008dynticksRCU +,Author="Paul E. McKenney and Steven Rostedt" +,Title="Integrating and Validating dynticks and Preemptable RCU" +,month="April" +,day="24" +,year="2008" +,note="Available: +\url{http://lwn.net/Articles/279077/} +[Viewed April 24, 2008]" +,annotation=" + Describes use of Promela and Spin to validate (and fix!) the + dynticks/RCU interface. +" +} + @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}" ,Year="2008" -,Month="April" +,Month="April-June" ,journal="IBM Systems Journal" ,volume="47" ,number="2" -,pages="@@-@@" +,pages="221-236" ,annotation=" RCU, realtime RCU, sleepable RCU, performance. " } +@unpublished{LaiJiangshan2008NewClassicAlgorithm +,Author="Lai Jiangshan" +,Title="[{RFC}][{PATCH}] rcu classic: new algorithm for callbacks-processing" +,month="June" +,day="3" +,year="2008" +,note="Available: +\url{http://lkml.org/lkml/2008/6/2/539} +[Viewed December 10, 2008]" +,annotation=" + Updated RCU classic algorithm. Introduced multi-tailed list + for RCU callbacks and also pulling common code into + __call_rcu(). +" +} + @article{PaulEMcKenney2008RCUOSR ,author="Paul E. McKenney and Jonathan Walpole" ,title="Introducing technology into the {Linux} kernel: a case study" @@ -778,6 +1969,52 @@ Revised: } } +@unpublished{ManfredSpraul2008StateMachineRCU +,Author="Manfred Spraul" +,Title="[{RFC}, {PATCH}] state machine based rcu" +,month="August" +,day="21" +,year="2008" +,note="Available: +\url{http://lkml.org/lkml/2008/8/21/336} +[Viewed December 8, 2008]" +,annotation=" + State-based RCU. One key thing that this patch does is to + separate the dynticks handling of NMIs and IRQs. +" +} + +@unpublished{ManfredSpraul2008dyntickIRQNMI +,Author="Manfred Spraul" +,Title="Re: [{RFC}, {PATCH}] v4 scalable classic {RCU} implementation" +,month="September" +,day="6" +,year="2008" +,note="Available: +\url{http://lkml.org/lkml/2008/9/6/86} +[Viewed December 8, 2008]" +,annotation=" + Manfred notes a fix required to my attempt to separate irq + and NMI processing for hierarchical RCU's dynticks interface. +" +} + +@techreport{PaulEMcKenney2008cyclicRCU +,author="Paul E. McKenney" +,title="Efficient Support of Consistent Cyclic Search With Read-Copy Update" +,institution="US Patent and Trademark Office" +,address="Washington, DC" +,year="2008" +,number="US Patent 7,426,511" +,month="September" +,pages="23" +,annotation=" + Maintains an additional level of indirection to allow + readers to confine themselves to the desired snapshot of the + data structure. Only permits one update at a time. +" +} + @unpublished{PaulEMcKenney2008HierarchicalRCU ,Author="Paul E. McKenney" ,Title="Hierarchical {RCU}" @@ -793,6 +2030,21 @@ Revised: " } +@unpublished{PaulEMcKenney2009BloatwatchRCU +,Author="Paul E. McKenney" +,Title="Re: [PATCH fyi] RCU: the bloatwatch edition" +,month="January" +,day="14" +,year="2009" +,note="Available: +\url{http://lkml.org/lkml/2009/1/14/449} +[Viewed January 15, 2009]" +,annotation=" + Small-footprint implementation of RCU for uniprocessor + embedded applications -- and also for exposition purposes. +" +} + @conference{PaulEMcKenney2009MaliciousURCU ,Author="Paul E. McKenney" ,Title="Using a Malicious User-Level {RCU} to Torture {RCU}-Based Algorithms" @@ -816,15 +2068,17 @@ Revised: ,year="2009" ,note="Available: \url{http://lkml.org/lkml/2009/2/5/572} -\url{git://lttng.org/userspace-rcu.git} +\url{http://lttng.org/urcu} [Viewed February 20, 2009]" ,annotation=" Mathieu Desnoyers's user-space RCU implementation. git://lttng.org/userspace-rcu.git + http://lttng.org/cgi-bin/gitweb.cgi?p=userspace-rcu.git + http://lttng.org/urcu " } -@unpublished{PaulEMcKenney2009BloatWatchRCU +@unpublished{PaulEMcKenney2009LWNBloatWatchRCU ,Author="Paul E. McKenney" ,Title="{RCU}: The {Bloatwatch} Edition" ,month="March" @@ -852,14 +2106,29 @@ Revised: " } -@unpublished{JoshTriplett2009RPHash +@unpublished{PaulEMcKenney2009fastRTRCU +,Author="Paul E. McKenney" +,Title="[{PATCH} {RFC} -tip 0/4] {RCU} cleanups and simplified preemptable {RCU}" +,month="July" +,day="23" +,year="2009" +,note="Available: +\url{http://lkml.org/lkml/2009/7/23/294} +[Viewed August 15, 2009]" +,annotation=" + First posting of simple and fast preemptable RCU. +" +} + +@InProceedings{JoshTriplett2009RPHash ,Author="Josh Triplett" ,Title="Scalable concurrent hash tables via relativistic programming" ,month="September" ,year="2009" -,note="Linux Plumbers Conference presentation" +,booktitle="Linux Plumbers Conference 2009" ,annotation=" RP fun with hash tables. + See also JoshTriplett2010RPHash " } @@ -872,4 +2141,323 @@ Revised: ,note="Available: \url{http://www.lttng.org/pub/thesis/desnoyers-dissertation-2009-12.pdf} [Viewed December 9, 2009]" +,annotation={ + Chapter 6 (page 97) covers user-level RCU. +} +} + +@unpublished{RelativisticProgrammingWiki +,Author="Josh Triplett and Paul E. McKenney and Jonathan Walpole" +,Title="Relativistic Programming" +,month="September" +,year="2009" +,note="Available: +\url{http://wiki.cs.pdx.edu/rp/} +[Viewed December 9, 2009]" +,annotation=" + Main Relativistic Programming Wiki. +" +} + +@conference{PaulEMcKenney2009DeterministicRCU +,Author="Paul E. McKenney" +,Title="Deterministic Synchronization in Multicore Systems: the Role of {RCU}" +,Booktitle="Eleventh Real Time Linux Workshop" +,month="September" +,year="2009" +,address="Dresden, Germany" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/realtime/paper/DetSyncRCU.2009.08.18a.pdf} +[Viewed January 14, 2009]" +} + +@unpublished{PaulEMcKenney2009HuntingHeisenbugs +,Author="Paul E. McKenney" +,Title="Hunting Heisenbugs" +,month="November" +,year="2009" +,day="1" +,note="Available: +\url{http://paulmck.livejournal.com/14639.html} +[Viewed June 4, 2010]" +,annotation=" + Day-one bug in Tree RCU that took forever to track down. +" +} + +@unpublished{MathieuDesnoyers2009defer:rcu +,Author="Mathieu Desnoyers" +,Title="Kernel RCU: shrink the size of the struct rcu\_head" +,month="December" +,year="2009" +,note="Available: +\url{http://lkml.org/lkml/2009/10/18/129} +[Viewed December 29, 2009]" +,annotation=" + Mathieu proposed defer_rcu() with fixed-size per-thread pool + of RCU callbacks. +" +} + +@unpublished{MathieuDesnoyers2009VerifPrePub +,Author="Mathieu Desnoyers and Paul E. McKenney and Michel R. Dagenais" +,Title="Multi-Core Systems Modeling for Formal Verification of Parallel Algorithms" +,month="December" +,year="2009" +,note="Submitted to IEEE TPDS" +,annotation=" + OOMem model for Mathieu's user-level RCU mechanical proof of + correctness. +" +} + +@unpublished{MathieuDesnoyers2009URCUPrePub +,Author="Mathieu Desnoyers and Paul E. McKenney and Alan Stern and Michel R. Dagenais and Jonathan Walpole" +,Title="User-Level Implementations of Read-Copy Update" +,month="December" +,year="2010" +,url=\url{http://www.computer.org/csdl/trans/td/2012/02/ttd2012020375-abs.html} +,annotation=" + RCU overview, desiderata, semi-formal semantics, user-level RCU + usage scenarios, three classes of RCU implementation, wait-free + RCU updates, RCU grace-period batching, update overhead, + http://www.rdrop.com/users/paulmck/RCU/urcu-main-accepted.2011.08.30a.pdf + http://www.rdrop.com/users/paulmck/RCU/urcu-supp-accepted.2011.08.30a.pdf + Superseded by MathieuDesnoyers2012URCU. +" +} + +@inproceedings{HariKannan2009DynamicAnalysisRCU +,author = {Kannan, Hari} +,title = {Ordering decoupled metadata accesses in multiprocessors} +,booktitle = {MICRO 42: Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture} +,year = {2009} +,isbn = {978-1-60558-798-1} +,pages = {381--390} +,location = {New York, New York} +,doi = {http://doi.acm.org/10.1145/1669112.1669161} +,publisher = {ACM} +,address = {New York, NY, USA} +,annotation={ + Uses RCU to protect metadata used in dynamic analysis. +}} + +@conference{PaulEMcKenney2010SimpleOptRCU +,Author="Paul E. McKenney" +,Title="Simplicity Through Optimization" +,Booktitle="linux.conf.au 2010" +,month="January" +,year="2010" +,address="Wellington, New Zealand" +,note="Available: +\url{http://www.rdrop.com/users/paulmck/RCU/SimplicityThruOptimization.2010.01.21f.pdf} +[Viewed October 10, 2010]" +,annotation=" + TREE_PREEMPT_RCU optimizations greatly simplified the old + PREEMPT_RCU implementation. +" +} + +@unpublished{PaulEMcKenney2010LockdepRCU +,Author="Paul E. McKenney" +,Title="Lockdep-{RCU}" +,month="February" +,year="2010" +,day="1" +,note="Available: +\url{https://lwn.net/Articles/371986/} +[Viewed June 4, 2010]" +,annotation=" + CONFIG_PROVE_RCU, or at least an early version. +" +} + +@unpublished{AviKivity2010KVM2RCU +,Author="Avi Kivity" +,Title="[{PATCH} 37/40] {KVM}: Bump maximum vcpu count to 64" +,month="February" +,year="2010" +,note="Available: +\url{http://www.mail-archive.com/[email protected]/msg28640.html} +[Viewed March 20, 2010]" +,annotation=" + Use of RCU permits KVM to increase the size of guest OSes from + 16 CPUs to 64 CPUs. +" +} + +@unpublished{HerbertXu2010RCUResizeHash +,Author="Herbert Xu" +,Title="bridge: Add core IGMP snooping support" +,month="February" +,year="2010" +,note="Available: +\url{http://kerneltrap.com/mailarchive/linux-netdev/2010/2/26/6270589} +[Viewed March 20, 2011]" +,annotation={ + Use a pair of list_head structures to support RCU-protected + resizable hash tables. +}} + +@article{JoshTriplett2010RPHash +,author="Josh Triplett and Paul E. McKenney and Jonathan Walpole" +,title="Scalable Concurrent Hash Tables via Relativistic Programming" +,journal="ACM Operating Systems Review" +,year=2010 +,volume=44 +,number=3 +,month="July" +,annotation={ + RP fun with hash tables. + http://portal.acm.org/citation.cfm?id=1842733.1842750 +}} + +@unpublished{PaulEMcKenney2010RCUAPI +,Author="Paul E. McKenney" +,Title="The {RCU} {API}, 2010 Edition" +,month="December" +,day="8" +,year="2010" +,note="Available: +\url{http://lwn.net/Articles/418853/} +[Viewed December 8, 2010]" +,annotation=" + Includes updated software-engineering features. +" +} + +@mastersthesis{AndrejPodzimek2010masters +,author="Andrej Podzimek" +,title="Read-Copy-Update for OpenSolaris" +,school="Charles University in Prague" +,year="2010" +,note="Available: +\url{https://andrej.podzimek.org/thesis.pdf} +[Viewed January 31, 2011]" +,annotation={ + Reviews RCU implementations and creates a few for OpenSolaris. + Drives quiescent-state detection from RCU read-side primitives, + in a manner roughly similar to that of Jim Houston. +}} + +@unpublished{LinusTorvalds2011Linux2:6:38:rc1:NPigginVFS +,Author="Linus Torvalds" +,Title="Linux 2.6.38-rc1" +,month="January" +,year="2011" +,note="Available: +\url{https://lkml.org/lkml/2011/1/18/322} +[Viewed March 4, 2011]" +,annotation={ + "The RCU-based name lookup is at the other end of the spectrum - the + absolute anti-gimmick. It's some seriously good stuff, and gets rid of + the last main global lock that really tends to hurt some kernel loads. + The dentry lock is no longer a big serializing issue. What's really + nice about it is that it actually improves performance a lot even for + single-threaded loads (on an SMP kernel), because it gets rid of some + of the most expensive parts of path component lookup, which was the + d_lock on every component lookup. So I'm seeing improvements of 30-50% + on some seriously pathname-lookup intensive loads." +}} + +@techreport{JoshTriplett2011RPScalableCorrectOrdering +,author = {Josh Triplett and Philip W. Howard and Paul E. McKenney and Jonathan Walpole} +,title = {Scalable Correct Memory Ordering via Relativistic Programming} +,year = {2011} +,number = {11-03} +,institution = {Portland State University} +,note = {\url{http://www.cs.pdx.edu/pdfs/tr1103.pdf}} +} + +@inproceedings{PhilHoward2011RCUTMRBTree +,author = {Philip W. Howard and Jonathan Walpole} +,title = {A Relativistic Enhancement to Software Transactional Memory} +,booktitle = {Proceedings of the 3rd USENIX conference on Hot topics in parallelism} +,series = {HotPar'11} +,year = {2011} +,location = {Berkeley, CA} +,pages = {1--6} +,numpages = {6} +,url = {http://www.usenix.org/event/hotpar11/tech/final_files/Howard.pdf} +,publisher = {USENIX Association} +,address = {Berkeley, CA, USA} +} + +@techreport{PaulEMcKenney2011cyclicparallelRCU +,author="Paul E. McKenney and Jonathan Walpole" +,title="Efficient Support of Consistent Cyclic Search With Read-Copy Update and Parallel Updates" +,institution="US Patent and Trademark Office" +,address="Washington, DC" +,year="2011" +,number="US Patent 7,953,778" +,month="May" +,pages="34" +,annotation=" + Maintains an array of generation numbers to track in-flight + updates and keeps an additional level of indirection to allow + readers to confine themselves to the desired snapshot of the + data structure. +" +} + +@inproceedings{Triplett:2011:RPHash +,author = {Triplett, Josh and McKenney, Paul E. and Walpole, Jonathan} +,title = {Resizable, Scalable, Concurrent Hash Tables via Relativistic Programming} +,booktitle = {Proceedings of the 2011 USENIX Annual Technical Conference} +,month = {June} +,year = {2011} +,pages = {145--158} +,numpages = {14} +,url={http://www.usenix.org/event/atc11/tech/final_files/atc11_proceedings.pdf} +,publisher = {The USENIX Association} +,address = {Portland, OR USA} +} + +@unpublished{PaulEMcKenney2011RCU3.0trainwreck +,Author="Paul E. McKenney" +,Title="3.0 and {RCU:} what went wrong" +,month="July" +,day="27" +,year="2011" +,note="Available: +\url{http://lwn.net/Articles/453002/} +[Viewed July 27, 2011]" +,annotation=" + Analysis of the RCU trainwreck in Linux kernel 3.0. +" +} + +@unpublished{NeilBrown2011MeetTheLockers +,Author="Neil Brown" +,Title="Meet the Lockers" +,month="August" +,day="3" +,year="2011" +,note="Available: +\url{http://lwn.net/Articles/453685/} +[Viewed September 2, 2011]" +,annotation=" + The Locker family as an analogy for locking, reference counting, + RCU, and seqlock. +" +} + +@article{MathieuDesnoyers2012URCU +,Author="Mathieu Desnoyers and Paul E. McKenney and Alan Stern and Michel R. Dagenais and Jonathan Walpole" +,Title="User-Level Implementations of Read-Copy Update" +,journal="IEEE Transactions on Parallel and Distributed Systems" +,volume={23} +,year="2012" +,issn="1045-9219" +,pages="375-382" +,doi="http://doi.ieeecomputersociety.org/10.1109/TPDS.2011.159" +,publisher="IEEE Computer Society" +,address="Los Alamitos, CA, USA" +,annotation={ + RCU overview, desiderata, semi-formal semantics, user-level RCU + usage scenarios, three classes of RCU implementation, wait-free + RCU updates, RCU grace-period batching, update overhead, + http://www.rdrop.com/users/paulmck/RCU/urcu-main-accepted.2011.08.30a.pdf + http://www.rdrop.com/users/paulmck/RCU/urcu-supp-accepted.2011.08.30a.pdf +} } diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index bff2d8be1e18..5c8d74968090 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -180,6 +180,20 @@ over a rather long period of time, but improvements are always welcome! operations that would not normally be undertaken while a real-time workload is running. + In particular, if you find yourself invoking one of the expedited + primitives repeatedly in a loop, please do everyone a favor: + Restructure your code so that it batches the updates, allowing + a single non-expedited primitive to cover the entire batch. + This will very likely be faster than the loop containing the + expedited primitive, and will be much much easier on the rest + of the system, especially to real-time workloads running on + the rest of the system. + + In addition, it is illegal to call the expedited forms from + a CPU-hotplug notifier, or while holding a lock that is acquired + by a CPU-hotplug notifier. Failing to observe this restriction + will result in deadlock. + 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 diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 083d88cbc089..523364e4e1f1 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -12,14 +12,38 @@ CONFIG_RCU_CPU_STALL_TIMEOUT This kernel configuration parameter defines the period of time that RCU will wait from the beginning of a grace period until it issues an RCU CPU stall warning. This time period is normally - ten seconds. + sixty seconds. -RCU_SECONDS_TILL_STALL_RECHECK + This configuration parameter may be changed at runtime via the + /sys/module/rcutree/parameters/rcu_cpu_stall_timeout, however + this parameter is checked only at the beginning of a cycle. + So if you are 30 seconds into a 70-second stall, setting this + sysfs parameter to (say) five will shorten the timeout for the + -next- stall, or the following warning for the current stall + (assuming the stall lasts long enough). It will not affect the + timing of the next warning for the current stall. - This macro defines the period of time that RCU will wait after - issuing a stall warning until it issues another stall warning - for the same stall. This time period is normally set to three - times the check interval plus thirty seconds. + Stall-warning messages may be enabled and disabled completely via + /sys/module/rcutree/parameters/rcu_cpu_stall_suppress. + +CONFIG_RCU_CPU_STALL_VERBOSE + + This kernel configuration parameter causes the stall warning to + also dump the stacks of any tasks that are blocking the current + RCU-preempt grace period. + +RCU_CPU_STALL_INFO + + This kernel configuration parameter causes the stall warning to + print out additional per-CPU diagnostic information, including + information on scheduling-clock ticks and RCU's idle-CPU tracking. + +RCU_STALL_DELAY_DELTA + + Although the lockdep facility is extremely useful, it does add + some overhead. Therefore, under CONFIG_PROVE_RCU, the + RCU_STALL_DELAY_DELTA macro allows five extra seconds before + giving an RCU CPU stall warning message. RCU_STALL_RAT_DELAY @@ -64,6 +88,54 @@ INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffi This is rare, but does happen from time to time in real life. +If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set, +more information is printed with the stall-warning message, for example: + + INFO: rcu_preempt detected stall on CPU + 0: (63959 ticks this GP) idle=241/3fffffffffffffff/0 + (t=65000 jiffies) + +In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is +printed: + + INFO: rcu_preempt detected stall on CPU + 0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 drain=0 . timer=-1 + (t=65000 jiffies) + +The "(64628 ticks this GP)" indicates that this CPU has taken more +than 64,000 scheduling-clock interrupts during the current stalled +grace period. If the CPU was not yet aware of the current grace +period (for example, if it was offline), then this part of the message +indicates how many grace periods behind the CPU is. + +The "idle=" portion of the message prints the dyntick-idle state. +The hex number before the first "/" is the low-order 12 bits of the +dynticks counter, which will have an even-numbered value if the CPU is +in dyntick-idle mode and an odd-numbered value otherwise. The hex +number between the two "/"s is the value of the nesting, which will +be a small positive number if in the idle loop and a very large positive +number (as shown above) otherwise. + +For CONFIG_RCU_FAST_NO_HZ kernels, the "drain=0" indicates that the +CPU is not in the process of trying to force itself into dyntick-idle +state, the "." indicates that the CPU has not given up forcing RCU +into dyntick-idle mode (it would be "H" otherwise), and the "timer=-1" +indicates that the CPU has not recented forced RCU into dyntick-idle +mode (it would otherwise indicate the number of microseconds remaining +in this forced state). + + +Multiple Warnings From One Stall + +If a stall lasts long enough, multiple stall-warning messages will be +printed for it. The second and subsequent messages are printed at +longer intervals, so that the time between (say) the first and second +message will be about three times the interval between the beginning +of the stall and the first message. + + +What Causes RCU CPU Stall Warnings? + So your kernel printed an RCU CPU stall warning. The next question is "What caused it?" The following problems can result in RCU CPU stall warnings: @@ -128,4 +200,5 @@ is occurring, which will usually be in the function nearest the top of that portion of the stack which remains the same from trace to trace. If you can reliably trigger the stall, ftrace can be quite helpful. -RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE. +RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE +and with RCU's event tracing. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index d67068d0d2b9..375d3fb71437 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -69,6 +69,13 @@ onoff_interval CPU-hotplug operations regardless of what value is specified for onoff_interval. +onoff_holdoff The number of seconds to wait until starting CPU-hotplug + operations. This would normally only be used when + rcutorture was built into the kernel and started + automatically at boot time, in which case it is useful + in order to avoid confusing boot-time code with CPUs + coming and going. + shuffle_interval The number of seconds to keep the test threads affinitied to a particular subset of the CPUs, defaults to 3 seconds. @@ -79,6 +86,24 @@ shutdown_secs The number of seconds to run the test before terminating zero, which disables test termination and system shutdown. This capability is useful for automated testing. +stall_cpu The number of seconds that a CPU should be stalled while + within both an rcu_read_lock() and a preempt_disable(). + This stall happens only once per rcutorture run. + If you need multiple stalls, use modprobe and rmmod to + repeatedly run rcutorture. The default for stall_cpu + is zero, which prevents rcutorture from stalling a CPU. + + Note that attempts to rmmod rcutorture while the stall + is ongoing will hang, so be careful what value you + choose for this module parameter! In addition, too-large + values for stall_cpu might well induce failures and + warnings in other parts of the kernel. You have been + warned! + +stall_cpu_holdoff + The number of seconds to wait after rcutorture starts + before stalling a CPU. Defaults to 10 seconds. + stat_interval The number of seconds between output of torture statistics (via printk()). Regardless of the interval, statistics are printed when the module is unloaded. @@ -271,11 +296,13 @@ The following script may be used to torture RCU: #!/bin/sh modprobe rcutorture - sleep 100 + sleep 3600 rmmod rcutorture dmesg | grep torture: The output can be manually inspected for the error flag of "!!!". One could of course create a more elaborate script that automatically -checked for such errors. The "rmmod" command forces a "SUCCESS" or -"FAILURE" indication to be printk()ed. +checked for such errors. The "rmmod" command forces a "SUCCESS", +"FAILURE", or "RCU_HOTPLUG" indication to be printk()ed. The first +two are self-explanatory, while the last indicates that while there +were no RCU failures, CPU-hotplug problems were detected. diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index 49587abfc2f7..f6f15ce39903 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -33,23 +33,23 @@ rcu/rcuboost: The output of "cat rcu/rcudata" looks as follows: rcu_sched: - 0 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=545/1/0 df=50 of=0 ri=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0 - 1 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=967/1/0 df=58 of=0 ri=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0 - 2 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1081/1/0 df=175 of=0 ri=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0 - 3 c=20942 g=20943 pq=1 pgp=20942 qp=1 dt=1846/0/0 df=404 of=0 ri=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0 - 4 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=369/1/0 df=83 of=0 ri=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0 - 5 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=381/1/0 df=64 of=0 ri=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0 - 6 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1037/1/0 df=183 of=0 ri=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0 - 7 c=20897 g=20897 pq=1 pgp=20896 qp=0 dt=1572/0/0 df=382 of=0 ri=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0 + 0 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=545/1/0 df=50 of=0 ql=163 qs=NRW. kt=0/W/0 ktl=ebc3 b=10 ci=153737 co=0 ca=0 + 1 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=967/1/0 df=58 of=0 ql=634 qs=NRW. kt=0/W/1 ktl=58c b=10 ci=191037 co=0 ca=0 + 2 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1081/1/0 df=175 of=0 ql=74 qs=N.W. kt=0/W/2 ktl=da94 b=10 ci=75991 co=0 ca=0 + 3 c=20942 g=20943 pq=1 pgp=20942 qp=1 dt=1846/0/0 df=404 of=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=72261 co=0 ca=0 + 4 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=369/1/0 df=83 of=0 ql=48 qs=N.W. kt=0/W/4 ktl=e0e7 b=10 ci=128365 co=0 ca=0 + 5 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=381/1/0 df=64 of=0 ql=169 qs=NRW. kt=0/W/5 ktl=fb2f b=10 ci=164360 co=0 ca=0 + 6 c=20972 g=20973 pq=1 pgp=20973 qp=0 dt=1037/1/0 df=183 of=0 ql=62 qs=N.W. kt=0/W/6 ktl=d2ad b=10 ci=65663 co=0 ca=0 + 7 c=20897 g=20897 pq=1 pgp=20896 qp=0 dt=1572/0/0 df=382 of=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=75006 co=0 ca=0 rcu_bh: - 0 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=545/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0 - 1 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=967/1/0 df=3 of=0 ri=1 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0 - 2 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1081/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0 - 3 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1846/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0 - 4 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=369/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0 - 5 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=381/1/0 df=4 of=0 ri=1 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0 - 6 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1037/1/0 df=6 of=0 ri=1 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0 - 7 c=1474 g=1474 pq=1 pgp=1473 qp=0 dt=1572/0/0 df=8 of=0 ri=1 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0 + 0 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=545/1/0 df=6 of=0 ql=0 qs=.... kt=0/W/0 ktl=ebc3 b=10 ci=0 co=0 ca=0 + 1 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=967/1/0 df=3 of=0 ql=0 qs=.... kt=0/W/1 ktl=58c b=10 ci=151 co=0 ca=0 + 2 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1081/1/0 df=6 of=0 ql=0 qs=.... kt=0/W/2 ktl=da94 b=10 ci=0 co=0 ca=0 + 3 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1846/0/0 df=8 of=0 ql=0 qs=.... kt=0/W/3 ktl=d1cd b=10 ci=0 co=0 ca=0 + 4 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=369/1/0 df=6 of=0 ql=0 qs=.... kt=0/W/4 ktl=e0e7 b=10 ci=0 co=0 ca=0 + 5 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=381/1/0 df=4 of=0 ql=0 qs=.... kt=0/W/5 ktl=fb2f b=10 ci=0 co=0 ca=0 + 6 c=1480 g=1480 pq=1 pgp=1480 qp=0 dt=1037/1/0 df=6 of=0 ql=0 qs=.... kt=0/W/6 ktl=d2ad b=10 ci=0 co=0 ca=0 + 7 c=1474 g=1474 pq=1 pgp=1473 qp=0 dt=1572/0/0 df=8 of=0 ql=0 qs=.... kt=0/W/7 ktl=cf15 b=10 ci=0 co=0 ca=0 The first section lists the rcu_data structures for rcu_sched, the second for rcu_bh. Note that CONFIG_TREE_PREEMPT_RCU kernels will have an @@ -119,10 +119,6 @@ o "of" is the number of times that some other CPU has forced a CPU is offline when it is really alive and kicking) is a fatal error, so it makes sense to err conservatively. -o "ri" is the number of times that RCU has seen fit to send a - reschedule IPI to this CPU in order to get it to report a - quiescent state. - o "ql" is the number of RCU callbacks currently residing on this CPU. This is the total number of callbacks, regardless of what state they are in (new, waiting for grace period to diff --git a/Documentation/hwmon/w83627ehf b/Documentation/hwmon/w83627ehf index 3f44dbdfda70..ceaf6f652b00 100644 --- a/Documentation/hwmon/w83627ehf +++ b/Documentation/hwmon/w83627ehf @@ -50,7 +50,7 @@ W83627DHG, W83627DHG-P, W83627UHG, W83667HG, W83667HG-B, W83667HG-I (NCT6775F), and NCT6776F super I/O chips. We will refer to them collectively as Winbond chips. -The chips implement 2 to 4 temperature sensors (9 for NCT6775F and NCT6776F), +The chips implement 3 to 4 temperature sensors (9 for NCT6775F and NCT6776F), 2 to 5 fan rotation speed sensors, 8 to 10 analog voltage sensors, one VID (except for 627UHG), alarms with beep warnings (control unimplemented), and some automatic fan regulation strategies (plus manual fan control mode). @@ -143,8 +143,13 @@ pwm[1-4]_min_output - minimum fan speed (range 1 - 255), when the temperature pwm[1-4]_stop_time - how many milliseconds [ms] must elapse to switch corresponding fan off. (when the temperature was below defined range). +pwm[1-4]_start_output-minimum fan speed (range 1 - 255) when spinning up +pwm[1-4]_step_output- rate of fan speed change (1 - 255) +pwm[1-4]_stop_output- minimum fan speed (range 1 - 255) when spinning down +pwm[1-4]_max_output - maximum fan speed (range 1 - 255), when the temperature + is above defined range. -Note: last two functions are influenced by other control bits, not yet exported +Note: last six functions are influenced by other control bits, not yet exported by the driver, so a change might not have any effect. Implementation Details diff --git a/Documentation/hwmon/zl6100 b/Documentation/hwmon/zl6100 index 51f76a189fee..a4e8d90f59f6 100644 --- a/Documentation/hwmon/zl6100 +++ b/Documentation/hwmon/zl6100 @@ -88,14 +88,12 @@ Module parameters delay ----- -Some Intersil/Zilker Labs DC-DC controllers require a minimum interval between -I2C bus accesses. According to Intersil, the minimum interval is 2 ms, though -1 ms appears to be sufficient and has not caused any problems in testing. -The problem is known to affect ZL6100, ZL2105, and ZL2008. It is known not to -affect ZL2004 and ZL6105. The driver automatically sets the interval to 1 ms -except for ZL2004 and ZL6105. To enable manual override, the driver provides a -writeable module parameter, 'delay', which can be used to set the interval to -a value between 0 and 65,535 microseconds. +Intersil/Zilker Labs DC-DC controllers require a minimum interval between I2C +bus accesses. According to Intersil, the minimum interval is 2 ms, though 1 ms +appears to be sufficient and has not caused any problems in testing. The problem +is known to affect all currently supported chips. For manual override, the +driver provides a writeable module parameter, 'delay', which can be used to set +the interval to a value between 0 and 65,535 microseconds. Sysfs entries diff --git a/Documentation/scheduler/sched-stats.txt b/Documentation/scheduler/sched-stats.txt index 1cd5d51bc761..8259b34a66ae 100644 --- a/Documentation/scheduler/sched-stats.txt +++ b/Documentation/scheduler/sched-stats.txt @@ -38,7 +38,8 @@ First field is a sched_yield() statistic: 1) # of times sched_yield() was called Next three are schedule() statistics: - 2) # of times we switched to the expired queue and reused it + 2) This field is a legacy array expiration count field used in the O(1) + scheduler. We kept it for ABI compatibility, but it is always set to zero. 3) # of times schedule() was called 4) # of times schedule() left the processor idle diff --git a/MAINTAINERS b/MAINTAINERS index 95e4e43a12b4..9c63a43ab63a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1513,19 +1513,23 @@ F: drivers/mtd/devices/block2mtd.c BLUETOOTH DRIVERS M: Marcel Holtmann <[email protected]> -M: "Gustavo F. Padovan" <[email protected]> +M: Gustavo Padovan <[email protected]> +M: Johan Hedberg <[email protected]> W: http://www.bluez.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jh/bluetooth.git S: Maintained F: drivers/bluetooth/ BLUETOOTH SUBSYSTEM M: Marcel Holtmann <[email protected]> -M: "Gustavo F. Padovan" <[email protected]> +M: Gustavo Padovan <[email protected]> +M: Johan Hedberg <[email protected]> W: http://www.bluez.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/padovan/bluetooth.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jh/bluetooth.git S: Maintained F: net/bluetooth/ F: include/net/bluetooth/ @@ -1717,6 +1721,14 @@ F: include/linux/can/error.h F: include/linux/can/netlink.h F: include/linux/can/platform/ +CAPABILITIES +M: Serge Hallyn <[email protected]> +S: Supported +F: include/linux/capability.h +F: security/capability.c +F: security/commoncap.c + CELL BROADBAND ENGINE ARCHITECTURE M: Arnd Bergmann <[email protected]> @@ -2351,6 +2363,15 @@ S: Supported F: drivers/gpu/drm/exynos F: include/drm/exynos* +EXYNOS MIPI DISPLAY DRIVERS +M: Inki Dae <[email protected]> +M: Donghwa Lee <[email protected]> +M: Kyungmin Park <[email protected]> +S: Maintained +F: drivers/video/exynos/exynos_mipi* +F: include/video/exynos_mipi* + DSCC4 DRIVER M: Francois Romieu <[email protected]> @@ -5859,6 +5880,7 @@ F: drivers/mmc/host/sdhci-s3c.c SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) ST SPEAR DRIVER M: Viresh Kumar <[email protected]> S: Maintained F: drivers/mmc/host/sdhci-spear.c @@ -6201,24 +6223,32 @@ F: drivers/tty/serial/sunzilog.h SPEAR PLATFORM SUPPORT M: Viresh Kumar <[email protected]> +L: [email protected] (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained F: arch/arm/plat-spear/ SPEAR3XX MACHINE SUPPORT M: Viresh Kumar <[email protected]> +L: [email protected] (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained F: arch/arm/mach-spear3xx/ SPEAR6XX MACHINE SUPPORT M: Rajeev Kumar <[email protected]> +L: [email protected] (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained F: arch/arm/mach-spear6xx/ SPEAR CLOCK FRAMEWORK SUPPORT M: Viresh Kumar <[email protected]> +L: [email protected] (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained F: arch/arm/mach-spear*/clock.c @@ -6227,6 +6257,8 @@ F: arch/arm/plat-spear/include/plat/clock.h SPEAR PAD MULTIPLEXING SUPPORT M: Viresh Kumar <[email protected]> +L: [email protected] (moderated for non-subscribers) W: http://www.st.com/spear S: Maintained F: arch/arm/plat-spear/include/plat/padmux.h @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 971d65c253a9..c2ae3cd331fe 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -239,9 +239,7 @@ void cpu_idle(void) leds_event(led_idle_end); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index cdeb727527d3..d616ed51e7a7 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -295,13 +295,6 @@ asmlinkage void __cpuinit secondary_start_kernel(void) */ percpu_timer_setup(); - while (!cpu_active(cpu)) - cpu_relax(); - - /* - * cpu_active bit is set, so it's safe to enalbe interrupts - * now. - */ local_irq_enable(); local_fiq_enable(); diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index ea3395750324..92c5af98a6f7 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -40,9 +40,7 @@ void cpu_idle(void) cpu_idle_sleep(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 8dd0416673cb..a80a643f3691 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -94,9 +94,7 @@ void cpu_idle(void) idle(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/c6x/kernel/entry.S b/arch/c6x/kernel/entry.S index 3e977ccda827..30b37e5f4a61 100644 --- a/arch/c6x/kernel/entry.S +++ b/arch/c6x/kernel/entry.S @@ -717,33 +717,6 @@ ENTRY(sys_ftruncate64_c6x) #endif ENDPROC(sys_ftruncate64_c6x) -#ifdef __ARCH_WANT_SYSCALL_OFF_T -;; On Entry -;; A4 - fd -;; B4 - offset_lo (LE), offset_hi (BE) -;; A6 - offset_lo (BE), offset_hi (LE) -;; B6 - len -;; A8 - advice -ENTRY(sys_fadvise64_c6x) -#ifdef CONFIG_C6X_BIG_KERNEL - MVKL .S1 sys_fadvise64,A0 - MVKH .S1 sys_fadvise64,A0 - BNOP .S2X A0,2 -#else - B .S2 sys_fadvise64 - NOP 2 -#endif -#ifdef CONFIG_CPU_BIG_ENDIAN - MV .L2 B4,B5 - || MV .D2X A6,B4 -#else - MV .D2X A6,B5 -#endif - MV .D1X B6,A6 - MV .D2X A8,B6 -#endif -ENDPROC(sys_fadvise64_c6x) - ;; On Entry ;; A4 - fd ;; B4 - offset_lo (LE), offset_hi (BE) diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c index aa585e4e979e..d8f50ff6fadd 100644 --- a/arch/cris/kernel/process.c +++ b/arch/cris/kernel/process.c @@ -115,9 +115,7 @@ void cpu_idle (void) idle = default_idle; idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c index 3901df1213c0..29cc49783787 100644 --- a/arch/frv/kernel/process.c +++ b/arch/frv/kernel/process.c @@ -92,9 +92,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 933bd388efb2..1a173b35f475 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -81,9 +81,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index c871a2cffaef..0123c63e9a3a 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -179,8 +179,6 @@ void __cpuinit start_secondary(void) printk(KERN_INFO "%s cpu %d\n", __func__, current_thread_info()->cpu); set_cpu_online(cpu, true); - while (!cpumask_test_cpu(cpu, cpu_active_mask)) - cpu_relax(); local_irq_enable(); cpu_idle(); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 6d33c5cc94f0..9dc52b63fc87 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -330,9 +330,7 @@ cpu_idle (void) normal_xtp(); #endif } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); if (cpu_is_offline(cpu)) play_dead(); diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c index 422bea9f1dbc..3a4a32b27208 100644 --- a/arch/m32r/kernel/process.c +++ b/arch/m32r/kernel/process.c @@ -90,9 +90,7 @@ void cpu_idle (void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c index 099283ee1a8f..fe4186b5fc32 100644 --- a/arch/m68k/kernel/process_mm.c +++ b/arch/m68k/kernel/process_mm.c @@ -78,9 +78,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c index 5e1078cabe0e..f7fe6c348595 100644 --- a/arch/m68k/kernel/process_no.c +++ b/arch/m68k/kernel/process_no.c @@ -73,9 +73,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 7dcb5bfffb75..9155f7d92669 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -110,9 +110,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 7955409051c4..61f1cb45a1d5 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -80,9 +80,7 @@ void __noreturn cpu_idle(void) #endif rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 28eec3102535..cac401d37f75 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -123,9 +123,7 @@ void cpu_idle(void) idle(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 62c60b87d039..d4b94b395c16 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -71,9 +71,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 0a48bf5db6c8..c97fc60c790c 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -101,11 +101,11 @@ void cpu_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - if (cpu_should_die()) + if (cpu_should_die()) { + sched_preempt_enable_no_resched(); cpu_die(); - schedule(); - preempt_disable(); + } + schedule_preempt_disabled(); } } diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 8fc62586a973..a5fbf4cb6329 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -584,9 +584,7 @@ static void iseries_shared_idle(void) if (hvlpevent_is_pending()) process_iSeries_events(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } @@ -615,9 +613,7 @@ static void iseries_dedicated_idle(void) ppc64_runlatch_on(); rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index b9a7fdd9c814..e30b2dfa8ba0 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -165,13 +165,6 @@ static inline int ext_hash(u16 code) return (code + (code >> 9)) & 0xff; } -static void ext_int_hash_update(struct rcu_head *head) -{ - struct ext_int_info *p = container_of(head, struct ext_int_info, rcu); - - kfree(p); -} - int register_external_interrupt(u16 code, ext_int_handler_t handler) { struct ext_int_info *p; @@ -202,7 +195,7 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler) list_for_each_entry_rcu(p, &ext_int_hash[index], entry) if (p->code == code && p->handler == handler) { list_del_rcu(&p->entry); - call_rcu(&p->rcu, ext_int_hash_update); + kfree_rcu(p, rcu); } spin_unlock_irqrestore(&ext_int_hash_lock, flags); return 0; diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index e795933eb2cb..7618085b4164 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -97,9 +97,7 @@ void cpu_idle(void) tick_nohz_idle_exit(); if (test_thread_flag(TIF_MCCK_PENDING)) s390_handle_mcck(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 2398ce6b15ae..b0e28c47ab83 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -550,12 +550,6 @@ int __cpuinit start_secondary(void *cpuvoid) S390_lowcore.restart_psw.addr = PSW_ADDR_AMODE | (unsigned long) psw_restart_int_handler; __ctl_set_bit(0, 28); /* Enable lowcore protection */ - /* - * Wait until the cpu which brought this one up marked it - * active before enabling interrupts. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); local_irq_enable(); /* cpu_idle will call schedule for us */ cpu_idle(); diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c index 25d08030a883..2707023c7563 100644 --- a/arch/score/kernel/process.c +++ b/arch/score/kernel/process.c @@ -53,9 +53,7 @@ void __noreturn cpu_idle(void) while (!need_resched()) barrier(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 406508d4ce74..7e4892826563 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -114,9 +114,7 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index f793742eec2b..935fdbcd88c2 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } @@ -138,9 +136,7 @@ void cpu_idle(void) while (!need_resched()) cpu_relax(); } - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); check_pgt_cache(); } } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 39d8b05201a2..06b5b5fc20c7 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -104,15 +104,13 @@ void cpu_idle(void) rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - #ifdef CONFIG_HOTPLUG_CPU - if (cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) { + sched_preempt_enable_no_resched(); cpu_play_dead(); + } #endif - - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 7960d5896504..b8d99aca5431 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -1,363 +1,93 @@ -# -# Automatically generated file; DO NOT EDIT. -# Linux/tilegx 3.3.0-rc7 Kernel Configuration -# -CONFIG_TILE=y -CONFIG_MMU=y -CONFIG_GENERIC_CSUM=y -CONFIG_SEMAPHORE_SLEEPERS=y -CONFIG_HAVE_ARCH_ALLOC_REMAP=y -CONFIG_HAVE_SETUP_PER_CPU_AREA=y -CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y -CONFIG_SYS_SUPPORTS_HUGETLBFS=y -CONFIG_GENERIC_CLOCKEVENTS=y -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_DEFAULT_MIGRATION_COST=10000000 -CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y -CONFIG_ARCH_PHYS_ADDR_T_64BIT=y -CONFIG_ARCH_DMA_ADDR_T_64BIT=y -CONFIG_LOCKDEP_SUPPORT=y -CONFIG_STACKTRACE_SUPPORT=y -CONFIG_ARCH_DISCONTIGMEM_ENABLE=y -CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y -CONFIG_TRACE_IRQFLAGS_SUPPORT=y -CONFIG_STRICT_DEVMEM=y -CONFIG_SMP=y -# CONFIG_DEBUG_COPY_FROM_USER is not set -CONFIG_HVC_TILE=y CONFIG_TILEGX=y -CONFIG_64BIT=y -CONFIG_ARCH_DEFCONFIG="arch/tile/configs/tilegx_defconfig" -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" - -# -# General setup -# CONFIG_EXPERIMENTAL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 -CONFIG_CROSS_COMPILE="" -CONFIG_LOCALVERSION="" # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="(none)" -CONFIG_SWAP=y CONFIG_SYSVIPC=y -CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y -CONFIG_POSIX_MQUEUE_SYSCTL=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y -# CONFIG_FHANDLE is not set +CONFIG_FHANDLE=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y -# CONFIG_AUDIT_LOGINUID_IMMUTABLE is not set -CONFIG_HAVE_GENERIC_HARDIRQS=y - -# -# IRQ subsystem -# -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_GENERIC_IRQ_SHOW=y -CONFIG_GENERIC_PENDING_IRQ=y - -# -# RCU Subsystem -# -CONFIG_TREE_RCU=y -# CONFIG_PREEMPT_RCU is not set -# CONFIG_RCU_TRACE is not set -CONFIG_RCU_FANOUT=64 -# CONFIG_RCU_FANOUT_EXACT is not set -# CONFIG_RCU_FAST_NO_HZ is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=19 CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y -# CONFIG_CGROUP_FREEZER is not set CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y -CONFIG_PROC_PID_CPUSET=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEM_RES_CTLR=y CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED=y -# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set CONFIG_CGROUP_SCHED=y -CONFIG_FAIR_GROUP_SCHED=y -# CONFIG_CFS_BANDWIDTH is not set CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y -# CONFIG_DEBUG_BLK_CGROUP is not set -# CONFIG_CHECKPOINT_RESTORE is not set CONFIG_NAMESPACES=y -CONFIG_UTS_NS=y -CONFIG_IPC_NS=y -CONFIG_USER_NS=y -CONFIG_PID_NS=y -CONFIG_NET_NS=y -# CONFIG_SCHED_AUTOGROUP is not set -CONFIG_MM_OWNER=y -# CONFIG_SYSFS_DEPRECATED is not set CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_RD_GZIP=y -# CONFIG_RD_BZIP2 is not set -# CONFIG_RD_LZMA is not set -# CONFIG_RD_XZ is not set -# CONFIG_RD_LZO is not set -CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_SYSCTL=y -CONFIG_ANON_INODES=y -CONFIG_EXPERT=y CONFIG_SYSCTL_SYSCALL=y -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -CONFIG_HOTPLUG=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_ELF_CORE=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SIGNALFD=y -CONFIG_TIMERFD=y -CONFIG_EVENTFD=y -CONFIG_SHMEM=y -CONFIG_AIO=y CONFIG_EMBEDDED=y - -# -# Kernel Performance Events And Counters -# -CONFIG_VM_EVENT_COUNTERS=y -CONFIG_PCI_QUIRKS=y -CONFIG_SLUB_DEBUG=y # CONFIG_COMPAT_BRK is not set -# CONFIG_SLAB is not set -CONFIG_SLUB=y -# CONFIG_SLOB is not set CONFIG_PROFILING=y -CONFIG_USE_GENERIC_SMP_HELPERS=y -CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y - -# -# GCOV-based kernel profiling -# -# CONFIG_GCOV_KERNEL is not set -# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set -CONFIG_SLABINFO=y -CONFIG_RT_MUTEXES=y -CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_STOP_MACHINE=y -CONFIG_BLOCK=y -CONFIG_BLK_DEV_BSG=y -# CONFIG_BLK_DEV_BSGLIB is not set CONFIG_BLK_DEV_INTEGRITY=y -# CONFIG_BLK_DEV_THROTTLING is not set - -# -# Partition Types -# CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set CONFIG_OSF_PARTITION=y CONFIG_AMIGA_PARTITION=y -# CONFIG_ATARI_PARTITION is not set CONFIG_MAC_PARTITION=y -CONFIG_MSDOS_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -# CONFIG_LDM_PARTITION is not set CONFIG_SGI_PARTITION=y -# CONFIG_ULTRIX_PARTITION is not set CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -# CONFIG_SYSV68_PARTITION is not set -CONFIG_BLOCK_COMPAT=y - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y CONFIG_CFQ_GROUP_IOSCHED=y -# CONFIG_DEFAULT_DEADLINE is not set -CONFIG_DEFAULT_CFQ=y -# CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="cfq" -CONFIG_PADATA=y -# CONFIG_INLINE_SPIN_TRYLOCK is not set -# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK is not set -# CONFIG_INLINE_SPIN_LOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK_IRQ is not set -# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set -CONFIG_INLINE_SPIN_UNLOCK=y -# CONFIG_INLINE_SPIN_UNLOCK_BH is not set -CONFIG_INLINE_SPIN_UNLOCK_IRQ=y -# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_READ_TRYLOCK is not set -# CONFIG_INLINE_READ_LOCK is not set -# CONFIG_INLINE_READ_LOCK_BH is not set -# CONFIG_INLINE_READ_LOCK_IRQ is not set -# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set -CONFIG_INLINE_READ_UNLOCK=y -# CONFIG_INLINE_READ_UNLOCK_BH is not set -CONFIG_INLINE_READ_UNLOCK_IRQ=y -# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_WRITE_TRYLOCK is not set -# CONFIG_INLINE_WRITE_LOCK is not set -# CONFIG_INLINE_WRITE_LOCK_BH is not set -# CONFIG_INLINE_WRITE_LOCK_IRQ is not set -# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set -CONFIG_INLINE_WRITE_UNLOCK=y -# CONFIG_INLINE_WRITE_UNLOCK_BH is not set -CONFIG_INLINE_WRITE_UNLOCK_IRQ=y -# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set -CONFIG_MUTEX_SPIN_ON_OWNER=y - -# -# Tilera-specific configuration -# CONFIG_NR_CPUS=100 -CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y -CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_HZ_100=y -# CONFIG_HZ_250 is not set -# CONFIG_HZ_300 is not set -# CONFIG_HZ_1000 is not set -CONFIG_HZ=100 -CONFIG_SCHED_HRTICK=y -# CONFIG_KEXEC is not set -CONFIG_COMPAT=y -CONFIG_SYSVIPC_COMPAT=y -# CONFIG_HIGHMEM is not set -CONFIG_NUMA=y -CONFIG_NODES_SHIFT=2 -CONFIG_PAGE_OFFSET=0xC0000000 -CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_DISCONTIGMEM_MANUAL=y -CONFIG_DISCONTIGMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_NEED_MULTIPLE_NODES=y -CONFIG_PAGEFLAGS_EXTENDED=y -CONFIG_SPLIT_PTLOCK_CPUS=4 -# CONFIG_COMPACTION is not set -CONFIG_MIGRATION=y -CONFIG_PHYS_ADDR_T_64BIT=y -CONFIG_ZONE_DMA_FLAG=0 -CONFIG_VIRT_TO_BUS=y -# CONFIG_KSM is not set -CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 -# CONFIG_CLEANCACHE is not set -# CONFIG_CMDLINE_BOOL is not set -CONFIG_VMALLOC_RESERVE=0x1000000 -CONFIG_HARDWALL=y -CONFIG_KERNEL_PL=1 - -# -# Bus options -# -CONFIG_PCI=y -CONFIG_PCI_DOMAINS=y -# CONFIG_NO_IOMEM is not set -# CONFIG_NO_IOPORT is not set -# CONFIG_ARCH_SUPPORTS_MSI is not set CONFIG_PCI_DEBUG=y -# CONFIG_PCI_STUB is not set -# CONFIG_PCI_IOV is not set -# CONFIG_PCI_PRI is not set -# CONFIG_PCI_PASID is not set -# CONFIG_HOTPLUG_PCI is not set - -# -# Executable file formats -# -CONFIG_KCORE_ELF=y -CONFIG_BINFMT_ELF=y -CONFIG_COMPAT_BINFMT_ELF=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_HAVE_AOUT is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y - -# -# Networking options -# CONFIG_PACKET=y CONFIG_UNIX=y -# CONFIG_UNIX_DIAG is not set -CONFIG_XFRM=y CONFIG_XFRM_USER=y CONFIG_XFRM_SUB_POLICY=y -CONFIG_XFRM_MIGRATE=y CONFIG_XFRM_STATISTICS=y -CONFIG_XFRM_IPCOMP=m CONFIG_NET_KEY=m CONFIG_NET_KEY_MIGRATE=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y -# CONFIG_IP_FIB_TRIE_STATS is not set CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_ROUTE_MULTIPATH=y CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_IP_ROUTE_CLASSID=y -# CONFIG_IP_PNP is not set CONFIG_NET_IPIP=m -# CONFIG_NET_IPGRE_DEMUX is not set CONFIG_IP_MROUTE=y -# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -# CONFIG_ARPD is not set CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_TUNNEL=m -CONFIG_INET_TUNNEL=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m CONFIG_INET_XFRM_MODE_BEET=m -CONFIG_INET_LRO=y CONFIG_INET_DIAG=m -CONFIG_INET_TCP_DIAG=m -# CONFIG_INET_UDP_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y -CONFIG_TCP_CONG_BIC=m -CONFIG_TCP_CONG_CUBIC=y -CONFIG_TCP_CONG_WESTWOOD=m -CONFIG_TCP_CONG_HTCP=m CONFIG_TCP_CONG_HSTCP=m CONFIG_TCP_CONG_HYBLA=m -CONFIG_TCP_CONG_VEGAS=m CONFIG_TCP_CONG_SCALABLE=m CONFIG_TCP_CONG_LP=m CONFIG_TCP_CONG_VENO=m CONFIG_TCP_CONG_YEAH=m CONFIG_TCP_CONG_ILLINOIS=m -CONFIG_DEFAULT_CUBIC=y -# CONFIG_DEFAULT_RENO is not set -CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y CONFIG_IPV6=y CONFIG_IPV6_PRIVACY=y @@ -368,111 +98,60 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_TUNNEL=m -CONFIG_INET6_TUNNEL=m CONFIG_INET6_XFRM_MODE_TRANSPORT=m CONFIG_INET6_XFRM_MODE_TUNNEL=m CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_SIT=m -# CONFIG_IPV6_SIT_6RD is not set -CONFIG_IPV6_NDISC_NODETYPE=y CONFIG_IPV6_TUNNEL=m CONFIG_IPV6_MULTIPLE_TABLES=y -# CONFIG_IPV6_SUBTREES is not set CONFIG_IPV6_MROUTE=y -# CONFIG_IPV6_MROUTE_MULTIPLE_TABLES is not set CONFIG_IPV6_PIMSM_V2=y CONFIG_NETLABEL=y -CONFIG_NETWORK_SECMARK=y -# CONFIG_NETWORK_PHY_TIMESTAMPING is not set CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_NETFILTER_ADVANCED=y -CONFIG_BRIDGE_NETFILTER=y - -# -# Core Netfilter Configuration -# -CONFIG_NETFILTER_NETLINK=m -# CONFIG_NETFILTER_NETLINK_ACCT is not set -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NETFILTER_NETLINK_LOG=m CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_ZONES=y -CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y -# CONFIG_NF_CONNTRACK_TIMESTAMP is not set CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_GRE=m -CONFIG_NF_CT_PROTO_SCTP=m CONFIG_NF_CT_PROTO_UDPLITE=m CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_BROADCAST=m CONFIG_NF_CONNTRACK_NETBIOS_NS=m -# CONFIG_NF_CONNTRACK_SNMP is not set CONFIG_NF_CONNTRACK_PPTP=m CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m -# CONFIG_NF_CT_NETLINK is not set CONFIG_NETFILTER_TPROXY=m -CONFIG_NETFILTER_XTABLES=y - -# -# Xtables combined modules -# -CONFIG_NETFILTER_XT_MARK=m -CONFIG_NETFILTER_XT_CONNMARK=m - -# -# Xtables targets -# -# CONFIG_NETFILTER_XT_TARGET_AUDIT is not set -# CONFIG_NETFILTER_XT_TARGET_CHECKSUM is not set CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m CONFIG_NETFILTER_XT_TARGET_CONNMARK=m CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m CONFIG_NETFILTER_XT_TARGET_CT=m CONFIG_NETFILTER_XT_TARGET_DSCP=m -CONFIG_NETFILTER_XT_TARGET_HL=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_NOTRACK=m -CONFIG_NETFILTER_XT_TARGET_RATEEST=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_SECMARK=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m - -# -# Xtables matches -# -# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m CONFIG_NETFILTER_XT_MATCH_CONNMARK=m CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -# CONFIG_NETFILTER_XT_MATCH_CPU is not set CONFIG_NETFILTER_XT_MATCH_DCCP=m -# CONFIG_NETFILTER_XT_MATCH_DEVGROUP is not set CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ECN=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_HL=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -480,7 +159,6 @@ CONFIG_NETFILTER_XT_MATCH_LIMIT=m CONFIG_NETFILTER_XT_MATCH_MAC=m CONFIG_NETFILTER_XT_MATCH_MARK=m CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -# CONFIG_NETFILTER_XT_MATCH_NFACCT is not set CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m @@ -490,7 +168,6 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m @@ -498,66 +175,33 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -# CONFIG_IP_SET is not set CONFIG_IP_VS=m CONFIG_IP_VS_IPV6=y -# CONFIG_IP_VS_DEBUG is not set -CONFIG_IP_VS_TAB_BITS=12 - -# -# IPVS transport protocol load balancing support -# CONFIG_IP_VS_PROTO_TCP=y CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_AH_ESP=y CONFIG_IP_VS_PROTO_ESP=y CONFIG_IP_VS_PROTO_AH=y CONFIG_IP_VS_PROTO_SCTP=y - -# -# IPVS scheduler -# CONFIG_IP_VS_RR=m CONFIG_IP_VS_WRR=m CONFIG_IP_VS_LC=m CONFIG_IP_VS_WLC=m CONFIG_IP_VS_LBLC=m CONFIG_IP_VS_LBLCR=m -# CONFIG_IP_VS_DH is not set -# CONFIG_IP_VS_SH is not set CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m - -# -# IPVS SH scheduler -# -CONFIG_IP_VS_SH_TAB_BITS=8 - -# -# IPVS application helper -# -# CONFIG_IP_VS_NFCT is not set -# CONFIG_IP_VS_PE_SIP is not set - -# -# IP: Netfilter Configuration -# -CONFIG_NF_DEFRAG_IPV4=m CONFIG_NF_CONNTRACK_IPV4=m # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m -# CONFIG_IP_NF_MATCH_RPFILTER is not set CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y CONFIG_IP_NF_TARGET_LOG=m CONFIG_IP_NF_TARGET_ULOG=m -# CONFIG_NF_NAT is not set CONFIG_IP_NF_MANGLE=m -# CONFIG_IP_NF_TARGET_CLUSTERIP is not set CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m @@ -565,11 +209,6 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m - -# -# IPv6: Netfilter Configuration -# -CONFIG_NF_DEFRAG_IPV6=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m @@ -580,7 +219,6 @@ CONFIG_IP6_NF_MATCH_OPTS=m CONFIG_IP6_NF_MATCH_HL=m CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m -# CONFIG_IP6_NF_MATCH_RPFILTER is not set CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m CONFIG_IP6_NF_TARGET_LOG=m @@ -611,52 +249,20 @@ CONFIG_BRIDGE_EBT_SNAT=m CONFIG_BRIDGE_EBT_LOG=m CONFIG_BRIDGE_EBT_ULOG=m CONFIG_BRIDGE_EBT_NFLOG=m -# CONFIG_IP_DCCP is not set -CONFIG_IP_SCTP=m -# CONFIG_SCTP_DBG_MSG is not set -# CONFIG_SCTP_DBG_OBJCNT is not set -# CONFIG_SCTP_HMAC_NONE is not set -# CONFIG_SCTP_HMAC_SHA1 is not set -CONFIG_SCTP_HMAC_MD5=y CONFIG_RDS=m CONFIG_RDS_TCP=m -# CONFIG_RDS_DEBUG is not set -# CONFIG_TIPC is not set -# CONFIG_ATM is not set -# CONFIG_L2TP is not set -CONFIG_STP=m -CONFIG_GARP=m CONFIG_BRIDGE=m -CONFIG_BRIDGE_IGMP_SNOOPING=y CONFIG_NET_DSA=y -CONFIG_NET_DSA_TAG_DSA=y -CONFIG_NET_DSA_TAG_EDSA=y -CONFIG_NET_DSA_TAG_TRAILER=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y -# CONFIG_DECNET is not set -CONFIG_LLC=m -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set CONFIG_PHONET=m -# CONFIG_IEEE802154 is not set CONFIG_NET_SCHED=y - -# -# Queueing/Scheduling -# CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_HFSC=m CONFIG_NET_SCH_PRIO=m CONFIG_NET_SCH_MULTIQ=m CONFIG_NET_SCH_RED=m -# CONFIG_NET_SCH_SFB is not set CONFIG_NET_SCH_SFQ=m CONFIG_NET_SCH_TEQL=m CONFIG_NET_SCH_TBF=m @@ -664,15 +270,7 @@ CONFIG_NET_SCH_GRED=m CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_NETEM=m CONFIG_NET_SCH_DRR=m -# CONFIG_NET_SCH_MQPRIO is not set -# CONFIG_NET_SCH_CHOKE is not set -# CONFIG_NET_SCH_QFQ is not set CONFIG_NET_SCH_INGRESS=m - -# -# Classification -# -CONFIG_NET_CLS=y CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -685,7 +283,6 @@ CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m CONFIG_NET_EMATCH_NBYTE=m CONFIG_NET_EMATCH_U32=m @@ -701,252 +298,46 @@ CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m -# CONFIG_NET_ACT_CSUM is not set CONFIG_NET_CLS_IND=y -CONFIG_NET_SCH_FIFO=y CONFIG_DCB=y -CONFIG_DNS_RESOLVER=y -# CONFIG_BATMAN_ADV is not set -# CONFIG_OPENVSWITCH is not set -CONFIG_RPS=y -CONFIG_RFS_ACCEL=y -CONFIG_XPS=y -# CONFIG_NETPRIO_CGROUP is not set -CONFIG_BQL=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_HAMRADIO is not set -# CONFIG_CAN is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -# CONFIG_AF_RXRPC is not set -CONFIG_FIB_RULES=y # CONFIG_WIRELESS is not set -# CONFIG_WIMAX is not set -# CONFIG_RFKILL is not set -# CONFIG_NET_9P is not set -# CONFIG_CAIF is not set -# CONFIG_CEPH_LIB is not set -# CONFIG_NFC is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_EXTRA_FIRMWARE="" -# CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set -CONFIG_SYS_HYPERVISOR=y -# CONFIG_GENERIC_CPU_DEVICES is not set -# CONFIG_DMA_SHARED_BUFFER is not set CONFIG_CONNECTOR=y -CONFIG_PROC_EVENTS=y -# CONFIG_MTD is not set -# CONFIG_PARPORT is not set -CONFIG_BLK_DEV=y -# CONFIG_BLK_CPQ_DA is not set -# CONFIG_BLK_CPQ_CISS_DA is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_LOOP_MIN_COUNT=8 CONFIG_BLK_DEV_CRYPTOLOOP=m -# CONFIG_BLK_DEV_DRBD is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_NVME is not set CONFIG_BLK_DEV_SX8=m -# CONFIG_BLK_DEV_UB is not set CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=16384 -# CONFIG_BLK_DEV_XIP is not set -# CONFIG_CDROM_PKTCDVD is not set CONFIG_ATA_OVER_ETH=m -# CONFIG_BLK_DEV_RBD is not set - -# -# Misc devices -# -# CONFIG_SENSORS_LIS3LV02D is not set -# CONFIG_AD525X_DPOT is not set -# CONFIG_PHANTOM is not set -# CONFIG_INTEL_MID_PTI is not set -# CONFIG_SGI_IOC4 is not set -# CONFIG_TIFM_CORE is not set -# CONFIG_ICS932S401 is not set -# CONFIG_ENCLOSURE_SERVICES is not set -# CONFIG_HP_ILO is not set -# CONFIG_APDS9802ALS is not set -# CONFIG_ISL29003 is not set -# CONFIG_ISL29020 is not set -# CONFIG_SENSORS_TSL2550 is not set -# CONFIG_SENSORS_BH1780 is not set -# CONFIG_SENSORS_BH1770 is not set -# CONFIG_SENSORS_APDS990X is not set -# CONFIG_HMC6352 is not set -# CONFIG_DS1682 is not set -# CONFIG_BMP085 is not set -# CONFIG_PCH_PHUB is not set -# CONFIG_USB_SWITCH_FSA9480 is not set -# CONFIG_C2PORT is not set - -# -# EEPROM support -# -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set -# CONFIG_EEPROM_MAX6875 is not set -# CONFIG_EEPROM_93CX6 is not set -# CONFIG_CB710_CORE is not set - -# -# Texas Instruments shared transport line discipline -# -# CONFIG_SENSORS_LIS3_I2C is not set - -# -# Altera FPGA firmware download module -# -# CONFIG_ALTERA_STAPL is not set - -# -# SCSI device support -# -CONFIG_SCSI_MOD=y CONFIG_RAID_ATTRS=m -CONFIG_SCSI=y -CONFIG_SCSI_DMA=y CONFIG_SCSI_TGT=m -# CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# CONFIG_BLK_DEV_SD=y -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set -# CONFIG_CHR_DEV_SCH is not set -# CONFIG_SCSI_MULTI_LUN is not set CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y -# CONFIG_SCSI_SCAN_ASYNC is not set -CONFIG_SCSI_WAIT_SCAN=m - -# -# SCSI Transports -# -# CONFIG_SCSI_SPI_ATTRS is not set -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set -CONFIG_SCSI_SAS_ATTRS=y -CONFIG_SCSI_SAS_LIBSAS=y CONFIG_SCSI_SAS_ATA=y -CONFIG_SCSI_SAS_HOST_SMP=y -# CONFIG_SCSI_SRP_ATTRS is not set -CONFIG_SCSI_LOWLEVEL=y -# CONFIG_ISCSI_TCP is not set -# CONFIG_ISCSI_BOOT_SYSFS is not set -# CONFIG_SCSI_CXGB3_ISCSI is not set -# CONFIG_SCSI_CXGB4_ISCSI is not set -# CONFIG_SCSI_BNX2_ISCSI is not set -# CONFIG_SCSI_BNX2X_FCOE is not set -# CONFIG_BE2ISCSI is not set -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set -# CONFIG_SCSI_HPSA is not set -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_3W_SAS is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set -# CONFIG_SCSI_AIC7XXX_OLD is not set -# CONFIG_SCSI_AIC79XX is not set -# CONFIG_SCSI_AIC94XX is not set CONFIG_SCSI_MVSAS=y # CONFIG_SCSI_MVSAS_DEBUG is not set CONFIG_SCSI_MVSAS_TASKLET=y -# CONFIG_SCSI_MVUMI is not set -# CONFIG_SCSI_DPT_I2O is not set -# CONFIG_SCSI_ADVANSYS is not set -# CONFIG_SCSI_ARCMSR is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_MEGARAID_SAS is not set -# CONFIG_SCSI_MPT2SAS is not set -# CONFIG_SCSI_HPTIOP is not set -# CONFIG_LIBFC is not set -# CONFIG_LIBFCOE is not set -# CONFIG_FCOE is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_STEX is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -# CONFIG_SCSI_QLA_FC is not set -# CONFIG_SCSI_QLA_ISCSI is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_DEBUG is not set -# CONFIG_SCSI_PMCRAID is not set -# CONFIG_SCSI_PM8001 is not set -# CONFIG_SCSI_SRP is not set -# CONFIG_SCSI_BFA_FC is not set -# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set -# CONFIG_SCSI_DH is not set -# CONFIG_SCSI_OSD_INITIATOR is not set CONFIG_ATA=y -# CONFIG_ATA_NONSTANDARD is not set -CONFIG_ATA_VERBOSE_ERROR=y -CONFIG_SATA_PMP=y - -# -# Controllers with non-SFF native interface -# -# CONFIG_SATA_AHCI is not set -# CONFIG_SATA_AHCI_PLATFORM is not set -# CONFIG_SATA_INIC162X is not set -# CONFIG_SATA_ACARD_AHCI is not set CONFIG_SATA_SIL24=y # CONFIG_ATA_SFF is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=y -CONFIG_MD_AUTODETECT=y CONFIG_MD_LINEAR=m CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m CONFIG_MULTICORE_RAID456=y -# CONFIG_MD_MULTIPATH is not set CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m -# CONFIG_DM_THIN_PROVISIONING is not set CONFIG_DM_MIRROR=m -# CONFIG_DM_RAID is not set CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m @@ -954,55 +345,22 @@ CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y -# CONFIG_DM_FLAKEY is not set -# CONFIG_TARGET_CORE is not set CONFIG_FUSION=y -# CONFIG_FUSION_SPI is not set -# CONFIG_FUSION_FC is not set CONFIG_FUSION_SAS=y -CONFIG_FUSION_MAX_SGE=128 -# CONFIG_FUSION_CTL is not set -# CONFIG_FUSION_LOGGING is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_FIREWIRE is not set -# CONFIG_FIREWIRE_NOSY is not set -# CONFIG_I2O is not set CONFIG_NETDEVICES=y -CONFIG_NET_CORE=y CONFIG_BONDING=m CONFIG_DUMMY=m -# CONFIG_EQUALIZER is not set -# CONFIG_NET_FC is not set -# CONFIG_MII is not set CONFIG_IFB=m -# CONFIG_NET_TEAM is not set CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y -CONFIG_NETPOLL=y CONFIG_NETPOLL_TRAP=y -CONFIG_NET_POLL_CONTROLLER=y CONFIG_TUN=y CONFIG_VETH=m -# CONFIG_ARCNET is not set - -# -# CAIF transport drivers -# - -# -# Distributed Switch Architecture drivers -# -CONFIG_NET_DSA_MV88E6XXX=y CONFIG_NET_DSA_MV88E6060=y -CONFIG_NET_DSA_MV88E6XXX_NEED_PPU=y CONFIG_NET_DSA_MV88E6131=y CONFIG_NET_DSA_MV88E6123_61_65=y -CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_3COM is not set # CONFIG_NET_VENDOR_ADAPTEC is not set # CONFIG_NET_VENDOR_ALTEON is not set @@ -1010,27 +368,21 @@ CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set -# CONFIG_NET_CALXEDA_XGMAC is not set # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set -# CONFIG_DNET is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EXAR is not set # CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_IP1000 is not set -# CONFIG_JME is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MELLANOX is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MYRI is not set -# CONFIG_FEALNX is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set -# CONFIG_ETHOC is not set # CONFIG_NET_PACKET_ENGINE is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_REALTEK is not set @@ -1038,7 +390,6 @@ CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SILAN is not set # CONFIG_NET_VENDOR_SIS is not set -# CONFIG_SFC is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set @@ -1046,673 +397,91 @@ CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_TILE_NET is not set # CONFIG_NET_VENDOR_VIA is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -CONFIG_PHYLIB=y - -# -# MII PHY device drivers -# -# CONFIG_MARVELL_PHY is not set -# CONFIG_DAVICOM_PHY is not set -# CONFIG_QSEMI_PHY is not set -# CONFIG_LXT_PHY is not set -# CONFIG_CICADA_PHY is not set -# CONFIG_VITESSE_PHY is not set -# CONFIG_SMSC_PHY is not set -# CONFIG_BROADCOM_PHY is not set -# CONFIG_ICPLUS_PHY is not set -# CONFIG_REALTEK_PHY is not set -# CONFIG_NATIONAL_PHY is not set -# CONFIG_STE10XP is not set -# CONFIG_LSI_ET1011C_PHY is not set -# CONFIG_MICREL_PHY is not set -# CONFIG_FIXED_PHY is not set -# CONFIG_MDIO_BITBANG is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_TR is not set - -# -# USB Network Adapters -# -# CONFIG_USB_CATC is not set -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET is not set -# CONFIG_USB_CDC_PHONET is not set -# CONFIG_USB_IPHETH is not set # CONFIG_WLAN is not set - -# -# Enable WiMAX (Networking options) to see the WiMAX drivers -# -# CONFIG_WAN is not set -# CONFIG_VMXNET3 is not set -# CONFIG_ISDN is not set -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set -# CONFIG_INPUT_SPARSEKMAP is not set - -# -# Userland interfaces -# # CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# # CONFIG_SERIO is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# # CONFIG_VT is not set -CONFIG_UNIX98_PTYS=y -# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_SERIAL_NONSTANDARD is not set -# CONFIG_NOZOMI is not set -# CONFIG_N_GSM is not set -# CONFIG_TRACE_SINK is not set -CONFIG_DEVKMEM=y - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_MFD_HSU is not set -# CONFIG_SERIAL_JSM is not set -# CONFIG_SERIAL_TIMBERDALE is not set -# CONFIG_SERIAL_ALTERA_JTAGUART is not set -# CONFIG_SERIAL_ALTERA_UART is not set -# CONFIG_SERIAL_PCH_UART is not set -# CONFIG_SERIAL_XILINX_PS_UART is not set -# CONFIG_TTY_PRINTK is not set -CONFIG_HVC_DRIVER=y -# CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_TIMERIOMEM=m -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# PCMCIA character devices -# -# CONFIG_RAW_DRIVER is not set -# CONFIG_TCG_TPM is not set -CONFIG_DEVPORT=y -# CONFIG_RAMOOPS is not set -CONFIG_TILE_SROM=y CONFIG_I2C=y -CONFIG_I2C_BOARDINFO=y -CONFIG_I2C_COMPAT=y CONFIG_I2C_CHARDEV=y -# CONFIG_I2C_MUX is not set -CONFIG_I2C_HELPER_AUTO=y - -# -# I2C Hardware Bus support -# - -# -# PC SMBus host controller drivers -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -# CONFIG_I2C_AMD756 is not set -# CONFIG_I2C_AMD8111 is not set -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_ISCH is not set -# CONFIG_I2C_PIIX4 is not set -# CONFIG_I2C_NFORCE2 is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -# CONFIG_I2C_SIS96X is not set -# CONFIG_I2C_VIA is not set -# CONFIG_I2C_VIAPRO is not set - -# -# I2C system bus drivers (mostly embedded / system-on-chip) -# -# CONFIG_I2C_DESIGNWARE_PCI is not set -# CONFIG_I2C_INTEL_MID is not set -# CONFIG_I2C_OCORES is not set -# CONFIG_I2C_PCA_PLATFORM is not set -# CONFIG_I2C_PXA_PCI is not set -# CONFIG_I2C_SIMTEC is not set -# CONFIG_I2C_XILINX is not set -# CONFIG_I2C_EG20T is not set - -# -# External I2C/SMBus adapter drivers -# -# CONFIG_I2C_DIOLAN_U2C is not set -# CONFIG_I2C_PARPORT_LIGHT is not set -# CONFIG_I2C_TAOS_EVM is not set -# CONFIG_I2C_TINY_USB is not set - -# -# Other I2C/SMBus bus drivers -# -# CONFIG_I2C_STUB is not set -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_SPI is not set - -# -# PPS support -# -# CONFIG_PPS is not set - -# -# PPS generators support -# - -# -# PTP clock support -# - -# -# Enable Device Drivers -> PPS to see the PTP clock options. -# -# CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set # CONFIG_HWMON is not set -# CONFIG_THERMAL is not set CONFIG_WATCHDOG=y -# CONFIG_WATCHDOG_CORE is not set CONFIG_WATCHDOG_NOWAYOUT=y - -# -# Watchdog Device Drivers -# -# CONFIG_SOFT_WATCHDOG is not set -# CONFIG_ALIM7101_WDT is not set - -# -# PCI-based Watchdog Cards -# -# CONFIG_PCIPCWATCHDOG is not set -# CONFIG_WDTPCI is not set - -# -# USB-based Watchdog Cards -# -# CONFIG_USBPCWATCHDOG is not set -CONFIG_SSB_POSSIBLE=y - -# -# Sonics Silicon Backplane -# -# CONFIG_SSB is not set -CONFIG_BCMA_POSSIBLE=y - -# -# Broadcom specific AMBA -# -# CONFIG_BCMA is not set - -# -# Multifunction device drivers -# -# CONFIG_MFD_CORE is not set -# CONFIG_MFD_88PM860X is not set -# CONFIG_MFD_SM501 is not set -# CONFIG_HTC_PASIC3 is not set -# CONFIG_TPS6105X is not set -# CONFIG_TPS6507X is not set -# CONFIG_TWL4030_CORE is not set -# CONFIG_MFD_STMPE is not set -# CONFIG_MFD_TC3589X is not set -# CONFIG_MFD_TMIO is not set -# CONFIG_PMIC_DA903X is not set -# CONFIG_MFD_DA9052_I2C is not set -# CONFIG_PMIC_ADP5520 is not set -# CONFIG_MFD_MAX8925 is not set -# CONFIG_MFD_MAX8997 is not set -# CONFIG_MFD_MAX8998 is not set -# CONFIG_MFD_S5M_CORE is not set -# CONFIG_MFD_WM8400 is not set -# CONFIG_MFD_WM831X_I2C is not set -# CONFIG_MFD_WM8350_I2C is not set -# CONFIG_MFD_WM8994 is not set -# CONFIG_MFD_PCF50633 is not set -# CONFIG_ABX500_CORE is not set -# CONFIG_LPC_SCH is not set -# CONFIG_MFD_RDC321X is not set -# CONFIG_MFD_JANZ_CMODIO is not set -# CONFIG_MFD_VX855 is not set -# CONFIG_MFD_WL1273_CORE is not set -# CONFIG_REGULATOR is not set -# CONFIG_MEDIA_SUPPORT is not set - -# -# Graphics support -# # CONFIG_VGA_ARB is not set -# CONFIG_DRM is not set -# CONFIG_STUB_POULSBO is not set -# CONFIG_VGASTATE is not set -# CONFIG_VIDEO_OUTPUT_CONTROL is not set -# CONFIG_FB is not set -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set -# CONFIG_SOUND is not set # CONFIG_HID_SUPPORT is not set -CONFIG_USB_SUPPORT=y -CONFIG_USB_COMMON=y -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB_ARCH_HAS_EHCI=y -CONFIG_USB_ARCH_HAS_XHCI=y CONFIG_USB=y -# CONFIG_USB_DEBUG is not set -# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set - -# -# Miscellaneous USB options -# -# CONFIG_USB_DEVICEFS is not set # CONFIG_USB_DEVICE_CLASS is not set -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_OTG_WHITELIST is not set -# CONFIG_USB_OTG_BLACKLIST_HUB is not set -# CONFIG_USB_MON is not set -# CONFIG_USB_WUSB_CBAF is not set - -# -# USB Host Controller Drivers -# -# CONFIG_USB_C67X00_HCD is not set -# CONFIG_USB_XHCI_HCD is not set CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_ROOT_HUB_TT is not set -CONFIG_USB_EHCI_TT_NEWSCHED=y -# CONFIG_USB_EHCI_MV is not set -# CONFIG_USB_OXU210HP_HCD is not set -# CONFIG_USB_ISP116X_HCD is not set -# CONFIG_USB_ISP1760_HCD is not set -# CONFIG_USB_ISP1362_HCD is not set CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set -# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -# CONFIG_USB_UHCI_HCD is not set -# CONFIG_USB_SL811_HCD is not set -# CONFIG_USB_R8A66597_HCD is not set - -# -# USB Device Class drivers -# -# CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set -# CONFIG_USB_WDM is not set -# CONFIG_USB_TMC is not set - -# -# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may -# - -# -# also be needed; see USB_STORAGE Help for more info -# CONFIG_USB_STORAGE=y -# CONFIG_USB_STORAGE_DEBUG is not set -# CONFIG_USB_STORAGE_REALTEK is not set -# CONFIG_USB_STORAGE_DATAFAB is not set -# CONFIG_USB_STORAGE_FREECOM is not set -# CONFIG_USB_STORAGE_ISD200 is not set -# CONFIG_USB_STORAGE_USBAT is not set -# CONFIG_USB_STORAGE_SDDR09 is not set -# CONFIG_USB_STORAGE_SDDR55 is not set -# CONFIG_USB_STORAGE_JUMPSHOT is not set -# CONFIG_USB_STORAGE_ALAUDA is not set -# CONFIG_USB_STORAGE_ONETOUCH is not set -# CONFIG_USB_STORAGE_KARMA is not set -# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set -# CONFIG_USB_STORAGE_ENE_UB6250 is not set -# CONFIG_USB_UAS is not set CONFIG_USB_LIBUSUAL=y - -# -# USB Imaging devices -# -# CONFIG_USB_MDC800 is not set -# CONFIG_USB_MICROTEK is not set - -# -# USB port drivers -# -# CONFIG_USB_SERIAL is not set - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -# CONFIG_USB_ADUTUX is not set -# CONFIG_USB_SEVSEG is not set -# CONFIG_USB_RIO500 is not set -# CONFIG_USB_LEGOTOWER is not set -# CONFIG_USB_LCD is not set -# CONFIG_USB_LED is not set -# CONFIG_USB_CYPRESS_CY7C63 is not set -# CONFIG_USB_CYTHERM is not set -# CONFIG_USB_IDMOUSE is not set -# CONFIG_USB_FTDI_ELAN is not set -# CONFIG_USB_APPLEDISPLAY is not set -# CONFIG_USB_SISUSBVGA is not set -# CONFIG_USB_LD is not set -# CONFIG_USB_TRANCEVIBRATOR is not set -# CONFIG_USB_IOWARRIOR is not set -# CONFIG_USB_TEST is not set -# CONFIG_USB_ISIGHTFW is not set -# CONFIG_USB_YUREX is not set -# CONFIG_USB_GADGET is not set - -# -# OTG and related infrastructure -# -# CONFIG_NOP_USB_XCEIV is not set -# CONFIG_UWB is not set -# CONFIG_MMC is not set -# CONFIG_MEMSTICK is not set -# CONFIG_NEW_LEDS is not set -# CONFIG_ACCESSIBILITY is not set -# CONFIG_INFINIBAND is not set CONFIG_EDAC=y - -# -# Reporting subsystems -# -# CONFIG_EDAC_DEBUG is not set CONFIG_EDAC_MM_EDAC=y -CONFIG_EDAC_TILE=y -CONFIG_RTC_LIB=y CONFIG_RTC_CLASS=y -CONFIG_RTC_HCTOSYS=y -CONFIG_RTC_HCTOSYS_DEVICE="rtc0" -# CONFIG_RTC_DEBUG is not set - -# -# RTC interfaces -# -CONFIG_RTC_INTF_SYSFS=y -CONFIG_RTC_INTF_PROC=y -CONFIG_RTC_INTF_DEV=y -# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set -# CONFIG_RTC_DRV_TEST is not set - -# -# I2C RTC drivers -# -# CONFIG_RTC_DRV_DS1307 is not set -# CONFIG_RTC_DRV_DS1374 is not set -# CONFIG_RTC_DRV_DS1672 is not set -# CONFIG_RTC_DRV_DS3232 is not set -# CONFIG_RTC_DRV_MAX6900 is not set -# CONFIG_RTC_DRV_RS5C372 is not set -# CONFIG_RTC_DRV_ISL1208 is not set -# CONFIG_RTC_DRV_ISL12022 is not set -# CONFIG_RTC_DRV_X1205 is not set -# CONFIG_RTC_DRV_PCF8563 is not set -# CONFIG_RTC_DRV_PCF8583 is not set -# CONFIG_RTC_DRV_M41T80 is not set -# CONFIG_RTC_DRV_BQ32K is not set -# CONFIG_RTC_DRV_S35390A is not set -# CONFIG_RTC_DRV_FM3130 is not set -# CONFIG_RTC_DRV_RX8581 is not set -# CONFIG_RTC_DRV_RX8025 is not set -# CONFIG_RTC_DRV_EM3027 is not set -# CONFIG_RTC_DRV_RV3029C2 is not set - -# -# SPI RTC drivers -# - -# -# Platform RTC drivers -# -# CONFIG_RTC_DRV_DS1286 is not set -# CONFIG_RTC_DRV_DS1511 is not set -# CONFIG_RTC_DRV_DS1553 is not set -# CONFIG_RTC_DRV_DS1742 is not set -# CONFIG_RTC_DRV_STK17TA8 is not set -# CONFIG_RTC_DRV_M48T86 is not set -# CONFIG_RTC_DRV_M48T35 is not set -# CONFIG_RTC_DRV_M48T59 is not set -# CONFIG_RTC_DRV_MSM6242 is not set -# CONFIG_RTC_DRV_BQ4802 is not set -# CONFIG_RTC_DRV_RP5C01 is not set -# CONFIG_RTC_DRV_V3020 is not set - -# -# on-CPU RTC drivers -# CONFIG_RTC_DRV_TILE=y -# CONFIG_DMADEVICES is not set -# CONFIG_AUXDISPLAY is not set -# CONFIG_UIO is not set - -# -# Virtio drivers -# -# CONFIG_VIRTIO_PCI is not set -# CONFIG_VIRTIO_BALLOON is not set -# CONFIG_VIRTIO_MMIO is not set - -# -# Microsoft Hyper-V guest support -# -# CONFIG_STAGING is not set - -# -# Hardware Spinlock drivers -# -CONFIG_IOMMU_SUPPORT=y -# CONFIG_VIRT_DRIVERS is not set -# CONFIG_PM_DEVFREQ is not set - -# -# File systems -# CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT2_FS_XIP=y CONFIG_EXT3_FS=y -CONFIG_EXT3_DEFAULTS_TO_ORDERED=y -CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y CONFIG_EXT3_FS_SECURITY=y CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_XATTR=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -# CONFIG_EXT4_DEBUG is not set -CONFIG_FS_XIP=y -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_JBD2=y -# CONFIG_JBD2_DEBUG is not set -CONFIG_FS_MBCACHE=y -# CONFIG_REISERFS_FS is not set -# CONFIG_JFS_FS is not set CONFIG_XFS_FS=y CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y -# CONFIG_XFS_RT is not set -# CONFIG_XFS_DEBUG is not set CONFIG_GFS2_FS=m CONFIG_GFS2_FS_LOCKING_DLM=y -# CONFIG_OCFS2_FS is not set CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y -# CONFIG_BTRFS_FS_CHECK_INTEGRITY is not set -# CONFIG_NILFS2_FS is not set -CONFIG_FS_POSIX_ACL=y -CONFIG_EXPORTFS=y -CONFIG_FILE_LOCKING=y -CONFIG_FSNOTIFY=y -CONFIG_DNOTIFY=y -CONFIG_INOTIFY_USER=y -# CONFIG_FANOTIFY is not set CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -# CONFIG_QUOTA_DEBUG is not set -CONFIG_QUOTA_TREE=y -# CONFIG_QFMT_V1 is not set CONFIG_QFMT_V2=y -CONFIG_QUOTACTL=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m -CONFIG_GENERIC_ACL=y - -# -# Caches -# CONFIG_FSCACHE=m CONFIG_FSCACHE_STATS=y -# CONFIG_FSCACHE_HISTOGRAM is not set -# CONFIG_FSCACHE_DEBUG is not set -# CONFIG_FSCACHE_OBJECT_LIST is not set CONFIG_CACHEFILES=m -# CONFIG_CACHEFILES_DEBUG is not set -# CONFIG_CACHEFILES_HISTOGRAM is not set - -# -# CD-ROM/DVD Filesystems -# CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_ZISOFS=y CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_FAT_DEFAULT_IOCHARSET="ascii" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y -CONFIG_PROC_SYSCTL=y -CONFIG_PROC_PAGE_MONITOR=y -CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y -CONFIG_TMPFS_XATTR=y CONFIG_HUGETLBFS=y -CONFIG_HUGETLB_PAGE=y -CONFIG_CONFIGFS_FS=m -CONFIG_MISC_FILESYSTEMS=y -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set CONFIG_ECRYPT_FS=m -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_LOGFS is not set CONFIG_CRAMFS=m CONFIG_SQUASHFS=m -# CONFIG_SQUASHFS_XATTR is not set -CONFIG_SQUASHFS_ZLIB=y -# CONFIG_SQUASHFS_LZO is not set -# CONFIG_SQUASHFS_XZ is not set -# CONFIG_SQUASHFS_4K_DEVBLK_SIZE is not set -# CONFIG_SQUASHFS_EMBEDDED is not set -CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE=3 -# CONFIG_VXFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_OMFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_PSTORE is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set -CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=m CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_NFS_V4_1=y -CONFIG_PNFS_FILE_LAYOUT=m -CONFIG_PNFS_BLOCK=m CONFIG_NFS_FSCACHE=y -# CONFIG_NFS_USE_LEGACY_DNS is not set -CONFIG_NFS_USE_KERNEL_DNS=y -# CONFIG_NFS_USE_NEW_IDMAPPER is not set CONFIG_NFSD=m -CONFIG_NFSD_V2_ACL=y -CONFIG_NFSD_V3=y CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y -# CONFIG_NFSD_FAULT_INJECTION is not set -CONFIG_LOCKD=m -CONFIG_LOCKD_V4=y -CONFIG_NFS_ACL_SUPPORT=m -CONFIG_NFS_COMMON=y -CONFIG_SUNRPC=m -CONFIG_SUNRPC_GSS=m -CONFIG_SUNRPC_BACKCHANNEL=y -CONFIG_RPCSEC_GSS_KRB5=m -# CONFIG_CEPH_FS is not set CONFIG_CIFS=m CONFIG_CIFS_STATS=y -# CONFIG_CIFS_STATS2 is not set CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y -# CONFIG_CIFS_DEBUG2 is not set CONFIG_CIFS_DFS_UPCALL=y CONFIG_CIFS_FSCACHE=y -# CONFIG_CIFS_ACL is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set -CONFIG_NLS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_737=m @@ -1752,191 +521,47 @@ CONFIG_NLS_ISO8859_15=m CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m -CONFIG_DLM=m CONFIG_DLM_DEBUG=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4 # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_ENABLE_MUST_CHECK=y -CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y CONFIG_STRIP_ASM_SYMS=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y CONFIG_HEADERS_CHECK=y -# CONFIG_DEBUG_SECTION_MISMATCH is not set -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_SHIRQ is not set CONFIG_LOCKUP_DETECTOR=y -# CONFIG_HARDLOCKUP_DETECTOR is not set -# CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is not set -CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE=0 -# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 -CONFIG_DETECT_HUNG_TASK=y -CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120 -# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set -CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 -CONFIG_SCHED_DEBUG=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -# CONFIG_DEBUG_OBJECTS is not set -# CONFIG_SLUB_DEBUG_ON is not set -# CONFIG_SLUB_STATS is not set -# CONFIG_DEBUG_KMEMLEAK is not set -# CONFIG_DEBUG_RT_MUTEXES is not set -# CONFIG_RT_MUTEX_TESTER is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_MUTEXES is not set -# CONFIG_DEBUG_LOCK_ALLOC is not set -# CONFIG_PROVE_LOCKING is not set -# CONFIG_SPARSE_RCU_POINTER is not set -# CONFIG_LOCK_STAT is not set -# CONFIG_DEBUG_ATOMIC_SLEEP is not set -# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set -CONFIG_STACKTRACE=y -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_KOBJECT is not set -CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_REDUCED=y CONFIG_DEBUG_VM=y -# CONFIG_DEBUG_WRITECOUNT is not set CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_LIST=y -# CONFIG_TEST_LIST_SORT is not set -# CONFIG_DEBUG_SG is not set -# CONFIG_DEBUG_NOTIFIERS is not set CONFIG_DEBUG_CREDENTIALS=y -# CONFIG_RCU_TORTURE_TEST is not set -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -# CONFIG_BACKTRACE_SELF_TEST is not set -# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -# CONFIG_DEBUG_PER_CPU_MAPS is not set -# CONFIG_LKDTM is not set -# CONFIG_FAULT_INJECTION is not set -# CONFIG_SYSCTL_SYSCALL_CHECK is not set -# CONFIG_DEBUG_PAGEALLOC is not set -CONFIG_TRACING_SUPPORT=y -CONFIG_FTRACE=y -# CONFIG_IRQSOFF_TRACER is not set -# CONFIG_SCHED_TRACER is not set -# CONFIG_ENABLE_DEFAULT_TRACERS is not set -CONFIG_BRANCH_PROFILE_NONE=y -# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set -# CONFIG_PROFILE_ALL_BRANCHES is not set -# CONFIG_BLK_DEV_IO_TRACE is not set -# CONFIG_BUILD_DOCSRC is not set CONFIG_DYNAMIC_DEBUG=y -# CONFIG_ATOMIC64_SELFTEST is not set CONFIG_ASYNC_RAID6_TEST=m -# CONFIG_SAMPLES is not set -# CONFIG_TEST_KSTRTOX is not set -CONFIG_EARLY_PRINTK=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_DEBUG_EXTRA_FLAGS="" - -# -# Security options -# -CONFIG_KEYS=y -# CONFIG_ENCRYPTED_KEYS is not set CONFIG_KEYS_DEBUG_PROC_KEYS=y -# CONFIG_SECURITY_DMESG_RESTRICT is not set CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_NETWORK_XFRM=y -# CONFIG_SECURITY_PATH is not set -CONFIG_LSM_MMAP_MIN_ADDR=65536 CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_SECURITY_SELINUX_DEVELOP=y -CONFIG_SECURITY_SELINUX_AVC_STATS=y -CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 -# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set -# CONFIG_SECURITY_SMACK is not set -# CONFIG_SECURITY_TOMOYO is not set -# CONFIG_SECURITY_APPARMOR is not set -# CONFIG_IMA is not set -# CONFIG_EVM is not set -CONFIG_DEFAULT_SECURITY_SELINUX=y -# CONFIG_DEFAULT_SECURITY_DAC is not set -CONFIG_DEFAULT_SECURITY="selinux" -CONFIG_XOR_BLOCKS=m -CONFIG_ASYNC_CORE=m -CONFIG_ASYNC_MEMCPY=m -CONFIG_ASYNC_XOR=m -CONFIG_ASYNC_PQ=m -CONFIG_ASYNC_RAID6_RECOV=m -CONFIG_CRYPTO=y - -# -# Crypto core or helper -# -CONFIG_CRYPTO_ALGAPI=y -CONFIG_CRYPTO_ALGAPI2=y -CONFIG_CRYPTO_AEAD=m -CONFIG_CRYPTO_AEAD2=y -CONFIG_CRYPTO_BLKCIPHER=m -CONFIG_CRYPTO_BLKCIPHER2=y -CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_HASH2=y -CONFIG_CRYPTO_RNG=m -CONFIG_CRYPTO_RNG2=y -CONFIG_CRYPTO_PCOMP=m -CONFIG_CRYPTO_PCOMP2=y -CONFIG_CRYPTO_MANAGER=y -CONFIG_CRYPTO_MANAGER2=y -# CONFIG_CRYPTO_USER is not set -CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y -CONFIG_CRYPTO_GF128MUL=m CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_WORKQUEUE=y CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m - -# -# Authenticated Encryption with Associated Data -# CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m -CONFIG_CRYPTO_SEQIV=m - -# -# Block modes -# -CONFIG_CRYPTO_CBC=m -CONFIG_CRYPTO_CTR=m CONFIG_CRYPTO_CTS=m -CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m - -# -# Hash modes -# CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m - -# -# Digest -# CONFIG_CRYPTO_CRC32C=y -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -1947,77 +572,16 @@ CONFIG_CRYPTO_SHA256=m CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m - -# -# Ciphers -# -CONFIG_CRYPTO_AES=m CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_BLOWFISH_COMMON=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m -# CONFIG_CRYPTO_SALSA20 is not set CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_TWOFISH_COMMON=m - -# -# Compression -# -CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m - -# -# Random Number Generation -# -CONFIG_CRYPTO_ANSI_CPRNG=m -# CONFIG_CRYPTO_USER_API_HASH is not set -# CONFIG_CRYPTO_USER_API_SKCIPHER is not set -CONFIG_CRYPTO_HW=y -# CONFIG_BINARY_PRINTF is not set - -# -# Library routines -# -CONFIG_RAID6_PQ=m -CONFIG_BITREVERSE=y -CONFIG_GENERIC_FIND_FIRST_BIT=y -CONFIG_GENERIC_PCI_IOMAP=y -# CONFIG_CRC_CCITT is not set -CONFIG_CRC16=y -CONFIG_CRC_T10DIF=y -CONFIG_CRC_ITU_T=m -CONFIG_CRC32=y -# CONFIG_CRC7 is not set -CONFIG_LIBCRC32C=m -# CONFIG_CRC8 is not set -CONFIG_AUDIT_GENERIC=y -CONFIG_ZLIB_INFLATE=y -CONFIG_ZLIB_DEFLATE=m -CONFIG_LZO_COMPRESS=m -CONFIG_LZO_DECOMPRESS=m -# CONFIG_XZ_DEC is not set -# CONFIG_XZ_DEC_BCJ is not set -CONFIG_DECOMPRESS_GZIP=y -CONFIG_TEXTSEARCH=y -CONFIG_TEXTSEARCH_KMP=m -CONFIG_TEXTSEARCH_BM=m -CONFIG_TEXTSEARCH_FSM=m -CONFIG_HAS_IOMEM=y -CONFIG_HAS_IOPORT=y -CONFIG_HAS_DMA=y -CONFIG_CPU_RMAP=y -CONFIG_DQL=y -CONFIG_NLATTR=y -# CONFIG_AVERAGE is not set -# CONFIG_CORDIC is not set -# CONFIG_VIRTUALIZATION is not set diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index 87829912c045..2b1fd31894f1 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -1,368 +1,91 @@ -# -# Automatically generated file; DO NOT EDIT. -# Linux/tilepro 3.3.0-rc7 Kernel Configuration -# -CONFIG_TILE=y -CONFIG_MMU=y -CONFIG_GENERIC_CSUM=y -CONFIG_SEMAPHORE_SLEEPERS=y -CONFIG_HAVE_ARCH_ALLOC_REMAP=y -CONFIG_HAVE_SETUP_PER_CPU_AREA=y -CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y -CONFIG_SYS_SUPPORTS_HUGETLBFS=y -CONFIG_GENERIC_CLOCKEVENTS=y -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_DEFAULT_MIGRATION_COST=10000000 -CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y -CONFIG_ARCH_PHYS_ADDR_T_64BIT=y -CONFIG_ARCH_DMA_ADDR_T_64BIT=y -CONFIG_LOCKDEP_SUPPORT=y -CONFIG_STACKTRACE_SUPPORT=y -CONFIG_ARCH_DISCONTIGMEM_ENABLE=y -CONFIG_ARCH_DISCONTIGMEM_DEFAULT=y -CONFIG_TRACE_IRQFLAGS_SUPPORT=y -CONFIG_STRICT_DEVMEM=y -CONFIG_SMP=y -# CONFIG_DEBUG_COPY_FROM_USER is not set -CONFIG_HVC_TILE=y -# CONFIG_TILEGX is not set -CONFIG_ARCH_DEFCONFIG="arch/tile/configs/tile_defconfig" -CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" - -# -# General setup -# CONFIG_EXPERIMENTAL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 -CONFIG_CROSS_COMPILE="" -CONFIG_LOCALVERSION="" # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="(none)" -CONFIG_SWAP=y CONFIG_SYSVIPC=y -CONFIG_SYSVIPC_SYSCTL=y CONFIG_POSIX_MQUEUE=y -CONFIG_POSIX_MQUEUE_SYSCTL=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y -# CONFIG_FHANDLE is not set +CONFIG_FHANDLE=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_AUDIT=y -# CONFIG_AUDIT_LOGINUID_IMMUTABLE is not set -CONFIG_HAVE_GENERIC_HARDIRQS=y - -# -# IRQ subsystem -# -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_GENERIC_IRQ_SHOW=y -CONFIG_GENERIC_PENDING_IRQ=y - -# -# RCU Subsystem -# -CONFIG_TREE_RCU=y -# CONFIG_PREEMPT_RCU is not set -# CONFIG_RCU_TRACE is not set -CONFIG_RCU_FANOUT=32 -# CONFIG_RCU_FANOUT_EXACT is not set -# CONFIG_RCU_FAST_NO_HZ is not set -# CONFIG_TREE_RCU_TRACE is not set -# CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=19 CONFIG_CGROUPS=y CONFIG_CGROUP_DEBUG=y -# CONFIG_CGROUP_FREEZER is not set CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y -CONFIG_PROC_PID_CPUSET=y CONFIG_CGROUP_CPUACCT=y CONFIG_RESOURCE_COUNTERS=y CONFIG_CGROUP_MEM_RES_CTLR=y CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y -CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED=y -# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set CONFIG_CGROUP_SCHED=y -CONFIG_FAIR_GROUP_SCHED=y -# CONFIG_CFS_BANDWIDTH is not set CONFIG_RT_GROUP_SCHED=y CONFIG_BLK_CGROUP=y -# CONFIG_DEBUG_BLK_CGROUP is not set -# CONFIG_CHECKPOINT_RESTORE is not set CONFIG_NAMESPACES=y -CONFIG_UTS_NS=y -CONFIG_IPC_NS=y -CONFIG_USER_NS=y -CONFIG_PID_NS=y -CONFIG_NET_NS=y -# CONFIG_SCHED_AUTOGROUP is not set -CONFIG_MM_OWNER=y -# CONFIG_SYSFS_DEPRECATED is not set CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_RD_GZIP=y -# CONFIG_RD_BZIP2 is not set -# CONFIG_RD_LZMA is not set -# CONFIG_RD_XZ is not set -# CONFIG_RD_LZO is not set -CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_SYSCTL=y -CONFIG_ANON_INODES=y -CONFIG_EXPERT=y CONFIG_SYSCTL_SYSCALL=y -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -CONFIG_HOTPLUG=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_ELF_CORE=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SIGNALFD=y -CONFIG_TIMERFD=y -CONFIG_EVENTFD=y -CONFIG_SHMEM=y -CONFIG_AIO=y CONFIG_EMBEDDED=y - -# -# Kernel Performance Events And Counters -# -CONFIG_VM_EVENT_COUNTERS=y -CONFIG_PCI_QUIRKS=y -CONFIG_SLUB_DEBUG=y # CONFIG_COMPAT_BRK is not set -# CONFIG_SLAB is not set -CONFIG_SLUB=y -# CONFIG_SLOB is not set CONFIG_PROFILING=y -CONFIG_USE_GENERIC_SMP_HELPERS=y -CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y - -# -# GCOV-based kernel profiling -# -# CONFIG_GCOV_KERNEL is not set -# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set -CONFIG_SLABINFO=y -CONFIG_RT_MUTEXES=y -CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_STOP_MACHINE=y -CONFIG_BLOCK=y -CONFIG_LBDAF=y -CONFIG_BLK_DEV_BSG=y -# CONFIG_BLK_DEV_BSGLIB is not set CONFIG_BLK_DEV_INTEGRITY=y -# CONFIG_BLK_DEV_THROTTLING is not set - -# -# Partition Types -# CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set CONFIG_OSF_PARTITION=y CONFIG_AMIGA_PARTITION=y -# CONFIG_ATARI_PARTITION is not set CONFIG_MAC_PARTITION=y -CONFIG_MSDOS_PARTITION=y CONFIG_BSD_DISKLABEL=y CONFIG_MINIX_SUBPARTITION=y CONFIG_SOLARIS_X86_PARTITION=y CONFIG_UNIXWARE_DISKLABEL=y -# CONFIG_LDM_PARTITION is not set CONFIG_SGI_PARTITION=y -# CONFIG_ULTRIX_PARTITION is not set CONFIG_SUN_PARTITION=y CONFIG_KARMA_PARTITION=y CONFIG_EFI_PARTITION=y -# CONFIG_SYSV68_PARTITION is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y CONFIG_CFQ_GROUP_IOSCHED=y -# CONFIG_DEFAULT_DEADLINE is not set -CONFIG_DEFAULT_CFQ=y -# CONFIG_DEFAULT_NOOP is not set -CONFIG_DEFAULT_IOSCHED="cfq" -CONFIG_PADATA=y -# CONFIG_INLINE_SPIN_TRYLOCK is not set -# CONFIG_INLINE_SPIN_TRYLOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK is not set -# CONFIG_INLINE_SPIN_LOCK_BH is not set -# CONFIG_INLINE_SPIN_LOCK_IRQ is not set -# CONFIG_INLINE_SPIN_LOCK_IRQSAVE is not set -CONFIG_INLINE_SPIN_UNLOCK=y -# CONFIG_INLINE_SPIN_UNLOCK_BH is not set -CONFIG_INLINE_SPIN_UNLOCK_IRQ=y -# CONFIG_INLINE_SPIN_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_READ_TRYLOCK is not set -# CONFIG_INLINE_READ_LOCK is not set -# CONFIG_INLINE_READ_LOCK_BH is not set -# CONFIG_INLINE_READ_LOCK_IRQ is not set -# CONFIG_INLINE_READ_LOCK_IRQSAVE is not set -CONFIG_INLINE_READ_UNLOCK=y -# CONFIG_INLINE_READ_UNLOCK_BH is not set -CONFIG_INLINE_READ_UNLOCK_IRQ=y -# CONFIG_INLINE_READ_UNLOCK_IRQRESTORE is not set -# CONFIG_INLINE_WRITE_TRYLOCK is not set -# CONFIG_INLINE_WRITE_LOCK is not set -# CONFIG_INLINE_WRITE_LOCK_BH is not set -# CONFIG_INLINE_WRITE_LOCK_IRQ is not set -# CONFIG_INLINE_WRITE_LOCK_IRQSAVE is not set -CONFIG_INLINE_WRITE_UNLOCK=y -# CONFIG_INLINE_WRITE_UNLOCK_BH is not set -CONFIG_INLINE_WRITE_UNLOCK_IRQ=y -# CONFIG_INLINE_WRITE_UNLOCK_IRQRESTORE is not set -CONFIG_MUTEX_SPIN_ON_OWNER=y - -# -# Tilera-specific configuration -# -CONFIG_NR_CPUS=64 -CONFIG_TICK_ONESHOT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y -CONFIG_GENERIC_CLOCKEVENTS_BUILD=y CONFIG_HZ_100=y -# CONFIG_HZ_250 is not set -# CONFIG_HZ_300 is not set -# CONFIG_HZ_1000 is not set -CONFIG_HZ=100 -CONFIG_SCHED_HRTICK=y -# CONFIG_KEXEC is not set -CONFIG_HIGHMEM=y -CONFIG_NUMA=y -CONFIG_NODES_SHIFT=2 -# CONFIG_VMSPLIT_3_75G is not set -# CONFIG_VMSPLIT_3_5G is not set -CONFIG_VMSPLIT_3G=y -# CONFIG_VMSPLIT_2_75G is not set -# CONFIG_VMSPLIT_2_5G is not set -# CONFIG_VMSPLIT_2_25G is not set -# CONFIG_VMSPLIT_2G is not set -# CONFIG_VMSPLIT_1G is not set -CONFIG_PAGE_OFFSET=0xC0000000 -CONFIG_SELECT_MEMORY_MODEL=y -CONFIG_DISCONTIGMEM_MANUAL=y -CONFIG_DISCONTIGMEM=y -CONFIG_FLAT_NODE_MEM_MAP=y -CONFIG_NEED_MULTIPLE_NODES=y -CONFIG_PAGEFLAGS_EXTENDED=y -CONFIG_SPLIT_PTLOCK_CPUS=4 -# CONFIG_COMPACTION is not set -CONFIG_MIGRATION=y -CONFIG_PHYS_ADDR_T_64BIT=y -CONFIG_ZONE_DMA_FLAG=0 -CONFIG_BOUNCE=y -CONFIG_VIRT_TO_BUS=y -# CONFIG_KSM is not set -CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 -# CONFIG_CLEANCACHE is not set -# CONFIG_CMDLINE_BOOL is not set -CONFIG_VMALLOC_RESERVE=0x1000000 -CONFIG_HARDWALL=y -CONFIG_KERNEL_PL=1 - -# -# Bus options -# -CONFIG_PCI=y -CONFIG_PCI_DOMAINS=y -# CONFIG_NO_IOMEM is not set -# CONFIG_NO_IOPORT is not set -# CONFIG_ARCH_SUPPORTS_MSI is not set CONFIG_PCI_DEBUG=y -# CONFIG_PCI_STUB is not set -# CONFIG_PCI_IOV is not set -# CONFIG_PCI_PRI is not set -# CONFIG_PCI_PASID is not set -# CONFIG_HOTPLUG_PCI is not set - -# -# Executable file formats -# -CONFIG_KCORE_ELF=y -CONFIG_BINFMT_ELF=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_HAVE_AOUT is not set CONFIG_BINFMT_MISC=y CONFIG_NET=y - -# -# Networking options -# CONFIG_PACKET=y CONFIG_UNIX=y -# CONFIG_UNIX_DIAG is not set -CONFIG_XFRM=y CONFIG_XFRM_USER=y CONFIG_XFRM_SUB_POLICY=y -CONFIG_XFRM_MIGRATE=y CONFIG_XFRM_STATISTICS=y -CONFIG_XFRM_IPCOMP=m CONFIG_NET_KEY=m CONFIG_NET_KEY_MIGRATE=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y -# CONFIG_IP_FIB_TRIE_STATS is not set CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_ROUTE_MULTIPATH=y CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_IP_ROUTE_CLASSID=y -# CONFIG_IP_PNP is not set CONFIG_NET_IPIP=m -# CONFIG_NET_IPGRE_DEMUX is not set CONFIG_IP_MROUTE=y -# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -# CONFIG_ARPD is not set CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_INET_XFRM_TUNNEL=m -CONFIG_INET_TUNNEL=m CONFIG_INET_XFRM_MODE_TRANSPORT=m CONFIG_INET_XFRM_MODE_TUNNEL=m CONFIG_INET_XFRM_MODE_BEET=m -CONFIG_INET_LRO=y CONFIG_INET_DIAG=m -CONFIG_INET_TCP_DIAG=m -# CONFIG_INET_UDP_DIAG is not set CONFIG_TCP_CONG_ADVANCED=y -CONFIG_TCP_CONG_BIC=m -CONFIG_TCP_CONG_CUBIC=y -CONFIG_TCP_CONG_WESTWOOD=m -CONFIG_TCP_CONG_HTCP=m CONFIG_TCP_CONG_HSTCP=m CONFIG_TCP_CONG_HYBLA=m -CONFIG_TCP_CONG_VEGAS=m CONFIG_TCP_CONG_SCALABLE=m CONFIG_TCP_CONG_LP=m CONFIG_TCP_CONG_VENO=m CONFIG_TCP_CONG_YEAH=m CONFIG_TCP_CONG_ILLINOIS=m -CONFIG_DEFAULT_CUBIC=y -# CONFIG_DEFAULT_RENO is not set -CONFIG_DEFAULT_TCP_CONG="cubic" CONFIG_TCP_MD5SIG=y CONFIG_IPV6=y CONFIG_IPV6_PRIVACY=y @@ -373,111 +96,60 @@ CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m -CONFIG_INET6_XFRM_TUNNEL=m -CONFIG_INET6_TUNNEL=m CONFIG_INET6_XFRM_MODE_TRANSPORT=m CONFIG_INET6_XFRM_MODE_TUNNEL=m CONFIG_INET6_XFRM_MODE_BEET=m CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m CONFIG_IPV6_SIT=m -# CONFIG_IPV6_SIT_6RD is not set -CONFIG_IPV6_NDISC_NODETYPE=y CONFIG_IPV6_TUNNEL=m CONFIG_IPV6_MULTIPLE_TABLES=y -# CONFIG_IPV6_SUBTREES is not set CONFIG_IPV6_MROUTE=y -# CONFIG_IPV6_MROUTE_MULTIPLE_TABLES is not set CONFIG_IPV6_PIMSM_V2=y CONFIG_NETLABEL=y -CONFIG_NETWORK_SECMARK=y -# CONFIG_NETWORK_PHY_TIMESTAMPING is not set CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_NETFILTER_ADVANCED=y -CONFIG_BRIDGE_NETFILTER=y - -# -# Core Netfilter Configuration -# -CONFIG_NETFILTER_NETLINK=m -# CONFIG_NETFILTER_NETLINK_ACCT is not set -CONFIG_NETFILTER_NETLINK_QUEUE=m -CONFIG_NETFILTER_NETLINK_LOG=m CONFIG_NF_CONNTRACK=m -CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_ZONES=y -CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y -# CONFIG_NF_CONNTRACK_TIMESTAMP is not set CONFIG_NF_CT_PROTO_DCCP=m -CONFIG_NF_CT_PROTO_GRE=m -CONFIG_NF_CT_PROTO_SCTP=m CONFIG_NF_CT_PROTO_UDPLITE=m CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m CONFIG_NF_CONNTRACK_IRC=m -CONFIG_NF_CONNTRACK_BROADCAST=m CONFIG_NF_CONNTRACK_NETBIOS_NS=m -# CONFIG_NF_CONNTRACK_SNMP is not set CONFIG_NF_CONNTRACK_PPTP=m CONFIG_NF_CONNTRACK_SANE=m CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m -# CONFIG_NF_CT_NETLINK is not set CONFIG_NETFILTER_TPROXY=m -CONFIG_NETFILTER_XTABLES=y - -# -# Xtables combined modules -# -CONFIG_NETFILTER_XT_MARK=m -CONFIG_NETFILTER_XT_CONNMARK=m - -# -# Xtables targets -# -# CONFIG_NETFILTER_XT_TARGET_AUDIT is not set -# CONFIG_NETFILTER_XT_TARGET_CHECKSUM is not set CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m CONFIG_NETFILTER_XT_TARGET_CONNMARK=m CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m CONFIG_NETFILTER_XT_TARGET_CT=m CONFIG_NETFILTER_XT_TARGET_DSCP=m -CONFIG_NETFILTER_XT_TARGET_HL=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m CONFIG_NETFILTER_XT_TARGET_NOTRACK=m -CONFIG_NETFILTER_XT_TARGET_RATEEST=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_SECMARK=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m - -# -# Xtables matches -# -# CONFIG_NETFILTER_XT_MATCH_ADDRTYPE is not set CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m CONFIG_NETFILTER_XT_MATCH_CONNMARK=m CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m -# CONFIG_NETFILTER_XT_MATCH_CPU is not set CONFIG_NETFILTER_XT_MATCH_DCCP=m -# CONFIG_NETFILTER_XT_MATCH_DEVGROUP is not set CONFIG_NETFILTER_XT_MATCH_DSCP=m -CONFIG_NETFILTER_XT_MATCH_ECN=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m -CONFIG_NETFILTER_XT_MATCH_HL=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -485,7 +157,6 @@ CONFIG_NETFILTER_XT_MATCH_LIMIT=m CONFIG_NETFILTER_XT_MATCH_MAC=m CONFIG_NETFILTER_XT_MATCH_MARK=m CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m -# CONFIG_NETFILTER_XT_MATCH_NFACCT is not set CONFIG_NETFILTER_XT_MATCH_OSF=m CONFIG_NETFILTER_XT_MATCH_OWNER=m CONFIG_NETFILTER_XT_MATCH_POLICY=m @@ -495,7 +166,6 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m -CONFIG_NETFILTER_XT_MATCH_SCTP=m CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m @@ -503,66 +173,33 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -# CONFIG_IP_SET is not set CONFIG_IP_VS=m CONFIG_IP_VS_IPV6=y -# CONFIG_IP_VS_DEBUG is not set -CONFIG_IP_VS_TAB_BITS=12 - -# -# IPVS transport protocol load balancing support -# CONFIG_IP_VS_PROTO_TCP=y CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_AH_ESP=y CONFIG_IP_VS_PROTO_ESP=y CONFIG_IP_VS_PROTO_AH=y CONFIG_IP_VS_PROTO_SCTP=y - -# -# IPVS scheduler -# CONFIG_IP_VS_RR=m CONFIG_IP_VS_WRR=m CONFIG_IP_VS_LC=m CONFIG_IP_VS_WLC=m CONFIG_IP_VS_LBLC=m CONFIG_IP_VS_LBLCR=m -# CONFIG_IP_VS_DH is not set -# CONFIG_IP_VS_SH is not set CONFIG_IP_VS_SED=m CONFIG_IP_VS_NQ=m - -# -# IPVS SH scheduler -# -CONFIG_IP_VS_SH_TAB_BITS=8 - -# -# IPVS application helper -# -# CONFIG_IP_VS_NFCT is not set -# CONFIG_IP_VS_PE_SIP is not set - -# -# IP: Netfilter Configuration -# -CONFIG_NF_DEFRAG_IPV4=m CONFIG_NF_CONNTRACK_IPV4=m # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set CONFIG_IP_NF_QUEUE=m CONFIG_IP_NF_IPTABLES=y CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m -# CONFIG_IP_NF_MATCH_RPFILTER is not set CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y CONFIG_IP_NF_TARGET_LOG=m CONFIG_IP_NF_TARGET_ULOG=m -# CONFIG_NF_NAT is not set CONFIG_IP_NF_MANGLE=m -# CONFIG_IP_NF_TARGET_CLUSTERIP is not set CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m @@ -570,11 +207,6 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m - -# -# IPv6: Netfilter Configuration -# -CONFIG_NF_DEFRAG_IPV6=m CONFIG_NF_CONNTRACK_IPV6=m CONFIG_IP6_NF_QUEUE=m CONFIG_IP6_NF_IPTABLES=m @@ -585,7 +217,6 @@ CONFIG_IP6_NF_MATCH_OPTS=m CONFIG_IP6_NF_MATCH_HL=m CONFIG_IP6_NF_MATCH_IPV6HEADER=m CONFIG_IP6_NF_MATCH_MH=m -# CONFIG_IP6_NF_MATCH_RPFILTER is not set CONFIG_IP6_NF_MATCH_RT=m CONFIG_IP6_NF_TARGET_HL=m CONFIG_IP6_NF_TARGET_LOG=m @@ -616,52 +247,20 @@ CONFIG_BRIDGE_EBT_SNAT=m CONFIG_BRIDGE_EBT_LOG=m CONFIG_BRIDGE_EBT_ULOG=m CONFIG_BRIDGE_EBT_NFLOG=m -# CONFIG_IP_DCCP is not set -CONFIG_IP_SCTP=m -# CONFIG_SCTP_DBG_MSG is not set -# CONFIG_SCTP_DBG_OBJCNT is not set -# CONFIG_SCTP_HMAC_NONE is not set -# CONFIG_SCTP_HMAC_SHA1 is not set -CONFIG_SCTP_HMAC_MD5=y CONFIG_RDS=m CONFIG_RDS_TCP=m -# CONFIG_RDS_DEBUG is not set -# CONFIG_TIPC is not set -# CONFIG_ATM is not set -# CONFIG_L2TP is not set -CONFIG_STP=m -CONFIG_GARP=m CONFIG_BRIDGE=m -CONFIG_BRIDGE_IGMP_SNOOPING=y CONFIG_NET_DSA=y -CONFIG_NET_DSA_TAG_DSA=y -CONFIG_NET_DSA_TAG_EDSA=y -CONFIG_NET_DSA_TAG_TRAILER=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y -# CONFIG_DECNET is not set -CONFIG_LLC=m -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set CONFIG_PHONET=m -# CONFIG_IEEE802154 is not set CONFIG_NET_SCHED=y - -# -# Queueing/Scheduling -# CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_HFSC=m CONFIG_NET_SCH_PRIO=m CONFIG_NET_SCH_MULTIQ=m CONFIG_NET_SCH_RED=m -# CONFIG_NET_SCH_SFB is not set CONFIG_NET_SCH_SFQ=m CONFIG_NET_SCH_TEQL=m CONFIG_NET_SCH_TBF=m @@ -669,15 +268,7 @@ CONFIG_NET_SCH_GRED=m CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_NETEM=m CONFIG_NET_SCH_DRR=m -# CONFIG_NET_SCH_MQPRIO is not set -# CONFIG_NET_SCH_CHOKE is not set -# CONFIG_NET_SCH_QFQ is not set CONFIG_NET_SCH_INGRESS=m - -# -# Classification -# -CONFIG_NET_CLS=y CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -690,7 +281,6 @@ CONFIG_NET_CLS_RSVP6=m CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m CONFIG_NET_EMATCH_NBYTE=m CONFIG_NET_EMATCH_U32=m @@ -706,248 +296,42 @@ CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m -# CONFIG_NET_ACT_CSUM is not set CONFIG_NET_CLS_IND=y -CONFIG_NET_SCH_FIFO=y CONFIG_DCB=y -CONFIG_DNS_RESOLVER=y -# CONFIG_BATMAN_ADV is not set -# CONFIG_OPENVSWITCH is not set -CONFIG_RPS=y -CONFIG_RFS_ACCEL=y -CONFIG_XPS=y -# CONFIG_NETPRIO_CGROUP is not set -CONFIG_BQL=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_HAMRADIO is not set -# CONFIG_CAN is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -# CONFIG_AF_RXRPC is not set -CONFIG_FIB_RULES=y # CONFIG_WIRELESS is not set -# CONFIG_WIMAX is not set -# CONFIG_RFKILL is not set -# CONFIG_NET_9P is not set -# CONFIG_CAIF is not set -# CONFIG_CEPH_LIB is not set -# CONFIG_NFC is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_EXTRA_FIRMWARE="" -# CONFIG_DEBUG_DRIVER is not set -# CONFIG_DEBUG_DEVRES is not set -CONFIG_SYS_HYPERVISOR=y -# CONFIG_GENERIC_CPU_DEVICES is not set -# CONFIG_DMA_SHARED_BUFFER is not set CONFIG_CONNECTOR=y -CONFIG_PROC_EVENTS=y -# CONFIG_MTD is not set -# CONFIG_PARPORT is not set -CONFIG_BLK_DEV=y -# CONFIG_BLK_CPQ_DA is not set -# CONFIG_BLK_CPQ_CISS_DA is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_LOOP_MIN_COUNT=8 CONFIG_BLK_DEV_CRYPTOLOOP=m -# CONFIG_BLK_DEV_DRBD is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_NVME is not set CONFIG_BLK_DEV_SX8=m CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=16384 -# CONFIG_BLK_DEV_XIP is not set -# CONFIG_CDROM_PKTCDVD is not set CONFIG_ATA_OVER_ETH=m -# CONFIG_BLK_DEV_RBD is not set - -# -# Misc devices -# -# CONFIG_SENSORS_LIS3LV02D is not set -# CONFIG_AD525X_DPOT is not set -# CONFIG_PHANTOM is not set -# CONFIG_INTEL_MID_PTI is not set -# CONFIG_SGI_IOC4 is not set -# CONFIG_TIFM_CORE is not set -# CONFIG_ICS932S401 is not set -# CONFIG_ENCLOSURE_SERVICES is not set -# CONFIG_HP_ILO is not set -# CONFIG_APDS9802ALS is not set -# CONFIG_ISL29003 is not set -# CONFIG_ISL29020 is not set -# CONFIG_SENSORS_TSL2550 is not set -# CONFIG_SENSORS_BH1780 is not set -# CONFIG_SENSORS_BH1770 is not set -# CONFIG_SENSORS_APDS990X is not set -# CONFIG_HMC6352 is not set -# CONFIG_DS1682 is not set -# CONFIG_BMP085 is not set -# CONFIG_PCH_PHUB is not set -# CONFIG_USB_SWITCH_FSA9480 is not set -# CONFIG_C2PORT is not set - -# -# EEPROM support -# -# CONFIG_EEPROM_AT24 is not set -# CONFIG_EEPROM_LEGACY is not set -# CONFIG_EEPROM_MAX6875 is not set -# CONFIG_EEPROM_93CX6 is not set -# CONFIG_CB710_CORE is not set - -# -# Texas Instruments shared transport line discipline -# -# CONFIG_SENSORS_LIS3_I2C is not set - -# -# Altera FPGA firmware download module -# -# CONFIG_ALTERA_STAPL is not set - -# -# SCSI device support -# -CONFIG_SCSI_MOD=y CONFIG_RAID_ATTRS=m -CONFIG_SCSI=y -CONFIG_SCSI_DMA=y CONFIG_SCSI_TGT=m -# CONFIG_SCSI_NETLINK is not set -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# CONFIG_BLK_DEV_SD=y -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set -# CONFIG_CHR_DEV_SCH is not set -# CONFIG_SCSI_MULTI_LUN is not set CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y -# CONFIG_SCSI_SCAN_ASYNC is not set -CONFIG_SCSI_WAIT_SCAN=m - -# -# SCSI Transports -# -# CONFIG_SCSI_SPI_ATTRS is not set -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set -CONFIG_SCSI_SAS_ATTRS=y -# CONFIG_SCSI_SAS_LIBSAS is not set -# CONFIG_SCSI_SRP_ATTRS is not set -CONFIG_SCSI_LOWLEVEL=y -# CONFIG_ISCSI_TCP is not set -# CONFIG_ISCSI_BOOT_SYSFS is not set -# CONFIG_SCSI_CXGB3_ISCSI is not set -# CONFIG_SCSI_CXGB4_ISCSI is not set -# CONFIG_SCSI_BNX2_ISCSI is not set -# CONFIG_SCSI_BNX2X_FCOE is not set -# CONFIG_BE2ISCSI is not set -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set -# CONFIG_SCSI_HPSA is not set -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_3W_SAS is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set -# CONFIG_SCSI_AIC7XXX_OLD is not set -# CONFIG_SCSI_AIC79XX is not set -# CONFIG_SCSI_AIC94XX is not set -# CONFIG_SCSI_MVSAS is not set -# CONFIG_SCSI_MVUMI is not set -# CONFIG_SCSI_DPT_I2O is not set -# CONFIG_SCSI_ADVANSYS is not set -# CONFIG_SCSI_ARCMSR is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_MEGARAID_SAS is not set -# CONFIG_SCSI_MPT2SAS is not set -# CONFIG_SCSI_HPTIOP is not set -# CONFIG_LIBFC is not set -# CONFIG_LIBFCOE is not set -# CONFIG_FCOE is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_STEX is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -# CONFIG_SCSI_QLA_FC is not set -# CONFIG_SCSI_QLA_ISCSI is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_NSP32 is not set -# CONFIG_SCSI_DEBUG is not set -# CONFIG_SCSI_PMCRAID is not set -# CONFIG_SCSI_PM8001 is not set -# CONFIG_SCSI_SRP is not set -# CONFIG_SCSI_BFA_FC is not set -# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set -# CONFIG_SCSI_DH is not set -# CONFIG_SCSI_OSD_INITIATOR is not set CONFIG_ATA=y -# CONFIG_ATA_NONSTANDARD is not set -CONFIG_ATA_VERBOSE_ERROR=y -CONFIG_SATA_PMP=y - -# -# Controllers with non-SFF native interface -# -# CONFIG_SATA_AHCI is not set -# CONFIG_SATA_AHCI_PLATFORM is not set -# CONFIG_SATA_INIC162X is not set -# CONFIG_SATA_ACARD_AHCI is not set CONFIG_SATA_SIL24=y # CONFIG_ATA_SFF is not set CONFIG_MD=y CONFIG_BLK_DEV_MD=y -CONFIG_MD_AUTODETECT=y CONFIG_MD_LINEAR=m CONFIG_MD_RAID0=m CONFIG_MD_RAID1=m CONFIG_MD_RAID10=m CONFIG_MD_RAID456=m CONFIG_MULTICORE_RAID456=y -# CONFIG_MD_MULTIPATH is not set CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=m CONFIG_DM_DEBUG=y CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m -# CONFIG_DM_THIN_PROVISIONING is not set CONFIG_DM_MIRROR=m -# CONFIG_DM_RAID is not set CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m @@ -955,55 +339,22 @@ CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y -# CONFIG_DM_FLAKEY is not set -# CONFIG_TARGET_CORE is not set CONFIG_FUSION=y -# CONFIG_FUSION_SPI is not set -# CONFIG_FUSION_FC is not set CONFIG_FUSION_SAS=y -CONFIG_FUSION_MAX_SGE=128 -# CONFIG_FUSION_CTL is not set -# CONFIG_FUSION_LOGGING is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_FIREWIRE is not set -# CONFIG_FIREWIRE_NOSY is not set -# CONFIG_I2O is not set CONFIG_NETDEVICES=y -CONFIG_NET_CORE=y CONFIG_BONDING=m CONFIG_DUMMY=m -# CONFIG_EQUALIZER is not set -# CONFIG_NET_FC is not set -# CONFIG_MII is not set CONFIG_IFB=m -# CONFIG_NET_TEAM is not set CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y -CONFIG_NETPOLL=y CONFIG_NETPOLL_TRAP=y -CONFIG_NET_POLL_CONTROLLER=y CONFIG_TUN=y CONFIG_VETH=m -# CONFIG_ARCNET is not set - -# -# CAIF transport drivers -# - -# -# Distributed Switch Architecture drivers -# -CONFIG_NET_DSA_MV88E6XXX=y CONFIG_NET_DSA_MV88E6060=y -CONFIG_NET_DSA_MV88E6XXX_NEED_PPU=y CONFIG_NET_DSA_MV88E6131=y CONFIG_NET_DSA_MV88E6123_61_65=y -CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_3COM is not set # CONFIG_NET_VENDOR_ADAPTEC is not set # CONFIG_NET_VENDOR_ALTEON is not set @@ -1011,27 +362,21 @@ CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set -# CONFIG_NET_CALXEDA_XGMAC is not set # CONFIG_NET_VENDOR_CHELSIO is not set # CONFIG_NET_VENDOR_CISCO is not set -# CONFIG_DNET is not set # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set # CONFIG_NET_VENDOR_EXAR is not set # CONFIG_NET_VENDOR_HP is not set # CONFIG_NET_VENDOR_INTEL is not set -# CONFIG_IP1000 is not set -# CONFIG_JME is not set # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MELLANOX is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MYRI is not set -# CONFIG_FEALNX is not set # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set -# CONFIG_ETHOC is not set # CONFIG_NET_PACKET_ENGINE is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_REALTEK is not set @@ -1039,548 +384,92 @@ CONFIG_ETHERNET=y # CONFIG_NET_VENDOR_SEEQ is not set # CONFIG_NET_VENDOR_SILAN is not set # CONFIG_NET_VENDOR_SIS is not set -# CONFIG_SFC is not set # CONFIG_NET_VENDOR_SMSC is not set # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_SUN is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set -CONFIG_TILE_NET=y # CONFIG_NET_VENDOR_VIA is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -CONFIG_PHYLIB=y - -# -# MII PHY device drivers -# -# CONFIG_MARVELL_PHY is not set -# CONFIG_DAVICOM_PHY is not set -# CONFIG_QSEMI_PHY is not set -# CONFIG_LXT_PHY is not set -# CONFIG_CICADA_PHY is not set -# CONFIG_VITESSE_PHY is not set -# CONFIG_SMSC_PHY is not set -# CONFIG_BROADCOM_PHY is not set -# CONFIG_ICPLUS_PHY is not set -# CONFIG_REALTEK_PHY is not set -# CONFIG_NATIONAL_PHY is not set -# CONFIG_STE10XP is not set -# CONFIG_LSI_ET1011C_PHY is not set -# CONFIG_MICREL_PHY is not set -# CONFIG_FIXED_PHY is not set -# CONFIG_MDIO_BITBANG is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_TR is not set # CONFIG_WLAN is not set - -# -# Enable WiMAX (Networking options) to see the WiMAX drivers -# -# CONFIG_WAN is not set -# CONFIG_VMXNET3 is not set -# CONFIG_ISDN is not set -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y -# CONFIG_INPUT_FF_MEMLESS is not set -# CONFIG_INPUT_POLLDEV is not set -# CONFIG_INPUT_SPARSEKMAP is not set - -# -# Userland interfaces -# # CONFIG_INPUT_MOUSEDEV is not set -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TABLET is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# # CONFIG_SERIO is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# # CONFIG_VT is not set -CONFIG_UNIX98_PTYS=y -# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_SERIAL_NONSTANDARD is not set -# CONFIG_NOZOMI is not set -# CONFIG_N_GSM is not set -# CONFIG_TRACE_SINK is not set -CONFIG_DEVKMEM=y - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_MFD_HSU is not set -# CONFIG_SERIAL_JSM is not set -# CONFIG_SERIAL_TIMBERDALE is not set -# CONFIG_SERIAL_ALTERA_JTAGUART is not set -# CONFIG_SERIAL_ALTERA_UART is not set -# CONFIG_SERIAL_PCH_UART is not set -# CONFIG_SERIAL_XILINX_PS_UART is not set -# CONFIG_TTY_PRINTK is not set -CONFIG_HVC_DRIVER=y -# CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_TIMERIOMEM=m -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# PCMCIA character devices -# -# CONFIG_RAW_DRIVER is not set -# CONFIG_TCG_TPM is not set -CONFIG_DEVPORT=y -# CONFIG_RAMOOPS is not set -CONFIG_TILE_SROM=y CONFIG_I2C=y -CONFIG_I2C_BOARDINFO=y -CONFIG_I2C_COMPAT=y CONFIG_I2C_CHARDEV=y -# CONFIG_I2C_MUX is not set -CONFIG_I2C_HELPER_AUTO=y - -# -# I2C Hardware Bus support -# - -# -# PC SMBus host controller drivers -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -# CONFIG_I2C_AMD756 is not set -# CONFIG_I2C_AMD8111 is not set -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_ISCH is not set -# CONFIG_I2C_PIIX4 is not set -# CONFIG_I2C_NFORCE2 is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -# CONFIG_I2C_SIS96X is not set -# CONFIG_I2C_VIA is not set -# CONFIG_I2C_VIAPRO is not set - -# -# I2C system bus drivers (mostly embedded / system-on-chip) -# -# CONFIG_I2C_DESIGNWARE_PCI is not set -# CONFIG_I2C_INTEL_MID is not set -# CONFIG_I2C_OCORES is not set -# CONFIG_I2C_PCA_PLATFORM is not set -# CONFIG_I2C_PXA_PCI is not set -# CONFIG_I2C_SIMTEC is not set -# CONFIG_I2C_XILINX is not set -# CONFIG_I2C_EG20T is not set - -# -# External I2C/SMBus adapter drivers -# -# CONFIG_I2C_PARPORT_LIGHT is not set -# CONFIG_I2C_TAOS_EVM is not set - -# -# Other I2C/SMBus bus drivers -# -# CONFIG_I2C_STUB is not set -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_SPI is not set - -# -# PPS support -# -# CONFIG_PPS is not set - -# -# PPS generators support -# - -# -# PTP clock support -# - -# -# Enable Device Drivers -> PPS to see the PTP clock options. -# -# CONFIG_W1 is not set -# CONFIG_POWER_SUPPLY is not set # CONFIG_HWMON is not set -# CONFIG_THERMAL is not set CONFIG_WATCHDOG=y -# CONFIG_WATCHDOG_CORE is not set CONFIG_WATCHDOG_NOWAYOUT=y - -# -# Watchdog Device Drivers -# -# CONFIG_SOFT_WATCHDOG is not set -# CONFIG_ALIM7101_WDT is not set - -# -# PCI-based Watchdog Cards -# -# CONFIG_PCIPCWATCHDOG is not set -# CONFIG_WDTPCI is not set -CONFIG_SSB_POSSIBLE=y - -# -# Sonics Silicon Backplane -# -# CONFIG_SSB is not set -CONFIG_BCMA_POSSIBLE=y - -# -# Broadcom specific AMBA -# -# CONFIG_BCMA is not set - -# -# Multifunction device drivers -# -# CONFIG_MFD_CORE is not set -# CONFIG_MFD_88PM860X is not set -# CONFIG_MFD_SM501 is not set -# CONFIG_HTC_PASIC3 is not set -# CONFIG_TPS6105X is not set -# CONFIG_TPS6507X is not set -# CONFIG_TWL4030_CORE is not set -# CONFIG_MFD_STMPE is not set -# CONFIG_MFD_TC3589X is not set -# CONFIG_MFD_TMIO is not set -# CONFIG_PMIC_DA903X is not set -# CONFIG_MFD_DA9052_I2C is not set -# CONFIG_PMIC_ADP5520 is not set -# CONFIG_MFD_MAX8925 is not set -# CONFIG_MFD_MAX8997 is not set -# CONFIG_MFD_MAX8998 is not set -# CONFIG_MFD_S5M_CORE is not set -# CONFIG_MFD_WM8400 is not set -# CONFIG_MFD_WM831X_I2C is not set -# CONFIG_MFD_WM8350_I2C is not set -# CONFIG_MFD_WM8994 is not set -# CONFIG_MFD_PCF50633 is not set -# CONFIG_ABX500_CORE is not set -# CONFIG_LPC_SCH is not set -# CONFIG_MFD_RDC321X is not set -# CONFIG_MFD_JANZ_CMODIO is not set -# CONFIG_MFD_VX855 is not set -# CONFIG_MFD_WL1273_CORE is not set -# CONFIG_REGULATOR is not set -# CONFIG_MEDIA_SUPPORT is not set - -# -# Graphics support -# # CONFIG_VGA_ARB is not set -# CONFIG_DRM is not set -# CONFIG_STUB_POULSBO is not set -# CONFIG_VGASTATE is not set -# CONFIG_VIDEO_OUTPUT_CONTROL is not set -# CONFIG_FB is not set -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set -# CONFIG_SOUND is not set # CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set -# CONFIG_UWB is not set -# CONFIG_MMC is not set -# CONFIG_MEMSTICK is not set -# CONFIG_NEW_LEDS is not set -# CONFIG_ACCESSIBILITY is not set -# CONFIG_INFINIBAND is not set CONFIG_EDAC=y - -# -# Reporting subsystems -# -# CONFIG_EDAC_DEBUG is not set CONFIG_EDAC_MM_EDAC=y -CONFIG_EDAC_TILE=y -CONFIG_RTC_LIB=y CONFIG_RTC_CLASS=y -CONFIG_RTC_HCTOSYS=y -CONFIG_RTC_HCTOSYS_DEVICE="rtc0" -# CONFIG_RTC_DEBUG is not set - -# -# RTC interfaces -# -CONFIG_RTC_INTF_SYSFS=y -CONFIG_RTC_INTF_PROC=y -CONFIG_RTC_INTF_DEV=y -# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set -# CONFIG_RTC_DRV_TEST is not set - -# -# I2C RTC drivers -# -# CONFIG_RTC_DRV_DS1307 is not set -# CONFIG_RTC_DRV_DS1374 is not set -# CONFIG_RTC_DRV_DS1672 is not set -# CONFIG_RTC_DRV_DS3232 is not set -# CONFIG_RTC_DRV_MAX6900 is not set -# CONFIG_RTC_DRV_RS5C372 is not set -# CONFIG_RTC_DRV_ISL1208 is not set -# CONFIG_RTC_DRV_ISL12022 is not set -# CONFIG_RTC_DRV_X1205 is not set -# CONFIG_RTC_DRV_PCF8563 is not set -# CONFIG_RTC_DRV_PCF8583 is not set -# CONFIG_RTC_DRV_M41T80 is not set -# CONFIG_RTC_DRV_BQ32K is not set -# CONFIG_RTC_DRV_S35390A is not set -# CONFIG_RTC_DRV_FM3130 is not set -# CONFIG_RTC_DRV_RX8581 is not set -# CONFIG_RTC_DRV_RX8025 is not set -# CONFIG_RTC_DRV_EM3027 is not set -# CONFIG_RTC_DRV_RV3029C2 is not set - -# -# SPI RTC drivers -# - -# -# Platform RTC drivers -# -# CONFIG_RTC_DRV_DS1286 is not set -# CONFIG_RTC_DRV_DS1511 is not set -# CONFIG_RTC_DRV_DS1553 is not set -# CONFIG_RTC_DRV_DS1742 is not set -# CONFIG_RTC_DRV_STK17TA8 is not set -# CONFIG_RTC_DRV_M48T86 is not set -# CONFIG_RTC_DRV_M48T35 is not set -# CONFIG_RTC_DRV_M48T59 is not set -# CONFIG_RTC_DRV_MSM6242 is not set -# CONFIG_RTC_DRV_BQ4802 is not set -# CONFIG_RTC_DRV_RP5C01 is not set -# CONFIG_RTC_DRV_V3020 is not set - -# -# on-CPU RTC drivers -# CONFIG_RTC_DRV_TILE=y -# CONFIG_DMADEVICES is not set -# CONFIG_AUXDISPLAY is not set -# CONFIG_UIO is not set - -# -# Virtio drivers -# -# CONFIG_VIRTIO_PCI is not set -# CONFIG_VIRTIO_BALLOON is not set -# CONFIG_VIRTIO_MMIO is not set - -# -# Microsoft Hyper-V guest support -# -# CONFIG_STAGING is not set - -# -# Hardware Spinlock drivers -# -CONFIG_IOMMU_SUPPORT=y -# CONFIG_VIRT_DRIVERS is not set -# CONFIG_PM_DEVFREQ is not set - -# -# File systems -# CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT2_FS_XIP=y CONFIG_EXT3_FS=y -CONFIG_EXT3_DEFAULTS_TO_ORDERED=y -CONFIG_EXT3_FS_XATTR=y CONFIG_EXT3_FS_POSIX_ACL=y CONFIG_EXT3_FS_SECURITY=y CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_XATTR=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -# CONFIG_EXT4_DEBUG is not set -CONFIG_FS_XIP=y -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_JBD2=y -# CONFIG_JBD2_DEBUG is not set -CONFIG_FS_MBCACHE=y -# CONFIG_REISERFS_FS is not set -# CONFIG_JFS_FS is not set CONFIG_XFS_FS=y CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y -# CONFIG_XFS_RT is not set -# CONFIG_XFS_DEBUG is not set CONFIG_GFS2_FS=m CONFIG_GFS2_FS_LOCKING_DLM=y -# CONFIG_OCFS2_FS is not set CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y -# CONFIG_BTRFS_FS_CHECK_INTEGRITY is not set -# CONFIG_NILFS2_FS is not set -CONFIG_FS_POSIX_ACL=y -CONFIG_EXPORTFS=y -CONFIG_FILE_LOCKING=y -CONFIG_FSNOTIFY=y -CONFIG_DNOTIFY=y -CONFIG_INOTIFY_USER=y -# CONFIG_FANOTIFY is not set CONFIG_QUOTA=y CONFIG_QUOTA_NETLINK_INTERFACE=y # CONFIG_PRINT_QUOTA_WARNING is not set -# CONFIG_QUOTA_DEBUG is not set -CONFIG_QUOTA_TREE=y -# CONFIG_QFMT_V1 is not set CONFIG_QFMT_V2=y -CONFIG_QUOTACTL=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m -CONFIG_GENERIC_ACL=y - -# -# Caches -# CONFIG_FSCACHE=m CONFIG_FSCACHE_STATS=y -# CONFIG_FSCACHE_HISTOGRAM is not set -# CONFIG_FSCACHE_DEBUG is not set -# CONFIG_FSCACHE_OBJECT_LIST is not set CONFIG_CACHEFILES=m -# CONFIG_CACHEFILES_DEBUG is not set -# CONFIG_CACHEFILES_HISTOGRAM is not set - -# -# CD-ROM/DVD Filesystems -# CONFIG_ISO9660_FS=m CONFIG_JOLIET=y CONFIG_ZISOFS=y CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_FAT_DEFAULT_IOCHARSET="ascii" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y CONFIG_PROC_KCORE=y -CONFIG_PROC_SYSCTL=y -CONFIG_PROC_PAGE_MONITOR=y -CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y -CONFIG_TMPFS_XATTR=y CONFIG_HUGETLBFS=y -CONFIG_HUGETLB_PAGE=y -CONFIG_CONFIGFS_FS=m -CONFIG_MISC_FILESYSTEMS=y -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set CONFIG_ECRYPT_FS=m -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_LOGFS is not set CONFIG_CRAMFS=m CONFIG_SQUASHFS=m -# CONFIG_SQUASHFS_XATTR is not set -CONFIG_SQUASHFS_ZLIB=y -# CONFIG_SQUASHFS_LZO is not set -# CONFIG_SQUASHFS_XZ is not set -# CONFIG_SQUASHFS_4K_DEVBLK_SIZE is not set -# CONFIG_SQUASHFS_EMBEDDED is not set -CONFIG_SQUASHFS_FRAGMENT_CACHE_SIZE=3 -# CONFIG_VXFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_OMFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_PSTORE is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set -CONFIG_NETWORK_FILESYSTEMS=y CONFIG_NFS_FS=m CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_NFS_V4_1=y -CONFIG_PNFS_FILE_LAYOUT=m -CONFIG_PNFS_BLOCK=m CONFIG_NFS_FSCACHE=y -# CONFIG_NFS_USE_LEGACY_DNS is not set -CONFIG_NFS_USE_KERNEL_DNS=y -# CONFIG_NFS_USE_NEW_IDMAPPER is not set CONFIG_NFSD=m -CONFIG_NFSD_V2_ACL=y -CONFIG_NFSD_V3=y CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y -# CONFIG_NFSD_FAULT_INJECTION is not set -CONFIG_LOCKD=m -CONFIG_LOCKD_V4=y -CONFIG_NFS_ACL_SUPPORT=m -CONFIG_NFS_COMMON=y -CONFIG_SUNRPC=m -CONFIG_SUNRPC_GSS=m -CONFIG_SUNRPC_BACKCHANNEL=y -CONFIG_RPCSEC_GSS_KRB5=m -# CONFIG_CEPH_FS is not set CONFIG_CIFS=m CONFIG_CIFS_STATS=y -# CONFIG_CIFS_STATS2 is not set CONFIG_CIFS_WEAK_PW_HASH=y CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y -# CONFIG_CIFS_DEBUG2 is not set CONFIG_CIFS_DFS_UPCALL=y CONFIG_CIFS_FSCACHE=y -# CONFIG_CIFS_ACL is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set CONFIG_NLS=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=y @@ -1621,192 +510,48 @@ CONFIG_NLS_ISO8859_15=m CONFIG_NLS_KOI8_R=m CONFIG_NLS_KOI8_U=m CONFIG_NLS_UTF8=m -CONFIG_DLM=m CONFIG_DLM_DEBUG=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEFAULT_MESSAGE_LOGLEVEL=4 # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_WARN=2048 CONFIG_MAGIC_SYSRQ=y CONFIG_STRIP_ASM_SYMS=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y CONFIG_HEADERS_CHECK=y -# CONFIG_DEBUG_SECTION_MISMATCH is not set -CONFIG_DEBUG_KERNEL=y -# CONFIG_DEBUG_SHIRQ is not set CONFIG_LOCKUP_DETECTOR=y -# CONFIG_HARDLOCKUP_DETECTOR is not set -# CONFIG_BOOTPARAM_HARDLOCKUP_PANIC is not set -CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE=0 -# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set -CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0 -CONFIG_DETECT_HUNG_TASK=y -CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=120 -# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set -CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0 -CONFIG_SCHED_DEBUG=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -# CONFIG_DEBUG_OBJECTS is not set -# CONFIG_SLUB_DEBUG_ON is not set -# CONFIG_SLUB_STATS is not set -# CONFIG_DEBUG_KMEMLEAK is not set -# CONFIG_DEBUG_RT_MUTEXES is not set -# CONFIG_RT_MUTEX_TESTER is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_MUTEXES is not set -# CONFIG_DEBUG_LOCK_ALLOC is not set -# CONFIG_PROVE_LOCKING is not set -# CONFIG_SPARSE_RCU_POINTER is not set -# CONFIG_LOCK_STAT is not set -# CONFIG_DEBUG_ATOMIC_SLEEP is not set -# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set -CONFIG_STACKTRACE=y -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_HIGHMEM is not set -CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_REDUCED=y CONFIG_DEBUG_VM=y -# CONFIG_DEBUG_WRITECOUNT is not set CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_LIST=y -# CONFIG_TEST_LIST_SORT is not set -# CONFIG_DEBUG_SG is not set -# CONFIG_DEBUG_NOTIFIERS is not set CONFIG_DEBUG_CREDENTIALS=y -# CONFIG_RCU_TORTURE_TEST is not set -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -# CONFIG_BACKTRACE_SELF_TEST is not set -# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -# CONFIG_DEBUG_PER_CPU_MAPS is not set -# CONFIG_LKDTM is not set -# CONFIG_FAULT_INJECTION is not set -# CONFIG_SYSCTL_SYSCALL_CHECK is not set -# CONFIG_DEBUG_PAGEALLOC is not set -CONFIG_TRACING_SUPPORT=y -CONFIG_FTRACE=y -# CONFIG_IRQSOFF_TRACER is not set -# CONFIG_SCHED_TRACER is not set -# CONFIG_ENABLE_DEFAULT_TRACERS is not set -CONFIG_BRANCH_PROFILE_NONE=y -# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set -# CONFIG_PROFILE_ALL_BRANCHES is not set -# CONFIG_BLK_DEV_IO_TRACE is not set -# CONFIG_BUILD_DOCSRC is not set CONFIG_DYNAMIC_DEBUG=y -# CONFIG_ATOMIC64_SELFTEST is not set CONFIG_ASYNC_RAID6_TEST=m -# CONFIG_SAMPLES is not set -# CONFIG_TEST_KSTRTOX is not set -CONFIG_EARLY_PRINTK=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_DEBUG_EXTRA_FLAGS="" - -# -# Security options -# -CONFIG_KEYS=y -# CONFIG_ENCRYPTED_KEYS is not set CONFIG_KEYS_DEBUG_PROC_KEYS=y -# CONFIG_SECURITY_DMESG_RESTRICT is not set CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_NETWORK_XFRM=y -# CONFIG_SECURITY_PATH is not set -CONFIG_LSM_MMAP_MIN_ADDR=65536 CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_SECURITY_SELINUX_DEVELOP=y -CONFIG_SECURITY_SELINUX_AVC_STATS=y -CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 -# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set -# CONFIG_SECURITY_SMACK is not set -# CONFIG_SECURITY_TOMOYO is not set -# CONFIG_SECURITY_APPARMOR is not set -# CONFIG_IMA is not set -# CONFIG_EVM is not set -CONFIG_DEFAULT_SECURITY_SELINUX=y -# CONFIG_DEFAULT_SECURITY_DAC is not set -CONFIG_DEFAULT_SECURITY="selinux" -CONFIG_XOR_BLOCKS=m -CONFIG_ASYNC_CORE=m -CONFIG_ASYNC_MEMCPY=m -CONFIG_ASYNC_XOR=m -CONFIG_ASYNC_PQ=m -CONFIG_ASYNC_RAID6_RECOV=m -CONFIG_CRYPTO=y - -# -# Crypto core or helper -# -CONFIG_CRYPTO_ALGAPI=y -CONFIG_CRYPTO_ALGAPI2=y -CONFIG_CRYPTO_AEAD=m -CONFIG_CRYPTO_AEAD2=y -CONFIG_CRYPTO_BLKCIPHER=m -CONFIG_CRYPTO_BLKCIPHER2=y -CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_HASH2=y -CONFIG_CRYPTO_RNG=m -CONFIG_CRYPTO_RNG2=y -CONFIG_CRYPTO_PCOMP=m -CONFIG_CRYPTO_PCOMP2=y -CONFIG_CRYPTO_MANAGER=y -CONFIG_CRYPTO_MANAGER2=y -# CONFIG_CRYPTO_USER is not set -CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y -CONFIG_CRYPTO_GF128MUL=m CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_PCRYPT=m -CONFIG_CRYPTO_WORKQUEUE=y CONFIG_CRYPTO_CRYPTD=m -CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m - -# -# Authenticated Encryption with Associated Data -# CONFIG_CRYPTO_CCM=m CONFIG_CRYPTO_GCM=m -CONFIG_CRYPTO_SEQIV=m - -# -# Block modes -# -CONFIG_CRYPTO_CBC=m -CONFIG_CRYPTO_CTR=m CONFIG_CRYPTO_CTS=m -CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m - -# -# Hash modes -# CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m - -# -# Digest -# CONFIG_CRYPTO_CRC32C=y -CONFIG_CRYPTO_GHASH=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -1817,78 +562,18 @@ CONFIG_CRYPTO_SHA256=m CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m - -# -# Ciphers -# -CONFIG_CRYPTO_AES=m CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_BLOWFISH_COMMON=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m -# CONFIG_CRYPTO_SALSA20 is not set CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_TWOFISH_COMMON=m - -# -# Compression -# -CONFIG_CRYPTO_DEFLATE=m CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m - -# -# Random Number Generation -# -CONFIG_CRYPTO_ANSI_CPRNG=m -# CONFIG_CRYPTO_USER_API_HASH is not set -# CONFIG_CRYPTO_USER_API_SKCIPHER is not set -CONFIG_CRYPTO_HW=y -# CONFIG_BINARY_PRINTF is not set - -# -# Library routines -# -CONFIG_RAID6_PQ=m -CONFIG_BITREVERSE=y -CONFIG_GENERIC_FIND_FIRST_BIT=y -CONFIG_GENERIC_PCI_IOMAP=y CONFIG_CRC_CCITT=m -CONFIG_CRC16=y -CONFIG_CRC_T10DIF=y -CONFIG_CRC_ITU_T=m -CONFIG_CRC32=y CONFIG_CRC7=m -CONFIG_LIBCRC32C=m -# CONFIG_CRC8 is not set -CONFIG_AUDIT_GENERIC=y -CONFIG_ZLIB_INFLATE=y -CONFIG_ZLIB_DEFLATE=m -CONFIG_LZO_COMPRESS=m -CONFIG_LZO_DECOMPRESS=m -# CONFIG_XZ_DEC is not set -# CONFIG_XZ_DEC_BCJ is not set -CONFIG_DECOMPRESS_GZIP=y -CONFIG_TEXTSEARCH=y -CONFIG_TEXTSEARCH_KMP=m -CONFIG_TEXTSEARCH_BM=m -CONFIG_TEXTSEARCH_FSM=m -CONFIG_HAS_IOMEM=y -CONFIG_HAS_IOPORT=y -CONFIG_HAS_DMA=y -CONFIG_CPU_RMAP=y -CONFIG_DQL=y -CONFIG_NLATTR=y -# CONFIG_AVERAGE is not set -# CONFIG_CORDIC is not set -CONFIG_HAVE_KVM=y -# CONFIG_VIRTUALIZATION is not set diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 4c1ac6e5347a..6ae495ef2b99 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -108,9 +108,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5bed94e189fa..09675d3e0ac3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -82,6 +82,7 @@ config X86 select CLKEVT_I8253 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP + select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index da0b3ca815b7..382f75d735f3 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -7,7 +7,6 @@ typedef struct { unsigned int __softirq_pending; unsigned int __nmi_count; /* arch dependent */ - unsigned int irq0_irqs; #ifdef CONFIG_X86_LOCAL_APIC unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 431793e5d484..34baa0eb5d0c 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset); static inline unsigned long long __cycles_2_ns(unsigned long long cyc) { - unsigned long long quot; - unsigned long long rem; int cpu = smp_processor_id(); unsigned long long ns = per_cpu(cyc2ns_offset, cpu); - quot = (cyc >> CYC2NS_SCALE_FACTOR); - rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1); - ns += quot * per_cpu(cyc2ns, cpu) + - ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR); + ns += mult_frac(cyc, per_cpu(cyc2ns, cpu), + (1UL << CYC2NS_SCALE_FACTOR)); return ns; } diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 40fc86161d92..58b7f27cb3e9 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -100,13 +100,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) irqctx->tinfo.task = curctx->tinfo.task; irqctx->tinfo.previous_esp = current_stack_pointer; - /* - * Copy the softirq bits in preempt_count so that the - * softirq checks work in the hardirq context. - */ - irqctx->tinfo.preempt_count = - (irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) | - (curctx->tinfo.preempt_count & SOFTIRQ_MASK); + /* Copy the preempt_count so that the [soft]irq checks work. */ + irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count; if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp); @@ -196,7 +191,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) if (unlikely(!desc)) return false; - if (!execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) { if (unlikely(overflow)) print_stack_overflow(); desc->handle_irq(irq, desc); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c08d1ff12b7c..49888fefe794 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -119,9 +119,7 @@ void cpu_idle(void) } rcu_idle_exit(); tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cfa5c90c01db..e34257c70c28 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -156,9 +156,7 @@ void cpu_idle(void) } tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 66d250c00d11..58f78165d308 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -291,19 +291,6 @@ notrace static void __cpuinit start_secondary(void *unused) per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; x86_platform.nmi_init(); - /* - * Wait until the cpu which brought this one up marked it - * online before enabling interrupts. If we don't do that then - * we can end up waking up the softirq thread before this cpu - * reached the active state, which makes the scheduler unhappy - * and schedule the softirq thread on the wrong cpu. This is - * only observable with forced threaded interrupts, but in - * theory it could also happen w/o them. It's just way harder - * to achieve. - */ - while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask)) - cpu_relax(); - /* enable local interrupts */ local_irq_enable(); diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index dd5fbf4101fc..c6eba2b42673 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -57,9 +57,6 @@ EXPORT_SYMBOL(profile_pc); */ static irqreturn_t timer_interrupt(int irq, void *dev_id) { - /* Keep nmi watchdog up to date */ - inc_irq_stat(irq0_irqs); - global_clock_event->event_handler(global_clock_event); /* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index a62c201c97ec..183c5925a9fe 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -620,7 +620,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) if (cpu_khz) { *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz; - *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR); + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); } sched_clock_idle_wakeup_event(0); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 9eba29b46cb7..fc25e60a5884 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -42,7 +42,7 @@ static __cpuinitdata int nr_warps; /* * TSC-warp measurement loop running on both CPUs: */ -static __cpuinit void check_tsc_warp(void) +static __cpuinit void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; @@ -51,9 +51,9 @@ static __cpuinit void check_tsc_warp(void) start = get_cycles(); rdtsc_barrier(); /* - * The measurement runs for 20 msecs: + * The measurement runs for 'timeout' msecs: */ - end = start + tsc_khz * 20ULL; + end = start + (cycles_t) tsc_khz * timeout; now = start; for (i = 0; ; i++) { @@ -99,6 +99,25 @@ static __cpuinit void check_tsc_warp(void) } /* + * If the target CPU coming online doesn't have any of its core-siblings + * online, a timeout of 20msec will be used for the TSC-warp measurement + * loop. Otherwise a smaller timeout of 2msec will be used, as we have some + * information about this socket already (and this information grows as we + * have more and more logical-siblings in that socket). + * + * Ideally we should be able to skip the TSC sync check on the other + * core-siblings, if the first logical CPU in a socket passed the sync test. + * But as the TSC is per-logical CPU and can potentially be modified wrongly + * by the bios, TSC sync test for smaller duration should be able + * to catch such errors. Also this will catch the condition where all the + * cores in the socket doesn't get reset at the same time. + */ +static inline unsigned int loop_timeout(int cpu) +{ + return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; +} + +/* * Source CPU calls into this - it waits for the freshly booted * target CPU to arrive and then starts the measurement: */ @@ -135,7 +154,7 @@ void __cpuinit check_tsc_sync_source(int cpu) */ atomic_inc(&start_count); - check_tsc_warp(); + check_tsc_warp(loop_timeout(cpu)); while (atomic_read(&stop_count) != cpus-1) cpu_relax(); @@ -183,7 +202,7 @@ void __cpuinit check_tsc_sync_target(void) while (atomic_read(&start_count) != cpus) cpu_relax(); - check_tsc_warp(); + check_tsc_warp(loop_timeout(smp_processor_id())); /* * Ok, we are done: diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 47041e7c088c..2c9004770c4e 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -113,9 +113,7 @@ void cpu_idle(void) while (1) { while (!need_resched()) platform_idle(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } } diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 8b782a63c297..fb95dd2f889a 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -36,11 +36,23 @@ static void icq_free_icq_rcu(struct rcu_head *head) kmem_cache_free(icq->__rcu_icq_cache, icq); } -/* - * Exit and free an icq. Called with both ioc and q locked. - */ +/* Exit an icq. Called with both ioc and q locked. */ static void ioc_exit_icq(struct io_cq *icq) { + struct elevator_type *et = icq->q->elevator->type; + + if (icq->flags & ICQ_EXITED) + return; + + if (et->ops.elevator_exit_icq_fn) + et->ops.elevator_exit_icq_fn(icq); + + icq->flags |= ICQ_EXITED; +} + +/* Release an icq. Called with both ioc and q locked. */ +static void ioc_destroy_icq(struct io_cq *icq) +{ struct io_context *ioc = icq->ioc; struct request_queue *q = icq->q; struct elevator_type *et = q->elevator->type; @@ -60,8 +72,7 @@ static void ioc_exit_icq(struct io_cq *icq) if (rcu_dereference_raw(ioc->icq_hint) == icq) rcu_assign_pointer(ioc->icq_hint, NULL); - if (et->ops.elevator_exit_icq_fn) - et->ops.elevator_exit_icq_fn(icq); + ioc_exit_icq(icq); /* * @icq->q might have gone away by the time RCU callback runs @@ -79,7 +90,6 @@ static void ioc_release_fn(struct work_struct *work) { struct io_context *ioc = container_of(work, struct io_context, release_work); - struct request_queue *last_q = NULL; unsigned long flags; /* @@ -93,44 +103,19 @@ static void ioc_release_fn(struct work_struct *work) while (!hlist_empty(&ioc->icq_list)) { struct io_cq *icq = hlist_entry(ioc->icq_list.first, struct io_cq, ioc_node); - struct request_queue *this_q = icq->q; - - if (this_q != last_q) { - /* - * Need to switch to @this_q. Once we release - * @ioc->lock, it can go away along with @cic. - * Hold on to it. - */ - __blk_get_queue(this_q); - - /* - * blk_put_queue() might sleep thanks to kobject - * idiocy. Always release both locks, put and - * restart. - */ - if (last_q) { - spin_unlock(last_q->queue_lock); - spin_unlock_irqrestore(&ioc->lock, flags); - blk_put_queue(last_q); - } else { - spin_unlock_irqrestore(&ioc->lock, flags); - } - - last_q = this_q; - spin_lock_irqsave(this_q->queue_lock, flags); - spin_lock_nested(&ioc->lock, 1); - continue; + struct request_queue *q = icq->q; + + if (spin_trylock(q->queue_lock)) { + ioc_destroy_icq(icq); + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); + cpu_relax(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); } - ioc_exit_icq(icq); } - if (last_q) { - spin_unlock(last_q->queue_lock); - spin_unlock_irqrestore(&ioc->lock, flags); - blk_put_queue(last_q); - } else { - spin_unlock_irqrestore(&ioc->lock, flags); - } + spin_unlock_irqrestore(&ioc->lock, flags); kmem_cache_free(iocontext_cachep, ioc); } @@ -145,6 +130,7 @@ static void ioc_release_fn(struct work_struct *work) void put_io_context(struct io_context *ioc) { unsigned long flags; + bool free_ioc = false; if (ioc == NULL) return; @@ -159,8 +145,13 @@ void put_io_context(struct io_context *ioc) spin_lock_irqsave(&ioc->lock, flags); if (!hlist_empty(&ioc->icq_list)) schedule_work(&ioc->release_work); + else + free_ioc = true; spin_unlock_irqrestore(&ioc->lock, flags); } + + if (free_ioc) + kmem_cache_free(iocontext_cachep, ioc); } EXPORT_SYMBOL(put_io_context); @@ -168,13 +159,41 @@ EXPORT_SYMBOL(put_io_context); void exit_io_context(struct task_struct *task) { struct io_context *ioc; + struct io_cq *icq; + struct hlist_node *n; + unsigned long flags; task_lock(task); ioc = task->io_context; task->io_context = NULL; task_unlock(task); - atomic_dec(&ioc->nr_tasks); + if (!atomic_dec_and_test(&ioc->nr_tasks)) { + put_io_context(ioc); + return; + } + + /* + * Need ioc lock to walk icq_list and q lock to exit icq. Perform + * reverse double locking. Read comment in ioc_release_fn() for + * explanation on the nested locking annotation. + */ +retry: + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node) { + if (icq->flags & ICQ_EXITED) + continue; + if (spin_trylock(icq->q->queue_lock)) { + ioc_exit_icq(icq); + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); + cpu_relax(); + goto retry; + } + } + spin_unlock_irqrestore(&ioc->lock, flags); + put_io_context(ioc); } @@ -194,7 +213,7 @@ void ioc_clear_queue(struct request_queue *q) struct io_context *ioc = icq->ioc; spin_lock(&ioc->lock); - ioc_exit_icq(icq); + ioc_destroy_icq(icq); spin_unlock(&ioc->lock); } } @@ -363,13 +382,13 @@ struct io_cq *ioc_create_icq(struct request_queue *q, gfp_t gfp_mask) return icq; } -void ioc_set_changed(struct io_context *ioc, int which) +void ioc_set_icq_flags(struct io_context *ioc, unsigned int flags) { struct io_cq *icq; struct hlist_node *n; hlist_for_each_entry(icq, n, &ioc->icq_list, ioc_node) - set_bit(which, &icq->changed); + icq->flags |= flags; } /** @@ -387,7 +406,7 @@ void ioc_ioprio_changed(struct io_context *ioc, int ioprio) spin_lock_irqsave(&ioc->lock, flags); ioc->ioprio = ioprio; - ioc_set_changed(ioc, ICQ_IOPRIO_CHANGED); + ioc_set_icq_flags(ioc, ICQ_IOPRIO_CHANGED); spin_unlock_irqrestore(&ioc->lock, flags); } @@ -404,11 +423,33 @@ void ioc_cgroup_changed(struct io_context *ioc) unsigned long flags; spin_lock_irqsave(&ioc->lock, flags); - ioc_set_changed(ioc, ICQ_CGROUP_CHANGED); + ioc_set_icq_flags(ioc, ICQ_CGROUP_CHANGED); spin_unlock_irqrestore(&ioc->lock, flags); } EXPORT_SYMBOL(ioc_cgroup_changed); +/** + * icq_get_changed - fetch and clear icq changed mask + * @icq: icq of interest + * + * Fetch and clear ICQ_*_CHANGED bits from @icq. Grabs and releases + * @icq->ioc->lock. + */ +unsigned icq_get_changed(struct io_cq *icq) +{ + unsigned int changed = 0; + unsigned long flags; + + if (unlikely(icq->flags & ICQ_CHANGED_MASK)) { + spin_lock_irqsave(&icq->ioc->lock, flags); + changed = icq->flags & ICQ_CHANGED_MASK; + icq->flags &= ~ICQ_CHANGED_MASK; + spin_unlock_irqrestore(&icq->ioc->lock, flags); + } + return changed; +} +EXPORT_SYMBOL(icq_get_changed); + static int __init blk_ioc_init(void) { iocontext_cachep = kmem_cache_create("blkdev_ioc", diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 1366a89d8e66..467c8de88642 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -8,6 +8,7 @@ #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/cpu.h> +#include <linux/sched.h> #include "blk.h" @@ -103,9 +104,10 @@ static struct notifier_block __cpuinitdata blk_cpu_notifier = { void __blk_complete_request(struct request *req) { - int ccpu, cpu, group_cpu = NR_CPUS; + int ccpu, cpu; struct request_queue *q = req->q; unsigned long flags; + bool shared = false; BUG_ON(!q->softirq_done_fn); @@ -117,22 +119,20 @@ void __blk_complete_request(struct request *req) */ if (req->cpu != -1) { ccpu = req->cpu; - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) { - ccpu = blk_cpu_to_group(ccpu); - group_cpu = blk_cpu_to_group(cpu); - } + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) + shared = cpus_share_cache(cpu, ccpu); } else ccpu = cpu; /* - * If current CPU and requested CPU are in the same group, running - * softirq in current CPU. One might concern this is just like + * If current CPU and requested CPU share a cache, run the softirq on + * the current CPU. One might concern this is just like * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is * running in interrupt handler, and currently I/O controller doesn't * support multiple interrupts, so current CPU is unique actually. This * avoids IPI sending from current CPU to the first CPU of a group. */ - if (ccpu == cpu || ccpu == group_cpu) { + if (ccpu == cpu || shared) { struct list_head *list; do_local: list = &__get_cpu_var(blk_cpu_done); diff --git a/block/blk.h b/block/blk.h index 9c12f80882b0..d45be871329e 100644 --- a/block/blk.h +++ b/block/blk.h @@ -166,22 +166,6 @@ static inline int queue_congestion_off_threshold(struct request_queue *q) return q->nr_congestion_off; } -static inline int blk_cpu_to_group(int cpu) -{ - int group = NR_CPUS; -#ifdef CONFIG_SCHED_MC - const struct cpumask *mask = cpu_coregroup_mask(cpu); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - group = cpumask_first(topology_thread_cpumask(cpu)); -#else - return cpu; -#endif - if (likely(group < NR_CPUS)) - return group; - return cpu; -} - /* * Contribute to IO statistics IFF: * diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index d0ba50533668..457295253566 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3470,20 +3470,20 @@ cfq_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask) const int rw = rq_data_dir(rq); const bool is_sync = rq_is_sync(rq); struct cfq_queue *cfqq; + unsigned int changed; might_sleep_if(gfp_mask & __GFP_WAIT); spin_lock_irq(q->queue_lock); /* handle changed notifications */ - if (unlikely(cic->icq.changed)) { - if (test_and_clear_bit(ICQ_IOPRIO_CHANGED, &cic->icq.changed)) - changed_ioprio(cic); + changed = icq_get_changed(&cic->icq); + if (unlikely(changed & ICQ_IOPRIO_CHANGED)) + changed_ioprio(cic); #ifdef CONFIG_CFQ_GROUP_IOSCHED - if (test_and_clear_bit(ICQ_CGROUP_CHANGED, &cic->icq.changed)) - changed_cgroup(cic); + if (unlikely(changed & ICQ_CGROUP_CHANGED)) + changed_cgroup(cic); #endif - } new_queue: cfqq = cic_to_cfqq(cic, is_sync); diff --git a/block/genhd.c b/block/genhd.c index 23b4f7063322..df9816ede75b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -35,6 +35,7 @@ static DEFINE_IDR(ext_devt_idr); static struct device_type disk_type; +static void disk_alloc_events(struct gendisk *disk); static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); @@ -601,6 +602,8 @@ void add_disk(struct gendisk *disk) disk->major = MAJOR(devt); disk->first_minor = MINOR(devt); + disk_alloc_events(disk); + /* Register BDI before referencing it from bdev */ bdi = &disk->queue->backing_dev_info; bdi_register_dev(bdi, disk_devt(disk)); @@ -1475,9 +1478,9 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now) intv = disk_events_poll_jiffies(disk); set_timer_slack(&ev->dwork.timer, intv / 4); if (check_now) - queue_delayed_work(system_nrt_wq, &ev->dwork, 0); + queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0); else if (intv) - queue_delayed_work(system_nrt_wq, &ev->dwork, intv); + queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv); out_unlock: spin_unlock_irqrestore(&ev->lock, flags); } @@ -1521,7 +1524,7 @@ void disk_flush_events(struct gendisk *disk, unsigned int mask) ev->clearing |= mask; if (!ev->block) { cancel_delayed_work(&ev->dwork); - queue_delayed_work(system_nrt_wq, &ev->dwork, 0); + queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0); } spin_unlock_irq(&ev->lock); } @@ -1558,7 +1561,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) /* uncondtionally schedule event check and wait for it to finish */ disk_block_events(disk); - queue_delayed_work(system_nrt_wq, &ev->dwork, 0); + queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, 0); flush_delayed_work(&ev->dwork); __disk_unblock_events(disk, false); @@ -1595,7 +1598,7 @@ static void disk_events_workfn(struct work_struct *work) intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) - queue_delayed_work(system_nrt_wq, &ev->dwork, intv); + queue_delayed_work(system_nrt_freezable_wq, &ev->dwork, intv); spin_unlock_irq(&ev->lock); @@ -1733,9 +1736,9 @@ module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, &disk_events_dfl_poll_msecs, 0644); /* - * disk_{add|del|release}_events - initialize and destroy disk_events. + * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. */ -static void disk_add_events(struct gendisk *disk) +static void disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; @@ -1748,16 +1751,6 @@ static void disk_add_events(struct gendisk *disk) return; } - if (sysfs_create_files(&disk_to_dev(disk)->kobj, - disk_events_attrs) < 0) { - pr_warn("%s: failed to create sysfs files for events\n", - disk->disk_name); - kfree(ev); - return; - } - - disk->ev = ev; - INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); @@ -1766,8 +1759,21 @@ static void disk_add_events(struct gendisk *disk) ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); + disk->ev = ev; +} + +static void disk_add_events(struct gendisk *disk) +{ + if (!disk->ev) + return; + + /* FIXME: error handling */ + if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) + pr_warn("%s: failed to create sysfs files for events\n", + disk->disk_name); + mutex_lock(&disk_events_mutex); - list_add_tail(&ev->node, &disk_events); + list_add_tail(&disk->ev->node, &disk_events); mutex_unlock(&disk_events_mutex); /* diff --git a/block/partition-generic.c b/block/partition-generic.c index d06ec1c829c2..6df5d6928a44 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -389,17 +389,11 @@ static bool disk_unlock_native_capacity(struct gendisk *disk) } } -int rescan_partitions(struct gendisk *disk, struct block_device *bdev) +static int drop_partitions(struct gendisk *disk, struct block_device *bdev) { - struct parsed_partitions *state = NULL; struct disk_part_iter piter; struct hd_struct *part; - int p, highest, res; -rescan: - if (state && !IS_ERR(state)) { - kfree(state); - state = NULL; - } + int res; if (bdev->bd_part_count) return -EBUSY; @@ -412,6 +406,24 @@ rescan: delete_partition(disk, part->partno); disk_part_iter_exit(&piter); + return 0; +} + +int rescan_partitions(struct gendisk *disk, struct block_device *bdev) +{ + struct parsed_partitions *state = NULL; + struct hd_struct *part; + int p, highest, res; +rescan: + if (state && !IS_ERR(state)) { + kfree(state); + state = NULL; + } + + res = drop_partitions(disk, bdev); + if (res) + return res; + if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); check_disk_size_change(disk, bdev); @@ -515,6 +527,26 @@ rescan: return 0; } +int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) +{ + int res; + + if (!bdev->bd_invalidated) + return 0; + + res = drop_partitions(disk, bdev); + if (res) + return res; + + set_capacity(disk, 0); + check_disk_size_change(disk, bdev); + bdev->bd_invalidated = 0; + /* tell userspace that the media / partition table may have changed */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + + return 0; +} + unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) { struct address_space *mapping = bdev->bd_inode->i_mapping; diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index e086fbbbe853..8db9089127c5 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -1177,7 +1177,8 @@ static bool DAC960_V1_EnableMemoryMailboxInterface(DAC960_Controller_T int TimeoutCounter; int i; - + memset(&CommandMailbox, 0, sizeof(DAC960_V1_CommandMailbox_T)); + if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32))) return DAC960_Failure(Controller, "DMA mask out of range"); Controller->BounceBufferLimit = DMA_BIT_MASK(32); @@ -4627,7 +4628,8 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) DAC960_Controller_T *Controller = Command->Controller; DAC960_CommandType_T CommandType = Command->CommandType; DAC960_V2_CommandMailbox_T *CommandMailbox = &Command->V2.CommandMailbox; - DAC960_V2_IOCTL_Opcode_T CommandOpcode = CommandMailbox->Common.IOCTL_Opcode; + DAC960_V2_IOCTL_Opcode_T IOCTLOpcode = CommandMailbox->Common.IOCTL_Opcode; + DAC960_V2_CommandOpcode_T CommandOpcode = CommandMailbox->SCSI_10.CommandOpcode; DAC960_V2_CommandStatus_T CommandStatus = Command->V2.CommandStatus; if (CommandType == DAC960_ReadCommand || @@ -4699,7 +4701,7 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) { if (Controller->ShutdownMonitoringTimer) return; - if (CommandOpcode == DAC960_V2_GetControllerInfo) + if (IOCTLOpcode == DAC960_V2_GetControllerInfo) { DAC960_V2_ControllerInfo_T *NewControllerInfo = Controller->V2.NewControllerInformation; @@ -4719,14 +4721,14 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) memcpy(ControllerInfo, NewControllerInfo, sizeof(DAC960_V2_ControllerInfo_T)); } - else if (CommandOpcode == DAC960_V2_GetEvent) + else if (IOCTLOpcode == DAC960_V2_GetEvent) { if (CommandStatus == DAC960_V2_NormalCompletion) { DAC960_V2_ReportEvent(Controller, Controller->V2.Event); } Controller->V2.NextEventSequenceNumber++; } - else if (CommandOpcode == DAC960_V2_GetPhysicalDeviceInfoValid && + else if (IOCTLOpcode == DAC960_V2_GetPhysicalDeviceInfoValid && CommandStatus == DAC960_V2_NormalCompletion) { DAC960_V2_PhysicalDeviceInfo_T *NewPhysicalDeviceInfo = @@ -4915,7 +4917,7 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) NewPhysicalDeviceInfo->LogicalUnit++; Controller->V2.PhysicalDeviceIndex++; } - else if (CommandOpcode == DAC960_V2_GetPhysicalDeviceInfoValid) + else if (IOCTLOpcode == DAC960_V2_GetPhysicalDeviceInfoValid) { unsigned int DeviceIndex; for (DeviceIndex = Controller->V2.PhysicalDeviceIndex; @@ -4938,7 +4940,7 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) } Controller->V2.NeedPhysicalDeviceInformation = false; } - else if (CommandOpcode == DAC960_V2_GetLogicalDeviceInfoValid && + else if (IOCTLOpcode == DAC960_V2_GetLogicalDeviceInfoValid && CommandStatus == DAC960_V2_NormalCompletion) { DAC960_V2_LogicalDeviceInfo_T *NewLogicalDeviceInfo = @@ -5065,7 +5067,7 @@ static void DAC960_V2_ProcessCompletedCommand(DAC960_Command_T *Command) [LogicalDeviceNumber] = true; NewLogicalDeviceInfo->LogicalDeviceNumber++; } - else if (CommandOpcode == DAC960_V2_GetLogicalDeviceInfoValid) + else if (IOCTLOpcode == DAC960_V2_GetLogicalDeviceInfoValid) { int LogicalDriveNumber; for (LogicalDriveNumber = 0; diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index e7472f567c9d..3fb6ab4c8b4e 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -1120,7 +1120,7 @@ static inline void carm_handle_resp(struct carm_host *host, break; case MISC_GET_FW_VER: { struct carm_fw_ver *ver = (struct carm_fw_ver *) - mem + sizeof(struct carm_msg_get_fw_ver); + (mem + sizeof(struct carm_msg_get_fw_ver)); if (!error) { host->fw_ver = le32_to_cpu(ver->version); host->flags |= (ver->features & FL_FW_VER_MASK); diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 6b5cf02c35c8..82e882028fcf 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -23,6 +23,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/delay.h> +#include <linux/async.h> #include <asm/io.h> /* @@ -179,17 +180,15 @@ static int verify_pmtmr_rate(void) /* Number of reads we try to get two different values */ #define ACPI_PM_READ_CHECKS 10000 -static int __init init_acpi_pm_clocksource(void) +static void __init acpi_pm_clocksource_async(void *unused, async_cookie_t cookie) { cycle_t value1, value2; unsigned int i, j = 0; - if (!pmtmr_ioport) - return -ENODEV; /* "verify" this timing source: */ for (j = 0; j < ACPI_PM_MONOTONICITY_CHECKS; j++) { - udelay(100 * j); + usleep_range(100 * j, 100 * j + 100); value1 = clocksource_acpi_pm.read(&clocksource_acpi_pm); for (i = 0; i < ACPI_PM_READ_CHECKS; i++) { value2 = clocksource_acpi_pm.read(&clocksource_acpi_pm); @@ -203,25 +202,34 @@ static int __init init_acpi_pm_clocksource(void) " 0x%#llx, 0x%#llx - aborting.\n", value1, value2); pmtmr_ioport = 0; - return -EINVAL; + return; } if (i == ACPI_PM_READ_CHECKS) { printk(KERN_INFO "PM-Timer failed consistency check " " (0x%#llx) - aborting.\n", value1); pmtmr_ioport = 0; - return -ENODEV; + return; } } if (verify_pmtmr_rate() != 0){ pmtmr_ioport = 0; - return -ENODEV; + return; } - return clocksource_register_hz(&clocksource_acpi_pm, + clocksource_register_hz(&clocksource_acpi_pm, PMTMR_TICKS_PER_SEC); } +static int __init init_acpi_pm_clocksource(void) +{ + if (!pmtmr_ioport) + return -ENODEV; + + async_schedule(acpi_pm_clocksource_async, NULL); + return 0; +} + /* We use fs_initcall because we want the PCI fixups to have run * but we still need to load before device_initcall */ diff --git a/drivers/clocksource/clksrc-dbx500-prcmu.c b/drivers/clocksource/clksrc-dbx500-prcmu.c index fb6b6d28b60e..c26c369eb9e6 100644 --- a/drivers/clocksource/clksrc-dbx500-prcmu.c +++ b/drivers/clocksource/clksrc-dbx500-prcmu.c @@ -52,7 +52,6 @@ static struct clocksource clocksource_dbx500_prcmu = { .name = "dbx500-prcmu-timer", .rating = 300, .read = clksrc_dbx500_prcmu_read, - .shift = 10, .mask = CLOCKSOURCE_MASK(32), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; @@ -90,7 +89,5 @@ void __init clksrc_dbx500_prcmu_init(void __iomem *base) setup_sched_clock(dbx500_prcmu_sched_clock_read, 32, RATE_32K); #endif - clocksource_calc_mult_shift(&clocksource_dbx500_prcmu, - RATE_32K, SCHED_CLOCK_MIN_WRAP); - clocksource_register(&clocksource_dbx500_prcmu); + clocksource_register_hz(&clocksource_dbx500_prcmu, RATE_32K); } diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c index b7dab32ce63c..540795cd0760 100644 --- a/drivers/clocksource/cs5535-clockevt.c +++ b/drivers/clocksource/cs5535-clockevt.c @@ -100,7 +100,6 @@ static struct clock_event_device cs5535_clockevent = { .set_mode = mfgpt_set_mode, .set_next_event = mfgpt_next_event, .rating = 250, - .cpumask = cpu_all_mask, .shift = 32 }; @@ -133,7 +132,7 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id) static struct irqaction mfgptirq = { .handler = mfgpt_tick, - .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER, + .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER | IRQF_SHARED, .name = DRV_NAME, }; diff --git a/drivers/clocksource/cyclone.c b/drivers/clocksource/cyclone.c index 72f811f73e9c..9e0998f22885 100644 --- a/drivers/clocksource/cyclone.c +++ b/drivers/clocksource/cyclone.c @@ -55,11 +55,11 @@ static int __init init_cyclone_clocksource(void) } /* even on 64bit systems, this is only 32bits: */ base = readl(reg); + iounmap(reg); if (!base) { printk(KERN_ERR "Summit chipset: Could not find valid CBAR value.\n"); return -ENODEV; } - iounmap(reg); /* setup PMCC: */ offset = base + CYCLONE_PMCC_OFFSET; diff --git a/drivers/clocksource/scx200_hrt.c b/drivers/clocksource/scx200_hrt.c index 27f4d9637b62..64f9e8294434 100644 --- a/drivers/clocksource/scx200_hrt.c +++ b/drivers/clocksource/scx200_hrt.c @@ -49,9 +49,6 @@ static cycle_t read_hrt(struct clocksource *cs) return (cycle_t) inl(scx200_cb_base + SCx200_TIMER_OFFSET); } -#define HRT_SHIFT_1 22 -#define HRT_SHIFT_27 26 - static struct clocksource cs_hrt = { .name = "scx200_hrt", .rating = 250, @@ -63,6 +60,7 @@ static struct clocksource cs_hrt = { static int __init init_hrt_clocksource(void) { + u32 freq; /* Make sure scx200 has initialized the configuration block */ if (!scx200_cb_present()) return -ENODEV; @@ -71,7 +69,7 @@ static int __init init_hrt_clocksource(void) if (!request_region(scx200_cb_base + SCx200_TIMER_OFFSET, SCx200_TIMER_SIZE, "NatSemi SCx200 High-Resolution Timer")) { - printk(KERN_WARNING NAME ": unable to lock timer region\n"); + pr_warn("unable to lock timer region\n"); return -ENODEV; } @@ -79,19 +77,13 @@ static int __init init_hrt_clocksource(void) outb(HR_TMEN | (mhz27 ? HR_TMCLKSEL : 0), scx200_cb_base + SCx200_TMCNFG_OFFSET); - if (mhz27) { - cs_hrt.shift = HRT_SHIFT_27; - cs_hrt.mult = clocksource_hz2mult((HRT_FREQ + ppm) * 27, - cs_hrt.shift); - } else { - cs_hrt.shift = HRT_SHIFT_1; - cs_hrt.mult = clocksource_hz2mult(HRT_FREQ + ppm, - cs_hrt.shift); - } - printk(KERN_INFO "enabling scx200 high-res timer (%s MHz +%d ppm)\n", - mhz27 ? "27":"1", ppm); + freq = (HRT_FREQ + ppm); + if (mhz27) + freq *= 27; + + pr_info("enabling scx200 high-res timer (%s MHz +%d ppm)\n", mhz27 ? "27":"1", ppm); - return clocksource_register(&cs_hrt); + return clocksource_register_hz(&cs_hrt, freq); } module_init(init_hrt_clocksource); diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c index 618bd4d87d28..99d5527b2ca6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_connector.c +++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c @@ -54,14 +54,14 @@ convert_to_display_mode(struct drm_display_mode *mode, mode->vrefresh = timing->refresh; mode->hdisplay = timing->xres; - mode->hsync_start = mode->hdisplay + timing->left_margin; + mode->hsync_start = mode->hdisplay + timing->right_margin; mode->hsync_end = mode->hsync_start + timing->hsync_len; - mode->htotal = mode->hsync_end + timing->right_margin; + mode->htotal = mode->hsync_end + timing->left_margin; mode->vdisplay = timing->yres; - mode->vsync_start = mode->vdisplay + timing->upper_margin; + mode->vsync_start = mode->vdisplay + timing->lower_margin; mode->vsync_end = mode->vsync_start + timing->vsync_len; - mode->vtotal = mode->vsync_end + timing->lower_margin; + mode->vtotal = mode->vsync_end + timing->upper_margin; mode->width_mm = panel->width_mm; mode->height_mm = panel->height_mm; @@ -85,14 +85,14 @@ convert_to_video_timing(struct fb_videomode *timing, timing->refresh = drm_mode_vrefresh(mode); timing->xres = mode->hdisplay; - timing->left_margin = mode->hsync_start - mode->hdisplay; + timing->right_margin = mode->hsync_start - mode->hdisplay; timing->hsync_len = mode->hsync_end - mode->hsync_start; - timing->right_margin = mode->htotal - mode->hsync_end; + timing->left_margin = mode->htotal - mode->hsync_end; timing->yres = mode->vdisplay; - timing->upper_margin = mode->vsync_start - mode->vdisplay; + timing->lower_margin = mode->vsync_start - mode->vdisplay; timing->vsync_len = mode->vsync_end - mode->vsync_start; - timing->lower_margin = mode->vtotal - mode->vsync_end; + timing->upper_margin = mode->vtotal - mode->vsync_end; if (mode->flags & DRM_MODE_FLAG_INTERLACE) timing->vmode = FB_VMODE_INTERLACED; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 58820ebd3558..09cc13f791b3 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -246,7 +246,7 @@ static struct platform_driver exynos_drm_platform_driver = { .remove = __devexit_p(exynos_drm_platform_remove), .driver = { .owner = THIS_MODULE, - .name = DRIVER_NAME, + .name = "exynos-drm", }, }; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 3508700e529b..54f8f074822f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -46,39 +46,13 @@ struct exynos_drm_fbdev { struct exynos_drm_gem_obj *exynos_gem_obj; }; -static int exynos_drm_fbdev_set_par(struct fb_info *info) -{ - struct fb_var_screeninfo *var = &info->var; - - switch (var->bits_per_pixel) { - case 32: - case 24: - case 18: - case 16: - case 12: - info->fix.visual = FB_VISUAL_TRUECOLOR; - break; - case 1: - info->fix.visual = FB_VISUAL_MONO01; - break; - default: - info->fix.visual = FB_VISUAL_PSEUDOCOLOR; - break; - } - - info->fix.line_length = (var->xres_virtual * var->bits_per_pixel) / 8; - - return drm_fb_helper_set_par(info); -} - - static struct fb_ops exynos_drm_fb_ops = { .owner = THIS_MODULE, .fb_fillrect = cfb_fillrect, .fb_copyarea = cfb_copyarea, .fb_imageblit = cfb_imageblit, .fb_check_var = drm_fb_helper_check_var, - .fb_set_par = exynos_drm_fbdev_set_par, + .fb_set_par = drm_fb_helper_set_par, .fb_blank = drm_fb_helper_blank, .fb_pan_display = drm_fb_helper_pan_display, .fb_setcmap = drm_fb_helper_setcmap, diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 360adf2bba04..56458eea0501 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -817,8 +817,6 @@ static int __devinit fimd_probe(struct platform_device *pdev) goto err_clk_get; } - clk_enable(ctx->bus_clk); - ctx->lcd_clk = clk_get(dev, "sclk_fimd"); if (IS_ERR(ctx->lcd_clk)) { dev_err(dev, "failed to get lcd clock\n"); @@ -826,8 +824,6 @@ static int __devinit fimd_probe(struct platform_device *pdev) goto err_bus_clk; } - clk_enable(ctx->lcd_clk); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { dev_err(dev, "failed to find registers\n"); @@ -864,17 +860,11 @@ static int __devinit fimd_probe(struct platform_device *pdev) goto err_req_irq; } - ctx->clkdiv = fimd_calc_clkdiv(ctx, &panel->timing); ctx->vidcon0 = pdata->vidcon0; ctx->vidcon1 = pdata->vidcon1; ctx->default_win = pdata->default_win; ctx->panel = panel; - panel->timing.pixclock = clk_get_rate(ctx->lcd_clk) / ctx->clkdiv; - - DRM_DEBUG_KMS("pixel clock = %d, clkdiv = %d\n", - panel->timing.pixclock, ctx->clkdiv); - subdrv = &ctx->subdrv; subdrv->probe = fimd_subdrv_probe; @@ -889,10 +879,15 @@ static int __devinit fimd_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ctx); - pm_runtime_set_active(dev); pm_runtime_enable(dev); pm_runtime_get_sync(dev); + ctx->clkdiv = fimd_calc_clkdiv(ctx, &panel->timing); + panel->timing.pixclock = clk_get_rate(ctx->lcd_clk) / ctx->clkdiv; + + DRM_DEBUG_KMS("pixel clock = %d, clkdiv = %d\n", + panel->timing.pixclock, ctx->clkdiv); + for (win = 0; win < WINDOWS_NR; win++) fimd_clear_win(ctx, win); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 03c53fcf8653..558ac716a328 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2689,7 +2689,7 @@ #define DVS_FORMAT_RGBX888 (2<<25) #define DVS_FORMAT_RGBX161616 (3<<25) #define DVS_SOURCE_KEY (1<<22) -#define DVS_RGB_ORDER_RGBX (1<<20) +#define DVS_RGB_ORDER_XBGR (1<<20) #define DVS_YUV_BYTE_ORDER_MASK (3<<16) #define DVS_YUV_ORDER_YUYV (0<<16) #define DVS_YUV_ORDER_UYVY (1<<16) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index f851db7be2cc..397087cf689e 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -7828,6 +7828,7 @@ int intel_framebuffer_init(struct drm_device *dev, case DRM_FORMAT_RGB332: case DRM_FORMAT_RGB565: case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ARGB8888: case DRM_FORMAT_XRGB2101010: case DRM_FORMAT_ARGB2101010: diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 2288abf88cce..a0835040c86b 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -225,16 +225,16 @@ snb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, /* Mask out pixel format bits in case we change it */ dvscntr &= ~DVS_PIXFORMAT_MASK; - dvscntr &= ~DVS_RGB_ORDER_RGBX; + dvscntr &= ~DVS_RGB_ORDER_XBGR; dvscntr &= ~DVS_YUV_BYTE_ORDER_MASK; switch (fb->pixel_format) { case DRM_FORMAT_XBGR8888: - dvscntr |= DVS_FORMAT_RGBX888; + dvscntr |= DVS_FORMAT_RGBX888 | DVS_RGB_ORDER_XBGR; pixel_size = 4; break; case DRM_FORMAT_XRGB8888: - dvscntr |= DVS_FORMAT_RGBX888 | DVS_RGB_ORDER_RGBX; + dvscntr |= DVS_FORMAT_RGBX888; pixel_size = 4; break; case DRM_FORMAT_YUYV: diff --git a/drivers/hwmon/pmbus/zl6100.c b/drivers/hwmon/pmbus/zl6100.c index 880b90cf4d32..e3e8420b7b81 100644 --- a/drivers/hwmon/pmbus/zl6100.c +++ b/drivers/hwmon/pmbus/zl6100.c @@ -200,17 +200,11 @@ static int zl6100_probe(struct i2c_client *client, data->id = mid->driver_data; /* - * ZL2005, ZL2008, ZL2105, and ZL6100 are known to require a wait time - * between I2C accesses. ZL2004 and ZL6105 are known to be safe. - * Other chips have not yet been tested. - * - * Only clear the wait time for chips known to be safe. The wait time - * can be cleared later for additional chips if tests show that it - * is not needed (in other words, better be safe than sorry). + * According to information from the chip vendor, all currently + * supported chips are known to require a wait time between I2C + * accesses. */ data->delay = delay; - if (data->id == zl2004 || data->id == zl6105) - data->delay = 0; /* * Since there was a direct I2C device access above, wait before diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c index 5276d1933dbc..a658d62c5e10 100644 --- a/drivers/hwmon/w83627ehf.c +++ b/drivers/hwmon/w83627ehf.c @@ -39,7 +39,7 @@ 0x8860 0xa1 w83627dhg 9 5 4 3 0xa020 0xc1 0x5ca3 w83627dhg-p 9 5 4 3 0xb070 0xc1 0x5ca3 - w83627uhg 8 2 2 2 0xa230 0xc1 0x5ca3 + w83627uhg 8 2 2 3 0xa230 0xc1 0x5ca3 w83667hg 9 5 3 3 0xa510 0xc1 0x5ca3 w83667hg-b 9 5 3 4 0xb350 0xc1 0x5ca3 nct6775f 9 4 3 9 0xb470 0xc1 0x5ca3 @@ -1607,7 +1607,7 @@ store_##reg(struct device *dev, struct device_attribute *attr, \ val = step_time_to_reg(val, data->pwm_mode[nr]); \ mutex_lock(&data->update_lock); \ data->reg[nr] = val; \ - w83627ehf_write_value(data, W83627EHF_REG_##REG[nr], val); \ + w83627ehf_write_value(data, data->REG_##REG[nr], val); \ mutex_unlock(&data->update_lock); \ return count; \ } \ @@ -2004,7 +2004,8 @@ static int __devinit w83627ehf_probe(struct platform_device *pdev) goto exit; } - data = kzalloc(sizeof(struct w83627ehf_data), GFP_KERNEL); + data = devm_kzalloc(&pdev->dev, sizeof(struct w83627ehf_data), + GFP_KERNEL); if (!data) { err = -ENOMEM; goto exit_release; @@ -2157,16 +2158,16 @@ static int __devinit w83627ehf_probe(struct platform_device *pdev) w83627ehf_set_temp_reg_ehf(data, 3); /* - * Temperature sources for temp1 and temp2 are selected with + * Temperature sources for temp2 and temp3 are selected with * bank 0, registers 0x49 and 0x4a. */ data->temp_src[0] = 0; /* SYSTIN */ reg = w83627ehf_read_value(data, 0x49) & 0x07; /* Adjust to have the same mapping as other source registers */ if (reg == 0) - data->temp_src[1]++; + data->temp_src[1] = 1; else if (reg >= 2 && reg <= 5) - data->temp_src[1] += 2; + data->temp_src[1] = reg + 2; else /* should never happen */ data->have_temp &= ~(1 << 1); reg = w83627ehf_read_value(data, 0x4a); @@ -2493,9 +2494,8 @@ static int __devinit w83627ehf_probe(struct platform_device *pdev) exit_remove: w83627ehf_device_remove_files(dev); - kfree(data); - platform_set_drvdata(pdev, NULL); exit_release: + platform_set_drvdata(pdev, NULL); release_region(res->start, IOREGION_LENGTH); exit: return err; @@ -2509,7 +2509,6 @@ static int __devexit w83627ehf_remove(struct platform_device *pdev) w83627ehf_device_remove_files(&pdev->dev); release_region(data->addr, IOREGION_LENGTH); platform_set_drvdata(pdev, NULL); - kfree(data); return 0; } diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index 525c7345fa0b..24f94f4ae395 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -103,8 +103,14 @@ static int sclhi(struct i2c_algo_bit_data *adap) * chips may hold it low ("clock stretching") while they * are processing data internally. */ - if (time_after(jiffies, start + adap->timeout)) + if (time_after(jiffies, start + adap->timeout)) { + /* Test one last time, as we may have been preempted + * between last check and timeout test. + */ + if (getscl(adap)) + break; return -ETIMEDOUT; + } cond_resched(); } #ifdef DEBUG diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index 1e5606185b4f..e9c18939eda7 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -1386,8 +1386,10 @@ int i2c_master_send(const struct i2c_client *client, const char *buf, int count) ret = i2c_transfer(adap, &msg, 1); - /* If everything went ok (i.e. 1 msg transmitted), return #bytes - transmitted, else error code. */ + /* + * If everything went ok (i.e. 1 msg transmitted), return #bytes + * transmitted, else error code. + */ return (ret == 1) ? count : ret; } EXPORT_SYMBOL(i2c_master_send); @@ -1414,8 +1416,10 @@ int i2c_master_recv(const struct i2c_client *client, char *buf, int count) ret = i2c_transfer(adap, &msg, 1); - /* If everything went ok (i.e. 1 msg transmitted), return #bytes - transmitted, else error code. */ + /* + * If everything went ok (i.e. 1 msg received), return #bytes received, + * else error code. + */ return (ret == 1) ? count : ret; } EXPORT_SYMBOL(i2c_master_recv); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index c9c6053198d4..a08a53448b72 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -48,8 +48,6 @@ #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE -#define IS_BRIDGE_HOST_DEVICE(pdev) \ - ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST) #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY) #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e) @@ -356,10 +354,18 @@ static int hw_pass_through = 1; /* si_domain contains mulitple devices */ #define DOMAIN_FLAG_STATIC_IDENTITY (1 << 2) +/* define the limit of IOMMUs supported in each domain */ +#ifdef CONFIG_X86 +# define IOMMU_UNITS_SUPPORTED MAX_IO_APICS +#else +# define IOMMU_UNITS_SUPPORTED 64 +#endif + struct dmar_domain { int id; /* domain id */ int nid; /* node id */ - unsigned long iommu_bmp; /* bitmap of iommus this domain uses*/ + DECLARE_BITMAP(iommu_bmp, IOMMU_UNITS_SUPPORTED); + /* bitmap of iommus this domain uses*/ struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ @@ -571,7 +577,7 @@ static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) BUG_ON(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE); BUG_ON(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY); - iommu_id = find_first_bit(&domain->iommu_bmp, g_num_of_iommus); + iommu_id = find_first_bit(domain->iommu_bmp, g_num_of_iommus); if (iommu_id < 0 || iommu_id >= g_num_of_iommus) return NULL; @@ -584,7 +590,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) domain->iommu_coherency = 1; - for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) { + for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) { if (!ecap_coherent(g_iommus[i]->ecap)) { domain->iommu_coherency = 0; break; @@ -598,7 +604,7 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain) domain->iommu_snooping = 1; - for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) { + for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus) { if (!ecap_sc_support(g_iommus[i]->ecap)) { domain->iommu_snooping = 0; break; @@ -1334,7 +1340,7 @@ static struct dmar_domain *alloc_domain(void) return NULL; domain->nid = -1; - memset(&domain->iommu_bmp, 0, sizeof(unsigned long)); + memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp)); domain->flags = 0; return domain; @@ -1360,7 +1366,7 @@ static int iommu_attach_domain(struct dmar_domain *domain, domain->id = num; set_bit(num, iommu->domain_ids); - set_bit(iommu->seq_id, &domain->iommu_bmp); + set_bit(iommu->seq_id, domain->iommu_bmp); iommu->domains[num] = domain; spin_unlock_irqrestore(&iommu->lock, flags); @@ -1385,7 +1391,7 @@ static void iommu_detach_domain(struct dmar_domain *domain, if (found) { clear_bit(num, iommu->domain_ids); - clear_bit(iommu->seq_id, &domain->iommu_bmp); + clear_bit(iommu->seq_id, domain->iommu_bmp); iommu->domains[num] = NULL; } spin_unlock_irqrestore(&iommu->lock, flags); @@ -1527,7 +1533,7 @@ static void domain_exit(struct dmar_domain *domain) dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw)); for_each_active_iommu(iommu, drhd) - if (test_bit(iommu->seq_id, &domain->iommu_bmp)) + if (test_bit(iommu->seq_id, domain->iommu_bmp)) iommu_detach_domain(domain, iommu); free_domain_mem(domain); @@ -1653,7 +1659,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, spin_unlock_irqrestore(&iommu->lock, flags); spin_lock_irqsave(&domain->iommu_lock, flags); - if (!test_and_set_bit(iommu->seq_id, &domain->iommu_bmp)) { + if (!test_and_set_bit(iommu->seq_id, domain->iommu_bmp)) { domain->iommu_count++; if (domain->iommu_count == 1) domain->nid = iommu->node; @@ -2369,18 +2375,18 @@ static int __init iommu_prepare_static_identity_mapping(int hw) return -EFAULT; for_each_pci_dev(pdev) { - /* Skip Host/PCI Bridge devices */ - if (IS_BRIDGE_HOST_DEVICE(pdev)) - continue; if (iommu_should_identity_map(pdev, 1)) { - printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n", - hw ? "hardware" : "software", pci_name(pdev)); - ret = domain_add_dev_info(si_domain, pdev, - hw ? CONTEXT_TT_PASS_THROUGH : - CONTEXT_TT_MULTI_LEVEL); - if (ret) + hw ? CONTEXT_TT_PASS_THROUGH : + CONTEXT_TT_MULTI_LEVEL); + if (ret) { + /* device not associated with an iommu */ + if (ret == -ENODEV) + continue; return ret; + } + pr_info("IOMMU: %s identity mapping for device %s\n", + hw ? "hardware" : "software", pci_name(pdev)); } } @@ -2402,12 +2408,17 @@ static int __init init_dmars(void) * endfor */ for_each_drhd_unit(drhd) { - g_num_of_iommus++; /* * lock not needed as this is only incremented in the single * threaded kernel __init code path all other access are read * only */ + if (g_num_of_iommus < IOMMU_UNITS_SUPPORTED) { + g_num_of_iommus++; + continue; + } + printk_once(KERN_ERR "intel-iommu: exceeded %d IOMMUs\n", + IOMMU_UNITS_SUPPORTED); } g_iommus = kcalloc(g_num_of_iommus, sizeof(struct intel_iommu *), @@ -3748,7 +3759,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, if (found == 0) { unsigned long tmp_flags; spin_lock_irqsave(&domain->iommu_lock, tmp_flags); - clear_bit(iommu->seq_id, &domain->iommu_bmp); + clear_bit(iommu->seq_id, domain->iommu_bmp); domain->iommu_count--; domain_update_iommu_cap(domain); spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags); @@ -3790,7 +3801,7 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain) */ spin_lock_irqsave(&domain->iommu_lock, flags2); if (test_and_clear_bit(iommu->seq_id, - &domain->iommu_bmp)) { + domain->iommu_bmp)) { domain->iommu_count--; domain_update_iommu_cap(domain); } @@ -3815,7 +3826,7 @@ static struct dmar_domain *iommu_alloc_vm_domain(void) domain->id = vm_domid++; domain->nid = -1; - memset(&domain->iommu_bmp, 0, sizeof(unsigned long)); + memset(domain->iommu_bmp, 0, sizeof(domain->iommu_bmp)); domain->flags = DOMAIN_FLAG_VIRTUAL_MACHINE; return domain; diff --git a/drivers/media/dvb/siano/smsdvb.c b/drivers/media/dvb/siano/smsdvb.c index 654685c9303e..aa77e54a8fae 100644 --- a/drivers/media/dvb/siano/smsdvb.c +++ b/drivers/media/dvb/siano/smsdvb.c @@ -49,9 +49,6 @@ struct smsdvb_client_t { struct completion tune_done; - /* todo: save freq/band instead whole struct */ - struct dtv_frontend_properties fe_params; - struct SMSHOSTLIB_STATISTICS_DVB_S sms_stat_dvb; int event_fe_state; int event_unc_state; @@ -744,12 +741,124 @@ static int smsdvb_get_frontend(struct dvb_frontend *fe) struct dtv_frontend_properties *fep = &fe->dtv_property_cache; struct smsdvb_client_t *client = container_of(fe, struct smsdvb_client_t, frontend); + struct smscore_device_t *coredev = client->coredev; + struct TRANSMISSION_STATISTICS_S *td = + &client->sms_stat_dvb.TransmissionData; - sms_debug(""); + switch (smscore_get_device_mode(coredev)) { + case DEVICE_MODE_DVBT: + case DEVICE_MODE_DVBT_BDA: + fep->frequency = td->Frequency; + + switch (td->Bandwidth) { + case 6: + fep->bandwidth_hz = 6000000; + break; + case 7: + fep->bandwidth_hz = 7000000; + break; + case 8: + fep->bandwidth_hz = 8000000; + break; + } + + switch (td->TransmissionMode) { + case 2: + fep->transmission_mode = TRANSMISSION_MODE_2K; + break; + case 8: + fep->transmission_mode = TRANSMISSION_MODE_8K; + } + + switch (td->GuardInterval) { + case 0: + fep->guard_interval = GUARD_INTERVAL_1_32; + break; + case 1: + fep->guard_interval = GUARD_INTERVAL_1_16; + break; + case 2: + fep->guard_interval = GUARD_INTERVAL_1_8; + break; + case 3: + fep->guard_interval = GUARD_INTERVAL_1_4; + break; + } + + switch (td->CodeRate) { + case 0: + fep->code_rate_HP = FEC_1_2; + break; + case 1: + fep->code_rate_HP = FEC_2_3; + break; + case 2: + fep->code_rate_HP = FEC_3_4; + break; + case 3: + fep->code_rate_HP = FEC_5_6; + break; + case 4: + fep->code_rate_HP = FEC_7_8; + break; + } + + switch (td->LPCodeRate) { + case 0: + fep->code_rate_LP = FEC_1_2; + break; + case 1: + fep->code_rate_LP = FEC_2_3; + break; + case 2: + fep->code_rate_LP = FEC_3_4; + break; + case 3: + fep->code_rate_LP = FEC_5_6; + break; + case 4: + fep->code_rate_LP = FEC_7_8; + break; + } + + switch (td->Constellation) { + case 0: + fep->modulation = QPSK; + break; + case 1: + fep->modulation = QAM_16; + break; + case 2: + fep->modulation = QAM_64; + break; + } + + switch (td->Hierarchy) { + case 0: + fep->hierarchy = HIERARCHY_NONE; + break; + case 1: + fep->hierarchy = HIERARCHY_1; + break; + case 2: + fep->hierarchy = HIERARCHY_2; + break; + case 3: + fep->hierarchy = HIERARCHY_4; + break; + } - /* todo: */ - memcpy(fep, &client->fe_params, - sizeof(struct dtv_frontend_properties)); + fep->inversion = INVERSION_AUTO; + break; + case DEVICE_MODE_ISDBT: + case DEVICE_MODE_ISDBT_BDA: + fep->frequency = td->Frequency; + fep->bandwidth_hz = 6000000; + /* todo: retrive the other parameters */ + break; + default: + return -EINVAL; + } return 0; } @@ -872,11 +981,11 @@ static int smsdvb_hotplug(struct smscore_device_t *coredev, switch (smscore_get_device_mode(coredev)) { case DEVICE_MODE_DVBT: case DEVICE_MODE_DVBT_BDA: - smsdvb_fe_ops.delsys[0] = SYS_DVBT; + client->frontend.ops.delsys[0] = SYS_DVBT; break; case DEVICE_MODE_ISDBT: case DEVICE_MODE_ISDBT_BDA: - smsdvb_fe_ops.delsys[0] = SYS_ISDBT; + client->frontend.ops.delsys[0] = SYS_ISDBT; break; } diff --git a/drivers/media/video/davinci/isif.c b/drivers/media/video/davinci/isif.c index 1e63852374be..5278fe7d6d0c 100644 --- a/drivers/media/video/davinci/isif.c +++ b/drivers/media/video/davinci/isif.c @@ -34,6 +34,7 @@ #include <linux/videodev2.h> #include <linux/clk.h> #include <linux/err.h> +#include <linux/module.h> #include <mach/mux.h> diff --git a/drivers/media/video/uvc/uvc_video.c b/drivers/media/video/uvc/uvc_video.c index c7e69b8f81c9..4a44f9a1bae0 100644 --- a/drivers/media/video/uvc/uvc_video.c +++ b/drivers/media/video/uvc/uvc_video.c @@ -611,9 +611,11 @@ void uvc_video_clock_update(struct uvc_streaming *stream, delta_stc = buf->pts - (1UL << 31); x1 = first->dev_stc - delta_stc; x2 = last->dev_stc - delta_stc; + if (x1 == x2) + goto done; + y1 = (first->dev_sof + 2048) << 16; y2 = (last->dev_sof + 2048) << 16; - if (y2 < y1) y2 += 2048 << 16; @@ -631,14 +633,16 @@ void uvc_video_clock_update(struct uvc_streaming *stream, x1, x2, y1, y2, clock->sof_offset); /* Second step, SOF to host clock conversion. */ - ts = timespec_sub(last->host_ts, first->host_ts); x1 = (uvc_video_clock_host_sof(first) + 2048) << 16; x2 = (uvc_video_clock_host_sof(last) + 2048) << 16; - y1 = NSEC_PER_SEC; - y2 = (ts.tv_sec + 1) * NSEC_PER_SEC + ts.tv_nsec; - if (x2 < x1) x2 += 2048 << 16; + if (x1 == x2) + goto done; + + ts = timespec_sub(last->host_ts, first->host_ts); + y1 = NSEC_PER_SEC; + y2 = (ts.tv_sec + 1) * NSEC_PER_SEC + ts.tv_nsec; /* Interpolated and host SOF timestamps can wrap around at slightly * different times. Handle this by adding or removing 2048 to or from diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 254521319150..b69f8762b339 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -10824,38 +10824,36 @@ do { \ int bnx2x_init_firmware(struct bnx2x *bp) { + const char *fw_file_name; struct bnx2x_fw_file_hdr *fw_hdr; int rc; + if (bp->firmware) + return 0; - if (!bp->firmware) { - const char *fw_file_name; - - if (CHIP_IS_E1(bp)) - fw_file_name = FW_FILE_NAME_E1; - else if (CHIP_IS_E1H(bp)) - fw_file_name = FW_FILE_NAME_E1H; - else if (!CHIP_IS_E1x(bp)) - fw_file_name = FW_FILE_NAME_E2; - else { - BNX2X_ERR("Unsupported chip revision\n"); - return -EINVAL; - } - BNX2X_DEV_INFO("Loading %s\n", fw_file_name); + if (CHIP_IS_E1(bp)) + fw_file_name = FW_FILE_NAME_E1; + else if (CHIP_IS_E1H(bp)) + fw_file_name = FW_FILE_NAME_E1H; + else if (!CHIP_IS_E1x(bp)) + fw_file_name = FW_FILE_NAME_E2; + else { + BNX2X_ERR("Unsupported chip revision\n"); + return -EINVAL; + } + BNX2X_DEV_INFO("Loading %s\n", fw_file_name); - rc = request_firmware(&bp->firmware, fw_file_name, - &bp->pdev->dev); - if (rc) { - BNX2X_ERR("Can't load firmware file %s\n", - fw_file_name); - goto request_firmware_exit; - } + rc = request_firmware(&bp->firmware, fw_file_name, &bp->pdev->dev); + if (rc) { + BNX2X_ERR("Can't load firmware file %s\n", + fw_file_name); + goto request_firmware_exit; + } - rc = bnx2x_check_firmware(bp); - if (rc) { - BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name); - goto request_firmware_exit; - } + rc = bnx2x_check_firmware(bp); + if (rc) { + BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name); + goto request_firmware_exit; } fw_hdr = (struct bnx2x_fw_file_hdr *)bp->firmware->data; @@ -10901,6 +10899,7 @@ init_ops_alloc_err: kfree(bp->init_data); request_firmware_exit: release_firmware(bp->firmware); + bp->firmware = NULL; return rc; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index bf01841bda5b..610860f28968 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -166,7 +166,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) dev_kfree_skb(skb); net->stats.tx_dropped++; - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } packet->extension = (void *)(unsigned long)packet + @@ -226,7 +226,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) dev_kfree_skb_any(skb); } - return ret ? NETDEV_TX_BUSY : NETDEV_TX_OK; + return NETDEV_TX_OK; } /* diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 81b96e303757..59681f01a54e 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -328,13 +328,13 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) unsigned long lockflags; size_t size = dev->rx_urb_size; - if ((skb = alloc_skb (size + NET_IP_ALIGN, flags)) == NULL) { + skb = __netdev_alloc_skb_ip_align(dev->net, size, flags); + if (!skb) { netif_dbg(dev, rx_err, dev->net, "no rx skb\n"); usbnet_defer_kevent (dev, EVENT_RX_MEMORY); usb_free_urb (urb); return -ENOMEM; } - skb_reserve (skb, NET_IP_ALIGN); entry = (struct skb_data *) skb->cb; entry->urb = urb; diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c index 64a110604ad3..63e4b709efa9 100644 --- a/drivers/net/wimax/i2400m/netdev.c +++ b/drivers/net/wimax/i2400m/netdev.c @@ -367,38 +367,28 @@ netdev_tx_t i2400m_hard_start_xmit(struct sk_buff *skb, { struct i2400m *i2400m = net_dev_to_i2400m(net_dev); struct device *dev = i2400m_dev(i2400m); - int result; + int result = -1; d_fnstart(3, dev, "(skb %p net_dev %p)\n", skb, net_dev); - if (skb_header_cloned(skb)) { - /* - * Make tcpdump/wireshark happy -- if they are - * running, the skb is cloned and we will overwrite - * the mac fields in i2400m_tx_prep_header. Expand - * seems to fix this... - */ - result = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (result) { - result = NETDEV_TX_BUSY; - goto error_expand; - } - } + + if (skb_header_cloned(skb) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + goto drop; if (i2400m->state == I2400M_SS_IDLE) result = i2400m_net_wake_tx(i2400m, net_dev, skb); else result = i2400m_net_tx(i2400m, net_dev, skb); - if (result < 0) + if (result < 0) { +drop: net_dev->stats.tx_dropped++; - else { + } else { net_dev->stats.tx_packets++; net_dev->stats.tx_bytes += skb->len; } - result = NETDEV_TX_OK; -error_expand: - kfree_skb(skb); + dev_kfree_skb(skb); d_fnend(3, dev, "(skb %p net_dev %p) = %d\n", skb, net_dev, result); - return result; + return NETDEV_TX_OK; } diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h index 822e54c394d5..1c226b31af13 100644 --- a/drivers/rapidio/devices/tsi721.h +++ b/drivers/rapidio/devices/tsi721.h @@ -118,34 +118,34 @@ #define TSI721_IDB_ENTRY_SIZE 64 -#define TSI721_IDQ_CTL(x) (0x20000 + (x) * 1000) +#define TSI721_IDQ_CTL(x) (0x20000 + (x) * 0x1000) #define TSI721_IDQ_SUSPEND 0x00000002 #define TSI721_IDQ_INIT 0x00000001 -#define TSI721_IDQ_STS(x) (0x20004 + (x) * 1000) +#define TSI721_IDQ_STS(x) (0x20004 + (x) * 0x1000) #define TSI721_IDQ_RUN 0x00200000 -#define TSI721_IDQ_MASK(x) (0x20008 + (x) * 1000) +#define TSI721_IDQ_MASK(x) (0x20008 + (x) * 0x1000) #define TSI721_IDQ_MASK_MASK 0xffff0000 #define TSI721_IDQ_MASK_PATT 0x0000ffff -#define TSI721_IDQ_RP(x) (0x2000c + (x) * 1000) +#define TSI721_IDQ_RP(x) (0x2000c + (x) * 0x1000) #define TSI721_IDQ_RP_PTR 0x0007ffff -#define TSI721_IDQ_WP(x) (0x20010 + (x) * 1000) +#define TSI721_IDQ_WP(x) (0x20010 + (x) * 0x1000) #define TSI721_IDQ_WP_PTR 0x0007ffff -#define TSI721_IDQ_BASEL(x) (0x20014 + (x) * 1000) +#define TSI721_IDQ_BASEL(x) (0x20014 + (x) * 0x1000) #define TSI721_IDQ_BASEL_ADDR 0xffffffc0 -#define TSI721_IDQ_BASEU(x) (0x20018 + (x) * 1000) -#define TSI721_IDQ_SIZE(x) (0x2001c + (x) * 1000) +#define TSI721_IDQ_BASEU(x) (0x20018 + (x) * 0x1000) +#define TSI721_IDQ_SIZE(x) (0x2001c + (x) * 0x1000) #define TSI721_IDQ_SIZE_VAL(size) (__fls(size) - 4) #define TSI721_IDQ_SIZE_MIN 512 #define TSI721_IDQ_SIZE_MAX (512 * 1024) -#define TSI721_SR_CHINT(x) (0x20040 + (x) * 1000) -#define TSI721_SR_CHINTE(x) (0x20044 + (x) * 1000) -#define TSI721_SR_CHINTSET(x) (0x20048 + (x) * 1000) +#define TSI721_SR_CHINT(x) (0x20040 + (x) * 0x1000) +#define TSI721_SR_CHINTE(x) (0x20044 + (x) * 0x1000) +#define TSI721_SR_CHINTSET(x) (0x20048 + (x) * 0x1000) #define TSI721_SR_CHINT_ODBOK 0x00000020 #define TSI721_SR_CHINT_IDBQRCV 0x00000010 #define TSI721_SR_CHINT_SUSP 0x00000008 @@ -156,7 +156,7 @@ #define TSI721_IBWIN_NUM 8 -#define TSI721_IBWINLB(x) (0x29000 + (x) * 20) +#define TSI721_IBWINLB(x) (0x29000 + (x) * 0x20) #define TSI721_IBWINLB_BA 0xfffff000 #define TSI721_IBWINLB_WEN 0x00000001 @@ -187,13 +187,13 @@ */ #define TSI721_OBWIN_NUM TSI721_PC2SR_WINS -#define TSI721_OBWINLB(x) (0x40000 + (x) * 20) +#define TSI721_OBWINLB(x) (0x40000 + (x) * 0x20) #define TSI721_OBWINLB_BA 0xffff8000 #define TSI721_OBWINLB_WEN 0x00000001 -#define TSI721_OBWINUB(x) (0x40004 + (x) * 20) +#define TSI721_OBWINUB(x) (0x40004 + (x) * 0x20) -#define TSI721_OBWINSZ(x) (0x40008 + (x) * 20) +#define TSI721_OBWINSZ(x) (0x40008 + (x) * 0x20) #define TSI721_OBWINSZ_SIZE 0x00001f00 #define TSI721_OBWIN_SIZE(size) (__fls(size) - 15) diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c index ea4d8f575ac6..09915e89705d 100644 --- a/drivers/regulator/da9052-regulator.c +++ b/drivers/regulator/da9052-regulator.c @@ -226,7 +226,7 @@ static int da9052_regulator_set_voltage_int(struct regulator_dev *rdev, if (min_uV < info->min_uV) min_uV = info->min_uV; - *selector = (min_uV - info->min_uV) / info->step_uV; + *selector = DIV_ROUND_UP(min_uV - info->min_uV, info->step_uV); ret = da9052_list_voltage(rdev, *selector); if (ret < 0) @@ -318,10 +318,10 @@ static int da9052_set_buckperi_voltage(struct regulator_dev *rdev, int min_uV, if ((regulator->da9052->chip_id == DA9052) && (min_uV >= DA9052_CONST_3uV)) *selector = DA9052_BUCK_PERI_REG_MAP_UPTO_3uV + - ((min_uV - DA9052_CONST_3uV) / - (DA9052_BUCK_PERI_3uV_STEP)); + DIV_ROUND_UP(min_uV - DA9052_CONST_3uV, + DA9052_BUCK_PERI_3uV_STEP); else - *selector = (min_uV - info->min_uV) / info->step_uV; + *selector = DIV_ROUND_UP(min_uV - info->min_uV, info->step_uV); ret = da9052_list_buckperi_voltage(rdev, *selector); if (ret < 0) @@ -400,6 +400,7 @@ static struct regulator_ops da9052_ldo_ops = { .ops = &da9052_ldo5_6_ops,\ .type = REGULATOR_VOLTAGE,\ .id = _id,\ + .n_voltages = (max - min) / step + 1, \ .owner = THIS_MODULE,\ },\ .min_uV = (min) * 1000,\ @@ -417,6 +418,7 @@ static struct regulator_ops da9052_ldo_ops = { .ops = &da9052_ldo_ops,\ .type = REGULATOR_VOLTAGE,\ .id = _id,\ + .n_voltages = (max - min) / step + 1, \ .owner = THIS_MODULE,\ },\ .min_uV = (min) * 1000,\ @@ -434,6 +436,7 @@ static struct regulator_ops da9052_ldo_ops = { .ops = &da9052_dcdc_ops,\ .type = REGULATOR_VOLTAGE,\ .id = _id,\ + .n_voltages = (max - min) / step + 1, \ .owner = THIS_MODULE,\ },\ .min_uV = (min) * 1000,\ @@ -451,6 +454,7 @@ static struct regulator_ops da9052_ldo_ops = { .ops = &da9052_buckperi_ops,\ .type = REGULATOR_VOLTAGE,\ .id = _id,\ + .n_voltages = (max - min) / step + 1, \ .owner = THIS_MODULE,\ },\ .min_uV = (min) * 1000,\ diff --git a/drivers/regulator/tps6524x-regulator.c b/drivers/regulator/tps6524x-regulator.c index 70b7b1f4f000..2e94686b6fe6 100644 --- a/drivers/regulator/tps6524x-regulator.c +++ b/drivers/regulator/tps6524x-regulator.c @@ -481,7 +481,7 @@ static int set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, if (i >= info->n_voltages) i = info->n_voltages - 1; - *selector = info->voltages[i]; + *selector = i; return write_field(hw, &info->voltage, i); } diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 8a1c031391d6..dc87eda65814 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -73,6 +73,8 @@ int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm) err = -EINVAL; mutex_unlock(&rtc->ops_lock); + /* A timer might have just expired */ + schedule_work(&rtc->irqwork); return err; } EXPORT_SYMBOL_GPL(rtc_set_time); @@ -112,6 +114,8 @@ int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs) err = -EINVAL; mutex_unlock(&rtc->ops_lock); + /* A timer might have just expired */ + schedule_work(&rtc->irqwork); return err; } @@ -380,18 +384,27 @@ EXPORT_SYMBOL_GPL(rtc_set_alarm); int rtc_initialize_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; + struct rtc_time now; err = rtc_valid_tm(&alarm->time); if (err != 0) return err; + err = rtc_read_time(rtc, &now); + if (err) + return err; + err = mutex_lock_interruptible(&rtc->ops_lock); if (err) return err; rtc->aie_timer.node.expires = rtc_tm_to_ktime(alarm->time); rtc->aie_timer.period = ktime_set(0, 0); - if (alarm->enabled) { + + /* Alarm has to be enabled & in the futrure for us to enqueue it */ + if (alarm->enabled && (rtc_tm_to_ktime(now).tv64 < + rtc->aie_timer.node.expires.tv64)) { + rtc->aie_timer.enabled = 1; timerqueue_add(&rtc->timerqueue, &rtc->aie_timer.node); } @@ -763,6 +776,14 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer) return 0; } +static void rtc_alarm_disable(struct rtc_device *rtc) +{ + if (!rtc->ops || !rtc->ops->alarm_irq_enable) + return; + + rtc->ops->alarm_irq_enable(rtc->dev.parent, false); +} + /** * rtc_timer_remove - Removes a rtc_timer from the rtc_device timerqueue * @rtc rtc device @@ -784,8 +805,10 @@ static void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer) struct rtc_wkalrm alarm; int err; next = timerqueue_getnext(&rtc->timerqueue); - if (!next) + if (!next) { + rtc_alarm_disable(rtc); return; + } alarm.time = rtc_ktime_to_tm(next->expires); alarm.enabled = 1; err = __rtc_set_alarm(rtc, &alarm); @@ -847,7 +870,8 @@ again: err = __rtc_set_alarm(rtc, &alarm); if (err == -ETIME) goto again; - } + } else + rtc_alarm_disable(rtc); mutex_unlock(&rtc->ops_lock); } diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 44262908def5..501b27c18145 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1028,7 +1028,7 @@ done: return iscsit_add_reject_from_cmd( ISCSI_REASON_BOOKMARK_NO_RESOURCES, 1, 1, buf, cmd); - } else if (transport_ret == -EINVAL) { + } else if (transport_ret < 0) { /* * Unsupported SAM Opcode. CHECK_CONDITION will be sent * in iscsit_execute_cmd() during the CmdSN OOO Execution diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index b7c779389eea..63e703bb6ac9 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -117,7 +117,7 @@ static struct t10_pr_registration *core_scsi3_locate_pr_reg(struct se_device *, struct se_node_acl *, struct se_session *); static void core_scsi3_put_pr_reg(struct t10_pr_registration *); -static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd, int *ret) +static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd) { struct se_session *se_sess = cmd->se_sess; struct se_subsystem_dev *su_dev = cmd->se_dev->se_sub_dev; @@ -127,7 +127,7 @@ static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd, int *ret) int conflict = 0; if (!crh) - return false; + return -EINVAL; pr_reg = core_scsi3_locate_pr_reg(cmd->se_dev, se_sess->se_node_acl, se_sess); @@ -155,16 +155,14 @@ static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd, int *ret) */ if (pr_reg->pr_res_holder) { core_scsi3_put_pr_reg(pr_reg); - *ret = 0; - return false; + return 1; } if ((pr_reg->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY) || (pr_reg->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY) || (pr_reg->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG) || (pr_reg->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) { core_scsi3_put_pr_reg(pr_reg); - *ret = 0; - return true; + return 1; } core_scsi3_put_pr_reg(pr_reg); conflict = 1; @@ -189,10 +187,10 @@ static int target_check_scsi2_reservation_conflict(struct se_cmd *cmd, int *ret) " while active SPC-3 registrations exist," " returning RESERVATION_CONFLICT\n"); cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; - return true; + return -EBUSY; } - return false; + return 0; } int target_scsi2_reservation_release(struct se_task *task) @@ -201,12 +199,18 @@ int target_scsi2_reservation_release(struct se_task *task) struct se_device *dev = cmd->se_dev; struct se_session *sess = cmd->se_sess; struct se_portal_group *tpg = sess->se_tpg; - int ret = 0; + int ret = 0, rc; if (!sess || !tpg) goto out; - if (target_check_scsi2_reservation_conflict(cmd, &ret)) + rc = target_check_scsi2_reservation_conflict(cmd); + if (rc == 1) + goto out; + else if (rc < 0) { + cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; + ret = -EINVAL; goto out; + } ret = 0; spin_lock(&dev->dev_reservation_lock); @@ -243,7 +247,7 @@ int target_scsi2_reservation_reserve(struct se_task *task) struct se_device *dev = cmd->se_dev; struct se_session *sess = cmd->se_sess; struct se_portal_group *tpg = sess->se_tpg; - int ret = 0; + int ret = 0, rc; if ((cmd->t_task_cdb[1] & 0x01) && (cmd->t_task_cdb[1] & 0x02)) { @@ -259,8 +263,14 @@ int target_scsi2_reservation_reserve(struct se_task *task) */ if (!sess || !tpg) goto out; - if (target_check_scsi2_reservation_conflict(cmd, &ret)) + rc = target_check_scsi2_reservation_conflict(cmd); + if (rc == 1) goto out; + else if (rc < 0) { + cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; + ret = -EINVAL; + goto out; + } ret = 0; spin_lock(&dev->dev_reservation_lock); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 58cea07b12fb..cd5cd95812bb 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -2539,6 +2539,7 @@ static int transport_generic_cmd_sequencer( cmd, cdb, pr_reg_type) != 0) { cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; cmd->se_cmd_flags |= SCF_SCSI_RESERVATION_CONFLICT; + cmd->scsi_status = SAM_STAT_RESERVATION_CONFLICT; cmd->scsi_sense_reason = TCM_RESERVATION_CONFLICT; return -EBUSY; } diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index 4c0507cf808c..eff512b5a2a0 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -86,16 +86,6 @@ static struct ft_tport *ft_tport_create(struct fc_lport *lport) } /* - * Free tport via RCU. - */ -static void ft_tport_rcu_free(struct rcu_head *rcu) -{ - struct ft_tport *tport = container_of(rcu, struct ft_tport, rcu); - - kfree(tport); -} - -/* * Delete a target local port. * Caller holds ft_lport_lock. */ @@ -114,7 +104,7 @@ static void ft_tport_delete(struct ft_tport *tport) tpg->tport = NULL; tport->tpg = NULL; } - call_rcu(&tport->rcu, ft_tport_rcu_free); + kfree_rcu(tport, rcu); } /* diff --git a/drivers/video/backlight/s6e63m0.c b/drivers/video/backlight/s6e63m0.c index e132157d8545..516db703dd24 100644 --- a/drivers/video/backlight/s6e63m0.c +++ b/drivers/video/backlight/s6e63m0.c @@ -690,7 +690,7 @@ static ssize_t s6e63m0_sysfs_store_gamma_mode(struct device *dev, struct backlight_device *bd = NULL; int brightness, rc; - rc = strict_strtoul(buf, 0, (unsigned long *)&lcd->gamma_mode); + rc = kstrtouint(buf, 0, &lcd->gamma_mode); if (rc < 0) return rc; diff --git a/fs/Kconfig b/fs/Kconfig index d621f02a3f9e..aa195265362f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -4,6 +4,10 @@ menu "File systems" +# Use unaligned word dcache accesses +config DCACHE_WORD_ACCESS + bool + if BLOCK source "fs/ext2/Kconfig" diff --git a/fs/afs/file.c b/fs/afs/file.c index 14d89fa58fee..8f6e9234d565 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -251,7 +251,7 @@ static int afs_readpages(struct file *file, struct address_space *mapping, ASSERT(key != NULL); vnode = AFS_FS_I(mapping->host); - if (vnode->flags & AFS_VNODE_DELETED) { + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { _leave(" = -ESTALE"); return -ESTALE; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index d2b0888126d4..a306bb6d88d9 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -109,7 +109,7 @@ struct afs_call { unsigned reply_size; /* current size of reply */ unsigned first_offset; /* offset into mapping[first] */ unsigned last_to; /* amount of mapping[last] */ - unsigned short offset; /* offset into received data store */ + unsigned offset; /* offset into received data store */ unsigned char unmarshall; /* unmarshalling phase */ bool incoming; /* T if incoming call */ bool send_pages; /* T if data from mapping should be sent */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index e45a323aebb4..8ad8c2a0703a 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -314,6 +314,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct msghdr msg; struct kvec iov[1]; int ret; + struct sk_buff *skb; _enter("%x,{%d},", addr->s_addr, ntohs(call->port)); @@ -380,6 +381,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, error_do_abort: rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT); + while ((skb = skb_dequeue(&call->rx_queue))) + afs_free_skb(skb); rxrpc_kernel_end_call(rxcall); call->rxcall = NULL; error_kill_call: diff --git a/fs/block_dev.c b/fs/block_dev.c index 0e575d1304b4..5e9f198f7712 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1183,8 +1183,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) * The latter is necessary to prevent ghost * partitions on a removed medium. */ - if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM)) - rescan_partitions(disk, bdev); + if (bdev->bd_invalidated) { + if (!ret) + rescan_partitions(disk, bdev); + else if (ret == -ENOMEDIUM) + invalidate_partitions(disk, bdev); + } if (ret) goto out_clear; } else { @@ -1214,8 +1218,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_disk->fops->open) ret = bdev->bd_disk->fops->open(bdev, mode); /* the same as first opener case, read comment there */ - if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM)) - rescan_partitions(bdev->bd_disk, bdev); + if (bdev->bd_invalidated) { + if (!ret) + rescan_partitions(bdev->bd_disk, bdev); + else if (ret == -ENOMEDIUM) + invalidate_partitions(bdev->bd_disk, bdev); + } if (ret) goto out_unlock_bdev; } diff --git a/fs/dcache.c b/fs/dcache.c index bcbdb33fcc20..11828de68dce 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -105,10 +105,10 @@ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; static inline struct hlist_bl_head *d_hash(const struct dentry *parent, - unsigned long hash) + unsigned int hash) { - hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES; - hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS); + hash += (unsigned long) parent / L1_CACHE_BYTES; + hash = hash + (hash >> D_HASHBITS); return dentry_hashtable + (hash & D_HASHMASK); } @@ -144,6 +144,28 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, static inline int dentry_cmp(const unsigned char *cs, size_t scount, const unsigned char *ct, size_t tcount) { +#ifdef CONFIG_DCACHE_WORD_ACCESS + unsigned long a,b,mask; + + if (unlikely(scount != tcount)) + return 1; + + for (;;) { + a = *(unsigned long *)cs; + b = *(unsigned long *)ct; + if (tcount < sizeof(unsigned long)) + break; + if (unlikely(a != b)) + return 1; + cs += sizeof(unsigned long); + ct += sizeof(unsigned long); + tcount -= sizeof(unsigned long); + if (!tcount) + return 0; + } + mask = ~(~0ul << tcount*8); + return unlikely(!!((a ^ b) & mask)); +#else if (scount != tcount) return 1; @@ -155,6 +177,7 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount, tcount--; } while (tcount); return 0; +#endif } static void __d_free(struct rcu_head *head) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ea54cdef04dd..4d9d3a45e356 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -988,6 +988,10 @@ static int path_count[PATH_ARR_SIZE]; static int path_count_inc(int nests) { + /* Allow an arbitrary number of depth 1 paths */ + if (nests == 0) + return 0; + if (++path_count[nests] > path_limits[nests]) return -1; return 0; diff --git a/fs/namei.c b/fs/namei.c index 46ea9cc16647..fa96a26d3291 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1374,6 +1374,126 @@ static inline int can_lookup(struct inode *inode) return 1; } +/* + * We can do the critical dentry name comparison and hashing + * operations one word at a time, but we are limited to: + * + * - Architectures with fast unaligned word accesses. We could + * do a "get_unaligned()" if this helps and is sufficiently + * fast. + * + * - Little-endian machines (so that we can generate the mask + * of low bytes efficiently). Again, we *could* do a byte + * swapping load on big-endian architectures if that is not + * expensive enough to make the optimization worthless. + * + * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we + * do not trap on the (extremely unlikely) case of a page + * crossing operation. + * + * - Furthermore, we need an efficient 64-bit compile for the + * 64-bit case in order to generate the "number of bytes in + * the final mask". Again, that could be replaced with a + * efficient population count instruction or similar. + */ +#ifdef CONFIG_DCACHE_WORD_ACCESS + +#ifdef CONFIG_64BIT + +/* + * Jan Achrenius on G+: microoptimized version of + * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" + * that works for the bytemasks without having to + * mask them first. + */ +static inline long count_masked_bytes(unsigned long mask) +{ + return mask*0x0001020304050608 >> 56; +} + +static inline unsigned int fold_hash(unsigned long hash) +{ + hash += hash >> (8*sizeof(int)); + return hash; +} + +#else /* 32-bit case */ + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline long count_masked_bytes(long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#define fold_hash(x) (x) + +#endif + +unsigned int full_name_hash(const unsigned char *name, unsigned int len) +{ + unsigned long a, mask; + unsigned long hash = 0; + + for (;;) { + a = *(unsigned long *)name; + hash *= 9; + if (len < sizeof(unsigned long)) + break; + hash += a; + name += sizeof(unsigned long); + len -= sizeof(unsigned long); + if (!len) + goto done; + } + mask = ~(~0ul << len*8); + hash += mask & a; +done: + return fold_hash(hash); +} +EXPORT_SYMBOL(full_name_hash); + +#define ONEBYTES 0x0101010101010101ul +#define SLASHBYTES 0x2f2f2f2f2f2f2f2ful +#define HIGHBITS 0x8080808080808080ul + +/* Return the high bit set in the first byte that is a zero */ +static inline unsigned long has_zero(unsigned long a) +{ + return ((a - ONEBYTES) & ~a) & HIGHBITS; +} + +/* + * Calculate the length and hash of the path component, and + * return the length of the component; + */ +static inline unsigned long hash_name(const char *name, unsigned int *hashp) +{ + unsigned long a, mask, hash, len; + + hash = a = 0; + len = -sizeof(unsigned long); + do { + hash = (hash + a) * 9; + len += sizeof(unsigned long); + a = *(unsigned long *)(name+len); + /* Do we have any NUL or '/' bytes in this word? */ + mask = has_zero(a) | has_zero(a ^ SLASHBYTES); + } while (!mask); + + /* The mask *below* the first high bit set */ + mask = (mask - 1) & ~mask; + mask >>= 7; + hash += a & mask; + *hashp = fold_hash(hash); + + return len + count_masked_bytes(mask); +} + +#else + unsigned int full_name_hash(const unsigned char *name, unsigned int len) { unsigned long hash = init_name_hash(); @@ -1402,6 +1522,8 @@ static inline unsigned long hash_name(const char *name, unsigned int *hashp) return len; } +#endif + /* * Name resolution. * This is the basic name resolution function, turning a pathname into diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index d32714094375..501b7f8b739f 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -409,6 +409,12 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, nilfs->ns_first_data_block = le64_to_cpu(sbp->s_first_data_block); nilfs->ns_r_segments_percentage = le32_to_cpu(sbp->s_r_segments_percentage); + if (nilfs->ns_r_segments_percentage < 1 || + nilfs->ns_r_segments_percentage > 99) { + printk(KERN_ERR "NILFS: invalid reserved segments percentage.\n"); + return -EINVAL; + } + nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; @@ -515,6 +521,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, brelse(sbh[1]); sbh[1] = NULL; sbp[1] = NULL; + valid[1] = 0; swp = 0; } if (!valid[swp]) { diff --git a/fs/proc/base.c b/fs/proc/base.c index d4548dd49b02..965d4bde3a3b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1310,8 +1310,7 @@ sched_autogroup_write(struct file *file, const char __user *buf, if (!p) return -ESRCH; - err = nice; - err = proc_sched_autogroup_set_nice(p, &err); + err = proc_sched_autogroup_set_nice(p, nice); if (err) count = err; diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 081147da0564..fbe89e17124e 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -319,13 +319,6 @@ static inline void __clocksource_updatefreq_khz(struct clocksource *cs, u32 khz) __clocksource_updatefreq_scale(cs, 1000, khz); } -static inline void -clocksource_calc_mult_shift(struct clocksource *cs, u32 freq, u32 minsec) -{ - return clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC, minsec); -} - #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct timespec *wtm, diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index dd478fc8f9f5..5f3f3be5af09 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -144,12 +144,14 @@ struct event_filter; enum trace_reg { TRACE_REG_REGISTER, TRACE_REG_UNREGISTER, +#ifdef CONFIG_PERF_EVENTS TRACE_REG_PERF_REGISTER, TRACE_REG_PERF_UNREGISTER, TRACE_REG_PERF_OPEN, TRACE_REG_PERF_CLOSE, TRACE_REG_PERF_ADD, TRACE_REG_PERF_DEL, +#endif }; struct ftrace_event_call; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index fe23ee768589..e61d3192448e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -596,6 +596,7 @@ extern char *disk_name (struct gendisk *hd, int partno, char *buf); extern int disk_expand_part_tbl(struct gendisk *disk, int target); extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); +extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9c66b1ada9d7..f994d51f70f2 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -149,7 +149,7 @@ extern struct cred init_cred; }, \ .rt = { \ .run_list = LIST_HEAD_INIT(tsk.rt.run_list), \ - .time_slice = HZ, \ + .time_slice = RR_TIMESLICE, \ .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 119773eebe31..1a3018063034 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -6,8 +6,11 @@ #include <linux/workqueue.h> enum { - ICQ_IOPRIO_CHANGED, - ICQ_CGROUP_CHANGED, + ICQ_IOPRIO_CHANGED = 1 << 0, + ICQ_CGROUP_CHANGED = 1 << 1, + ICQ_EXITED = 1 << 2, + + ICQ_CHANGED_MASK = ICQ_IOPRIO_CHANGED | ICQ_CGROUP_CHANGED, }; /* @@ -88,7 +91,7 @@ struct io_cq { struct rcu_head __rcu_head; }; - unsigned long changed; + unsigned int flags; }; /* @@ -139,6 +142,7 @@ struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); void ioc_ioprio_changed(struct io_context *ioc, int ioprio); void ioc_cgroup_changed(struct io_context *ioc); +unsigned int icq_get_changed(struct io_cq *icq); #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8343422240a..5582c7985567 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,6 +85,19 @@ } \ ) +/* + * Multiplies an integer by a fraction, while avoiding unnecessary + * overflow or loss of precision. + */ +#define mult_frac(x, numer, denom)( \ +{ \ + typeof(x) quot = (x) / (denom); \ + typeof(x) rem = (x) % (denom); \ + (quot * (numer)) + ((rem * (numer)) / (denom)); \ +} \ +) + + #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) @@ -414,16 +427,10 @@ extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); * Most likely, you want to use tracing_on/tracing_off. */ #ifdef CONFIG_RING_BUFFER -void tracing_on(void); -void tracing_off(void); /* trace_off_permanent stops recording with no way to bring it back */ void tracing_off_permanent(void); -int tracing_is_on(void); #else -static inline void tracing_on(void) { } -static inline void tracing_off(void) { } static inline void tracing_off_permanent(void) { } -static inline int tracing_is_on(void) { return 0; } #endif enum ftrace_dump_mode { @@ -433,6 +440,10 @@ enum ftrace_dump_mode { }; #ifdef CONFIG_TRACING +void tracing_on(void); +void tracing_off(void); +int tracing_is_on(void); + extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); @@ -517,6 +528,11 @@ static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void ftrace_off_permanent(void) { } static inline void trace_dump_stack(void) { } + +static inline void tracing_on(void) { } +static inline void tracing_off(void) { } +static inline int tracing_is_on(void) { return 0; } + static inline int trace_printk(const char *fmt, ...) { diff --git a/include/linux/math64.h b/include/linux/math64.h index 23fcdfcba81b..b8ba85544721 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -6,6 +6,8 @@ #if BITS_PER_LONG == 64 +#define div64_long(x,y) div64_s64((x),(y)) + /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder * @@ -45,6 +47,8 @@ static inline s64 div64_s64(s64 dividend, s64 divisor) #elif BITS_PER_LONG == 32 +#define div64_long(x,y) div_s64((x),(y)) + #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) { diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 58969b2a8a82..5a710b9c578e 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -48,12 +48,14 @@ do { \ barrier(); \ } while (0) -#define preempt_enable_no_resched() \ +#define sched_preempt_enable_no_resched() \ do { \ barrier(); \ dec_preempt_count(); \ } while (0) +#define preempt_enable_no_resched() sched_preempt_enable_no_resched() + #define preempt_enable() \ do { \ preempt_enable_no_resched(); \ @@ -92,6 +94,7 @@ do { \ #else /* !CONFIG_PREEMPT_COUNT */ #define preempt_disable() do { } while (0) +#define sched_preempt_enable_no_resched() do { } while (0) #define preempt_enable_no_resched() do { } while (0) #define preempt_enable() do { } while (0) diff --git a/include/linux/printk.h b/include/linux/printk.h index f0e22f75143f..1f77a4174ee0 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -101,6 +101,11 @@ asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* + * Special printk facility for scheduler use only, _DO_NOT_USE_ ! + */ +__printf(1, 2) __cold int printk_sched(const char *fmt, ...); + +/* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). @@ -127,6 +132,11 @@ int printk(const char *s, ...) { return 0; } +static inline __printf(1, 2) __cold +int printk_sched(const char *s, ...) +{ + return 0; +} static inline int printk_ratelimit(void) { return 0; diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 81c04f4348ec..937217425c47 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -190,6 +190,33 @@ extern void rcu_idle_exit(void); extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); +/** + * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers + * @a: Code that RCU needs to pay attention to. + * + * RCU, RCU-bh, and RCU-sched read-side critical sections are forbidden + * in the inner idle loop, that is, between the rcu_idle_enter() and + * the rcu_idle_exit() -- RCU will happily ignore any such read-side + * critical sections. However, things like powertop need tracepoints + * in the inner idle loop. + * + * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) + * will tell RCU that it needs to pay attending, invoke its argument + * (in this example, a call to the do_something_with_RCU() function), + * and then tell RCU to go back to ignoring this CPU. It is permissible + * to nest RCU_NONIDLE() wrappers, but the nesting level is currently + * quite limited. If deeper nesting is required, it will be necessary + * to adjust DYNTICK_TASK_NESTING_VALUE accordingly. + * + * This macro may be used from process-level code only. + */ +#define RCU_NONIDLE(a) \ + do { \ + rcu_idle_exit(); \ + do { a; } while (0); \ + rcu_idle_enter(); \ + } while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -226,6 +253,15 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) +bool rcu_lockdep_current_cpu_online(void); +#else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ +static inline bool rcu_lockdep_current_cpu_online(void) +{ + return 1; +} +#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC #ifdef CONFIG_PROVE_RCU @@ -239,13 +275,11 @@ static inline int rcu_is_cpu_idle(void) static inline void rcu_lock_acquire(struct lockdep_map *map) { - WARN_ON_ONCE(rcu_is_cpu_idle()); lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { - WARN_ON_ONCE(rcu_is_cpu_idle()); lock_release(map, 1, _THIS_IP_); } @@ -270,6 +304,9 @@ extern int debug_lockdep_rcu_enabled(void); * occur in the same context, for example, it is illegal to invoke * rcu_read_unlock() in process context if the matching rcu_read_lock() * was invoked from within an irq handler. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. */ static inline int rcu_read_lock_held(void) { @@ -277,6 +314,8 @@ static inline int rcu_read_lock_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return lock_is_held(&rcu_lock_map); } @@ -313,6 +352,9 @@ extern int rcu_read_lock_bh_held(void); * notice an extended quiescent state to other CPUs that started a grace * period. Otherwise we would delay any grace period as long as we run in * the idle task. + * + * Similarly, we avoid claiming an SRCU read lock held if the current + * CPU is offline. */ #ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) @@ -323,6 +365,8 @@ static inline int rcu_read_lock_sched_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); @@ -381,8 +425,22 @@ extern int rcu_my_thread_group_empty(void); } \ } while (0) +#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +static inline void rcu_preempt_sleep_check(void) +{ + rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), + "Illegal context switch in RCU read-side " + "critical section"); +} +#else /* #ifdef CONFIG_PROVE_RCU */ +static inline void rcu_preempt_sleep_check(void) +{ +} +#endif /* #else #ifdef CONFIG_PROVE_RCU */ + #define rcu_sleep_check() \ do { \ + rcu_preempt_sleep_check(); \ rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh" \ " read-side critical section"); \ @@ -470,6 +528,13 @@ extern int rcu_my_thread_group_empty(void); * NULL. Although rcu_access_pointer() may also be used in cases where * update-side locks prevent the value of the pointer from changing, you * should instead use rcu_dereference_protected() for this use case. + * + * It is also permissible to use rcu_access_pointer() when read-side + * access to the pointer was removed at least one grace period ago, as + * is the case in the context of the RCU callback that is freeing up + * the data, or after a synchronize_rcu() returns. This can be useful + * when tearing down multi-linked structures after a grace period + * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) @@ -659,6 +724,8 @@ static inline void rcu_read_lock(void) __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock() used illegally while idle"); } /* @@ -678,6 +745,8 @@ static inline void rcu_read_lock(void) */ static inline void rcu_read_unlock(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); __release(RCU); __rcu_read_unlock(); @@ -705,6 +774,8 @@ static inline void rcu_read_lock_bh(void) local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock_bh() used illegally while idle"); } /* @@ -714,6 +785,8 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); @@ -737,6 +810,8 @@ static inline void rcu_read_lock_sched(void) preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -753,6 +828,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); @@ -841,7 +918,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) /* See the kfree_rcu() header comment. */ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); - call_rcu(head, (rcu_callback)offset); + kfree_call_rcu(head, (rcu_callback)offset); } /** diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 00b7a5e493d2..e93df77176d1 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,13 +27,9 @@ #include <linux/cache.h> -#ifdef CONFIG_RCU_BOOST static inline void rcu_init(void) { } -#else /* #ifdef CONFIG_RCU_BOOST */ -void rcu_init(void); -#endif /* #else #ifdef CONFIG_RCU_BOOST */ static inline void rcu_barrier_bh(void) { @@ -83,6 +79,12 @@ static inline void synchronize_sched_expedited(void) synchronize_sched(); } +static inline void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + call_rcu(head, func); +} + #ifdef CONFIG_TINY_RCU static inline void rcu_preempt_note_context_switch(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 67458468f1a8..e8ee5dd0854c 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -61,6 +61,24 @@ extern void synchronize_rcu_bh(void); extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); +void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); + +/** + * synchronize_rcu_bh_expedited - Brute-force RCU-bh grace period + * + * Wait for an RCU-bh grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_rcu_bh_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_rcu_bh() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. + */ static inline void synchronize_rcu_bh_expedited(void) { synchronize_sched_expedited(); @@ -83,6 +101,7 @@ extern void rcu_sched_force_quiescent_state(void); /* A context switch is a grace period for RCU-sched and RCU-bh. */ static inline int rcu_blocking_is_gp(void) { + might_sleep(); /* Check for RCU read-side critical section. */ return num_online_cpus() == 1; } diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 67be0376d8e3..7be2e88f23fd 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_disable(struct ring_buffer *buffer); void ring_buffer_record_enable(struct ring_buffer *buffer); +void ring_buffer_record_off(struct ring_buffer *buffer); +void ring_buffer_record_on(struct ring_buffer *buffer); +int ring_buffer_record_is_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/sched.h b/include/linux/sched.h index 0657368bd78f..e074e1e54f85 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -361,6 +361,7 @@ extern signed long schedule_timeout_interruptible(signed long timeout); extern signed long schedule_timeout_killable(signed long timeout); extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); +extern void schedule_preempt_disabled(void); extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner); struct nsproxy; @@ -905,6 +906,7 @@ struct sched_group_power { * single CPU. */ unsigned int power, power_orig; + unsigned long next_update; /* * Number of busy cpus in this group. */ @@ -1052,6 +1054,8 @@ static inline int test_sd_parent(struct sched_domain *sd, int flag) unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu); unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu); +bool cpus_share_cache(int this_cpu, int that_cpu); + #else /* CONFIG_SMP */ struct sched_domain_attr; @@ -1061,6 +1065,12 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { } + +static inline bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return true; +} + #endif /* !CONFIG_SMP */ @@ -1225,6 +1235,12 @@ struct sched_rt_entity { #endif }; +/* + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define RR_TIMESLICE (100 * HZ / 1000) + struct rcu_node; enum perf_event_task_context { @@ -1319,6 +1335,11 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; +#ifdef CONFIG_GENERIC_HARDIRQS + /* IRQ handler threads */ + unsigned irq_thread:1; +#endif + pid_t pid; pid_t tgid; @@ -1427,11 +1448,6 @@ struct task_struct { * mempolicy */ spinlock_t alloc_lock; -#ifdef CONFIG_GENERIC_HARDIRQS - /* IRQ handler threads */ - struct irqaction *irqaction; -#endif - /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; @@ -1863,8 +1879,7 @@ extern void task_clear_jobctl_pending(struct task_struct *task, #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ static inline void rcu_copy_process(struct task_struct *p) { @@ -2048,7 +2063,7 @@ extern void sched_autogroup_fork(struct signal_struct *sig); extern void sched_autogroup_exit(struct signal_struct *sig); #ifdef CONFIG_PROC_FS extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); -extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); #endif #else static inline void sched_autogroup_create_attach(struct task_struct *p) { } @@ -2065,12 +2080,20 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); extern void rt_mutex_adjust_pi(struct task_struct *p); +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return tsk->pi_blocked_on != NULL; +} #else static inline int rt_mutex_getprio(struct task_struct *p) { return p->normal_prio; } # define rt_mutex_adjust_pi(p) do { } while (0) +static inline bool tsk_is_pi_blocked(struct task_struct *tsk) +{ + return false; +} #endif extern bool yield_to(struct task_struct *p, bool preempt); @@ -2389,12 +2412,15 @@ static inline void task_unlock(struct task_struct *p) extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, unsigned long *flags); -#define lock_task_sighand(tsk, flags) \ -({ struct sighand_struct *__ss; \ - __cond_lock(&(tsk)->sighand->siglock, \ - (__ss = __lock_task_sighand(tsk, flags))); \ - __ss; \ -}) \ +static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *ret; + + ret = __lock_task_sighand(tsk, flags); + (void)__cond_lock(&tsk->sighand->siglock, ret); + return ret; +} static inline void unlock_task_sighand(struct task_struct *tsk, unsigned long *flags) diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e1b005918bbb..d3d5fa54f25e 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -99,15 +99,18 @@ long srcu_batches_completed(struct srcu_struct *sp); * power mode. This way we can notice an extended quiescent state to * other CPUs that started a grace period. Otherwise we would delay any * grace period as long as we run in the idle task. + * + * Similarly, we avoid claiming an SRCU read lock held if the current + * CPU is offline. */ static inline int srcu_read_lock_held(struct srcu_struct *sp) { - if (rcu_is_cpu_idle()) - return 0; - if (!debug_lockdep_rcu_enabled()) return 1; - + if (rcu_is_cpu_idle()) + return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return lock_is_held(&sp->dep_map); } @@ -169,6 +172,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) int retval = __srcu_read_lock(sp); rcu_lock_acquire(&(sp)->dep_map); + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "srcu_read_lock() used illegally while idle"); return retval; } @@ -182,6 +187,8 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp) { + rcu_lockdep_assert(!rcu_is_cpu_idle(), + "srcu_read_unlock() used illegally while idle"); rcu_lock_release(&(sp)->dep_map); __srcu_read_unlock(sp, idx); } diff --git a/include/linux/timex.h b/include/linux/timex.h index aa60fe7b6ed6..b75e1864ed19 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -234,23 +234,9 @@ struct timex { extern unsigned long tick_usec; /* USER_HZ period (usec) */ extern unsigned long tick_nsec; /* ACTHZ period (nsec) */ -/* - * phase-lock loop variables - */ -extern int time_status; /* clock synchronization status bits */ - extern void ntp_init(void); extern void ntp_clear(void); -/** - * ntp_synced - Returns 1 if the NTP status is not UNSYNC - * - */ -static inline int ntp_synced(void) -{ - return !(time_status & STA_UNSYNC); -} - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ @@ -264,10 +250,9 @@ static inline int ntp_synced(void) #define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ) /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ -extern u64 tick_length; +extern u64 ntp_tick_length(void); extern void second_overflow(void); -extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); diff --git a/include/linux/wait.h b/include/linux/wait.h index a9ce45e8501c..7d9a9e990ce6 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -157,7 +157,7 @@ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode); +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_bit(wait_queue_head_t *, void *, int); int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned); @@ -170,7 +170,8 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) -#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL) +#define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) +#define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index eb8b9f15f2e0..af155450cabb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -289,12 +289,16 @@ enum { * * system_freezable_wq is equivalent to system_wq except that it's * freezable. + * + * system_nrt_freezable_wq is equivalent to system_nrt_wq except that + * it's freezable. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_nrt_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; +extern struct workqueue_struct *system_nrt_freezable_wq; extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index d2d88bed891b..337099783f37 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -313,19 +313,22 @@ TRACE_EVENT(rcu_prep_idle, /* * Tracepoint for the registration of a single RCU callback function. * The first argument is the type of RCU, the second argument is - * a pointer to the RCU callback itself, and the third element is the - * new RCU callback queue length for the current CPU. + * a pointer to the RCU callback itself, the third element is the + * number of lazy callbacks queued, and the fourth element is the + * total number of callbacks queued. */ TRACE_EVENT(rcu_callback, - TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen), + TP_PROTO(char *rcuname, struct rcu_head *rhp, long qlen_lazy, + long qlen), - TP_ARGS(rcuname, rhp, qlen), + TP_ARGS(rcuname, rhp, qlen_lazy, qlen), TP_STRUCT__entry( __field(char *, rcuname) __field(void *, rhp) __field(void *, func) + __field(long, qlen_lazy) __field(long, qlen) ), @@ -333,11 +336,13 @@ TRACE_EVENT(rcu_callback, __entry->rcuname = rcuname; __entry->rhp = rhp; __entry->func = rhp->func; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; ), - TP_printk("%s rhp=%p func=%pf %ld", - __entry->rcuname, __entry->rhp, __entry->func, __entry->qlen) + TP_printk("%s rhp=%p func=%pf %ld/%ld", + __entry->rcuname, __entry->rhp, __entry->func, + __entry->qlen_lazy, __entry->qlen) ); /* @@ -345,20 +350,21 @@ TRACE_EVENT(rcu_callback, * kfree() form. The first argument is the RCU type, the second argument * is a pointer to the RCU callback, the third argument is the offset * of the callback within the enclosing RCU-protected data structure, - * and the fourth argument is the new RCU callback queue length for the - * current CPU. + * the fourth argument is the number of lazy callbacks queued, and the + * fifth argument is the total number of callbacks queued. */ TRACE_EVENT(rcu_kfree_callback, TP_PROTO(char *rcuname, struct rcu_head *rhp, unsigned long offset, - long qlen), + long qlen_lazy, long qlen), - TP_ARGS(rcuname, rhp, offset, qlen), + TP_ARGS(rcuname, rhp, offset, qlen_lazy, qlen), TP_STRUCT__entry( __field(char *, rcuname) __field(void *, rhp) __field(unsigned long, offset) + __field(long, qlen_lazy) __field(long, qlen) ), @@ -366,41 +372,45 @@ TRACE_EVENT(rcu_kfree_callback, __entry->rcuname = rcuname; __entry->rhp = rhp; __entry->offset = offset; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; ), - TP_printk("%s rhp=%p func=%ld %ld", + TP_printk("%s rhp=%p func=%ld %ld/%ld", __entry->rcuname, __entry->rhp, __entry->offset, - __entry->qlen) + __entry->qlen_lazy, __entry->qlen) ); /* * Tracepoint for marking the beginning rcu_do_batch, performed to start * RCU callback invocation. The first argument is the RCU flavor, - * the second is the total number of callbacks (including those that - * are not yet ready to be invoked), and the third argument is the - * current RCU-callback batch limit. + * the second is the number of lazy callbacks queued, the third is + * the total number of callbacks queued, and the fourth argument is + * the current RCU-callback batch limit. */ TRACE_EVENT(rcu_batch_start, - TP_PROTO(char *rcuname, long qlen, int blimit), + TP_PROTO(char *rcuname, long qlen_lazy, long qlen, int blimit), - TP_ARGS(rcuname, qlen, blimit), + TP_ARGS(rcuname, qlen_lazy, qlen, blimit), TP_STRUCT__entry( __field(char *, rcuname) + __field(long, qlen_lazy) __field(long, qlen) __field(int, blimit) ), TP_fast_assign( __entry->rcuname = rcuname; + __entry->qlen_lazy = qlen_lazy; __entry->qlen = qlen; __entry->blimit = blimit; ), - TP_printk("%s CBs=%ld bl=%d", - __entry->rcuname, __entry->qlen, __entry->blimit) + TP_printk("%s CBs=%ld/%ld bl=%d", + __entry->rcuname, __entry->qlen_lazy, __entry->qlen, + __entry->blimit) ); /* @@ -531,16 +541,21 @@ TRACE_EVENT(rcu_torture_read, #else /* #ifdef CONFIG_RCU_TRACE */ #define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0) -#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, qsmask) do { } while (0) +#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \ + qsmask) do { } while (0) #define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0) #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) -#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0) +#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \ + grplo, grphi, gp_tasks) do { } \ + while (0) #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) #define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0) #define trace_rcu_prep_idle(reason) do { } while (0) -#define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0) -#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0) -#define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0) +#define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0) +#define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \ + do { } while (0) +#define trace_rcu_batch_start(rcuname, qlen_lazy, qlen, blimit) \ + do { } while (0) #define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0) #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0) #define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ diff --git a/init/Kconfig b/init/Kconfig index 3f42cd66f0f8..72f33faca44f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -438,15 +438,6 @@ config PREEMPT_RCU This option enables preemptible-RCU code that is common between the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. -config RCU_TRACE - bool "Enable tracing for RCU" - help - This option provides tracing in RCU which presents stats - in debugfs for debugging RCU implementation. - - Say Y here if you want to enable RCU tracing - Say N if you are unsure. - config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT diff --git a/init/main.c b/init/main.c index ff49a6dacfbb..4990f7ec776a 100644 --- a/init/main.c +++ b/init/main.c @@ -374,11 +374,8 @@ static noinline void __init_refok rest_init(void) * at least once to get things moving: */ init_idle_bootup_task(current); - preempt_enable_no_resched(); - schedule(); - + schedule_preempt_disabled(); /* Call into cpu_idle with preempt disabled */ - preempt_disable(); cpu_idle(); } diff --git a/kernel/exit.c b/kernel/exit.c index 4b4042f9bc6a..752d2c0abd19 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -935,8 +935,6 @@ void do_exit(long code) schedule(); } - exit_irq_thread(); - exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against @@ -945,6 +943,8 @@ void do_exit(long code) smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); + exit_irq_thread(); + if (unlikely(in_atomic())) printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), diff --git a/kernel/futex.c b/kernel/futex.c index 1614be20173d..72efa1e4359a 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2628,7 +2628,7 @@ void exit_robust_list(struct task_struct *curr) long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { - int ret = -ENOSYS, cmd = op & FUTEX_CMD_MASK; + int cmd = op & FUTEX_CMD_MASK; unsigned int flags = 0; if (!(op & FUTEX_PRIVATE_FLAG)) @@ -2641,49 +2641,44 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, } switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_UNLOCK_PI: + case FUTEX_TRYLOCK_PI: + case FUTEX_WAIT_REQUEUE_PI: + case FUTEX_CMP_REQUEUE_PI: + if (!futex_cmpxchg_enabled) + return -ENOSYS; + } + + switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAIT_BITSET: - ret = futex_wait(uaddr, flags, val, timeout, val3); - break; + return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAKE_BITSET: - ret = futex_wake(uaddr, flags, val, val3); - break; + return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); - break; + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); case FUTEX_WAKE_OP: - ret = futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); - break; + return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, flags, val, timeout, 0); - break; + return futex_lock_pi(uaddr, flags, val, timeout, 0); case FUTEX_UNLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_unlock_pi(uaddr, flags); - break; + return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: - if (futex_cmpxchg_enabled) - ret = futex_lock_pi(uaddr, flags, 0, timeout, 1); - break; + return futex_lock_pi(uaddr, flags, 0, timeout, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; - ret = futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, - uaddr2); - break; + return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, + uaddr2); case FUTEX_CMP_REQUEUE_PI: - ret = futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); - break; - default: - ret = -ENOSYS; + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); } - return ret; + return -ENOSYS; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 838687ed802a..6080f6bc8c33 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -63,8 +63,7 @@ int irq_set_irq_type(unsigned int irq, unsigned int type) return -EINVAL; type &= IRQ_TYPE_SENSE_MASK; - if (type != IRQ_TYPE_NONE) - ret = __irq_set_trigger(desc, irq, type); + ret = __irq_set_trigger(desc, irq, type); irq_put_desc_busunlock(desc, flags); return ret; } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 470d08c82bbe..6ff84e6a954c 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -60,7 +60,7 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) * device interrupt, so no irq storm is lurking. If the * RUNTHREAD bit is already set, nothing to do. */ - if (test_bit(IRQTF_DIED, &action->thread_flags) || + if ((action->thread->flags & PF_EXITING) || test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags)) return; @@ -110,6 +110,18 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) * threads_oneshot untouched and runs the thread another time. */ desc->threads_oneshot |= action->thread_mask; + + /* + * We increment the threads_active counter in case we wake up + * the irq thread. The irq thread decrements the counter when + * it returns from the handler or in the exit path and wakes + * up waiters which are stuck in synchronize_irq() when the + * active count becomes zero. synchronize_irq() is serialized + * against this code (hard irq handler) via IRQS_INPROGRESS + * like the finalize_oneshot() code. See comment above. + */ + atomic_inc(&desc->threads_active); + wake_up_process(action->thread); } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 40378ff877e7..8e5c56b3b7d9 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -20,14 +20,12 @@ extern bool noirqdebug; /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run - * IRQTF_DIED - handler thread died * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded */ enum { IRQTF_RUNTHREAD, - IRQTF_DIED, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0f0d4704ddd8..b0ccd1ac2d6a 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -759,6 +759,13 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, return ret; } +static void wake_threads_waitq(struct irq_desc *desc) +{ + if (atomic_dec_and_test(&desc->threads_active) && + waitqueue_active(&desc->wait_for_threads)) + wake_up(&desc->wait_for_threads); +} + /* * Interrupt handler thread */ @@ -771,57 +778,41 @@ static int irq_thread(void *data) struct irq_desc *desc = irq_to_desc(action->irq); irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); - int wake; - if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD, + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, &action->thread_flags)) handler_fn = irq_forced_thread_fn; else handler_fn = irq_thread_fn; sched_setscheduler(current, SCHED_FIFO, ¶m); - current->irqaction = action; + current->irq_thread = 1; while (!irq_wait_for_interrupt(action)) { + irqreturn_t action_ret; irq_thread_check_affinity(desc, action); - atomic_inc(&desc->threads_active); + action_ret = handler_fn(desc, action); + if (!noirqdebug) + note_interrupt(action->irq, desc, action_ret); - raw_spin_lock_irq(&desc->lock); - if (unlikely(irqd_irq_disabled(&desc->irq_data))) { - /* - * CHECKME: We might need a dedicated - * IRQ_THREAD_PENDING flag here, which - * retriggers the thread in check_irq_resend() - * but AFAICT IRQS_PENDING should be fine as it - * retriggers the interrupt itself --- tglx - */ - desc->istate |= IRQS_PENDING; - raw_spin_unlock_irq(&desc->lock); - } else { - irqreturn_t action_ret; - - raw_spin_unlock_irq(&desc->lock); - action_ret = handler_fn(desc, action); - if (!noirqdebug) - note_interrupt(action->irq, desc, action_ret); - } - - wake = atomic_dec_and_test(&desc->threads_active); - - if (wake && waitqueue_active(&desc->wait_for_threads)) - wake_up(&desc->wait_for_threads); + wake_threads_waitq(desc); } - /* Prevent a stale desc->threads_oneshot */ - irq_finalize_oneshot(desc, action, true); - /* - * Clear irqaction. Otherwise exit_irq_thread() would make + * This is the regular exit path. __free_irq() is stopping the + * thread via kthread_stop() after calling + * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. We cannot verify that as we + * cannot touch the oneshot mask at this point anymore as + * __setup_irq() might have given out currents thread_mask + * again. + * + * Clear irq_thread. Otherwise exit_irq_thread() would make * fuzz about an active irq thread going into nirvana. */ - current->irqaction = NULL; + current->irq_thread = 0; return 0; } @@ -832,27 +823,28 @@ void exit_irq_thread(void) { struct task_struct *tsk = current; struct irq_desc *desc; + struct irqaction *action; - if (!tsk->irqaction) + if (!tsk->irq_thread) return; + action = kthread_data(tsk); + printk(KERN_ERR "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq); + tsk->comm ? tsk->comm : "", tsk->pid, action->irq); - desc = irq_to_desc(tsk->irqaction->irq); + desc = irq_to_desc(action->irq); /* - * Prevent a stale desc->threads_oneshot. Must be called - * before setting the IRQTF_DIED flag. + * If IRQTF_RUNTHREAD is set, we need to decrement + * desc->threads_active and wake possible waiters. */ - irq_finalize_oneshot(desc, tsk->irqaction, true); + if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + wake_threads_waitq(desc); - /* - * Set the THREAD DIED flag to prevent further wakeups of the - * soon to be gone threaded handler. - */ - set_bit(IRQTF_DIED, &tsk->irqaction->flags); + /* Prevent a stale desc->threads_oneshot */ + irq_finalize_oneshot(desc, action, true); } static void irq_setup_forced_threading(struct irqaction *new) @@ -1135,8 +1127,7 @@ out_thread: struct task_struct *t = new->thread; new->thread = NULL; - if (likely(!test_bit(IRQTF_DIED, &new->thread_flags))) - kthread_stop(t); + kthread_stop(t); put_task_struct(t); } out_mput: @@ -1246,8 +1237,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif if (action->thread) { - if (!test_bit(IRQTF_DIED, &action->thread_flags)) - kthread_stop(action->thread); + kthread_stop(action->thread); put_task_struct(action->thread); } diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 8889f7dd7c46..ea9ee4518c35 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -4176,7 +4176,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) printk("-------------------------------\n"); printk("%s:%d %s!\n", file, line, s); printk("\nother info that might help us debug this:\n\n"); - printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); + printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n", + !rcu_lockdep_current_cpu_online() + ? "RCU used illegally from offline CPU!\n" + : rcu_is_cpu_idle() + ? "RCU used illegally from idle CPU!\n" + : "", + rcu_scheduler_active, debug_locks); /* * If a CPU is in the RCU-free window in idle (ie: in the section diff --git a/kernel/mutex.c b/kernel/mutex.c index 89096dd8786f..a307cc9c9526 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -240,9 +240,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); spin_lock_mutex(&lock->wait_lock, flags); } diff --git a/kernel/printk.c b/kernel/printk.c index 0b3ea2cbd5fb..b663c2c95d39 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1216,13 +1216,27 @@ int is_console_locked(void) return console_locked; } +/* + * Delayed printk facility, for scheduler-internal messages: + */ +#define PRINTK_BUF_SIZE 512 + +#define PRINTK_PENDING_WAKEUP 0x01 +#define PRINTK_PENDING_SCHED 0x02 + static DEFINE_PER_CPU(int, printk_pending); +static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf); void printk_tick(void) { if (__this_cpu_read(printk_pending)) { - __this_cpu_write(printk_pending, 0); - wake_up_interruptible(&log_wait); + int pending = __this_cpu_xchg(printk_pending, 0); + if (pending & PRINTK_PENDING_SCHED) { + char *buf = __get_cpu_var(printk_sched_buf); + printk(KERN_WARNING "[sched_delayed] %s", buf); + } + if (pending & PRINTK_PENDING_WAKEUP) + wake_up_interruptible(&log_wait); } } @@ -1236,7 +1250,7 @@ int printk_needs_cpu(int cpu) void wake_up_klogd(void) { if (waitqueue_active(&log_wait)) - this_cpu_write(printk_pending, 1); + this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP); } /** @@ -1629,6 +1643,26 @@ late_initcall(printk_late_init); #if defined CONFIG_PRINTK +int printk_sched(const char *fmt, ...) +{ + unsigned long flags; + va_list args; + char *buf; + int r; + + local_irq_save(flags); + buf = __get_cpu_var(printk_sched_buf); + + va_start(args, fmt); + r = vsnprintf(buf, PRINTK_BUF_SIZE, fmt, args); + va_end(args); + + __this_cpu_or(printk_pending, PRINTK_PENDING_SCHED); + local_irq_restore(flags); + + return r; +} + /* * printk rate limiting, lifted from the networking subsystem. * diff --git a/kernel/rcu.h b/kernel/rcu.h index aa88baab5f78..8ba99cdc6515 100644 --- a/kernel/rcu.h +++ b/kernel/rcu.h @@ -33,8 +33,27 @@ * Process-level increment to ->dynticks_nesting field. This allows for * architectures that use half-interrupts and half-exceptions from * process context. + * + * DYNTICK_TASK_NEST_MASK defines a field of width DYNTICK_TASK_NEST_WIDTH + * that counts the number of process-based reasons why RCU cannot + * consider the corresponding CPU to be idle, and DYNTICK_TASK_NEST_VALUE + * is the value used to increment or decrement this field. + * + * The rest of the bits could in principle be used to count interrupts, + * but this would mean that a negative-one value in the interrupt + * field could incorrectly zero out the DYNTICK_TASK_NEST_MASK field. + * We therefore provide a two-bit guard field defined by DYNTICK_TASK_MASK + * that is set to DYNTICK_TASK_FLAG upon initial exit from idle. + * The DYNTICK_TASK_EXIT_IDLE value is thus the combined value used upon + * initial exit from idle. */ -#define DYNTICK_TASK_NESTING (LLONG_MAX / 2 - 1) +#define DYNTICK_TASK_NEST_WIDTH 7 +#define DYNTICK_TASK_NEST_VALUE ((LLONG_MAX >> DYNTICK_TASK_NEST_WIDTH) + 1) +#define DYNTICK_TASK_NEST_MASK (LLONG_MAX - DYNTICK_TASK_NEST_VALUE + 1) +#define DYNTICK_TASK_FLAG ((DYNTICK_TASK_NEST_VALUE / 8) * 2) +#define DYNTICK_TASK_MASK ((DYNTICK_TASK_NEST_VALUE / 8) * 3) +#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \ + DYNTICK_TASK_FLAG) /* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally @@ -50,7 +69,6 @@ extern struct debug_obj_descr rcuhead_debug_descr; static inline void debug_rcu_head_queue(struct rcu_head *head) { - WARN_ON_ONCE((unsigned long)head & 0x3); debug_object_activate(head, &rcuhead_debug_descr); debug_object_active_state(head, &rcuhead_debug_descr, STATE_RCU_HEAD_READY, @@ -76,16 +94,18 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) extern void kfree(const void *); -static inline void __rcu_reclaim(char *rn, struct rcu_head *head) +static inline bool __rcu_reclaim(char *rn, struct rcu_head *head) { unsigned long offset = (unsigned long)head->func; if (__is_kfree_rcu_offset(offset)) { RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset)); kfree((void *)head - offset); + return 1; } else { RCU_TRACE(trace_rcu_invoke_callback(rn, head)); head->func(head); + return 0; } } diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 2bc4e135ff23..a86f1741cc27 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -88,6 +88,9 @@ EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); * section. * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. + * + * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * offline from an RCU perspective, so check for those as well. */ int rcu_read_lock_bh_held(void) { @@ -95,6 +98,8 @@ int rcu_read_lock_bh_held(void) return 1; if (rcu_is_cpu_idle()) return 0; + if (!rcu_lockdep_current_cpu_online()) + return 0; return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 977296dca0a4..37a5444204d2 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -53,7 +53,7 @@ static void __call_rcu(struct rcu_head *head, #include "rcutiny_plugin.h" -static long long rcu_dynticks_nesting = DYNTICK_TASK_NESTING; +static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ static void rcu_idle_enter_common(long long oldval) @@ -88,10 +88,16 @@ void rcu_idle_enter(void) local_irq_save(flags); oldval = rcu_dynticks_nesting; - rcu_dynticks_nesting = 0; + WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); + if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == + DYNTICK_TASK_NEST_VALUE) + rcu_dynticks_nesting = 0; + else + rcu_dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; rcu_idle_enter_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); /* * Exit an interrupt handler towards idle. @@ -140,11 +146,15 @@ void rcu_idle_exit(void) local_irq_save(flags); oldval = rcu_dynticks_nesting; - WARN_ON_ONCE(oldval != 0); - rcu_dynticks_nesting = DYNTICK_TASK_NESTING; + WARN_ON_ONCE(rcu_dynticks_nesting < 0); + if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) + rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_idle_exit_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); /* * Enter an interrupt handler, moving away from idle. @@ -258,7 +268,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* If no RCU callbacks ready to invoke, just return. */ if (&rcp->rcucblist == rcp->donetail) { - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1)); RCU_TRACE(trace_rcu_batch_end(rcp->name, 0, ACCESS_ONCE(rcp->rcucblist), need_resched(), @@ -269,7 +279,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); - RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); + RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; *rcp->donetail = NULL; @@ -319,6 +329,10 @@ static void rcu_process_callbacks(struct softirq_action *unused) */ void synchronize_sched(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU read-side critical section"); cond_resched(); } EXPORT_SYMBOL_GPL(synchronize_sched); diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 9cb1ae4aabdd..22ecea0dfb62 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,6 +132,7 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; +static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -146,6 +147,16 @@ static int rcu_cpu_blocking_cur_gp(void) /* * Check for a running RCU reader. Because there is only one CPU, * there can be but one running RCU reader at a time. ;-) + * + * Returns zero if there are no running readers. Returns a positive + * number if there is at least one reader within its RCU read-side + * critical section. Returns a negative number if an outermost reader + * is in the midst of exiting from its RCU read-side critical section + * + * Returns zero if there are no running readers. Returns a positive + * number if there is at least one reader within its RCU read-side + * critical section. Returns a negative number if an outermost reader + * is in the midst of exiting from its RCU read-side critical section. */ static int rcu_preempt_running_reader(void) { @@ -307,7 +318,6 @@ static int rcu_boost(void) t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -475,7 +485,7 @@ void rcu_preempt_note_context_switch(void) unsigned long flags; local_irq_save(flags); /* must exclude scheduler_tick(). */ - if (rcu_preempt_running_reader() && + if (rcu_preempt_running_reader() > 0 && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ @@ -494,6 +504,13 @@ void rcu_preempt_note_context_switch(void) list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; + } else if (rcu_preempt_running_reader() < 0 && + t->rcu_read_unlock_special) { + /* + * Complete exit from RCU read-side critical section on + * behalf of preempted instance of __rcu_read_unlock(). + */ + rcu_read_unlock_special(t); } /* @@ -526,12 +543,15 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock); * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static void rcu_read_unlock_special(struct task_struct *t) +static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; unsigned long flags; struct list_head *np; +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rbmp = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ int special; /* @@ -552,7 +572,7 @@ static void rcu_read_unlock_special(struct task_struct *t) rcu_preempt_cpu_qs(); /* Hardware IRQ handlers cannot block. */ - if (in_irq()) { + if (in_irq() || in_serving_softirq()) { local_irq_restore(flags); return; } @@ -597,10 +617,10 @@ static void rcu_read_unlock_special(struct task_struct *t) } #ifdef CONFIG_RCU_BOOST /* Unboost self if was boosted. */ - if (special & RCU_READ_UNLOCK_BOOSTED) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED; - rt_mutex_unlock(t->rcu_boost_mutex); + if (t->rcu_boost_mutex != NULL) { + rbmp = t->rcu_boost_mutex; t->rcu_boost_mutex = NULL; + rt_mutex_unlock(rbmp); } #endif /* #ifdef CONFIG_RCU_BOOST */ local_irq_restore(flags); @@ -618,13 +638,22 @@ void __rcu_read_unlock(void) struct task_struct *t = current; barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - --t->rcu_read_lock_nesting; - barrier(); /* decrement before load of ->rcu_read_unlock_special */ - if (t->rcu_read_lock_nesting == 0 && - unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); + if (t->rcu_read_lock_nesting != 1) + --t->rcu_read_lock_nesting; + else { + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(t->rcu_read_lock_nesting < 0); + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } #endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); @@ -649,7 +678,7 @@ static void rcu_preempt_check_callbacks(void) invoke_rcu_callbacks(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && - rcu_preempt_running_reader()) + rcu_preempt_running_reader() > 0) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } @@ -706,6 +735,11 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); + #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!rcu_scheduler_active) return; @@ -882,7 +916,8 @@ static void rcu_preempt_process_callbacks(void) static void invoke_rcu_callbacks(void) { have_rcu_kthread_work = 1; - wake_up(&rcu_kthread_wq); + if (rcu_kthread_task != NULL) + wake_up(&rcu_kthread_wq); } #ifdef CONFIG_RCU_TRACE @@ -943,12 +978,16 @@ early_initcall(rcu_spawn_kthreads); #else /* #ifdef CONFIG_RCU_BOOST */ +/* Hold off callback invocation until early_initcall() time. */ +static int rcu_scheduler_fully_active __read_mostly; + /* * Start up softirq processing of callbacks. */ void invoke_rcu_callbacks(void) { - raise_softirq(RCU_SOFTIRQ); + if (rcu_scheduler_fully_active) + raise_softirq(RCU_SOFTIRQ); } #ifdef CONFIG_RCU_TRACE @@ -963,10 +1002,14 @@ static bool rcu_is_callbacks_kthread(void) #endif /* #ifdef CONFIG_RCU_TRACE */ -void rcu_init(void) +static int __init rcu_scheduler_really_started(void) { + rcu_scheduler_fully_active = 1; open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + raise_softirq(RCU_SOFTIRQ); /* Invoke any callbacks from early boot. */ + return 0; } +early_initcall(rcu_scheduler_really_started); #endif /* #else #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index a58ac285fc69..a89b381a8c6e 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -65,7 +65,10 @@ static int fqs_duration; /* Duration of bursts (us), 0 to disable. */ static int fqs_holdoff; /* Hold time within burst (us). */ static int fqs_stutter = 3; /* Wait time between bursts (s). */ static int onoff_interval; /* Wait time between CPU hotplugs, 0=disable. */ +static int onoff_holdoff; /* Seconds after boot before CPU hotplugs. */ static int shutdown_secs; /* Shutdown time (s). <=0 for no shutdown. */ +static int stall_cpu; /* CPU-stall duration (s). 0 for no stall. */ +static int stall_cpu_holdoff = 10; /* Time to wait until stall (s). */ static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */ static int test_boost_interval = 7; /* Interval between boost tests, seconds. */ static int test_boost_duration = 4; /* Duration of each boost test, seconds. */ @@ -95,8 +98,14 @@ module_param(fqs_stutter, int, 0444); MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)"); module_param(onoff_interval, int, 0444); MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable"); +module_param(onoff_holdoff, int, 0444); +MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)"); module_param(shutdown_secs, int, 0444); MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable."); +module_param(stall_cpu, int, 0444); +MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable."); +module_param(stall_cpu_holdoff, int, 0444); +MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s)."); module_param(test_boost, int, 0444); MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); module_param(test_boost_interval, int, 0444); @@ -129,6 +138,7 @@ static struct task_struct *shutdown_task; #ifdef CONFIG_HOTPLUG_CPU static struct task_struct *onoff_task; #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static struct task_struct *stall_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -990,12 +1000,12 @@ static void rcu_torture_timer(unsigned long unused) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); return; } + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); spin_lock(&rand_lock); @@ -1053,13 +1063,13 @@ rcu_torture_reader(void *arg) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); - do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); schedule_timeout_interruptible(HZ); continue; } + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); cur_ops->read_delay(&rand); @@ -1300,13 +1310,13 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " "test_boost=%d/%d test_boost_interval=%d " "test_boost_duration=%d shutdown_secs=%d " - "onoff_interval=%d\n", + "onoff_interval=%d onoff_holdoff=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, test_boost, cur_ops->can_boost, test_boost_interval, test_boost_duration, shutdown_secs, - onoff_interval); + onoff_interval, onoff_holdoff); } static struct notifier_block rcutorture_shutdown_nb = { @@ -1410,6 +1420,11 @@ rcu_torture_onoff(void *arg) for_each_online_cpu(cpu) maxcpu = cpu; WARN_ON(maxcpu < 0); + if (onoff_holdoff > 0) { + VERBOSE_PRINTK_STRING("rcu_torture_onoff begin holdoff"); + schedule_timeout_interruptible(onoff_holdoff * HZ); + VERBOSE_PRINTK_STRING("rcu_torture_onoff end holdoff"); + } while (!kthread_should_stop()) { cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { @@ -1450,12 +1465,15 @@ rcu_torture_onoff(void *arg) static int __cpuinit rcu_torture_onoff_init(void) { + int ret; + if (onoff_interval <= 0) return 0; onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff"); if (IS_ERR(onoff_task)) { + ret = PTR_ERR(onoff_task); onoff_task = NULL; - return PTR_ERR(onoff_task); + return ret; } return 0; } @@ -1481,6 +1499,63 @@ static void rcu_torture_onoff_cleanup(void) #endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ +/* + * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then + * induces a CPU stall for the time specified by stall_cpu. + */ +static int __cpuinit rcu_torture_stall(void *args) +{ + unsigned long stop_at; + + VERBOSE_PRINTK_STRING("rcu_torture_stall task started"); + if (stall_cpu_holdoff > 0) { + VERBOSE_PRINTK_STRING("rcu_torture_stall begin holdoff"); + schedule_timeout_interruptible(stall_cpu_holdoff * HZ); + VERBOSE_PRINTK_STRING("rcu_torture_stall end holdoff"); + } + if (!kthread_should_stop()) { + stop_at = get_seconds() + stall_cpu; + /* RCU CPU stall is expected behavior in following code. */ + printk(KERN_ALERT "rcu_torture_stall start.\n"); + rcu_read_lock(); + preempt_disable(); + while (ULONG_CMP_LT(get_seconds(), stop_at)) + continue; /* Induce RCU CPU stall warning. */ + preempt_enable(); + rcu_read_unlock(); + printk(KERN_ALERT "rcu_torture_stall end.\n"); + } + rcutorture_shutdown_absorb("rcu_torture_stall"); + while (!kthread_should_stop()) + schedule_timeout_interruptible(10 * HZ); + return 0; +} + +/* Spawn CPU-stall kthread, if stall_cpu specified. */ +static int __init rcu_torture_stall_init(void) +{ + int ret; + + if (stall_cpu <= 0) + return 0; + stall_task = kthread_run(rcu_torture_stall, NULL, "rcu_torture_stall"); + if (IS_ERR(stall_task)) { + ret = PTR_ERR(stall_task); + stall_task = NULL; + return ret; + } + return 0; +} + +/* Clean up after the CPU-stall kthread, if one was spawned. */ +static void rcu_torture_stall_cleanup(void) +{ + if (stall_task == NULL) + return; + VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task."); + kthread_stop(stall_task); +} + static int rcutorture_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1523,6 +1598,7 @@ rcu_torture_cleanup(void) fullstop = FULLSTOP_RMMOD; mutex_unlock(&fullstop_mutex); unregister_reboot_notifier(&rcutorture_shutdown_nb); + rcu_torture_stall_cleanup(); if (stutter_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); kthread_stop(stutter_task); @@ -1602,6 +1678,10 @@ rcu_torture_cleanup(void) cur_ops->cleanup(); if (atomic_read(&n_rcu_torture_error)) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); + else if (n_online_successes != n_online_attempts || + n_offline_successes != n_offline_attempts) + rcu_torture_print_module_parms(cur_ops, + "End of test: RCU_HOTPLUG"); else rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS"); } @@ -1819,6 +1899,7 @@ rcu_torture_init(void) } rcu_torture_onoff_init(); register_reboot_notifier(&rcutorture_shutdown_nb); + rcu_torture_stall_init(); rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); return 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6c4a6722abfd..1050d6d3922c 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -50,6 +50,8 @@ #include <linux/wait.h> #include <linux/kthread.h> #include <linux/prefetch.h> +#include <linux/delay.h> +#include <linux/stop_machine.h> #include "rcutree.h" #include <trace/events/rcu.h> @@ -196,7 +198,7 @@ void rcu_note_context_switch(int cpu) EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = DYNTICK_TASK_NESTING, + .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), }; @@ -208,8 +210,11 @@ module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); -int rcu_cpu_stall_suppress __read_mostly; +int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ +int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; + module_param(rcu_cpu_stall_suppress, int, 0644); +module_param(rcu_cpu_stall_timeout, int, 0644); static void force_quiescent_state(struct rcu_state *rsp, int relaxed); static int rcu_pending(int cpu); @@ -301,8 +306,6 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) return &rsp->node[0]; } -#ifdef CONFIG_SMP - /* * If the specified CPU is offline, tell the caller that it is in * a quiescent state. Otherwise, whack it with a reschedule IPI. @@ -317,30 +320,21 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) static int rcu_implicit_offline_qs(struct rcu_data *rdp) { /* - * If the CPU is offline, it is in a quiescent state. We can - * trust its state not to change because interrupts are disabled. + * If the CPU is offline for more than a jiffy, it is in a quiescent + * state. We can trust its state not to change because interrupts + * are disabled. The reason for the jiffy's worth of slack is to + * handle CPUs initializing on the way up and finding their way + * to the idle loop on the way down. */ - if (cpu_is_offline(rdp->cpu)) { + if (cpu_is_offline(rdp->cpu) && + ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) { trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); rdp->offline_fqs++; return 1; } - - /* - * The CPU is online, so send it a reschedule IPI. This forces - * it through the scheduler, and (inefficiently) also handles cases - * where idle loops fail to inform RCU about the CPU being idle. - */ - if (rdp->cpu != smp_processor_id()) - smp_send_reschedule(rdp->cpu); - else - set_need_resched(); - rdp->resched_ipi++; return 0; } -#endif /* #ifdef CONFIG_SMP */ - /* * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle * @@ -366,6 +360,17 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) atomic_inc(&rdtp->dynticks); smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + + /* + * The idle task is not permitted to enter the idle loop while + * in an RCU read-side critical section. + */ + rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), + "Illegal idle entry in RCU read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), + "Illegal idle entry in RCU-bh read-side critical section."); + rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), + "Illegal idle entry in RCU-sched read-side critical section."); } /** @@ -389,10 +394,15 @@ void rcu_idle_enter(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); oldval = rdtp->dynticks_nesting; - rdtp->dynticks_nesting = 0; + WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) + rdtp->dynticks_nesting = 0; + else + rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; rcu_idle_enter_common(rdtp, oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle @@ -462,7 +472,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) * Exit idle mode, in other words, -enter- the mode in which RCU * read-side critical sections can occur. * - * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NESTING to + * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NEST to * allow for the possibility of usermode upcalls messing up our count * of interrupt nesting level during the busy period that is just * now starting. @@ -476,11 +486,15 @@ void rcu_idle_exit(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(oldval != 0); - rdtp->dynticks_nesting = DYNTICK_TASK_NESTING; + WARN_ON_ONCE(oldval < 0); + if (oldval & DYNTICK_TASK_NEST_MASK) + rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; rcu_idle_exit_common(rdtp, oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle @@ -581,6 +595,49 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Is the current CPU online? Disable preemption to avoid false positives + * that could otherwise happen due to the current CPU number being sampled, + * this task being preempted, its old CPU being taken offline, resuming + * on some other CPU, then determining that its old CPU is now offline. + * It is OK to use RCU on an offline processor during initial boot, hence + * the check for rcu_scheduler_fully_active. Note also that it is OK + * for a CPU coming online to use RCU for one jiffy prior to marking itself + * online in the cpu_online_mask. Similarly, it is OK for a CPU going + * offline to continue to use RCU for one jiffy after marking itself + * offline in the cpu_online_mask. This leniency is necessary given the + * non-atomic nature of the online and offline processing, for example, + * the fact that a CPU enters the scheduler after completing the CPU_DYING + * notifiers. + * + * This is also why RCU internally marks CPUs online during the + * CPU_UP_PREPARE phase and offline during the CPU_DEAD phase. + * + * Disable checking if in an NMI handler because we cannot safely report + * errors from NMI handlers anyway. + */ +bool rcu_lockdep_current_cpu_online(void) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + bool ret; + + if (in_nmi()) + return 1; + preempt_disable(); + rdp = &__get_cpu_var(rcu_sched_data); + rnp = rdp->mynode; + ret = (rdp->grpmask & rnp->qsmaskinit) || + !rcu_scheduler_fully_active; + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + #endif /* #ifdef CONFIG_PROVE_RCU */ /** @@ -595,8 +652,6 @@ int rcu_is_cpu_rrupt_from_idle(void) return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1; } -#ifdef CONFIG_SMP - /* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU @@ -640,12 +695,28 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return rcu_implicit_offline_qs(rdp); } -#endif /* #ifdef CONFIG_SMP */ +static int jiffies_till_stall_check(void) +{ + int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); + + /* + * Limit check must be consistent with the Kconfig limits + * for CONFIG_RCU_CPU_STALL_TIMEOUT. + */ + if (till_stall_check < 3) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; + till_stall_check = 3; + } else if (till_stall_check > 300) { + ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; + till_stall_check = 300; + } + return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; +} static void record_gp_stall_check_time(struct rcu_state *rsp) { rsp->gp_start = jiffies; - rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK; + rsp->jiffies_stall = jiffies + jiffies_till_stall_check(); } static void print_other_cpu_stall(struct rcu_state *rsp) @@ -664,13 +735,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK; - - /* - * Now rat on any tasks that got kicked up to the root rcu_node - * due to CPU offlining. - */ - ndetected = rcu_print_task_stall(rnp); + rsp->jiffies_stall = jiffies + 3 * jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -678,8 +743,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {", + printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks:", rsp->name); + print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); ndetected += rcu_print_task_stall(rnp); @@ -688,11 +754,22 @@ static void print_other_cpu_stall(struct rcu_state *rsp) continue; for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) if (rnp->qsmask & (1UL << cpu)) { - printk(" %d", rnp->grplo + cpu); + print_cpu_stall_info(rsp, rnp->grplo + cpu); ndetected++; } } - printk("} (detected by %d, t=%ld jiffies)\n", + + /* + * Now rat on any tasks that got kicked up to the root rcu_node + * due to CPU offlining. + */ + rnp = rcu_get_root(rsp); + raw_spin_lock_irqsave(&rnp->lock, flags); + ndetected = rcu_print_task_stall(rnp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + print_cpu_stall_info_end(); + printk(KERN_CONT "(detected by %d, t=%ld jiffies)\n", smp_processor_id(), (long)(jiffies - rsp->gp_start)); if (ndetected == 0) printk(KERN_ERR "INFO: Stall ended before state dump start\n"); @@ -716,15 +793,18 @@ static void print_cpu_stall(struct rcu_state *rsp) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n", - rsp->name, smp_processor_id(), jiffies - rsp->gp_start); + printk(KERN_ERR "INFO: %s self-detected stall on CPU", rsp->name); + print_cpu_stall_info_begin(); + print_cpu_stall_info(rsp, smp_processor_id()); + print_cpu_stall_info_end(); + printk(KERN_CONT " (t=%lu jiffies)\n", jiffies - rsp->gp_start); if (!trigger_all_cpu_backtrace()) dump_stack(); raw_spin_lock_irqsave(&rnp->lock, flags); if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall)) - rsp->jiffies_stall = - jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + rsp->jiffies_stall = jiffies + + 3 * jiffies_till_stall_check() + 3; raw_spin_unlock_irqrestore(&rnp->lock, flags); set_need_resched(); /* kick ourselves to get things going. */ @@ -807,6 +887,7 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rdp->passed_quiesce = 0; } else rdp->qs_pending = 0; + zero_cpu_stall_ticks(rdp); } } @@ -943,6 +1024,10 @@ rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat * in preparation for detecting the next grace period. The caller must hold * the root node's ->lock, which is released before return. Hard irqs must * be disabled. + * + * Note that it is legal for a dying CPU (which is marked as offline) to + * invoke this function. This can happen when the dying CPU reports its + * quiescent state. */ static void rcu_start_gp(struct rcu_state *rsp, unsigned long flags) @@ -980,26 +1065,8 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); - - /* Special-case the common single-level case. */ - if (NUM_RCU_NODES == 1) { - rcu_preempt_check_blocked_tasks(rnp); - rnp->qsmask = rnp->qsmaskinit; - rnp->gpnum = rsp->gpnum; - rnp->completed = rsp->completed; - rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state OK */ - rcu_start_gp_per_cpu(rsp, rnp, rdp); - rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gpnum, - rnp->level, rnp->grplo, - rnp->grphi, rnp->qsmask); - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - raw_spin_unlock(&rnp->lock); /* leave irqs disabled. */ - /* Exclude any concurrent CPU-hotplug operations. */ raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ @@ -1245,53 +1312,115 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) /* * Move a dying CPU's RCU callbacks to online CPU's callback list. - * Synchronization is not required because this function executes - * in stop_machine() context. + * Also record a quiescent state for this CPU for the current grace period. + * Synchronization and interrupt disabling are not required because + * this function executes in stop_machine() context. Therefore, cleanup + * operations that might block must be done later from the CPU_DEAD + * notifier. + * + * Note that the outgoing CPU's bit has already been cleared in the + * cpu_online_mask. This allows us to randomly pick a callback + * destination from the bits set in that mask. */ -static void rcu_send_cbs_to_online(struct rcu_state *rsp) +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { int i; - /* current DYING CPU is cleared in the cpu_online_mask */ + unsigned long mask; int receive_cpu = cpumask_any(cpu_online_mask); struct rcu_data *rdp = this_cpu_ptr(rsp->rda); struct rcu_data *receive_rdp = per_cpu_ptr(rsp->rda, receive_cpu); + RCU_TRACE(struct rcu_node *rnp = rdp->mynode); /* For dying CPU. */ + + /* First, adjust the counts. */ + if (rdp->nxtlist != NULL) { + receive_rdp->qlen_lazy += rdp->qlen_lazy; + receive_rdp->qlen += rdp->qlen; + rdp->qlen_lazy = 0; + rdp->qlen = 0; + } - if (rdp->nxtlist == NULL) - return; /* irqs disabled, so comparison is stable. */ + /* + * Next, move ready-to-invoke callbacks to be invoked on some + * other CPU. These will not be required to pass through another + * grace period: They are done, regardless of CPU. + */ + if (rdp->nxtlist != NULL && + rdp->nxttail[RCU_DONE_TAIL] != &rdp->nxtlist) { + struct rcu_head *oldhead; + struct rcu_head **oldtail; + struct rcu_head **newtail; + + oldhead = rdp->nxtlist; + oldtail = receive_rdp->nxttail[RCU_DONE_TAIL]; + rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = *oldtail; + *receive_rdp->nxttail[RCU_DONE_TAIL] = oldhead; + newtail = rdp->nxttail[RCU_DONE_TAIL]; + for (i = RCU_DONE_TAIL; i < RCU_NEXT_SIZE; i++) { + if (receive_rdp->nxttail[i] == oldtail) + receive_rdp->nxttail[i] = newtail; + if (rdp->nxttail[i] == newtail) + rdp->nxttail[i] = &rdp->nxtlist; + } + } - *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; - receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - receive_rdp->qlen += rdp->qlen; - receive_rdp->n_cbs_adopted += rdp->qlen; - rdp->n_cbs_orphaned += rdp->qlen; + /* + * Finally, put the rest of the callbacks at the end of the list. + * The ones that made it partway through get to start over: We + * cannot assume that grace periods are synchronized across CPUs. + * (We could splice RCU_WAIT_TAIL into RCU_NEXT_READY_TAIL, but + * this does not seem compelling. Not yet, anyway.) + */ + if (rdp->nxtlist != NULL) { + *receive_rdp->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; + receive_rdp->nxttail[RCU_NEXT_TAIL] = + rdp->nxttail[RCU_NEXT_TAIL]; + receive_rdp->n_cbs_adopted += rdp->qlen; + rdp->n_cbs_orphaned += rdp->qlen; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + } - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; - rdp->qlen = 0; + /* + * Record a quiescent state for the dying CPU. This is safe + * only because we have already cleared out the callbacks. + * (Otherwise, the RCU core might try to schedule the invocation + * of callbacks on this now-offline CPU, which would be bad.) + */ + mask = rdp->grpmask; /* rnp->grplo is constant. */ + trace_rcu_grace_period(rsp->name, + rnp->gpnum + 1 - !!(rnp->qsmask & mask), + "cpuofl"); + rcu_report_qs_rdp(smp_processor_id(), rsp, rdp, rsp->gpnum); + /* Note that rcu_report_qs_rdp() might call trace_rcu_grace_period(). */ } /* - * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy - * and move all callbacks from the outgoing CPU to the current one. + * The CPU has been completely removed, and some other CPU is reporting + * this fact from process context. Do the remainder of the cleanup. * There can only be one CPU hotplug operation at a time, so no other * CPU can be attempting to update rcu_cpu_kthread_task. */ -static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { unsigned long flags; unsigned long mask; int need_report = 0; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp; + struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rnp. */ + /* Adjust any no-longer-needed kthreads. */ rcu_stop_cpu_kthread(cpu); + rcu_node_kthread_setaffinity(rnp, -1); + + /* Remove the dying CPU from the bitmasks in the rcu_node hierarchy. */ /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ - rnp = rdp->mynode; /* this is the outgoing CPU's rnp. */ mask = rdp->grpmask; /* rnp->grplo is constant. */ do { raw_spin_lock(&rnp->lock); /* irqs already disabled. */ @@ -1299,20 +1428,11 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) if (rnp->qsmaskinit != 0) { if (rnp != rdp->mynode) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - else - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - - !!(rnp->qsmask & mask), - "cpuofl"); break; } - if (rnp == rdp->mynode) { - trace_rcu_grace_period(rsp->name, - rnp->gpnum + 1 - - !!(rnp->qsmask & mask), - "cpuofl"); + if (rnp == rdp->mynode) need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp); - } else + else raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ mask = rnp->grpmask; rnp = rnp->parent; @@ -1332,29 +1452,15 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); - rcu_node_kthread_setaffinity(rnp, -1); -} - -/* - * Remove the specified CPU from the RCU hierarchy and move any pending - * callbacks that it might have to the current CPU. This code assumes - * that at least one CPU in the system will remain running at all times. - * Any attempt to offline -all- CPUs is likely to strand RCU callbacks. - */ -static void rcu_offline_cpu(int cpu) -{ - __rcu_offline_cpu(cpu, &rcu_sched_state); - __rcu_offline_cpu(cpu, &rcu_bh_state); - rcu_preempt_offline_cpu(cpu); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_send_cbs_to_online(struct rcu_state *rsp) +static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { } -static void rcu_offline_cpu(int cpu) +static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { } @@ -1368,11 +1474,11 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; struct rcu_head *next, *list, **tail; - int bl, count; + int bl, count, count_lazy; /* If no callbacks are ready, just return.*/ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { - trace_rcu_batch_start(rsp->name, 0, 0); + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0); trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -1384,8 +1490,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) * races with call_rcu() from interrupt handlers. */ local_irq_save(flags); + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); bl = rdp->blimit; - trace_rcu_batch_start(rsp->name, rdp->qlen, bl); + trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl); list = rdp->nxtlist; rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; *rdp->nxttail[RCU_DONE_TAIL] = NULL; @@ -1396,12 +1503,13 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_restore(flags); /* Invoke callbacks. */ - count = 0; + count = count_lazy = 0; while (list) { next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - __rcu_reclaim(rsp->name, list); + if (__rcu_reclaim(rsp->name, list)) + count_lazy++; list = next; /* Stop only if limit reached and CPU has something to do. */ if (++count >= bl && @@ -1416,6 +1524,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rcu_is_callbacks_kthread()); /* Update count, and requeue any remaining callbacks. */ + rdp->qlen_lazy -= count_lazy; rdp->qlen -= count; rdp->n_cbs_invoked += count; if (list != NULL) { @@ -1458,6 +1567,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) void rcu_check_callbacks(int cpu, int user) { trace_rcu_utilization("Start scheduler-tick"); + increment_cpu_stall_ticks(); if (user || rcu_is_cpu_rrupt_from_idle()) { /* @@ -1492,8 +1602,6 @@ void rcu_check_callbacks(int cpu, int user) trace_rcu_utilization("End scheduler-tick"); } -#ifdef CONFIG_SMP - /* * Scan the leaf rcu_node structures, processing dyntick state for any that * have not yet encountered a quiescent state, using the function specified. @@ -1616,15 +1724,6 @@ unlock_fqs_ret: trace_rcu_utilization("End fqs"); } -#else /* #ifdef CONFIG_SMP */ - -static void force_quiescent_state(struct rcu_state *rsp, int relaxed) -{ - set_need_resched(); -} - -#endif /* #else #ifdef CONFIG_SMP */ - /* * This does the RCU core processing work for the specified rcu_state * and rcu_data structures. This may be called only from the CPU to @@ -1702,11 +1801,12 @@ static void invoke_rcu_core(void) static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), - struct rcu_state *rsp) + struct rcu_state *rsp, bool lazy) { unsigned long flags; struct rcu_data *rdp; + WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */ debug_rcu_head_queue(head); head->func = func; head->next = NULL; @@ -1720,18 +1820,21 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), * a quiescent state betweentimes. */ local_irq_save(flags); + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ *rdp->nxttail[RCU_NEXT_TAIL] = head; rdp->nxttail[RCU_NEXT_TAIL] = &head->next; rdp->qlen++; + if (lazy) + rdp->qlen_lazy++; if (__is_kfree_rcu_offset((unsigned long)func)) trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, - rdp->qlen); + rdp->qlen_lazy, rdp->qlen); else - trace_rcu_callback(rsp->name, head, rdp->qlen); + trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); /* If interrupts were disabled, don't dive into RCU core. */ if (irqs_disabled_flags(flags)) { @@ -1778,16 +1881,16 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), */ void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_sched_state); + __call_rcu(head, func, &rcu_sched_state, 0); } EXPORT_SYMBOL_GPL(call_rcu_sched); /* - * Queue an RCU for invocation after a quicker grace period. + * Queue an RCU callback for invocation after a quicker grace period. */ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_bh_state); + __call_rcu(head, func, &rcu_bh_state, 0); } EXPORT_SYMBOL_GPL(call_rcu_bh); @@ -1816,6 +1919,10 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); */ void synchronize_sched(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU-sched read-side critical section"); if (rcu_blocking_is_gp()) return; wait_rcu_gp(call_rcu_sched); @@ -1833,12 +1940,137 @@ EXPORT_SYMBOL_GPL(synchronize_sched); */ void synchronize_rcu_bh(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); if (rcu_blocking_is_gp()) return; wait_rcu_gp(call_rcu_bh); } EXPORT_SYMBOL_GPL(synchronize_rcu_bh); +static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); +static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); + +static int synchronize_sched_expedited_cpu_stop(void *data) +{ + /* + * There must be a full memory barrier on each affected CPU + * between the time that try_stop_cpus() is called and the + * time that it returns. + * + * In the current initial implementation of cpu_stop, the + * above condition is already met when the control reaches + * this point and the following smp_mb() is not strictly + * necessary. Do smp_mb() anyway for documentation and + * robustness against future implementation changes. + */ + smp_mb(); /* See above comment block. */ + return 0; +} + +/** + * synchronize_sched_expedited - Brute-force RCU-sched grace period + * + * Wait for an RCU-sched grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_sched_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_sched() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. + * + * This implementation can be thought of as an application of ticket + * locking to RCU, with sync_sched_expedited_started and + * sync_sched_expedited_done taking on the roles of the halves + * of the ticket-lock word. Each task atomically increments + * sync_sched_expedited_started upon entry, snapshotting the old value, + * then attempts to stop all the CPUs. If this succeeds, then each + * CPU will have executed a context switch, resulting in an RCU-sched + * grace period. We are then done, so we use atomic_cmpxchg() to + * update sync_sched_expedited_done to match our snapshot -- but + * only if someone else has not already advanced past our snapshot. + * + * On the other hand, if try_stop_cpus() fails, we check the value + * of sync_sched_expedited_done. If it has advanced past our + * initial snapshot, then someone else must have forced a grace period + * some time after we took our snapshot. In this case, our work is + * done for us, and we can simply return. Otherwise, we try again, + * but keep our initial snapshot for purposes of checking for someone + * doing our work for us. + * + * If we fail too many times in a row, we fall back to synchronize_sched(). + */ +void synchronize_sched_expedited(void) +{ + int firstsnap, s, snap, trycount = 0; + + /* Note that atomic_inc_return() implies full memory barrier. */ + firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started); + get_online_cpus(); + WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); + + /* + * Each pass through the following loop attempts to force a + * context switch on each CPU. + */ + while (try_stop_cpus(cpu_online_mask, + synchronize_sched_expedited_cpu_stop, + NULL) == -EAGAIN) { + put_online_cpus(); + + /* No joy, try again later. Or just synchronize_sched(). */ + if (trycount++ < 10) + udelay(trycount * num_online_cpus()); + else { + synchronize_sched(); + return; + } + + /* Check to see if someone else did our work for us. */ + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) { + smp_mb(); /* ensure test happens before caller kfree */ + return; + } + + /* + * Refetching sync_sched_expedited_started allows later + * callers to piggyback on our grace period. We subtract + * 1 to get the same token that the last incrementer got. + * We retry after they started, so our grace period works + * for them, and they started after our first try, so their + * grace period works for us. + */ + get_online_cpus(); + snap = atomic_read(&sync_sched_expedited_started); + smp_mb(); /* ensure read is before try_stop_cpus(). */ + } + + /* + * Everyone up to our most recent fetch is covered by our grace + * period. Update the counter, but only if our work is still + * relevant -- which it won't be if someone who started later + * than we did beat us to the punch. + */ + do { + s = atomic_read(&sync_sched_expedited_done); + if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) { + smp_mb(); /* ensure test happens before caller kfree */ + break; + } + } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s); + + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + /* * Check to see if there is any immediate RCU-related work to be done * by the current CPU, for the specified type of RCU, returning 1 if so. @@ -1932,7 +2164,7 @@ static int rcu_cpu_has_callbacks(int cpu) /* RCU callbacks either ready or pending? */ return per_cpu(rcu_sched_data, cpu).nxtlist || per_cpu(rcu_bh_data, cpu).nxtlist || - rcu_preempt_needs_cpu(cpu); + rcu_preempt_cpu_has_callbacks(cpu); } static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; @@ -2027,9 +2259,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->nxtlist = NULL; for (i = 0; i < RCU_NEXT_SIZE; i++) rdp->nxttail[i] = &rdp->nxtlist; + rdp->qlen_lazy = 0; rdp->qlen = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); - WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING); + WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); rdp->cpu = cpu; rdp->rsp = rsp; @@ -2057,7 +2290,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; - rdp->dynticks->dynticks_nesting = DYNTICK_TASK_NESTING; + rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); rcu_prepare_for_idle_init(cpu); @@ -2139,16 +2372,18 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, * touch any data without introducing corruption. We send the * dying CPU's callbacks to an arbitrarily chosen online CPU. */ - rcu_send_cbs_to_online(&rcu_bh_state); - rcu_send_cbs_to_online(&rcu_sched_state); - rcu_preempt_send_cbs_to_online(); + rcu_cleanup_dying_cpu(&rcu_bh_state); + rcu_cleanup_dying_cpu(&rcu_sched_state); + rcu_preempt_cleanup_dying_cpu(); rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - rcu_offline_cpu(cpu); + rcu_cleanup_dead_cpu(cpu, &rcu_bh_state); + rcu_cleanup_dead_cpu(cpu, &rcu_sched_state); + rcu_preempt_cleanup_dead_cpu(cpu); break; default: break; diff --git a/kernel/rcutree.h b/kernel/rcutree.h index fddff92d6676..cdd1be0a4072 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -239,6 +239,12 @@ struct rcu_data { bool preemptible; /* Preemptible RCU? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + unsigned long ticks_this_gp; /* The number of scheduling-clock */ + /* ticks this CPU has handled */ + /* during and after the last grace */ + /* period it is aware of. */ +#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ /* 2) batch handling */ /* @@ -265,7 +271,8 @@ struct rcu_data { */ struct rcu_head *nxtlist; struct rcu_head **nxttail[RCU_NEXT_SIZE]; - long qlen; /* # of queued callbacks */ + long qlen_lazy; /* # of lazy queued callbacks */ + long qlen; /* # of queued callbacks, incl lazy */ long qlen_last_fqs_check; /* qlen at last check for QS forcing */ unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */ @@ -282,7 +289,6 @@ struct rcu_data { /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ unsigned long offline_fqs; /* Kicked due to being offline. */ - unsigned long resched_ipi; /* Sent a resched IPI. */ /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ @@ -313,12 +319,6 @@ struct rcu_data { #else #define RCU_STALL_DELAY_DELTA 0 #endif - -#define RCU_SECONDS_TILL_STALL_CHECK (CONFIG_RCU_CPU_STALL_TIMEOUT * HZ + \ - RCU_STALL_DELAY_DELTA) - /* for rsp->jiffies_stall */ -#define RCU_SECONDS_TILL_STALL_RECHECK (3 * RCU_SECONDS_TILL_STALL_CHECK + 30) - /* for rsp->jiffies_stall */ #define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */ /* to take at least one */ /* scheduling clock irq */ @@ -438,8 +438,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp); -static void rcu_preempt_offline_cpu(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +static void rcu_preempt_cleanup_dead_cpu(int cpu); static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); @@ -448,9 +448,9 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); -static int rcu_preempt_needs_cpu(int cpu); +static int rcu_preempt_cpu_has_callbacks(int cpu); static void __cpuinit rcu_preempt_init_percpu_data(int cpu); -static void rcu_preempt_send_cbs_to_online(void); +static void rcu_preempt_cleanup_dying_cpu(void); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); @@ -471,5 +471,10 @@ static void __cpuinit rcu_prepare_kthreads(int cpu); static void rcu_prepare_for_idle_init(int cpu); static void rcu_cleanup_after_idle(int cpu); static void rcu_prepare_for_idle(int cpu); +static void print_cpu_stall_info_begin(void); +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); +static void print_cpu_stall_info_end(void); +static void zero_cpu_stall_ticks(struct rcu_data *rdp); +static void increment_cpu_stall_ticks(void); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 8bb35d73e1f9..c023464816be 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -25,7 +25,6 @@ */ #include <linux/delay.h> -#include <linux/stop_machine.h> #define RCU_KTHREAD_PRIO 1 @@ -63,7 +62,10 @@ static void __init rcu_bootup_announce_oddness(void) printk(KERN_INFO "\tRCU torture testing starts during boot.\n"); #endif #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE) - printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n"); + printk(KERN_INFO "\tDump stacks of tasks blocking RCU-preempt GP.\n"); +#endif +#if defined(CONFIG_RCU_CPU_STALL_INFO) + printk(KERN_INFO "\tAdditional per-CPU info printed with stalls.\n"); #endif #if NUM_RCU_LVL_4 != 0 printk(KERN_INFO "\tExperimental four-level hierarchy is enabled.\n"); @@ -490,6 +492,31 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) #endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */ +#ifdef CONFIG_RCU_CPU_STALL_INFO + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ + printk(KERN_ERR "\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", + rnp->level, rnp->grplo, rnp->grphi); +} + +static void rcu_print_task_stall_end(void) +{ + printk(KERN_CONT "\n"); +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void rcu_print_task_stall_begin(struct rcu_node *rnp) +{ +} + +static void rcu_print_task_stall_end(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ + /* * Scan the current list of tasks blocked within RCU read-side critical * sections, printing out the tid of each. @@ -501,12 +528,14 @@ static int rcu_print_task_stall(struct rcu_node *rnp) if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; + rcu_print_task_stall_begin(rnp); t = list_entry(rnp->gp_tasks, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { - printk(" P%d", t->pid); + printk(KERN_CONT " P%d", t->pid); ndetected++; } + rcu_print_task_stall_end(); return ndetected; } @@ -581,7 +610,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, * absolutely necessary, but this is a good performance/complexity * tradeoff. */ - if (rcu_preempt_blocked_readers_cgp(rnp)) + if (rcu_preempt_blocked_readers_cgp(rnp) && rnp->qsmask == 0) retval |= RCU_OFL_TASKS_NORM_GP; if (rcu_preempted_readers_exp(rnp)) retval |= RCU_OFL_TASKS_EXP_GP; @@ -618,16 +647,16 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, return retval; } +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Do CPU-offline processing for preemptible RCU. */ -static void rcu_preempt_offline_cpu(int cpu) +static void rcu_preempt_cleanup_dead_cpu(int cpu) { - __rcu_offline_cpu(cpu, &rcu_preempt_state); + rcu_cleanup_dead_cpu(cpu, &rcu_preempt_state); } -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the corresponding CPU's rcu_node structure, @@ -671,10 +700,24 @@ static void rcu_preempt_do_callbacks(void) */ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_preempt_state); + __call_rcu(head, func, &rcu_preempt_state, 0); } EXPORT_SYMBOL_GPL(call_rcu); +/* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_preempt_state, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + /** * synchronize_rcu - wait until a grace period has elapsed. * @@ -688,6 +731,10 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); if (!rcu_scheduler_active) return; wait_rcu_gp(call_rcu); @@ -788,10 +835,22 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */ } -/* - * Wait for an rcu-preempt grace period, but expedite it. The basic idea - * is to invoke synchronize_sched_expedited() to push all the tasks to - * the ->blkd_tasks lists and wait for this list to drain. +/** + * synchronize_rcu_expedited - Brute-force RCU grace period + * + * Wait for an RCU-preempt grace period, but expedite it. The basic + * idea is to invoke synchronize_sched_expedited() to push all the tasks to + * the ->blkd_tasks lists and wait for this list to drain. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. + * In fact, if you are using synchronize_rcu_expedited() in a loop, + * please restructure your code to batch your updates, and then Use a + * single synchronize_rcu() instead. + * + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. */ void synchronize_rcu_expedited(void) { @@ -869,9 +928,9 @@ static int rcu_preempt_pending(int cpu) } /* - * Does preemptible RCU need the CPU to stay out of dynticks mode? + * Does preemptible RCU have callbacks on this CPU? */ -static int rcu_preempt_needs_cpu(int cpu) +static int rcu_preempt_cpu_has_callbacks(int cpu) { return !!per_cpu(rcu_preempt_data, cpu).nxtlist; } @@ -894,11 +953,12 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Move preemptible RCU's callbacks from dying CPU to other online CPU. + * Move preemptible RCU's callbacks from dying CPU to other online CPU + * and record a quiescent state. */ -static void rcu_preempt_send_cbs_to_online(void) +static void rcu_preempt_cleanup_dying_cpu(void) { - rcu_send_cbs_to_online(&rcu_preempt_state); + rcu_cleanup_dying_cpu(&rcu_preempt_state); } /* @@ -1034,16 +1094,16 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, return 0; } +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + /* * Because preemptible RCU does not exist, it never needs CPU-offline * processing. */ -static void rcu_preempt_offline_cpu(int cpu) +static void rcu_preempt_cleanup_dead_cpu(int cpu) { } -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - /* * Because preemptible RCU does not exist, it never has any callbacks * to check. @@ -1061,6 +1121,22 @@ static void rcu_preempt_process_callbacks(void) } /* + * Queue an RCU callback for lazy invocation after a grace period. + * This will likely be later named something like "call_rcu_lazy()", + * but this change will require some way of tagging the lazy RCU + * callbacks in the list of pending callbacks. Until then, this + * function may only be called from __kfree_rcu(). + * + * Because there is no preemptible RCU, we use RCU-sched instead. + */ +void kfree_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_sched_state, 1); +} +EXPORT_SYMBOL_GPL(kfree_call_rcu); + +/* * Wait for an rcu-preempt grace period, but make it happen quickly. * But because preemptible RCU does not exist, map to rcu-sched. */ @@ -1093,9 +1169,9 @@ static int rcu_preempt_pending(int cpu) } /* - * Because preemptible RCU does not exist, it never needs any CPU. + * Because preemptible RCU does not exist, it never has callbacks */ -static int rcu_preempt_needs_cpu(int cpu) +static int rcu_preempt_cpu_has_callbacks(int cpu) { return 0; } @@ -1119,9 +1195,9 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Because there is no preemptible RCU, there are no callbacks to move. + * Because there is no preemptible RCU, there is no cleanup to do. */ -static void rcu_preempt_send_cbs_to_online(void) +static void rcu_preempt_cleanup_dying_cpu(void) { } @@ -1823,132 +1899,6 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) #endif /* #else #ifdef CONFIG_RCU_BOOST */ -#ifndef CONFIG_SMP - -void synchronize_sched_expedited(void) -{ - cond_resched(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#else /* #ifndef CONFIG_SMP */ - -static atomic_t sync_sched_expedited_started = ATOMIC_INIT(0); -static atomic_t sync_sched_expedited_done = ATOMIC_INIT(0); - -static int synchronize_sched_expedited_cpu_stop(void *data) -{ - /* - * There must be a full memory barrier on each affected CPU - * between the time that try_stop_cpus() is called and the - * time that it returns. - * - * In the current initial implementation of cpu_stop, the - * above condition is already met when the control reaches - * this point and the following smp_mb() is not strictly - * necessary. Do smp_mb() anyway for documentation and - * robustness against future implementation changes. - */ - smp_mb(); /* See above comment block. */ - return 0; -} - -/* - * Wait for an rcu-sched grace period to elapse, but use "big hammer" - * approach to force grace period to end quickly. This consumes - * significant time on all CPUs, and is thus not recommended for - * any sort of common-case code. - * - * Note that it is illegal to call this function while holding any - * lock that is acquired by a CPU-hotplug notifier. Failing to - * observe this restriction will result in deadlock. - * - * This implementation can be thought of as an application of ticket - * locking to RCU, with sync_sched_expedited_started and - * sync_sched_expedited_done taking on the roles of the halves - * of the ticket-lock word. Each task atomically increments - * sync_sched_expedited_started upon entry, snapshotting the old value, - * then attempts to stop all the CPUs. If this succeeds, then each - * CPU will have executed a context switch, resulting in an RCU-sched - * grace period. We are then done, so we use atomic_cmpxchg() to - * update sync_sched_expedited_done to match our snapshot -- but - * only if someone else has not already advanced past our snapshot. - * - * On the other hand, if try_stop_cpus() fails, we check the value - * of sync_sched_expedited_done. If it has advanced past our - * initial snapshot, then someone else must have forced a grace period - * some time after we took our snapshot. In this case, our work is - * done for us, and we can simply return. Otherwise, we try again, - * but keep our initial snapshot for purposes of checking for someone - * doing our work for us. - * - * If we fail too many times in a row, we fall back to synchronize_sched(). - */ -void synchronize_sched_expedited(void) -{ - int firstsnap, s, snap, trycount = 0; - - /* Note that atomic_inc_return() implies full memory barrier. */ - firstsnap = snap = atomic_inc_return(&sync_sched_expedited_started); - get_online_cpus(); - - /* - * Each pass through the following loop attempts to force a - * context switch on each CPU. - */ - while (try_stop_cpus(cpu_online_mask, - synchronize_sched_expedited_cpu_stop, - NULL) == -EAGAIN) { - put_online_cpus(); - - /* No joy, try again later. Or just synchronize_sched(). */ - if (trycount++ < 10) - udelay(trycount * num_online_cpus()); - else { - synchronize_sched(); - return; - } - - /* Check to see if someone else did our work for us. */ - s = atomic_read(&sync_sched_expedited_done); - if (UINT_CMP_GE((unsigned)s, (unsigned)firstsnap)) { - smp_mb(); /* ensure test happens before caller kfree */ - return; - } - - /* - * Refetching sync_sched_expedited_started allows later - * callers to piggyback on our grace period. We subtract - * 1 to get the same token that the last incrementer got. - * We retry after they started, so our grace period works - * for them, and they started after our first try, so their - * grace period works for us. - */ - get_online_cpus(); - snap = atomic_read(&sync_sched_expedited_started); - smp_mb(); /* ensure read is before try_stop_cpus(). */ - } - - /* - * Everyone up to our most recent fetch is covered by our grace - * period. Update the counter, but only if our work is still - * relevant -- which it won't be if someone who started later - * than we did beat us to the punch. - */ - do { - s = atomic_read(&sync_sched_expedited_done); - if (UINT_CMP_GE((unsigned)s, (unsigned)snap)) { - smp_mb(); /* ensure test happens before caller kfree */ - break; - } - } while (atomic_cmpxchg(&sync_sched_expedited_done, s, snap) != s); - - put_online_cpus(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#endif /* #else #ifndef CONFIG_SMP */ - #if !defined(CONFIG_RCU_FAST_NO_HZ) /* @@ -1981,7 +1931,7 @@ static void rcu_cleanup_after_idle(int cpu) } /* - * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=y, + * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n, * is nothing. */ static void rcu_prepare_for_idle(int cpu) @@ -2015,6 +1965,9 @@ static void rcu_prepare_for_idle(int cpu) * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your * system. And if you are -that- concerned about energy efficiency, * just power the system down and be done with it! + * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is + * permitted to sleep in dyntick-idle mode with only lazy RCU + * callbacks pending. Setting this too high can OOM your system. * * The values below work well in practice. If future workloads require * adjustment, they can be converted into kernel config parameters, though @@ -2023,11 +1976,13 @@ static void rcu_prepare_for_idle(int cpu) #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ #define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ static DEFINE_PER_CPU(int, rcu_dyntick_drain); static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer); -static ktime_t rcu_idle_gp_wait; +static ktime_t rcu_idle_gp_wait; /* If some non-lazy callbacks. */ +static ktime_t rcu_idle_lazy_gp_wait; /* If only lazy callbacks. */ /* * Allow the CPU to enter dyntick-idle mode if either: (1) There are no @@ -2048,6 +2003,48 @@ int rcu_needs_cpu(int cpu) } /* + * Does the specified flavor of RCU have non-lazy callbacks pending on + * the specified CPU? Both RCU flavor and CPU are specified by the + * rcu_data structure. + */ +static bool __rcu_cpu_has_nonlazy_callbacks(struct rcu_data *rdp) +{ + return rdp->qlen != rdp->qlen_lazy; +} + +#ifdef CONFIG_TREE_PREEMPT_RCU + +/* + * Are there non-lazy RCU-preempt callbacks? (There cannot be if there + * is no RCU-preempt in the kernel.) + */ +static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu) +{ + struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); + + return __rcu_cpu_has_nonlazy_callbacks(rdp); +} + +#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ + +static bool rcu_preempt_cpu_has_nonlazy_callbacks(int cpu) +{ + return 0; +} + +#endif /* else #ifdef CONFIG_TREE_PREEMPT_RCU */ + +/* + * Does any flavor of RCU have non-lazy callbacks on the specified CPU? + */ +static bool rcu_cpu_has_nonlazy_callbacks(int cpu) +{ + return __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_sched_data, cpu)) || + __rcu_cpu_has_nonlazy_callbacks(&per_cpu(rcu_bh_data, cpu)) || + rcu_preempt_cpu_has_nonlazy_callbacks(cpu); +} + +/* * Timer handler used to force CPU to start pushing its remaining RCU * callbacks in the case where it entered dyntick-idle mode with callbacks * pending. The hander doesn't really need to do anything because the @@ -2074,6 +2071,8 @@ static void rcu_prepare_for_idle_init(int cpu) unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY); rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000); + upj = jiffies_to_usecs(RCU_IDLE_LAZY_GP_DELAY); + rcu_idle_lazy_gp_wait = ns_to_ktime(upj * (u64)1000); firsttime = 0; } } @@ -2109,10 +2108,6 @@ static void rcu_cleanup_after_idle(int cpu) */ static void rcu_prepare_for_idle(int cpu) { - unsigned long flags; - - local_irq_save(flags); - /* * If there are no callbacks on this CPU, enter dyntick-idle mode. * Also reset state to avoid prejudicing later attempts. @@ -2120,7 +2115,6 @@ static void rcu_prepare_for_idle(int cpu) if (!rcu_cpu_has_callbacks(cpu)) { per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; per_cpu(rcu_dyntick_drain, cpu) = 0; - local_irq_restore(flags); trace_rcu_prep_idle("No callbacks"); return; } @@ -2130,7 +2124,6 @@ static void rcu_prepare_for_idle(int cpu) * refrained from disabling the scheduling-clock tick. */ if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) { - local_irq_restore(flags); trace_rcu_prep_idle("In holdoff"); return; } @@ -2140,18 +2133,22 @@ static void rcu_prepare_for_idle(int cpu) /* First time through, initialize the counter. */ per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES; } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES && - !rcu_pending(cpu)) { + !rcu_pending(cpu) && + !local_softirq_pending()) { /* Can we go dyntick-idle despite still having callbacks? */ trace_rcu_prep_idle("Dyntick with callbacks"); per_cpu(rcu_dyntick_drain, cpu) = 0; - per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; - hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), - rcu_idle_gp_wait, HRTIMER_MODE_REL); + per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) + hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), + rcu_idle_gp_wait, HRTIMER_MODE_REL); + else + hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), + rcu_idle_lazy_gp_wait, HRTIMER_MODE_REL); return; /* Nothing more to do immediately. */ } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) { /* We have hit the limit, so time to give up. */ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; - local_irq_restore(flags); trace_rcu_prep_idle("Begin holdoff"); invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */ return; @@ -2163,23 +2160,17 @@ static void rcu_prepare_for_idle(int cpu) */ #ifdef CONFIG_TREE_PREEMPT_RCU if (per_cpu(rcu_preempt_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_preempt_qs(cpu); force_quiescent_state(&rcu_preempt_state, 0); - local_irq_save(flags); } #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ if (per_cpu(rcu_sched_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_sched_qs(cpu); force_quiescent_state(&rcu_sched_state, 0); - local_irq_save(flags); } if (per_cpu(rcu_bh_data, cpu).nxtlist) { - local_irq_restore(flags); rcu_bh_qs(cpu); force_quiescent_state(&rcu_bh_state, 0); - local_irq_save(flags); } /* @@ -2187,13 +2178,124 @@ static void rcu_prepare_for_idle(int cpu) * So try forcing the callbacks through the grace period. */ if (rcu_cpu_has_callbacks(cpu)) { - local_irq_restore(flags); trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - } else { - local_irq_restore(flags); + } else trace_rcu_prep_idle("Callbacks drained"); - } } #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ + +#ifdef CONFIG_RCU_CPU_STALL_INFO + +#ifdef CONFIG_RCU_FAST_NO_HZ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ + struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu); + + sprintf(cp, "drain=%d %c timer=%lld", + per_cpu(rcu_dyntick_drain, cpu), + per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.', + hrtimer_active(hrtp) + ? ktime_to_us(hrtimer_get_remaining(hrtp)) + : -1); +} + +#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + +static void print_cpu_stall_fast_no_hz(char *cp, int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ + +/* Initiate the stall-info list. */ +static void print_cpu_stall_info_begin(void) +{ + printk(KERN_CONT "\n"); +} + +/* + * Print out diagnostic information for the specified stalled CPU. + * + * If the specified CPU is aware of the current RCU grace period + * (flavor specified by rsp), then print the number of scheduling + * clock interrupts the CPU has taken during the time that it has + * been aware. Otherwise, print the number of RCU grace periods + * that this CPU is ignorant of, for example, "1" if the CPU was + * aware of the previous grace period. + * + * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. + */ +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + char fast_no_hz[72]; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = rdp->dynticks; + char *ticks_title; + unsigned long ticks_value; + + if (rsp->gpnum == rdp->gpnum) { + ticks_title = "ticks this GP"; + ticks_value = rdp->ticks_this_gp; + } else { + ticks_title = "GPs behind"; + ticks_value = rsp->gpnum - rdp->gpnum; + } + print_cpu_stall_fast_no_hz(fast_no_hz, cpu); + printk(KERN_ERR "\t%d: (%lu %s) idle=%03x/%llx/%d %s\n", + cpu, ticks_value, ticks_title, + atomic_read(&rdtp->dynticks) & 0xfff, + rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, + fast_no_hz); +} + +/* Terminate the stall-info list. */ +static void print_cpu_stall_info_end(void) +{ + printk(KERN_ERR "\t"); +} + +/* Zero ->ticks_this_gp for all flavors of RCU. */ +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ + rdp->ticks_this_gp = 0; +} + +/* Increment ->ticks_this_gp for all flavors of RCU. */ +static void increment_cpu_stall_ticks(void) +{ + __get_cpu_var(rcu_sched_data).ticks_this_gp++; + __get_cpu_var(rcu_bh_data).ticks_this_gp++; +#ifdef CONFIG_TREE_PREEMPT_RCU + __get_cpu_var(rcu_preempt_data).ticks_this_gp++; +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ + +static void print_cpu_stall_info_begin(void) +{ + printk(KERN_CONT " {"); +} + +static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +{ + printk(KERN_CONT " %d", cpu); +} + +static void print_cpu_stall_info_end(void) +{ + printk(KERN_CONT "} "); +} + +static void zero_cpu_stall_ticks(struct rcu_data *rdp) +{ +} + +static void increment_cpu_stall_ticks(void) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 654cfe67f0d1..ed459edeff43 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -72,9 +72,9 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); - seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld qs=%c%c%c%c", - rdp->qlen, + seq_printf(m, " of=%lu", rdp->offline_fqs); + seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c", + rdp->qlen_lazy, rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != @@ -144,8 +144,8 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); - seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, + seq_printf(m, ",%lu", rdp->offline_fqs); + seq_printf(m, ",%ld,%ld,\"%c%c%c%c\"", rdp->qlen_lazy, rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]], ".R"[rdp->nxttail[RCU_WAIT_TAIL] != @@ -168,7 +168,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) { seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); - seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); + seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); #ifdef CONFIG_RCU_BOOST seq_puts(m, "\"kt\",\"ktl\""); #endif /* #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index e8a1f83ee0e7..0984a21076a3 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -195,20 +195,20 @@ __setup("noautogroup", setup_autogroup); #ifdef CONFIG_PROC_FS -int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) +int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) { static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; int err; - if (*nice < -20 || *nice > 19) + if (nice < -20 || nice > 19) return -EINVAL; - err = security_task_setnice(current, *nice); + err = security_task_setnice(current, nice); if (err) return err; - if (*nice < 0 && !can_nice(current, *nice)) + if (nice < 0 && !can_nice(current, nice)) return -EPERM; /* this is a heavy operation taking global locks.. */ @@ -219,9 +219,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice) ag = autogroup_task_get(p); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]); + err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); if (!err) - ag->nice = *nice; + ag->nice = nice; up_write(&ag->lock); autogroup_kref_put(ag); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6c41ba49767a..d2bd4647586c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1284,7 +1284,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", + printk_sched("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } @@ -1507,7 +1507,7 @@ static int ttwu_activate_remote(struct task_struct *p, int wake_flags) } #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -static inline int ttwu_share_cache(int this_cpu, int that_cpu) +bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } @@ -1518,7 +1518,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) struct rq *rq = cpu_rq(cpu); #if defined(CONFIG_SMP) - if (sched_feat(TTWU_QUEUE) && !ttwu_share_cache(smp_processor_id(), cpu)) { + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { sched_clock_cpu(cpu); /* sync clocks x-cpu */ ttwu_queue_remote(p, cpu); return; @@ -2266,13 +2266,10 @@ calc_load_n(unsigned long load, unsigned long exp, * Once we've updated the global active value, we need to apply the exponential * weights adjusted to the number of cycles missed. */ -static void calc_global_nohz(unsigned long ticks) +static void calc_global_nohz(void) { long delta, active, n; - if (time_before(jiffies, calc_load_update)) - return; - /* * If we crossed a calc_load_update boundary, make sure to fold * any pending idle changes, the respective CPUs might have @@ -2284,31 +2281,25 @@ static void calc_global_nohz(unsigned long ticks) atomic_long_add(delta, &calc_load_tasks); /* - * If we were idle for multiple load cycles, apply them. + * It could be the one fold was all it took, we done! */ - if (ticks >= LOAD_FREQ) { - n = ticks / LOAD_FREQ; + if (time_before(jiffies, calc_load_update + 10)) + return; - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; + /* + * Catch-up, fold however many we are behind still + */ + delta = jiffies - calc_load_update - 10; + n = 1 + (delta / LOAD_FREQ); - avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); - avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); - avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - calc_load_update += n * LOAD_FREQ; - } + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - /* - * Its possible the remainder of the above division also crosses - * a LOAD_FREQ period, the regular check in calc_global_load() - * which comes after this will take care of that. - * - * Consider us being 11 ticks before a cycle completion, and us - * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will - * age us 4 cycles, and the test in calc_global_load() will - * pick up the final one. - */ + calc_load_update += n * LOAD_FREQ; } #else void calc_load_account_idle(struct rq *this_rq) @@ -2320,7 +2311,7 @@ static inline long calc_load_fold_idle(void) return 0; } -static void calc_global_nohz(unsigned long ticks) +static void calc_global_nohz(void) { } #endif @@ -2348,8 +2339,6 @@ void calc_global_load(unsigned long ticks) { long active; - calc_global_nohz(ticks); - if (time_before(jiffies, calc_load_update + 10)) return; @@ -2361,6 +2350,16 @@ void calc_global_load(unsigned long ticks) avenrun[2] = calc_load(avenrun[2], EXP_15, active); calc_load_update += LOAD_FREQ; + + /* + * Account one period with whatever state we found before + * folding in the nohz state and ageing the entire idle period. + * + * This avoids loosing a sample when we go idle between + * calc_load_account_active() (10 ticks ago) and now and thus + * under-accounting. + */ + calc_global_nohz(); } /* @@ -3220,14 +3219,14 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); if (need_resched()) goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + if (!tsk->state || tsk_is_pi_blocked(tsk)) return; /* * If we are going to sleep and we have plugged IO queued, @@ -3246,6 +3245,18 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline bool owner_running(struct mutex *lock, struct task_struct *owner) @@ -3406,9 +3417,9 @@ EXPORT_SYMBOL(__wake_up); /* * Same as __wake_up but called with the spinlock in wait_queue_head_t held. */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) { - __wake_up_common(q, mode, 1, 0, NULL); + __wake_up_common(q, mode, nr, 0, NULL); } EXPORT_SYMBOL_GPL(__wake_up_locked); @@ -3767,6 +3778,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio) rq = __task_rq_lock(p); + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; @@ -3790,11 +3819,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); +out_unlock: __task_rq_unlock(rq); } - #endif - void set_user_nice(struct task_struct *p, long nice) { int old_prio, delta, on_rq; @@ -4474,7 +4502,7 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); schedule(); @@ -4548,8 +4576,24 @@ EXPORT_SYMBOL(__cond_resched_softirq); /** * yield - yield the current processor to other threads. * - * This is a shortcut for kernel-space yielding - it marks the - * thread runnable and calls sys_sched_yield(). + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! */ void __sched yield(void) { @@ -5381,7 +5425,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: + case CPU_STARTING: case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5753,7 +5797,7 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) * * Also keep a unique ID per domain (we use the first cpu number in * the cpumask of the domain), this allows us to quickly tell if - * two cpus are in the same cache domain, see ttwu_share_cache(). + * two cpus are in the same cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain *, sd_llc); DEFINE_PER_CPU(int, sd_llc_id); @@ -6930,6 +6974,9 @@ void __init sched_init(void) rq->online = 0; rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; + + INIT_LIST_HEAD(&rq->cfs_tasks); + rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ rq->nohz_flags = 0; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 2a075e10004b..09acaa15161d 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -288,7 +288,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(yld_count); - P(sched_switch); P(sched_count); P(sched_goidle); #ifdef CONFIG_SMP diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fd974faf467d..94340c7544a9 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -776,29 +776,16 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ -#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ - cfs_rq->task_weight += weight; -} -#else -static inline void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ -} -#endif - static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_add(&rq_of(cfs_rq)->load, se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, se->load.weight); - list_add(&se->group_node, &cfs_rq->tasks); - } +#ifdef CONFIG_SMP + if (entity_is_task(se)) + list_add_tail(&se->group_node, &rq_of(cfs_rq)->cfs_tasks); +#endif cfs_rq->nr_running++; } @@ -808,10 +795,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_sub(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); - if (entity_is_task(se)) { - add_cfs_task_weight(cfs_rq, -se->load.weight); + if (entity_is_task(se)) list_del_init(&se->group_node); - } cfs_rq->nr_running--; } @@ -2672,8 +2657,6 @@ static int select_idle_sibling(struct task_struct *p, int target) /* * Otherwise, iterate the domains and find an elegible idle cpu. */ - rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_llc, target)); for_each_lower_domain(sd) { sg = sd->groups; @@ -2695,8 +2678,6 @@ next: } while (sg != sd->groups); } done: - rcu_read_unlock(); - return target; } @@ -2922,7 +2903,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* - * This is possible from callers such as pull_task(), in which we + * This is possible from callers such as move_task(), in which we * unconditionally check_prempt_curr() after an enqueue (which may have * lead to a throttle). This both saves work and prevents false * next-buddy nomination below. @@ -3086,17 +3067,39 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * Fair scheduling class load-balancing methods: */ +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +#define LBF_ALL_PINNED 0x01 +#define LBF_NEED_BREAK 0x02 + +struct lb_env { + struct sched_domain *sd; + + int src_cpu; + struct rq *src_rq; + + int dst_cpu; + struct rq *dst_rq; + + enum cpu_idle_type idle; + long load_move; + unsigned int flags; + + unsigned int loop; + unsigned int loop_break; + unsigned int loop_max; +}; + /* - * pull_task - move a task from a remote runqueue to the local runqueue. + * move_task - move a task from one runqueue to another runqueue. * Both runqueues must be locked. */ -static void pull_task(struct rq *src_rq, struct task_struct *p, - struct rq *this_rq, int this_cpu) +static void move_task(struct task_struct *p, struct lb_env *env) { - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); - check_preempt_curr(this_rq, p, 0); + deactivate_task(env->src_rq, p, 0); + set_task_cpu(p, env->dst_cpu); + activate_task(env->dst_rq, p, 0); + check_preempt_curr(env->dst_rq, p, 0); } /* @@ -3131,19 +3134,11 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } -#define LBF_ALL_PINNED 0x01 -#define LBF_NEED_BREAK 0x02 /* clears into HAD_BREAK */ -#define LBF_HAD_BREAK 0x04 -#define LBF_HAD_BREAKS 0x0C /* count HAD_BREAKs overflows into ABORT */ -#define LBF_ABORT 0x10 - /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ static -int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +int can_migrate_task(struct task_struct *p, struct lb_env *env) { int tsk_cache_hot = 0; /* @@ -3152,13 +3147,13 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ - if (!cpumask_test_cpu(this_cpu, tsk_cpus_allowed(p))) { + if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { schedstat_inc(p, se.statistics.nr_failed_migrations_affine); return 0; } - *lb_flags &= ~LBF_ALL_PINNED; + env->flags &= ~LBF_ALL_PINNED; - if (task_running(rq, p)) { + if (task_running(env->src_rq, p)) { schedstat_inc(p, se.statistics.nr_failed_migrations_running); return 0; } @@ -3169,12 +3164,12 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq->clock_task, sd); + tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); if (!tsk_cache_hot || - sd->nr_balance_failed > sd->cache_nice_tries) { + env->sd->nr_balance_failed > env->sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS if (tsk_cache_hot) { - schedstat_inc(sd, lb_hot_gained[idle]); + schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } #endif @@ -3195,65 +3190,80 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * * Called with both runqueues locked. */ -static int -move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) +static int move_one_task(struct lb_env *env) { struct task_struct *p, *n; - struct cfs_rq *cfs_rq; - int pinned = 0; - for_each_leaf_cfs_rq(busiest, cfs_rq) { - list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) { - if (throttled_lb_pair(task_group(p), - busiest->cpu, this_cpu)) - break; + list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu)) + continue; - if (!can_migrate_task(p, busiest, this_cpu, - sd, idle, &pinned)) - continue; + if (!can_migrate_task(p, env)) + continue; - pull_task(busiest, p, this_rq, this_cpu); - /* - * Right now, this is only the second place pull_task() - * is called, so we can safely collect pull_task() - * stats here rather than inside pull_task(). - */ - schedstat_inc(sd, lb_gained[idle]); - return 1; - } + move_task(p, env); + /* + * Right now, this is only the second place move_task() + * is called, so we can safely collect move_task() + * stats here rather than inside move_task(). + */ + schedstat_inc(env->sd, lb_gained[env->idle]); + return 1; } - return 0; } -static unsigned long -balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, struct sched_domain *sd, - enum cpu_idle_type idle, int *lb_flags, - struct cfs_rq *busiest_cfs_rq) +static unsigned long task_h_load(struct task_struct *p); + +/* + * move_tasks tries to move up to load_move weighted load from busiest to + * this_rq, as part of a balancing operation within domain "sd". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int move_tasks(struct lb_env *env) { - int loops = 0, pulled = 0; - long rem_load_move = max_load_move; - struct task_struct *p, *n; + struct list_head *tasks = &env->src_rq->cfs_tasks; + struct task_struct *p; + unsigned long load; + int pulled = 0; + + if (env->load_move <= 0) + return 0; - if (max_load_move == 0) - goto out; + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); - list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) { - if (loops++ > sysctl_sched_nr_migrate) { - *lb_flags |= LBF_NEED_BREAK; + env->loop++; + /* We've more or less seen every task there is, call it quits */ + if (env->loop > env->loop_max) + break; + + /* take a breather every nr_migrate tasks */ + if (env->loop > env->loop_break) { + env->loop_break += sysctl_sched_nr_migrate; + env->flags |= LBF_NEED_BREAK; break; } - if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, - lb_flags)) - continue; + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + goto next; + + load = task_h_load(p); + + if (load < 16 && !env->sd->nr_balance_failed) + goto next; + + if ((load / 2) > env->load_move) + goto next; - pull_task(busiest, p, this_rq, this_cpu); + if (!can_migrate_task(p, env)) + goto next; + + move_task(p, env); pulled++; - rem_load_move -= p->se.load.weight; + env->load_move -= load; #ifdef CONFIG_PREEMPT /* @@ -3261,28 +3271,30 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, * kernels will stop after the first task is pulled to minimize * the critical section. */ - if (idle == CPU_NEWLY_IDLE) { - *lb_flags |= LBF_ABORT; + if (env->idle == CPU_NEWLY_IDLE) break; - } #endif /* * We only want to steal up to the prescribed amount of * weighted load. */ - if (rem_load_move <= 0) + if (env->load_move <= 0) break; + + continue; +next: + list_move_tail(&p->se.group_node, tasks); } -out: + /* - * Right now, this is one of only two places pull_task() is called, - * so we can safely collect pull_task() stats here rather than - * inside pull_task(). + * Right now, this is one of only two places move_task() is called, + * so we can safely collect move_task() stats here rather than + * inside move_task(). */ - schedstat_add(sd, lb_gained[idle], pulled); + schedstat_add(env->sd, lb_gained[env->idle], pulled); - return max_load_move - rem_load_move; + return pulled; } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -3362,113 +3374,35 @@ static int tg_load_down(struct task_group *tg, void *data) static void update_h_load(long cpu) { + rcu_read_lock(); walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); + rcu_read_unlock(); } -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static unsigned long task_h_load(struct task_struct *p) { - long rem_load_move = max_load_move; - struct cfs_rq *busiest_cfs_rq; - - rcu_read_lock(); - update_h_load(cpu_of(busiest)); - - for_each_leaf_cfs_rq(busiest, busiest_cfs_rq) { - unsigned long busiest_h_load = busiest_cfs_rq->h_load; - unsigned long busiest_weight = busiest_cfs_rq->load.weight; - u64 rem_load, moved_load; - - if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT)) - break; - - /* - * empty group or part of a throttled hierarchy - */ - if (!busiest_cfs_rq->task_weight || - throttled_lb_pair(busiest_cfs_rq->tg, cpu_of(busiest), this_cpu)) - continue; - - rem_load = (u64)rem_load_move * busiest_weight; - rem_load = div_u64(rem_load, busiest_h_load + 1); - - moved_load = balance_tasks(this_rq, this_cpu, busiest, - rem_load, sd, idle, lb_flags, - busiest_cfs_rq); - - if (!moved_load) - continue; + struct cfs_rq *cfs_rq = task_cfs_rq(p); + unsigned long load; - moved_load *= busiest_h_load; - moved_load = div_u64(moved_load, busiest_weight + 1); + load = p->se.load.weight; + load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1); - rem_load_move -= moved_load; - if (rem_load_move < 0) - break; - } - rcu_read_unlock(); - - return max_load_move - rem_load_move; + return load; } #else static inline void update_shares(int cpu) { } -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static inline void update_h_load(long cpu) { - return balance_tasks(this_rq, this_cpu, busiest, - max_load_move, sd, idle, lb_flags, - &busiest->cfs); } -#endif -/* - * move_tasks tries to move up to max_load_move weighted load from busiest to - * this_rq, as part of a balancing operation within domain "sd". - * Returns 1 if successful and 0 otherwise. - * - * Called with both runqueues locked. - */ -static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *lb_flags) +static unsigned long task_h_load(struct task_struct *p) { - unsigned long total_load_moved = 0, load_moved; - - do { - load_moved = load_balance_fair(this_rq, this_cpu, busiest, - max_load_move - total_load_moved, - sd, idle, lb_flags); - - total_load_moved += load_moved; - - if (*lb_flags & (LBF_NEED_BREAK|LBF_ABORT)) - break; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize - * the critical section. - */ - if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) { - *lb_flags |= LBF_ABORT; - break; - } -#endif - } while (load_moved && max_load_move > total_load_moved); - - return total_load_moved > 0; + return p->se.load.weight; } +#endif /********** Helpers for find_busiest_group ************************/ /* @@ -3778,6 +3712,11 @@ void update_group_power(struct sched_domain *sd, int cpu) struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; unsigned long power; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgp->next_update = jiffies + interval; if (!child) { update_cpu_power(sd, cpu); @@ -3885,12 +3824,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, * domains. In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ - if (idle != CPU_NEWLY_IDLE && local_group) { - if (balance_cpu != this_cpu) { - *balance = 0; - return; - } - update_group_power(sd, this_cpu); + if (local_group) { + if (idle != CPU_NEWLY_IDLE) { + if (balance_cpu != this_cpu) { + *balance = 0; + return; + } + update_group_power(sd, this_cpu); + } else if (time_after_eq(jiffies, group->sgp->next_update)) + update_group_power(sd, this_cpu); } /* Adjust by relative CPU power of the group */ @@ -4453,13 +4395,21 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, int *balance) { - int ld_moved, lb_flags = 0, active_balance = 0; + int ld_moved, active_balance = 0; struct sched_group *group; unsigned long imbalance; struct rq *busiest; unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); + struct lb_env env = { + .sd = sd, + .dst_cpu = this_cpu, + .dst_rq = this_rq, + .idle = idle, + .loop_break = sysctl_sched_nr_migrate, + }; + cpumask_copy(cpus, cpu_active_mask); schedstat_inc(sd, lb_count[idle]); @@ -4494,32 +4444,34 @@ redo: * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. */ - lb_flags |= LBF_ALL_PINNED; + env.flags |= LBF_ALL_PINNED; + env.load_move = imbalance; + env.src_cpu = busiest->cpu; + env.src_rq = busiest; + env.loop_max = busiest->nr_running; + +more_balance: local_irq_save(flags); double_rq_lock(this_rq, busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, idle, &lb_flags); + if (!env.loop) + update_h_load(env.src_cpu); + ld_moved += move_tasks(&env); double_rq_unlock(this_rq, busiest); local_irq_restore(flags); + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + /* * some other cpu did the load balance for us. */ if (ld_moved && this_cpu != smp_processor_id()) resched_cpu(this_cpu); - if (lb_flags & LBF_ABORT) - goto out_balanced; - - if (lb_flags & LBF_NEED_BREAK) { - lb_flags += LBF_HAD_BREAK - LBF_NEED_BREAK; - if (lb_flags & LBF_ABORT) - goto out_balanced; - goto redo; - } - /* All tasks on this runqueue were pinned by CPU affinity */ - if (unlikely(lb_flags & LBF_ALL_PINNED)) { + if (unlikely(env.flags & LBF_ALL_PINNED)) { cpumask_clear_cpu(cpu_of(busiest), cpus); if (!cpumask_empty(cpus)) goto redo; @@ -4549,7 +4501,7 @@ redo: tsk_cpus_allowed(busiest->curr))) { raw_spin_unlock_irqrestore(&busiest->lock, flags); - lb_flags |= LBF_ALL_PINNED; + env.flags |= LBF_ALL_PINNED; goto out_one_pinned; } @@ -4602,7 +4554,7 @@ out_balanced: out_one_pinned: /* tune up the balancing interval */ - if (((lb_flags & LBF_ALL_PINNED) && + if (((env.flags & LBF_ALL_PINNED) && sd->balance_interval < MAX_PINNED_INTERVAL) || (sd->balance_interval < sd->max_interval)) sd->balance_interval *= 2; @@ -4712,10 +4664,18 @@ static int active_load_balance_cpu_stop(void *data) } if (likely(sd)) { + struct lb_env env = { + .sd = sd, + .dst_cpu = target_cpu, + .dst_rq = target_rq, + .src_cpu = busiest_rq->cpu, + .src_rq = busiest_rq, + .idle = CPU_IDLE, + }; + schedstat_inc(sd, alb_count); - if (move_one_task(target_rq, target_cpu, busiest_rq, - sd, CPU_IDLE)) + if (move_one_task(&env)) schedstat_inc(sd, alb_pushed); else schedstat_inc(sd, alb_failed); @@ -4947,8 +4907,6 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, static DEFINE_SPINLOCK(balancing); -static unsigned long __read_mostly max_load_balance_interval = HZ/10; - /* * Scale the max load_balance interval with the number of CPUs in the system. * This trades load-balance latency on larger machines for less cross talk. @@ -5342,7 +5300,6 @@ static void set_curr_task_fair(struct rq *rq) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT; - INIT_LIST_HEAD(&cfs_rq->tasks); cfs_rq->min_vruntime = (u64)(-(1LL << 20)); #ifndef CONFIG_64BIT cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; @@ -5614,6 +5571,7 @@ __init void init_sched_fair_class(void) open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); #ifdef CONFIG_NO_HZ + nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f42ae7fb5ec5..b60dad720173 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -778,12 +778,9 @@ static inline int balance_runtime(struct rt_rq *rt_rq) static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) { - int i, idle = 1; + int i, idle = 1, throttled = 0; const struct cpumask *span; - if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) - return 1; - span = sched_rt_period_mask(); for_each_cpu(i, span) { int enqueue = 0; @@ -818,12 +815,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (!rt_rq_throttled(rt_rq)) enqueue = 1; } + if (rt_rq->rt_throttled) + throttled = 1; if (enqueue) sched_rt_rq_enqueue(rt_rq); raw_spin_unlock(&rq->lock); } + if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)) + return 1; + return idle; } @@ -855,8 +857,30 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) return 0; if (rt_rq->rt_time > runtime) { - rt_rq->rt_throttled = 1; - printk_once(KERN_WARNING "sched: RT throttling activated\n"); + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + /* + * Don't actually throttle groups that have no runtime assigned + * but accrue some time due to boosting. + */ + if (likely(rt_b->rt_runtime)) { + static bool once = false; + + rt_rq->rt_throttled = 1; + + if (!once) { + once = true; + printk_sched("sched: RT throttling activated\n"); + } + } else { + /* + * In case we did anyway, make it go away, + * replenishment is a joke, since it will replenish us + * with exactly 0 ns. + */ + rt_rq->rt_time = 0; + } + if (rt_rq_throttled(rt_rq)) { sched_rt_rq_dequeue(rt_rq); return 1; @@ -884,7 +908,8 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); @@ -1972,7 +1997,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) if (--p->rt.time_slice) return; - p->rt.time_slice = DEF_TIMESLICE; + p->rt.time_slice = RR_TIMESLICE; /* * Requeue to the end of queue if we are not the only element @@ -2000,7 +2025,7 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) * Time slice is 0 for SCHED_FIFO tasks */ if (task->policy == SCHED_RR) - return DEF_TIMESLICE; + return RR_TIMESLICE; else return 0; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b4cd6d8ea150..42b1f304b044 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -36,11 +36,7 @@ extern __read_mostly int scheduler_running; /* * These are the 'tuning knobs' of the scheduler: - * - * default timeslice is 100 msecs (used only for SCHED_RR tasks). - * Timeslices get refilled after they expire. */ -#define DEF_TIMESLICE (100 * HZ / 1000) /* * single value that denotes runtime == period, ie unlimited time. @@ -216,9 +212,6 @@ struct cfs_rq { struct rb_root tasks_timeline; struct rb_node *rb_leftmost; - struct list_head tasks; - struct list_head *balance_iterator; - /* * 'curr' points to currently running entity on this cfs_rq. * It is set to NULL otherwise (i.e when none are currently running). @@ -246,11 +239,6 @@ struct cfs_rq { #ifdef CONFIG_SMP /* - * the part of load.weight contributed by tasks - */ - unsigned long task_weight; - - /* * h_load = weight * f(tg) * * Where f(tg) is the recursive weight fraction assigned to @@ -424,6 +412,8 @@ struct rq { int cpu; int online; + struct list_head cfs_tasks; + u64 rt_avg; u64 age_stamp; u64 idle_stamp; @@ -462,7 +452,6 @@ struct rq { unsigned int yld_count; /* schedule() stats */ - unsigned int sched_switch; unsigned int sched_count; unsigned int sched_goidle; diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 2a581ba8e190..903ffa9e8872 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -32,9 +32,9 @@ static int show_schedstat(struct seq_file *seq, void *v) /* runqueue-specific stats */ seq_printf(seq, - "cpu%d %u %u %u %u %u %u %llu %llu %lu", + "cpu%d %u 0 %u %u %u %u %llu %llu %lu", cpu, rq->yld_count, - rq->sched_switch, rq->sched_count, rq->sched_goidle, + rq->sched_count, rq->sched_goidle, rq->ttwu_count, rq->ttwu_local, rq->rq_cpu_time, rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount); diff --git a/kernel/softirq.c b/kernel/softirq.c index 06d40993594a..671f9594e368 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -297,7 +297,7 @@ void irq_enter(void) int cpu = smp_processor_id(); rcu_irq_enter(); - if (idle_cpu(cpu) && !in_interrupt()) { + if (is_idle_task(current) && !in_interrupt()) { /* * Prevent raise_softirq from needlessly waking up ksoftirqd * here, as softirq will be serviced on return from interrupt. @@ -310,31 +310,21 @@ void irq_enter(void) __irq_enter(); } -#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED static inline void invoke_softirq(void) { - if (!force_irqthreads) + if (!force_irqthreads) { +#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED __do_softirq(); - else { - __local_bh_disable((unsigned long)__builtin_return_address(0), - SOFTIRQ_OFFSET); - wakeup_softirqd(); - __local_bh_enable(SOFTIRQ_OFFSET); - } -} #else -static inline void invoke_softirq(void) -{ - if (!force_irqthreads) do_softirq(); - else { +#endif + } else { __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); wakeup_softirqd(); __local_bh_enable(SOFTIRQ_OFFSET); } } -#endif /* * Exit an interrupt context. Process softirqs if needed and possible: @@ -353,7 +343,7 @@ void irq_exit(void) tick_nohz_irq_exit(); #endif rcu_irq_exit(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); } /* @@ -750,9 +740,7 @@ static int run_ksoftirqd(void * __bind_cpu) while (!kthread_should_stop()) { preempt_disable(); if (!local_softirq_pending()) { - preempt_enable_no_resched(); - schedule(); - preempt_disable(); + schedule_preempt_disabled(); } __set_current_state(TASK_RUNNING); @@ -767,7 +755,7 @@ static int run_ksoftirqd(void * __bind_cpu) if (local_softirq_pending()) __do_softirq(); local_irq_enable(); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); cond_resched(); preempt_disable(); rcu_note_context_switch((long)__bind_cpu); diff --git a/kernel/srcu.c b/kernel/srcu.c index 0febf61e1aa3..ba35f3a4a1f4 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -172,6 +172,12 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) { int idx; + rcu_lockdep_assert(!lock_is_held(&sp->dep_map) && + !lock_is_held(&rcu_bh_lock_map) && + !lock_is_held(&rcu_lock_map) && + !lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); + idx = sp->completed; mutex_lock(&sp->mutex); @@ -280,19 +286,26 @@ void synchronize_srcu(struct srcu_struct *sp) EXPORT_SYMBOL_GPL(synchronize_srcu); /** - * synchronize_srcu_expedited - like synchronize_srcu, but less patient + * synchronize_srcu_expedited - Brute-force SRCU grace period * @sp: srcu_struct with which to synchronize. * - * Flip the completed counter, and wait for the old count to drain to zero. - * As with classic RCU, the updater must use some separate means of - * synchronizing concurrent updates. Can block; must be called from - * process context. + * Wait for an SRCU grace period to elapse, but use a "big hammer" + * approach to force the grace period to end quickly. This consumes + * significant time on all CPUs and is unfriendly to real-time workloads, + * so is thus not recommended for any sort of common-case code. In fact, + * if you are using synchronize_srcu_expedited() in a loop, please + * restructure your code to batch your updates, and then use a single + * synchronize_srcu() instead. * - * Note that it is illegal to call synchronize_srcu_expedited() - * from the corresponding SRCU read-side critical section; doing so - * will result in deadlock. However, it is perfectly legal to call - * synchronize_srcu_expedited() on one srcu_struct from some other - * srcu_struct's read-side critical section. + * Note that it is illegal to call this function while holding any lock + * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal + * to call this function from a CPU-hotplug notifier. Failing to observe + * these restriction will result in deadlock. It is also illegal to call + * synchronize_srcu_expedited() from the corresponding SRCU read-side + * critical section; doing so will result in deadlock. However, it is + * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct + * from some other srcu_struct's read-side critical section, as long as + * the resulting graph of srcu_structs is acyclic. */ void synchronize_srcu_expedited(struct srcu_struct *sp) { diff --git a/kernel/sys.c b/kernel/sys.c index 40701538fbd1..888d227fd195 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1706,7 +1706,7 @@ static int prctl_set_mm(int opt, unsigned long addr, if (arg4 | arg5) return -EINVAL; - if (!capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (addr >= TASK_SIZE) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index f6117a4c7cb8..6e039b144daf 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -22,13 +22,16 @@ * NTP timekeeping variables: */ +DEFINE_SPINLOCK(ntp_lock); + + /* USER_HZ period (usecs): */ unsigned long tick_usec = TICK_USEC; /* ACTHZ period (nsecs): */ unsigned long tick_nsec; -u64 tick_length; +static u64 tick_length; static u64 tick_length_base; static struct hrtimer leap_timer; @@ -49,7 +52,7 @@ static struct hrtimer leap_timer; static int time_state = TIME_OK; /* clock status bits: */ -int time_status = STA_UNSYNC; +static int time_status = STA_UNSYNC; /* TAI offset (secs): */ static long time_tai; @@ -133,7 +136,7 @@ static inline void pps_reset_freq_interval(void) /** * pps_clear - Clears the PPS state variables * - * Must be called while holding a write on the xtime_lock + * Must be called while holding a write on the ntp_lock */ static inline void pps_clear(void) { @@ -149,7 +152,7 @@ static inline void pps_clear(void) * the last PPS signal. When it reaches 0, indicate that PPS signal is * missing. * - * Must be called while holding a write on the xtime_lock + * Must be called while holding a write on the ntp_lock */ static inline void pps_dec_valid(void) { @@ -233,6 +236,17 @@ static inline void pps_fill_timex(struct timex *txc) #endif /* CONFIG_NTP_PPS */ + +/** + * ntp_synced - Returns 1 if the NTP status is not UNSYNC + * + */ +static inline int ntp_synced(void) +{ + return !(time_status & STA_UNSYNC); +} + + /* * NTP methods: */ @@ -275,7 +289,7 @@ static inline s64 ntp_update_offset_fll(s64 offset64, long secs) time_status |= STA_MODE; - return div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); + return div64_long(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs); } static void ntp_update_offset(long offset) @@ -330,11 +344,13 @@ static void ntp_update_offset(long offset) /** * ntp_clear - Clears the NTP state variables - * - * Must be called while holding a write on the xtime_lock */ void ntp_clear(void) { + unsigned long flags; + + spin_lock_irqsave(&ntp_lock, flags); + time_adjust = 0; /* stop active adjtime() */ time_status |= STA_UNSYNC; time_maxerror = NTP_PHASE_LIMIT; @@ -347,8 +363,23 @@ void ntp_clear(void) /* Clear PPS state variables */ pps_clear(); + spin_unlock_irqrestore(&ntp_lock, flags); + } + +u64 ntp_tick_length(void) +{ + unsigned long flags; + s64 ret; + + spin_lock_irqsave(&ntp_lock, flags); + ret = tick_length; + spin_unlock_irqrestore(&ntp_lock, flags); + return ret; +} + + /* * Leap second processing. If in leap-insert state at the end of the * day, the system clock is set back one second; if in leap-delete @@ -357,14 +388,15 @@ void ntp_clear(void) static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) { enum hrtimer_restart res = HRTIMER_NORESTART; + unsigned long flags; + int leap = 0; - write_seqlock(&xtime_lock); - + spin_lock_irqsave(&ntp_lock, flags); switch (time_state) { case TIME_OK: break; case TIME_INS: - timekeeping_leap_insert(-1); + leap = -1; time_state = TIME_OOP; printk(KERN_NOTICE "Clock: inserting leap second 23:59:60 UTC\n"); @@ -372,7 +404,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) res = HRTIMER_RESTART; break; case TIME_DEL: - timekeeping_leap_insert(1); + leap = 1; time_tai--; time_state = TIME_WAIT; printk(KERN_NOTICE @@ -387,8 +419,14 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_state = TIME_OK; break; } + spin_unlock_irqrestore(&ntp_lock, flags); - write_sequnlock(&xtime_lock); + /* + * We have to call this outside of the ntp_lock to keep + * the proper locking hierarchy + */ + if (leap) + timekeeping_leap_insert(leap); return res; } @@ -404,6 +442,9 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) void second_overflow(void) { s64 delta; + unsigned long flags; + + spin_lock_irqsave(&ntp_lock, flags); /* Bump the maxerror field */ time_maxerror += MAXFREQ / NSEC_PER_USEC; @@ -423,23 +464,25 @@ void second_overflow(void) pps_dec_valid(); if (!time_adjust) - return; + goto out; if (time_adjust > MAX_TICKADJ) { time_adjust -= MAX_TICKADJ; tick_length += MAX_TICKADJ_SCALED; - return; + goto out; } if (time_adjust < -MAX_TICKADJ) { time_adjust += MAX_TICKADJ; tick_length -= MAX_TICKADJ_SCALED; - return; + goto out; } tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ) << NTP_SCALE_SHIFT; time_adjust = 0; +out: + spin_unlock_irqrestore(&ntp_lock, flags); } #ifdef CONFIG_GENERIC_CMOS_UPDATE @@ -663,7 +706,7 @@ int do_adjtimex(struct timex *txc) getnstimeofday(&ts); - write_seqlock_irq(&xtime_lock); + spin_lock_irq(&ntp_lock); if (txc->modes & ADJ_ADJTIME) { long save_adjust = time_adjust; @@ -705,7 +748,7 @@ int do_adjtimex(struct timex *txc) /* fill PPS status fields */ pps_fill_timex(txc); - write_sequnlock_irq(&xtime_lock); + spin_unlock_irq(&ntp_lock); txc->time.tv_sec = ts.tv_sec; txc->time.tv_usec = ts.tv_nsec; @@ -903,7 +946,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) pts_norm = pps_normalize_ts(*phase_ts); - write_seqlock_irqsave(&xtime_lock, flags); + spin_lock_irqsave(&ntp_lock, flags); /* clear the error bits, they will be set again if needed */ time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR); @@ -916,7 +959,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) * just start the frequency interval */ if (unlikely(pps_fbase.tv_sec == 0)) { pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); return; } @@ -931,7 +974,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) time_status |= STA_PPSJITTER; /* restart the frequency calibration interval */ pps_fbase = *raw_ts; - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); pr_err("hardpps: PPSJITTER: bad pulse\n"); return; } @@ -948,7 +991,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) hardpps_update_phase(pts_norm.nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); + spin_unlock_irqrestore(&ntp_lock, flags); } EXPORT_SYMBOL(hardpps); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index fd4a7b1625a2..e883f57a3cd3 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -575,11 +575,15 @@ void tick_broadcast_switch_to_oneshot(void) unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + if (cpumask_empty(tick_get_broadcast_mask())) + goto end; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) tick_broadcast_setup_oneshot(bc); + +end: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7656642e4b8e..3526038f2836 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -182,11 +182,7 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now) static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts) { - ktime_t now; - - now = ktime_get(); - - update_ts_time_stats(cpu, ts, now, NULL); + ktime_t now = ktime_get(); ts->idle_entrytime = now; ts->idle_active = 1; @@ -562,20 +558,21 @@ void tick_nohz_idle_exit(void) local_irq_disable(); - if (ts->idle_active || (ts->inidle && ts->tick_stopped)) + WARN_ON_ONCE(!ts->inidle); + + ts->inidle = 0; + + if (ts->idle_active || ts->tick_stopped) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(cpu, now); - if (!ts->inidle || !ts->tick_stopped) { - ts->inidle = 0; + if (!ts->tick_stopped) { local_irq_enable(); return; } - ts->inidle = 0; - /* Update jiffies first */ select_nohz_load_balancer(0); tick_do_update_jiffies64(now); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0c6358186401..403c2a092830 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -25,6 +25,8 @@ struct timekeeper { /* Current clocksource used for timekeeping. */ struct clocksource *clock; + /* NTP adjusted clock multiplier */ + u32 mult; /* The shift value of the current clocksource. */ int shift; @@ -45,12 +47,47 @@ struct timekeeper { /* Shift conversion between clock shifted nano seconds and * ntp shifted nano seconds. */ int ntp_error_shift; - /* NTP adjusted clock multiplier */ - u32 mult; + + /* The current time */ + struct timespec xtime; + /* + * wall_to_monotonic is what we need to add to xtime (or xtime corrected + * for sub jiffie times) to get to monotonic time. Monotonic is pegged + * at zero at system boot time, so wall_to_monotonic will be negative, + * however, we will ALWAYS keep the tv_nsec part positive so we can use + * the usual normalization. + * + * wall_to_monotonic is moved after resume from suspend for the + * monotonic time not to jump. We need to add total_sleep_time to + * wall_to_monotonic to get the real boot based time offset. + * + * - wall_to_monotonic is no longer the boot time, getboottime must be + * used instead. + */ + struct timespec wall_to_monotonic; + /* time spent in suspend */ + struct timespec total_sleep_time; + /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ + struct timespec raw_time; + + /* Seqlock for all timekeeper values */ + seqlock_t lock; }; static struct timekeeper timekeeper; +/* + * This read-write spinlock protects us from races in SMP while + * playing with xtime. + */ +__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); + + +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + + + /** * timekeeper_setup_internals - Set up internals to use clocksource clock. * @@ -135,47 +172,28 @@ static inline s64 timekeeping_get_ns_raw(void) return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); } -/* - * This read-write spinlock protects us from races in SMP while - * playing with xtime. - */ -__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); - - -/* - * The current time - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - * - * wall_to_monotonic is moved after resume from suspend for the monotonic - * time not to jump. We need to add total_sleep_time to wall_to_monotonic - * to get the real boot based time offset. - * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. - */ -static struct timespec xtime __attribute__ ((aligned (16))); -static struct timespec wall_to_monotonic __attribute__ ((aligned (16))); -static struct timespec total_sleep_time; - -/* - * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. - */ -static struct timespec raw_time; +/* must hold write on timekeeper.lock */ +static void timekeeping_update(bool clearntp) +{ + if (clearntp) { + timekeeper.ntp_error = 0; + ntp_clear(); + } + update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic, + timekeeper.clock, timekeeper.mult); +} -/* flag for if timekeeping is suspended */ -int __read_mostly timekeeping_suspended; -/* must hold xtime_lock */ void timekeeping_leap_insert(int leapsecond) { - xtime.tv_sec += leapsecond; - wall_to_monotonic.tv_sec -= leapsecond; - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + unsigned long flags; + + write_seqlock_irqsave(&timekeeper.lock, flags); + timekeeper.xtime.tv_sec += leapsecond; + timekeeper.wall_to_monotonic.tv_sec -= leapsecond; + timekeeping_update(false); + write_sequnlock_irqrestore(&timekeeper.lock, flags); + } /** @@ -202,10 +220,10 @@ static void timekeeping_forward_now(void) /* If arch requires, add in gettimeoffset() */ nsec += arch_gettimeoffset(); - timespec_add_ns(&xtime, nsec); + timespec_add_ns(&timekeeper.xtime, nsec); nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); - timespec_add_ns(&raw_time, nsec); + timespec_add_ns(&timekeeper.raw_time, nsec); } /** @@ -222,15 +240,15 @@ void getnstimeofday(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - *ts = xtime; + *ts = timekeeper.xtime; nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts, nsecs); } @@ -245,14 +263,16 @@ ktime_t ktime_get(void) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - secs = xtime.tv_sec + wall_to_monotonic.tv_sec; - nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec; + seq = read_seqbegin(&timekeeper.lock); + secs = timekeeper.xtime.tv_sec + + timekeeper.wall_to_monotonic.tv_sec; + nsecs = timekeeper.xtime.tv_nsec + + timekeeper.wall_to_monotonic.tv_nsec; nsecs += timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); /* * Use ktime_set/ktime_add_ns to create a proper ktime on * 32-bit architectures without CONFIG_KTIME_SCALAR. @@ -278,14 +298,14 @@ void ktime_get_ts(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - *ts = xtime; - tomono = wall_to_monotonic; + seq = read_seqbegin(&timekeeper.lock); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, ts->tv_nsec + tomono.tv_nsec + nsecs); @@ -313,10 +333,10 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) do { u32 arch_offset; - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - *ts_raw = raw_time; - *ts_real = xtime; + *ts_raw = timekeeper.raw_time; + *ts_real = timekeeper.xtime; nsecs_raw = timekeeping_get_ns_raw(); nsecs_real = timekeeping_get_ns(); @@ -326,7 +346,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) nsecs_raw += arch_offset; nsecs_real += arch_offset; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts_raw, nsecs_raw); timespec_add_ns(ts_real, nsecs_real); @@ -365,23 +385,19 @@ int do_settimeofday(const struct timespec *tv) if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); - ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; - ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; - wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta); - - xtime = *tv; + ts_delta.tv_sec = tv->tv_sec - timekeeper.xtime.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - timekeeper.xtime.tv_nsec; + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, ts_delta); - timekeeper.ntp_error = 0; - ntp_clear(); - - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeper.xtime = *tv; + timekeeping_update(true); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -405,20 +421,17 @@ int timekeeping_inject_offset(struct timespec *ts) if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); - xtime = timespec_add(xtime, *ts); - wall_to_monotonic = timespec_sub(wall_to_monotonic, *ts); - - timekeeper.ntp_error = 0; - ntp_clear(); + timekeeper.xtime = timespec_add(timekeeper.xtime, *ts); + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, *ts); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -490,11 +503,11 @@ void getrawmonotonic(struct timespec *ts) s64 nsecs; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); nsecs = timekeeping_get_ns_raw(); - *ts = raw_time; + *ts = timekeeper.raw_time; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); timespec_add_ns(ts, nsecs); } @@ -510,24 +523,30 @@ int timekeeping_valid_for_hres(void) int ret; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred - * - * Caller must observe xtime_lock via read_seqbegin/read_seqretry to - * ensure that the clocksource does not change! */ u64 timekeeping_max_deferment(void) { - return timekeeper.clock->max_idle_ns; + unsigned long seq; + u64 ret; + do { + seq = read_seqbegin(&timekeeper.lock); + + ret = timekeeper.clock->max_idle_ns; + + } while (read_seqretry(&timekeeper.lock, seq)); + + return ret; } /** @@ -572,28 +591,29 @@ void __init timekeeping_init(void) read_persistent_clock(&now); read_boot_clock(&boot); - write_seqlock_irqsave(&xtime_lock, flags); + seqlock_init(&timekeeper.lock); ntp_init(); + write_seqlock_irqsave(&timekeeper.lock, flags); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); timekeeper_setup_internals(clock); - xtime.tv_sec = now.tv_sec; - xtime.tv_nsec = now.tv_nsec; - raw_time.tv_sec = 0; - raw_time.tv_nsec = 0; + timekeeper.xtime.tv_sec = now.tv_sec; + timekeeper.xtime.tv_nsec = now.tv_nsec; + timekeeper.raw_time.tv_sec = 0; + timekeeper.raw_time.tv_nsec = 0; if (boot.tv_sec == 0 && boot.tv_nsec == 0) { - boot.tv_sec = xtime.tv_sec; - boot.tv_nsec = xtime.tv_nsec; + boot.tv_sec = timekeeper.xtime.tv_sec; + boot.tv_nsec = timekeeper.xtime.tv_nsec; } - set_normalized_timespec(&wall_to_monotonic, + set_normalized_timespec(&timekeeper.wall_to_monotonic, -boot.tv_sec, -boot.tv_nsec); - total_sleep_time.tv_sec = 0; - total_sleep_time.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + timekeeper.total_sleep_time.tv_sec = 0; + timekeeper.total_sleep_time.tv_nsec = 0; + write_sequnlock_irqrestore(&timekeeper.lock, flags); } /* time in seconds when suspend began */ @@ -614,9 +634,11 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta) return; } - xtime = timespec_add(xtime, *delta); - wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta); - total_sleep_time = timespec_add(total_sleep_time, *delta); + timekeeper.xtime = timespec_add(timekeeper.xtime, *delta); + timekeeper.wall_to_monotonic = + timespec_sub(timekeeper.wall_to_monotonic, *delta); + timekeeper.total_sleep_time = timespec_add( + timekeeper.total_sleep_time, *delta); } @@ -640,17 +662,15 @@ void timekeeping_inject_sleeptime(struct timespec *delta) if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) return; - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); + timekeeping_forward_now(); __timekeeping_inject_sleeptime(delta); - timekeeper.ntp_error = 0; - ntp_clear(); - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(true); - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); /* signal hrtimers about time change */ clock_was_set(); @@ -673,7 +693,7 @@ static void timekeeping_resume(void) clocksource_resume(); - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); @@ -683,7 +703,7 @@ static void timekeeping_resume(void) timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); timekeeper.ntp_error = 0; timekeeping_suspended = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); touch_softlockup_watchdog(); @@ -701,7 +721,7 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); - write_seqlock_irqsave(&xtime_lock, flags); + write_seqlock_irqsave(&timekeeper.lock, flags); timekeeping_forward_now(); timekeeping_suspended = 1; @@ -711,7 +731,7 @@ static int timekeeping_suspend(void) * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ - delta = timespec_sub(xtime, timekeeping_suspend_time); + delta = timespec_sub(timekeeper.xtime, timekeeping_suspend_time); delta_delta = timespec_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* @@ -724,7 +744,7 @@ static int timekeeping_suspend(void) timekeeping_suspend_time = timespec_add(timekeeping_suspend_time, delta_delta); } - write_sequnlock_irqrestore(&xtime_lock, flags); + write_sequnlock_irqrestore(&timekeeper.lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); @@ -775,7 +795,7 @@ static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, * Now calculate the error in (1 << look_ahead) ticks, but first * remove the single look ahead already included in the error. */ - tick_error = tick_length >> (timekeeper.ntp_error_shift + 1); + tick_error = ntp_tick_length() >> (timekeeper.ntp_error_shift + 1); tick_error -= timekeeper.xtime_interval >> 1; error = ((error - tick_error) >> look_ahead) + tick_error; @@ -943,22 +963,22 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) timekeeper.xtime_nsec += timekeeper.xtime_interval << shift; while (timekeeper.xtime_nsec >= nsecps) { timekeeper.xtime_nsec -= nsecps; - xtime.tv_sec++; + timekeeper.xtime.tv_sec++; second_overflow(); } /* Accumulate raw time */ raw_nsecs = timekeeper.raw_interval << shift; - raw_nsecs += raw_time.tv_nsec; + raw_nsecs += timekeeper.raw_time.tv_nsec; if (raw_nsecs >= NSEC_PER_SEC) { u64 raw_secs = raw_nsecs; raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - raw_time.tv_sec += raw_secs; + timekeeper.raw_time.tv_sec += raw_secs; } - raw_time.tv_nsec = raw_nsecs; + timekeeper.raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ - timekeeper.ntp_error += tick_length << shift; + timekeeper.ntp_error += ntp_tick_length() << shift; timekeeper.ntp_error -= (timekeeper.xtime_interval + timekeeper.xtime_remainder) << (timekeeper.ntp_error_shift + shift); @@ -970,17 +990,19 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) /** * update_wall_time - Uses the current clocksource to increment the wall time * - * Called from the timer interrupt, must hold a write on xtime_lock. */ static void update_wall_time(void) { struct clocksource *clock; cycle_t offset; int shift = 0, maxshift; + unsigned long flags; + + write_seqlock_irqsave(&timekeeper.lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) - return; + goto out; clock = timekeeper.clock; @@ -989,7 +1011,8 @@ static void update_wall_time(void) #else offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #endif - timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift; + timekeeper.xtime_nsec = (s64)timekeeper.xtime.tv_nsec << + timekeeper.shift; /* * With NO_HZ we may have to accumulate many cycle_intervals @@ -1002,7 +1025,7 @@ static void update_wall_time(void) shift = ilog2(offset) - ilog2(timekeeper.cycle_interval); shift = max(0, shift); /* Bound shift to one less then what overflows tick_length */ - maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1; + maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { offset = logarithmic_accumulation(offset, shift); @@ -1040,8 +1063,10 @@ static void update_wall_time(void) * Store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ - xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1; - timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift; + timekeeper.xtime.tv_nsec = ((s64)timekeeper.xtime_nsec >> + timekeeper.shift) + 1; + timekeeper.xtime_nsec -= (s64)timekeeper.xtime.tv_nsec << + timekeeper.shift; timekeeper.ntp_error += timekeeper.xtime_nsec << timekeeper.ntp_error_shift; @@ -1049,15 +1074,17 @@ static void update_wall_time(void) * Finally, make sure that after the rounding * xtime.tv_nsec isn't larger then NSEC_PER_SEC */ - if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) { - xtime.tv_nsec -= NSEC_PER_SEC; - xtime.tv_sec++; + if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) { + timekeeper.xtime.tv_nsec -= NSEC_PER_SEC; + timekeeper.xtime.tv_sec++; second_overflow(); } - /* check to see if there is a new clocksource to use */ - update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, - timekeeper.mult); + timekeeping_update(false); + +out: + write_sequnlock_irqrestore(&timekeeper.lock, flags); + } /** @@ -1074,8 +1101,10 @@ static void update_wall_time(void) void getboottime(struct timespec *ts) { struct timespec boottime = { - .tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec, - .tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec + .tv_sec = timekeeper.wall_to_monotonic.tv_sec + + timekeeper.total_sleep_time.tv_sec, + .tv_nsec = timekeeper.wall_to_monotonic.tv_nsec + + timekeeper.total_sleep_time.tv_nsec }; set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); @@ -1101,13 +1130,13 @@ void get_monotonic_boottime(struct timespec *ts) WARN_ON(timekeeping_suspended); do { - seq = read_seqbegin(&xtime_lock); - *ts = xtime; - tomono = wall_to_monotonic; - sleep = total_sleep_time; + seq = read_seqbegin(&timekeeper.lock); + *ts = timekeeper.xtime; + tomono = timekeeper.wall_to_monotonic; + sleep = timekeeper.total_sleep_time; nsecs = timekeeping_get_ns(); - } while (read_seqretry(&xtime_lock, seq)); + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec, ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs); @@ -1137,19 +1166,19 @@ EXPORT_SYMBOL_GPL(ktime_get_boottime); */ void monotonic_to_bootbased(struct timespec *ts) { - *ts = timespec_add(*ts, total_sleep_time); + *ts = timespec_add(*ts, timekeeper.total_sleep_time); } EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { - return xtime.tv_sec; + return timekeeper.xtime.tv_sec; } EXPORT_SYMBOL(get_seconds); struct timespec __current_kernel_time(void) { - return xtime; + return timekeeper.xtime; } struct timespec current_kernel_time(void) @@ -1158,10 +1187,10 @@ struct timespec current_kernel_time(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - now = xtime; - } while (read_seqretry(&xtime_lock, seq)); + now = timekeeper.xtime; + } while (read_seqretry(&timekeeper.lock, seq)); return now; } @@ -1173,11 +1202,11 @@ struct timespec get_monotonic_coarse(void) unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); + seq = read_seqbegin(&timekeeper.lock); - now = xtime; - mono = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + now = timekeeper.xtime; + mono = timekeeper.wall_to_monotonic; + } while (read_seqretry(&timekeeper.lock, seq)); set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); @@ -1209,11 +1238,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, unsigned long seq; do { - seq = read_seqbegin(&xtime_lock); - *xtim = xtime; - *wtom = wall_to_monotonic; - *sleep = total_sleep_time; - } while (read_seqretry(&xtime_lock, seq)); + seq = read_seqbegin(&timekeeper.lock); + *xtim = timekeeper.xtime; + *wtom = timekeeper.wall_to_monotonic; + *sleep = timekeeper.total_sleep_time; + } while (read_seqretry(&timekeeper.lock, seq)); } /** @@ -1225,9 +1254,10 @@ ktime_t ktime_get_monotonic_offset(void) struct timespec wtom; do { - seq = read_seqbegin(&xtime_lock); - wtom = wall_to_monotonic; - } while (read_seqretry(&xtime_lock, seq)); + seq = read_seqbegin(&timekeeper.lock); + wtom = timekeeper.wall_to_monotonic; + } while (read_seqretry(&timekeeper.lock, seq)); + return timespec_to_ktime(wtom); } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index cd3134510f3d..a1d2849f2473 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE + select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 867bd1dd2dd0..0fa92f677c92 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -249,7 +249,8 @@ static void update_ftrace_function(void) #else __ftrace_trace_function = func; #endif - ftrace_trace_function = ftrace_test_stop_func; + ftrace_trace_function = + (func == ftrace_stub) ? func : ftrace_test_stop_func; #endif } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f5b7b5c1195b..cf8d11e91efd 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -154,33 +154,10 @@ enum { static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; -#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) - -/** - * tracing_on - enable all tracing buffers - * - * This function enables all tracing buffers that may have been - * disabled with tracing_off. - */ -void tracing_on(void) -{ - set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_on); +/* Used for individual buffers (after the counter) */ +#define RB_BUFFER_OFF (1 << 20) -/** - * tracing_off - turn off all tracing buffers - * - * This function stops all tracing buffers from recording data. - * It does not disable any overhead the tracers themselves may - * be causing. This function simply causes all recording to - * the ring buffers to fail. - */ -void tracing_off(void) -{ - clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); -} -EXPORT_SYMBOL_GPL(tracing_off); +#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data) /** * tracing_off_permanent - permanently disable ring buffers @@ -193,15 +170,6 @@ void tracing_off_permanent(void) set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); } -/** - * tracing_is_on - show state of ring buffers enabled - */ -int tracing_is_on(void) -{ - return ring_buffer_flags == RB_BUFFERS_ON; -} -EXPORT_SYMBOL_GPL(tracing_is_on); - #define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array)) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) @@ -2619,6 +2587,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer) EXPORT_SYMBOL_GPL(ring_buffer_record_enable); /** + * ring_buffer_record_off - stop all writes into the buffer + * @buffer: The ring buffer to stop writes to. + * + * This prevents all writes to the buffer. Any attempt to write + * to the buffer after this will fail and return NULL. + * + * This is different than ring_buffer_record_disable() as + * it works like an on/off switch, where as the disable() verison + * must be paired with a enable(). + */ +void ring_buffer_record_off(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd | RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_off); + +/** + * ring_buffer_record_on - restart writes into the buffer + * @buffer: The ring buffer to start writes to. + * + * This enables all writes to the buffer that was disabled by + * ring_buffer_record_off(). + * + * This is different than ring_buffer_record_enable() as + * it works like an on/off switch, where as the enable() verison + * must be paired with a disable(). + */ +void ring_buffer_record_on(struct ring_buffer *buffer) +{ + unsigned int rd; + unsigned int new_rd; + + do { + rd = atomic_read(&buffer->record_disabled); + new_rd = rd & ~RB_BUFFER_OFF; + } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); +} +EXPORT_SYMBOL_GPL(ring_buffer_record_on); + +/** + * ring_buffer_record_is_on - return true if the ring buffer can write + * @buffer: The ring buffer to see if write is enabled + * + * Returns true if the ring buffer is in a state that it accepts writes. + */ +int ring_buffer_record_is_on(struct ring_buffer *buffer) +{ + return !atomic_read(&buffer->record_disabled); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop @@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_read_page); -#ifdef CONFIG_TRACING -static ssize_t -rb_simple_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - char buf[64]; - int r; - - if (test_bit(RB_BUFFERS_DISABLED_BIT, p)) - r = sprintf(buf, "permanently disabled\n"); - else - r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p)); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); -} - -static ssize_t -rb_simple_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - unsigned long *p = filp->private_data; - unsigned long val; - int ret; - - ret = kstrtoul_from_user(ubuf, cnt, 10, &val); - if (ret) - return ret; - - if (val) - set_bit(RB_BUFFERS_ON_BIT, p); - else - clear_bit(RB_BUFFERS_ON_BIT, p); - - (*ppos)++; - - return cnt; -} - -static const struct file_operations rb_simple_fops = { - .open = tracing_open_generic, - .read = rb_simple_read, - .write = rb_simple_write, - .llseek = default_llseek, -}; - - -static __init int rb_init_debugfs(void) -{ - struct dentry *d_tracer; - - d_tracer = tracing_init_dentry(); - - trace_create_file("tracing_on", 0644, d_tracer, - &ring_buffer_flags, &rb_simple_fops); - - return 0; -} - -fs_initcall(rb_init_debugfs); -#endif - #ifdef CONFIG_HOTPLUG_CPU static int rb_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 10d5503f0d04..3a19c354edd6 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -36,6 +36,7 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/poll.h> +#include <linux/nmi.h> #include <linux/fs.h> #include "trace.h" @@ -352,6 +353,59 @@ static void wakeup_work_handler(struct work_struct *work) static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); /** + * tracing_on - enable tracing buffers + * + * This function enables tracing buffers that may have been + * disabled with tracing_off. + */ +void tracing_on(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 0; +} +EXPORT_SYMBOL_GPL(tracing_on); + +/** + * tracing_off - turn off tracing buffers + * + * This function stops the tracing buffers from recording data. + * It does not disable any overhead the tracers themselves may + * be causing. This function simply causes all recording to + * the ring buffers to fail. + */ +void tracing_off(void) +{ + if (global_trace.buffer) + ring_buffer_record_on(global_trace.buffer); + /* + * This flag is only looked at when buffers haven't been + * allocated yet. We don't really care about the race + * between setting this flag and actually turning + * on the buffer. + */ + global_trace.buffer_disabled = 1; +} +EXPORT_SYMBOL_GPL(tracing_off); + +/** + * tracing_is_on - show state of ring buffers enabled + */ +int tracing_is_on(void) +{ + if (global_trace.buffer) + return ring_buffer_record_is_on(global_trace.buffer); + return !global_trace.buffer_disabled; +} +EXPORT_SYMBOL_GPL(tracing_is_on); + +/** * trace_wake_up - wake up tasks waiting for trace input * * Schedules a delayed work to wake up any task that is blocked on the @@ -4567,6 +4621,55 @@ static __init void create_trace_options_dir(void) create_trace_option_core_file(trace_options[i], i); } +static ssize_t +rb_simple_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + char buf[64]; + int r; + + if (buffer) + r = ring_buffer_record_is_on(buffer); + else + r = 0; + + r = sprintf(buf, "%d\n", r); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +rb_simple_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct ring_buffer *buffer = filp->private_data; + unsigned long val; + int ret; + + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) + return ret; + + if (buffer) { + if (val) + ring_buffer_record_on(buffer); + else + ring_buffer_record_off(buffer); + } + + (*ppos)++; + + return cnt; +} + +static const struct file_operations rb_simple_fops = { + .open = tracing_open_generic, + .read = rb_simple_read, + .write = rb_simple_write, + .llseek = default_llseek, +}; + static __init int tracer_init_debugfs(void) { struct dentry *d_tracer; @@ -4626,6 +4729,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("trace_clock", 0644, d_tracer, NULL, &trace_clock_fops); + trace_create_file("tracing_on", 0644, d_tracer, + global_trace.buffer, &rb_simple_fops); + #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, &tracing_dyn_info_fops); @@ -4798,6 +4904,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); } + touch_nmi_watchdog(); trace_printk_seq(&iter.seq); } @@ -4863,6 +4970,8 @@ __init static int tracer_alloc_buffers(void) goto out_free_cpumask; } global_trace.entries = ring_buffer_size(global_trace.buffer); + if (global_trace.buffer_disabled) + tracing_off(); #ifdef CONFIG_TRACER_MAX_TRACE diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 54faec790bc1..95059f091a24 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -154,6 +154,7 @@ struct trace_array { struct ring_buffer *buffer; unsigned long entries; int cpu; + int buffer_disabled; cycle_t time_start; struct task_struct *waiter; struct trace_array_cpu *data[NR_CPUS]; @@ -835,13 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[]; filter) #include "trace_entries.h" -#ifdef CONFIG_PERF_EVENTS #ifdef CONFIG_FUNCTION_TRACER int perf_ftrace_event_register(struct ftrace_event_call *call, enum trace_reg type, void *data); #else #define perf_ftrace_event_register NULL #endif /* CONFIG_FUNCTION_TRACER */ -#endif /* CONFIG_PERF_EVENTS */ #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bec7b5b53e03..f2c5638bb5ab 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -253,11 +253,13 @@ struct workqueue_struct *system_long_wq __read_mostly; struct workqueue_struct *system_nrt_wq __read_mostly; struct workqueue_struct *system_unbound_wq __read_mostly; struct workqueue_struct *system_freezable_wq __read_mostly; +struct workqueue_struct *system_nrt_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_wq); EXPORT_SYMBOL_GPL(system_long_wq); EXPORT_SYMBOL_GPL(system_nrt_wq); EXPORT_SYMBOL_GPL(system_unbound_wq); EXPORT_SYMBOL_GPL(system_freezable_wq); +EXPORT_SYMBOL_GPL(system_nrt_freezable_wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> @@ -3833,8 +3835,11 @@ static int __init init_workqueues(void) WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); + system_nrt_freezable_wq = alloc_workqueue("events_nrt_freezable", + WQ_NON_REENTRANT | WQ_FREEZABLE, 0); BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq || - !system_unbound_wq || !system_freezable_wq); + !system_unbound_wq || !system_freezable_wq || + !system_nrt_freezable_wq); return 0; } early_initcall(init_workqueues); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9739c0b45e93..05037dc9bde7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -931,6 +931,30 @@ config RCU_CPU_STALL_VERBOSE Say Y if you want to enable such checks. +config RCU_CPU_STALL_INFO + bool "Print additional diagnostics on RCU CPU stall" + depends on (TREE_RCU || TREE_PREEMPT_RCU) && DEBUG_KERNEL + default n + help + For each stalled CPU that is aware of the current RCU grace + period, print out additional per-CPU diagnostic information + regarding scheduling-clock ticks, idle state, and, + for RCU_FAST_NO_HZ kernels, idle-entry state. + + Say N if you are unsure. + + Say Y if you want to enable such diagnostics. + +config RCU_TRACE + bool "Enable tracing for RCU" + depends on DEBUG_KERNEL + help + This option provides tracing in RCU which presents stats + in debugfs for debugging RCU implementation. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d0e57a3cda18..58a08fc7414a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -230,10 +230,30 @@ struct mem_cgroup { * the counter to account for memory usage */ struct res_counter res; - /* - * the counter to account for mem+swap usage. - */ - struct res_counter memsw; + + union { + /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; + + /* + * rcu_freeing is used only when freeing struct mem_cgroup, + * so put it into a union to avoid wasting more memory. + * It must be disjoint from the css field. It could be + * in a union with the res field, but res plays a much + * larger part in mem_cgroup life than memsw, and might + * be of interest, even at time of free, when debugging. + * So share rcu_head with the less interesting memsw. + */ + struct rcu_head rcu_freeing; + /* + * But when using vfree(), that cannot be done at + * interrupt time, so we must then queue the work. + */ + struct work_struct work_freeing; + }; + /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. @@ -4780,6 +4800,27 @@ out_free: } /* + * Helpers for freeing a vzalloc()ed mem_cgroup by RCU, + * but in process context. The work_freeing structure is overlaid + * on the rcu_freeing structure, which itself is overlaid on memsw. + */ +static void vfree_work(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, work_freeing); + vfree(memcg); +} +static void vfree_rcu(struct rcu_head *rcu_head) +{ + struct mem_cgroup *memcg; + + memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing); + INIT_WORK(&memcg->work_freeing, vfree_work); + schedule_work(&memcg->work_freeing); +} + +/* * At destroying mem_cgroup, references from swap_cgroup can remain. * (scanning all at force_empty is too costly...) * @@ -4802,9 +4843,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_percpu(memcg->stat); if (sizeof(struct mem_cgroup) < PAGE_SIZE) - kfree(memcg); + kfree_rcu(memcg, rcu_freeing); else - vfree(memcg); + call_rcu(&memcg->rcu_freeing, vfree_rcu); } static void mem_cgroup_get(struct mem_cgroup *memcg) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 86f3b885b4f3..c48adc565e92 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1857,11 +1857,6 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } -static void opt_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_options_rcu, rcu)); -} - /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket @@ -1938,7 +1933,7 @@ int cipso_v4_sock_setattr(struct sock *sk, } rcu_assign_pointer(sk_inet->inet_opt, opt); if (old) - call_rcu(&old->rcu, opt_kfree_rcu); + kfree_rcu(old, rcu); return 0; @@ -2005,7 +2000,7 @@ int cipso_v4_req_setattr(struct request_sock *req, req_inet = inet_rsk(req); opt = xchg(&req_inet->opt, opt); if (opt) - call_rcu(&opt->rcu, opt_kfree_rcu); + kfree_rcu(opt, rcu); return 0; @@ -2075,7 +2070,7 @@ static int cipso_v4_delopt(struct ip_options_rcu **opt_ptr) * remove the entire option struct */ *opt_ptr = NULL; hdr_delta = opt->opt.optlen; - call_rcu(&opt->rcu, opt_kfree_rcu); + kfree_rcu(opt, rcu); } return hdr_delta; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8aa87c19fa00..5343d9ac510b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -445,11 +445,6 @@ out: } -static void opt_kfree_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct ip_options_rcu, rcu)); -} - /* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. @@ -525,7 +520,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, } rcu_assign_pointer(inet->inet_opt, opt); if (old) - call_rcu(&old->rcu, opt_kfree_rcu); + kfree_rcu(old, rcu); break; } case IP_PKTINFO: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index b853f06cc148..16c33e308121 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -257,7 +257,6 @@ static struct inet6_dev *ip6_mc_find_dev_rcu(struct net *net, if (rt) { dev = rt->dst.dev; - dev_hold(dev); dst_release(&rt->dst); } } else diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8c2e3ab58f2a..22b766407de1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1077,7 +1077,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct net *net = dev_net(dev); if (unlikely(!idev)) - return NULL; + return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); if (unlikely(!rt)) { diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index edf167e3b8f3..30420bc1f699 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -413,12 +413,6 @@ struct mesh_path *mesh_path_lookup_by_idx(int idx, struct ieee80211_sub_if_data return NULL; } -static void mesh_gate_node_reclaim(struct rcu_head *rp) -{ - struct mpath_node *node = container_of(rp, struct mpath_node, rcu); - kfree(node); -} - /** * mesh_path_add_gate - add the given mpath to a mesh gate to our path table * @mpath: gate path to add to table @@ -479,7 +473,7 @@ static int mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) if (gate->mpath == mpath) { spin_lock_bh(&tbl->gates_lock); hlist_del_rcu(&gate->list); - call_rcu(&gate->rcu, mesh_gate_node_reclaim); + kfree_rcu(gate, rcu); spin_unlock_bh(&tbl->gates_lock); mpath->sdata->u.mesh.num_gates--; mpath->is_gate = false; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 10687692831e..b49da6c925b3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -943,20 +943,21 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, } } - if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).pid, - nlmsg_report(nlh)) < 0) { + if (del_timer(&ct->timeout)) { + if (nf_conntrack_event_report(IPCT_DESTROY, ct, + NETLINK_CB(skb).pid, + nlmsg_report(nlh)) < 0) { + nf_ct_delete_from_lists(ct); + /* we failed to report the event, try later */ + nf_ct_insert_dying_list(ct); + nf_ct_put(ct); + return 0; + } + /* death_by_timeout would report the event again */ + set_bit(IPS_DYING_BIT, &ct->status); nf_ct_delete_from_lists(ct); - /* we failed to report the event, try later */ - nf_ct_insert_dying_list(ct); nf_ct_put(ct); - return 0; } - - /* death_by_timeout would report the event again */ - set_bit(IPS_DYING_BIT, &ct->status); - - nf_ct_kill(ct); nf_ct_put(ct); return 0; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 60d47180f043..02a21abea65e 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -469,11 +469,15 @@ enqueue: if (slot->qlen == 1) { /* The flow is new */ if (q->tail == NULL) { /* It is the first flow */ slot->next = x; - q->tail = slot; } else { slot->next = q->tail->next; q->tail->next = x; } + /* We put this flow at the end of our flow list. + * This might sound unfair for a new flow to wait after old ones, + * but we could endup servicing new flows only, and freeze old ones. + */ + q->tail = slot; /* We could use a bigger initial quantum for new flows */ slot->allot = q->scaled_quantum; } |