diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 7f40c72..273e654d 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -39,7 +39,7 @@
 write-side contention and parallelize the other write-side overheads by
 providing a fine-grained locking design, however, it would be interesting
 to see how much of the performance advantage reported in 1990 remains
-in 2004.
+today.
 
 At about this same time, Adams [Adams91] described ``chaotic relaxation'',
 where the normal barriers between successive iterations of convergent
@@ -86,9 +86,9 @@
 [McKenney98].
 
 In 1999, the Tornado and K42 groups described their "generations"
-mechanism, which quite similar to RCU [Gamsa99].  These operating systems
-made pervasive use of RCU in place of "existence locks", which greatly
-simplifies locking hierarchies.
+mechanism, which is quite similar to RCU [Gamsa99].  These operating
+systems made pervasive use of RCU in place of "existence locks", which
+greatly simplifies locking hierarchies and helps avoid deadlocks.
 
 2001 saw the first RCU presentation involving Linux [McKenney01a]
 at OLS.  The resulting abundance of RCU patches was presented the
@@ -106,8 +106,11 @@
 form of memory barriers.  Researchers at Sun worked along similar lines
 in the same timeframe [HerlihyLM02].  These techniques can be thought
 of as inside-out reference counts, where the count is represented by the
-number of hazard pointers referencing a given data structure (rather than
-the more conventional counter field within the data structure itself).
+number of hazard pointers referencing a given data structure rather than
+the more conventional counter field within the data structure itself.
+The key advantage of inside-out reference counts is that they can be
+stored in immortal variables, thus allowing races between access and
+deletion to be avoided.
 
 By the same token, RCU can be thought of as a "bulk reference count",
 where some form of reference counter covers all reference by a given CPU
@@ -179,7 +182,25 @@
 (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].
+Lockers" LWN article [NeilBrown2011MeetTheLockers].  Some academic
+work looked at debugging uses of RCU [Seyster:2011:RFA:2075416.2075425].
+
+In 2012, Josh Triplett received his Ph.D. with his dissertation
+covering RCU-protected resizable hash tables and the relationship
+between memory barriers and read-side traversal order:  If the updater
+is making changes in the opposite direction from the read-side traveral
+order, the updater need only execute a memory-barrier instruction,
+but if in the same direction, the updater needs to wait for a grace
+period between the individual updates [JoshTriplettPhD].  Also in 2012,
+after seventeen years of attempts, an RCU paper made it into a top-flight
+academic journal, IEEE Transactions on Parallel and Distributed Systems
+[MathieuDesnoyers2012URCU].  A group of researchers in Spain applied
+user-level RCU to crowd simulation [GuillermoVigueras2012RCUCrowd], and
+another group of researchers in Europe produced a formal description of
+RCU based on separation logic [AlexeyGotsman2012VerifyGraceExtended],
+which was published in the 2013 European Symposium on Programming
+[AlexeyGotsman2013ESOPRCU].
+
 
 
 Bibtex Entries
@@ -193,13 +214,12 @@
 ,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.
+	http://portal.acm.org/citation.cfm?id=320619&dl=GUIDE,
+	[Viewed December 3, 2007]
 }
 }
 
@@ -309,7 +329,7 @@
 ,doi = {http://doi.acm.org/10.1145/42392.42399}
 ,publisher = {ACM}
 ,address = {New York, NY, USA}
-,annotation= {
+,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
@@ -346,8 +366,9 @@
 }
 }
 
-@Book{Adams91
-,Author="Gregory R. Adams"
+# Was Adams91, see also syncrefs.bib.
+@Book{Andrews91textbook
+,Author="Gregory R. Andrews"
 ,title="Concurrent Programming, Principles, and Practices"
 ,Publisher="Benjamin Cummins"
 ,Year="1991"
@@ -398,39 +419,39 @@
 }
 }
 
-@conference{Pu95a,
-Author = "Calton Pu and Tito Autrey and Andrew Black and Charles Consel and
+@conference{Pu95a
+,Author = "Calton Pu and Tito Autrey and Andrew Black and Charles Consel and
 Crispin Cowan and Jon Inouye and Lakshmi Kethana and Jonathan Walpole and
-Ke Zhang",
-Title = "Optimistic Incremental Specialization: Streamlining a Commercial
-Operating System",
-Booktitle = "15\textsuperscript{th} ACM Symposium on
-Operating Systems Principles (SOSP'95)",
-address = "Copper Mountain, CO",
-month="December",
-year="1995",
-pages="314-321",
-annotation="
+Ke Zhang"
+,Title = "Optimistic Incremental Specialization: Streamlining a Commercial
+,Operating System"
+,Booktitle = "15\textsuperscript{th} ACM Symposium on
+,Operating Systems Principles (SOSP'95)"
+,address = "Copper Mountain, CO"
+,month="December"
+,year="1995"
+,pages="314-321"
+,annotation={
 	Uses a replugger, but with a flag to signal when people are
 	using the resource at hand.  Only one reader at a time.
-"
+}
 }
 
-@conference{Cowan96a,
-Author = "Crispin Cowan and Tito Autrey and Charles Krasic and
-Calton Pu and Jonathan Walpole",
-Title = "Fast Concurrent Dynamic Linking for an Adaptive Operating System",
-Booktitle = "International Conference on Configurable Distributed Systems
-(ICCDS'96)",
-address = "Annapolis, MD",
-month="May",
-year="1996",
-pages="108",
-isbn="0-8186-7395-8",
-annotation="
+@conference{Cowan96a
+,Author = "Crispin Cowan and Tito Autrey and Charles Krasic and
+,Calton Pu and Jonathan Walpole"
+,Title = "Fast Concurrent Dynamic Linking for an Adaptive Operating System"
+,Booktitle = "International Conference on Configurable Distributed Systems
+(ICCDS'96)"
+,address = "Annapolis, MD"
+,month="May"
+,year="1996"
+,pages="108"
+,isbn="0-8186-7395-8"
+,annotation={
 	Uses a replugger, but with a counter to signal when people are
 	using the resource at hand.  Allows multiple readers.
-"
+}
 }
 
 @techreport{Slingwine95
@@ -493,14 +514,13 @@
 ,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.
+	http://www.rdrop.com/users/paulmck/RCU/rclockpdcsproof.pdf
+	[Viewed December 3, 2007]
 }
 }
 
@@ -514,13 +534,12 @@
 ,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).
+	http://www.usenix.org/events/osdi99/full_papers/gamsa/gamsa.pdf
+	[Viewed August 30, 2006]
 }
 }
 
@@ -611,9 +630,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100259266316456&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Memory-barrier and Alpha thread.  100 messages, not too bad...
-"
+}
 }
 
 @unpublished{Spraul01
@@ -624,10 +643,10 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=100264675012867&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Suggested burying memory barriers in Linux's list-manipulation
 	primitives.
-"
+}
 }
 
 @unpublished{LinusTorvalds2001a
@@ -638,6 +657,8 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2001/10/13/105}
 [Viewed August 21, 2004]"
+,annotation={
+}
 }
 
 @unpublished{Blanchard02a
@@ -657,10 +678,10 @@
 ,Month="June"
 ,Year="2002"
 ,pages="289-300"
-,annotation="
+,annotation={
 	Measured scalability of Linux 2.4 kernel's directory-entry cache
 	(dcache), and measured some scalability enhancements.
-"
+}
 }
 
 @Conference{McKenney02a
@@ -674,10 +695,10 @@
 ,note="Available:
 \url{http://www.linux.org.uk/~ajh/ols2002_proceedings.pdf.gz}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Presented and compared a number of RCU implementations for the
 	Linux kernel.
-"
+}
 }
 
 @unpublished{Sarma02a
@@ -688,9 +709,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=102645767914212&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Compare fastwalk and RCU for dcache.  RCU won.
-"
+}
 }
 
 @unpublished{Barbieri02
@@ -701,9 +722,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103082050621241&w=2}
 [Viewed: June 23, 2004]"
-,annotation="
+,annotation={
 	Suggested RCU for vfs\_shared\_cred.
-"
+}
 }
 
 @unpublished{Dickins02a
@@ -722,10 +743,10 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=103462075416638&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,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
@@ -736,14 +757,14 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2003/3/9/205}
 [Viewed March 13, 2006]"
-,annotation="
+,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
@@ -758,9 +779,9 @@
 ,volume="42"
 ,number="1"
 ,pages="60-76"
-,annotation="
+,annotation={
 	Use of RCU to enable hot-swapping for autonomic behavior in K42.
-"
+}
 }
 
 @unpublished{Seigh03
@@ -769,9 +790,9 @@
 ,Year="2003"
 ,Month="March"
 ,note="email correspondence"
-,annotation="
+,annotation={
 	Described the relationship of the VM/XA passive serialization to RCU.
-"
+}
 }
 
 @Conference{Arcangeli03
@@ -785,14 +806,12 @@
 ,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="
+,annotation={
 	Compared updated RCU implementations for the Linux kernel, and
 	described System V IPC use of RCU, including order-of-magnitude
 	performance improvements.
-"
+	http://www.rdrop.com/users/paulmck/RCU/rcu.FREENIX.2003.06.14.pdf
+}
 }
 
 @Conference{Soules03a
@@ -820,10 +839,10 @@
 ,note="Available:
 \url{http://www.linuxjournal.com/article/6993}
 [Viewed November 14, 2007]"
-,annotation="
+,annotation={
 	Reader-friendly intro to RCU, with the infamous old-man-and-brat
 	cartoon.
-"
+}
 }
 
 @unpublished{Sarma03a
@@ -832,7 +851,9 @@
 ,month="December"
 ,year="2003"
 ,note="Message ID: 20031222180114.GA2248@in.ibm.com"
-,annotation="dipankar/ct.2004.03.27/RCUll.2003.12.22.patch"
+,annotation={
+	dipankar/ct.2004.03.27/RCUll.2003.12.22.patch
+}
 }
 
 @techreport{Friedberg03a
@@ -844,11 +865,11 @@
 ,number="US Patent 6,662,184"
 ,month="December"
 ,pages="112"
-,annotation="
+,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
@@ -860,12 +881,11 @@
 ,volume="1"
 ,number="118"
 ,pages="38-46"
-,note="Available:
-\url{http://www.linuxjournal.com/node/7124}
-[Viewed December 26, 2010]"
-,annotation="
+,annotation={
 	Reader friendly intro to dcache and RCU.
-"
+	http://www.linuxjournal.com/node/7124
+	[Viewed December 26, 2010]
+}
 }
 
 @Conference{McKenney04b
@@ -879,10 +899,10 @@
 \url{http://www.linux.org.au/conf/2004/abstracts.html#90}
 \url{http://www.rdrop.com/users/paulmck/RCU/lockperf.2004.01.17a.pdf}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Compares performance of RCU to that of other locking primitives
 	over a number of CPUs (x86, Opteron, Itanium, and PPC).
-"
+}
 }
 
 @unpublished{Sarma04a
@@ -891,7 +911,9 @@
 ,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"
+,annotation={
+	Head of thread: dipankar/2004.03.23/rcu-low-lat.1.patch
+}
 }
 
 @unpublished{Sarma04b
@@ -900,7 +922,9 @@
 ,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"
+,annotation={
+	dipankar/rcuth.2004.03.24/rcu-throttle.patch
+}
 }
 
 @unpublished{Spraul04a
@@ -911,9 +935,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=108546407726602&w=2}
 [Viewed June 23, 2004]"
-,annotation="
+,annotation={
 	Hierarchical-bitmap patch for RCU infrastructure.
-"
+}
 }
 
 @unpublished{Steiner04a
@@ -950,10 +974,12 @@
 ,year="2004"
 ,month="June"
 ,pages="182-191"
-,annotation="
+,annotation={
 	Describes and compares a number of modifications to the Linux RCU
 	implementation that make it friendly to realtime applications.
-"
+	https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response
+	[Viewed July 26, 2012]
+}
 }
 
 @phdthesis{PaulEdwardMcKenneyPhD
@@ -964,14 +990,13 @@
 ,school="OGI School of Science and Engineering at
 Oregon Health and Sciences University"
 ,year="2004"
-,note="Available:
-\url{http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf}
-[Viewed October 15, 2004]"
-,annotation="
+,annotation={
 	Describes RCU implementations and presents design patterns
 	corresponding to common uses of RCU in several operating-system
 	kernels.
-"
+	http://www.rdrop.com/users/paulmck/RCU/RCUdissertation.2004.07.14e1.pdf
+	[Viewed October 15, 2004]
+}
 }
 
 @unpublished{PaulEMcKenney2004rcu:dereference
@@ -982,9 +1007,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2004/8/6/237}
 [Viewed June 8, 2010]"
-,annotation="
+,annotation={
 	Introduce rcu_dereference().
-"
+}
 }
 
 @unpublished{JimHouston04a
@@ -995,11 +1020,11 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2004/8/30/87}
 [Viewed February 17, 2005]"
-,annotation="
+,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
@@ -1010,9 +1035,9 @@
 ,note="Available:
 \url{http://www.cs.toronto.edu/~tomhart/masters_thesis.html}
 [Viewed October 15, 2004]"
-,annotation="
+,annotation={
 	Proposes comparing RCU to lock-free methods for the Linux kernel.
-"
+}
 }
 
 @unpublished{Vaddagiri04a
@@ -1023,9 +1048,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?t=109395731700004&r=1&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Srivatsa's RCU patch for tcp_ehash lookup.
-"
+}
 }
 
 @unpublished{Thirumalai04a
@@ -1036,9 +1061,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?t=109144217400003&r=1&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Ravikiran's lockfree FD patch.
-"
+}
 }
 
 @unpublished{Thirumalai04b
@@ -1049,9 +1074,9 @@
 ,note="Available:
 \url{http://marc.theaimsgroup.com/?l=linux-kernel&m=109152521410459&w=2}
 [Viewed October 18, 2004]"
-,annotation="
+,annotation={
 	Ravikiran's lockfree FD patch.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2004rcu:assign:pointer
@@ -1062,9 +1087,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2004/10/23/241}
 [Viewed June 8, 2010]"
-,annotation="
+,annotation={
 	Introduce rcu_assign_pointer().
-"
+}
 }
 
 @unpublished{JamesMorris04a
@@ -1073,12 +1098,12 @@
 ,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="
+,note="\url{http://marc.theaimsgroup.com/?l=linux-kernel&m=110054979416004&w=2}"
+,annotation={
 	James Morris posts Kaigai Kohei's patch to LKML.
-"
+	[Viewed December 10, 2004]
+	Kaigai's patch is at https://lkml.org/lkml/2004/9/27/52
+}
 }
 
 @unpublished{JamesMorris04b
@@ -1089,9 +1114,9 @@
 ,note="Available:
 \url{http://www.livejournal.com/users/james_morris/2153.html}
 [Viewed December 10, 2004]"
-,annotation="
+,annotation={
 	RCU helps SELinux performance.  ;-)  Made LWN.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005RCUSemantics
@@ -1103,9 +1128,9 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/rcu-semantics.2005.01.30a.pdf}
 [Viewed December 6, 2009]"
-,annotation="
+,annotation={
 	Early derivation of RCU semantics.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005e
@@ -1117,10 +1142,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/3/17/199}
 [Viewed September 5, 2005]"
-,annotation="
+,annotation={
 	First posting showing how RCU can be safely adapted for
 	preemptable RCU read side critical sections.
-"
+}
 }
 
 @unpublished{EsbenNeilsen2005a
@@ -1132,12 +1157,12 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/3/18/122}
 [Viewed March 30, 2006]"
-,annotation="
+,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
+	is indefinite grace periods...  But this is OK for experimentation
 	and testing.
-"
+}
 }
 
 @unpublished{TomHart05a
@@ -1149,10 +1174,10 @@
 ,note="Available:
 \url{ftp://ftp.cs.toronto.edu/csrg-technical-reports/515/}
 [Viewed March 4, 2005]"
-,annotation="
+,annotation={
 	Comparison of RCU, QBSR, and EBSR.  RCU wins for read-mostly
 	workloads.  ;-)
-"
+}
 }
 
 @unpublished{JonCorbet2005DeprecateSyncKernel
@@ -1164,10 +1189,10 @@
 ,note="Available:
 \url{http://lwn.net/Articles/134484/}
 [Viewed May 3, 2005]"
-,annotation="
+,annotation={
 	Jon Corbet describes deprecation of synchronize_kernel()
 	in favor of synchronize_rcu() and synchronize_sched().
-"
+}
 }
 
 @unpublished{PaulMcKenney05a
@@ -1178,10 +1203,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/5/9/185}
 [Viewed May 13, 2005]"
-,annotation="
+,annotation={
 	First publication of working lock-based deferred free patches
 	for the CONFIG_PREEMPT_RT environment.
-"
+}
 }
 
 @conference{PaulMcKenney05b
@@ -1194,10 +1219,10 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/realtimeRCU.2005.04.23a.pdf}
 [Viewed May 13, 2005]"
-,annotation="
+,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
@@ -1208,9 +1233,9 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/}
 [Viewed May 25, 2005]"
-,annotation="
+,annotation={
 	Paul McKenney's home page.
-"
+}
 }
 
 @unpublished{PaulEMcKenneyRCUPage
@@ -1221,9 +1246,9 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU}
 [Viewed May 25, 2005]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page.
-"
+}
 }
 
 @unpublished{JosephSeigh2005a
@@ -1232,10 +1257,10 @@
 ,month="July"
 ,year="2005"
 ,note="Personal communication"
-,annotation="
+,annotation={
 	Joe Seigh announcing his atomic-ptr-plus project.
 	http://sourceforge.net/projects/atomic-ptr-plus/
-"
+}
 }
 
 @unpublished{JosephSeigh2005b
@@ -1247,9 +1272,9 @@
 ,note="Available:
 \url{http://sourceforge.net/projects/atomic-ptr-plus/}
 [Viewed August 8, 2005]"
-,annotation="
+,annotation={
 	Joe Seigh's atomic-ptr-plus project.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005c
@@ -1261,9 +1286,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/8/1/155}
 [Viewed March 14, 2006]"
-,annotation="
+,annotation={
 	First operating counter-based realtime RCU patch posted to LKML.
-"
+}
 }
 
 @unpublished{PaulMcKenney2005d
@@ -1275,11 +1300,11 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/8/8/108}
 [Viewed March 14, 2006]"
-,annotation="
+,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
@@ -1291,9 +1316,25 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2005/10/1/70}
 [Viewed March 14, 2006]"
-,annotation="
+,annotation={
 	First rcutorture patch.
-"
+}
+}
+
+@unpublished{DavidSMiller2006HashedLocking
+,Author="David S. Miller"
+,Title="Re: [{PATCH}, {RFC}] {RCU} : {OOM} avoidance and lower latency"
+,month="January"
+,day="6"
+,year="2006"
+,note="Available:
+\url{https://lkml.org/lkml/2006/1/7/22}
+[Viewed February 29, 2012]"
+,annotation={
+	David Miller's view on hashed arrays of locks: used to really
+	like it, but time he saw an opportunity for this technique,
+	something else always proved superior.  Partitioning or RCU.  ;-)
+}
 }
 
 @conference{ThomasEHart2006a
@@ -1309,10 +1350,10 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/hart_ipdps06.pdf}
 [Viewed April 28, 2008]"
-,annotation="
+,annotation={
 	Compares QSBR, HPBR, EBR, and lock-free reference counting.
 	http://www.cs.toronto.edu/~tomhart/perflab/ipdps06.tgz
-"
+}
 }
 
 @unpublished{NickPiggin2006radixtree
@@ -1324,9 +1365,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2006/6/20/238}
 [Viewed March 25, 2008]"
-,annotation="
+,annotation={
 	RCU-protected radix tree.
-"
+}
 }
 
 @Conference{PaulEMcKenney2006b
@@ -1341,9 +1382,9 @@
 \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="
+,annotation={
 	Described how to improve the -rt implementation of realtime RCU.
-"
+}
 }
 
 @unpublished{WikipediaRCU
@@ -1354,12 +1395,11 @@
 ,month="July"
 ,day="8"
 ,year="2006"
-,note="Available:
-\url{http://en.wikipedia.org/wiki/Read-copy-update}
-[Viewed August 21, 2006]"
-,annotation="
+,note="\url{http://en.wikipedia.org/wiki/Read-copy-update}"
+,annotation={
 	Wikipedia RCU page as of July 8 2006.
-"
+	[Viewed August 21, 2006]
+}
 }
 
 @Conference{NickPiggin2006LocklessPageCache
@@ -1372,9 +1412,9 @@
 ,note="Available:
 \url{http://www.linuxsymposium.org/2006/view_abstract.php?content_key=184}
 [Viewed January 11, 2009]"
-,annotation="
+,annotation={
 	Uses RCU-protected radix tree for a lockless page cache.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2006c
@@ -1388,9 +1428,9 @@
 Revised:
 \url{http://www.rdrop.com/users/paulmck/RCU/srcu.2007.01.14a.pdf}
 [Viewed August 21, 2006]"
-,annotation="
+,annotation={
 	LWN article introducing SRCU.
-"
+}
 }
 
 @unpublished{RobertOlsson2006a
@@ -1399,12 +1439,11 @@
 ,month="August"
 ,day="18"
 ,year="2006"
-,note="Available:
-\url{http://www.nada.kth.se/~snilsson/publications/TRASH/trash.pdf}
-[Viewed March 4, 2011]"
-,annotation="
+,note="\url{http://www.nada.kth.se/~snilsson/publications/TRASH/trash.pdf}"
+,annotation={
 	RCU-protected dynamic trie-hash combination.
-"
+	[Viewed March 4, 2011]
+}
 }
 
 @unpublished{ChristophHellwig2006RCU2SRCU
@@ -1426,10 +1465,10 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/linuxusage.html}
 [Viewed January 14, 2007]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page showing graphs plotting Linux-kernel
 	usage of RCU.
-"
+}
 }
 
 @unpublished{PaulEMcKenneyRCUusageRawDataPage
@@ -1440,10 +1479,10 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html}
 [Viewed January 14, 2007]"
-,annotation="
+,annotation={
 	Paul McKenney's RCU page showing Linux usage of RCU in tabular
 	form, with links to corresponding cscope databases.
-"
+}
 }
 
 @unpublished{GauthamShenoy2006RCUrwlock
@@ -1455,13 +1494,13 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2006/10/26/73}
 [Viewed January 26, 2009]"
-,annotation="
+,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
@@ -1474,11 +1513,11 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/17/56}
 [Viewed May 28, 2007]"
-,annotation="
+,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
@@ -1491,10 +1530,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/19/69}
 [Viewed May 28, 2007]"
-,annotation="
+,annotation={
 	First cut of QRCU.  Expanded/corrected versions followed.
 	Used to be OlegNesterov2007QRCU, now time-corrected.
-"
+}
 }
 
 @unpublished{OlegNesterov2006aQRCU
@@ -1506,10 +1545,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2006/11/29/330}
 [Viewed November 26, 2008]"
-,annotation="
+,annotation={
 	Expanded/corrected version of QRCU.
 	Used to be OlegNesterov2007aQRCU, now time-corrected.
-"
+}
 }
 
 @unpublished{EvgeniyPolyakov2006RCUslowdown
@@ -1521,10 +1560,10 @@
 ,note="Available:
 \url{http://www.ioremap.net/node/41}
 [Viewed October 28, 2008]"
-,annotation="
+,annotation={
 	Using RCU as a pure delay leads to a 2.5x slowdown in skbs in
 	the Linux kernel.
-"
+}
 }
 
 @inproceedings{ChrisMatthews2006ClusteredObjectsRCU
@@ -1541,7 +1580,8 @@
 ,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}
@@ -1557,7 +1597,8 @@
 ,address = {New York, NY, USA}
 ,annotation={
 	Describes relationship of K42 generations to RCU.
-}}
+}
+}
 
 # CoreyMinyard2007list_splice_rcu
 @unpublished{CoreyMinyard2007list:splice:rcu
@@ -1569,9 +1610,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2007/1/3/112}
 [Viewed May 28, 2007]"
-,annotation="
+,annotation={
 	Patch for list_splice_rcu().
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007rcubarrier
@@ -1583,9 +1624,9 @@
 ,note="Available:
 \url{http://lwn.net/Articles/217484/}
 [Viewed November 22, 2007]"
-,annotation="
+,annotation={
 	LWN article introducing the rcu_barrier() primitive.
-"
+}
 }
 
 @unpublished{PeterZijlstra2007SyncBarrier
@@ -1597,10 +1638,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2007/1/28/34}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	RCU-like implementation for frequent updaters and rare readers(!).
 	Subsumed into QRCU.  Maybe...
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007BoostRCU
@@ -1609,14 +1650,13 @@
 ,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="
+,note="\url{http://lwn.net/Articles/220677/}"
+,annotation={
 	LWN article introducing RCU priority boosting.
-"
+	Revised:
+	http://www.rdrop.com/users/paulmck/RCU/RCUbooststate.2007.04.16a.pdf
+	[Viewed September 7, 2007]
+}
 }
 
 @unpublished{PaulMcKenney2007QRCUpatch
@@ -1628,9 +1668,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2007/2/25/18}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Patch for QRCU supplying lock-free fast path.
-"
+}
 }
 
 @article{JonathanAppavoo2007K42RCU
@@ -1647,7 +1687,8 @@
 ,address = {New York, NY, USA}
 ,annotation={
 	Role of RCU in K42.
-}}
+}
+}
 
 @conference{RobertOlsson2007Trash
 ,Author="Robert Olsson and Stefan Nilsson"
@@ -1658,9 +1699,9 @@
 ,note="Available:
 \url{http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4281239}
 [Viewed October 1, 2010]"
-,annotation="
+,annotation={
 	RCU-protected dynamic trie-hash combination.
-"
+}
 }
 
 @conference{PeterZijlstra2007ConcurrentPagecacheRCU
@@ -1673,10 +1714,10 @@
 ,note="Available:
 \url{http://ols.108.redhat.com/2007/Reprints/zijlstra-Reprint.pdf}
 [Viewed April 14, 2008]"
-,annotation="
+,annotation={
 	Page-cache modifications permitting RCU readers and concurrent
 	updates.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007whatisRCU
@@ -1701,11 +1742,11 @@
 ,note="Available:
 \url{http://lwn.net/Articles/243851/}
 [Viewed September 8, 2007]"
-,annotation="
+,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
@@ -1714,12 +1755,12 @@
 ,month="August"
 ,day="3"
 ,year="2007"
-,note="Preprint:
+,note="Available:
 \url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2664.htm}
 [Viewed December 7, 2009]"
-,annotation="
+,annotation={
 	RCU for C++, parts 1 and 2.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007WG21DDOannotation
@@ -1728,12 +1769,12 @@
 ,month="September"
 ,day="18"
 ,year="2008"
-,note="Preprint:
+,note="Available:
 \url{http://open-std.org/jtc1/sc22/wg21/docs/papers/2008/n2782.htm}
 [Viewed December 7, 2009]"
-,annotation="
+,annotation={
 	RCU for C++, part 2, updated many times.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007PreemptibleRCUPatch
@@ -1745,10 +1786,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2007/9/10/213}
 [Viewed October 25, 2007]"
-,annotation="
+,annotation={
 	Final patch for preemptable RCU to -rt.  (Later patches were
 	to mainline, eventually incorporated.)
-"
+}
 }
 
 @unpublished{PaulEMcKenney2007PreemptibleRCU
@@ -1760,9 +1801,9 @@
 ,note="Available:
 \url{http://lwn.net/Articles/253651/}
 [Viewed October 25, 2007]"
-,annotation="
+,annotation={
 	LWN article describing the design of preemptible RCU.
-"
+}
 }
 
 @article{ThomasEHart2007a
@@ -1783,6 +1824,7 @@
 }
 }
 
+# MathieuDesnoyers2007call_rcu_schedNeeded
 @unpublished{MathieuDesnoyers2007call:rcu:schedNeeded
 ,Author="Mathieu Desnoyers"
 ,Title="Re: [patch 1/2] {Linux} Kernel Markers - Support Multiple Probes"
@@ -1792,9 +1834,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2007/12/20/244}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Request for call_rcu_sched() and rcu_barrier_sched().
-"
+}
 }
 
 
@@ -1815,11 +1857,11 @@
 ,note="Available:
 \url{http://lwn.net/Articles/262464/}
 [Viewed December 27, 2007]"
-,annotation="
+,annotation={
 	Lays out the three basic components of RCU: (1) publish-subscribe,
 	(2) wait for pre-existing readers to complete, and (2) maintain
 	multiple versions.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008WhatIsRCUUsage
@@ -1831,7 +1873,7 @@
 ,note="Available:
 \url{http://lwn.net/Articles/263130/}
 [Viewed January 4, 2008]"
-,annotation="
+,annotation={
 	Lays out six uses of RCU:
 	1. RCU is a Reader-Writer Lock Replacement
 	2. RCU is a Restricted Reference-Counting Mechanism
@@ -1839,7 +1881,7 @@
 	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
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008WhatIsRCUAPI
@@ -1851,10 +1893,10 @@
 ,note="Available:
 \url{http://lwn.net/Articles/264090/}
 [Viewed January 10, 2008]"
-,annotation="
+,annotation={
 	Gives an overview of the Linux-kernel RCU API and a brief annotated RCU
 	bibliography.
-"
+}
 }
 
 #
@@ -1872,10 +1914,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2008/1/29/208}
 [Viewed March 27, 2008]"
-,annotation="
+,annotation={
 	Patch that prevents preemptible RCU from unnecessarily waking
 	up dynticks-idle CPUs.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2008LKMLDependencyOrdering
@@ -1887,9 +1929,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2008/2/2/255}
 [Viewed October 18, 2008]"
-,annotation="
+,annotation={
 	Explanation of compilers violating dependency ordering.
-"
+}
 }
 
 @Conference{PaulEMcKenney2008Beijing
@@ -1916,24 +1958,26 @@
 ,note="Available:
 \url{http://lwn.net/Articles/279077/}
 [Viewed April 24, 2008]"
-,annotation="
+,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-June"
+,Month="May"
 ,journal="IBM Systems Journal"
 ,volume="47"
 ,number="2"
 ,pages="221-236"
-,annotation="
+,annotation={
 	RCU, realtime RCU, sleepable RCU, performance.
-"
+	http://www.research.ibm.com/journal/sj/472/guniguntala.pdf
+	[Viewed April 24, 2008]
+}
 }
 
 @unpublished{LaiJiangshan2008NewClassicAlgorithm
@@ -1945,11 +1989,11 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2008/6/2/539}
 [Viewed December 10, 2008]"
-,annotation="
+,annotation={
 	Updated RCU classic algorithm.  Introduced multi-tailed list
 	for RCU callbacks and also pulling common code into
 	__call_rcu().
-"
+}
 }
 
 @article{PaulEMcKenney2008RCUOSR
@@ -1966,6 +2010,7 @@
 ,address="New York, NY, USA"
 ,annotation={
 	Linux changed RCU to a far greater degree than RCU has changed Linux.
+	http://portal.acm.org/citation.cfm?doid=1400097.1400099
 }
 }
 
@@ -1978,10 +2023,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2008/8/21/336}
 [Viewed December 8, 2008]"
-,annotation="
+,annotation={
 	State-based RCU.  One key thing that this patch does is to
 	separate the dynticks handling of NMIs and IRQs.
-"
+}
 }
 
 @unpublished{ManfredSpraul2008dyntickIRQNMI
@@ -1993,12 +2038,13 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2008/9/6/86}
 [Viewed December 8, 2008]"
-,annotation="
+,annotation={
 	Manfred notes a fix required to my attempt to separate irq
 	and NMI processing for hierarchical RCU's dynticks interface.
-"
+}
 }
 
+# Was PaulEMcKenney2011cyclicRCU
 @techreport{PaulEMcKenney2008cyclicRCU
 ,author="Paul E. McKenney"
 ,title="Efficient Support of Consistent Cyclic Search With Read-Copy Update"
@@ -2008,11 +2054,11 @@
 ,number="US Patent 7,426,511"
 ,month="September"
 ,pages="23"
-,annotation="
+,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
@@ -2021,13 +2067,12 @@
 ,month="November"
 ,day="3"
 ,year="2008"
-,note="Available:
-\url{http://lwn.net/Articles/305782/}
-[Viewed November 6, 2008]"
-,annotation="
+,note="\url{http://lwn.net/Articles/305782/}"
+,annotation={
 	RCU with combining-tree-based grace-period detection,
 	permitting it to handle thousands of CPUs.
-"
+	[Viewed November 6, 2008]
+}
 }
 
 @unpublished{PaulEMcKenney2009BloatwatchRCU
@@ -2039,10 +2084,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2009/1/14/449}
 [Viewed January 15, 2009]"
-,annotation="
+,annotation={
 	Small-footprint implementation of RCU for uniprocessor
 	embedded applications -- and also for exposition purposes.
-"
+}
 }
 
 @conference{PaulEMcKenney2009MaliciousURCU
@@ -2055,9 +2100,9 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/urcutorture.2009.01.22a.pdf}
 [Viewed February 2, 2009]"
-,annotation="
+,annotation={
 	Realtime RCU and torture-testing RCU uses.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009URCU
@@ -2066,16 +2111,14 @@
 ,month="February"
 ,day="5"
 ,year="2009"
-,note="Available:
-\url{http://lkml.org/lkml/2009/2/5/572}
-\url{http://lttng.org/urcu}
-[Viewed February 20, 2009]"
-,annotation="
+,note="\url{http://lttng.org/urcu}"
+,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
-"
+	http://lkml.org/lkml/2009/2/5/572
+}
 }
 
 @unpublished{PaulEMcKenney2009LWNBloatWatchRCU
@@ -2087,9 +2130,24 @@
 ,note="Available:
 \url{http://lwn.net/Articles/323929/}
 [Viewed March 20, 2009]"
-,annotation="
+,annotation={
 	Uniprocessor assumptions allow simplified RCU implementation.
-"
+}
+}
+
+@unpublished{EvgeniyPolyakov2009EllipticsNetwork
+,Author="Evgeniy Polyakov"
+,Title="The Elliptics Network"
+,month="April"
+,day="17"
+,year="2009"
+,note="Available:
+\url{http://www.ioremap.net/projects/elliptics}
+[Viewed April 30, 2009]"
+,annotation={
+	Distributed hash table with transactions, using elliptic
+	hash functions to distribute data.
+}
 }
 
 @unpublished{PaulEMcKenney2009expeditedRCU
@@ -2101,9 +2159,9 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2009/6/25/306}
 [Viewed August 16, 2009]"
-,annotation="
+,annotation={
 	First posting of expedited RCU to be accepted into -tip.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2009fastRTRCU
@@ -2115,21 +2173,21 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2009/7/23/294}
 [Viewed August 15, 2009]"
-,annotation="
+,annotation={
 	First posting of simple and fast preemptable RCU.
-"
+}
 }
 
-@InProceedings{JoshTriplett2009RPHash
+@unpublished{JoshTriplett2009RPHash
 ,Author="Josh Triplett"
 ,Title="Scalable concurrent hash tables via relativistic programming"
 ,month="September"
 ,year="2009"
-,booktitle="Linux Plumbers Conference 2009"
-,annotation="
+,note="Linux Plumbers Conference presentation"
+,annotation={
 	RP fun with hash tables.
-	See also JoshTriplett2010RPHash
-"
+	Superseded by JoshTriplett2010RPHash
+}
 }
 
 @phdthesis{MathieuDesnoyersPhD
@@ -2154,9 +2212,9 @@
 ,note="Available:
 \url{http://wiki.cs.pdx.edu/rp/}
 [Viewed December 9, 2009]"
-,annotation="
+,annotation={
 	Main Relativistic Programming Wiki.
-"
+}
 }
 
 @conference{PaulEMcKenney2009DeterministicRCU
@@ -2180,9 +2238,9 @@
 ,note="Available:
 \url{http://paulmck.livejournal.com/14639.html}
 [Viewed June 4, 2010]"
-,annotation="
+,annotation={
 	Day-one bug in Tree RCU that took forever to track down.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009defer:rcu
@@ -2193,10 +2251,10 @@
 ,note="Available:
 \url{http://lkml.org/lkml/2009/10/18/129}
 [Viewed December 29, 2009]"
-,annotation="
+,annotation={
 	Mathieu proposed defer_rcu() with fixed-size per-thread pool
 	of RCU callbacks.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009VerifPrePub
@@ -2205,10 +2263,10 @@
 ,month="December"
 ,year="2009"
 ,note="Submitted to IEEE TPDS"
-,annotation="
+,annotation={
 	OOMem model for Mathieu's user-level RCU mechanical proof of
 	correctness.
-"
+}
 }
 
 @unpublished{MathieuDesnoyers2009URCUPrePub
@@ -2216,15 +2274,15 @@
 ,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="
+,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
@@ -2240,7 +2298,8 @@
 ,address = {New York, NY, USA}
 ,annotation={
 	Uses RCU to protect metadata used in dynamic analysis.
-}}
+}
+}
 
 @conference{PaulEMcKenney2010SimpleOptRCU
 ,Author="Paul E. McKenney"
@@ -2252,10 +2311,10 @@
 ,note="Available:
 \url{http://www.rdrop.com/users/paulmck/RCU/SimplicityThruOptimization.2010.01.21f.pdf}
 [Viewed October 10, 2010]"
-,annotation="
+,annotation={
 	TREE_PREEMPT_RCU optimizations greatly simplified the old
 	PREEMPT_RCU implementation.
-"
+}
 }
 
 @unpublished{PaulEMcKenney2010LockdepRCU
@@ -2264,12 +2323,11 @@
 ,month="February"
 ,year="2010"
 ,day="1"
-,note="Available:
-\url{https://lwn.net/Articles/371986/}
-[Viewed June 4, 2010]"
-,annotation="
+,note="\url{https://lwn.net/Articles/371986/}"
+,annotation={
 	CONFIG_PROVE_RCU, or at least an early version.
-"
+	[Viewed June 4, 2010]
+}
 }
 
 @unpublished{AviKivity2010KVM2RCU
@@ -2280,10 +2338,10 @@
 ,note="Available:
 \url{http://www.mail-archive.com/kvm@vger.kernel.org/msg28640.html}
 [Viewed March 20, 2010]"
-,annotation="
+,annotation={
 	Use of RCU permits KVM to increase the size of guest OSes from
 	16 CPUs to 64 CPUs.
-"
+}
 }
 
 @unpublished{HerbertXu2010RCUResizeHash
@@ -2297,7 +2355,19 @@
 ,annotation={
 	Use a pair of list_head structures to support RCU-protected
 	resizable hash tables.
-}}
+}
+}
+
+@mastersthesis{AbhinavDuggal2010Masters
+,author="Abhinav Duggal"
+,title="Stopping Data Races Using Redflag"
+,school="Stony Brook University"
+,year="2010"
+,annotation={
+	Data-race detector incorporating RCU.
+	http://www.filesystems.org/docs/abhinav-thesis/abhinav_thesis.pdf
+}
+}
 
 @article{JoshTriplett2010RPHash
 ,author="Josh Triplett and Paul E. McKenney and Jonathan Walpole"
@@ -2310,7 +2380,8 @@
 ,annotation={
 	RP fun with hash tables.
 	http://portal.acm.org/citation.cfm?id=1842733.1842750
-}}
+}
+}
 
 @unpublished{PaulEMcKenney2010RCUAPI
 ,Author="Paul E. McKenney"
@@ -2318,12 +2389,11 @@
 ,month="December"
 ,day="8"
 ,year="2010"
-,note="Available:
-\url{http://lwn.net/Articles/418853/}
-[Viewed December 8, 2010]"
-,annotation="
+,note="\url{http://lwn.net/Articles/418853/}"
+,annotation={
 	Includes updated software-engineering features.
-"
+	[Viewed December 8, 2010]
+}
 }
 
 @mastersthesis{AndrejPodzimek2010masters
@@ -2338,7 +2408,8 @@
 	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"
@@ -2358,7 +2429,8 @@
 	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}
@@ -2392,12 +2464,12 @@
 ,number="US Patent 7,953,778"
 ,month="May"
 ,pages="34"
-,annotation="
+,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
@@ -2408,7 +2480,7 @@
 ,year = {2011}
 ,pages = {145--158}
 ,numpages = {14}
-,url={http://www.usenix.org/event/atc11/tech/final_files/atc11_proceedings.pdf}
+,url={http://www.usenix.org/event/atc11/tech/final_files/Triplett.pdf}
 ,publisher = {The USENIX Association}
 ,address = {Portland, OR USA}
 }
@@ -2419,27 +2491,58 @@
 ,month="July"
 ,day="27"
 ,year="2011"
-,note="Available:
-\url{http://lwn.net/Articles/453002/}
-[Viewed July 27, 2011]"
-,annotation="
+,note="\url{http://lwn.net/Articles/453002/}"
+,annotation={
 	Analysis of the RCU trainwreck in Linux kernel 3.0.
-"
+	[Viewed July 27, 2011]
+}
 }
 
 @unpublished{NeilBrown2011MeetTheLockers
 ,Author="Neil Brown"
-,Title="Meet the Lockers"
+,Title="Meet the {Lockers}"
 ,month="August"
 ,day="3"
 ,year="2011"
 ,note="Available:
 \url{http://lwn.net/Articles/453685/}
 [Viewed September 2, 2011]"
-,annotation="
+,annotation={
 	The Locker family as an analogy for locking, reference counting,
 	RCU, and seqlock.
-"
+}
+}
+
+@inproceedings{Seyster:2011:RFA:2075416.2075425
+,author = {Seyster, Justin and Radhakrishnan, Prabakar and Katoch, Samriti and Duggal, Abhinav and Stoller, Scott D. and Zadok, Erez}
+,title = {Redflag: a framework for analysis of Kernel-level concurrency}
+,booktitle = {Proceedings of the 11th international conference on Algorithms and architectures for parallel processing - Volume Part I}
+,series = {ICA3PP'11}
+,year = {2011}
+,isbn = {978-3-642-24649-4}
+,location = {Melbourne, Australia}
+,pages = {66--79}
+,numpages = {14}
+,url = {http://dl.acm.org/citation.cfm?id=2075416.2075425}
+,acmid = {2075425}
+,publisher = {Springer-Verlag}
+,address = {Berlin, Heidelberg}
+}
+
+@phdthesis{JoshTriplettPhD
+,author="Josh Triplett"
+,title="Relativistic Causal Ordering: A Memory Model for Scalable Concurrent Data Structures"
+,school="Portland State University"
+,year="2012"
+,annotation={
+	RCU-protected hash tables, barriers vs. read-side traversal order.
+	.
+	If the updater is making changes in the opposite direction from
+	the read-side traveral order, the updater need only execute a
+	memory-barrier instruction, but if in the same direction, the
+	updater needs to wait for a grace period between the individual
+	updates.
+}
 }
 
 @article{MathieuDesnoyers2012URCU
@@ -2459,5 +2562,150 @@
 	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
+	http://www.computer.org/cms/Computer.org/dl/trans/td/2012/02/extras/ttd2012020375s.pdf
+}
+}
+
+@inproceedings{AustinClements2012RCULinux:mmapsem
+,author = {Austin Clements and Frans Kaashoek and Nickolai Zeldovich}
+,title = {Scalable Address Spaces Using {RCU} Balanced Trees}
+,booktitle = {Architectural Support for Programming Languages and Operating Systems (ASPLOS 2012)}
+,month = {March}
+,year = {2012}
+,pages = {199--210}
+,numpages = {12}
+,publisher = {ACM}
+,address = {London, UK}
+,url="http://people.csail.mit.edu/nickolai/papers/clements-bonsai.pdf"
+}
+
+@unpublished{PaulEMcKenney2012ELCbattery
+,Author="Paul E. McKenney"
+,Title="Making {RCU} Safe For Battery-Powered Devices"
+,month="February"
+,day="15"
+,year="2012"
+,note="Available:
+\url{http://www.rdrop.com/users/paulmck/RCU/RCUdynticks.2012.02.15b.pdf}
+[Viewed March 1, 2012]"
+,annotation={
+	RCU_FAST_NO_HZ, round 2.
+}
+}
+
+@article{GuillermoVigueras2012RCUCrowd
+,author = {Vigueras, Guillermo and Ordu\~{n}a, Juan M. and Lozano, Miguel}
+,day = {25}
+,doi = {10.1007/s11227-012-0766-x}
+,issn = {0920-8542}
+,journal = {The Journal of Supercomputing}
+,keywords = {linux, simulation}
+,month = apr
+,posted-at = {2012-05-03 09:12:04}
+,priority = {2}
+,title = {{A Read-Copy Update based parallel server for distributed crowd simulations}}
+,url = {http://dx.doi.org/10.1007/s11227-012-0766-x}
+,year = {2012}
+}
+
+
+@unpublished{JonCorbet2012ACCESS:ONCE
+,Author="Jon Corbet"
+,Title="{ACCESS\_ONCE()}"
+,month="August"
+,day="1"
+,year="2012"
+,note="\url{http://lwn.net/Articles/508991/}"
+,annotation={
+	A couple of simple specific compiler optimizations that motivate
+	ACCESS_ONCE().
+}
+}
+
+@unpublished{AlexeyGotsman2012VerifyGraceExtended
+,Author="Alexey Gotsman and Noam Rinetzky and Hongseok Yang"
+,Title="Verifying Highly Concurrent Algorithms with Grace (extended version)"
+,month="July"
+,day="10"
+,year="2012"
+,note="\url{http://software.imdea.org/~gotsman/papers/recycling-esop13-ext.pdf}"
+,annotation={
+	Separation-logic formulation of RCU uses.
+}
+}
+
+@unpublished{PaulMcKenney2012RCUUsage
+,Author="Paul E. McKenney and Silas Boyd-Wickizer and Jonathan Walpole"
+,Title="{RCU} Usage In the Linux Kernel: One Decade Later"
+,month="September"
+,day="17"
+,year="2012"
+,url=http://rdrop.com/users/paulmck/techreports/survey.2012.09.17a.pdf
+,note="Technical report paulmck.2012.09.17"
+,annotation={
+	Overview of the first variant of no-CBs CPUs for RCU.
+}
+}
+
+@unpublished{JonCorbet2012NOCB
+,Author="Jon Corbet"
+,Title="Relocating RCU callbacks"
+,month="October"
+,day="31"
+,year="2012"
+,note="\url{http://lwn.net/Articles/522262/}"
+,annotation={
+	Overview of the first variant of no-CBs CPUs for RCU.
+}
+}
+
+@phdthesis{JustinSeyster2012PhD
+,author="Justin Seyster"
+,title="Runtime Verification of Kernel-Level Concurrency Using Compiler-Based Instrumentation"
+,school="Stony Brook University"
+,year="2012"
+,annotation={
+	Looking for data races, including those involving RCU.
+	Proposal:
+	http://www.fsl.cs.sunysb.edu/docs/jseyster-proposal/redflag.pdf
+	Dissertation:
+	http://www.fsl.cs.sunysb.edu/docs/jseyster-dissertation/redflag.pdf
+}
+}
+
+@unpublished{PaulEMcKenney2013RCUUsage
+,Author="Paul E. McKenney and Silas Boyd-Wickizer and Jonathan Walpole"
+,Title="{RCU} Usage in the {Linux} Kernel: One Decade Later"
+,month="February"
+,day="24"
+,year="2013"
+,note="\url{http://rdrop.com/users/paulmck/techreports/RCUUsage.2013.02.24a.pdf}"
+,annotation={
+	Usage of RCU within the Linux kernel.
+}
+}
+
+@inproceedings{AlexeyGotsman2013ESOPRCU
+,author = {Alexey Gotsman and Noam Rinetzky and Hongseok Yang}
+,title = {Verifying concurrent memory reclamation algorithms with grace}
+,booktitle = {ESOP'13: European Symposium on Programming}
+,year = {2013}
+,pages = {249--269}
+,publisher = {Springer}
+,address = {Rome, Italy}
+,annotation={
+	http://software.imdea.org/~gotsman/papers/recycling-esop13.pdf
+}
+}
+
+@unpublished{PaulEMcKenney2013NoTinyPreempt
+,Author="Paul E. McKenney"
+,Title="Simplifying RCU"
+,month="March"
+,day="6"
+,year="2013"
+,note="\url{http://lwn.net/Articles/541037/}"
+,annotation={
+	Getting rid of TINY_PREEMPT_RCU.
 }
 }
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index 2e319d1..b10cfe7 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -70,10 +70,14 @@
 
 rcu_barrier()
 
-We instead need the rcu_barrier() primitive. This primitive is similar
-to synchronize_rcu(), but instead of waiting solely for a grace
-period to elapse, it also waits for all outstanding RCU callbacks to
-complete. Pseudo-code using rcu_barrier() is as follows:
+We instead need the rcu_barrier() primitive.  Rather than waiting for
+a grace period to elapse, rcu_barrier() waits for all outstanding RCU
+callbacks to complete.  Please note that rcu_barrier() does -not- imply
+synchronize_rcu(), in particular, if there are no RCU callbacks queued
+anywhere, rcu_barrier() is within its rights to return immediately,
+without waiting for a grace period to elapse.
+
+Pseudo-code using rcu_barrier() is as follows:
 
    1. Prevent any new RCU callbacks from being posted.
    2. Execute rcu_barrier().
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index d8a5023..dac02a6 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -42,6 +42,16 @@
 fqs_stutter	Wait time (in seconds) between consecutive bursts
 		of calls to force_quiescent_state().
 
+gp_normal	Make the fake writers use normal synchronous grace-period
+		primitives.
+
+gp_exp		Make the fake writers use expedited synchronous grace-period
+		primitives.  If both gp_normal and gp_exp are set, or
+		if neither gp_normal nor gp_exp are set, then randomly
+		choose the primitive so that about 50% are normal and
+		50% expedited.  By default, neither are set, which
+		gives best overall test coverage.
+
 irqreader	Says to invoke RCU readers from irq level.  This is currently
 		done via timers.  Defaults to "1" for variants of RCU that
 		permit this.  (Or, more accurately, variants of RCU that do
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index fa5d8a9..c8c42e6 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -531,9 +531,10 @@
 code:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<data dependency barrier>
 		q = &b;
-	<data dependency barrier>
+	}
 	x = *q;
 
 This will not have the desired effect because there is no actual data
@@ -542,9 +543,10 @@
 required is:
 
 	q = &a;
-	if (p)
+	if (p) {
+		<read barrier>
 		q = &b;
-	<read barrier>
+	}
 	x = *q;
 
 
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 0e5f578..98ffcbd 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -63,7 +63,7 @@
 extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
 extern void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
-extern void debug_object_activate  (void *addr, struct debug_obj_descr *descr);
+extern int debug_object_activate  (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
@@ -85,8 +85,8 @@
 debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
 static inline void
 debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
-static inline void
-debug_object_activate  (void *addr, struct debug_obj_descr *descr) { }
+static inline int
+debug_object_activate  (void *addr, struct debug_obj_descr *descr) { return 0; }
 static inline void
 debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
 static inline void
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 97ba4e7..d235e88 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -101,13 +101,13 @@
 #define time_after(a,b)		\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(b) - (long)(a) < 0))
+	 ((long)((b) - (a)) < 0))
 #define time_before(a,b)	time_after(b,a)
 
 #define time_after_eq(a,b)	\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
-	 ((long)(a) - (long)(b) >= 0))
+	 ((long)((a) - (b)) >= 0))
 #define time_before_eq(a,b)	time_after_eq(b,a)
 
 /*
@@ -130,13 +130,13 @@
 #define time_after64(a,b)	\
 	(typecheck(__u64, a) &&	\
 	 typecheck(__u64, b) && \
-	 ((__s64)(b) - (__s64)(a) < 0))
+	 ((__s64)((b) - (a)) < 0))
 #define time_before64(a,b)	time_after64(b,a)
 
 #define time_after_eq64(a,b)	\
 	(typecheck(__u64, a) && \
 	 typecheck(__u64, b) && \
-	 ((__s64)(a) - (__s64)(b) >= 0))
+	 ((__s64)((a) - (b)) >= 0))
 #define time_before_eq64(a,b)	time_after_eq64(b,a)
 
 #define time_in_range64(a, b, c) \
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index f4b1001..4106721 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -267,8 +267,9 @@
  */
 #define list_first_or_null_rcu(ptr, type, member) \
 	({struct list_head *__ptr = (ptr); \
-	  struct list_head __rcu *__next = list_next_rcu(__ptr); \
-	  likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+	  struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+	  likely(__ptr != __next) ? \
+		list_entry_rcu(__next, type, member) : NULL; \
 	})
 
 /**
diff --git a/init/Kconfig b/init/Kconfig
index 247084b..c08a549 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -470,6 +470,7 @@
 config TREE_PREEMPT_RCU
 	bool "Preemptible tree-based hierarchical RCU"
 	depends on PREEMPT
+	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP systems with hundreds or
diff --git a/kernel/rcu.h b/kernel/rcu.h
index 0a90ccc..7713196 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -67,12 +67,15 @@
 
 extern struct debug_obj_descr rcuhead_debug_descr;
 
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
-	debug_object_activate(head, &rcuhead_debug_descr);
+	int r1;
+
+	r1 = debug_object_activate(head, &rcuhead_debug_descr);
 	debug_object_active_state(head, &rcuhead_debug_descr,
 				  STATE_RCU_HEAD_READY,
 				  STATE_RCU_HEAD_QUEUED);
+	return r1;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -83,8 +86,9 @@
 	debug_object_deactivate(head, &rcuhead_debug_descr);
 }
 #else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-static inline void debug_rcu_head_queue(struct rcu_head *head)
+static inline int debug_rcu_head_queue(struct rcu_head *head)
 {
+	return 0;
 }
 
 static inline void debug_rcu_head_unqueue(struct rcu_head *head)
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 14994d4..33eb462 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -212,43 +212,6 @@
 }
 
 /*
- * fixup_init is called when:
- * - an active object is initialized
- */
-static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_init(head, &rcuhead_debug_descr);
-		return 1;
-	default:
-		return 0;
-	}
-}
-
-/*
  * fixup_activate is called when:
  * - an active object is activated
  * - an unknown object is activated (might be a statically initialized object)
@@ -268,69 +231,8 @@
 		debug_object_init(head, &rcuhead_debug_descr);
 		debug_object_activate(head, &rcuhead_debug_descr);
 		return 0;
-
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_activate(head, &rcuhead_debug_descr);
-		return 1;
 	default:
-		return 0;
-	}
-}
-
-/*
- * fixup_free is called when:
- * - an active object is freed
- */
-static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
-{
-	struct rcu_head *head = addr;
-
-	switch (state) {
-	case ODEBUG_STATE_ACTIVE:
-		/*
-		 * Ensure that queued callbacks are all executed.
-		 * If we detect that we are nested in a RCU read-side critical
-		 * section, we should simply fail, otherwise we would deadlock.
-		 * In !PREEMPT configurations, there is no way to tell if we are
-		 * in a RCU read-side critical section or not, so we never
-		 * attempt any fixup and just print a warning.
-		 */
-#ifndef CONFIG_PREEMPT
-		WARN_ON_ONCE(1);
-		return 0;
-#endif
-		if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
-		    irqs_disabled()) {
-			WARN_ON_ONCE(1);
-			return 0;
-		}
-		rcu_barrier();
-		rcu_barrier_sched();
-		rcu_barrier_bh();
-		debug_object_free(head, &rcuhead_debug_descr);
 		return 1;
-	default:
-		return 0;
 	}
 }
 
@@ -369,9 +271,7 @@
 
 struct debug_obj_descr rcuhead_debug_descr = {
 	.name = "rcu_head",
-	.fixup_init = rcuhead_fixup_init,
 	.fixup_activate = rcuhead_fixup_activate,
-	.fixup_free = rcuhead_fixup_free,
 };
 EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
 #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 3d936f0f..be63101 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -52,72 +52,78 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
 
-static int nreaders = -1;	/* # reader threads, defaults to 2*ncpus */
-static int nfakewriters = 4;	/* # fake writer threads */
-static int stat_interval = 60;	/* Interval between stats, in seconds. */
-				/*  Zero means "only at end of test". */
-static bool verbose;		/* Print more debug info. */
-static bool test_no_idle_hz = true;
-				/* Test RCU support for tickless idle CPUs. */
-static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
-static int stutter = 5;		/* Start/stop testing interval (in sec) */
-static int irqreader = 1;	/* RCU readers from irq (timers). */
-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 n_barrier_cbs;	/* Number of callbacks to test RCU barriers. */
-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. */
-static char *torture_type = "rcu"; /* What RCU implementation to torture. */
-
-module_param(nreaders, int, 0444);
-MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
-module_param(nfakewriters, int, 0444);
-MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
-module_param(stat_interval, int, 0644);
-MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
-module_param(verbose, bool, 0444);
-MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
-module_param(test_no_idle_hz, bool, 0444);
-MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
-module_param(shuffle_interval, int, 0444);
-MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
-module_param(stutter, int, 0444);
-MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
-module_param(irqreader, int, 0444);
-MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
+static int fqs_duration;
 module_param(fqs_duration, int, 0444);
-MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us)");
+MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
+static int fqs_holdoff;
 module_param(fqs_holdoff, int, 0444);
 MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
+static int fqs_stutter = 3;
 module_param(fqs_stutter, int, 0444);
 MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+static bool gp_exp;
+module_param(gp_exp, bool, 0444);
+MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives");
+static bool gp_normal;
+module_param(gp_normal, bool, 0444);
+MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives");
+static int irqreader = 1;
+module_param(irqreader, int, 0444);
+MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
+static int n_barrier_cbs;
 module_param(n_barrier_cbs, int, 0444);
 MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
-module_param(onoff_interval, int, 0444);
-MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
+static int nfakewriters = 4;
+module_param(nfakewriters, int, 0444);
+MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
+static int nreaders = -1;
+module_param(nreaders, int, 0444);
+MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
+static int object_debug;
+module_param(object_debug, int, 0444);
+MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing");
+static int onoff_holdoff;
 module_param(onoff_holdoff, int, 0444);
 MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)");
+static int onoff_interval;
+module_param(onoff_interval, int, 0444);
+MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
+static int shuffle_interval = 3;
+module_param(shuffle_interval, int, 0444);
+MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+static int shutdown_secs;
 module_param(shutdown_secs, int, 0444);
-MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable.");
+MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable.");
+static int stall_cpu;
 module_param(stall_cpu, int, 0444);
 MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable.");
+static int stall_cpu_holdoff = 10;
 module_param(stall_cpu_holdoff, int, 0444);
 MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s).");
+static int stat_interval = 60;
+module_param(stat_interval, int, 0644);
+MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
+static int stutter = 5;
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
+static int test_boost = 1;
 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);
-MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+static int test_boost_duration = 4;
 module_param(test_boost_duration, int, 0444);
 MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
+static int test_boost_interval = 7;
+module_param(test_boost_interval, int, 0444);
+MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+static bool test_no_idle_hz = true;
+module_param(test_no_idle_hz, bool, 0444);
+MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
+static char *torture_type = "rcu";
 module_param(torture_type, charp, 0444);
-MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
+MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
+static bool verbose;
+module_param(verbose, bool, 0444);
+MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
 
 #define TORTURE_FLAG "-torture:"
 #define PRINTK_STRING(s) \
@@ -360,6 +366,7 @@
 	int (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
+	void (*exp_sync)(void);
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
@@ -443,14 +450,20 @@
 	call_rcu(&p->rtort_rcu, rcu_torture_cb);
 }
 
+static void rcu_sync_torture_init(void)
+{
+	INIT_LIST_HEAD(&rcu_torture_removed);
+}
+
 static struct rcu_torture_ops rcu_ops = {
-	.init		= NULL,
+	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
 	.completed	= rcu_torture_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
+	.exp_sync	= synchronize_rcu_expedited,
 	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
@@ -460,66 +473,6 @@
 	.name		= "rcu"
 };
 
-static void rcu_sync_torture_deferred_free(struct rcu_torture *p)
-{
-	int i;
-	struct rcu_torture *rp;
-	struct rcu_torture *rp1;
-
-	cur_ops->sync();
-	list_add(&p->rtort_free, &rcu_torture_removed);
-	list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) {
-		i = rp->rtort_pipe_count;
-		if (i > RCU_TORTURE_PIPE_LEN)
-			i = RCU_TORTURE_PIPE_LEN;
-		atomic_inc(&rcu_torture_wcount[i]);
-		if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
-			rp->rtort_mbtest = 0;
-			list_del(&rp->rtort_free);
-			rcu_torture_free(rp);
-		}
-	}
-}
-
-static void rcu_sync_torture_init(void)
-{
-	INIT_LIST_HEAD(&rcu_torture_removed);
-}
-
-static struct rcu_torture_ops rcu_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_torture_read_lock,
-	.read_delay	= rcu_read_delay,
-	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.can_boost	= rcu_can_boost(),
-	.name		= "rcu_sync"
-};
-
-static struct rcu_torture_ops rcu_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.can_boost	= rcu_can_boost(),
-	.name		= "rcu_expedited"
-};
-
 /*
  * Definitions for rcu_bh torture testing.
  */
@@ -546,13 +499,14 @@
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
-	.init		= NULL,
+	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
 	.completed	= rcu_bh_torture_completed,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
+	.exp_sync	= synchronize_rcu_bh_expedited,
 	.call		= call_rcu_bh,
 	.cb_barrier	= rcu_barrier_bh,
 	.fqs		= rcu_bh_force_quiescent_state,
@@ -561,38 +515,6 @@
 	.name		= "rcu_bh"
 };
 
-static struct rcu_torture_ops rcu_bh_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_bh,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "rcu_bh_sync"
-};
-
-static struct rcu_torture_ops rcu_bh_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_bh_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "rcu_bh_expedited"
-};
-
 /*
  * Definitions for srcu torture testing.
  */
@@ -667,6 +589,11 @@
 	return cnt;
 }
 
+static void srcu_torture_synchronize_expedited(void)
+{
+	synchronize_srcu_expedited(&srcu_ctl);
+}
+
 static struct rcu_torture_ops srcu_ops = {
 	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
@@ -675,45 +602,13 @@
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu"
 };
 
-static struct rcu_torture_ops srcu_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= srcu_torture_read_lock,
-	.read_delay	= srcu_read_delay,
-	.readunlock	= srcu_torture_read_unlock,
-	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= srcu_torture_synchronize,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.stats		= srcu_torture_stats,
-	.name		= "srcu_sync"
-};
-
-static void srcu_torture_synchronize_expedited(void)
-{
-	synchronize_srcu_expedited(&srcu_ctl);
-}
-
-static struct rcu_torture_ops srcu_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= srcu_torture_read_lock,
-	.read_delay	= srcu_read_delay,
-	.readunlock	= srcu_torture_read_unlock,
-	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= srcu_torture_synchronize_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.stats		= srcu_torture_stats,
-	.name		= "srcu_expedited"
-};
-
 /*
  * Definitions for sched torture testing.
  */
@@ -742,6 +637,8 @@
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
+	.exp_sync	= synchronize_sched_expedited,
+	.call		= call_rcu_sched,
 	.cb_barrier	= rcu_barrier_sched,
 	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
@@ -749,35 +646,6 @@
 	.name		= "sched"
 };
 
-static struct rcu_torture_ops sched_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_sched,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.name		= "sched_sync"
-};
-
-static struct rcu_torture_ops sched_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_sched_expedited,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "sched_expedited"
-};
-
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -927,9 +795,10 @@
 static int
 rcu_torture_writer(void *arg)
 {
+	bool exp;
 	int i;
-	long oldbatch = rcu_batches_completed();
 	struct rcu_torture *rp;
+	struct rcu_torture *rp1;
 	struct rcu_torture *old_rp;
 	static DEFINE_RCU_RANDOM(rand);
 
@@ -954,10 +823,33 @@
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			cur_ops->deferred_free(old_rp);
+			if (gp_normal == gp_exp)
+				exp = !!(rcu_random(&rand) & 0x80);
+			else
+				exp = gp_exp;
+			if (!exp) {
+				cur_ops->deferred_free(old_rp);
+			} else {
+				cur_ops->exp_sync();
+				list_add(&old_rp->rtort_free,
+					 &rcu_torture_removed);
+				list_for_each_entry_safe(rp, rp1,
+							 &rcu_torture_removed,
+							 rtort_free) {
+					i = rp->rtort_pipe_count;
+					if (i > RCU_TORTURE_PIPE_LEN)
+						i = RCU_TORTURE_PIPE_LEN;
+					atomic_inc(&rcu_torture_wcount[i]);
+					if (++rp->rtort_pipe_count >=
+					    RCU_TORTURE_PIPE_LEN) {
+						rp->rtort_mbtest = 0;
+						list_del(&rp->rtort_free);
+						rcu_torture_free(rp);
+					}
+				 }
+			}
 		}
 		rcutorture_record_progress(++rcu_torture_current_version);
-		oldbatch = cur_ops->completed();
 		rcu_stutter_wait("rcu_torture_writer");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
@@ -983,10 +875,18 @@
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		if (cur_ops->cb_barrier != NULL &&
-		    rcu_random(&rand) % (nfakewriters * 8) == 0)
+		    rcu_random(&rand) % (nfakewriters * 8) == 0) {
 			cur_ops->cb_barrier();
-		else
+		} else if (gp_normal == gp_exp) {
+			if (rcu_random(&rand) & 0x80)
+				cur_ops->sync();
+			else
+				cur_ops->exp_sync();
+		} else if (gp_normal) {
 			cur_ops->sync();
+		} else {
+			cur_ops->exp_sync();
+		}
 		rcu_stutter_wait("rcu_torture_fakewriter");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 
@@ -1534,7 +1434,13 @@
 					 torture_type, cpu);
 			starttime = jiffies;
 			n_online_attempts++;
-			if (cpu_up(cpu) == 0) {
+			ret = cpu_up(cpu);
+			if (ret) {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "rcu_torture_onoff task: online %d failed: errno %d\n",
+						 torture_type, cpu, ret);
+			} else {
 				if (verbose)
 					pr_alert("%s" TORTURE_FLAG
 						 "rcu_torture_onoff task: onlined %d\n",
@@ -1934,6 +1840,62 @@
 		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
 }
 
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+static void rcu_torture_leak_cb(struct rcu_head *rhp)
+{
+}
+
+static void rcu_torture_err_cb(struct rcu_head *rhp)
+{
+	/*
+	 * This -might- happen due to race conditions, but is unlikely.
+	 * The scenario that leads to this happening is that the
+	 * first of the pair of duplicate callbacks is queued,
+	 * someone else starts a grace period that includes that
+	 * callback, then the second of the pair must wait for the
+	 * next grace period.  Unlikely, but can happen.  If it
+	 * does happen, the debug-objects subsystem won't have splatted.
+	 */
+	pr_alert("rcutorture: duplicated callback was invoked.\n");
+}
+#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
+/*
+ * Verify that double-free causes debug-objects to complain, but only
+ * if CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.  Otherwise, say that the test
+ * cannot be carried out.
+ */
+static void rcu_test_debug_objects(void)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	struct rcu_head rh1;
+	struct rcu_head rh2;
+
+	init_rcu_head_on_stack(&rh1);
+	init_rcu_head_on_stack(&rh2);
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n");
+
+	/* Try to queue the rh2 pair of callbacks for the same grace period. */
+	preempt_disable(); /* Prevent preemption from interrupting test. */
+	rcu_read_lock(); /* Make it impossible to finish a grace period. */
+	call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */
+	local_irq_disable(); /* Make it harder to start a new grace period. */
+	call_rcu(&rh2, rcu_torture_leak_cb);
+	call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */
+	local_irq_enable();
+	rcu_read_unlock();
+	preempt_enable();
+
+	/* Wait for them all to get done so we can safely return. */
+	rcu_barrier();
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n");
+	destroy_rcu_head_on_stack(&rh1);
+	destroy_rcu_head_on_stack(&rh2);
+#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+	pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n");
+#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+}
+
 static int __init
 rcu_torture_init(void)
 {
@@ -1941,11 +1903,9 @@
 	int cpu;
 	int firsterr = 0;
 	int retval;
-	static struct rcu_torture_ops *torture_ops[] =
-		{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
-		  &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
-		  &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops,
-		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
+	static struct rcu_torture_ops *torture_ops[] = {
+		&rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
+	};
 
 	mutex_lock(&fullstop_mutex);
 
@@ -2163,6 +2123,8 @@
 		firsterr = retval;
 		goto unwind;
 	}
+	if (object_debug)
+		rcu_test_debug_objects();
 	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 64eaafb..32618b3 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -54,6 +54,7 @@
 #include <linux/stop_machine.h>
 #include <linux/random.h>
 #include <linux/ftrace_event.h>
+#include <linux/suspend.h>
 
 #include "rcutree.h"
 #include <trace/events/rcu.h>
@@ -1556,10 +1557,12 @@
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
-	 * could cause possible deadlocks with the rq->lock. Deter
-	 * the wakeup to interrupt context.
+	 * could cause possible deadlocks with the rq->lock. Defer
+	 * the wakeup to interrupt context.  And don't bother waking
+	 * up the running kthread.
 	 */
-	irq_work_queue(&rsp->wakeup_work);
+	if (current != rsp->gp_kthread)
+		irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
@@ -2291,6 +2294,13 @@
 }
 
 /*
+ * RCU callback function to leak a callback.
+ */
+static void rcu_leak_callback(struct rcu_head *rhp)
+{
+}
+
+/*
  * Helper function for call_rcu() and friends.  The cpu argument will
  * normally be -1, indicating "currently running CPU".  It may specify
  * a CPU only if that CPU is a no-CBs CPU.  Currently, only _rcu_barrier()
@@ -2304,7 +2314,12 @@
 	struct rcu_data *rdp;
 
 	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
-	debug_rcu_head_queue(head);
+	if (debug_rcu_head_queue(head)) {
+		/* Probable double call_rcu(), so leak the callback. */
+		ACCESS_ONCE(head->func) = rcu_leak_callback;
+		WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
+		return;
+	}
 	head->func = func;
 	head->next = NULL;
 
@@ -2789,9 +2804,20 @@
 	 * transition.  The "if" expression below therefore rounds the old
 	 * value up to the next even number and adds two before comparing.
 	 */
-	snap_done = ACCESS_ONCE(rsp->n_barrier_done);
+	snap_done = rsp->n_barrier_done;
 	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
-	if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) {
+
+	/*
+	 * If the value in snap is odd, we needed to wait for the current
+	 * rcu_barrier() to complete, then wait for the next one, in other
+	 * words, we need the value of snap_done to be three larger than
+	 * the value of snap.  On the other hand, if the value in snap is
+	 * even, we only had to wait for the next rcu_barrier() to complete,
+	 * in other words, we need the value of snap_done to be only two
+	 * greater than the value of snap.  The "(snap + 3) & ~0x1" computes
+	 * this for us (thank you, Linus!).
+	 */
+	if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
 		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
@@ -3020,6 +3046,25 @@
 	return NOTIFY_OK;
 }
 
+static int rcu_pm_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
+			rcu_expedited = 1;
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		rcu_expedited = 0;
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 /*
  * Spawn the kthread that handles this RCU flavor's grace periods.
  */
@@ -3261,6 +3306,7 @@
 	 * or the scheduler are operational.
 	 */
 	cpu_notifier(rcu_cpu_notify, 0);
+	pm_notifier(rcu_pm_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
 }
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 37061ed..bf2c8b1 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -381,19 +381,21 @@
  * debug_object_activate - debug checks when an object is activated
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
+ * Returns 0 for success, -EINVAL for check failed.
  */
-void debug_object_activate(void *addr, struct debug_obj_descr *descr)
+int debug_object_activate(void *addr, struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
+	int ret;
 	struct debug_obj o = { .object = addr,
 			       .state = ODEBUG_STATE_NOTAVAILABLE,
 			       .descr = descr };
 
 	if (!debug_objects_enabled)
-		return;
+		return 0;
 
 	db = get_bucket((unsigned long) addr);
 
@@ -405,23 +407,26 @@
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 			obj->state = ODEBUG_STATE_ACTIVE;
+			ret = 0;
 			break;
 
 		case ODEBUG_STATE_ACTIVE:
 			debug_print_object(obj, "activate");
 			state = obj->state;
 			raw_spin_unlock_irqrestore(&db->lock, flags);
-			debug_object_fixup(descr->fixup_activate, addr, state);
-			return;
+			ret = debug_object_fixup(descr->fixup_activate, addr, state);
+			return ret ? -EINVAL : 0;
 
 		case ODEBUG_STATE_DESTROYED:
 			debug_print_object(obj, "activate");
+			ret = -EINVAL;
 			break;
 		default:
+			ret = 0;
 			break;
 		}
 		raw_spin_unlock_irqrestore(&db->lock, flags);
-		return;
+		return ret;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
@@ -431,8 +436,11 @@
 	 * true or not.
 	 */
 	if (debug_object_fixup(descr->fixup_activate, addr,
-			   ODEBUG_STATE_NOTAVAILABLE))
+			   ODEBUG_STATE_NOTAVAILABLE)) {
 		debug_print_object(&o, "activate");
+		return -EINVAL;
+	}
+	return 0;
 }
 
 /**