Merge branch 'for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Pull RCU updates from Paul E. McKenney:

  - Documentation updates.

  - Miscellaneous fixes.

  - Preemptible-RCU fixes, including fixing an old bug in the
    interaction of RCU priority boosting and CPU hotplug.

  - SRCU updates.

  - RCU CPU stall-warning updates.

  - RCU torture-test updates.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

48 files changed, 657 insertions, 586 deletions

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index ed186a902d31..b57c0c1cdac6 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -15,7 +15,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 	21 seconds.
 
 	This configuration parameter may be changed at runtime via the
-	/sys/module/rcutree/parameters/rcu_cpu_stall_timeout, however
+	/sys/module/rcupdate/parameters/rcu_cpu_stall_timeout, however
 	this parameter is checked only at the beginning of a cycle.
 	So if you are 10 seconds into a 40-second stall, setting this
 	sysfs parameter to (say) five will shorten the timeout for the
@@ -152,6 +152,15 @@ no non-lazy callbacks ("." is printed otherwise, as shown above) and
 "D" indicates that dyntick-idle processing is enabled ("." is printed
 otherwise, for example, if disabled via the "nohz=" kernel boot parameter).
 
+If the relevant grace-period kthread has been unable to run prior to
+the stall warning, the following additional line is printed:
+
+	rcu_preempt kthread starved for 2023 jiffies!
+
+Starving the grace-period kthreads of CPU time can of course result in
+RCU CPU stall warnings even when all CPUs and tasks have passed through
+the required quiescent states.
+
 
 Multiple Warnings From One Stall
 
@@ -187,6 +196,11 @@ o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
 	behavior, you might need to replace some of the cond_resched()
 	calls with calls to cond_resched_rcu_qs().
 
+o	Anything that prevents RCU's grace-period kthreads from running.
+	This can result in the "All QSes seen" console-log message.
+	This message will include information on when the kthread last
+	ran and how often it should be expected to run.
+
 o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
 	happen to preempt a low-priority task in the middle of an RCU
 	read-side critical section.   This is especially damaging if
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index b63b9bb3bc0c..08651da15448 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -56,14 +56,14 @@ rcuboost:
 
 The output of "cat rcu/rcu_preempt/rcudata" looks as follows:
 
-  0!c=30455 g=30456 pq=1 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
-  1!c=30719 g=30720 pq=1 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
-  2!c=30150 g=30151 pq=1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
-  3 c=31249 g=31250 pq=1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
-  4!c=29502 g=29503 pq=1 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
-  5 c=31201 g=31202 pq=1 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
-  6!c=30253 g=30254 pq=1 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
-  7 c=31178 g=31178 pq=1 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
+  0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
+  1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
+  2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
+  3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
+  4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
+  5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
+  6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
+  7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
 
 This file has one line per CPU, or eight for this 8-CPU system.
 The fields are as follows:
@@ -188,14 +188,14 @@ o	"ca" is the number of RCU callbacks that have been adopted by this
 Kernels compiled with CONFIG_RCU_BOOST=y display the following from
 /debug/rcu/rcu_preempt/rcudata:
 
-  0!c=12865 g=12866 pq=1 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
-  1 c=14407 g=14408 pq=1 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
-  2 c=14407 g=14408 pq=1 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
-  3 c=14407 g=14408 pq=1 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
-  4 c=14405 g=14406 pq=1 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
-  5!c=14168 g=14169 pq=1 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
-  6 c=14404 g=14405 pq=1 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
-  7 c=14407 g=14408 pq=1 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
+  0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
+  1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
+  2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
+  3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
+  4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
+  5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
+  6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
+  7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
 
 This is similar to the output discussed above, but contains the following
 additional fields:
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 70a09f8a0383..ca2387ef27ab 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -269,6 +269,50 @@ And there are a number of things that _must_ or _must_not_ be assumed:
 	STORE *(A + 4) = Y; STORE *A = X;
 	STORE {*A, *(A + 4) } = {X, Y};
 
+And there are anti-guarantees:
+
+ (*) These guarantees do not apply to bitfields, because compilers often
+     generate code to modify these using non-atomic read-modify-write
+     sequences.  Do not attempt to use bitfields to synchronize parallel
+     algorithms.
+
+ (*) Even in cases where bitfields are protected by locks, all fields
+     in a given bitfield must be protected by one lock.  If two fields
+     in a given bitfield are protected by different locks, the compiler's
+     non-atomic read-modify-write sequences can cause an update to one
+     field to corrupt the value of an adjacent field.
+
+ (*) These guarantees apply only to properly aligned and sized scalar
+     variables.  "Properly sized" currently means variables that are
+     the same size as "char", "short", "int" and "long".  "Properly
+     aligned" means the natural alignment, thus no constraints for
+     "char", two-byte alignment for "short", four-byte alignment for
+     "int", and either four-byte or eight-byte alignment for "long",
+     on 32-bit and 64-bit systems, respectively.  Note that these
+     guarantees were introduced into the C11 standard, so beware when
+     using older pre-C11 compilers (for example, gcc 4.6).  The portion
+     of the standard containing this guarantee is Section 3.14, which
+     defines "memory location" as follows:
+
+     	memory location
+		either an object of scalar type, or a maximal sequence
+		of adjacent bit-fields all having nonzero width
+
+		NOTE 1: Two threads of execution can update and access
+		separate memory locations without interfering with
+		each other.
+
+		NOTE 2: A bit-field and an adjacent non-bit-field member
+		are in separate memory locations. The same applies
+		to two bit-fields, if one is declared inside a nested
+		structure declaration and the other is not, or if the two
+		are separated by a zero-length bit-field declaration,
+		or if they are separated by a non-bit-field member
+		declaration. It is not safe to concurrently update two
+		bit-fields in the same structure if all members declared
+		between them are also bit-fields, no matter what the
+		sizes of those intervening bit-fields happen to be.
+
 
 =========================
 WHAT ARE MEMORY BARRIERS?
@@ -750,7 +794,7 @@ In summary:
       However, they do -not- guarantee any other sort of ordering:
       Not prior loads against later loads, nor prior stores against
       later anything.  If you need these other forms of ordering,
-      use smb_rmb(), smp_wmb(), or, in the case of prior stores and
+      use smp_rmb(), smp_wmb(), or, in the case of prior stores and
       later loads, smp_mb().
 
   (*) If both legs of the "if" statement begin with identical stores
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 466bd299b1a8..3afee5f40f4f 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
+	select SRCU
 	depends on ARM_VIRT_EXT && ARM_LPAE
 	---help---
 	  Support hosting virtualized guest machines. You will also
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 8ba85e9ea388..b334084d3675 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -26,6 +26,7 @@ config KVM
 	select KVM_ARM_HOST
 	select KVM_ARM_VGIC
 	select KVM_ARM_TIMER
+	select SRCU
 	---help---
 	  Support hosting virtualized guest machines.
 
diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig
index 30e334e823bd..2ae12825529f 100644
--- a/arch/mips/kvm/Kconfig
+++ b/arch/mips/kvm/Kconfig
@@ -20,6 +20,7 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select KVM_MMIO
+	select SRCU
 	---help---
 	  Support for hosting Guest kernels.
 	  Currently supported on MIPS32 processors.
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index f5769f19ae25..11850f310fb4 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_EVENTFD
+	select SRCU
 
 config KVM_BOOK3S_HANDLER
 	bool
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 646db9c467d1..5fce52cf0e57 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
+	select SRCU
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/tile/kvm/Kconfig b/arch/tile/kvm/Kconfig
index 2298cb1daff7..1e968f7550dc 100644
--- a/arch/tile/kvm/Kconfig
+++ b/arch/tile/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
 	depends on HAVE_KVM && MODULES
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select SRCU
 	---help---
 	  Support hosting paravirtualized guest machines.
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba397bde7948..661269953c1a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -138,6 +138,7 @@ config X86
 	select HAVE_ACPI_APEI_NMI if ACPI
 	select ACPI_LEGACY_TABLES_LOOKUP if ACPI
 	select X86_FEATURE_NAMES if PROC_FS
+	select SRCU
 
 config INSTRUCTION_DECODER
 	def_bool y
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index f9d16ff56c6b..7dc7ba577ecd 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -40,6 +40,7 @@ config KVM
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_VFIO
+	select SRCU
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 3f44f292d066..91f86131bb7a 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -13,6 +13,7 @@ config COMMON_CLK
 	bool
 	select HAVE_CLK_PREPARE
 	select CLKDEV_LOOKUP
+	select SRCU
 	---help---
 	  The common clock framework is a single definition of struct
 	  clk, useful across many platforms, as well as an
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 29b2ef5a68b9..a171fef2c2b6 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -2,6 +2,7 @@ menu "CPU Frequency scaling"
 
 config CPU_FREQ
 	bool "CPU Frequency scaling"
+	select SRCU
 	help
 	  CPU Frequency scaling allows you to change the clock speed of 
 	  CPUs on the fly. This is a nice method to save power, because 
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index faf4e70c42e0..3891f6781298 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -1,5 +1,6 @@
 menuconfig PM_DEVFREQ
 	bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
+	select SRCU
 	help
 	  A device may have a list of frequencies and voltages available.
 	  devfreq, a generic DVFS framework can be registered for a device
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 5bdedf6df153..c355a226a024 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -5,6 +5,7 @@
 menuconfig MD
 	bool "Multiple devices driver support (RAID and LVM)"
 	depends on BLOCK
+	select SRCU
 	help
 	  Support multiple physical spindles through a single logical device.
 	  Required for RAID and logical volume management.
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index d6607ee9c855..84673ebcf428 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -197,6 +197,7 @@ config NETCONSOLE_DYNAMIC
 
 config NETPOLL
 	def_bool NETCONSOLE
+	select SRCU
 
 config NET_POLL_CONTROLLER
 	def_bool NETPOLL
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768ebc8d1..80e9c18ea64f 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -8,6 +8,7 @@ config BTRFS_FS
 	select LZO_DECOMPRESS
 	select RAID6_PQ
 	select XOR_BLOCKS
+	select SRCU
 
 	help
 	  Btrfs is a general purpose copy-on-write filesystem with extents,
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
index 22c629eedd82..2a24249b30af 100644
--- a/fs/notify/Kconfig
+++ b/fs/notify/Kconfig
@@ -1,5 +1,6 @@
 config FSNOTIFY
 	def_bool n
+	select SRCU
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index c51df1dd237e..4a09975aac90 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -5,6 +5,7 @@
 config QUOTA
 	bool "Quota support"
 	select QUOTACTL
+	select SRCU
 	help
 	  If you say Y here, you will be able to set per user limits for disk
 	  usage (also called disk quotas). Currently, it works for the
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 33063f872ee3..176bf816875e 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -385,7 +385,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 
 /* Is this type a native word size -- useful for atomic operations */
 #ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 #endif
 
 /* Compile time object size, -1 for unknown */
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 529bc946f450..a18b16f1dc0e 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu(pos, member)			\
-	for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point
@@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu_bh(pos, member)		\
-	for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(  \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ed4f5939a452..78097491cd99 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void)
 extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
+		rcu_all_qs(); \
 		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
 			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
-#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#define rcu_note_voluntary_context_switch(t)	rcu_all_qs()
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
@@ -582,11 +583,11 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_check(p, c, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
 	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
@@ -603,10 +604,10 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_index_check(p, c) \
 ({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(p) _________p1 = lockless_dereference(p); \
 	rcu_lockdep_assert(c, \
 			   "suspicious rcu_dereference_index_check() usage"); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 0e5366200154..937edaeb150d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -92,17 +92,49 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 /*
- * Return the number of grace periods.
+ * Return the number of grace periods started.
  */
-static inline long rcu_batches_completed(void)
+static inline unsigned long rcu_batches_started(void)
 {
 	return 0;
 }
 
 /*
- * Return the number of bottom-half grace periods.
+ * Return the number of bottom-half grace periods started.
  */
-static inline long rcu_batches_completed_bh(void)
+static inline unsigned long rcu_batches_started_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods started.
+ */
+static inline unsigned long rcu_batches_started_sched(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods completed.
+ */
+static inline unsigned long rcu_batches_completed_sched(void)
 {
 	return 0;
 }
@@ -154,7 +186,10 @@ static inline bool rcu_is_watching(void)
 	return true;
 }
 
-
 #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
+static inline void rcu_all_qs(void)
+{
+}
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 52953790dcca..d2e583a6aaca 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -81,9 +81,12 @@ void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-long rcu_batches_completed(void);
-long rcu_batches_completed_bh(void);
-long rcu_batches_completed_sched(void);
+unsigned long rcu_batches_started(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_started_sched(void);
+unsigned long rcu_batches_completed(void);
+unsigned long rcu_batches_completed_bh(void);
+unsigned long rcu_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
@@ -97,4 +100,6 @@ extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
 
+void rcu_all_qs(void);
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index a2783cb5d275..9cfd9623fb03 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -45,7 +45,7 @@ struct rcu_batch {
 #define RCU_BATCH_INIT(name) { NULL, &(name.head) }
 
 struct srcu_struct {
-	unsigned completed;
+	unsigned long completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
@@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work);
  * define and init a srcu struct at build time.
  * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
  */
-#define DEFINE_SRCU(name)						\
+#define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
-
-#define DEFINE_STATIC_SRCU(name)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
+#define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
@@ -135,7 +133,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
-long srcu_batches_completed(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/init/Kconfig b/init/Kconfig
index 9afb971497f4