Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle are:

   - 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"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  rcu: Initialize tiny RCU stall-warning timeouts at boot
  rcu: Fix RCU CPU stall detection in tiny implementation
  rcu: Add GP-kthread-starvation checks to CPU stall warnings
  rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors
  rcu: Optionally run grace-period kthreads at real-time priority
  ksoftirqd: Use new cond_resched_rcu_qs() function
  ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
  rcutorture: Add more diagnostics in rcu_barrier() test failure case
  torture: Flag console.log file to prevent holdovers from earlier runs
  torture: Add "-enable-kvm -soundhw pcspk" to qemu command line
  rcutorture: Handle different mpstat versions
  rcutorture: Check from beginning to end of grace period
  rcu: Remove redundant rcu_batches_completed() declaration
  rcutorture: Drop rcu_torture_completed() and friends
  rcu: Provide rcu_batches_completed_sched() for TINY_RCU
  rcutorture: Use unsigned for Reader Batch computations
  rcutorture: Make build-output parsing correctly flag RCU's warnings
  rcu: Make _batches_completed() functions return unsigned long
  rcutorture: Issue warnings on close calls due to Reader Batch blows
  documentation: Fix smp typo in memory-barriers.txt
  ...

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

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:

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

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

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.
 

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.

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

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

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.
 

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

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

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

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 

drivers/devfreq/Kconfig

 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

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.

drivers/net/Kconfig

@@ -197,6 +197,7 @@ config NETCONSOLE_DYNAMIC
 
 config NETPOLL
 	def_bool NETCONSOLE
+	select SRCU
 
 config NET_POLL_CONTROLLER
 	def_bool NETPOLL

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,

fs/notify/Kconfig

 config FSNOTIFY
 	def_bool n
+	select SRCU
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"

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

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 */

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

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); \
 })
 

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 */

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 */

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

init/Kconfig

@@ -470,7 +470,6 @@ choice
 config TREE_RCU
 	bool "Tree-based hierarchical RCU"
 	depends on !PREEMPT && SMP
-	select IRQ_WORK
 	help
 	  This option selects the RCU implementation that is
 	  designed for very large SMP system with hundreds or
@@ -480,7 +479,6 @@ config TREE_RCU
 config 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
@@ -501,9 +499,17 @@ config TINY_RCU
 
 endchoice
 
+config SRCU
+	bool
+	help
+	  This option selects the sleepable version of RCU. This version
+	  permits arbitrary sleeping or blocking within RCU read-side critical
+	  sections.
+
 config TASKS_RCU
 	bool "Task_based RCU implementation using voluntary context switch"
 	default n
+	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
 	  only voluntary context switch (not preemption!), idle, and
@@ -668,9 +674,10 @@ config RCU_BOOST
 
 config RCU_KTHREAD_PRIO
 	int "Real-time priority to use for RCU worker threads"
-	range 1 99
-	depends on RCU_BOOST
-	default 1
+	range 1 99 if RCU_BOOST
+	range 0 99 if !RCU_BOOST
+	default 1 if RCU_BOOST
+	default 0 if !RCU_BOOST
 	help
 	  This option specifies the SCHED_FIFO priority value that will be
 	  assigned to the rcuc/n and rcub/n threads and is also the value
@@ -1595,6 +1602,7 @@ config PERF_EVENTS
 	depends on HAVE_PERF_EVENTS
 	select ANON_INODES
 	select IRQ_WORK
+	select SRCU
 	help
 	  Enable kernel support for various performance events provided
 	  by software and hardware.

kernel/cpu.c

@@ -58,22 +58,23 @@ static int cpu_hotplug_disabled;
 
 static struct {
 	struct task_struct *active_writer;
-	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/* wait queue to wake up the active_writer */
+	wait_queue_head_t wq;
+	/* verifies that no writer will get active while readers are active */
+	struct mutex lock;
 	/*
 	 * Also blocks the new readers during
 	 * an ongoing cpu hotplug operation.
 	 */
-	int refcount;
-	/* And allows lockless put_online_cpus(). */
-	atomic_t puts_pending;
+	atomic_t refcount;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
 #endif
 } cpu_hotplug = {
 	.active_writer = NULL,
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-	.refcount = 0,
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	.dep_map = {.name = "cpu_hotplug.lock" },
 #endif
@@ -86,15 +87,6 @@ static struct {
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
-static void apply_puts_pending(int max)
-{
-	int delta;
-
-	if (atomic_read(&cpu_hotplug.puts_pending) >= max) {
-		delta = atomic_xchg(&cpu_hotplug.puts_pending, 0);
-		cpu_hotplug.refcount -= delta;
-	}
-}
 
 void get_online_cpus(void)
 {
@@ -103,8 +95,7 @@ void get_online_cpus(void)
 		return;
 	cpuhp_lock_acquire_read();
 	mutex_lock(&cpu_hotplug.lock);
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 }
 EXPORT_SYMBOL_GPL(get_online_cpus);
@@ -116,8 +107,7 @@ bool try_get_online_cpus(void)
 	if (!mutex_trylock(&cpu_hotplug.lock))
 		return false;
 	cpuhp_lock_acquire_tryread();
-	apply_puts_pending(65536);
-	cpu_hotplug.refcount++;
+	atomic_inc(&cpu_hotplug.refcount);
 	mutex_unlock(&cpu_hotplug.lock);
 	return true;
 }
@@ -125,20 +115,18 @@ EXPORT_SYMBOL_GPL(try_get_online_cpus);
 
 void put_online_cpus(void)
 {
+	int refcount;
+
 	if (cpu_hotplug.active_writer == current)
 		return;
-	if (!mutex_trylock(&cpu_hotplug.lock)) {
-		atomic_inc(&cpu_hotplug.puts_pending);
-		cpuhp_lock_release();
-		return;
-	}
 
-	if (WARN_ON(!cpu_hotplug.refcount))
-		cpu_hotplug.refcount++; /* try to fix things up */
+	refcount = atomic_dec_return(&cpu_hotplug.refcount);
+	if (WARN_ON(refcount < 0)) /* try to fix things up */
+		atomic_inc(&cpu_hotplug.refcount);
+
+	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
+		wake_up(&cpu_hotplug.wq);
 
-	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
-		wake_up_process(cpu_hotplug.active_writer);
-	mutex_unlock(&cpu_hotplug.lock);
 	cpuhp_lock_release();
 
 }
@@ -168,18 +156,20 @@ EXPORT_SYMBOL_GPL(put_online_cpus);
  */
 void cpu_hotplug_begin(void)
 {
-	cpu_hotplug.active_writer = current;
+	DEFINE_WAIT(wait);
 
+	cpu_hotplug.active_writer = current;
 	cpuhp_lock_acquire();
+
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
-		apply_puts_pending(1);
-		if (likely(!cpu_hotplug.refcount))
-			break;
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
+		if (likely(!atomic_read(&cpu_hotplug.refcount)))
+				break;
 		mutex_unlock(&cpu_hotplug.lock);
 		schedule();
 	}
+	finish_wait(&cpu_hotplug.wq, &wait);
 }
 
 void cpu_hotplug_done(void)

kernel/notifier.c

@@ -402,6 +402,7 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh,
 }
 EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
 
+#ifdef CONFIG_SRCU
 /*
  *	SRCU notifier chain routines.    Registration and unregistration
  *	use a mutex, and call_chain is synchronized by SRCU (no locks).
@@ -528,6 +529,8 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh)
 }
 EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
 
+#endif /* CONFIG_SRCU */
+
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
 int notrace notify_die(enum die_val val, const char *str,

kernel/power/Kconfig

@@ -251,6 +251,7 @@ config APM_EMULATION
 
 config PM_OPP
 	bool
+	select SRCU
 	---help---
 	  SOCs have a standard set of tuples consisting of frequency and
 	  voltage pairs that the device will support per voltage domain. This

kernel/rcu/Makefile

-obj-y += update.o srcu.o
+obj-y += update.o
+obj-$(CONFIG_SRCU) += srcu.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_PREEMPT_RCU) += tree.o

kernel/rcu/rcu.h

@@ -137,4 +137,10 @@ int rcu_jiffies_till_stall_check(void);
 
 void rcu_early_boot_tests(void);
 
+/*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
 #endif /* __LINUX_RCU_H */

kernel/rcu/rcutorture.c

@@ -244,7 +244,8 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	int (*completed)(void);
+	unsigned long (*started)(void);
+	unsigned long (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -296,11 +297,6 @@ static void rcu_torture_read_unlock(int idx) __releases(RCU)
 	rcu_read_unlock();
 }
 
-static int rcu_torture_completed(void)
-{
-	return rcu_batches_completed();
-}
-
 /*
  * Update callback in the pipe.  This should be invoked after a grace period.
  */
@@ -356,7 +352,7 @@ rcu_torture_cb(struct rcu_head *p)
 		cur_ops->deferred_free(rp);
 }
 
-static int rcu_no_completed(void)
+static unsigned long rcu_no_completed(void)
 {
 	return 0;
 }
@@ -377,7 +373,8 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
+	.started	= rcu_batches_started,
+	.completed	= rcu_batches_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -407,11 +404,6 @@ static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH)
 	rcu_read_unlock_bh();
 }
 
-static int rcu_bh_torture_completed(void)
-{
-	return rcu_batches_completed_bh();
-}
-
 static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 {
 	call_rcu_bh(&p->rtort_rcu, rcu_torture_cb);
@@ -423,7 +415,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.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,
+	.started	= rcu_batches_started_bh,
+	.completed	= rcu_batches_completed_bh,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -466,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
@@ -510,7 +504,7 @@ static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
 	srcu_read_unlock(&srcu_ctl, idx);
 }
 
-static int srcu_torture_completed(void)
+static unsigned long srcu_torture_completed(void)
 {
 	return srcu_batches_completed(&srcu_ctl);
 }
@@ -564,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
@@ -600,7 +595,8 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
+	.started	= rcu_batches_started_sched,
+	.completed	= rcu_batches_completed_sched,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -638,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
@@ -1015,8 +1012,8 @@ static void rcutorture_trace_dump(void)
 static void rcu_torture_timer(unsigned long unused)
 {
 	int idx;
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	static DEFINE_TORTURE_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
@@ -1024,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused)
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
+	if (cur_ops->started)
+		started = cur_ops->started();
+	else
+		started = cur_ops->completed();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1047,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed_end = cur_ops->completed();
+	completed = cur_ops->completed();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
+					  started, completed);
 		rcutorture_trace_dump();
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
+	completed = completed - started;
+	if (cur_ops->started)
+		completed++;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1073,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused)
 static int
 rcu_torture_reader(void *arg)
 {
-	int completed;
-	int completed_end;
+	unsigned long started;
+	unsigned long completed;
 	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct rcu_torture *p;
@@ -1093,7 +1095,10 @@ rcu_torture_reader(void *arg)
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
+		if (cur_ops->started)
+			started = cur_ops->started();
+		else
+			started = cur_ops->completed();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1114,14 +1119,16 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed_end = cur_ops->completed();
+		completed = cur_ops->completed();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
+						  ts, started, completed);
 			rcutorture_trace_dump();
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
+		completed = completed - started;
+		if (cur_ops->started)
+			completed++;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
@@ -1420,6 +1427,9 @@ static int rcu_torture_barrier(void *arg)
 		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
+			pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
+			       atomic_read(&barrier_cbs_invoked),
+			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
 		}
 		n_barrier_successes++;

kernel/rcu/srcu.c

@@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }

kernel/rcu/tiny.c

@@ -47,54 +47,14 @@ static void __call_rcu(struct rcu_head *head,
 		       void (*func)(struct rcu_head *rcu),
 		       struct rcu_ctrlblk *rcp);
 
-static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-
 #include "tiny_plugin.h"
 
-/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcu/tree.c. */
-static void rcu_idle_enter_common(long long newval)
-{
-	if (newval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("--="),
-					    rcu_dynticks_nesting, newval));
-		rcu_dynticks_nesting = newval;
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
-				    rcu_dynticks_nesting, newval));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
-					    rcu_dynticks_nesting, newval));
-		ftrace_dump(DUMP_ALL);
-		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
-			  current->pid, current->comm,
-			  idle->pid, idle->comm); /* must be idle task! */
-	}
-	rcu_sched_qs(); /* implies rcu_bh_inc() */
-	barrier();
-	rcu_dynticks_nesting = newval;
-}
-
 /*
  * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode (i.e., if the new value of dynticks_nesting is zero).
+ * entered that mode.
  */
 void rcu_idle_enter(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) ==
-	    DYNTICK_TASK_NEST_VALUE)
-		newval = 0;
-	else
-		newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE;
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
@@ -103,55 +63,14 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
  */
 void rcu_irq_exit(void)
 {
-	unsigned long flags;
-	long long newval;
-
-	local_irq_save(flags);
-	newval = rcu_dynticks_nesting - 1;
-	WARN_ON_ONCE(newval < 0);
-	rcu_idle_enter_common(newval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_exit);
 
-/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcu/tree.c. */
-static void rcu_idle_exit_common(long long oldval)
-{
-	if (oldval) {
-		RCU_TRACE(trace_rcu_dyntick(TPS("++="),
-					    oldval, rcu_dynticks_nesting));
-		return;
-	}
-	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
-	if (IS_ENABLED(CONFIG_RCU_TRACE) && !is_idle_task(current)) {
-		struct task_struct *idle __maybe_unused = idle_task(smp_processor_id());
-
-		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
-			  oldval, rcu_dynticks_nesting));
-		ftrace_dump(DUMP_ALL);
-		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
-			  current->pid, current->comm,
-			  idle->pid, idle->comm); /* must be idle task! */
-	}
-}
-
 /*
  * Exit idle, so that we are no longer in an extended quiescent state.
  */
 void rcu_idle_exit(void)
 {
-	unsigned long flags;
-	long long oldval;
-
-	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
-	WARN_ON_ONCE(rcu_dynticks_nesting < 0);
-	if (rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK)
-		rcu_dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
-		rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_idle_exit_common(oldval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
@@ -160,15 +79,6 @@ EXPORT_SYMBOL_GPL(rcu_idle_exit);
  */
 void rcu_irq_enter(void)
 {
-	unsigned long flags;
-	long long oldval;
-
-	local_irq_save(flags);
-	oldval = rcu_dynticks_nesting;
-	rcu_dynticks_nesting++;
-	WARN_ON_ONCE(rcu_dynticks_nesting == 0);
-	rcu_idle_exit_common(oldval);
-	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
@@ -179,22 +89,12 @@ EXPORT_SYMBOL_GPL(rcu_irq_enter);
  */
 bool notrace __rcu_is_watching(void)
 {
-	return rcu_dynticks_nesting;
+	return true;
 }
 EXPORT_SYMBOL(__rcu_is_watching);
 
 #endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
-/*
- * Test whether the current CPU was interrupted from idle.  Nested
- * interrupts don't count, we must be running at the first interrupt
- * level.
- */
-static int rcu_is_cpu_rrupt_from_idle(void)
-{
-	return rcu_dynticks_nesting <= 1;
-}
-
 /*
  * Helper function for rcu_sched_qs() and rcu_bh_qs().
  * Also irqs are disabled to avoid confusion due to interrupt handlers
@@ -250,7 +150,7 @@ void rcu_bh_qs(void)
 void rcu_check_callbacks(int user)
 {
 	RCU_TRACE(check_cpu_stalls());
-	if (user || rcu_is_cpu_rrupt_from_idle())
+	if (user)
 		rcu_sched_qs();
 	else if (!in_softirq())
 		rcu_bh_qs();
@@ -357,6 +257,11 @@ static void __call_rcu(struct rcu_head *head,
 	rcp->curtail = &head->next;
 	RCU_TRACE(rcp->qlen++);
 	local_irq_restore(flags);
+
+	if (unlikely(is_idle_task(current))) {
+		/* force scheduling for rcu_sched_qs() */
+		resched_cpu(0);
+	}
 }
 
 /*
@@ -383,6 +288,8 @@ EXPORT_SYMBOL_GPL(call_rcu_bh);
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
+	RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
 
 	rcu_early_boot_tests();
 }

kernel/rcu/tiny_plugin.h

@@ -145,17 +145,16 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 	rcp->ticks_this_gp++;
 	j = jiffies;
 	js = ACCESS_ONCE(rcp->jiffies_stall);
-	if (*rcp->curtail && ULONG_CMP_GE(j, js)) {
+	if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
-		       rcp->name, rcp->ticks_this_gp, rcu_dynticks_nesting,
+		       rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
 		       jiffies - rcp->gp_start, rcp->qlen);
 		dump_stack();
-	}
-	if (*rcp->curtail && ULONG_CMP_GE(j, js))
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
 			3 * rcu_jiffies_till_stall_check() + 3;
-	else if (ULONG_CMP_GE(j, js))
+	} else if (ULONG_CMP_GE(j, js)) {
 		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+	}
 }
 
 static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)

kernel/rcu/tree.h

@@ -27,7 +27,6 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
-#include <linux/irq_work.h>
 
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
@@ -172,11 +171,6 @@ struct rcu_node {
 				/*  queued on this rcu_node structure that */
 				/*  are blocking the current grace period, */
 				/*  there can be no such task. */
-	struct completion boost_completion;
-				/* Used to ensure that the rt_mutex used */
-				/*  to carry out the boosting is fully */
-				/*  released with no future boostee accesses */
-				/*  before that rt_mutex is re-initialized. */
 	struct rt_mutex boost_mtx;
 				/* Used only for the priority-boosting */
 				/*  side effect, not as a lock. */
@@ -257,9 +251,12 @@ struct rcu_data {
 					/*  in order to detect GP end. */
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
+	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
+					/*  for rcu_all_qs() invocations. */
 	bool		passed_quiesce;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
+	bool		gpwrap;		/* Possible gpnum/completed wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 #ifdef CONFIG_RCU_CPU_STALL_INFO
@@ -340,14 +337,10 @@ struct rcu_data {
 #ifdef CONFIG_RCU_NOCB_CPU
 	struct rcu_head *nocb_head;	/* CBs waiting for kthread. */
 	struct rcu_head **nocb_tail;
-	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
-	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	atomic_long_t nocb_q_count;	/* # CBs waiting for nocb */
+	atomic_long_t nocb_q_count_lazy; /*  invocation (all stages). */
 	struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
 	struct rcu_head **nocb_follower_tail;
-	atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */
-	atomic_long_t nocb_follower_count_lazy; /*  (approximate). */
-	int nocb_p_count;		/* # CBs being invoked by kthread */
-	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
 	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
@@ -356,8 +349,6 @@ struct rcu_data {
 	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
 					/* CBs waiting for GP. */
 	struct rcu_head **nocb_gp_tail;
-	long nocb_gp_count;
-	long nocb_gp_count_lazy;
 	bool nocb_leader_sleep;		/* Is the nocb leader thread asleep? */
 	struct rcu_data *nocb_next_follower;
 					/* Next follower in wakeup chain. */
@@ -488,10 +479,14 @@ struct rcu_state {
 						/*  due to no GP active. */
 	unsigned long gp_start;			/* Time at which GP started, */
 						/*  but in jiffies. */
+	unsigned long gp_activity;		/* Time of last GP kthread */
+						/*  activity in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
 						/*  a reluctant CPU. */
+	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */
+						/*  GP start. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	const char *name;			/* Name of structure. */
@@ -514,13 +509,6 @@ extern struct list_head rcu_struct_flavors;
 #define for_each_rcu_flavor(rsp) \
 	list_for_each_entry((rsp), &rcu_struct_flavors, flavors)
 
-/* Return values for rcu_preempt_offline_tasks(). */
-
-#define RCU_OFL_TASKS_NORM_GP	0x1		/* Tasks blocking normal */
-						/*  GP were moved to root. */
-#define RCU_OFL_TASKS_EXP_GP	0x2		/* Tasks blocking expedited */
-						/*  GP were moved to root. */
-
 /*
  * RCU implementation internal declarations:
  */
@@ -546,27 +534,16 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
-long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
-static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
-				      unsigned long flags);
+static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
-#ifdef CONFIG_HOTPLUG_CPU
-static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
-				     struct rcu_node *rnp,
-				     struct rcu_data *rdp);
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU)
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
-			       bool wake);
-#endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PREEMPT_RCU) */
 static void __init __rcu_init_preempt(void);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
@@ -622,24 +599,15 @@ static void rcu_dynticks_task_exit(void);
 #endif /* #ifndef RCU_TREE_NONCORE */
 
 #ifdef CONFIG_RCU_TRACE
-#ifdef CONFIG_RCU_NOCB_CPU
-/* Sum up queue lengths for tracing. */
+/* Read out queue lengths for tracing. */
 static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 {
-	*ql = atomic_long_read(&rdp->nocb_q_count) +
-	      rdp->nocb_p_count +
-	      atomic_long_read(&rdp->nocb_follower_count) +
-	      rdp->nocb_p_count + rdp->nocb_gp_count;
-	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) +
-	       rdp->nocb_p_count_lazy +
-	       atomic_long_read(&rdp->nocb_follower_count_lazy) +
-	       rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy;
-}
+#ifdef CONFIG_RCU_NOCB_CPU
+	*ql = atomic_long_read(&rdp->nocb_q_count);
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
-static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
-{
 	*ql = 0;
 	*qll = 0;
-}
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
+}
 #endif /* #ifdef CONFIG_RCU_TRACE */

kernel/rcu/tree_trace.c

@@ -46,6 +46,8 @@
 #define RCU_TREE_NONCORE
 #include "tree.h"
 
+DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+
 static int r_open(struct inode *inode, struct file *file,
 					const struct seq_operations *op)
 {
@@ -115,11 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d",
+	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
-		   rdp->passed_quiesce, rdp->qs_pending);
+		   rdp->passed_quiesce,
+		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+		   rdp->qs_pending);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,

kernel/softirq.c

@@ -656,9 +656,8 @@ static void run_ksoftirqd(unsigned int cpu)
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		rcu_note_context_switch();
 		local_irq_enable();
-		cond_resched();
+		cond_resched_rcu_qs();
 		return;
 	}
 	local_irq_enable();

lib/Kconfig.debug

@@ -1215,6 +1215,7 @@ config RCU_TORTURE_TEST
 	tristate "torture tests for RCU"
 	depends on DEBUG_KERNEL
 	select TORTURE_TEST
+	select SRCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests
@@ -1257,7 +1258,7 @@ config RCU_CPU_STALL_TIMEOUT
 config RCU_CPU_STALL_INFO
 	bool "Print additional diagnostics on RCU CPU stall"
 	depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL
-	default n
+	default y
 	help
 	  For each stalled CPU that is aware of the current RCU grace
 	  period, print out additional per-CPU diagnostic information

mm/Kconfig

@@ -325,6 +325,7 @@ config VIRT_TO_BUS
 
 config MMU_NOTIFIER
 	bool
+	select SRCU
 
 config KSM
 	bool "Enable KSM for page merging"

security/tomoyo/Kconfig

@@ -5,6 +5,7 @@ config SECURITY_TOMOYO
 	select SECURITYFS
 	select SECURITY_PATH
 	select SECURITY_NETWORK
+	select SRCU
 	default n
 	help
 	  This selects TOMOYO Linux, pathname-based access control.

tools/testing/selftests/rcutorture/bin/cpus2use.sh

@@ -24,7 +24,7 @@
 
 ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
 idlecpus=`mpstat | tail -1 | \
-	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'`
+	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'`
 awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '
 BEGIN {
 	cpus2use = idlecpus;

tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh

@@ -30,6 +30,7 @@ else
 	echo Unreadable results directory: $i
 	exit 1
 fi
+. tools/testing/selftests/rcutorture/bin/functions.sh
 
 configfile=`echo $i | sed -e 's/^.*\///'`
 ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
@@ -48,4 +49,21 @@ else
 		title="$title ($ngpsps per second)"
 	fi
 	echo $title
+	nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	if test -z "$nclosecalls"
+	then
+		exit 0
+	fi
+	if test "$nclosecalls" -eq 0
+	then
+		exit 0
+	fi
+	# Compute number of close calls per tenth of an hour
+	nclosecalls10=`awk -v nclosecalls=$nclosecalls -v dur=$dur 'BEGIN { print int(nclosecalls * 36000 / dur) }' < /dev/null`
+	if test $nclosecalls10 -gt 5 -a $nclosecalls -gt 1
+	then
+		print_bug $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	else
+		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
+	fi
 fi

tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh

@@ -8,9 +8,9 @@
 #
 # Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args
 #
-# qemu-args defaults to "-nographic", along with arguments specifying the
-#			number of CPUs and other options generated from
-#			the underlying CPU architecture.
+# qemu-args defaults to "-enable-kvm -soundhw pcspk -nographic", along with
+#			arguments specifying the number of CPUs and other
+#			options generated from the underlying CPU architecture.
 # boot_args defaults to value returned by the per_version_boot_params
 #			shell function.
 #
@@ -138,7 +138,7 @@ then
 fi
 
 # Generate -smp qemu argument.
-qemu_args="-nographic $qemu_args"
+qemu_args="-enable-kvm -soundhw pcspk -nographic $qemu_args"
 cpu_count=`configNR_CPUS.sh $config_template`
 cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"`
 vcpus=`identify_qemu_vcpus`
@@ -168,6 +168,7 @@ then
 	touch $resdir/buildonly
 	exit 0
 fi
+echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log
 echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!

tools/testing/selftests/rcutorture/bin/parse-build.sh

@@ -26,12 +26,15 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=$1
+F=$1
 title=$2
+T=/tmp/parse-build.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
 
 . functions.sh
 
-if grep -q CC < $T
+if grep -q CC < $F
 then
 	:
 else
@@ -39,18 +42,21 @@ else
 	exit 1
 fi
 
-if grep -q "error:" < $T
+if grep -q "error:" < $F
 then
 	print_bug $title build errors:
-	grep "error:" < $T
+	grep "error:" < $F
 	exit 2
 fi
-exit 0
 
-if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+grep warning: < $F > $T/warnings
+grep "include/linux/*rcu*\.h:" $T/warnings > $T/hwarnings
+grep "kernel/rcu/[^/]*:" $T/warnings > $T/cwarnings
+cat $T/hwarnings $T/cwarnings > $T/rcuwarnings
+if test -s $T/rcuwarnings
 then
 	print_warning $title build errors:
-	egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	cat $T/rcuwarnings
 	exit 2
 fi
 exit 0

tools/testing/selftests/rcutorture/bin/parse-console.sh

@@ -36,7 +36,7 @@ if grep -Pq '\x00' < $file
 then
 	print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
 	print_warning Assertion failure in $file $title