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 changes are:

   - Debloat RCU headers

   - Parallelize SRCU callback handling (plus overlapping patches)

   - Improve the performance of Tree SRCU on a CPU-hotplug stress test

   - Documentation updates

   - Miscellaneous fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (74 commits)
  rcu: Open-code the rcu_cblist_n_lazy_cbs() function
  rcu: Open-code the rcu_cblist_n_cbs() function
  rcu: Open-code the rcu_cblist_empty() function
  rcu: Separately compile large rcu_segcblist functions
  srcu: Debloat the <linux/rcu_segcblist.h> header
  srcu: Adjust default auto-expediting holdoff
  srcu: Specify auto-expedite holdoff time
  srcu: Expedite first synchronize_srcu() when idle
  srcu: Expedited grace periods with reduced memory contention
  srcu: Make rcutorture writer stalls print SRCU GP state
  srcu: Exact tracking of srcu_data structures containing callbacks
  srcu: Make SRCU be built by default
  srcu: Fix Kconfig botch when SRCU not selected
  rcu: Make non-preemptive schedule be Tasks RCU quiescent state
  srcu: Expedite srcu_schedule_cbs_snp() callback invocation
  srcu: Parallelize callback handling
  kvm: Move srcu_struct fields to end of struct kvm
  rcu: Fix typo in PER_RCU_NODE_PERIOD header comment
  rcu: Use true/false in assignment to bool
  rcu: Use bool value directly
  ...

Documentation/RCU/00-INDEX

@@ -17,7 +17,7 @@ rcu_dereference.txt
 rcubarrier.txt
 	- RCU and Unloadable Modules
 rculist_nulls.txt
-	- RCU list primitives for use with SLAB_DESTROY_BY_RCU
+	- RCU list primitives for use with SLAB_TYPESAFE_BY_RCU
 rcuref.txt
 	- Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt

Documentation/RCU/Design/Data-Structures/nxtlist.svg

@@ -19,7 +19,7 @@
    id="svg2"
    version="1.1"
    inkscape:version="0.48.4 r9939"
-   sodipodi:docname="nxtlist.fig">
+   sodipodi:docname="segcblist.svg">
   <metadata
      id="metadata94">
     <rdf:RDF>
@@ -28,7 +28,7 @@
         <dc:format>image/svg+xml</dc:format>
         <dc:type
            rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
-        <dc:title></dc:title>
+        <dc:title />
       </cc:Work>
     </rdf:RDF>
   </metadata>
@@ -241,61 +241,51 @@
        xml:space="preserve"
        x="225"
        y="675"
-       fill="#000000"
-       font-family="Courier"
        font-style="normal"
        font-weight="bold"
        font-size="324"
-       text-anchor="start"
-       id="text64">nxtlist</text>
+       id="text64"
+       style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;head</text>
     <!-- Text -->
     <text
        xml:space="preserve"
        x="225"
        y="1800"
-       fill="#000000"
-       font-family="Courier"
        font-style="normal"
        font-weight="bold"
        font-size="324"
-       text-anchor="start"
-       id="text66">nxttail[RCU_DONE_TAIL]</text>
+       id="text66"
+       style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_DONE_TAIL]</text>
     <!-- Text -->
     <text
        xml:space="preserve"
        x="225"
        y="2925"
-       fill="#000000"
-       font-family="Courier"
        font-style="normal"
        font-weight="bold"
        font-size="324"
-       text-anchor="start"
-       id="text68">nxttail[RCU_WAIT_TAIL]</text>
+       id="text68"
+       style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_WAIT_TAIL]</text>
     <!-- Text -->
     <text
        xml:space="preserve"
        x="225"
        y="4050"
-       fill="#000000"
-       font-family="Courier"
        font-style="normal"
        font-weight="bold"
        font-size="324"
-       text-anchor="start"
-       id="text70">nxttail[RCU_NEXT_READY_TAIL]</text>
+       id="text70"
+       style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_NEXT_READY_TAIL]</text>
     <!-- Text -->
     <text
        xml:space="preserve"
        x="225"
        y="5175"
-       fill="#000000"
-       font-family="Courier"
        font-style="normal"
        font-weight="bold"
        font-size="324"
-       text-anchor="start"
-       id="text72">nxttail[RCU_NEXT_TAIL]</text>
+       id="text72"
+       style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;tails[RCU_NEXT_TAIL]</text>
     <!-- Text -->
     <text
        xml:space="preserve"

Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html

@@ -284,6 +284,7 @@ Expedited Grace Period Refinements</a></h2>
 	Funnel locking and wait/wakeup</a>.
 <li>	<a href="#Use of Workqueues">Use of Workqueues</a>.
 <li>	<a href="#Stall Warnings">Stall warnings</a>.
+<li>	<a href="#Mid-Boot Operation">Mid-boot operation</a>.
 </ol>
 
 <h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
@@ -524,7 +525,7 @@ their grace periods and carrying out their wakeups.
 In earlier implementations, the task requesting the expedited
 grace period also drove it to completion.
 This straightforward approach had the disadvantage of needing to
-account for signals sent to user tasks,
+account for POSIX signals sent to user tasks,
 so more recent implemementations use the Linux kernel's
 <a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>.
 
@@ -533,8 +534,8 @@ The requesting task still does counter snapshotting and funnel-lock
 processing, but the task reaching the top of the funnel lock
 does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
 so that a workqueue kthread does the actual grace-period processing.
-Because workqueue kthreads do not accept signals, grace-period-wait
-processing need not allow for signals.
+Because workqueue kthreads do not accept POSIX signals, grace-period-wait
+processing need not allow for POSIX signals.
 
 In addition, this approach allows wakeups for the previous expedited
 grace period to be overlapped with processing for the next expedited
@@ -586,6 +587,46 @@ blocking the current grace period are printed.
 Each stall warning results in another pass through the loop, but the
 second and subsequent passes use longer stall times.
 
+<h3><a name="Mid-Boot Operation">Mid-boot operation</a></h3>
+
+<p>
+The use of workqueues has the advantage that the expedited
+grace-period code need not worry about POSIX signals.
+Unfortunately, it has the
+corresponding disadvantage that workqueues cannot be used until
+they are initialized, which does not happen until some time after
+the scheduler spawns the first task.
+Given that there are parts of the kernel that really do want to
+execute grace periods during this mid-boot &ldquo;dead zone&rdquo;,
+expedited grace periods must do something else during thie time.
+
+<p>
+What they do is to fall back to the old practice of requiring that the
+requesting task drive the expedited grace period, as was the case
+before the use of workqueues.
+However, the requesting task is only required to drive the grace period
+during the mid-boot dead zone.
+Before mid-boot, a synchronous grace period is a no-op.
+Some time after mid-boot, workqueues are used.
+
+<p>
+Non-expedited non-SRCU synchronous grace periods must also operate
+normally during mid-boot.
+This is handled by causing non-expedited grace periods to take the
+expedited code path during mid-boot.
+
+<p>
+The current code assumes that there are no POSIX signals during
+the mid-boot dead zone.
+However, if an overwhelming need for POSIX signals somehow arises,
+appropriate adjustments can be made to the expedited stall-warning code.
+One such adjustment would reinstate the pre-workqueue stall-warning
+checks, but only during the mid-boot dead zone.
+
+<p>
+With this refinement, synchronous grace periods can now be used from
+task context pretty much any time during the life of the kernel.
+
 <h3><a name="Summary">
 Summary</a></h3>
 

Documentation/RCU/rcu_dereference.txt

@@ -138,6 +138,15 @@ o	Be very careful about comparing pointers obtained from
 		This sort of comparison occurs frequently when scanning
 		RCU-protected circular linked lists.
 
+		Note that if checks for being within an RCU read-side
+		critical section are not required and the pointer is never
+		dereferenced, rcu_access_pointer() should be used in place
+		of rcu_dereference(). The rcu_access_pointer() primitive
+		does not require an enclosing read-side critical section,
+		and also omits the smp_read_barrier_depends() included in
+		rcu_dereference(), which in turn should provide a small
+		performance gain in some CPUs (e.g., the DEC Alpha).
+
 	o	The comparison is against a pointer that references memory
 		that was initialized "a long time ago."  The reason
 		this is safe is that even if misordering occurs, the

Documentation/RCU/rculist_nulls.txt

 Using hlist_nulls to protect read-mostly linked lists and
-objects using SLAB_DESTROY_BY_RCU allocations.
+objects using SLAB_TYPESAFE_BY_RCU allocations.
 
 Please read the basics in Documentation/RCU/listRCU.txt
 
@@ -7,7 +7,7 @@ Using special makers (called 'nulls') is a convenient way
 to solve following problem :
 
 A typical RCU linked list managing objects which are
-allocated with SLAB_DESTROY_BY_RCU kmem_cache can
+allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can
 use following algos :
 
 1) Lookup algo
@@ -96,7 +96,7 @@ unlock_chain(); // typically a spin_unlock()
 3) Remove algo
 --------------
 Nothing special here, we can use a standard RCU hlist deletion.
-But thanks to SLAB_DESTROY_BY_RCU, beware a deleted object can be reused
+But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused
 very very fast (before the end of RCU grace period)
 
 if (put_last_reference_on(obj) {

Documentation/RCU/stallwarn.txt

 Using RCU's CPU Stall Detector
 
-The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
-detector, which detects conditions that unduly delay RCU grace periods.
-This module parameter enables CPU stall detection by default, but
-may be overridden via boot-time parameter or at runtime via sysfs.
+This document first discusses what sorts of issues RCU's CPU stall
+detector can locate, and then discusses kernel parameters and Kconfig
+options that can be used to fine-tune the detector's operation.  Finally,
+this document explains the stall detector's "splat" format.
+
+
+What Causes RCU CPU Stall Warnings?
+
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
+
+o	A CPU looping in an RCU read-side critical section.
+
+o	A CPU looping with interrupts disabled.
+
+o	A CPU looping with preemption disabled.  This condition can
+	result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+	stalls.
+
+o	A CPU looping with bottom halves disabled.  This condition can
+	result in RCU-sched and RCU-bh stalls.
+
+o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
+	kernel without invoking schedule().  Note that cond_resched()
+	does not necessarily prevent RCU CPU stall warnings.  Therefore,
+	if the looping in the kernel is really expected and desirable
+	behavior, you might need to replace some of the cond_resched()
+	calls with calls to cond_resched_rcu_qs().
+
+o	Booting Linux using a console connection that is too slow to
+	keep up with the boot-time console-message rate.  For example,
+	a 115Kbaud serial console can be -way- too slow to keep up
+	with boot-time message rates, and will frequently result in
+	RCU CPU stall warning messages.  Especially if you have added
+	debug printk()s.
+
+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
+	that low-priority task is not permitted to run on any other CPU,
+	in which case the next RCU grace period can never complete, which
+	will eventually cause the system to run out of memory and hang.
+	While the system is in the process of running itself out of
+	memory, you might see stall-warning messages.
+
+o	A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+	is running at a higher priority than the RCU softirq threads.
+	This will prevent RCU callbacks from ever being invoked,
+	and in a CONFIG_PREEMPT_RCU kernel will further prevent
+	RCU grace periods from ever completing.  Either way, the
+	system will eventually run out of memory and hang.  In the
+	CONFIG_PREEMPT_RCU case, you might see stall-warning
+	messages.
+
+o	A hardware or software issue shuts off the scheduler-clock
+	interrupt on a CPU that is not in dyntick-idle mode.  This
+	problem really has happened, and seems to be most likely to
+	result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
+
+o	A bug in the RCU implementation.
+
+o	A hardware failure.  This is quite unlikely, but has occurred
+	at least once in real life.  A CPU failed in a running system,
+	becoming unresponsive, but not causing an immediate crash.
+	This resulted in a series of RCU CPU stall warnings, eventually
+	leading the realization that the CPU had failed.
+
+The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
+warning.  Note that SRCU does -not- have CPU stall warnings.  Please note
+that RCU only detects CPU stalls when there is a grace period in progress.
+No grace period, no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
+
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
+and with RCU's event tracing.  For information on RCU's event tracing,
+see include/trace/events/rcu.h.
+
+
+Fine-Tuning the RCU CPU Stall Detector
+
+The rcuupdate.rcu_cpu_stall_suppress module parameter disables RCU's
+CPU stall detector, which detects conditions that unduly delay RCU grace
+periods.  This module parameter enables CPU stall detection by default,
+but may be overridden via boot-time parameter or at runtime via sysfs.
 The stall detector's idea of what constitutes "unduly delayed" is
 controlled by a set of kernel configuration variables and cpp macros:
 
@@ -56,6 +149,9 @@ rcupdate.rcu_task_stall_timeout
 	And continues with the output of sched_show_task() for each
 	task stalling the current RCU-tasks grace period.
 
+
+Interpreting RCU's CPU Stall-Detector "Splats"
+
 For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling,
 it will print a message similar to the following:
 
@@ -178,89 +274,3 @@ grace period is in flight.
 
 It is entirely possible to see stall warnings from normal and from
 expedited grace periods at about the same time from the same run.
-
-
-What Causes RCU CPU Stall Warnings?
-
-So your kernel printed an RCU CPU stall warning.  The next question is
-"What caused it?"  The following problems can result in RCU CPU stall
-warnings:
-
-o	A CPU looping in an RCU read-side critical section.
-	
-o	A CPU looping with interrupts disabled.  This condition can
-	result in RCU-sched and RCU-bh stalls.
-
-o	A CPU looping with preemption disabled.  This condition can
-	result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
-	stalls.
-
-o	A CPU looping with bottom halves disabled.  This condition can
-	result in RCU-sched and RCU-bh stalls.
-
-o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
-	kernel without invoking schedule().  Note that cond_resched()
-	does not necessarily prevent RCU CPU stall warnings.  Therefore,
-	if the looping in the kernel is really expected and desirable
-	behavior, you might need to replace some of the cond_resched()
-	calls with calls to cond_resched_rcu_qs().
-
-o	Booting Linux using a console connection that is too slow to
-	keep up with the boot-time console-message rate.  For example,
-	a 115Kbaud serial console can be -way- too slow to keep up
-	with boot-time message rates, and will frequently result in
-	RCU CPU stall warning messages.  Especially if you have added
-	debug printk()s.
-
-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
-	that low-priority task is not permitted to run on any other CPU,
-	in which case the next RCU grace period can never complete, which
-	will eventually cause the system to run out of memory and hang.
-	While the system is in the process of running itself out of
-	memory, you might see stall-warning messages.
-
-o	A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
-	is running at a higher priority than the RCU softirq threads.
-	This will prevent RCU callbacks from ever being invoked,
-	and in a CONFIG_PREEMPT_RCU kernel will further prevent
-	RCU grace periods from ever completing.  Either way, the
-	system will eventually run out of memory and hang.  In the
-	CONFIG_PREEMPT_RCU case, you might see stall-warning
-	messages.
-
-o	A hardware or software issue shuts off the scheduler-clock
-	interrupt on a CPU that is not in dyntick-idle mode.  This
-	problem really has happened, and seems to be most likely to
-	result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
-
-o	A bug in the RCU implementation.
-
-o	A hardware failure.  This is quite unlikely, but has occurred
-	at least once in real life.  A CPU failed in a running system,
-	becoming unresponsive, but not causing an immediate crash.
-	This resulted in a series of RCU CPU stall warnings, eventually
-	leading the realization that the CPU had failed.
-
-The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
-warning.  Note that SRCU does -not- have CPU stall warnings.  Please note
-that RCU only detects CPU stalls when there is a grace period in progress.
-No grace period, no CPU stall warnings.
-
-To diagnose the cause of the stall, inspect the stack traces.
-The offending function will usually be near the top of the stack.
-If you have a series of stall warnings from a single extended stall,
-comparing the stack traces can often help determine where the stall
-is occurring, which will usually be in the function nearest the top of
-that portion of the stack which remains the same from trace to trace.
-If you can reliably trigger the stall, ftrace can be quite helpful.
-
-RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
-and with RCU's event tracing.  For information on RCU's event tracing,
-see include/trace/events/rcu.h.

Documentation/RCU/whatisRCU.txt

@@ -562,7 +562,9 @@ This section presents a "toy" RCU implementation that is based on
 familiar locking primitives.  Its overhead makes it a non-starter for
 real-life use, as does its lack of scalability.  It is also unsuitable
 for realtime use, since it allows scheduling latency to "bleed" from
-one read-side critical section to another.
+one read-side critical section to another.  It also assumes recursive
+reader-writer locks:  If you try this with non-recursive locks, and
+you allow nested rcu_read_lock() calls, you can deadlock.
 
 However, it is probably the easiest implementation to relate to, so is
 a good starting point.
@@ -587,16 +589,17 @@ It is extremely simple:
 		write_unlock(&rcu_gp_mutex);
 	}
 
-[You can ignore rcu_assign_pointer() and rcu_dereference() without
-missing much.  But here they are anyway.  And whatever you do, don't
-forget about them when submitting patches making use of RCU!]
+[You can ignore rcu_assign_pointer() and rcu_dereference() without missing
+much.  But here are simplified versions anyway.  And whatever you do,
+don't forget about them when submitting patches making use of RCU!]
 
-	#define rcu_assign_pointer(p, v)	({ \
-							smp_wmb(); \
-							(p) = (v); \
+	#define rcu_assign_pointer(p, v) \
+	({ \
+		smp_store_release(&(p), (v)); \
 	})
 
-	#define rcu_dereference(p)     ({ \
+	#define rcu_dereference(p) \
+	({ \
 		typeof(p) _________p1 = p; \
 		smp_read_barrier_depends(); \
 		(_________p1); \
@@ -925,7 +928,8 @@ d.	Do you need RCU grace periods to complete even in the face
 
 e.	Is your workload too update-intensive for normal use of
 	RCU, but inappropriate for other synchronization mechanisms?
-	If so, consider SLAB_DESTROY_BY_RCU.  But please be careful!
+	If so, consider SLAB_TYPESAFE_BY_RCU (which was originally
+	named SLAB_DESTROY_BY_RCU).  But please be careful!
 
 f.	Do you need read-side critical sections that are respected
 	even though they are in the middle of the idle loop, during

Documentation/admin-guide/kernel-parameters.txt

@@ -3800,6 +3800,14 @@
 	spia_pedr=
 	spia_peddr=
 
+	srcutree.exp_holdoff [KNL]
+			Specifies how many nanoseconds must elapse
+			since the end of the last SRCU grace period for
+			a given srcu_struct until the next normal SRCU
+			grace period will be considered for automatic
+			expediting.  Set to zero to disable automatic
+			expediting.
+
 	stacktrace	[FTRACE]
 			Enabled the stack tracer on boot up.
 

Documentation/memory-barriers.txt

@@ -768,7 +768,7 @@ equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
 	q = READ_ONCE(a);
-	WRITE_ONCE(b, 1);
+	WRITE_ONCE(b, 2);
 	do_something_else();
 
 Given this transformation, the CPU is not required to respect the ordering

arch/Kconfig

@@ -324,6 +324,9 @@ config HAVE_CMPXCHG_LOCAL
 config HAVE_CMPXCHG_DOUBLE
 	bool
 
+config ARCH_WEAK_RELEASE_ACQUIRE
+	bool
+
 config ARCH_WANT_IPC_PARSE_VERSION
 	bool
 

arch/powerpc/Kconfig

@@ -146,6 +146,7 @@ config PPC
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS

drivers/gpu/drm/i915/i915_gem.c

@@ -4789,7 +4789,7 @@ i915_gem_load_init(struct drm_i915_private *dev_priv)
 	dev_priv->requests = KMEM_CACHE(drm_i915_gem_request,
 					SLAB_HWCACHE_ALIGN |
 					SLAB_RECLAIM_ACCOUNT |
-					SLAB_DESTROY_BY_RCU);
+					SLAB_TYPESAFE_BY_RCU);
 	if (!dev_priv->requests)
 		goto err_vmas;
 

drivers/gpu/drm/i915/i915_gem_request.h

@@ -521,7 +521,7 @@ static inline struct drm_i915_gem_request *
 __i915_gem_active_get_rcu(const struct i915_gem_active *active)
 {
 	/* Performing a lockless retrieval of the active request is super
-	 * tricky. SLAB_DESTROY_BY_RCU merely guarantees that the backing
+	 * tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
 	 * slab of request objects will not be freed whilst we hold the
 	 * RCU read lock. It does not guarantee that the request itself
 	 * will not be freed and then *reused*. Viz,

drivers/gpu/drm/i915/selftests/mock_gem_device.c

@@ -174,7 +174,7 @@ struct drm_i915_private *mock_gem_device(void)
 	i915->requests = KMEM_CACHE(mock_request,
 				    SLAB_HWCACHE_ALIGN |
 				    SLAB_RECLAIM_ACCOUNT |
-				    SLAB_DESTROY_BY_RCU);
+				    SLAB_TYPESAFE_BY_RCU);
 	if (!i915->requests)
 		goto err_vmas;
 

drivers/staging/lustre/lustre/ldlm/ldlm_lockd.c

@@ -1115,7 +1115,7 @@ int ldlm_init(void)
 	ldlm_lock_slab = kmem_cache_create("ldlm_locks",
 					   sizeof(struct ldlm_lock), 0,
 					   SLAB_HWCACHE_ALIGN |
-					   SLAB_DESTROY_BY_RCU, NULL);
+					   SLAB_TYPESAFE_BY_RCU, NULL);
 	if (!ldlm_lock_slab) {
 		kmem_cache_destroy(ldlm_resource_slab);
 		return -ENOMEM;

fs/jbd2/journal.c

@@ -2363,7 +2363,7 @@ static int jbd2_journal_init_journal_head_cache(void)
 	jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
 				sizeof(struct journal_head),
 				0,		/* offset */
-				SLAB_TEMPORARY | SLAB_DESTROY_BY_RCU,
+				SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
 				NULL);		/* ctor */
 	retval = 0;
 	if (!jbd2_journal_head_cache) {

fs/signalfd.c

@@ -38,7 +38,7 @@ void signalfd_cleanup(struct sighand_struct *sighand)
 	/*
 	 * The lockless check can race with remove_wait_queue() in progress,
 	 * but in this case its caller should run under rcu_read_lock() and
-	 * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
+	 * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
 	 */
 	if (likely(!waitqueue_active(wqh)))
 		return;

include/linux/dma-fence.h

@@ -229,7 +229,7 @@ static inline struct dma_fence *dma_fence_get_rcu(struct dma_fence *fence)
  *
  * Function returns NULL if no refcount could be obtained, or the fence.
  * This function handles acquiring a reference to a fence that may be
- * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU),
+ * reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU),
  * so long as the caller is using RCU on the pointer to the fence.
  *
  * An alternative mechanism is to employ a seqlock to protect a bunch of
@@ -257,7 +257,7 @@ dma_fence_get_rcu_safe(struct dma_fence * __rcu *fencep)
 		 * have successfully acquire a reference to it. If it no
 		 * longer matches, we are holding a reference to some other
 		 * reallocated pointer. This is possible if the allocator
-		 * is using a freelist like SLAB_DESTROY_BY_RCU where the
+		 * is using a freelist like SLAB_TYPESAFE_BY_RCU where the
 		 * fence remains valid for the RCU grace period, but it
 		 * may be reallocated. When using such allocators, we are
 		 * responsible for ensuring the reference we get is to

include/linux/kvm_host.h

@@ -384,8 +384,6 @@ struct kvm {
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
-	struct srcu_struct srcu;
-	struct srcu_struct irq_srcu;
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 
 	/*
@@ -438,6 +436,8 @@ struct kvm {
 	struct list_head devices;
 	struct dentry *debugfs_dentry;
 	struct kvm_stat_data **debugfs_stat_data;
+	struct srcu_struct srcu;
+	struct srcu_struct irq_srcu;
 };
 
 #define kvm_err(fmt, ...) \

include/linux/rcu_node_tree.h

+/*
+ * RCU node combining tree definitions.  These are used to compute
+ * global attributes while avoiding common-case global contention.  A key
+ * property that these computations rely on is a tournament-style approach
+ * where only one of the tasks contending a lower level in the tree need
+ * advance to the next higher level.  If properly configured, this allows
+ * unlimited scalability while maintaining a constant level of contention
+ * on the root node.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifndef __LINUX_RCU_NODE_TREE_H
+#define __LINUX_RCU_NODE_TREE_H
+
+/*
+ * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
+ * CONFIG_RCU_FANOUT_LEAF.
+ * In theory, it should be possible to add more levels straightforwardly.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
+ */
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+#define RCU_FANOUT_LEAF 16
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2	      (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3	      (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4	      (RCU_FANOUT_3 * RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
+#  define RCU_NUM_LVLS	      1
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_NODES	      NUM_RCU_LVL_0
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
+#elif NR_CPUS <= RCU_FANOUT_2
+#  define RCU_NUM_LVLS	      2
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
+#elif NR_CPUS <= RCU_FANOUT_3
+#  define RCU_NUM_LVLS	      3
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
+#elif NR_CPUS <= RCU_FANOUT_4
+#  define RCU_NUM_LVLS	      4
+#  define NUM_RCU_LVL_0	      1
+#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+#  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
+#else
+# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
+
+#endif /* __LINUX_RCU_NODE_TREE_H */

include/linux/rcu_segcblist.h

+/*
+ * RCU segmented callback lists
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifndef __INCLUDE_LINUX_RCU_SEGCBLIST_H
+#define __INCLUDE_LINUX_RCU_SEGCBLIST_H
+
+/* Simple unsegmented callback lists. */
+struct rcu_cblist {
+	struct rcu_head *head;
+	struct rcu_head **tail;
+	long len;
+	long len_lazy;
+};
+
+#define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head }
+
+/* Complicated segmented callback lists.  ;-) */
+
+/*
+ * Index values for segments in rcu_segcblist structure.
+ *
+ * The segments are as follows:
+ *
+ * [head, *tails[RCU_DONE_TAIL]):
+ *	Callbacks whose grace period has elapsed, and thus can be invoked.
+ * [*tails[RCU_DONE_TAIL], *tails[RCU_WAIT_TAIL]):
+ *	Callbacks waiting for the current GP from the current CPU's viewpoint.
+ * [*tails[RCU_WAIT_TAIL], *tails[RCU_NEXT_READY_TAIL]):
+ *	Callbacks that arrived before the next GP started, again from
+ *	the current CPU's viewpoint.  These can be handled by the next GP.
+ * [*tails[RCU_NEXT_READY_TAIL], *tails[RCU_NEXT_TAIL]):
+ *	Callbacks that might have arrived after the next GP started.
+ *	There is some uncertainty as to when a given GP starts and
+ *	ends, but a CPU knows the exact times if it is the one starting
+ *	or ending the GP.  Other CPUs know that the previous GP ends
+ *	before the next one starts.
+ *
+ * Note that RCU_WAIT_TAIL cannot be empty unless RCU_NEXT_READY_TAIL is also
+ * empty.
+ *
+ * The ->gp_seq[] array contains the grace-period number at which the
+ * corresponding segment of callbacks will be ready to invoke.  A given
+ * element of this array is meaningful only when the corresponding segment
+ * is non-empty, and it is never valid for RCU_DONE_TAIL (whose callbacks
+ * are already ready to invoke) or for RCU_NEXT_TAIL (whose callbacks have
+ * not yet been assigned a grace-period number).
+ */
+#define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
+#define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
+#define RCU_NEXT_READY_TAIL	2	/* Also RCU_NEXT head. */
+#define RCU_NEXT_TAIL		3
+#define RCU_CBLIST_NSEGS	4
+
+struct rcu_segcblist {
+	struct rcu_head *head;
+	struct rcu_head **tails[RCU_CBLIST_NSEGS];
+	unsigned long gp_seq[RCU_CBLIST_NSEGS];
+	long len;
+	long len_lazy;
+};
+
+#define RCU_SEGCBLIST_INITIALIZER(n) \
+{ \
+	.head = NULL, \
+	.tails[RCU_DONE_TAIL] = &n.head, \
+	.tails[RCU_WAIT_TAIL] = &n.head, \
+	.tails[RCU_NEXT_READY_TAIL] = &n.head, \
+	.tails[RCU_NEXT_TAIL] = &n.head, \
+}
+
+#endif /* __INCLUDE_LINUX_RCU_SEGCBLIST_H */

include/linux/rculist.h

@@ -509,7 +509,8 @@ static inline void hlist_add_tail_rcu(struct hlist_node *n,
 {
 	struct hlist_node *i, *last = NULL;
 
-	for (i = hlist_first_rcu(h); i; i = hlist_next_rcu(i))
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; i; i = i->next)
 		last = i;
 
 	if (last) {

include/linux/rcupdate.h

@@ -368,14 +368,19 @@ static inline void rcu_init_nohz(void)
 #ifdef CONFIG_TASKS_RCU
 #define TASKS_RCU(x) x
 extern struct srcu_struct tasks_rcu_exit_srcu;
-#define rcu_note_voluntary_context_switch(t) \
+#define rcu_note_voluntary_context_switch_lite(t) \
 	do { \
-		rcu_all_qs(); \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
 			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
 	} while (0)
+#define rcu_note_voluntary_context_switch(t) \
+	do { \
+		rcu_all_qs(); \
+		rcu_note_voluntary_context_switch_lite(t); \
+	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
+#define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
@@ -1132,11 +1137,11 @@ do { \
  * if the UNLOCK and LOCK are executed by the same CPU or if the
  * UNLOCK and LOCK operate on the same lock variable.
  */
-#ifdef CONFIG_PPC
+#ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE
 #define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
+#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
 #define smp_mb__after_unlock_lock()	do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
+#endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
 
 
 #endif /* __LINUX_RCUPDATE_H */

include/linux/rcutiny.h

@@ -33,6 +33,11 @@ static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
 	return 0;
 }
 
+static inline bool rcu_eqs_special_set(int cpu)
+{
+	return false;  /* Never flag non-existent other CPUs! */
+}
+
 static inline unsigned long get_state_synchronize_rcu(void)
 {
 	return 0;
@@ -87,10 +92,11 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 	call_rcu(head, func);
 }
 
-static inline void rcu_note_context_switch(void)
-{
-	rcu_sched_qs();
-}
+#define rcu_note_context_switch(preempt) \
+	do { \
+		rcu_sched_qs(); \
+		rcu_note_voluntary_context_switch_lite(current); \
+	} while (0)
 
 /*
  * Take advantage of the fact that there is only one CPU, which
@@ -212,14 +218,14 @@ static inline void exit_rcu(void)
 {
 }
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
 extern int rcu_scheduler_active __read_mostly;
 void rcu_scheduler_starting(void);
-#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
 static inline void rcu_scheduler_starting(void)
 {
 }
-#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
@@ -237,6 +243,10 @@ static inline bool rcu_is_watching(void)
 
 #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
+static inline void rcu_request_urgent_qs_task(struct task_struct *t)
+{
+}
+
 static inline void rcu_all_qs(void)
 {
 	barrier(); /* Avoid RCU read-side critical sections leaking across. */

include/linux/rcutree.h

@@ -30,7 +30,7 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-void rcu_note_context_switch(void);
+void rcu_note_context_switch(bool preempt);
 int rcu_needs_cpu(u64 basem, u64 *nextevt);
 void rcu_cpu_stall_reset(void);
 
@@ -41,7 +41,7 @@ void rcu_cpu_stall_reset(void);
  */
 static inline void rcu_virt_note_context_switch(int cpu)
 {
-	rcu_note_context_switch();
+	rcu_note_context_switch(false);
 }
 
 void synchronize_rcu_bh(void);
@@ -108,6 +108,7 @@ void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
+void rcu_request_urgent_qs_task(struct task_struct *t);
 
 void rcu_all_qs(void);
 

include/linux/slab.h

@@ -28,7 +28,7 @@
 #define SLAB_STORE_USER		0x00010000UL	/* DEBUG: Store the last owner for bug hunting */
 #define SLAB_PANIC		0x00040000UL	/* Panic if kmem_cache_create() fails */
 /*
- * SLAB_DESTROY_BY_RCU - **WARNING** READ THIS!
+ * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
  *
  * This delays freeing the SLAB page by a grace period, it does _NOT_
  * delay object freeing. This means that if you do kmem_cache_free()
@@ -61,8 +61,10 @@
  *
  * rcu_read_lock before reading the address, then rcu_read_unlock after
  * taking the spinlock within the structure expected at that address.
+ *
+ * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
  */
-#define SLAB_DESTROY_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
+#define SLAB_TYPESAFE_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
 #define SLAB_MEM_SPREAD		0x00100000UL	/* Spread some memory over cpuset */
 #define SLAB_TRACE		0x00200000UL	/* Trace allocations and frees */
 

include/linux/srcu.h

@@ -32,35 +32,9 @@
 #include <linux/mutex.h>
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
+#include <linux/rcu_segcblist.h>
 
-struct srcu_array {
-	unsigned long lock_count[2];
-	unsigned long unlock_count[2];
-};
-
-struct rcu_batch {
-	struct rcu_head *head, **tail;
-};
-
-#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
-
-struct srcu_struct {
-	unsigned long completed;
-	struct srcu_array __percpu *per_cpu_ref;
-	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
-	bool running;
-	/* callbacks just queued */
-	struct rcu_batch batch_queue;
-	/* callbacks try to do the first check_zero */
-	struct rcu_batch batch_check0;
-	/* callbacks done with the first check_zero and the flip */
-	struct rcu_batch batch_check1;
-	struct rcu_batch batch_done;
-	struct delayed_work work;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-};
+struct srcu_struct;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
@@ -82,46 +56,15 @@ int init_srcu_struct(struct srcu_struct *sp);
 #define __SRCU_DEP_MAP_INIT(srcu_name)
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
-void process_srcu(struct work_struct *work);
-
-#define __SRCU_STRUCT_INIT(name)					\
-	{								\
-		.completed = -300,					\
-		.per_cpu_ref = &name##_srcu_array,			\
-		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
-		.running = false,					\
-		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
-		.batch_check0 = RCU_BATCH_INIT(name.batch_check0),	\
-		.batch_check1 = RCU_BATCH_INIT(name.batch_check1),	\
-		.batch_done = RCU_BATCH_INIT(name.batch_done),		\
-		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
-		__SRCU_DEP_MAP_INIT(name)				\
-	}
-
-/*
- * Define and initialize a srcu struct at build time.
- * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
- *
- * Note that although DEFINE_STATIC_SRCU() hides the name from other
- * files, the per-CPU variable rules nevertheless require that the
- * chosen name be globally unique.  These rules also prohibit use of
- * DEFINE_STATIC_SRCU() within a function.  If these rules are too
- * restrictive, declare the srcu_struct manually.  For example, in
- * each file:
- *
- *	static struct srcu_struct my_srcu;
- *
- * Then, before the first use of each my_srcu, manually initialize it:
- *
- *	init_srcu_struct(&my_srcu);
- *
- * See include/linux/percpu-defs.h for the rules on per-CPU variables.
- */
-#define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
-	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)
+#ifdef CONFIG_TINY_SRCU
+#include <linux/srcutiny.h>
+#elif defined(CONFIG_TREE_SRCU)
+#include <linux/srcutree.h>
+#elif defined(CONFIG_CLASSIC_SRCU)
+#include <linux/srcuclassic.h>
+#else
+#error "Unknown SRCU implementation specified to kernel configuration"
+#endif
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
@@ -147,9 +90,6 @@ void cleanup_srcu_struct(struct srcu_struct *sp);
 int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
-void synchronize_srcu_expedited(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
 

include/linux/srcuclassic.h

+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ *	classic v4.11 variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_CLASSIC_H
+#define _LINUX_SRCU_CLASSIC_H
+
+struct srcu_array {
+	unsigned long lock_count[2];
+	unsigned long unlock_count[2];
+};
+
+struct rcu_batch {
+	struct rcu_head *head, **tail;
+};
+
+#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
+
+struct srcu_struct {
+	unsigned long completed;
+	struct srcu_array __percpu *per_cpu_ref;
+	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
+	bool running;
+	/* callbacks just queued */
+	struct rcu_batch batch_queue;
+	/* callbacks try to do the first check_zero */
+	struct rcu_batch batch_check0;
+	/* callbacks done with the first check_zero and the flip */
+	struct rcu_batch batch_check1;
+	struct rcu_batch batch_done;
+	struct delayed_work work;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+void process_srcu(struct work_struct *work);
+
+#define __SRCU_STRUCT_INIT(name)					\
+	{								\
+		.completed = -300,					\
+		.per_cpu_ref = &name##_srcu_array,			\
+		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
+		.running = false,					\
+		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
+		.batch_check0 = RCU_BATCH_INIT(name.batch_check0),	\
+		.batch_check1 = RCU_BATCH_INIT(name.batch_check1),	\
+		.batch_done = RCU_BATCH_INIT(name.batch_done),		\
+		.work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
+		__SRCU_DEP_MAP_INIT(name)				\
+	}
+
+/*
+ * Define and initialize a srcu struct at build time.
+ * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ *
+ * Note that although DEFINE_STATIC_SRCU() hides the name from other
+ * files, the per-CPU variable rules nevertheless require that the
+ * chosen name be globally unique.  These rules also prohibit use of
+ * DEFINE_STATIC_SRCU() within a function.  If these rules are too
+ * restrictive, declare the srcu_struct manually.  For example, in
+ * each file:
+ *
+ *	static struct srcu_struct my_srcu;
+ *
+ * Then, before the first use of each my_srcu, manually initialize it:
+ *
+ *	init_srcu_struct(&my_srcu);
+ *
+ * See include/linux/percpu-defs.h for the rules on per-CPU variables.
+ */
+#define __DEFINE_SRCU(name, is_static)					\
+	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
+	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)
+
+void synchronize_srcu_expedited(struct srcu_struct *sp);
+void srcu_barrier(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
+
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+					   struct srcu_struct *sp, int *flags,
+					   unsigned long *gpnum,
+					   unsigned long *completed)
+{
+	if (test_type != SRCU_FLAVOR)
+		return;
+	*flags = 0;
+	*completed = sp->completed;
+	*gpnum = *completed;
+	if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head)
+		(*gpnum)++;
+}
+
+#endif

include/linux/srcutiny.h

+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ *	tiny variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_TINY_H
+#define _LINUX_SRCU_TINY_H
+
+#include <linux/swait.h>
+
+struct srcu_struct {
+	int srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
+	struct swait_queue_head srcu_wq;
+					/* Last srcu_read_unlock() wakes GP. */
+	unsigned long srcu_gp_seq;	/* GP seq # for callback tagging. */
+	struct rcu_segcblist srcu_cblist;
+					/* Pending SRCU callbacks. */
+	int srcu_idx;			/* Current reader array element. */
+	bool srcu_gp_running;		/* GP workqueue running? */
+	bool srcu_gp_waiting;		/* GP waiting for readers? */
+	struct work_struct srcu_work;	/* For driving grace periods. */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+void srcu_drive_gp(struct work_struct *wp);
+
+#define __SRCU_STRUCT_INIT(name)					\
+{									\
+	.srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq),	\
+	.srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist),	\
+	.srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp),	\
+	__SRCU_DEP_MAP_INIT(name)					\
+}
+
+/*
+ * This odd _STATIC_ arrangement is needed for API compatibility with
+ * Tree SRCU, which needs some per-CPU data.
+ */
+#define DEFINE_SRCU(name) \
+	struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_STATIC_SRCU(name) \
+	static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+
+void synchronize_srcu(struct srcu_struct *sp);
+
+static inline void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+	synchronize_srcu(sp);
+}
+
+static inline void srcu_barrier(struct srcu_struct *sp)
+{
+	synchronize_srcu(sp);
+}
+
+static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
+{
+	return 0;
+}
+
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+					   struct srcu_struct *sp, int *flags,
+					   unsigned long *gpnum,
+					   unsigned long *completed)
+{
+	if (test_type != SRCU_FLAVOR)
+		return;
+	*flags = 0;
+	*completed = sp->srcu_gp_seq;
+	*gpnum = *completed;
+}
+
+#endif

include/linux/srcutree.h

+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ *	tree variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_TREE_H
+#define _LINUX_SRCU_TREE_H
+
+#include <linux/rcu_node_tree.h>
+#include <linux/completion.h>
+
+struct srcu_node;
+struct srcu_struct;
+
+/*
+ * Per-CPU structure feeding into leaf srcu_node, similar in function
+ * to rcu_node.
+ */
+struct srcu_data {
+	/* Read-side state. */
+	unsigned long srcu_lock_count[2];	/* Locks per CPU. */
+	unsigned long srcu_unlock_count[2];	/* Unlocks per CPU. */
+
+	/* Update-side state. */
+	spinlock_t lock ____cacheline_internodealigned_in_smp;
+	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
+	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
+	bool srcu_cblist_invoking;		/* Invoking these CBs? */
+	struct delayed_work work;		/* Context for CB invoking. */
+	struct rcu_head srcu_barrier_head;	/* For srcu_barrier() use. */
+	struct srcu_node *mynode;		/* Leaf srcu_node. */
+	unsigned long grpmask;			/* Mask for leaf srcu_node */
+						/*  ->srcu_data_have_cbs[]. */
+	int cpu;
+	struct srcu_struct *sp;
+};
+
+/*
+ * Node in SRCU combining tree, similar in function to rcu_data.
+ */
+struct srcu_node {
+	spinlock_t lock;
+	unsigned long srcu_have_cbs[4];		/* GP seq for children */
+						/*  having CBs, but only */
+						/*  is > ->srcu_gq_seq. */
+	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs */
+						/*  have CBs for given GP? */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
+	struct srcu_node *srcu_parent;		/* Next up in tree. */
+	int grplo;				/* Least CPU for node. */
+	int grphi;				/* Biggest CPU for node. */
+};
+
+/*
+ * Per-SRCU-domain structure, similar in function to rcu_state.
+ */
+struct srcu_struct {
+	struct srcu_node node[NUM_RCU_NODES];	/* Combining tree. */
+	struct srcu_node *level[RCU_NUM_LVLS + 1];
+						/* First node at each level. */
+	struct mutex srcu_cb_mutex;		/* Serialize CB preparation. */
+	spinlock_t gp_lock;			/* protect ->srcu_cblist */
+	struct mutex srcu_gp_mutex;		/* Serialize GP work. */
+	unsigned int srcu_idx;			/* Current rdr array element. */
+	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
+	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
+	unsigned long srcu_last_gp_end;		/* Last GP end timestamp (ns) */
+	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
+	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
+	struct mutex srcu_barrier_mutex;	/* Serialize barrier ops. */
+	struct completion srcu_barrier_completion;
+						/* Awaken barrier rq at end. */
+	atomic_t srcu_barrier_cpu_cnt;		/* # CPUs not yet posting a */
+						/*  callback for the barrier */
+						/*  operation. */
+	struct delayed_work work;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+/* Values for state variable (bottom bits of ->srcu_gp_seq). */
+#define SRCU_STATE_IDLE		0
+#define SRCU_STATE_SCAN1	1
+#define SRCU_STATE_SCAN2	2
+
+void process_srcu(struct work_struct *work);
+
+#define __SRCU_STRUCT_INIT(name)					\
+	{								\
+		.sda = &name##_srcu_data,				\
+		.gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock),		\
+		.srcu_gp_seq_needed = 0 - 1,				\
+		__SRCU_DEP_MAP_INIT(name)				\
+	}
+
+/*
+ * Define and initialize a srcu struct at build time.
+ * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ *
+ * Note that although DEFINE_STATIC_SRCU() hides the name from other
+ * files, the per-CPU variable rules nevertheless require that the
+ * chosen name be globally unique.  These rules also prohibit use of
+ * DEFINE_STATIC_SRCU() within a function.  If these rules are too
+ * restrictive, declare the srcu_struct manually.  For example, in
+ * each file:
+ *
+ *	static struct srcu_struct my_srcu;
+ *
+ * Then, before the first use of each my_srcu, manually initialize it:
+ *
+ *	init_srcu_struct(&my_srcu);
+ *
+ * See include/linux/percpu-defs.h for the rules on per-CPU variables.
+ */
+#define __DEFINE_SRCU(name, is_static)					\
+	static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
+	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)
+
+void synchronize_srcu_expedited(struct srcu_struct *sp);
+void srcu_barrier(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
+
+void srcutorture_get_gp_data(enum rcutorture_type test_type,
+			     struct srcu_struct *sp, int *flags,
+			     unsigned long *gpnum, unsigned long *completed);
+
+#endif

include/linux/types.h

@@ -209,7 +209,7 @@ struct ustat {
  * naturally due ABI requirements, but some architectures (like CRIS) have
  * weird ABI and we need to ask it explicitly.
  *
- * The alignment is required to guarantee that bits 0 and 1 of @next will be
+ * The alignment is required to guarantee that bit 0 of @next will be
  * clear under normal conditions -- as long as we use call_rcu(),
  * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
  *

include/net/sock.h

@@ -995,7 +995,7 @@ struct smc_hashinfo;
 struct module;
 
 /*
- * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
+ * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
  * un-modified. Special care is taken when initializing object to zero.
  */
 static inline void sk_prot_clear_nulls(struct sock *sk, int size)

init/Kconfig

@@ -521,11 +521,41 @@ config RCU_EXPERT
 
 config SRCU
 	bool
+	default y
 	help
 	  This option selects the sleepable version of RCU. This version
 	  permits arbitrary sleeping or blocking within RCU read-side critical
 	  sections.
 
+config CLASSIC_SRCU
+	bool "Use v4.11 classic SRCU implementation"
+	default n
+	depends on RCU_EXPERT && SRCU
+	help
+	  This option selects the traditional well-tested classic SRCU
+	  implementation from v4.11, as might be desired for enterprise
+	  Linux distributions.  Without this option, the shiny new
+	  Tiny SRCU and Tree SRCU implementations are used instead.
+	  At some point, it is hoped that Tiny SRCU and Tree SRCU
+	  will accumulate enough test time and confidence to allow
+	  Classic SRCU to be dropped entirely.
+
+	  Say Y if you need a rock-solid SRCU.
+
+	  Say N if you would like help test Tree SRCU.
+
+config TINY_SRCU
+	bool
+	default y if SRCU && TINY_RCU && !CLASSIC_SRCU
+	help
+	  This option selects the single-CPU non-preemptible version of SRCU.
+
+config TREE_SRCU
+	bool
+	default y if SRCU && !TINY_RCU && !CLASSIC_SRCU
+	help
+	  This option selects the full-fledged version of SRCU.
+
 config TASKS_RCU
 	bool
 	default n
@@ -543,6 +573,9 @@ config RCU_STALL_COMMON
 	  the tiny variants to disable RCU CPU stall warnings, while
 	  making these warnings mandatory for the tree variants.
 
+config RCU_NEED_SEGCBLIST
+	def_bool ( TREE_RCU || PREEMPT_RCU || TINY_SRCU || TREE_SRCU )
+
 config CONTEXT_TRACKING
        bool
 
@@ -612,11 +645,17 @@ config RCU_FANOUT_LEAF
 	  initialization.  These systems tend to run CPU-bound, and thus
 	  are not helped by synchronized interrupts, and thus tend to
 	  skew them, which reduces lock contention enough that large
-	  leaf-level fanouts work well.
+	  leaf-level fanouts work well.  That said, setting leaf-level
+	  fanout to a large number will likely cause problematic
+	  lock contention on the leaf-level rcu_node structures unless
+	  you boot with the skew_tick kernel parameter.
 
 	  Select a specific number if testing RCU itself.
 
-	  Select the maximum permissible value for large systems.
+	  Select the maximum permissible value for large systems, but
+	  please understand that you may also need to set the skew_tick
+	  kernel boot parameter to avoid contention on the rcu_node
+	  structure's locks.
 
 	  Take the default if unsure.
 

kernel/fork.c

@@ -1337,7 +1337,7 @@ void __cleanup_sighand(struct sighand_struct *sighand)
 	if (atomic_dec_and_test(&sighand->count)) {
 		signalfd_cleanup(sighand);
 		/*
-		 * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
+		 * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
 		 * without an RCU grace period, see __lock_task_sighand().
 		 */
 		kmem_cache_free(sighand_cachep, sighand);
@@ -2176,7 +2176,7 @@ void __init proc_caches_init(void)
 {
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
 			SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
 	signal_cachep = kmem_cache_create("signal_cache",
 			sizeof(struct signal_struct), 0,

kernel/locking/lockdep.c

@@ -1158,10 +1158,10 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 		return 0;
 
 	printk("\n");
-	printk("======================================================\n");
-	printk("[ INFO: possible circular locking dependency detected ]\n");
+	pr_warn("======================================================\n");
+	pr_warn("WARNING: possible circular locking dependency detected\n");
 	print_kernel_ident();
-	printk("-------------------------------------------------------\n");
+	pr_warn("------------------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, task_pid_nr(curr));
 	print_lock(check_src);
@@ -1496,11 +1496,11 @@ print_bad_irq_dependency(struct task_struct *curr,
 		return 0;
 
 	printk("\n");
-	printk("======================================================\n");
-	printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n",
+	pr_warn("=====================================================\n");
+	pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n",
 		irqclass, irqclass);
 	print_kernel_ident();
-	printk("------------------------------------------------------\n");
+	pr_warn("-----------------------------------------------------\n");
 	printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
 		curr->comm, task_pid_nr(curr),
 		curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
@@ -1725,10 +1725,10 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 		return 0;
 
 	printk("\n");
-	printk("=============================================\n");
-	printk("[ INFO: possible recursive locking detected ]\n");
+	pr_warn("============================================\n");
+	pr_warn("WARNING: possible recursive locking detected\n");
 	print_kernel_ident();
-	printk("---------------------------------------------\n");
+	pr_warn("--------------------------------------------\n");
 	printk("%s/%d is trying to acquire lock:\n",
 		curr->comm, task_pid_nr(curr));
 	print_lock(next);
@@ -2075,10 +2075,10 @@ static void print_collision(struct task_struct *curr,
 			struct lock_chain *chain)
 {
 	printk("\n");
-	printk("======================\n");
-	printk("[chain_key collision ]\n");
+	pr_warn("============================\n");
+	pr_warn("WARNING: chain_key collision\n");
 	print_kernel_ident();
-	printk("----------------------\n");
+	pr_warn("----------------------------\n");
 	printk("%s/%d: ", current->comm, task_pid_nr(current));
 	printk("Hash chain already cached but the contents don't match!\n");
 
@@ -2374,10 +2374,10 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 		return 0;
 
 	printk("\n");
-	printk("=================================\n");
-	printk("[ INFO: inconsistent lock state ]\n");
+	pr_warn("================================\n");
+	pr_warn("WARNING: inconsistent lock state\n");
 	print_kernel_ident();
-	printk("---------------------------------\n");
+	pr_warn("--------------------------------\n");
 
 	printk("inconsistent {%s} -> {%s} usage.\n",
 		usage_str[prev_bit], usage_str[new_bit]);
@@ -2439,10 +2439,10 @@ print_irq_inversion_bug(struct task_struct *curr,
 		return 0;
 
 	printk("\n");
-	printk("=========================================================\n");
-	printk("[ INFO: possible irq lock inversion dependency detected ]\n");
+	pr_warn("========================================================\n");
+	pr_warn("WARNING: possible irq lock inversion dependency detected\n");
 	print_kernel_ident();
-	printk("---------------------------------------------------------\n");
+	pr_warn("--------------------------------------------------------\n");
 	printk("%s/%d just changed the state of lock:\n",
 		curr->comm, task_pid_nr(curr));
 	print_lock(this);
@@ -3190,10 +3190,10 @@ print_lock_nested_lock_not_held(struct task_struct *curr,
 		return 0;
 
 	printk("\n");
-	printk("==================================\n");
-	printk("[ BUG: Nested lock was not taken ]\n");
+	pr_warn("==================================\n");
+	pr_warn("WARNING: Nested lock was not taken\n");
 	print_kernel_ident();
-	printk("----------------------------------\n");
+	pr_warn("----------------------------------\n");
 
 	printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
 	print_lock(hlock);
@@ -3403,10 +3403,10 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
 		return 0;
 
 	printk("\n");
-	printk("=====================================\n");
-	printk("[ BUG: bad unlock balance detected! ]\n");
+	pr_warn("=====================================\n");
+	pr_warn("WARNING: bad unlock balance detected!\n");
 	print_kernel_ident();
-	printk("-------------------------------------\n");
+	pr_warn("-------------------------------------\n");
 	printk("%s/%d is trying to release lock (",
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
@@ -3975,10 +3975,10 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
 		return 0;
 
 	printk("\n");
-	printk("=================================\n");
-	printk("[ BUG: bad contention detected! ]\n");
+	pr_warn("=================================\n");
+	pr_warn("WARNING: bad contention detected!\n");
 	print_kernel_ident();
-	printk("---------------------------------\n");
+	pr_warn("---------------------------------\n");
 	printk("%s/%d is trying to contend lock (",
 		curr->comm, task_pid_nr(curr));
 	print_lockdep_cache(lock);
@@ -4319,10 +4319,10 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
 		return;
 
 	printk("\n");
-	printk("=========================\n");
-	printk("[ BUG: held lock freed! ]\n");
+	pr_warn("=========================\n");
+	pr_warn("WARNING: held lock freed!\n");
 	print_kernel_ident();
-	printk("-------------------------\n");
+	pr_warn("-------------------------\n");
 	printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n",
 		curr->comm, task_pid_nr(curr), mem_from, mem_to-1);
 	print_lock(hlock);
@@ -4377,11 +4377,11 @@ static void print_held_locks_bug(void)
 		return;
 
 	printk("\n");
-	printk("=====================================\n");
-	printk("[ BUG: %s/%d still has locks held! ]\n",
+	pr_warn("====================================\n");
+	pr_warn("WARNING: %s/%d still has locks held!\n",
 	       current->comm, task_pid_nr(current));
 	print_kernel_ident();
-	printk("-------------------------------------\n");
+	pr_warn("------------------------------------\n");
 	lockdep_print_held_locks(current);
 	printk("\nstack backtrace:\n");
 	dump_stack();
@@ -4446,7 +4446,7 @@ void debug_show_all_locks(void)
 	} while_each_thread(g, p);
 
 	printk("\n");
-	printk("=============================================\n\n");
+	pr_warn("=============================================\n\n");
 
 	if (unlock)
 		read_unlock(&tasklist_lock);
@@ -4476,10 +4476,10 @@ asmlinkage __visible void lockdep_sys_exit(void)
 		if (!debug_locks_off())
 			return;
 		printk("\n");
-		printk("================================================\n");
-		printk("[ BUG: lock held when returning to user space! ]\n");
+		pr_warn("================================================\n");
+		pr_warn("WARNING: lock held when returning to user space!\n");
 		print_kernel_ident();
-		printk("------------------------------------------------\n");
+		pr_warn("------------------------------------------------\n");
 		printk("%s/%d is leaving the kernel with locks still held!\n",
 				curr->comm, curr->pid);
 		lockdep_print_held_locks(curr);
@@ -4496,13 +4496,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 #endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
 	/* Note: the following can be executed concurrently, so be careful. */
 	printk("\n");
-	pr_err("===============================\n");
-	pr_err("[ ERR: suspicious RCU usage.  ]\n");
+	pr_warn("=============================\n");
+	pr_warn("WARNING: suspicious RCU usage\n");
 	print_kernel_ident();
-	pr_err("-------------------------------\n");
-	pr_err("%s:%d %s!\n", file, line, s);
-	pr_err("\nother info that might help us debug this:\n\n");
-	pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+	pr_warn("-----------------------------\n");
+	printk("%s:%d %s!\n", file, line, s);
+	printk("\nother info that might help us debug this:\n\n");
+	printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
 			: !rcu_is_watching()

kernel/locking/rtmutex-debug.c

@@ -102,10 +102,11 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter)
 		return;
 	}
 
-	printk("\n============================================\n");
-	printk(  "[ BUG: circular locking deadlock detected! ]\n");
-	printk("%s\n", print_tainted());
-	printk(  "--------------------------------------------\n");
+	pr_warn("\n");
+	pr_warn("============================================\n");
+	pr_warn("WARNING: circular locking deadlock detected!\n");
+	pr_warn("%s\n", print_tainted());
+	pr_warn("--------------------------------------------\n");
 	printk("%s/%d is deadlocking current task %s/%d\n\n",
 	       task->comm, task_pid_nr(task),
 	       current->comm, task_pid_nr(current));

kernel/rcu/Makefile

@@ -3,10 +3,13 @@
 KCOV_INSTRUMENT := n
 
 obj-y += update.o sync.o
-obj-$(CONFIG_SRCU) += srcu.o
+obj-$(CONFIG_CLASSIC_SRCU) += srcu.o
+obj-$(CONFIG_TREE_SRCU) += srcutree.o
+obj-$(CONFIG_TINY_SRCU) += srcutiny.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
 obj-$(CONFIG_TREE_RCU) += tree.o
 obj-$(CONFIG_PREEMPT_RCU) += tree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
 obj-$(CONFIG_TINY_RCU) += tiny.o
+obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o

kernel/rcu/rcu.h

@@ -56,6 +56,83 @@
 #define DYNTICK_TASK_EXIT_IDLE	   (DYNTICK_TASK_NEST_VALUE + \
 				    DYNTICK_TASK_FLAG)
 
+
+/*
+ * Grace-period counter management.
+ */
+
+#define RCU_SEQ_CTR_SHIFT	2
+#define RCU_SEQ_STATE_MASK	((1 << RCU_SEQ_CTR_SHIFT) - 1)
+
+/*
+ * Return the counter portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline unsigned long rcu_seq_ctr(unsigned long s)
+{
+	return s >> RCU_SEQ_CTR_SHIFT;
+}
+
+/*
+ * Return the state portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline int rcu_seq_state(unsigned long s)
+{
+	return s & RCU_SEQ_STATE_MASK;
+}
+
+/*
+ * Set the state portion of the pointed-to sequence number.
+ * The caller is responsible for preventing conflicting updates.
+ */
+static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
+{
+	WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
+	WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
+}
+
+/* Adjust sequence number for start of update-side operation. */
+static inline void rcu_seq_start(unsigned long *sp)
+{
+	WRITE_ONCE(*sp, *sp + 1);
+	smp_mb(); /* Ensure update-side operation after counter increment. */
+	WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
+}
+
+/* Adjust sequence number for end of update-side operation. */
+static inline void rcu_seq_end(unsigned long *sp)
+{
+	smp_mb(); /* Ensure update-side operation before counter increment. */
+	WARN_ON_ONCE(!rcu_seq_state(*sp));
+	WRITE_ONCE(*sp, (*sp | RCU_SEQ_STATE_MASK) + 1);
+}
+
+/* Take a snapshot of the update side's sequence number. */
+static inline unsigned long rcu_seq_snap(unsigned long *sp)
+{
+	unsigned long s;
+
+	s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
+	smp_mb(); /* Above access must not bleed into critical section. */
+	return s;
+}
+
+/* Return the current value the update side's sequence number, no ordering. */
+static inline unsigned long rcu_seq_current(unsigned long *sp)
+{
+	return READ_ONCE(*sp);
+}
+
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred.
+ */
+static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
+{
+	return ULONG_CMP_GE(READ_ONCE(*sp), s);
+}
+
 /*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
@@ -109,12 +186,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 
 	rcu_lock_acquire(&rcu_callback_map);
 	if (__is_kfree_rcu_offset(offset)) {
-		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
+		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset);)
 		kfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
 		return true;
 	} else {
-		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
+		RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
 		head->func(head);
 		rcu_lock_release(&rcu_callback_map);
 		return false;
@@ -144,4 +221,76 @@ void rcu_test_sync_prims(void);
  */
 extern void resched_cpu(int cpu);
 
+#if defined(SRCU) || !defined(TINY_RCU)
+
+#include <linux/rcu_node_tree.h>
+
+extern int rcu_num_lvls;
+extern int num_rcu_lvl[];
+extern int rcu_num_nodes;
+static bool rcu_fanout_exact;
+static int rcu_fanout_leaf;
+
+/*
+ * Compute the per-level fanout, either using the exact fanout specified
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
+ */
+static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
+{
+	int i;
+
+	if (rcu_fanout_exact) {
+		levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+		for (i = rcu_num_lvls - 2; i >= 0; i--)
+			levelspread[i] = RCU_FANOUT;
+	} else {
+		int ccur;
+		int cprv;
+
+		cprv = nr_cpu_ids;
+		for (i = rcu_num_lvls - 1; i >= 0; i--) {
+			ccur = levelcnt[i];
+			levelspread[i] = (cprv + ccur - 1) / ccur;
+			cprv = ccur;
+		}
+	}
+}
+
+/*
+ * Do a full breadth-first scan of the rcu_node structures for the
+ * specified rcu_state structure.
+ */
+#define rcu_for_each_node_breadth_first(rsp, rnp) \
+	for ((rnp) = &(rsp)->node[0]; \
+	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure.  Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+	for ((rnp) = &(rsp)->node[0]; \
+	     (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure.  Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
+#define rcu_for_each_leaf_node(rsp, rnp) \
+	for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Iterate over all possible CPUs in a leaf RCU node.
+ */
+#define for_each_leaf_node_possible_cpu(rnp, cpu) \
+	for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
+	     cpu <= rnp->grphi; \
+	     cpu = cpumask_next((cpu), cpu_possible_mask))
+
+#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
+
 #endif /* __LINUX_RCU_H */

kernel/rcu/rcu_segcblist.h

+/*
+ * RCU segmented callback lists, internal-to-rcu header file
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#include <linux/rcu_segcblist.h>
+
+/*
+ * Account for the fact that a previously dequeued callback turned out
+ * to be marked as lazy.
+ */
+static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
+{
+	rclp->len_lazy--;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer.  Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
+{
+	return rclp->head;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer.  Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
+{
+	WARN_ON_ONCE(!rclp->head);
+	return rclp->tail;
+}
+
+void rcu_cblist_init(struct rcu_cblist *rclp);
+long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim);
+struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
+
+/*
+ * Is the specified rcu_segcblist structure empty?
+ *
+ * But careful!  The fact that the ->head field is NULL does not
+ * necessarily imply that there are no callbacks associated with
+ * this structure.  When callbacks are being invoked, they are
+ * removed as a group.  If callback invocation must be preempted,
+ * the remaining callbacks will be added back to the list.  Either
+ * way, the counts are updated later.
+ *
+ * So it is often the case that rcu_segcblist_n_cbs() should be used
+ * instead.
+ */
+static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
+{
+	return !rsclp->head;
+}
+
+/* Return number of callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
+{
+	return READ_ONCE(rsclp->len);
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
+{
+	return rsclp->len_lazy;
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
+{
+	return rsclp->len - rsclp->len_lazy;
+}
+
+/*
+ * Is the specified rcu_segcblist enabled, for example, not corresponding
+ * to an offline or callback-offloaded CPU?
+ */
+static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
+{
+	return !!rsclp->tails[RCU_NEXT_TAIL];
+}
+
+/*
+ * Are all segments following the specified segment of the specified
+ * rcu_segcblist structure empty of callbacks?  (The specified
+ * segment might well contain callbacks.)
+ */
+static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
+{
+	return !*rsclp->tails[seg];
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer.  Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
+{
+	return rsclp->head;
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer.  Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
+{
+	WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
+	return rsclp->tails[RCU_NEXT_TAIL];
+}
+
+void rcu_segcblist_init(struct rcu_segcblist *rsclp);
+void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg);
+bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp);
+void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp);
+void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
+			   struct rcu_head *rhp, bool lazy);
+bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+			   struct rcu_head *rhp, bool lazy);
+void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
+				 struct rcu_cblist *rclp);
+void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
+				    struct rcu_cblist *rclp);
+void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
+				    struct rcu_cblist *rclp);
+void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
+				struct rcu_cblist *rclp);
+void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
+				   struct rcu_cblist *rclp);
+void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
+				   struct rcu_cblist *rclp);
+void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
+				    unsigned long seq);

kernel/rcu/rcutorture.c

@@ -559,19 +559,34 @@ static void srcu_torture_barrier(void)
 
 static void srcu_torture_stats(void)
 {
-	int cpu;
-	int idx = srcu_ctlp->completed & 0x1;
+	int __maybe_unused cpu;
+	int idx;
 
-	pr_alert("%s%s per-CPU(idx=%d):",
+#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU)
+#ifdef CONFIG_TREE_SRCU
+	idx = srcu_ctlp->srcu_idx & 0x1;
+#else /* #ifdef CONFIG_TREE_SRCU */
+	idx = srcu_ctlp->completed & 0x1;
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
+	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
-		struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
+#ifdef CONFIG_TREE_SRCU
+		struct srcu_data *counts;
+
+		counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
+		u0 = counts->srcu_unlock_count[!idx];
+		u1 = counts->srcu_unlock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
+		struct srcu_array *counts;
 
+		counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
 		u0 = counts->unlock_count[!idx];
 		u1 = counts->unlock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -579,14 +594,26 @@ static void srcu_torture_stats(void)
 		 */
 		smp_rmb();
 
+#ifdef CONFIG_TREE_SRCU
+		l0 = counts->srcu_lock_count[!idx];
+		l1 = counts->srcu_lock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
 		l0 = counts->lock_count[!idx];
 		l1 = counts->lock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
+#elif defined(CONFIG_TINY_SRCU)
+	idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n",
+		 torture_type, TORTURE_FLAG, idx,
+		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
+		 READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
+#endif
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -1333,12 +1360,14 @@ rcu_torture_stats_print(void)
 		cur_ops->stats();
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
-		int __maybe_unused flags;
-		unsigned long __maybe_unused gpnum;
-		unsigned long __maybe_unused completed;
+		int __maybe_unused flags = 0;
+		unsigned long __maybe_unused gpnum = 0;
+		unsigned long __maybe_unused completed = 0;
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
+		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+					&flags, &gpnum, &completed);
 		wtp = READ_ONCE(writer_task);
 		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
 			 rcu_torture_writer_state_getname(),

kernel/rcu/srcu.c

@@ -243,8 +243,14 @@ static bool srcu_readers_active(struct srcu_struct *sp)
  * cleanup_srcu_struct - deconstruct a sleep-RCU structure
  * @sp: structure to clean up.
  *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
+ * Must invoke this only after you are finished using a given srcu_struct
+ * that was initialized via init_srcu_struct().  This code does some
+ * probabalistic checking, spotting late uses of srcu_read_lock(),
+ * synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
+ * If any such late uses are detected, the per-CPU memory associated with
+ * the srcu_struct is simply leaked and WARN_ON() is invoked.  If the
+ * caller frees the srcu_struct itself, a use-after-free crash will likely
+ * ensue, but at least there will be a warning printed.
  */
 void cleanup_srcu_struct(struct srcu_struct *sp)
 {

kernel/rcu/srcutiny.c

+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ *	tiny version for non-preemptible single-CPU use.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/srcu.h>
+
+#include <linux/rcu_node_tree.h>
+#include "rcu_segcblist.h"
+#include "rcu.h"
+
+static int init_srcu_struct_fields(struct srcu_struct *sp)
+{
+	sp->srcu_lock_nesting[0] = 0;
+	sp->srcu_lock_nesting[1] = 0;
+	init_swait_queue_head(&sp->srcu_wq);
+	sp->srcu_gp_seq = 0;
+	rcu_segcblist_init(&sp->srcu_cblist);
+	sp->srcu_gp_running = false;
+	sp->srcu_gp_waiting = false;
+	sp->srcu_idx = 0;
+	INIT_WORK(&sp->srcu_work, srcu_drive_gp);
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+		       struct lock_class_key *key)
+{
+	/* Don't re-initialize a lock while it is held. */
+	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+	lockdep_init_map(&sp->dep_map, name, key, 0);
+	return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * init_srcu_struct - initialize a sleep-RCU structure
+ * @sp: structure to initialize.
+ *
+ * Must invoke this on a given srcu_struct before passing that srcu_struct
+ * to any other function.  Each srcu_struct represents a separate domain
+ * of SRCU protection.
+ */
+int init_srcu_struct(struct srcu_struct *sp)
+{
+	return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+	WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+	flush_work(&sp->srcu_work);
+	WARN_ON(rcu_seq_state(sp->srcu_gp_seq));
+	WARN_ON(sp->srcu_gp_running);
+	WARN_ON(sp->srcu_gp_waiting);
+	WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist));
+}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct.  Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+int __srcu_read_lock(struct srcu_struct *sp)
+{
+	int idx;
+
+	idx = READ_ONCE(sp->srcu_idx);
+	WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1);
+	return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
+
+/*
+ * Removes the count for the old reader from the appropriate element of
+ * the srcu_struct.  Must be called from process context.
+ */
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+{
+	int newval = sp->srcu_lock_nesting[idx] - 1;
+
+	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
+	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
+		swake_up(&sp->srcu_wq);
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
+
+/*
+ * Workqueue handler to drive one grace period and invoke any callbacks
+ * that become ready as a result.  Single-CPU and !PREEMPT operation
+ * means that we get away with murder on synchronization.  ;-)
+ */
+void srcu_drive_gp(struct work_struct *wp)
+{
+	int idx;
+	struct rcu_cblist ready_cbs;
+	struct srcu_struct *sp;
+	struct rcu_head *rhp;
+
+	sp = container_of(wp, struct srcu_struct, srcu_work);
+	if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist))
+		return; /* Already running or nothing to do. */
+
+	/* Tag recently arrived callbacks and wait for readers. */
+	WRITE_ONCE(sp->srcu_gp_running, true);
+	rcu_segcblist_accelerate(&sp->srcu_cblist,
+				 rcu_seq_snap(&sp->srcu_gp_seq));
+	rcu_seq_start(&sp->srcu_gp_seq);
+	idx = sp->srcu_idx;
+	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
+	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
+	swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+	rcu_seq_end(&sp->srcu_gp_seq);
+
+	/* Update callback list based on GP, and invoke ready callbacks. */
+	rcu_segcblist_advance(&sp->srcu_cblist,
+			      rcu_seq_current(&sp->srcu_gp_seq));
+	if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) {
+		rcu_cblist_init(&ready_cbs);
+		local_irq_disable();
+		rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs);
+		local_irq_enable();
+		rhp = rcu_cblist_dequeue(&ready_cbs);
+		for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
+			local_bh_disable();
+			rhp->func(rhp);
+			local_bh_enable();
+		}
+		local_irq_disable();
+		rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs);
+		local_irq_enable();
+	}
+	WRITE_ONCE(sp->srcu_gp_running, false);
+
+	/*
+	 * If more callbacks, reschedule ourselves.  This can race with
+	 * a call_srcu() at interrupt level, but the ->srcu_gp_running
+	 * checks will straighten that out.
+	 */
+	if (!rcu_segcblist_empty(&sp->srcu_cblist))
+		schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_drive_gp);
+
+/*
+ * Enqueue an SRCU callback on the specified srcu_struct structure,
+ * initiating grace-period processing if it is not already running.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+	       rcu_callback_t func)
+{
+	unsigned long flags;
+
+	head->func = func;
+	local_irq_save(flags);
+	rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
+	local_irq_restore(flags);
+	if (!READ_ONCE(sp->srcu_gp_running))
+		schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+/*
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+	struct rcu_synchronize rs;
+
+	init_rcu_head_on_stack(&rs.head);
+	init_completion(&rs.completion);
+	call_srcu(sp, &rs.head, wakeme_after_rcu);
+	wait_for_completion(&rs.completion);
+	destroy_rcu_head_on_stack(&rs.head);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);

kernel/rcu/tiny.c

@@ -79,7 +79,7 @@ EXPORT_SYMBOL(__rcu_is_watching);
  */
 static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
 {
-	RCU_TRACE(reset_cpu_stall_ticks(rcp));
+	RCU_TRACE(reset_cpu_stall_ticks(rcp);)
 	if (rcp->donetail != rcp->curtail) {
 		rcp->donetail = rcp->curtail;
 		return 1;
@@ -125,7 +125,7 @@ void rcu_bh_qs(void)
  */
 void rcu_check_callbacks(int user)
 {
-	RCU_TRACE(check_cpu_stalls());
+	RCU_TRACE(check_cpu_stalls();)
 	if (user)
 		rcu_sched_qs();
 	else if (!in_softirq())
@@ -143,7 +143,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	const char *rn = NULL;
 	struct rcu_head *next, *list;
 	unsigned long flags;
-	RCU_TRACE(int cb_count = 0);
+	RCU_TRACE(int cb_count = 0;)
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
@@ -152,7 +152,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		local_irq_restore(flags);
 		return;
 	}
-	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
+	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);)
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;
 	*rcp->donetail = NULL;
@@ -162,7 +162,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	local_irq_restore(flags);
 
 	/* Invoke the callbacks on the local list. */
-	RCU_TRACE(rn = rcp->name);
+	RCU_TRACE(rn = rcp->name;)
 	while (list) {
 		next = list->next;
 		prefetch(next);
@@ -171,9 +171,9 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		__rcu_reclaim(rn, list);
 		local_bh_enable();
 		list = next;
-		RCU_TRACE(cb_count++);
+		RCU_TRACE(cb_count++;)
 	}
-	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
+	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);)
 	RCU_TRACE(trace_rcu_batch_end(rcp->name,
 				      cb_count, 0, need_resched(),
 				      is_idle_task(current),
@@ -221,7 +221,7 @@ static void __call_rcu(struct rcu_head *head,
 	local_irq_save(flags);
 	*rcp->curtail = head;
 	rcp->curtail = &head->next;
-	RCU_TRACE(rcp->qlen++);
+	RCU_TRACE(rcp->qlen++;)
 	local_irq_restore(flags);
 
 	if (unlikely(is_idle_task(current))) {
@@ -254,8 +254,8 @@ 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_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

@@ -52,7 +52,7 @@ static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	RCU_TRACE(.name = "rcu_bh")
 };
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
 #include <linux/kernel_stat.h>
 
 int rcu_scheduler_active __read_mostly;
@@ -65,15 +65,16 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  * to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
  * The reason for this is that Tiny RCU does not need kthreads, so does
  * not have to care about the fact that the scheduler is half-initialized
- * at a certain phase of the boot process.
+ * at a certain phase of the boot process.  Unless SRCU is in the mix.
  */
 void __init rcu_scheduler_starting(void)
 {
 	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+	rcu_scheduler_active = IS_ENABLED(CONFIG_SRCU)
+		? RCU_SCHEDULER_INIT : RCU_SCHEDULER_RUNNING;
 }
 
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
 
 #ifdef CONFIG_RCU_TRACE
 
@@ -162,8 +163,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
 
 static void check_cpu_stalls(void)
 {
-	RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
-	RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
+	RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);)
+	RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);)
 }
 
 #endif /* #ifdef CONFIG_RCU_TRACE */

kernel/rcu/tree.h

@@ -30,80 +30,9 @@
 #include <linux/seqlock.h>
 #include <linux/swait.h>
 #include <linux/stop_machine.h>
+#include <linux/rcu_node_tree.h>
 
-/*
- * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
- * CONFIG_RCU_FANOUT_LEAF.
- * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this did work well going from three levels to four.
- * Of course, your mileage may vary.
- */
-
-#ifdef CONFIG_RCU_FANOUT
-#define RCU_FANOUT CONFIG_RCU_FANOUT
-#else /* #ifdef CONFIG_RCU_FANOUT */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT 64
-# else
-# define RCU_FANOUT 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT */
-
-#ifdef CONFIG_RCU_FANOUT_LEAF
-#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
-#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT_LEAF 64
-# else
-# define RCU_FANOUT_LEAF 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
-
-#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2	      (RCU_FANOUT_1 * RCU_FANOUT)
-#define RCU_FANOUT_3	      (RCU_FANOUT_2 * RCU_FANOUT)
-#define RCU_FANOUT_4	      (RCU_FANOUT_3 * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT_1
-#  define RCU_NUM_LVLS	      1
-#  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_NODES	      NUM_RCU_LVL_0
-#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
-#  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
-#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
-#elif NR_CPUS <= RCU_FANOUT_2
-#  define RCU_NUM_LVLS	      2
-#  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
-#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
-#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
-#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
-#elif NR_CPUS <= RCU_FANOUT_3
-#  define RCU_NUM_LVLS	      3
-#  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
-#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
-#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
-#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
-#elif NR_CPUS <= RCU_FANOUT_4
-#  define RCU_NUM_LVLS	      4
-#  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
-#  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-#  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
-#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
-#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
-#else
-# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
-
-extern int rcu_num_lvls;
-extern int rcu_num_nodes;
+#include "rcu_segcblist.h"
 
 /*
  * Dynticks per-CPU state.
@@ -113,6 +42,9 @@ struct rcu_dynticks {
 				    /* Process level is worth LLONG_MAX/2. */
 	int dynticks_nmi_nesting;   /* Track NMI nesting level. */
 	atomic_t dynticks;	    /* Even value for idle, else odd. */
+	bool rcu_need_heavy_qs;     /* GP old, need heavy quiescent state. */
+	unsigned long rcu_qs_ctr;   /* Light universal quiescent state ctr. */
+	bool rcu_urgent_qs;	    /* GP old need light quiescent state. */
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
 	long long dynticks_idle_nesting;
 				    /* irq/process nesting level from idle. */
@@ -261,41 +193,6 @@ struct rcu_node {
  */
 #define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo))
 
-/*
- * Do a full breadth-first scan of the rcu_node structures for the
- * specified rcu_state structure.
- */
-#define rcu_for_each_node_breadth_first(rsp, rnp) \
-	for ((rnp) = &(rsp)->node[0]; \
-	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Do a breadth-first scan of the non-leaf rcu_node structures for the
- * specified rcu_state structure.  Note that if there is a singleton
- * rcu_node tree with but one rcu_node structure, this loop is a no-op.
- */
-#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
-	for ((rnp) = &(rsp)->node[0]; \
-	     (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
-
-/*
- * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
- * structure.  Note that if there is a singleton rcu_node tree with but
- * one rcu_node structure, this loop -will- visit the rcu_node structure.
- * It is still a leaf node, even if it is also the root node.
- */
-#define rcu_for_each_leaf_node(rsp, rnp) \
-	for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
-	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Iterate over all possible CPUs in a leaf RCU node.
- */
-#define for_each_leaf_node_possible_cpu(rnp, cpu) \
-	for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
-	     cpu <= rnp->grphi; \
-	     cpu = cpumask_next((cpu), cpu_possible_mask))
-
 /*
  * Union to allow "aggregate OR" operation on the need for a quiescent
  * state by the normal and expedited grace periods.
@@ -336,34 +233,9 @@ struct rcu_data {
 					/* period it is aware of. */
 
 	/* 2) batch handling */
-	/*
-	 * If nxtlist is not NULL, it is partitioned as follows.
-	 * Any of the partitions might be empty, in which case the
-	 * pointer to that partition will be equal to the pointer for
-	 * the following partition.  When the list is empty, all of
-	 * the nxttail elements point to the ->nxtlist pointer itself,
-	 * which in that case is NULL.
-	 *
-	 * [nxtlist, *nxttail[RCU_DONE_TAIL]):
-	 *	Entries that batch # <= ->completed
-	 *	The grace period for these entries has completed, and
-	 *	the other grace-period-completed entries may be moved
-	 *	here temporarily in rcu_process_callbacks().
-	 * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
-	 *	Entries that batch # <= ->completed - 1: waiting for current GP
-	 * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
-	 *	Entries known to have arrived before current GP ended
-	 * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
-	 *	Entries that might have arrived after current GP ended
-	 *	Note that the value of *nxttail[RCU_NEXT_TAIL] will
-	 *	always be NULL, as this is the end of the list.
-	 */
-	struct rcu_head *nxtlist;
-	struct rcu_head **nxttail[RCU_NEXT_SIZE];
-	unsigned long	nxtcompleted[RCU_NEXT_SIZE];
-					/* grace periods for sublists. */
-	long		qlen_lazy;	/* # of lazy queued callbacks */
-	long		qlen;		/* # of queued callbacks, incl lazy */
+	struct rcu_segcblist cblist;	/* Segmented callback list, with */
+					/* different callbacks waiting for */
+					/* different grace periods. */
 	long		qlen_last_fqs_check;
 					/* qlen at last check for QS forcing */
 	unsigned long	n_cbs_invoked;	/* count of RCU cbs invoked. */
@@ -482,7 +354,6 @@ struct rcu_state {
 	struct rcu_node *level[RCU_NUM_LVLS + 1];
 						/* Hierarchy levels (+1 to */
 						/*  shut bogus gcc warning) */
-	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	call_rcu_func_t call;			/* call_rcu() flavor. */
 	int ncpus;				/* # CPUs seen so far. */
@@ -502,14 +373,11 @@ struct rcu_state {
 
 	raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
 						/* Protect following fields. */
-	struct rcu_head *orphan_nxtlist;	/* Orphaned callbacks that */
+	struct rcu_cblist orphan_pend;		/* Orphaned callbacks that */
 						/*  need a grace period. */
-	struct rcu_head **orphan_nxttail;	/* Tail of above. */
-	struct rcu_head *orphan_donelist;	/* Orphaned callbacks that */
+	struct rcu_cblist orphan_done;		/* Orphaned callbacks that */
 						/*  are ready to invoke. */
-	struct rcu_head **orphan_donetail;	/* Tail of above. */
-	long qlen_lazy;				/* Number of lazy callbacks. */
-	long qlen;				/* Total number of callbacks. */
+						/* (Contains counts.) */
 	/* End of fields guarded by orphan_lock. */
 
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
@@ -596,6 +464,7 @@ extern struct rcu_state rcu_preempt_state;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+bool rcu_eqs_special_set(int cpu);
 
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
@@ -673,6 +542,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
 
+#ifdef CONFIG_SRCU
+void srcu_online_cpu(unsigned int cpu);
+void srcu_offline_cpu(unsigned int cpu);
+#else /* #ifdef CONFIG_SRCU */
+void srcu_online_cpu(unsigned int cpu) { }
+void srcu_offline_cpu(unsigned int cpu) { }
+#endif /* #else #ifdef CONFIG_SRCU */
+
 #endif /* #ifndef RCU_TREE_NONCORE */
 
 #ifdef CONFIG_RCU_TRACE

kernel/rcu/tree_exp.h

@@ -292,7 +292,7 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 			trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
 						  rnp->grplo, rnp->grphi,
 						  TPS("wait"));
-			wait_event(rnp->exp_wq[(s >> 1) & 0x3],
+			wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
 				   sync_exp_work_done(rsp,
 						      &rdp->exp_workdone2, s));
 			return true;
@@ -331,6 +331,8 @@ static void sync_sched_exp_handler(void *data)
 		return;
 	}
 	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
+	/* Store .exp before .rcu_urgent_qs. */
+	smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
 	resched_cpu(smp_processor_id());
 }
 
@@ -531,7 +533,8 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
 				rnp->exp_seq_rq = s;
 			spin_unlock(&rnp->exp_lock);
 		}
-		wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
+		smp_mb(); /* All above changes before wakeup. */
+		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]);
 	}
 	trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
 	mutex_unlock(&rsp->exp_wake_mutex);
@@ -609,9 +612,9 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
 	/* Wait for expedited grace period to complete. */
 	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
 	rnp = rcu_get_root(rsp);
-	wait_event(rnp->exp_wq[(s >> 1) & 0x3],
-		   sync_exp_work_done(rsp,
-				      &rdp->exp_workdone0, s));
+	wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
+		   sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+	smp_mb(); /* Workqueue actions happen before return. */
 
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rsp->exp_mutex);
@@ -735,15 +738,3 @@ void synchronize_rcu_expedited(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
-/*
- * Switch to run-time mode once Tree RCU has fully initialized.
- */
-static int __init rcu_exp_runtime_mode(void)
-{
-	rcu_test_sync_prims();
-	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
-	rcu_test_sync_prims();
-	return 0;
-}
-core_initcall(rcu_exp_runtime_mode);

kernel/rcu/tree_trace.c

@@ -41,11 +41,11 @@
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/prefetch.h>
 
 #define RCU_TREE_NONCORE
 #include "tree.h"
-
-DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+#include "rcu.h"
 
 static int r_open(struct inode *inode, struct file *file,
 					const struct seq_operations *op)
@@ -121,7 +121,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
 		   rdp->cpu_no_qs.b.norm,
-		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+		   rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu),
 		   rdp->core_needs_qs);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   rcu_dynticks_snap(rdp->dynticks),
@@ -130,17 +130,15 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->dynticks_fqs);
 	seq_printf(m, " of=%lu", rdp->offline_fqs);
 	rcu_nocb_q_lengths(rdp, &ql, &qll);
-	qll += rdp->qlen_lazy;
-	ql += rdp->qlen;
+	qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist);
+	ql += rcu_segcblist_n_cbs(&rdp->cblist);
 	seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
 		   qll, ql,
-		   ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
-			rdp->nxttail[RCU_NEXT_TAIL]],
-		   ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
-			rdp->nxttail[RCU_NEXT_READY_TAIL]],
-		   ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
-			rdp->nxttail[RCU_WAIT_TAIL]],
-		   ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
+		   ".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)],
+		   ".R"[!rcu_segcblist_segempty(&rdp->cblist,
+						RCU_NEXT_READY_TAIL)],
+		   ".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)],
+		   ".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]);
 #ifdef CONFIG_RCU_BOOST
 	seq_printf(m, " kt=%d/%c ktl=%x",
 		   per_cpu(rcu_cpu_has_work, rdp->cpu),
@@ -278,7 +276,9 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 	seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+		   READ_ONCE(rsp->n_force_qs_lh),
+		   rsp->orphan_done.len_lazy,
+		   rsp->orphan_done.len);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");

kernel/sched/core.c

@@ -3382,7 +3382,7 @@ static void __sched notrace __schedule(bool preempt)
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch();
+	rcu_note_context_switch(preempt);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below

kernel/signal.c

@@ -1237,7 +1237,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 		}
 		/*
 		 * This sighand can be already freed and even reused, but
-		 * we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which
+		 * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which
 		 * initializes ->siglock: this slab can't go away, it has
 		 * the same object type, ->siglock can't be reinitialized.
 		 *