63 files changed, 1395 insertions, 1268 deletions
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
index e4233ac93c2b..6189ffcc6aff 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
@@ -328,13 +328,13 @@
     inkscape:window-height="1148"
     id="namedview90"
     showgrid="true"
-     inkscape:zoom="0.80021373"
+     inkscape:zoom="0.69092787"
-     inkscape:cx="462.49289"
+     inkscape:cx="476.34085"
-     inkscape:cy="473.6718"
+     inkscape:cy="712.80957"
     inkscape:window-x="770"
     inkscape:window-y="24"
     inkscape:window-maximized="0"
-     inkscape:current-layer="g4114-9-3-9"
+     inkscape:current-layer="g4"
     inkscape:snap-grids="false"
     fit-margin-top="5"
     fit-margin-right="5"
@@ -813,14 +813,18 @@
      <text
         sodipodi:linespacing="125%"
         id="text4110-5-7-6-2-4-0"
-         y="841.88086"
+         y="670.74316"
         x="1460.1007"
         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
         xml:space="preserve"><tspan
-           y="841.88086"
+           y="670.74316"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1-2-4-5">Request</tspan><tspan
+           y="1004.7976"
           x="1460.1007"
           sodipodi:role="line"
-           id="tspan4925-1-2-4-5">reched_cpu()</tspan></text>
+           id="tspan3100">context switch</tspan></text>
    </g>
  </g>
 </svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
index 8e4f873b979f..19e7a5fb6b73 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -72,10 +72,10 @@ will ignore it because idle and offline CPUs are already residing
 in quiescent states.
 Otherwise, the expedited grace period will use
 <tt>smp_call_function_single()</tt> to send the CPU an IPI, which
-is handled by <tt>sync_rcu_exp_handler()</tt>.
+is handled by <tt>rcu_exp_handler()</tt>.
 <p>
-However, because this is preemptible RCU, <tt>sync_rcu_exp_handler()</tt>
+However, because this is preemptible RCU, <tt>rcu_exp_handler()</tt>
 can check to see if the CPU is currently running in an RCU read-side
 critical section.
 If not, the handler can immediately report a quiescent state.
@@ -145,19 +145,18 @@ expedited grace period is shown in the following diagram:
 <p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%">
 <p>
-As with RCU-preempt's <tt>synchronize_rcu_expedited()</tt>,
+As with RCU-preempt, RCU-sched's
 <tt>synchronize_sched_expedited()</tt> ignores offline and
 idle CPUs, again because they are in remotely detectable
 quiescent states.
-However, the <tt>synchronize_rcu_expedited()</tt> handler
+However, because the
-is <tt>sync_sched_exp_handler()</tt>, and because the
 <tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
 leave no trace of their invocation, in general it is not possible to tell
 whether or not the current CPU is in an RCU read-side critical section.
-The best that <tt>sync_sched_exp_handler()</tt> can do is to check
+The best that RCU-sched's <tt>rcu_exp_handler()</tt> can do is to check
 for idle, on the off-chance that the CPU went idle while the IPI
 was in flight.
-If the CPU is idle, then <tt>sync_sched_exp_handler()</tt> reports
+If the CPU is idle, then <tt>rcu_exp_handler()</tt> reports
 the quiescent state.
 <p> Otherwise, the handler forces a future context switch by setting the
@@ -298,19 +297,18 @@ Instead, the task pushing the grace period forward will include the
 idle CPUs in the mask passed to <tt>rcu_report_exp_cpu_mult()</tt>.
 <p>
-For RCU-sched, there is an additional check for idle in the IPI
+For RCU-sched, there is an additional check:
-handler, <tt>sync_sched_exp_handler()</tt>.
 If the IPI has interrupted the idle loop, then
-<tt>sync_sched_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt>
+<tt>rcu_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt>
 to report the corresponding quiescent state.
 <p>
 For RCU-preempt, there is no specific check for idle in the
-IPI handler (<tt>sync_rcu_exp_handler()</tt>), but because
+IPI handler (<tt>rcu_exp_handler()</tt>), but because
 RCU read-side critical sections are not permitted within the
-idle loop, if <tt>sync_rcu_exp_handler()</tt> sees that the CPU is within
+idle loop, if <tt>rcu_exp_handler()</tt> sees that the CPU is within
 RCU read-side critical section, the CPU cannot possibly be idle.
-Otherwise, <tt>sync_rcu_exp_handler()</tt> invokes
+Otherwise, <tt>rcu_exp_handler()</tt> invokes
 <tt>rcu_report_exp_rdp()</tt> to report the corresponding quiescent
 state, regardless of whether or not that quiescent state was due to
 the CPU being idle.
@@ -625,6 +623,8 @@ 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.
+That is, aside from some points in the suspend, hibernate, or shutdown
+code path.
 <h3><a name="Summary">
 Summary</a></h3>
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index e4d94fba6c89..8d21af02b1f0 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -485,13 +485,13 @@ section that the grace period must wait on.
 noted by <tt>rcu_node_context_switch()</tt> on the left.
 On the other hand, if the CPU takes a scheduler-clock interrupt
 while executing in usermode, a quiescent state will be noted by
-<tt>rcu_check_callbacks()</tt> on the right.
+<tt>rcu_sched_clock_irq()</tt> on the right.
 Either way, the passage through a quiescent state will be noted
 in a per-CPU variable.
 <p>The next time an <tt>RCU_SOFTIRQ</tt> handler executes on
 this CPU (for example, after the next scheduler-clock
-interrupt), <tt>__rcu_process_callbacks()</tt> will invoke
+interrupt), <tt>rcu_core()</tt> will invoke
 <tt>rcu_check_quiescent_state()</tt>, which will notice the
 recorded quiescent state, and invoke
 <tt>rcu_report_qs_rdp()</tt>.
@@ -651,7 +651,7 @@ to end.
 These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
 which is usually invoked by <tt>__note_gp_changes()</tt>.
 As shown in the diagram below, this invocation can be triggered by
-the scheduling-clock interrupt (<tt>rcu_check_callbacks()</tt> on
+the scheduling-clock interrupt (<tt>rcu_sched_clock_irq()</tt> on
 the left) or by idle entry (<tt>rcu_cleanup_after_idle()</tt> on
 the right, but only for kernels build with
 <tt>CONFIG_RCU_FAST_NO_HZ=y</tt>).
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg
index 832408313d93..3fcf0c17cef2 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-invocation.svg
@@ -349,7 +349,7 @@
       font-weight="bold"
       font-size="192"
       id="text202-7-5"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_check_callbacks()</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_sched_clock_irq()</text>
    <rect
       x="7069.6187"
       y="5087.4678"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index acd73c7ad0f4..2bcd742d6e49 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -3902,7 +3902,7 @@
         font-style="normal"
         y="-4418.6582"
         x="3745.7725"
-         xml:space="preserve">rcu_check_callbacks()</text>
+         xml:space="preserve">rcu_sched_clock_irq()</text>
    </g>
    <g
       transform="translate(-850.30204,55463.106)"
@@ -3924,7 +3924,7 @@
         font-style="normal"
         y="-4418.6582"
         x="3745.7725"
-         xml:space="preserve">rcu_process_callbacks()</text>
+         xml:space="preserve">rcu_core()</text>
      <text
         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"
         id="text202-7-5-3-27-0"
@@ -3933,7 +3933,7 @@
         font-style="normal"
         y="-4165.7954"
         x="3745.7725"
-         xml:space="preserve">rcu_check_quiescent_state())</text>
+         xml:space="preserve">rcu_check_quiescent_state()</text>
      <text
         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"
         id="text202-7-5-3-27-0-9"
@@ -4968,7 +4968,7 @@
       font-weight="bold"
       font-size="192"
       id="text202-7-5-19"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_check_callbacks()</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_sched_clock_irq()</text>
    <rect
       x="5314.2671"
       y="82817.688"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
index 149bec2a4493..779c9ac31a52 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
@@ -775,7 +775,7 @@
         font-style="normal"
         y="-4418.6582"
         x="3745.7725"
-         xml:space="preserve">rcu_check_callbacks()</text>
+         xml:space="preserve">rcu_sched_clock_irq()</text>
    </g>
    <g
       transform="translate(399.7744,828.86448)"
@@ -797,7 +797,7 @@
         font-style="normal"
         y="-4418.6582"
         x="3745.7725"
-         xml:space="preserve">rcu_process_callbacks()</text>
+         xml:space="preserve">rcu_core()</text>
      <text
         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"
         id="text202-7-5-3-27-0"
@@ -806,7 +806,7 @@
         font-style="normal"
         y="-4165.7954"
         x="3745.7725"
-         xml:space="preserve">rcu_check_quiescent_state())</text>
+         xml:space="preserve">rcu_check_quiescent_state()</text>
      <text
         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"
         id="text202-7-5-3-27-0-9"
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 9fca73e03a98..5a9238a2883c 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -3099,7 +3099,7 @@ If you block forever in one of a given domain's SRCU read-side critical
 sections, then that domain's grace periods will also be blocked forever.
 Of course, one good way to block forever is to deadlock, which can
 happen if any operation in a given domain's SRCU read-side critical
-section can block waiting, either directly or indirectly, for that domain's
+section can wait, either directly or indirectly, for that domain's
 grace period to elapse.
 For example, this results in a self-deadlock:
@@ -3139,12 +3139,18 @@ API, which, in combination with <tt>srcu_read_unlock()</tt>,
 guarantees a full memory barrier.
 <p>
-Also unlike other RCU flavors, SRCU's callbacks-wait function
+Also unlike other RCU flavors, <tt>synchronize_srcu()</tt> may <b>not</b>
-<tt>srcu_barrier()</tt> may be invoked from CPU-hotplug notifiers,
+be invoked from CPU-hotplug notifiers, due to the fact that SRCU grace
-though this is not necessarily a good idea.
+periods make use of timers and the possibility of timers being temporarily
-The reason that this is possible is that SRCU is insensitive
+&ldquo;stranded&rdquo; on the outgoing CPU.
-to whether or not a CPU is online, which means that <tt>srcu_barrier()</tt>
+This stranding of timers means that timers posted to the outgoing CPU
-need not exclude CPU-hotplug operations.
+will not fire until late in the CPU-hotplug process.
+The problem is that if a notifier is waiting on an SRCU grace period,
+that grace period is waiting on a timer, and that timer is stranded on the
+outgoing CPU, then the notifier will never be awakened, in other words,
+deadlock has occurred.
+This same situation of course also prohibits <tt>srcu_barrier()</tt>
+from being invoked from CPU-hotplug notifiers.
 <p>
 SRCU also differs from other RCU flavors in that SRCU's expedited and
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 073dbc12d1ea..1ab70c37921f 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -219,17 +219,18 @@ an estimate of the total number of RCU callbacks queued across all CPUs
 In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
 for each CPU:
-        0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D
+        0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 Nonlazy posted: ..D
 The "last_accelerate:" prints the low-order 16 bits (in hex) of the
 jiffies counter when this CPU last invoked rcu_try_advance_all_cbs()
 from rcu_needs_cpu() or last invoked rcu_accelerate_cbs() from
-rcu_prepare_for_idle().  The "nonlazy_posted:" prints the number
+rcu_prepare_for_idle().  The "Nonlazy posted:" indicates lazy-callback
-of non-lazy callbacks posted since the last call to rcu_needs_cpu().
+status, so that an "l" indicates that all callbacks were lazy at the start
-Finally, an "L" indicates that there are currently no non-lazy callbacks
+of the last idle period and an "L" indicates that there are currently
-("." is printed otherwise, as shown above) and "D" indicates that
+no non-lazy callbacks (in both cases, "." is printed otherwise, as
-dyntick-idle processing is enabled ("." is printed otherwise, for example,
+shown above) and "D" indicates that dyntick-idle processing is enabled
-if disabled via the "nohz=" kernel boot parameter).
+("." is printed otherwise, for example, if disabled via the "nohz="
+kernel boot parameter).
 If the grace period ends just as the stall warning starts printing,
 there will be a spurious stall-warning message, which will include
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 55918b54808b..a41a0384d20c 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -10,173 +10,8 @@ status messages via printk(), which can be examined via the dmesg
 command (perhaps grepping for "torture").  The test is started
 when the module is loaded, and stops when the module is unloaded.
+Module parameters are prefixed by "rcutorture." in
-MODULE PARAMETERS
+Documentation/admin-guide/kernel-parameters.txt.
-This module has the following parameters:
-fqs_duration    Duration (in microseconds) of artificially induced bursts
-                of force_quiescent_state() invocations.  In RCU
-                implementations having force_quiescent_state(), these
-                bursts help force races between forcing a given grace
-                period and that grace period ending on its own.
-fqs_holdoff     Holdoff time (in microseconds) between consecutive calls
-                to force_quiescent_state() within a burst.
-fqs_stutter     Wait time (in seconds) between consecutive bursts
-                of calls to force_quiescent_state().
-gp_normal       Make the fake writers use normal synchronous grace-period
-                primitives.
-gp_exp          Make the fake writers use expedited synchronous grace-period
-                primitives.  If both gp_normal and gp_exp are set, or
-                if neither gp_normal nor gp_exp are set, then randomly
-                choose the primitive so that about 50% are normal and
-                50% expedited.  By default, neither are set, which
-                gives best overall test coverage.
-irqreader       Says to invoke RCU readers from irq level.  This is currently
-                done via timers.  Defaults to "1" for variants of RCU that
-                permit this.  (Or, more accurately, variants of RCU that do
-                -not- permit this know to ignore this variable.)
-n_barrier_cbs   If this is nonzero, RCU barrier testing will be conducted,
-                in which case n_barrier_cbs specifies the number of
-                RCU callbacks (and corresponding kthreads) to use for
-                this testing.  The value cannot be negative.  If you
-                specify this to be non-zero when torture_type indicates a
-                synchronous RCU implementation (one for which a member of
-                the synchronize_rcu() rather than the call_rcu() family is
-                used -- see the documentation for torture_type below), an
-                error will be reported and no testing will be carried out.
-nfakewriters    This is the number of RCU fake writer threads to run.  Fake
-                writer threads repeatedly use the synchronous "wait for
-                current readers" function of the interface selected by
-                torture_type, with a delay between calls to allow for various
-                different numbers of writers running in parallel.
-                nfakewriters defaults to 4, which provides enough parallelism
-                to trigger special cases caused by multiple writers, such as
-                the synchronize_srcu() early return optimization.
-nreaders        This is the number of RCU reading threads supported.
-                The default is twice the number of CPUs.  Why twice?
-                To properly exercise RCU implementations with preemptible
-                read-side critical sections.
-onoff_interval
-                The number of seconds between each attempt to execute a
-                randomly selected CPU-hotplug operation.  Defaults to
-                zero, which disables CPU hotplugging.  In HOTPLUG_CPU=n
-                kernels, rcutorture will silently refuse to do any
-                CPU-hotplug operations regardless of what value is
-                specified for onoff_interval.
-onoff_holdoff   The number of seconds to wait until starting CPU-hotplug
-                operations.  This would normally only be used when
-                rcutorture was built into the kernel and started
-                automatically at boot time, in which case it is useful
-                in order to avoid confusing boot-time code with CPUs
-                coming and going.
-shuffle_interval
-                The number of seconds to keep the test threads affinitied
-                to a particular subset of the CPUs, defaults to 3 seconds.
-                Used in conjunction with test_no_idle_hz.
-shutdown_secs   The number of seconds to run the test before terminating
-                the test and powering off the system.  The default is
-                zero, which disables test termination and system shutdown.
-                This capability is useful for automated testing.
-stall_cpu       The number of seconds that a CPU should be stalled while
-                within both an rcu_read_lock() and a preempt_disable().
-                This stall happens only once per rcutorture run.
-                If you need multiple stalls, use modprobe and rmmod to
-                repeatedly run rcutorture.  The default for stall_cpu
-                is zero, which prevents rcutorture from stalling a CPU.
-                Note that attempts to rmmod rcutorture while the stall
-                is ongoing will hang, so be careful what value you
-                choose for this module parameter!  In addition, too-large
-                values for stall_cpu might well induce failures and
-                warnings in other parts of the kernel.  You have been
-                warned!
-stall_cpu_holdoff
-                The number of seconds to wait after rcutorture starts
-                before stalling a CPU.  Defaults to 10 seconds.
-stat_interval   The number of seconds between output of torture
-                statistics (via printk()).  Regardless of the interval,
-                statistics are printed when the module is unloaded.
-                Setting the interval to zero causes the statistics to
-                be printed -only- when the module is unloaded, and this
-                is the default.
-stutter         The length of time to run the test before pausing for this
-                same period of time.  Defaults to "stutter=5", so as
-                to run and pause for (roughly) five-second intervals.
-                Specifying "stutter=0" causes the test to run continuously
-                without pausing, which is the old default behavior.
-test_boost      Whether or not to test the ability of RCU to do priority
-                boosting.  Defaults to "test_boost=1", which performs
-                RCU priority-inversion testing only if the selected
-                RCU implementation supports priority boosting.  Specifying
-                "test_boost=0" never performs RCU priority-inversion
-                testing.  Specifying "test_boost=2" performs RCU
-                priority-inversion testing even if the selected RCU
-                implementation does not support RCU priority boosting,
-                which can be used to test rcutorture's ability to
-                carry out RCU priority-inversion testing.
-test_boost_interval
-                The number of seconds in an RCU priority-inversion test
-                cycle.  Defaults to "test_boost_interval=7".  It is
-                usually wise for this value to be relatively prime to
-                the value selected for "stutter".
-test_boost_duration
-                The number of seconds to do RCU priority-inversion testing
-                within any given "test_boost_interval".  Defaults to
-                "test_boost_duration=4".
-test_no_idle_hz Whether or not to test the ability of RCU to operate in
-                a kernel that disables the scheduling-clock interrupt to
-                idle CPUs.  Boolean parameter, "1" to test, "0" otherwise.
-                Defaults to omitting this test.
-torture_type    The type of RCU to test, with string values as follows:
-                "rcu":  rcu_read_lock(), rcu_read_unlock() and call_rcu(),
-                        along with expedited, synchronous, and polling
-                        variants.
-                "rcu_bh": rcu_read_lock_bh(), rcu_read_unlock_bh(), and
-                        call_rcu_bh(), along with expedited and synchronous
-                        variants.
-                "rcu_busted": This tests an intentionally incorrect version
-                        of RCU in order to help test rcutorture itself.
-                "srcu": srcu_read_lock(), srcu_read_unlock() and
-                        call_srcu(), along with expedited and
-                        synchronous variants.
-                "sched": preempt_disable(), preempt_enable(), and
-                        call_rcu_sched(), along with expedited,
-                        synchronous, and polling variants.
-                "tasks": voluntary context switch and call_rcu_tasks(),
-                        along with expedited and synchronous variants.
-                Defaults to "rcu".
-verbose         Enable debug printk()s.  Default is disabled.
 OUTPUT
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 4a6854318b17..1ace20815bb1 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -302,7 +302,7 @@ rcu_dereference()
        must prohibit.  The rcu_dereference_protected() variant takes
        a lockdep expression to indicate which locks must be acquired
        by the caller. If the indicated protection is not provided,
-        a lockdep splat is emitted.  See RCU/Design/Requirements.html
+        a lockdep splat is emitted.  See RCU/Design/Requirements/Requirements.html
        and the API's code comments for more details and example usage.
 The following diagram shows how each API communicates among the
@@ -560,7 +560,7 @@ presents two such "toy" implementations of RCU, one that is implemented
 in terms of familiar locking primitives, and another that more closely
 resembles "classic" RCU.  Both are way too simple for real-world use,
 lacking both functionality and performance.  However, they are useful
-in getting a feel for how RCU works.  See kernel/rcupdate.c for a
+in getting a feel for how RCU works.  See kernel/rcu/update.c for a
 production-quality implementation, and see:
        http://www.rdrop.com/users/paulmck/RCU
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 858b6c0b9a15..28481510ad4e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3653,19 +3653,6 @@
                        latencies, which will choose a value aligned
                        with the appropriate hardware boundaries.
-        rcutree.jiffies_till_sched_qs= [KNL]
-                        Set required age in jiffies for a
-                        given grace period before RCU starts
-                        soliciting quiescent-state help from
-                        rcu_note_context_switch().  If not specified, the
-                        kernel will calculate a value based on the most
-                        recent settings of rcutree.jiffies_till_first_fqs
-                        and rcutree.jiffies_till_next_fqs.
-                        This calculated value may be viewed in
-                        rcutree.jiffies_to_sched_qs.  Any attempt to
-                        set rcutree.jiffies_to_sched_qs will be
-                        cheerfully overwritten.
        rcutree.jiffies_till_first_fqs= [KNL]
                        Set delay from grace-period initialization to
                        first attempt to force quiescent states.
@@ -3677,6 +3664,20 @@
                        quiescent states.  Units are jiffies, minimum
                        value is one, and maximum value is HZ.
+        rcutree.jiffies_till_sched_qs= [KNL]
+                        Set required age in jiffies for a
+                        given grace period before RCU starts
+                        soliciting quiescent-state help from
+                        rcu_note_context_switch() and cond_resched().
+                        If not specified, the kernel will calculate
+                        a value based on the most recent settings
+                        of rcutree.jiffies_till_first_fqs
+                        and rcutree.jiffies_till_next_fqs.
+                        This calculated value may be viewed in
+                        rcutree.jiffies_to_sched_qs.  Any attempt to set
+                        rcutree.jiffies_to_sched_qs will be cheerfully
+                        overwritten.
        rcutree.kthread_prio=    [KNL,BOOT]
                        Set the SCHED_FIFO priority of the RCU per-CPU
                        kthreads (rcuc/N). This value is also used for
@@ -3720,6 +3721,11 @@
                        This wake_up() will be accompanied by a
                        WARN_ONCE() splat and an ftrace_dump().
+        rcutree.sysrq_rcu= [KNL]
+                        Commandeer a sysrq key to dump out Tree RCU's
+                        rcu_node tree with an eye towards determining
+                        why a new grace period has not yet started.
        rcuperf.gp_async= [KNL]
                        Measure performance of asynchronous
                        grace-period primitives such as call_rcu().
diff --git a/MAINTAINERS b/MAINTAINERS
index 9919840d54cd..65217477b036 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10797,6 +10797,12 @@ F:	drivers/power/supply/bq27xxx_battery_i2c.c
 F:      drivers/power/supply/isp1704_charger.c
 F:      drivers/power/supply/rx51_battery.c
+NOLIBC HEADER FILE
+M:      Willy Tarreau <w@1wt.eu>
+S:      Maintained
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/nolibc.git
+F:      tools/include/nolibc/
 NTB AMD DRIVER
 M:      Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
 L:      linux-ntb@googlegroups.com
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 20561a60db9c..0e9bd9c83870 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -211,9 +211,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 /*
 * WARN_ON_SMP() is for cases that the warning is either
 * meaningless for !SMP or may even cause failures.
- * This is usually used for cases that we have
- * WARN_ON(!spin_is_locked(&lock)) checks, as spin_is_locked()
- * returns 0 for uniprocessor settings.
 * It can also be used with values that are only defined
 * on SMP:
 *
diff --git a/include/linux/rcu_node_tree.h b/include/linux/rcu_node_tree.h
index 426cee67f0e2..b8e094b125ee 100644
--- a/include/linux/rcu_node_tree.h
+++ b/include/linux/rcu_node_tree.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * RCU node combining tree definitions.  These are used to compute
 * global attributes while avoiding common-case global contention.  A key
@@ -11,23 +12,9 @@
 * because the size of the TREE SRCU srcu_struct structure depends
 * on these definitions.
 *
- * 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>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #ifndef __LINUX_RCU_NODE_TREE_H
diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h
index c3ad00e63556..87404cb015f1 100644
--- a/include/linux/rcu_segcblist.h
+++ b/include/linux/rcu_segcblist.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * RCU segmented callback lists
 *
@@ -5,23 +6,9 @@
 * because the size of the TREE SRCU srcu_struct structure depends
 * on these definitions.
 *
- * 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>
+ * Authors: Paul E. McKenney <paulmck@linux.net.ibm.com>
 */
 #ifndef __INCLUDE_LINUX_RCU_SEGCBLIST_H
diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h
index ece7ed9a4a70..6fc53a1345b3 100644
--- a/include/linux/rcu_sync.h
+++ b/include/linux/rcu_sync.h
@@ -1,20 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * RCU-based infrastructure for lightweight reader-writer locking
 *
- * 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) 2015, Red Hat, Inc.
 *
 * Author: Oleg Nesterov <oleg@redhat.com>
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 4db8bcacc51a..6cdb1db776cf 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1,25 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update mechanism for mutual exclusion
 *
- * 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, 2001
 *
 * Author: Dipankar Sarma <dipankar@in.ibm.com>
 *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 * Papers:
 * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
@@ -89,7 +76,7 @@ static inline int rcu_preempt_depth(void)
 /* Internal to kernel */
 void rcu_init(void);
 extern int rcu_scheduler_active __read_mostly;
-void rcu_check_callbacks(int user);
+void rcu_sched_clock_irq(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
@@ -309,16 +296,16 @@ static inline void rcu_preempt_sleep_check(void) { }
 */
 #ifdef __CHECKER__
-#define rcu_dereference_sparse(p, space) \
+#define rcu_check_sparse(p, space) \
        ((void)(((typeof(*p) space *)p) == p))
 #else /* #ifdef __CHECKER__ */
-#define rcu_dereference_sparse(p, space)
+#define rcu_check_sparse(p, space)
 #endif /* #else #ifdef __CHECKER__ */
 #define __rcu_access_pointer(p, space) \
 ({ \
        typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
-        rcu_dereference_sparse(p, space); \
+        rcu_check_sparse(p, space); \
        ((typeof(*p) __force __kernel *)(_________p1)); \
 })
 #define __rcu_dereference_check(p, c, space) \
@@ -326,13 +313,13 @@ static inline void rcu_preempt_sleep_check(void) { }
        /* Dependency order vs. p above. */ \
        typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
        RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
-        rcu_dereference_sparse(p, space); \
+        rcu_check_sparse(p, space); \
        ((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
        RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \
-        rcu_dereference_sparse(p, space); \
+        rcu_check_sparse(p, space); \
        ((typeof(*p) __force __kernel *)(p)); \
 })
 #define rcu_dereference_raw(p) \
@@ -382,6 +369,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_assign_pointer(p, v)                                              \
 ({                                                                            \
        uintptr_t _r_a_p__v = (uintptr_t)(v);                                 \
+        rcu_check_sparse(p, __rcu);                                   \
                                                                              \
        if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)        \
                WRITE_ONCE((p), (typeof(p))(_r_a_p__v));                      \
@@ -785,7 +773,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 */
 #define RCU_INIT_POINTER(p, v) \
        do { \
-                rcu_dereference_sparse(p, __rcu); \
+                rcu_check_sparse(p, __rcu); \
                WRITE_ONCE(p, RCU_INITIALIZER(v)); \
        } while (0)
@@ -859,7 +847,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 /* Has the specified rcu_head structure been handed to call_rcu()? */
-/*
+/**
 * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu()
 * @rhp: The rcu_head structure to initialize.
 *
@@ -874,10 +862,10 @@ static inline void rcu_head_init(struct rcu_head *rhp)
        rhp->func = (rcu_callback_t)~0L;
 }
-/*
+/**
 * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()?
 * @rhp: The rcu_head structure to test.
- * @func: The function passed to call_rcu() along with @rhp.
+ * @f: The function passed to call_rcu() along with @rhp.
 *
 * Returns @true if the @rhp has been passed to call_rcu() with @func,
 * and @false otherwise.  Emits a warning in any other case, including
@@ -896,57 +884,4 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
        return false;
 }
-/* Transitional pre-consolidation compatibility definitions. */
-static inline void synchronize_rcu_bh(void)
-{
-        synchronize_rcu();
-}
-static inline void synchronize_rcu_bh_expedited(void)
-{
-        synchronize_rcu_expedited();
-}
-static inline void call_rcu_bh(struct rcu_head *head, rcu_callback_t func)
-{
-        call_rcu(head, func);
-}
-static inline void rcu_barrier_bh(void)
-{
-        rcu_barrier();
-}
-static inline void synchronize_sched(void)
-{
-        synchronize_rcu();
-}
-static inline void synchronize_sched_expedited(void)
-{
-        synchronize_rcu_expedited();
-}
-static inline void call_rcu_sched(struct rcu_head *head, rcu_callback_t func)
-{
-        call_rcu(head, func);
-}
-static inline void rcu_barrier_sched(void)
-{
-        rcu_barrier();
-}
-static inline unsigned long get_state_synchronize_sched(void)
-{
-        return get_state_synchronize_rcu();
-}
-static inline void cond_synchronize_sched(unsigned long oldstate)
-{
-        cond_synchronize_rcu(oldstate);
-}
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index af65d1f36ddb..8e727f57d814 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
 *
- * 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, 2008
 *
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *              Documentation/RCU
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 7f83179177d1..735601ac27d3 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -1,26 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 *
- * 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, 2008
 *
 * Author: Dipankar Sarma <dipankar@in.ibm.com>
- *         Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical algorithm
+ *         Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical algorithm
 *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 *
 * For detailed explanation of Read-Copy Update mechanism see -
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c614375cd264..c495b2d51569 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -1,24 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Sleepable Read-Copy Update mechanism for mutual exclusion
 *
- * 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, 2006
 * Copyright (C) Fujitsu, 2012
 *
- * Author: Paul McKenney <paulmck@us.ibm.com>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
 *         Lai Jiangshan <laijs@cn.fujitsu.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
@@ -223,6 +210,7 @@ srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp)
 static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx)
        __releases(ssp)
 {
+        WARN_ON_ONCE(idx & ~0x1);
        rcu_lock_release(&(ssp)->dep_map);
        __srcu_read_unlock(ssp, idx);
 }
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index b19216aaaef2..5a5a1941ca15 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -1,24 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * 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>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
 */
 #ifndef _LINUX_SRCU_TINY_H
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 6f292bd3e7db..7f7c8c050f63 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -1,24 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * 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>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
 */
 #ifndef _LINUX_SRCU_TREE_H
@@ -45,7 +32,8 @@ struct srcu_data {
        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 timer_list delay_work;           /* Delay for CB invoking */
+        struct work_struct 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 */
diff --git a/include/linux/torture.h b/include/linux/torture.h
index 48fad21109fc..23d80db426d7 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Common functions for in-kernel torture tests.
 *
- * 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, 2014
 *
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #ifndef __LINUX_TORTURE_H
@@ -50,11 +37,12 @@
        do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0)
 /* Definitions for online/offline exerciser. */
+typedef void torture_ofl_func(void);
 bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes,
                     unsigned long *sum_offl, int *min_onl, int *max_onl);
 bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
                    unsigned long *sum_onl, int *min_onl, int *max_onl);
-int torture_onoff_init(long ooholdoff, long oointerval);
+int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f);
 void torture_onoff_stats(void);
 bool torture_onoff_failures(void);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 7d0b0ed74404..ad40a2617063 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Module-based torture test facility for locking
 *
- * 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, 2014
 *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 *          Davidlohr Bueso <dave@stgolabs.net>
 *      Based on kernel/rcu/torture.c.
 */
@@ -45,7 +32,7 @@
 #include <linux/torture.h>
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 torture_param(int, nwriters_stress, -1,
             "Number of write-locking stress-test threads");
@@ -970,7 +957,7 @@ static int __init lock_torture_init(void)
        /* Prepare torture context. */
        if (onoff_interval > 0) {
                firsterr = torture_onoff_init(onoff_holdoff * HZ,
-                                              onoff_interval * HZ);
+                                              onoff_interval * HZ, NULL);
                if (firsterr)
                        goto unwind;
        }
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index a393e24a9195..acee72c0b24b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update definitions shared among RCU implementations.
 *
- * 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, 2011
 *
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #ifndef __LINUX_RCU_H
@@ -30,7 +17,7 @@
 #define RCU_TRACE(stmt)
 #endif /* #else #ifdef CONFIG_RCU_TRACE */
-/* Offset to allow for unmatched rcu_irq_{enter,exit}(). */
+/* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
 #define DYNTICK_IRQ_NONIDLE     ((LONG_MAX / 2) + 1)
@@ -462,8 +449,6 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
 enum rcutorture_type {
        RCU_FLAVOR,
-        RCU_BH_FLAVOR,
-        RCU_SCHED_FLAVOR,
        RCU_TASKS_FLAVOR,
        SRCU_FLAVOR,
        INVALID_RCU_FLAVOR
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 5aff271adf1e..9bd5f6023c21 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * RCU segmented callback lists, function definitions
 *
- * 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>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/types.h>
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 948470cef385..71b64648464e 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * 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>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/rcu_segcblist.h>
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index b459da70b4fc..c29761152874 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Read-Copy Update module-based performance-test facility
 *
- * 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, 2015
 *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #define pr_fmt(fmt) fmt
@@ -54,7 +41,7 @@
 #include "rcu.h"
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 #define PERF_FLAG "-perf:"
 #define PERFOUT_STRING(s) \
@@ -83,13 +70,19 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.vnet.ibm.com>");
 * Various other use cases may of course be specified.
 */
+#ifdef MODULE
+# define RCUPERF_SHUTDOWN 0
+#else
+# define RCUPERF_SHUTDOWN 1
+#endif
 torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
 torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
 torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
 torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
 torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
-torture_param(bool, shutdown, !IS_ENABLED(MODULE),
+torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
              "Shutdown at end of performance tests.");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f6e85faa4ff4..f14d1b18a74f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Read-Copy Update module-based torture test facility
 *
- * 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, 2005, 2006
 *
- * Authors: Paul E. McKenney <paulmck@us.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 *        Josh Triplett <josh@joshtriplett.org>
 *
 * See also:  Documentation/RCU/torture.txt
@@ -61,7 +48,7 @@
 #include "rcu.h"
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 /* Bits for ->extendables field, extendables param, and related definitions. */
@@ -1630,21 +1617,34 @@ static bool rcu_fwd_emergency_stop;
 #define MIN_FWD_CB_LAUNDERS     3       /* This many CB invocations to count. */
 #define MIN_FWD_CBS_LAUNDERED   100     /* Number of counted CBs. */
 #define FWD_CBS_HIST_DIV        10      /* Histogram buckets/second. */
-static long n_launders_hist[2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)];
+struct rcu_launder_hist {
+        long n_launders;
+        unsigned long launder_gp_seq;
+};
+#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
+static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
+static unsigned long rcu_launder_gp_seq_start;
 static void rcu_torture_fwd_cb_hist(void)
 {
+        unsigned long gps;
+        unsigned long gps_old;
        int i;
        int j;
        for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
-                if (n_launders_hist[i] > 0)
+                if (n_launders_hist[i].n_launders > 0)
                        break;
        pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
                 __func__, jiffies - rcu_fwd_startat);
-        for (j = 0; j <= i; j++)
+        gps_old = rcu_launder_gp_seq_start;
-                pr_cont(" %ds/%d: %ld",
+        for (j = 0; j <= i; j++) {
-                        j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j]);
+                gps = n_launders_hist[j].launder_gp_seq;
+                pr_cont(" %ds/%d: %ld:%ld",
+                        j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
+                        rcutorture_seq_diff(gps, gps_old));
+                gps_old = gps;
+        }
        pr_cont("\n");
 }
@@ -1666,7 +1666,8 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
        i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
        if (i >= ARRAY_SIZE(n_launders_hist))
                i = ARRAY_SIZE(n_launders_hist) - 1;
-        n_launders_hist[i]++;
+        n_launders_hist[i].n_launders++;
+        n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
        spin_unlock_irqrestore(&rcu_fwd_lock, flags);
 }
@@ -1786,9 +1787,10 @@ static void rcu_torture_fwd_prog_cr(void)
        n_max_cbs = 0;
        n_max_gps = 0;
        for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
-                n_launders_hist[i] = 0;
+                n_launders_hist[i].n_launders = 0;
        cver = READ_ONCE(rcu_torture_current_version);
        gps = cur_ops->get_gp_seq();
+        rcu_launder_gp_seq_start = gps;
        while (time_before(jiffies, stopat) &&
               !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
                rfcp = READ_ONCE(rcu_fwd_cb_head);
@@ -2228,6 +2230,14 @@ static void rcu_test_debug_objects(void)
 #endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 }
+static void rcutorture_sync(void)
+{
+        static unsigned long n;
+        if (cur_ops->sync && !(++n & 0xfff))
+                cur_ops->sync();
+}
 static int __init
 rcu_torture_init(void)
 {
@@ -2389,7 +2399,8 @@ rcu_torture_init(void)
        firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
        if (firsterr)
                goto unwind;
-        firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
+        firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval,
+                                      rcutorture_sync);
        if (firsterr)
                goto unwind;
        firsterr = rcu_torture_stall_init();
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 32dfd6522548..5d4a39a6505a 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -1,24 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * 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>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/export.h>
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 3600d88d8956..a60b8ba9e1ac 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1,24 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Sleepable Read-Copy Update mechanism for mutual exclusion.
 *
- * 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, 2006
 * Copyright (C) Fujitsu, 2012
 *
- * Author: Paul McKenney <paulmck@us.ibm.com>
+ * Author: Paul McKenney <paulmck@linux.ibm.com>
 *         Lai Jiangshan <laijs@cn.fujitsu.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
@@ -58,6 +45,7 @@ static bool __read_mostly srcu_init_done;
 static void srcu_invoke_callbacks(struct work_struct *work);
 static void srcu_reschedule(struct srcu_struct *ssp, unsigned long delay);
 static void process_srcu(struct work_struct *work);
+static void srcu_delay_timer(struct timer_list *t);
 /* Wrappers for lock acquisition and release, see raw_spin_lock_rcu_node(). */
 #define spin_lock_rcu_node(p)                                   \
@@ -156,7 +144,8 @@ static void init_srcu_struct_nodes(struct srcu_struct *ssp, bool is_static)
                        snp->grphi = cpu;
                }
                sdp->cpu = cpu;
-                INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
+                INIT_WORK(&sdp->work, srcu_invoke_callbacks);
+                timer_setup(&sdp->delay_work, srcu_delay_timer, 0);
                sdp->ssp = ssp;
                sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
                if (is_static)
@@ -386,13 +375,19 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
        } else {
                flush_delayed_work(&ssp->work);
        }
-        for_each_possible_cpu(cpu)
+        for_each_possible_cpu(cpu) {
+                struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
                if (quiesced) {
-                        if (WARN_ON(delayed_work_pending(&per_cpu_ptr(ssp->sda, cpu)->work)))
+                        if (WARN_ON(timer_pending(&sdp->delay_work)))
+                                return; /* Just leak it! */
+                        if (WARN_ON(work_pending(&sdp->work)))
                                return; /* Just leak it! */
                } else {
-                        flush_delayed_work(&per_cpu_ptr(ssp->sda, cpu)->work);
+                        del_timer_sync(&sdp->delay_work);
+                        flush_work(&sdp->work);
                }
+        }
        if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
            WARN_ON(srcu_readers_active(ssp))) {
                pr_info("%s: Active srcu_struct %p state: %d\n",
@@ -463,39 +458,23 @@ static void srcu_gp_start(struct srcu_struct *ssp)
        WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
 }
-/*
- * Track online CPUs to guide callback workqueue placement.
- */
-DEFINE_PER_CPU(bool, srcu_online);
-void srcu_online_cpu(unsigned int cpu)
+static void srcu_delay_timer(struct timer_list *t)
 {
-        WRITE_ONCE(per_cpu(srcu_online, cpu), true);
+        struct srcu_data *sdp = container_of(t, struct srcu_data, delay_work);
-}
-void srcu_offline_cpu(unsigned int cpu)
+        queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
-{
-        WRITE_ONCE(per_cpu(srcu_online, cpu), false);
 }
-/*
+static void srcu_queue_delayed_work_on(struct srcu_data *sdp,
- * Place the workqueue handler on the specified CPU if online, otherwise
- * just run it whereever.  This is useful for placing workqueue handlers
- * that are to invoke the specified CPU's callbacks.
- */
-static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
-                                       struct delayed_work *dwork,
                                       unsigned long delay)
 {
-        bool ret;
+        if (!delay) {
+                queue_work_on(sdp->cpu, rcu_gp_wq, &sdp->work);
+                return;
+        }
-        preempt_disable();
+        timer_reduce(&sdp->delay_work, jiffies + delay);
-        if (READ_ONCE(per_cpu(srcu_online, cpu)))
-                ret = queue_delayed_work_on(cpu, wq, dwork, delay);
-        else
-                ret = queue_delayed_work(wq, dwork, delay);
-        preempt_enable();
-        return ret;
 }
 /*
@@ -504,7 +483,7 @@ static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 */
 static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
 {
-        srcu_queue_delayed_work_on(sdp->cpu, rcu_gp_wq, &sdp->work, delay);
+        srcu_queue_delayed_work_on(sdp, delay);
 }
 /*
@@ -1186,7 +1165,8 @@ static void srcu_invoke_callbacks(struct work_struct *work)
        struct srcu_data *sdp;
        struct srcu_struct *ssp;
-        sdp = container_of(work, struct srcu_data, work.work);
+        sdp = container_of(work, struct srcu_data, work);
        ssp = sdp->ssp;
        rcu_cblist_init(&ready_cbs);
        spin_lock_irq_rcu_node(sdp);
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index be10036fa621..a8304d90573f 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * RCU-based infrastructure for lightweight reader-writer locking
 *
- * 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) 2015, Red Hat, Inc.
 *
 * Author: Oleg Nesterov <oleg@redhat.com>
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 5f5963ba313e..911bd9076d43 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
 *
- * 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, 2008
 *
- * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 *
 * For detailed explanation of Read-Copy Update mechanism see -
 *              Documentation/RCU
@@ -76,7 +63,7 @@ void rcu_qs(void)
 * be called from hardirq context.  It is normally called from the
 * scheduling-clock interrupt.
 */
-void rcu_check_callbacks(int user)
+void rcu_sched_clock_irq(int user)
 {
        if (user) {
                rcu_qs();
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9180158756d2..3b084dbfb4bc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1,27 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Read-Copy Update mechanism for mutual exclusion
 *
- * 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, 2008
 *
 * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 *          Manfred Spraul <manfred@colorfullife.com>
- *          Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
+ *          Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
 *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 *
 * For detailed explanation of Read-Copy Update mechanism see -
@@ -62,6 +49,7 @@
 #include <linux/suspend.h>
 #include <linux/ftrace.h>
 #include <linux/tick.h>
+#include <linux/sysrq.h>
 #include "tree.h"
 #include "rcu.h"
@@ -115,6 +103,9 @@ int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
 int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
 /* panic() on RCU Stall sysctl. */
 int sysctl_panic_on_rcu_stall __read_mostly;
+/* Commandeer a sysrq key to dump RCU's tree. */
+static bool sysrq_rcu;
+module_param(sysrq_rcu, bool, 0444);
 /*
 * The rcu_scheduler_active variable is initialized to the value
@@ -479,7 +470,6 @@ module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next
 module_param(rcu_kick_kthreads, bool, 0644);
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
-static void force_quiescent_state(void);
 static int rcu_pending(void);
 /*
@@ -504,13 +494,12 @@ unsigned long rcu_exp_batches_completed(void)
 EXPORT_SYMBOL_GPL(rcu_exp_batches_completed);
 /*
- * Force a quiescent state.
+ * Return the root node of the rcu_state structure.
 */
-void rcu_force_quiescent_state(void)
+static struct rcu_node *rcu_get_root(void)
 {
-        force_quiescent_state();
+        return &rcu_state.node[0];
 }
-EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 /*
 * Convert a ->gp_state value to a character string.
@@ -529,19 +518,30 @@ void show_rcu_gp_kthreads(void)
 {
        int cpu;
        unsigned long j;
+        unsigned long ja;
+        unsigned long jr;
+        unsigned long jw;
        struct rcu_data *rdp;
        struct rcu_node *rnp;
-        j = jiffies - READ_ONCE(rcu_state.gp_activity);
+        j = jiffies;
-        pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %ld\n",
+        ja = j - READ_ONCE(rcu_state.gp_activity);
+        jr = j - READ_ONCE(rcu_state.gp_req_activity);
+        jw = j - READ_ONCE(rcu_state.gp_wake_time);
+        pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
                rcu_state.name, gp_state_getname(rcu_state.gp_state),
-                rcu_state.gp_state, rcu_state.gp_kthread->state, j);
+                rcu_state.gp_state,
+                rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+                ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+                (long)READ_ONCE(rcu_state.gp_seq),
+                (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+                READ_ONCE(rcu_state.gp_flags));
        rcu_for_each_node_breadth_first(rnp) {
                if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
                        continue;
-                pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+                pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-                        rnp->grplo, rnp->grphi, rnp->gp_seq,
+                        rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
-                        rnp->gp_seq_needed);
+                        (long)rnp->gp_seq_needed);
                if (!rcu_is_leaf_node(rnp))
                        continue;
                for_each_leaf_node_possible_cpu(rnp, cpu) {
@@ -550,14 +550,35 @@ void show_rcu_gp_kthreads(void)
                            ULONG_CMP_GE(rcu_state.gp_seq,
                                         rdp->gp_seq_needed))
                                continue;
-                        pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+                        pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-                                cpu, rdp->gp_seq_needed);
+                                cpu, (long)rdp->gp_seq_needed);
                }
        }
        /* sched_show_task(rcu_state.gp_kthread); */
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+/* Dump grace-period-request information due to commandeered sysrq. */
+static void sysrq_show_rcu(int key)
+{
+        show_rcu_gp_kthreads();
+}
+static struct sysrq_key_op sysrq_rcudump_op = {
+        .handler = sysrq_show_rcu,
+        .help_msg = "show-rcu(y)",
+        .action_msg = "Show RCU tree",
+        .enable_mask = SYSRQ_ENABLE_DUMP,
+};
+static int __init rcu_sysrq_init(void)
+{
+        if (sysrq_rcu)
+                return register_sysrq_key('y', &sysrq_rcudump_op);
+        return 0;
+}
+early_initcall(rcu_sysrq_init);
 /*
 * Send along grace-period-related data for rcutorture diagnostics.
 */
@@ -566,8 +587,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 {
        switch (test_type) {
        case RCU_FLAVOR:
-        case RCU_BH_FLAVOR:
-        case RCU_SCHED_FLAVOR:
                *flags = READ_ONCE(rcu_state.gp_flags);
                *gp_seq = rcu_seq_current(&rcu_state.gp_seq);
                break;
@@ -578,14 +597,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
 /*
- * Return the root node of the rcu_state structure.
- */
-static struct rcu_node *rcu_get_root(void)
-{
-        return &rcu_state.node[0];
-}
-/*
 * Enter an RCU extended quiescent state, which can be either the
 * idle loop or adaptive-tickless usermode execution.
 *
@@ -701,7 +712,6 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 /**
 * rcu_nmi_exit - inform RCU of exit from NMI context
- * @irq: Is this call from rcu_irq_exit?
 *
 * If you add or remove a call to rcu_nmi_exit(), be sure to test
 * with CONFIG_RCU_EQS_DEBUG=y.
@@ -1115,7 +1125,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
        }
        /*
-         * NO_HZ_FULL CPUs can run in-kernel without rcu_check_callbacks!
+         * NO_HZ_FULL CPUs can run in-kernel without rcu_sched_clock_irq!
         * The above code handles this, but only for straight cond_resched().
         * And some in-kernel loops check need_resched() before calling
         * cond_resched(), which defeats the above code for CPUs that are
@@ -1181,7 +1191,7 @@ static void rcu_check_gp_kthread_starvation(void)
                pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
                       rcu_state.name, j,
                       (long)rcu_seq_current(&rcu_state.gp_seq),
-                       rcu_state.gp_flags,
+                       READ_ONCE(rcu_state.gp_flags),
                       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
                       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
                if (gpk) {
@@ -1310,7 +1320,7 @@ static void print_other_cpu_stall(unsigned long gp_seq)
        panic_on_rcu_stall();
-        force_quiescent_state();  /* Kick them all. */
+        rcu_force_quiescent_state();  /* Kick them all. */
 }
 static void print_cpu_stall(void)
@@ -1557,17 +1567,28 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 }
 /*
- * Awaken the grace-period kthread.  Don't do a self-awaken, and don't
+ * Awaken the grace-period kthread.  Don't do a self-awaken (unless in
- * bother awakening when there is nothing for the grace-period kthread
+ * an interrupt or softirq handler), and don't bother awakening when there
- * to do (as in several CPUs raced to awaken, and we lost), and finally
+ * is nothing for the grace-period kthread to do (as in several CPUs raced
- * don't try to awaken a kthread that has not yet been created.
+ * to awaken, and we lost), and finally don't try to awaken a kthread that
+ * has not yet been created.  If all those checks are passed, track some
+ * debug information and awaken.
+ *
+ * So why do the self-wakeup when in an interrupt or softirq handler
+ * in the grace-period kthread's context?  Because the kthread might have
+ * been interrupted just as it was going to sleep, and just after the final
+ * pre-sleep check of the awaken condition.  In this case, a wakeup really
+ * is required, and is therefore supplied.
 */
 static void rcu_gp_kthread_wake(void)
 {
-        if (current == rcu_state.gp_kthread ||
+        if ((current == rcu_state.gp_kthread &&
+             !in_interrupt() && !in_serving_softirq()) ||
            !READ_ONCE(rcu_state.gp_flags) ||
            !rcu_state.gp_kthread)
                return;
+        WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
+        WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
        swake_up_one(&rcu_state.gp_wq);
 }
@@ -1711,7 +1732,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
                zero_cpu_stall_ticks(rdp);
        }
        rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
-        if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+        if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
                rdp->gp_seq_needed = rnp->gp_seq_needed;
        WRITE_ONCE(rdp->gpwrap, false);
        rcu_gpnum_ovf(rnp, rdp);
@@ -1939,7 +1960,7 @@ static void rcu_gp_fqs_loop(void)
                if (!ret) {
                        rcu_state.jiffies_force_qs = jiffies + j;
                        WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
-                                   jiffies + 3 * j);
+                                   jiffies + (j ? 3 * j : 2));
                }
                trace_rcu_grace_period(rcu_state.name,
                                       READ_ONCE(rcu_state.gp_seq),
@@ -2497,14 +2518,14 @@ static void rcu_do_batch(struct rcu_data *rdp)
 }
 /*
- * Check to see if this CPU is in a non-context-switch quiescent state
+ * This function is invoked from each scheduling-clock interrupt,
- * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
+ * and checks to see if this CPU is in a non-context-switch quiescent
- * Also schedule RCU core processing.
+ * state, for example, user mode or idle loop.  It also schedules RCU
- *
+ * core processing.  If the current grace period has gone on too long,
- * This function must be called from hardirq context.  It is normally
+ * it will ask the scheduler to manufacture a context switch for the sole
- * invoked from the scheduling-clock interrupt.
+ * purpose of providing a providing the needed quiescent state.
 */
-void rcu_check_callbacks(int user)
+void rcu_sched_clock_irq(int user)
 {
        trace_rcu_utilization(TPS("Start scheduler-tick"));
        raw_cpu_inc(rcu_data.ticks_this_gp);
@@ -2517,7 +2538,7 @@ void rcu_check_callbacks(int user)
                }
                __this_cpu_write(rcu_data.rcu_urgent_qs, false);
        }
-        rcu_flavor_check_callbacks(user);
+        rcu_flavor_sched_clock_irq(user);
        if (rcu_pending())
                invoke_rcu_core();
@@ -2578,7 +2599,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 * Force quiescent states on reluctant CPUs, and also detect which
 * CPUs are in dyntick-idle mode.
 */
-static void force_quiescent_state(void)
+void rcu_force_quiescent_state(void)
 {
        unsigned long flags;
        bool ret;
@@ -2610,6 +2631,7 @@ static void force_quiescent_state(void)
        raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags);
        rcu_gp_kthread_wake();
 }
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 /*
 * This function checks for grace-period requests that fail to motivate
@@ -2657,16 +2679,11 @@ rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
                raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
                return;
        }
-        pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
-                 __func__, (long)READ_ONCE(rcu_state.gp_seq),
-                 (long)READ_ONCE(rnp_root->gp_seq_needed),
-                 j - rcu_state.gp_req_activity, j - rcu_state.gp_activity,
-                 rcu_state.gp_flags, rcu_state.gp_state, rcu_state.name,
-                 rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL);
        WARN_ON(1);
        if (rnp_root != rnp)
                raw_spin_unlock_rcu_node(rnp_root);
        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+        show_rcu_gp_kthreads();
 }
 /*
@@ -2711,12 +2728,8 @@ void rcu_fwd_progress_check(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
-/*
+/* Perform RCU core processing work for the current CPU.  */
- * This does the RCU core processing work for the specified rcu_data
+static __latent_entropy void rcu_core(struct softirq_action *unused)
- * structures.  This may be called only from the CPU to whom the rdp
- * belongs.
- */
-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
 {
        unsigned long flags;
        struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
@@ -2801,9 +2814,9 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
        /*
         * Force the grace period if too many callbacks or too long waiting.
-         * Enforce hysteresis, and don't invoke force_quiescent_state()
+         * Enforce hysteresis, and don't invoke rcu_force_quiescent_state()
         * if some other CPU has recently done so.  Also, don't bother
-         * invoking force_quiescent_state() if the newly enqueued callback
+         * invoking rcu_force_quiescent_state() if the newly enqueued callback
         * is the only one waiting for a grace period to complete.
         */
        if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
@@ -2820,7 +2833,7 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
                        rdp->blimit = LONG_MAX;
                        if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
                            rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
-                                force_quiescent_state();
+                                rcu_force_quiescent_state();
                        rdp->n_force_qs_snap = rcu_state.n_force_qs;
                        rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
                }
@@ -2889,9 +2902,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy)
                        rcu_segcblist_init(&rdp->cblist);
        }
        rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
-        if (!lazy)
-                rcu_idle_count_callbacks_posted();
        if (__is_kfree_rcu_offset((unsigned long)func))
                trace_rcu_kfree_callback(rcu_state.name, head,
                                         (unsigned long)func,
@@ -2961,6 +2971,79 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
+/*
+ * During early boot, any blocking grace-period wait automatically
+ * implies a grace period.  Later on, this is never the case for PREEMPT.
+ *
+ * Howevr, because a context switch is a grace period for !PREEMPT, any
+ * blocking grace-period wait automatically implies a grace period if
+ * there is only one CPU online at any point time during execution of
+ * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
+ * occasionally incorrectly indicate that there are multiple CPUs online
+ * when there was in fact only one the whole time, as this just adds some
+ * overhead: RCU still operates correctly.
+ */
+static int rcu_blocking_is_gp(void)
+{
+        int ret;
+        if (IS_ENABLED(CONFIG_PREEMPT))
+                return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
+        might_sleep();  /* Check for RCU read-side critical section. */
+        preempt_disable();
+        ret = num_online_cpus() <= 1;
+        preempt_enable();
+        return ret;
+}
+/**
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed.  Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting.  RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
+ * In addition, regions of code across which interrupts, preemption, or
+ * softirqs have been disabled also serve as RCU read-side critical
+ * sections.  This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
+ *
+ * Note that this guarantee implies further memory-ordering guarantees.
+ * On systems with more than one CPU, when synchronize_rcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last RCU read-side critical section whose beginning
+ * preceded the call to synchronize_rcu().  In addition, each CPU having
+ * an RCU read-side critical section that extends beyond the return from
+ * synchronize_rcu() is guaranteed to have executed a full memory barrier
+ * after the beginning of synchronize_rcu() and before the beginning of
+ * that RCU read-side critical section.  Note that these guarantees include
+ * CPUs that are offline, idle, or executing in user mode, as well as CPUs
+ * that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_rcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ */
+void synchronize_rcu(void)
+{
+        RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+                         lock_is_held(&rcu_lock_map) ||
+                         lock_is_held(&rcu_sched_lock_map),
+                         "Illegal synchronize_rcu() in RCU read-side critical section");
+        if (rcu_blocking_is_gp())
+                return;
+        if (rcu_gp_is_expedited())
+                synchronize_rcu_expedited();
+        else
+                wait_rcu_gp(call_rcu);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
 /**
 * get_state_synchronize_rcu - Snapshot current RCU state
 *
@@ -3049,28 +3132,6 @@ static int rcu_pending(void)
 }
 /*
- * Return true if the specified CPU has any callback.  If all_lazy is
- * non-NULL, store an indication of whether all callbacks are lazy.
- * (If there are no callbacks, all of them are deemed to be lazy.)
- */
-static bool rcu_cpu_has_callbacks(bool *all_lazy)
-{
-        bool al = true;
-        bool hc = false;
-        struct rcu_data *rdp;
-        rdp = this_cpu_ptr(&rcu_data);
-        if (!rcu_segcblist_empty(&rdp->cblist)) {
-                hc = true;
-                if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist))
-                        al = false;
-        }
-        if (all_lazy)
-                *all_lazy = al;
-        return hc;
-}
-/*
 * Helper function for rcu_barrier() tracing.  If tracing is disabled,
 * the compiler is expected to optimize this away.
 */
@@ -3299,7 +3360,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
        trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
        rcu_prepare_kthreads(cpu);
-        rcu_spawn_all_nocb_kthreads(cpu);
+        rcu_spawn_cpu_nocb_kthread(cpu);
        return 0;
 }
@@ -3329,8 +3390,6 @@ int rcutree_online_cpu(unsigned int cpu)
        raw_spin_lock_irqsave_rcu_node(rnp, flags);
        rnp->ffmask |= rdp->grpmask;
        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-        if (IS_ENABLED(CONFIG_TREE_SRCU))
-                srcu_online_cpu(cpu);
        if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
                return 0; /* Too early in boot for scheduler work. */
        sync_sched_exp_online_cleanup(cpu);
@@ -3355,8 +3414,6 @@ int rcutree_offline_cpu(unsigned int cpu)
        raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
        rcutree_affinity_setting(cpu, cpu);
-        if (IS_ENABLED(CONFIG_TREE_SRCU))
-                srcu_offline_cpu(cpu);
        return 0;
 }
@@ -3777,7 +3834,7 @@ void __init rcu_init(void)
        rcu_init_one();
        if (dump_tree)
                rcu_dump_rcu_node_tree();
-        open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+        open_softirq(RCU_SOFTIRQ, rcu_core);
        /*
         * We don't need protection against CPU-hotplug here because
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d90b02b53c0e..bb4f995f2d3f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -1,25 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions.
 *
- * 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, 2008
 *
 * Author: Ingo Molnar <mingo@elte.hu>
- *         Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *         Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/cache.h>
@@ -36,7 +23,6 @@
 /* Communicate arguments to a workqueue handler. */
 struct rcu_exp_work {
-        smp_call_func_t rew_func;
        unsigned long rew_s;
        struct work_struct rew_work;
 };
@@ -194,10 +180,7 @@ struct rcu_data {
        bool rcu_need_heavy_qs;         /* GP old, so heavy quiescent state! */
        bool rcu_urgent_qs;             /* GP old need light quiescent state. */
 #ifdef CONFIG_RCU_FAST_NO_HZ
-        bool all_lazy;                  /* Are all CPU's CBs lazy? */
+        bool all_lazy;                  /* All CPU's CBs lazy at idle start? */
-        unsigned long nonlazy_posted;   /* # times non-lazy CB posted to CPU. */
-        unsigned long nonlazy_posted_snap;
-                                        /* Nonlazy_posted snapshot. */
        unsigned long last_accelerate;  /* Last jiffy CBs were accelerated. */
        unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */
        int tick_nohz_enabled_snap;     /* Previously seen value from sysfs. */
@@ -234,7 +217,13 @@ struct rcu_data {
                                        /* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-        /* 6) Diagnostic data, including RCU CPU stall warnings. */
+        /* 6) RCU priority boosting. */
+        struct task_struct *rcu_cpu_kthread_task;
+                                        /* rcuc per-CPU kthread or NULL. */
+        unsigned int rcu_cpu_kthread_status;
+        char rcu_cpu_has_work;
+        /* 7) Diagnostic data, including RCU CPU stall warnings. */
        unsigned int softirq_snap;      /* Snapshot of softirq activity. */
        /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
        struct irq_work rcu_iw;         /* Check for non-irq activity. */
@@ -303,6 +292,8 @@ struct rcu_state {
        struct swait_queue_head gp_wq;          /* Where GP task waits. */
        short gp_flags;                         /* Commands for GP task. */
        short gp_state;                         /* GP kthread sleep state. */
+        unsigned long gp_wake_time;             /* Last GP kthread wake. */
+        unsigned long gp_wake_seq;              /* ->gp_seq at ^^^. */
        /* End of fields guarded by root rcu_node's lock. */
@@ -402,13 +393,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
 int rcu_dynticks_snap(struct rcu_data *rdp);
-#ifdef CONFIG_RCU_BOOST
-DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
-DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DECLARE_PER_CPU(char, rcu_cpu_has_work);
-#endif /* #ifdef CONFIG_RCU_BOOST */
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
 static void rcu_qs(void);
@@ -420,7 +404,7 @@ static void rcu_print_detail_task_stall(void);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
-static void rcu_flavor_check_callbacks(int user);
+static void rcu_flavor_sched_clock_irq(int user);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
@@ -431,7 +415,6 @@ static void __init rcu_spawn_boost_kthreads(void);
 static void rcu_prepare_kthreads(int cpu);
 static void rcu_cleanup_after_idle(void);
 static void rcu_prepare_for_idle(void);
-static void rcu_idle_count_callbacks_posted(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
@@ -451,7 +434,7 @@ static bool rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
-static void rcu_spawn_all_nocb_kthreads(int cpu);
+static void rcu_spawn_cpu_nocb_kthread(int cpu);
 static void __init rcu_spawn_nocb_kthreads(void);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(void);
@@ -462,11 +445,3 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 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 */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 928fe5893a57..4c2a0189e748 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -1,27 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * RCU expedited grace periods
 *
- * 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, 2016
 *
- * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/lockdep.h>
+static void rcu_exp_handler(void *unused);
 /*
 * Record the start of an expedited grace period.
 */
@@ -344,7 +333,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 {
        int cpu;
        unsigned long flags;
-        smp_call_func_t func;
        unsigned long mask_ofl_test;
        unsigned long mask_ofl_ipi;
        int ret;
@@ -352,7 +340,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
                container_of(wp, struct rcu_exp_work, rew_work);
        struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
-        func = rewp->rew_func;
        raw_spin_lock_irqsave_rcu_node(rnp, flags);
        /* Each pass checks a CPU for identity, offline, and idle. */
@@ -396,7 +383,7 @@ retry_ipi:
                        mask_ofl_test |= mask;
                        continue;
                }
-                ret = smp_call_function_single(cpu, func, NULL, 0);
+                ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
                if (!ret) {
                        mask_ofl_ipi &= ~mask;
                        continue;
@@ -426,7 +413,7 @@ retry_ipi:
 * Select the nodes that the upcoming expedited grace period needs
 * to wait for.
 */
-static void sync_rcu_exp_select_cpus(smp_call_func_t func)
+static void sync_rcu_exp_select_cpus(void)
 {
        int cpu;
        struct rcu_node *rnp;
@@ -440,7 +427,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
                rnp->exp_need_flush = false;
                if (!READ_ONCE(rnp->expmask))
                        continue; /* Avoid early boot non-existent wq. */
-                rnp->rew.rew_func = func;
                if (!READ_ONCE(rcu_par_gp_wq) ||
                    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
                    rcu_is_last_leaf_node(rnp)) {
@@ -449,7 +435,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
                        continue;
                }
                INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-                preempt_disable();
                cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
                /* If all offline, queue the work on an unbound CPU. */
                if (unlikely(cpu > rnp->grphi - rnp->grplo))
@@ -457,7 +442,6 @@ static void sync_rcu_exp_select_cpus(smp_call_func_t func)
                else
                        cpu += rnp->grplo;
                queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
-                preempt_enable();
                rnp->exp_need_flush = true;
        }
@@ -580,10 +564,10 @@ static void rcu_exp_wait_wake(unsigned long s)
 * Common code to drive an expedited grace period forward, used by
 * workqueues and mid-boot-time tasks.
 */
-static void rcu_exp_sel_wait_wake(smp_call_func_t func, unsigned long s)
+static void rcu_exp_sel_wait_wake(unsigned long s)
 {
        /* Initialize the rcu_node tree in preparation for the wait. */
-        sync_rcu_exp_select_cpus(func);
+        sync_rcu_exp_select_cpus();
        /* Wait and clean up, including waking everyone. */
        rcu_exp_wait_wake(s);
@@ -597,52 +581,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
        struct rcu_exp_work *rewp;
        rewp = container_of(wp, struct rcu_exp_work, rew_work);
-        rcu_exp_sel_wait_wake(rewp->rew_func, rewp->rew_s);
+        rcu_exp_sel_wait_wake(rewp->rew_s);
-}
-/*
- * Given a smp_call_function() handler, kick off the specified
- * implementation of expedited grace period.
- */
-static void _synchronize_rcu_expedited(smp_call_func_t func)
-{
-        struct rcu_data *rdp;
-        struct rcu_exp_work rew;
-        struct rcu_node *rnp;
-        unsigned long s;
-        /* If expedited grace periods are prohibited, fall back to normal. */
-        if (rcu_gp_is_normal()) {
-                wait_rcu_gp(call_rcu);
-                return;
-        }
-        /* Take a snapshot of the sequence number.  */
-        s = rcu_exp_gp_seq_snap();
-        if (exp_funnel_lock(s))
-                return;  /* Someone else did our work for us. */
-        /* Ensure that load happens before action based on it. */
-        if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
-                /* Direct call during scheduler init and early_initcalls(). */
-                rcu_exp_sel_wait_wake(func, s);
-        } else {
-                /* Marshall arguments & schedule the expedited grace period. */
-                rew.rew_func = func;
-                rew.rew_s = s;
-                INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
-                queue_work(rcu_gp_wq, &rew.rew_work);
-        }
-        /* Wait for expedited grace period to complete. */
-        rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
-        rnp = rcu_get_root();
-        wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
-                   sync_exp_work_done(s));
-        smp_mb(); /* Workqueue actions happen before return. */
-        /* Let the next expedited grace period start. */
-        mutex_unlock(&rcu_state.exp_mutex);
 }
 #ifdef CONFIG_PREEMPT_RCU
@@ -654,7 +593,7 @@ static void _synchronize_rcu_expedited(smp_call_func_t func)
 * ->expmask fields in the rcu_node tree.  Otherwise, immediately
 * report the quiescent state.
 */
-static void sync_rcu_exp_handler(void *unused)
+static void rcu_exp_handler(void *unused)
 {
        unsigned long flags;
        struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -697,6 +636,7 @@ static void sync_rcu_exp_handler(void *unused)
                        WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
                }
                raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+                return;
        }
        /*
@@ -730,43 +670,10 @@ static void sync_sched_exp_online_cleanup(int cpu)
 {
 }
-/**
- * synchronize_rcu_expedited - Brute-force RCU grace period
- *
- * Wait for an RCU-preempt grace period, but expedite it.  The basic
- * idea is to IPI all non-idle non-nohz online CPUs.  The IPI handler
- * checks whether the CPU is in an RCU-preempt critical section, and
- * if so, it sets a flag that causes the outermost rcu_read_unlock()
- * to report the quiescent state.  On the other hand, if the CPU is
- * not in an RCU read-side critical section, the IPI handler reports
- * the quiescent state immediately.
- *
- * Although this is a greate improvement over previous expedited
- * implementations, it is still unfriendly to real-time workloads, so is
- * thus not recommended for any sort of common-case code.  In fact, if
- * you are using synchronize_rcu_expedited() in a loop, please restructure
- * your code to batch your updates, and then Use a single synchronize_rcu()
- * instead.
- *
- * This has the same semantics as (but is more brutal than) synchronize_rcu().
- */
-void synchronize_rcu_expedited(void)
-{
-        RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
-                         lock_is_held(&rcu_lock_map) ||
-                         lock_is_held(&rcu_sched_lock_map),
-                         "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
-        if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
-                return;
-        _synchronize_rcu_expedited(sync_rcu_exp_handler);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
-static void sync_sched_exp_handler(void *unused)
+static void rcu_exp_handler(void *unused)
 {
        struct rcu_data *rdp;
        struct rcu_node *rnp;
@@ -798,44 +705,78 @@ static void sync_sched_exp_online_cleanup(int cpu)
        rnp = rdp->mynode;
        if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
                return;
-        ret = smp_call_function_single(cpu, sync_sched_exp_handler, NULL, 0);
+        ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
        WARN_ON_ONCE(ret);
 }
-/*
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
- * Because a context switch is a grace period for !PREEMPT, any
- * blocking grace-period wait automatically implies a grace period if
- * there is only one CPU online at any point time during execution of
- * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
- * occasionally incorrectly indicate that there are multiple CPUs online
- * when there was in fact only one the whole time, as this just adds some
- * overhead: RCU still operates correctly.
- */
-static int rcu_blocking_is_gp(void)
-{
-        int ret;
-        might_sleep();  /* Check for RCU read-side critical section. */
-        preempt_disable();
-        ret = num_online_cpus() <= 1;
-        preempt_enable();
-        return ret;
-}
-/* PREEMPT=n implementation of synchronize_rcu_expedited(). */
+/**
+ * synchronize_rcu_expedited - Brute-force RCU grace period
+ *
+ * Wait for an RCU grace period, but expedite it.  The basic idea is to
+ * IPI all non-idle non-nohz online CPUs.  The IPI handler checks whether
+ * the CPU is in an RCU critical section, and if so, it sets a flag that
+ * causes the outermost rcu_read_unlock() to report the quiescent state
+ * for RCU-preempt or asks the scheduler for help for RCU-sched.  On the
+ * other hand, if the CPU is not in an RCU read-side critical section,
+ * the IPI handler reports the quiescent state immediately.
+ *
+ * Although this is a greate improvement over previous expedited
+ * implementations, it is still unfriendly to real-time workloads, so is
+ * thus not recommended for any sort of common-case code.  In fact, if
+ * you are using synchronize_rcu_expedited() in a loop, please restructure
+ * your code to batch your updates, and then Use a single synchronize_rcu()
+ * instead.
+ *
+ * This has the same semantics as (but is more brutal than) synchronize_rcu().
+ */
 void synchronize_rcu_expedited(void)
 {
+        struct rcu_data *rdp;
+        struct rcu_exp_work rew;
+        struct rcu_node *rnp;
+        unsigned long s;
        RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
                         lock_is_held(&rcu_lock_map) ||
                         lock_is_held(&rcu_sched_lock_map),
                         "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
-        /* If only one CPU, this is automatically a grace period. */
+        /* Is the state is such that the call is a grace period? */
        if (rcu_blocking_is_gp())
                return;
-        _synchronize_rcu_expedited(sync_sched_exp_handler);
+        /* If expedited grace periods are prohibited, fall back to normal. */
+        if (rcu_gp_is_normal()) {
+                wait_rcu_gp(call_rcu);
+                return;
+        }
+        /* Take a snapshot of the sequence number.  */
+        s = rcu_exp_gp_seq_snap();
+        if (exp_funnel_lock(s))
+                return;  /* Someone else did our work for us. */
+        /* Ensure that load happens before action based on it. */
+        if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
+                /* Direct call during scheduler init and early_initcalls(). */
+                rcu_exp_sel_wait_wake(s);
+        } else {
+                /* Marshall arguments & schedule the expedited grace period. */
+                rew.rew_s = s;
+                INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
+                queue_work(rcu_gp_wq, &rew.rew_work);
+        }
+        /* Wait for expedited grace period to complete. */
+        rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
+        rnp = rcu_get_root();
+        wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
+                   sync_exp_work_done(s));
+        smp_mb(); /* Workqueue actions happen before return. */
+        /* Let the next expedited grace period start. */
+        mutex_unlock(&rcu_state.exp_mutex);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
-#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1b3dd2fc0cd6..97dba50f6fb2 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1,27 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions that provide either classic
 * or preemptible semantics.
 *
- * 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 Red Hat, 2009
 * Copyright IBM Corporation, 2009
 *
 * Author: Ingo Molnar <mingo@elte.hu>
- *         Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ *         Paul E. McKenney <paulmck@linux.ibm.com>
 */
 #include <linux/delay.h>
@@ -34,17 +21,7 @@
 #include "../time/tick-internal.h"
 #ifdef CONFIG_RCU_BOOST
 #include "../locking/rtmutex_common.h"
-/*
- * Control variables for per-CPU and per-rcu_node kthreads.
- */
-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-DEFINE_PER_CPU(char, rcu_cpu_has_work);
 #else /* #ifdef CONFIG_RCU_BOOST */
 /*
@@ -307,7 +284,7 @@ static void rcu_qs(void)
                                       __this_cpu_read(rcu_data.gp_seq),
                                       TPS("cpuqs"));
                __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
-                barrier(); /* Coordinate with rcu_flavor_check_callbacks(). */
+                barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
                current->rcu_read_unlock_special.b.need_qs = false;
        }
 }
@@ -788,13 +765,13 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 }
 /*
- * Check for a quiescent state from the current CPU.  When a task blocks,
+ * Check for a quiescent state from the current CPU, including voluntary
- * the task is recorded in the corresponding CPU's rcu_node structure,
+ * context switches for Tasks RCU.  When a task blocks, the task is
- * which is checked elsewhere.
+ * recorded in the corresponding CPU's rcu_node structure, which is checked
- *
+ * elsewhere, hence this function need only check for quiescent states
- * Caller must disable hard irqs.
+ * related to the current CPU, not to those related to tasks.
 */
-static void rcu_flavor_check_callbacks(int user)
+static void rcu_flavor_sched_clock_irq(int user)
 {
        struct task_struct *t = current;
@@ -825,54 +802,6 @@ static void rcu_flavor_check_callbacks(int user)
                t->rcu_read_unlock_special.b.need_qs = true;
 }
-/**
- * synchronize_rcu - wait until a grace period has elapsed.
- *
- * Control will return to the caller some time after a full grace
- * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed.  Note, however, that
- * upon return from synchronize_rcu(), the caller might well be executing
- * concurrently with new RCU read-side critical sections that began while
- * synchronize_rcu() was waiting.  RCU read-side critical sections are
- * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
- * In addition, regions of code across which interrupts, preemption, or
- * softirqs have been disabled also serve as RCU read-side critical
- * sections.  This includes hardware interrupt handlers, softirq handlers,
- * and NMI handlers.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu() returns,
- * each CPU is guaranteed to have executed a full memory barrier since
- * the end of its last RCU read-side critical section whose beginning
- * preceded the call to synchronize_rcu().  In addition, each CPU having
- * an RCU read-side critical section that extends beyond the return from
- * synchronize_rcu() is guaranteed to have executed a full memory barrier
- * after the beginning of synchronize_rcu() and before the beginning of
- * that RCU read-side critical section.  Note that these guarantees include
- * CPUs that are offline, idle, or executing in user mode, as well as CPUs
- * that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but
- * again only if the system has more than one CPU).
- */
-void synchronize_rcu(void)
-{
-        RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
-                         lock_is_held(&rcu_lock_map) ||
-                         lock_is_held(&rcu_sched_lock_map),
-                         "Illegal synchronize_rcu() in RCU read-side critical section");
-        if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
-                return;
-        if (rcu_gp_is_expedited())
-                synchronize_rcu_expedited();
-        else
-                wait_rcu_gp(call_rcu);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
 /*
 * Check for a task exiting while in a preemptible-RCU read-side
 * critical section, clean up if so.  No need to issue warnings,
@@ -1088,14 +1017,10 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 }
 /*
- * Check to see if this CPU is in a non-context-switch quiescent state
+ * Check to see if this CPU is in a non-context-switch quiescent state,
- * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
+ * namely user mode and idle loop.
- * Also schedule RCU core processing.
- *
- * This function must be called from hardirq context.  It is normally
- * invoked from the scheduling-clock interrupt.
 */
-static void rcu_flavor_check_callbacks(int user)
+static void rcu_flavor_sched_clock_irq(int user)
 {
        if (user || rcu_is_cpu_rrupt_from_idle()) {
@@ -1115,22 +1040,6 @@ static void rcu_flavor_check_callbacks(int user)
        }
 }
-/* PREEMPT=n implementation of synchronize_rcu(). */
-void synchronize_rcu(void)
-{
-        RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
-                         lock_is_held(&rcu_lock_map) ||
-                         lock_is_held(&rcu_sched_lock_map),
-                         "Illegal synchronize_rcu() in RCU read-side critical section");
-        if (rcu_blocking_is_gp())
-                return;
-        if (rcu_gp_is_expedited())
-                synchronize_rcu_expedited();
-        else
-                wait_rcu_gp(call_rcu);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu);
 /*
 * Because preemptible RCU does not exist, tasks cannot possibly exit
 * while in preemptible RCU read-side critical sections.
@@ -1307,11 +1216,11 @@ static void invoke_rcu_callbacks_kthread(void)
        unsigned long flags;
        local_irq_save(flags);
-        __this_cpu_write(rcu_cpu_has_work, 1);
+        __this_cpu_write(rcu_data.rcu_cpu_has_work, 1);
-        if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
+        if (__this_cpu_read(rcu_data.rcu_cpu_kthread_task) != NULL &&
-            current != __this_cpu_read(rcu_cpu_kthread_task)) {
+            current != __this_cpu_read(rcu_data.rcu_cpu_kthread_task)) {
-                rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
+                rcu_wake_cond(__this_cpu_read(rcu_data.rcu_cpu_kthread_task),
-                              __this_cpu_read(rcu_cpu_kthread_status));
+                              __this_cpu_read(rcu_data.rcu_cpu_kthread_status));
        }
        local_irq_restore(flags);
 }
@@ -1322,7 +1231,7 @@ static void invoke_rcu_callbacks_kthread(void)
 */
 static bool rcu_is_callbacks_kthread(void)
 {
-        return __this_cpu_read(rcu_cpu_kthread_task) == current;
+        return __this_cpu_read(rcu_data.rcu_cpu_kthread_task) == current;
 }
 #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1369,11 +1278,6 @@ static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
        return 0;
 }
-static void rcu_kthread_do_work(void)
-{
-        rcu_do_batch(this_cpu_ptr(&rcu_data));
-}
 static void rcu_cpu_kthread_setup(unsigned int cpu)
 {
        struct sched_param sp;
@@ -1384,12 +1288,12 @@ static void rcu_cpu_kthread_setup(unsigned int cpu)
 static void rcu_cpu_kthread_park(unsigned int cpu)
 {
-        per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
+        per_cpu(rcu_data.rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
 }
 static int rcu_cpu_kthread_should_run(unsigned int cpu)
 {
-        return __this_cpu_read(rcu_cpu_has_work);
+        return __this_cpu_read(rcu_data.rcu_cpu_has_work);
 }
 /*
@@ -1399,21 +1303,20 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
 */
 static void rcu_cpu_kthread(unsigned int cpu)
 {
-        unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
+        unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status);
-        char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
+        char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
        int spincnt;
        for (spincnt = 0; spincnt < 10; spincnt++) {
                trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
                local_bh_disable();
                *statusp = RCU_KTHREAD_RUNNING;
-                this_cpu_inc(rcu_cpu_kthread_loops);
                local_irq_disable();
                work = *workp;
                *workp = 0;
                local_irq_enable();
                if (work)
-                        rcu_kthread_do_work();
+                        rcu_do_batch(this_cpu_ptr(&rcu_data));
                local_bh_enable();
                if (*workp == 0) {
                        trace_rcu_utilization(TPS("End CPU kthread@rcu_wait"));
@@ -1459,7 +1362,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 }
 static struct smp_hotplug_thread rcu_cpu_thread_spec = {
-        .store                  = &rcu_cpu_kthread_task,
+        .store                  = &rcu_data.rcu_cpu_kthread_task,
        .thread_should_run      = rcu_cpu_kthread_should_run,
        .thread_fn              = rcu_cpu_kthread,
        .thread_comm            = "rcuc/%u",
@@ -1476,7 +1379,7 @@ static void __init rcu_spawn_boost_kthreads(void)
        int cpu;
        for_each_possible_cpu(cpu)
-                per_cpu(rcu_cpu_has_work, cpu) = 0;
+                per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0;
        if (WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcub kthread, OOM is now expected behavior\n", __func__))
                return;
        rcu_for_each_leaf_node(rnp)
@@ -1543,7 +1446,7 @@ static void rcu_prepare_kthreads(int cpu)
 int rcu_needs_cpu(u64 basemono, u64 *nextevt)
 {
        *nextevt = KTIME_MAX;
-        return rcu_cpu_has_callbacks(NULL);
+        return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist);
 }
 /*
@@ -1562,14 +1465,6 @@ static void rcu_prepare_for_idle(void)
 {
 }
-/*
- * Don't bother keeping a running count of the number of RCU callbacks
- * posted because CONFIG_RCU_FAST_NO_HZ=n.
- */
-static void rcu_idle_count_callbacks_posted(void)
-{
-}
 #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 /*
@@ -1652,11 +1547,8 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
        lockdep_assert_irqs_disabled();
-        /* Snapshot to detect later posting of non-lazy callback. */
-        rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
        /* If no callbacks, RCU doesn't need the CPU. */
-        if (!rcu_cpu_has_callbacks(&rdp->all_lazy)) {
+        if (rcu_segcblist_empty(&rdp->cblist)) {
                *nextevt = KTIME_MAX;
                return 0;
        }
@@ -1670,11 +1562,12 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt)
        rdp->last_accelerate = jiffies;
        /* Request timer delay depending on laziness, and round. */
-        if (!rdp->all_lazy) {
+        rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
+        if (rdp->all_lazy) {
+                dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
+        } else {
                dj = round_up(rcu_idle_gp_delay + jiffies,
                               rcu_idle_gp_delay) - jiffies;
-        } else {
-                dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
        }
        *nextevt = basemono + dj * TICK_NSEC;
        return 0;
@@ -1704,7 +1597,7 @@ static void rcu_prepare_for_idle(void)
        /* Handle nohz enablement switches conservatively. */
        tne = READ_ONCE(tick_nohz_active);
        if (tne != rdp->tick_nohz_enabled_snap) {
-                if (rcu_cpu_has_callbacks(NULL))
+                if (!rcu_segcblist_empty(&rdp->cblist))
                        invoke_rcu_core(); /* force nohz to see update. */
                rdp->tick_nohz_enabled_snap = tne;
                return;
@@ -1717,10 +1610,8 @@ static void rcu_prepare_for_idle(void)
         * callbacks, invoke RCU core for the side-effect of recalculating
         * idle duration on re-entry to idle.
         */
-        if (rdp->all_lazy &&
+        if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
-            rdp->nonlazy_posted != rdp->nonlazy_posted_snap) {
                rdp->all_lazy = false;
-                rdp->nonlazy_posted_snap = rdp->nonlazy_posted;
                invoke_rcu_core();
                return;
        }
@@ -1756,19 +1647,6 @@ static void rcu_cleanup_after_idle(void)
                invoke_rcu_core();
 }
-/*
- * Keep a running count of the number of non-lazy callbacks posted
- * on this CPU.  This running counter (which is never decremented) allows
- * rcu_prepare_for_idle() to detect when something out of the idle loop
- * posts a callback, even if an equal number of callbacks are invoked.
- * Of course, callbacks should only be posted from within a trace event
- * designed to be called from idle or from within RCU_NONIDLE().
- */
-static void rcu_idle_count_callbacks_posted(void)
-{
-        __this_cpu_add(rcu_data.nonlazy_posted, 1);
-}
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 #ifdef CONFIG_RCU_FAST_NO_HZ
@@ -1776,13 +1654,12 @@ static void rcu_idle_count_callbacks_posted(void)
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
 {
        struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-        unsigned long nlpd = rdp->nonlazy_posted - rdp->nonlazy_posted_snap;
-        sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c",
+        sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
                rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-                ulong2long(nlpd),
+                ".l"[rdp->all_lazy],
-                rdp->all_lazy ? 'L' : '.',
+                ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
-                rdp->tick_nohz_enabled_snap ? '.' : 'D');
+                ".D"[!rdp->tick_nohz_enabled_snap]);
 }
 #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -1868,22 +1745,24 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
 /*
 * Offload callback processing from the boot-time-specified set of CPUs
- * specified by rcu_nocb_mask.  For each CPU in the set, there is a
+ * specified by rcu_nocb_mask.  For the CPUs in the set, there are kthreads
- * kthread created that pulls the callbacks from the corresponding CPU,
+ * created that pull the callbacks from the corresponding CPU, wait for
- * waits for a grace period to elapse, and invokes the callbacks.
+ * a grace period to elapse, and invoke the callbacks.  These kthreads
- * The no-CBs CPUs do a wake_up() on their kthread when they insert
+ * are organized into leaders, which manage incoming callbacks, wait for
- * a callback into any empty list, unless the rcu_nocb_poll boot parameter
+ * grace periods, and awaken followers, and the followers, which only
- * has been specified, in which case each kthread actively polls its
+ * invoke callbacks.  Each leader is its own follower.  The no-CBs CPUs
- * CPU.  (Which isn't so great for energy efficiency, but which does
+ * do a wake_up() on their kthread when they insert a callback into any
- * reduce RCU's overhead on that CPU.)
+ * empty list, unless the rcu_nocb_poll boot parameter has been specified,
+ * in which case each kthread actively polls its CPU.  (Which isn't so great
+ * for energy efficiency, but which does reduce RCU's overhead on that CPU.)
 *
 * This is intended to be used in conjunction with Frederic Weisbecker's
 * adaptive-idle work, which would seriously reduce OS jitter on CPUs
 * running CPU-bound user-mode computations.
 *
- * Offloading of callback processing could also in theory be used as
+ * Offloading of callbacks can also be used as an energy-efficiency
- * an energy-efficiency measure because CPUs with no RCU callbacks
+ * measure because CPUs with no RCU callbacks queued are more aggressive
- * queued are more aggressive about entering dyntick-idle mode.
+ * about entering dyntick-idle mode.
 */
@@ -1987,10 +1866,7 @@ static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype,
        raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 }
-/*
+/* Does rcu_barrier need to queue an RCU callback on the specified CPU?  */
- * Does the specified CPU need an RCU callback for this invocation
- * of rcu_barrier()?
- */
 static bool rcu_nocb_cpu_needs_barrier(int cpu)
 {
        struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -2006,8 +1882,8 @@ static bool rcu_nocb_cpu_needs_barrier(int cpu)
         * callbacks would be posted.  In the worst case, the first
         * barrier in rcu_barrier() suffices (but the caller cannot
         * necessarily rely on this, not a substitute for the caller
-         * getting the concurrency design right!).  There must also be
+         * getting the concurrency design right!).  There must also be a
-         * a barrier between the following load an posting of a callback
+         * barrier between the following load and posting of a callback
         * (if a callback is in fact needed).  This is associated with an
         * atomic_inc() in the caller.
         */
@@ -2517,9 +2393,9 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
 /*
 * If the specified CPU is a no-CBs CPU that does not already have its
- * rcuo kthreads, spawn them.
+ * rcuo kthread, spawn it.
 */
-static void rcu_spawn_all_nocb_kthreads(int cpu)
+static void rcu_spawn_cpu_nocb_kthread(int cpu)
 {
        if (rcu_scheduler_fully_active)
                rcu_spawn_one_nocb_kthread(cpu);
@@ -2536,7 +2412,7 @@ static void __init rcu_spawn_nocb_kthreads(void)
        int cpu;
        for_each_online_cpu(cpu)
-                rcu_spawn_all_nocb_kthreads(cpu);
+                rcu_spawn_cpu_nocb_kthread(cpu);
 }
 /* How many follower CPU IDs per leader?  Default of -1 for sqrt(nr_cpu_ids). */
@@ -2670,7 +2546,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 {
 }
-static void rcu_spawn_all_nocb_kthreads(int cpu)
+static void rcu_spawn_cpu_nocb_kthread(int cpu)
 {
 }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1971869c4072..e3c6395c9b4c 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -1,26 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Read-Copy Update mechanism for mutual exclusion
 *
- * 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, 2001
 *
 * Authors: Dipankar Sarma <dipankar@in.ibm.com>
 *          Manfred Spraul <manfred@colorfullife.com>
 *
- * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
 * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
 * Papers:
 * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 22bd8980f32f..835671f0f917 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -48,8 +48,8 @@ EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook);
 *
 * Clear the update_util_data pointer for the given CPU.
 *
- * Callers must use RCU-sched callbacks to free any memory that might be
+ * Callers must use RCU callbacks to free any memory that might be
- * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * accessed via the old update_util_data pointer or invoke synchronize_rcu()
 * right after this function to avoid use-after-free.
 */
 void cpufreq_remove_update_util_hook(int cpu)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 033ec7c45f13..2efe629425be 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -859,7 +859,7 @@ static void sugov_stop(struct cpufreq_policy *policy)
        for_each_cpu(cpu, policy->cpus)
                cpufreq_remove_update_util_hook(cpu);
-        synchronize_sched();
+        synchronize_rcu();
        if (!policy->fast_switch_enabled) {
                irq_work_sync(&sg_policy->irq_work);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d04530bf251f..6665b9c02e2f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1260,7 +1260,7 @@ extern void sched_ttwu_pending(void);
 /*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
- * See detach_destroy_domains: synchronize_sched for details.
+ * See destroy_sched_domains: call_rcu for details.
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 3f35ba1d8fde..7d905f55e7fa 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -442,7 +442,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
        raw_spin_unlock_irqrestore(&rq->lock, flags);
        if (old_rd)
-                call_rcu_sched(&old_rd->rcu, free_rootdomain);
+                call_rcu(&old_rd->rcu, free_rootdomain);
 }
 void sched_get_rd(struct root_domain *rd)
@@ -455,7 +455,7 @@ void sched_put_rd(struct root_domain *rd)
        if (!atomic_dec_and_test(&rd->refcount))
                return;
-        call_rcu_sched(&rd->rcu, free_rootdomain);
+        call_rcu(&rd->rcu, free_rootdomain);
 }
 static int init_rootdomain(struct root_domain *rd)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 444156debfa0..6eb7cc4b6d52 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1632,7 +1632,7 @@ void update_process_times(int user_tick)
        /* Note: this timer irq context must be accounted for as well. */
        account_process_tick(p, user_tick);
        run_local_timers();
-        rcu_check_callbacks(user_tick);
+        rcu_sched_clock_irq(user_tick);
 #ifdef CONFIG_IRQ_WORK
        if (in_irq())
                irq_work_tick();
diff --git a/kernel/torture.c b/kernel/torture.c
index bbf6d473e50c..8faa1a9aaeb9 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -1,23 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
 * Common functions for in-kernel torture tests.
 *
- * 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, 2014
 *
- * Author: Paul E. McKenney <paulmck@us.ibm.com>
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
 *      Based on kernel/rcu/torture.c.
 */
@@ -53,7 +40,7 @@
 #include "rcu/rcu.h"
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 static char *torture_type;
 static int verbose;
@@ -75,6 +62,7 @@ static DEFINE_MUTEX(fullstop_mutex);
 static struct task_struct *onoff_task;
 static long onoff_holdoff;
 static long onoff_interval;
+static torture_ofl_func *onoff_f;
 static long n_offline_attempts;
 static long n_offline_successes;
 static unsigned long sum_offline;
@@ -118,6 +106,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
                        pr_alert("%s" TORTURE_FLAG
                                 "torture_onoff task: offlined %d\n",
                                 torture_type, cpu);
+                if (onoff_f)
+                        onoff_f();
                (*n_offl_successes)++;
                delta = jiffies - starttime;
                *sum_offl += delta;
@@ -243,11 +233,12 @@ stop:
 /*
 * Initiate online-offline handling.
 */
-int torture_onoff_init(long ooholdoff, long oointerval)
+int torture_onoff_init(long ooholdoff, long oointerval, torture_ofl_func *f)
 {
 #ifdef CONFIG_HOTPLUG_CPU
        onoff_holdoff = ooholdoff;
        onoff_interval = oointerval;
+        onoff_f = f;
        if (onoff_interval <= 0)
                return 0;
        return torture_create_kthread(torture_onoff, NULL, onoff_task);
diff --git a/tools/testing/selftests/rcutorture/bin/nolibc.h b/tools/include/nolibc/nolibc.h
index f98f5b92d3eb..1708e9f9f8aa 100644
--- a/tools/testing/selftests/rcutorture/bin/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -3,7 +3,85 @@
 * Copyright (C) 2017-2018 Willy Tarreau <w@1wt.eu>
 */
-/* some archs (at least aarch64) don't expose the regular syscalls anymore by
+/*
+ * This file is designed to be used as a libc alternative for minimal programs
+ * with very limited requirements. It consists of a small number of syscall and
+ * type definitions, and the minimal startup code needed to call main().
+ * All syscalls are declared as static functions so that they can be optimized
+ * away by the compiler when not used.
+ *
+ * Syscalls are split into 3 levels:
+ *   - The lower level is the arch-specific syscall() definition, consisting in
+ *     assembly code in compound expressions. These are called my_syscall0() to
+ *     my_syscall6() depending on the number of arguments. The MIPS
+ *     implementation is limited to 5 arguments. All input arguments are cast
+ *     to a long stored in a register. These expressions always return the
+ *     syscall's return value as a signed long value which is often either a
+ *     pointer or the negated errno value.
+ *
+ *   - The second level is mostly architecture-independent. It is made of
+ *     static functions called sys_<name>() which rely on my_syscallN()
+ *     depending on the syscall definition. These functions are responsible
+ *     for exposing the appropriate types for the syscall arguments (int,
+ *     pointers, etc) and for setting the appropriate return type (often int).
+ *     A few of them are architecture-specific because the syscalls are not all
+ *     mapped exactly the same among architectures. For example, some archs do
+ *     not implement select() and need pselect6() instead, so the sys_select()
+ *     function will have to abstract this.
+ *
+ *   - The third level is the libc call definition. It exposes the lower raw
+ *     sys_<name>() calls in a way that looks like what a libc usually does,
+ *     takes care of specific input values, and of setting errno upon error.
+ *     There can be minor variations compared to standard libc calls. For
+ *     example the open() call always takes 3 args here.
+ *
+ * The errno variable is declared static and unused. This way it can be
+ * optimized away if not used. However this means that a program made of
+ * multiple C files may observe different errno values (one per C file). For
+ * the type of programs this project targets it usually is not a problem. The
+ * resulting program may even be reduced by defining the NOLIBC_IGNORE_ERRNO
+ * macro, in which case the errno value will never be assigned.
+ *
+ * Some stdint-like integer types are defined. These are valid on all currently
+ * supported architectures, because signs are enforced, ints are assumed to be
+ * 32 bits, longs the size of a pointer and long long 64 bits. If more
+ * architectures have to be supported, this may need to be adapted.
+ *
+ * Some macro definitions like the O_* values passed to open(), and some
+ * structures like the sys_stat struct depend on the architecture.
+ *
+ * The definitions start with the architecture-specific parts, which are picked
+ * based on what the compiler knows about the target architecture, and are
+ * completed with the generic code. Since it is the compiler which sets the
+ * target architecture, cross-compiling normally works out of the box without
+ * having to specify anything.
+ *
+ * Finally some very common libc-level functions are provided. It is the case
+ * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing
+ * is currently provided regarding stdio emulation.
+ *
+ * The macro NOLIBC is always defined, so that it is possible for a program to
+ * check this macro to know if it is being built against and decide to disable
+ * some features or simply not to include some standard libc files.
+ *
+ * Ideally this file should be split in multiple files for easier long term
+ * maintenance, but provided as a single file as it is now, it's quite
+ * convenient to use. Maybe some variations involving a set of includes at the
+ * top could work.
+ *
+ * A simple static executable may be built this way :
+ *      $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ *            -static -include nolibc.h -lgcc -o hello hello.c
+ *
+ * A very useful calling convention table may be found here :
+ *      http://man7.org/linux/man-pages/man2/syscall.2.html
+ *
+ * This doc is quite convenient though not necessarily up to date :
+ *      https://w3challs.com/syscalls/
+ *
+ */
+/* Some archs (at least aarch64) don't expose the regular syscalls anymore by
 * default, either because they have an "_at" replacement, or because there are
 * more modern alternatives. For now we'd rather still use them.
 */
@@ -19,18 +97,6 @@
 #define NOLIBC
-/* Build a static executable this way :
- *      $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
- *            -static -include nolibc.h -lgcc -o hello hello.c
- *
- * Useful calling convention table found here :
- *      http://man7.org/linux/man-pages/man2/syscall.2.html
- *
- * This doc is even better :
- *      https://w3challs.com/syscalls/
- */
 /* this way it will be removed if unused */
 static int errno;
@@ -81,9 +147,9 @@ typedef   signed long        time_t;
 /* for poll() */
 struct pollfd {
-    int fd;
+        int fd;
-    short int events;
+        short int events;
-    short int revents;
+        short int revents;
 };
 /* for select() */
@@ -239,7 +305,7 @@ struct stat {
                "syscall\n"                                                   \
                : "=a" (_ret)                                                 \
                : "0"(_num)                                                   \
-                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"                                \
+                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
        );                                                                    \
        _ret;                                                                 \
 })
@@ -255,7 +321,7 @@ struct stat {
                : "=a" (_ret)                                                 \
                : "r"(_arg1),                                                 \
                  "0"(_num)                                                   \
-                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"                                \
+                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
        );                                                                    \
        _ret;                                                                 \
 })
@@ -272,7 +338,7 @@ struct stat {
                : "=a" (_ret)                                                 \
                : "r"(_arg1), "r"(_arg2),                                     \
                  "0"(_num)                                                   \
-                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"                                \
+                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
        );                                                                    \
        _ret;                                                                 \
 })
@@ -290,7 +356,7 @@ struct stat {
                : "=a" (_ret)                                                 \
                : "r"(_arg1), "r"(_arg2), "r"(_arg3),                         \
                  "0"(_num)                                                   \
-                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"                                \
+                : "rcx", "r8", "r9", "r10", "r11", "memory", "cc"             \
        );                                                                    \
        _ret;                                                                 \
 })
@@ -1006,7 +1072,7 @@ struct sys_stat_struct {
                : "=r"(_num), "=r"(_arg4)                                     \
                : "r"(_num)                                                   \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
@@ -1025,7 +1091,7 @@ struct sys_stat_struct {
                : "0"(_num),                                                  \
                  "r"(_arg1)                                                  \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
@@ -1045,7 +1111,7 @@ struct sys_stat_struct {
                : "0"(_num),                                                  \
                  "r"(_arg1), "r"(_arg2)                                      \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
@@ -1066,7 +1132,7 @@ struct sys_stat_struct {
                : "0"(_num),                                                  \
                  "r"(_arg1), "r"(_arg2), "r"(_arg3)                          \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
@@ -1087,7 +1153,7 @@ struct sys_stat_struct {
                : "0"(_num),                                                  \
                  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4)              \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
@@ -1110,7 +1176,7 @@ struct sys_stat_struct {
                : "0"(_num),                                                  \
                  "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5)  \
                : "memory", "cc", "at", "v1", "hi", "lo",                     \
-                                                                              \
+                  "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9"  \
        );                                                                    \
        _arg4 ? -_num : _num;                                                 \
 })
diff --git a/tools/memory-model/.gitignore b/tools/memory-model/.gitignore
new file mode 100644
index 000000000000..b1d34c52f3c3
--- /dev/null
+++ b/tools/memory-model/.gitignore
@@ -0,0 +1 @@
+litmus
diff --git a/tools/memory-model/README b/tools/memory-model/README
index acf9077cffaa..0f2c366518c6 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -156,6 +156,8 @@ lock.cat
 README
        This file.
+scripts Various scripts, see scripts/README.
 ===========
 LIMITATIONS
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index b84fb2f67109..796513362c05 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -29,7 +29,8 @@ enum Barriers = 'wmb (*smp_wmb*) ||
                'sync-rcu (*synchronize_rcu*) ||
                'before-atomic (*smp_mb__before_atomic*) ||
                'after-atomic (*smp_mb__after_atomic*) ||
-                'after-spinlock (*smp_mb__after_spinlock*)
+                'after-spinlock (*smp_mb__after_spinlock*) ||
+                'after-unlock-lock (*smp_mb__after_unlock_lock*)
 instructions F[Barriers]
 (* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 882fc33274ac..8f23c74a96fd 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -30,7 +30,9 @@ let wmb = [W] ; fencerel(Wmb) ; [W]
 let mb = ([M] ; fencerel(Mb) ; [M]) |
        ([M] ; fencerel(Before-atomic) ; [RMW] ; po? ; [M]) |
        ([M] ; po? ; [RMW] ; fencerel(After-atomic) ; [M]) |
-        ([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M])
+        ([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) |
+        ([M] ; po ; [UL] ; (co | po) ; [LKW] ;
+                fencerel(After-unlock-lock) ; [M])
 let gp = po ; [Sync-rcu] ; po?
 let strong-fence = mb | gp
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index 6fa3eb28d40b..b27911cc087d 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -23,6 +23,7 @@ smp_wmb() { __fence{wmb}; }
 smp_mb__before_atomic() { __fence{before-atomic}; }
 smp_mb__after_atomic() { __fence{after-atomic}; }
 smp_mb__after_spinlock() { __fence{after-spinlock}; }
+smp_mb__after_unlock_lock() { __fence{after-unlock-lock}; }
 // Exchange
 xchg(X,V)  __xchg{mb}(X,V)
diff --git a/tools/memory-model/scripts/README b/tools/memory-model/scripts/README
new file mode 100644
index 000000000000..29375a1fbbfa
--- /dev/null
+++ b/tools/memory-model/scripts/README
@@ -0,0 +1,70 @@
+                        ============
+                        LKMM SCRIPTS
+                        ============
+These scripts are run from the tools/memory-model directory.
+checkalllitmus.sh
+        Run all litmus tests in the litmus-tests directory, checking
+        the results against the expected results recorded in the
+        "Result:" comment lines.
+checkghlitmus.sh
+        Run all litmus tests in the https://github.com/paulmckrcu/litmus
+        archive that are C-language and that have "Result:" comment lines
+        documenting expected results, comparing the actual results to
+        those expected.
+checklitmushist.sh
+        Run all litmus tests having .litmus.out files from previous
+        initlitmushist.sh or newlitmushist.sh runs, comparing the
+        herd output to that of the original runs.
+checklitmus.sh
+        Check a single litmus test against its "Result:" expected result.
+cmplitmushist.sh
+        Compare output from two different runs of the same litmus tests,
+        with the absolute pathnames of the tests to run provided one
+        name per line on standard input.  Not normally run manually,
+        provided instead for use by other scripts.
+initlitmushist.sh
+        Run all litmus tests having no more than the specified number
+        of processes given a specified timeout, recording the results
+        in .litmus.out files.
+judgelitmus.sh
+        Given a .litmus file and its .litmus.out herd output, check the
+        .litmus.out file against the .litmus file's "Result:" comment to
+        judge whether the test ran correctly.  Not normally run manually,
+        provided instead for use by other scripts.
+newlitmushist.sh
+        For all new or updated litmus tests having no more than the
+        specified number of processes given a specified timeout, run
+        and record the results in .litmus.out files.
+parseargs.sh
+        Parse command-line arguments.  Not normally run manually,
+        provided instead for use by other scripts.
+runlitmushist.sh
+        Run the litmus tests whose absolute pathnames are provided one
+        name per line on standard input.  Not normally run manually,
+        provided instead for use by other scripts.
+README
+        This file
diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
index ca528f9a24d4..b35fcd61ecf6 100755
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -1,42 +1,27 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
 #
-# Run herd tests on all .litmus files in the specified directory (which
+# Run herd tests on all .litmus files in the litmus-tests directory
-# defaults to litmus-tests) and check each file's result against a "Result:"
+# and check each file's result against a "Result:" comment within that
-# comment within that litmus test.  If the verification result does not
+# litmus test.  If the verification result does not match that specified
-# match that specified in the litmus test, this script prints an error
+# in the litmus test, this script prints an error message prefixed with
-# message prefixed with "^^^".  It also outputs verification results to
+# "^^^".  It also outputs verification results to a file whose name is
-# a file whose name is that of the specified litmus test, but with ".out"
+# that of the specified litmus test, but with ".out" appended.
-# appended.
 #
 # Usage:
-#       checkalllitmus.sh [ directory ]
+#       checkalllitmus.sh
 #
-# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# Run this in the directory containing the memory model.
-# arguments to herd, whose default is defined by the checklitmus.sh script.
-# Thus, one would normally run this in the directory containing the memory
-# model, specifying the pathname of the litmus test to check.
 #
 # This script makes no attempt to run the litmus tests concurrently.
 #
-# 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, 2018
 #
 # Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-litmusdir=${1-litmus-tests}
+. scripts/parseargs.sh
+litmusdir=litmus-tests
 if test -d "$litmusdir" -a -r "$litmusdir" -a -x "$litmusdir"
 then
        :
@@ -45,6 +30,14 @@ else
        exit 255
 fi
+# Create any new directories that have appeared in the github litmus
+# repo since the last run.
+if test "$LKMM_DESTDIR" != "."
+then
+        find $litmusdir -type d -print |
+        ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
+fi
 # Find the checklitmus script.  If it is not where we expect it, then
 # assume that the caller has the PATH environment variable set
 # appropriately.
@@ -57,7 +50,7 @@ fi
 # Run the script on all the litmus tests in the specified directory
 ret=0
-for i in litmus-tests/*.litmus
+for i in $litmusdir/*.litmus
 do
        if ! $clscript $i
        then
@@ -66,8 +59,8 @@ do
 done
 if test "$ret" -ne 0
 then
-        echo " ^^^ VERIFICATION MISMATCHES"
+        echo " ^^^ VERIFICATION MISMATCHES" 1>&2
 else
-        echo All litmus tests verified as was expected.
+        echo All litmus tests verified as was expected. 1>&2
 fi
 exit $ret
diff --git a/tools/memory-model/scripts/checkghlitmus.sh b/tools/memory-model/scripts/checkghlitmus.sh
new file mode 100644
index 000000000000..6589fbb6f653
--- /dev/null
+++ b/tools/memory-model/scripts/checkghlitmus.sh
@@ -0,0 +1,65 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Runs the C-language litmus tests having a maximum number of processes
+# to run, defaults to 6.
+#
+# sh checkghlitmus.sh
+#
+# Run from the Linux kernel tools/memory-model directory.  See the
+# parseargs.sh scripts for arguments.
+. scripts/parseargs.sh
+T=/tmp/checkghlitmus.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+# Clone the repository if it is not already present.
+if test -d litmus
+then
+        :
+else
+        git clone https://github.com/paulmckrcu/litmus
+        ( cd litmus; git checkout origin/master )
+fi
+# Create any new directories that have appeared in the github litmus
+# repo since the last run.
+if test "$LKMM_DESTDIR" != "."
+then
+        find litmus -type d -print |
+        ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
+fi
+# Create a list of the C-language litmus tests previously run.
+( cd $LKMM_DESTDIR; find litmus -name '*.litmus.out' -print ) |
+        sed -e 's/\.out$//' |
+        xargs -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' |
+        xargs -r grep -L "^P${LKMM_PROCS}"> $T/list-C-already
+# Create a list of C-language litmus tests with "Result:" commands and
+# no more than the specified number of processes.
+find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C
+xargs < $T/list-C -r egrep -l '^ \* Result: (Never|Sometimes|Always|DEADLOCK)' > $T/list-C-result
+xargs < $T/list-C-result -r grep -L "^P${LKMM_PROCS}" > $T/list-C-result-short
+# Form list of tests without corresponding .litmus.out files
+sort $T/list-C-already $T/list-C-result-short | uniq -u > $T/list-C-needed
+# Run any needed tests.
+if scripts/runlitmushist.sh < $T/list-C-needed > $T/run.stdout 2> $T/run.stderr
+then
+        errs=
+else
+        errs=1
+fi
+sed < $T/list-C-result-short -e 's,^,scripts/judgelitmus.sh ,' |
+        sh > $T/judge.stdout 2> $T/judge.stderr
+if test -n "$errs"
+then
+        cat $T/run.stderr 1>&2
+fi
+grep '!!!' $T/judge.stdout
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
index bf12a75c0719..dd08801a30b0 100755
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -1,40 +1,24 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
 #
-# Run a herd test and check the result against a "Result:" comment within
+# Run a herd test and invokes judgelitmus.sh to check the result against
-# the litmus test.  If the verification result does not match that specified
+# a "Result:" comment within the litmus test.  It also outputs verification
-# in the litmus test, this script prints an error message prefixed with
-# "^^^" and exits with a non-zero status.  It also outputs verification
 # results to a file whose name is that of the specified litmus test, but
 # with ".out" appended.
 #
 # Usage:
 #       checklitmus.sh file.litmus
 #
-# The LINUX_HERD_OPTIONS environment variable may be used to specify
+# Run this in the directory containing the memory model, specifying the
-# arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
+# pathname of the litmus test to check.  The caller is expected to have
-# one would normally run this in the directory containing the memory model,
+# properly set up the LKMM environment variables.
-# specifying the pathname of the litmus test to check.
-#
-# 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, 2018
 #
 # Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 litmus=$1
-herdoptions=${LINUX_HERD_OPTIONS--conf linux-kernel.cfg}
+herdoptions=${LKMM_HERD_OPTIONS--conf linux-kernel.cfg}
 if test -f "$litmus" -a -r "$litmus"
 then
@@ -43,44 +27,8 @@ else
        echo ' --- ' error: \"$litmus\" is not a readable file
        exit 255
 fi
-if grep -q '^ \* Result: ' $litmus
-then
-        outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'`
-else
-        outcome=specified
-fi
-echo Herd options: $herdoptions > $litmus.out
+echo Herd options: $herdoptions > $LKMM_DESTDIR/$litmus.out
-/usr/bin/time herd7 -o ~/tmp $herdoptions $litmus >> $litmus.out 2>&1
+/usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $litmus >> $LKMM_DESTDIR/$litmus.out 2>&1
-grep "Herd options:" $litmus.out
-grep '^Observation' $litmus.out
+scripts/judgelitmus.sh $litmus
-if grep -q '^Observation' $litmus.out
-then
-        :
-else
-        cat $litmus.out
-        echo ' ^^^ Verification error'
-        echo ' ^^^ Verification error' >> $litmus.out 2>&1
-        exit 255
-fi
-if test "$outcome" = DEADLOCK
-then
-        echo grep 3 and 4
-        if grep '^Observation' $litmus.out | grep -q 'Never 0 0$'
-        then
-                ret=0
-        else
-                echo " ^^^ Unexpected non-$outcome verification"
-                echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
-                ret=1
-        fi
-elif grep '^Observation' $litmus.out | grep -q $outcome || test "$outcome" = Maybe
-then
-        ret=0
-else
-        echo " ^^^ Unexpected non-$outcome verification"
-        echo " ^^^ Unexpected non-$outcome verification" >> $litmus.out 2>&1
-        ret=1
-fi
-tail -2 $litmus.out | head -1
-exit $ret
diff --git a/tools/memory-model/scripts/checklitmushist.sh b/tools/memory-model/scripts/checklitmushist.sh
new file mode 100644
index 000000000000..1d210ffb7c8a
--- /dev/null
+++ b/tools/memory-model/scripts/checklitmushist.sh
@@ -0,0 +1,60 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Reruns the C-language litmus tests previously run that match the
+# specified criteria, and compares the result to that of the previous
+# runs from initlitmushist.sh and/or newlitmushist.sh.
+#
+# sh checklitmushist.sh
+#
+# Run from the Linux kernel tools/memory-model directory.
+# See scripts/parseargs.sh for list of arguments.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+. scripts/parseargs.sh
+T=/tmp/checklitmushist.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+if test -d litmus
+then
+        :
+else
+        echo Run scripts/initlitmushist.sh first, need litmus repo.
+        exit 1
+fi
+# Create the results directory and populate it with subdirectories.
+# The initial output is created here to avoid clobbering the output
+# generated earlier.
+mkdir $T/results
+find litmus -type d -print | ( cd $T/results; sed -e 's/^/mkdir -p /' | sh )
+# Create the list of litmus tests already run, then remove those that
+# are excluded by this run's --procs argument.
+( cd $LKMM_DESTDIR; find litmus -name '*.litmus.out' -print ) |
+        sed -e 's/\.out$//' |
+        xargs -r grep -L "^P${LKMM_PROCS}"> $T/list-C-already
+xargs < $T/list-C-already -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short
+# Redirect output, run tests, then restore destination directory.
+destdir="$LKMM_DESTDIR"
+LKMM_DESTDIR=$T/results; export LKMM_DESTDIR
+scripts/runlitmushist.sh < $T/list-C-short > $T/runlitmushist.sh.out 2>&1
+LKMM_DESTDIR="$destdir"; export LKMM_DESTDIR
+# Move the newly generated .litmus.out files to .litmus.out.new files
+# in the destination directory.
+cdir=`pwd`
+ddir=`awk -v c="$cdir" -v d="$LKMM_DESTDIR" \
+        'END { if (d ~ /^\//) print d; else print c "/" d; }' < /dev/null`
+( cd $T/results; find litmus -type f -name '*.litmus.out' -print |
+  sed -e 's,^.*$,cp & '"$ddir"'/&.new,' | sh )
+sed < $T/list-C-short -e 's,^,'"$LKMM_DESTDIR/"',' |
+        sh scripts/cmplitmushist.sh
+exit $?
diff --git a/tools/memory-model/scripts/cmplitmushist.sh b/tools/memory-model/scripts/cmplitmushist.sh
new file mode 100644
index 000000000000..0f498aeeccf5
--- /dev/null
+++ b/tools/memory-model/scripts/cmplitmushist.sh
@@ -0,0 +1,87 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Compares .out and .out.new files for each name on standard input,
+# one full pathname per line.  Outputs comparison results followed by
+# a summary.
+#
+# sh cmplitmushist.sh
+T=/tmp/cmplitmushist.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+# comparetest oldpath newpath
+perfect=0
+obsline=0
+noobsline=0
+obsresult=0
+badcompare=0
+comparetest () {
+        grep -v 'maxresident)k\|minor)pagefaults\|^Time' $1 > $T/oldout
+        grep -v 'maxresident)k\|minor)pagefaults\|^Time' $2 > $T/newout
+        if cmp -s $T/oldout $T/newout && grep -q '^Observation' $1
+        then
+                echo Exact output match: $2
+                perfect=`expr "$perfect" + 1`
+                return 0
+        fi
+        grep '^Observation' $1 > $T/oldout
+        grep '^Observation' $2 > $T/newout
+        if test -s $T/oldout -o -s $T/newout
+        then
+                if cmp -s $T/oldout $T/newout
+                then
+                        echo Matching Observation result and counts: $2
+                        obsline=`expr "$obsline" + 1`
+                        return 0
+                fi
+        else
+                echo Missing Observation line "(e.g., herd7 timeout)": $2
+                noobsline=`expr "$noobsline" + 1`
+                return 0
+        fi
+        grep '^Observation' $1 | awk '{ print $3 }' > $T/oldout
+        grep '^Observation' $2 | awk '{ print $3 }' > $T/newout
+        if cmp -s $T/oldout $T/newout
+        then
+                echo Matching Observation Always/Sometimes/Never result: $2
+                obsresult=`expr "$obsresult" + 1`
+                return 0
+        fi
+        echo ' !!!' Result changed: $2
+        badcompare=`expr "$badcompare" + 1`
+        return 1
+}
+sed -e 's/^.*$/comparetest &.out &.out.new/' > $T/cmpscript
+. $T/cmpscript > $T/cmpscript.out
+cat $T/cmpscript.out
+echo ' ---' Summary: 1>&2
+grep '!!!' $T/cmpscript.out 1>&2
+if test "$perfect" -ne 0
+then
+        echo Exact output matches: $perfect 1>&2
+fi
+if test "$obsline" -ne 0
+then
+        echo Matching Observation result and counts: $obsline 1>&2
+fi
+if test "$noobsline" -ne 0
+then
+        echo Missing Observation line "(e.g., herd7 timeout)": $noobsline 1>&2
+fi
+if test "$obsresult" -ne 0
+then
+        echo Matching Observation Always/Sometimes/Never result: $obsresult 1>&2
+fi
+if test "$badcompare" -ne 0
+then
+        echo "!!!" Result changed: $badcompare 1>&2
+        exit 1
+fi
+exit 0
diff --git a/tools/memory-model/scripts/initlitmushist.sh b/tools/memory-model/scripts/initlitmushist.sh
new file mode 100644
index 000000000000..956b6957484d
--- /dev/null
+++ b/tools/memory-model/scripts/initlitmushist.sh
@@ -0,0 +1,68 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Runs the C-language litmus tests matching the specified criteria.
+# Generates the output for each .litmus file into a corresponding
+# .litmus.out file, and does not judge the result.
+#
+# sh initlitmushist.sh
+#
+# Run from the Linux kernel tools/memory-model directory.
+# See scripts/parseargs.sh for list of arguments.
+#
+# This script can consume significant wallclock time and CPU, especially as
+# the value of --procs rises.  On a four-core (eight hardware threads)
+# 2.5GHz x86 with a one-minute per-run timeout:
+#
+# --procs wallclock CPU         timeouts        tests
+#       1 0m11.241s 0m1.086s           0           19
+#       2 1m12.598s 2m8.459s           2          393
+#       3 1m30.007s 6m2.479s           4         2291
+#       4 3m26.042s 18m5.139s          9         3217
+#       5 4m26.661s 23m54.128s        13         3784
+#       6 4m41.900s 26m4.721s         13         4352
+#       7 5m51.463s 35m50.868s        13         4626
+#       8 10m5.235s 68m43.672s        34         5117
+#       9 15m57.80s 105m58.101s       69         5156
+#      10 16m14.13s 103m35.009s       69         5165
+#      20 27m48.55s 198m3.286s       156         5269
+#
+# Increasing the timeout on the 20-process run to five minutes increases
+# the runtime to about 90 minutes with the CPU time rising to about
+# 10 hours.  On the other hand, it decreases the number of timeouts to 101.
+#
+# Note that there are historical tests for which herd7 will fail
+# completely, for example, litmus/manual/atomic/C-unlock-wait-00.litmus
+# contains a call to spin_unlock_wait(), which no longer exists in either
+# the kernel or LKMM.
+. scripts/parseargs.sh
+T=/tmp/initlitmushist.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+if test -d litmus
+then
+        :
+else
+        git clone https://github.com/paulmckrcu/litmus
+        ( cd litmus; git checkout origin/master )
+fi
+# Create any new directories that have appeared in the github litmus
+# repo since the last run.
+if test "$LKMM_DESTDIR" != "."
+then
+        find litmus -type d -print |
+        ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
+fi
+# Create a list of the C-language litmus tests with no more than the
+# specified number of processes (per the --procs argument).
+find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C
+xargs < $T/list-C -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short
+scripts/runlitmushist.sh < $T/list-C-short
+exit 0
diff --git a/tools/memory-model/scripts/judgelitmus.sh b/tools/memory-model/scripts/judgelitmus.sh
new file mode 100644
index 000000000000..0cc63875e395
--- /dev/null
+++ b/tools/memory-model/scripts/judgelitmus.sh
@@ -0,0 +1,78 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Given a .litmus test and the corresponding .litmus.out file, check
+# the .litmus.out file against the "Result:" comment to judge whether
+# the test ran correctly.
+#
+# Usage:
+#       judgelitmus.sh file.litmus
+#
+# Run this in the directory containing the memory model, specifying the
+# pathname of the litmus test to check.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+litmus=$1
+if test -f "$litmus" -a -r "$litmus"
+then
+        :
+else
+        echo ' --- ' error: \"$litmus\" is not a readable file
+        exit 255
+fi
+if test -f "$LKMM_DESTDIR/$litmus".out -a -r "$LKMM_DESTDIR/$litmus".out
+then
+        :
+else
+        echo ' --- ' error: \"$LKMM_DESTDIR/$litmus\".out is not a readable file
+        exit 255
+fi
+if grep -q '^ \* Result: ' $litmus
+then
+        outcome=`grep -m 1 '^ \* Result: ' $litmus | awk '{ print $3 }'`
+else
+        outcome=specified
+fi
+grep '^Observation' $LKMM_DESTDIR/$litmus.out
+if grep -q '^Observation' $LKMM_DESTDIR/$litmus.out
+then
+        :
+else
+        echo ' !!! Verification error' $litmus
+        if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+        then
+                echo ' !!! Verification error' >> $LKMM_DESTDIR/$litmus.out 2>&1
+        fi
+        exit 255
+fi
+if test "$outcome" = DEADLOCK
+then
+        if grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q 'Never 0 0$'
+        then
+                ret=0
+        else
+                echo " !!! Unexpected non-$outcome verification" $litmus
+                if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+                then
+                        echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1
+                fi
+                ret=1
+        fi
+elif grep '^Observation' $LKMM_DESTDIR/$litmus.out | grep -q $outcome || test "$outcome" = Maybe
+then
+        ret=0
+else
+        echo " !!! Unexpected non-$outcome verification" $litmus
+        if ! grep -q '!!!' $LKMM_DESTDIR/$litmus.out
+        then
+                echo " !!! Unexpected non-$outcome verification" >> $LKMM_DESTDIR/$litmus.out 2>&1
+        fi
+        ret=1
+fi
+tail -2 $LKMM_DESTDIR/$litmus.out | head -1
+exit $ret
diff --git a/tools/memory-model/scripts/newlitmushist.sh b/tools/memory-model/scripts/newlitmushist.sh
new file mode 100644
index 000000000000..991f8f814881
--- /dev/null
+++ b/tools/memory-model/scripts/newlitmushist.sh
@@ -0,0 +1,61 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Runs the C-language litmus tests matching the specified criteria
+# that do not already have a corresponding .litmus.out file, and does
+# not judge the result.
+#
+# sh newlitmushist.sh
+#
+# Run from the Linux kernel tools/memory-model directory.
+# See scripts/parseargs.sh for list of arguments.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+. scripts/parseargs.sh
+T=/tmp/newlitmushist.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+if test -d litmus
+then
+        :
+else
+        echo Run scripts/initlitmushist.sh first, need litmus repo.
+        exit 1
+fi
+# Create any new directories that have appeared in the github litmus
+# repo since the last run.
+if test "$LKMM_DESTDIR" != "."
+then
+        find litmus -type d -print |
+        ( cd "$LKMM_DESTDIR"; sed -e 's/^/mkdir -p /' | sh )
+fi
+# Create a list of the C-language litmus tests previously run.
+( cd $LKMM_DESTDIR; find litmus -name '*.litmus.out' -print ) |
+        sed -e 's/\.out$//' |
+        xargs -r grep -L "^P${LKMM_PROCS}"> $T/list-C-already
+# Form full list of litmus tests with no more than the specified
+# number of processes (per the --procs argument).
+find litmus -name '*.litmus' -exec grep -l -m 1 "^C " {} \; > $T/list-C-all
+xargs < $T/list-C-all -r grep -L "^P${LKMM_PROCS}" > $T/list-C-short
+# Form list of new tests.  Note: This does not handle litmus-test deletion!
+sort $T/list-C-already $T/list-C-short | uniq -u > $T/list-C-new
+# Form list of litmus tests that have changed since the last run.
+sed < $T/list-C-short -e 's,^.*$,if test & -nt '"$LKMM_DESTDIR"'/&.out; then echo &; fi,' > $T/list-C-script
+sh $T/list-C-script > $T/list-C-newer
+# Merge the list of new and of updated litmus tests: These must be (re)run.
+sort -u $T/list-C-new $T/list-C-newer > $T/list-C-needed
+scripts/runlitmushist.sh < $T/list-C-needed
+exit 0
diff --git a/tools/memory-model/scripts/parseargs.sh b/tools/memory-model/scripts/parseargs.sh
new file mode 100644
index 000000000000..859e1d581e05
--- /dev/null
+++ b/tools/memory-model/scripts/parseargs.sh
@@ -0,0 +1,136 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+#
+# the corresponding .litmus.out file, and does not judge the result.
+#
+# . scripts/parseargs.sh
+#
+# Include into other Linux kernel tools/memory-model scripts.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+T=/tmp/parseargs.sh.$$
+mkdir $T
+# Initialize one parameter: initparam name default
+initparam () {
+        echo if test -z '"$'$1'"' > $T/s
+        echo then >> $T/s
+        echo    $1='"'$2'"' >> $T/s
+        echo    export $1 >> $T/s
+        echo fi >> $T/s
+        echo $1_DEF='$'$1  >> $T/s
+        . $T/s
+}
+initparam LKMM_DESTDIR "."
+initparam LKMM_HERD_OPTIONS "-conf linux-kernel.cfg"
+initparam LKMM_JOBS `getconf _NPROCESSORS_ONLN`
+initparam LKMM_PROCS "3"
+initparam LKMM_TIMEOUT "1m"
+scriptname=$0
+usagehelp () {
+        echo "Usage $scriptname [ arguments ]"
+        echo "      --destdir path (place for .litmus.out, default by .litmus)"
+        echo "      --herdopts -conf linux-kernel.cfg ..."
+        echo "      --jobs N (number of jobs, default one per CPU)"
+        echo "      --procs N (litmus tests with at most this many processes)"
+        echo "      --timeout N (herd7 timeout (e.g., 10s, 1m, 2hr, 1d, '')"
+        echo "Defaults: --destdir '$LKMM_DESTDIR_DEF' --herdopts '$LKMM_HERD_OPTIONS_DEF' --jobs '$LKMM_JOBS_DEF' --procs '$LKMM_PROCS_DEF' --timeout '$LKMM_TIMEOUT_DEF'"
+        exit 1
+}
+usage () {
+        usagehelp 1>&2
+}
+# checkarg --argname argtype $# arg mustmatch cannotmatch
+checkarg () {
+        if test $3 -le 1
+        then
+                echo $1 needs argument $2 matching \"$5\"
+                usage
+        fi
+        if echo "$4" | grep -q -e "$5"
+        then
+                :
+        else
+                echo $1 $2 \"$4\" must match \"$5\"
+                usage
+        fi
+        if echo "$4" | grep -q -e "$6"
+        then
+                echo $1 $2 \"$4\" must not match \"$6\"
+                usage
+        fi
+}
+while test $# -gt 0
+do
+        case "$1" in
+        --destdir)
+                checkarg --destdir "(path to directory)" "$#" "$2" '.\+' '^--'
+                LKMM_DESTDIR="$2"
+                mkdir $LKMM_DESTDIR > /dev/null 2>&1
+                if ! test -e "$LKMM_DESTDIR"
+                then
+                        echo "Cannot create directory --destdir '$LKMM_DESTDIR'"
+                        usage
+                fi
+                if test -d "$LKMM_DESTDIR" -a -w "$LKMM_DESTDIR" -a -x "$LKMM_DESTDIR"
+                then
+                        :
+                else
+                        echo "Directory --destdir '$LKMM_DESTDIR' insufficient permissions to create files"
+                        usage
+                fi
+                shift
+                ;;
+        --herdopts|--herdopt)
+                checkarg --destdir "(herd options)" "$#" "$2" '.*' '^--'
+                LKMM_HERD_OPTIONS="$2"
+                shift
+                ;;
+        -j[1-9]*)
+                njobs="`echo $1 | sed -e 's/^-j//'`"
+                trailchars="`echo $njobs | sed -e 's/[0-9]\+\(.*\)$/\1/'`"
+                if test -n "$trailchars"
+                then
+                        echo $1 trailing characters "'$trailchars'"
+                        usagehelp
+                fi
+                LKMM_JOBS="`echo $njobs | sed -e 's/^\([0-9]\+\).*$/\1/'`"
+                ;;
+        --jobs|--job|-j)
+                checkarg --jobs "(number)" "$#" "$2" '^[1-9][0-9]\+$' '^--'
+                LKMM_JOBS="$2"
+                shift
+                ;;
+        --procs|--proc)
+                checkarg --procs "(number)" "$#" "$2" '^[0-9]\+$' '^--'
+                LKMM_PROCS="$2"
+                shift
+                ;;
+        --timeout)
+                checkarg --timeout "(timeout spec)" "$#" "$2" '^\([0-9]\+[smhd]\?\|\)$' '^--'
+                LKMM_TIMEOUT="$2"
+                shift
+                ;;
+        *)
+                echo Unknown argument $1
+                usage
+                ;;
+        esac
+        shift
+done
+if test -z "$LKMM_TIMEOUT"
+then
+        LKMM_TIMEOUT_CMD=""; export LKMM_TIMEOUT_CMD
+else
+        LKMM_TIMEOUT_CMD="timeout $LKMM_TIMEOUT"; export LKMM_TIMEOUT_CMD
+fi
+rm -rf $T
diff --git a/tools/memory-model/scripts/runlitmushist.sh b/tools/memory-model/scripts/runlitmushist.sh
new file mode 100644
index 000000000000..e507f5f933d5
--- /dev/null
+++ b/tools/memory-model/scripts/runlitmushist.sh
@@ -0,0 +1,87 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Runs the C-language litmus tests specified on standard input, using up
+# to the specified number of CPUs (defaulting to all of them) and placing
+# the results in the specified directory (defaulting to the same place
+# the litmus test came from).
+#
+# sh runlitmushist.sh
+#
+# Run from the Linux kernel tools/memory-model directory.
+# This script uses environment variables produced by parseargs.sh.
+#
+# Copyright IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+T=/tmp/runlitmushist.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+if test -d litmus
+then
+        :
+else
+        echo Directory \"litmus\" missing, aborting run.
+        exit 1
+fi
+# Prefixes for per-CPU scripts
+for ((i=0;i<$LKMM_JOBS;i++))
+do
+        echo dir="$LKMM_DESTDIR" > $T/$i.sh
+        echo T=$T >> $T/$i.sh
+        echo herdoptions=\"$LKMM_HERD_OPTIONS\" >> $T/$i.sh
+        cat << '___EOF___' >> $T/$i.sh
+        runtest () {
+                echo ' ... ' /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 '>' $dir/$1.out '2>&1'
+                if /usr/bin/time $LKMM_TIMEOUT_CMD herd7 $herdoptions $1 > $dir/$1.out 2>&1
+                then
+                        if ! grep -q '^Observation ' $dir/$1.out
+                        then
+                                echo ' !!! Herd failed, no Observation:' $1
+                        fi
+                else
+                        exitcode=$?
+                        if test "$exitcode" -eq 124
+                        then
+                                exitmsg="timed out"
+                        else
+                                exitmsg="failed, exit code $exitcode"
+                        fi
+                        echo ' !!! Herd' ${exitmsg}: $1
+                fi
+        }
+___EOF___
+done
+awk -v q="'" -v b='\\' '
+{
+        print "echo `grep " q "^P[0-9]" b "+(" q " " $0 " | tail -1 | sed -e " q "s/^P" b "([0-9]" b "+" b ")(.*$/" b "1/" q "` " $0
+}' | bash |
+sort -k1n |
+awk -v ncpu=$LKMM_JOBS -v t=$T '
+{
+        print "runtest " $2 >> t "/" NR % ncpu ".sh";
+}
+END {
+        for (i = 0; i < ncpu; i++) {
+                print "sh " t "/" i ".sh > " t "/" i ".sh.out 2>&1 &";
+                close(t "/" i ".sh");
+        }
+        print "wait";
+}' | sh
+cat $T/*.sh.out
+if grep -q '!!!' $T/*.sh.out
+then
+        echo ' ---' Summary: 1>&2
+        grep '!!!' $T/*.sh.out 1>&2
+        nfail="`grep '!!!' $T/*.sh.out | wc -l`"
+        echo 'Number of failed herd runs (e.g., timeout): ' $nfail 1>&2
+        exit 1
+else
+        echo All runs completed successfully. 1>&2
+        exit 0
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
index da298394daa2..83552bb007b4 100755
--- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -40,17 +40,24 @@ mkdir $T
 cat > $T/init << '__EOF___'
 #!/bin/sh
 # Run in userspace a few milliseconds every second.  This helps to
-# exercise the NO_HZ_FULL portions of RCU.
+# exercise the NO_HZ_FULL portions of RCU.  The 192 instances of "a" was
+# empirically shown to give a nice multi-millisecond burst of user-mode
+# execution on a 2GHz CPU, as desired.  Modern CPUs will vary from a
+# couple of milliseconds up to perhaps 100 milliseconds, which is an
+# acceptable range.
+#
+# Why not calibrate an exact delay?  Because within this initrd, we
+# are restricted to Bourne-shell builtins, which as far as I know do not
+# provide any means of obtaining a fine-grained timestamp.
+a4="a a a a"
+a16="$a4 $a4 $a4 $a4"
+a64="$a16 $a16 $a16 $a16"
+a192="$a64 $a64 $a64"
 while :
 do
        q=
-        for i in \
+        for i in $a192
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a \
-                a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a
        do
                q="$q $i"
        done
@@ -124,8 +131,8 @@ if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \
   | grep -q '^yes'; then
        # architecture supported by nolibc
        ${CROSS_COMPILE}gcc -fno-asynchronous-unwind-tables -fno-ident \
-                -nostdlib -include ../bin/nolibc.h -lgcc -s -static -Os \
+                -nostdlib -include ../../../../include/nolibc/nolibc.h \
-                -o init init.c
+                -lgcc -s -static -Os -o init init.c
 else
        ${CROSS_COMPILE}gcc -s -static -Os -o init init.c
 fi
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 585845203db8..38df17b7760e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4084,7 +4084,7 @@ static int kvm_suspend(void)
 static void kvm_resume(void)
 {
        if (kvm_usage_count) {
-                WARN_ON(raw_spin_is_locked(&kvm_count_lock));
+                lockdep_assert_held(&kvm_count_lock);
                hardware_enable_nolock(NULL);
        }
 }