scftorture.2020.08.24a: Torture tests for smp_call_function() and friends.

doc.2020.08.24a: Documentation updates.
fixes.2020.09.03b: Miscellaneous fixes.
torture.2020.08.24a: Torture-test updates.

CPUs can go offline shortly after kfree_call_rcu() has been invoked,
which can leave memory stranded until those CPUs come back online.
This commit therefore drains the kcrp of each CPU, not just the
ones that happen to be online.
Acked-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The rcu_segcblist_accelerate() function returns true iff it is necessary
to request another grace period.  A tracing session showed that this
function unnecessarily requests grace periods.

For example, consider the following sequence of events:
1. Callbacks are queued only on the NEXT segment of CPU A's callback list.
2. CPU A runs RCU_SOFTIRQ, accelerating these callbacks from NEXT to WAIT.
3. Thus rcu_segcblist_accelerate() returns true, requesting grace period N.
4. RCU's grace-period kthread wakes up on CPU B and starts grace period N.
4. CPU A notices the new grace period and invokes RCU_SOFTIRQ.
5. CPU A's RCU_SOFTIRQ again invokes rcu_segcblist_accelerate(), but
   there are no new callbacks.  However, rcu_segcblist_accelerate()
   nevertheless (uselessly) requests a new grace period N+1.

This extra grace period results in additional lock contention and also
additional wakeups, all for no good reason.

This commit therefore adds a check to rcu_segcblist_accelerate() that
prevents the return of true when there are no new callbacks.

This change reduces the number of grace periods (GPs) and wakeups in each
of eleven five-second rcutorture runs as follows:

+----+-------------------+-------------------+
| #  | Number of GPs     | Number of Wakeups |
+====+=========+=========+=========+=========+
| 1  | With    | Without | With    | Without |
+----+---------+---------+---------+---------+
| 2  |      75 |      89 |     113 |     119 |
+----+---------+---------+---------+---------+
| 3  |      62 |      91 |     105 |     123 |
+----+---------+---------+---------+---------+
| 4  |      60 |      79 |      98 |     110 |
+----+---------+---------+---------+---------+
| 5  |      63 |      79 |      99 |     112 |
+----+---------+---------+---------+---------+
| 6  |      57 |      89 |      96 |     123 |
+----+---------+---------+---------+---------+
| 7  |      64 |      85 |      97 |     118 |
+----+---------+---------+---------+---------+
| 8  |      58 |      83 |      98 |     113 |
+----+---------+---------+---------+---------+
| 9  |      57 |      77 |      89 |     104 |
+----+---------+---------+---------+---------+
| 10 |      66 |      82 |      98 |     119 |
+----+---------+---------+---------+---------+
| 11 |      52 |      82 |      83 |     117 |
+----+---------+---------+---------+---------+

The reduction in the number of wakeups ranges from 5% to 40%.

Cc: urezki@gmail.com
[ paulmck: Rework commit log and comment. ]
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds a "--gdb" parameter to kvm.sh, which causes
"CONFIG_DEBUG_INFO=y" to be added to the Kconfig options, "nokaslr"
to be added to the boot parameters, and "-s -S" to be added to the qemu
arguments.  Furthermore, the scripting prints messages telling the user
how to start up gdb for the run in question.

Because of the interactive nature of gdb sessions, only one "--configs"
scenario is permitted when "--gdb" is specified.  For most torture types,
this means that a "--configs" argument is required, and that argument
must specify the single scenario of interest.

The usual cautions about breakpoints and timing apply, for example,
staring at your gdb prompt for too long will likely get you many
complaints, including RCU CPU stall warnings.  Omar Sandoval further
suggests using gdb's "hbreak" command instead of the "break" command on
systems supporting hardware breakpoints, and further using the "commands"
option because the resulting non-interactive breakpoints are less likely
to get you RCU CPU stall warnings.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds an rcutorture.leakpointer module parameter that
intentionally leaks an RCU-protected pointer out of the RCU read-side
critical section and checks to see if the corresponding grace period
has elapsed, emitting a WARN_ON_ONCE() if so.  This module parameter can
be used to test facilities like CONFIG_RCU_STRICT_GRACE_PERIOD that end
grace periods quickly.

While in the area, also document rcutorture.irqreader, which was
previously left out.

Reported-by Jann Horn <jannh@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently, registering and unregistering the OOM notifier is done
right before and after the test, respectively.  This will not work
well for multi-threaded tests, so this commit hoists this registering
and unregistering up into the rcu_torture_fwd_prog_init() and
rcu_torture_fwd_prog_cleanup() functions.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently in the unlikely event that buf fails to be allocated it
is dereferenced a few times.  Use the errexit flag to determine if
buf should be written to to avoid the null pointer dereferences.

Addresses-Coverity: ("Dereference after null check")
Fixes: f518f154 ("refperf: Dynamically allocate experiment-summary output buffer")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The current rcutorture forward-progress code assumes that it is the
only cause of out-of-memory (OOM) events.  For script-based rcutorture
testing, this assumption is in fact correct.  However, testing based
on modprobe/rmmod might well encounter external OOM events, which could
happen at any time.

This commit therefore properly synchronizes the interaction between
rcutorture's forward-progress testing and its OOM notifier by adding a
global mutex.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The conversion of rcu_fwds to dynamic allocation failed to actually
allocate the required structure.  This commit therefore allocates it,
frees it, and updates rcu_fwds accordingly.  While in the area, it
abstracts the cleanup actions into rcu_torture_fwd_prog_cleanup().

Fixes: 5155be99 ("rcutorture: Dynamically allocate rcu_fwds structure")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds a --help argument (along with its synonym -h) to display
the help text.  While in the area, this commit also updates the help text.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently, the CONFIG_PROVE_RCU_LIST=y case is untested.  This commit
therefore adds CONFIG_PROVE_RCU_LIST=y to rcutorture's TREE05 scenario.

Cc: Madhuparna Bhowmik <madhuparnabhowmik10@gmail.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The rcu-test-image.txt documentation covers a very uncommon case where
a real userspace environment is required.  However, someone reading this
document might reasonably conclude that this is in fact a prerequisite.
In addition, the initrd.txt file mentions dracut, which is no longer used.
This commit therefore provides the needed updates.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Rationale:
Reduces attack surface on kernel devs opening the links for MITM
as HTTPS traffic is much harder to manipulate.

Deterministic algorithm:
For each file:
  If not .svg:
    For each line:
      If doesn't contain `\bxmlns\b`:
        For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`:
	  If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`:
            If both the HTTP and HTTPS versions
            return 200 OK and serve the same content:
              Replace HTTP with HTTPS.
Signed-off-by: Alexander A. Klimov <grandmaster@al2klimov.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The sparse tool complains as follows:

kernel/locking/locktorture.c:569:6: warning:
 symbol 'torture_percpu_rwsem_init' was not declared. Should it be static?

And this function is not used outside of locktorture.c,
so this commit marks it static.
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds code to print the grace-period number at the start
of the test along with both the grace-period number and the number of
elapsed grace periods at the end of the test.  Note that variants of
RCU)without the notion of a grace-period number (for example, Tiny RCU)
just print zeroes.

[ paulmck: Adjust commit log. ]
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

KCSAN is now in mainline, so this commit removes the stubs for the
data_race(), ASSERT_EXCLUSIVE_WRITER(), and ASSERT_EXCLUSIVE_ACCESS()
macros.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit further avoids conflation of rcuperf with the kernel's perf
feature by renaming kernel/rcu/rcuperf.c to kernel/rcu/rcuscale.c, and
also by similarly renaming the functions and variables inside this file.
This has the side effect of changing the names of the kernel boot
parameters, so kernel-parameters.txt and ver_functions.sh are also
updated.  The rcutorture --torture type was also updated from rcuperf
to rcuscale.

[ paulmck: Fix bugs located by Stephen Rothwell. ]
Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Although the test loop does randomly delay, which would provide quiescent
states and so forth, it is possible for there to be a series of long
smp_call_function*() handler runtimes with no delays, which results in
softlockup and RCU CPU stall warning messages.  This commit therefore
inserts a cond_resched() into the main test loop.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

On uniprocessor systems, smp_call_function() does nothing.  This commit
therefore avoids complaining about the lack of handler accesses in the
single-CPU case where there is no handler.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently, CPU-hotplug operations might result in all but two
of (say) 100 CPUs being offline, which in turn might result in
false-positive diagnostics due to overload.  This commit therefore
causes scftorture_invoker() kthreads for offline CPUs to loop blocking
for 200 milliseconds at a time, thus continuously adjusting the number
of threads to match the number of online CPUs.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds a "default" case to the switch statement in
scftorture_invoke_one() which contains a WARN_ON_ONCE() and an assignment
to ->scfc_out to suppress knock-on warnings.  These knock-on warnings
could otherwise cause the user to think that there was a memory-ordering
problem in smp_call_function() instead of a bug in scftorture.c itself.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The sparse tool complains as follows

kernel/scftorture.c:124:1: warning:
 symbol '__pcpu_scope_scf_torture_rand' was not declared. Should it be static?

And this per-CPU variable is not used outside of scftorture.c,
so this commit marks it static.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Detecting smp_call_function() memory misordering requires close timing,
so it is necessary to have the checks immediately before and after
the call to the smp_call_function*() function under test.  This commit
therefore inserts barrier() calls to prevent the compiler from optimizing
memory-misordering detection down into the zone of extreme improbability.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit prints error counts on the statistics line and also adds a
"!!!" if any of the counters are non-zero.  Allocation failures are
(somewhat) forgiven, but all other errors result in a "FAILURE" print
at the end of the test.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit hoists much of the initialization of the scf_check
structure out of the switch statement, thus saving a few lines of code.
The initialization of the ->scfc_in field remains in each leg of the
switch statement in order to more heavily stress memory ordering.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit moves checking of the ->scfc_out field and the freeing of
the scf_check structure down below the end of switch statement, thus
saving a few lines of code.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds checks for memory misordering across calls to and
returns from smp_call_function() in the case where the caller waits.
Misordering results in a splat.

Note that in contrast to smp_call_function_single(), this code does not
test memory ordering into the handler in the no-wait case because none
of the handlers would be able to free the scf_check structure without
introducing heavy synchronization to work out which was last.

[ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds checks for memory misordering across calls to and
returns from smp_call_function_many() in the case where the caller waits.
Misordering results in a splat.

Note that in contrast to smp_call_function_single(), this code does not
test memory ordering into the handler in the no-wait case because none
of the handlers would be able to free the scf_check structure without
introducing heavy synchronization to work out which was last.

[ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds checks for memory misordering across calls to
smp_call_function_single() and also across returns in the case where
the caller waits.  Misordering results in a splat.

[ paulmck: s/GFP_KERNEL/GFP_ATOMIC/ per kernel test robot feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit summarizes the per-thread statistics, providing counts of
the number of single, many, and all calls, both no-wait and wait, and,
for the single case, the number where the target CPU was offline.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently, can_stop_idle_tick() prints "NOHZ: local_softirq_pending HH"
(where "HH" is the hexadecimal softirq vector number) when one or more
non-RCU softirq handlers are still enabled when checking to stop the
scheduler-tick interrupt.  This message is not as enlightening as one
might hope, so this commit changes it to "NOHZ tick-stop error: Non-RCU
local softirq work is pending, handler #HH".
Reported-by: Andy Lutomirski <luto@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit uses the scftorture.weight* kernel parameters to randomly
chooses between smp_call_function_single(), smp_call_function_many(),
and smp_call_function().  For each variant, it also randomly chooses
whether to invoke it synchronously (wait=1) or asynchronously (wait=0).
The percentage weighting for each option are dumped to the console log
(search for "scf_sel_dump").

This accumulates statistics, which a later commit will dump out at the
end of the run.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit updates the rcutorture scripting to include the new scftorture
torture-test module.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Currently, parse-torture.sh looks at the fifth field of torture-test
console output for the version number.  This works fine for rcutorture,
but not for scftorture, which lacks the pointer field.  This commit
therefore adjusts matching lines so that the parse-console.sh awk script
always sees the version number as the first field in the lines passed
to it.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

This commit adds an smp_call_function() torture test that repeatedly
invokes this function and complains if things go badly awry.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The x86/entry work removed all uses of __rcu_is_watching(), therefore
this commit removes it entirely.

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

The RCU grace-period kthread's force-quiescent state (FQS) loop should
never see an offline CPU that has not yet reported a quiescent state.
After all, the offline CPU should have reported a quiescent state
during the CPU-offline process, or, failing that, by rcu_gp_init()
if it ran concurrently with either the CPU going offline or the last
task on a leaf rcu_node structure exiting its RCU read-side critical
section while all CPUs corresponding to that structure are offline.
The FQS loop should therefore complain if it does see an offline CPU
that has not yet reported a quiescent state.

And it does, but only once the grace period has been in force for a
full second.  This commit therefore makes this warning more aggressive,
so that it will trigger as soon as the condition makes its appearance.

Light testing with TREE03 and hotplug shows no warnings.  This commit
also converts the warning to WARN_ON_ONCE() in order to stave off possible
log spam.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Since at least v4.19, the FQS loop no longer reports quiescent states
for offline CPUs except in emergency situations.

This commit therefore fixes the comment in rcu_gp_init() to match the
current code.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>