summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst2
-rw-r--r--Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg9
-rw-r--r--Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg4
-rw-r--r--Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg13
-rw-r--r--Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg4
-rw-r--r--Documentation/RCU/Design/Requirements/Requirements.rst4
-rw-r--r--Documentation/RCU/listRCU.rst9
-rw-r--r--Documentation/RCU/whatisRCU.rst4
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt70
-rw-r--r--arch/arm64/kernel/smp.c4
-rw-r--r--arch/powerpc/kernel/smp.c2
-rw-r--r--arch/s390/kernel/smp.c2
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--include/linux/interrupt.h2
-rw-r--r--include/linux/rcu_notifier.h32
-rw-r--r--include/linux/rcupdate.h2
-rw-r--r--include/linux/rcutiny.h2
-rw-r--r--include/linux/rcutree.h17
-rw-r--r--include/linux/slab.h5
-rw-r--r--include/linux/torture.h8
-rw-r--r--kernel/cpu.c13
-rw-r--r--kernel/locking/locktorture.c214
-rw-r--r--kernel/rcu/rcu.h17
-rw-r--r--kernel/rcu/rcu_segcblist.c4
-rw-r--r--kernel/rcu/rcutorture.c37
-rw-r--r--kernel/rcu/refscale.c6
-rw-r--r--kernel/rcu/srcutiny.c1
-rw-r--r--kernel/rcu/srcutree.c74
-rw-r--r--kernel/rcu/tasks.h11
-rw-r--r--kernel/rcu/tiny.c1
-rw-r--r--kernel/rcu/tree.c242
-rw-r--r--kernel/rcu/tree.h4
-rw-r--r--kernel/rcu/tree_exp.h6
-rw-r--r--kernel/rcu/tree_stall.h135
-rw-r--r--kernel/rcu/update.c9
-rw-r--r--kernel/torture.c75
-rw-r--r--mm/slab_common.c41
-rw-r--r--mm/util.c4
-rwxr-xr-xscripts/checkpatch.pl9
-rwxr-xr-x[-rw-r--r--]tools/testing/selftests/rcutorture/bin/functions.sh29
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh17
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh9
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/torture.sh2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE021
45 files changed, 809 insertions, 351 deletions
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
index 93d899d53258..414f8a2012d6 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
@@ -181,7 +181,7 @@ operations is carried out at several levels:
of this wait (or series of waits, as the case may be) is to permit a
concurrent CPU-hotplug operation to complete.
#. In the case of RCU-sched, one of the last acts of an outgoing CPU is
- to invoke ``rcu_report_dead()``, which reports a quiescent state for
+ to invoke ``rcutree_report_cpu_dead()``, which reports a quiescent state for
that CPU. However, this is likely paranoia-induced redundancy.
+-----------------------------------------------------------------------+
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg
index 7ac6f9269806..63eff867175a 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-callback-registry.svg
@@ -566,15 +566,6 @@
style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_migrate_callbacks()</text>
<text
xml:space="preserve"
- x="8335.4873"
- y="5357.1006"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-7-9-6-0"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_migrate_callbacks()</text>
- <text
- xml:space="preserve"
x="8768.4678"
y="6224.9038"
font-style="normal"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg
index 7ddc094d7f28..d82a77d03d8c 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-fqs.svg
@@ -1135,7 +1135,7 @@
font-weight="bold"
font-size="192"
id="text202-7-5-3-27-6-5"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
<text
xml:space="preserve"
x="3745.7725"
@@ -1256,7 +1256,7 @@
font-style="normal"
y="3679.27"
x="-3804.9949"
- xml:space="preserve">rcu_cpu_starting()</text>
+ xml:space="preserve">rcutree_report_cpu_starting()</text>
<g
style="fill:none;stroke-width:0.025in"
id="g3107-7-5-0"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index 069f6f8371c2..53e0dc2a2c79 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -1448,15 +1448,6 @@
style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_migrate_callbacks()</text>
<text
xml:space="preserve"
- x="8335.4873"
- y="5357.1006"
- font-style="normal"
- font-weight="bold"
- font-size="192"
- id="text202-7-9-6-0"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_migrate_callbacks()</text>
- <text
- xml:space="preserve"
x="8768.4678"
y="6224.9038"
font-style="normal"
@@ -3274,7 +3265,7 @@
font-weight="bold"
font-size="192"
id="text202-7-5-3-27-6-5"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
<text
xml:space="preserve"
x="3745.7725"
@@ -3395,7 +3386,7 @@
font-style="normal"
y="3679.27"
x="-3804.9949"
- xml:space="preserve">rcu_cpu_starting()</text>
+ xml:space="preserve">rcutree_report_cpu_starting()</text>
<g
style="fill:none;stroke-width:0.025in"
id="g3107-7-5-0"
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg
index 2c9310ba29ba..4fa7506082bf 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-hotplug.svg
@@ -607,7 +607,7 @@
font-weight="bold"
font-size="192"
id="text202-7-5-3-27-6"
- style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_report_dead()</text>
+ style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcutree_report_cpu_dead()</text>
<text
xml:space="preserve"
x="3745.7725"
@@ -728,7 +728,7 @@
font-style="normal"
y="3679.27"
x="-3804.9949"
- xml:space="preserve">rcu_cpu_starting()</text>
+ xml:space="preserve">rcutree_report_cpu_starting()</text>
<g
style="fill:none;stroke-width:0.025in"
id="g3107-7-5-0"
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index f3b605285a87..cccafdaa1f84 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -1955,12 +1955,12 @@ if offline CPUs block an RCU grace period for too long.
An offline CPU's quiescent state will be reported either:
-1. As the CPU goes offline using RCU's hotplug notifier (rcu_report_dead()).
+1. As the CPU goes offline using RCU's hotplug notifier (rcutree_report_cpu_dead()).
2. When grace period initialization (rcu_gp_init()) detects a
race either with CPU offlining or with a task unblocking on a leaf
``rcu_node`` structure whose CPUs are all offline.
-The CPU-online path (rcu_cpu_starting()) should never need to report
+The CPU-online path (rcutree_report_cpu_starting()) should never need to report
a quiescent state for an offline CPU. However, as a debugging measure,
it does emit a warning if a quiescent state was not already reported
for that CPU.
diff --git a/Documentation/RCU/listRCU.rst b/Documentation/RCU/listRCU.rst
index bdc4bcc5289f..ed5c9d8c9afe 100644
--- a/Documentation/RCU/listRCU.rst
+++ b/Documentation/RCU/listRCU.rst
@@ -8,6 +8,15 @@ One of the most common uses of RCU is protecting read-mostly linked lists
that all of the required memory ordering is provided by the list macros.
This document describes several list-based RCU use cases.
+When iterating a list while holding the rcu_read_lock(), writers may
+modify the list. The reader is guaranteed to see all of the elements
+which were added to the list before they acquired the rcu_read_lock()
+and are still on the list when they drop the rcu_read_unlock().
+Elements which are added to, or removed from the list may or may not
+be seen. If the writer calls list_replace_rcu(), the reader may see
+either the old element or the new element; they will not see both,
+nor will they see neither.
+
Example 1: Read-mostly list: Deferred Destruction
-------------------------------------------------
diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst
index e488c8e557a9..60ce02475142 100644
--- a/Documentation/RCU/whatisRCU.rst
+++ b/Documentation/RCU/whatisRCU.rst
@@ -59,8 +59,8 @@ experiment with should focus on Section 2. People who prefer to start
with example uses should focus on Sections 3 and 4. People who need to
understand the RCU implementation should focus on Section 5, then dive
into the kernel source code. People who reason best by analogy should
-focus on Section 6. Section 7 serves as an index to the docbook API
-documentation, and Section 8 is the traditional answer key.
+focus on Section 6 and 7. Section 8 serves as an index to the docbook
+API documentation, and Section 9 is the traditional answer key.
So, start with the section that makes the most sense to you and your
preferred method of learning. If you need to know everything about
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 582f7a395153..dca212b6adfb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2919,6 +2919,38 @@
to extract confidential information from the kernel
are also disabled.
+ locktorture.acq_writer_lim= [KNL]
+ Set the time limit in jiffies for a lock
+ acquisition. Acquisitions exceeding this limit
+ will result in a splat once they do complete.
+
+ locktorture.bind_readers= [KNL]
+ Specify the list of CPUs to which the readers are
+ to be bound.
+
+ locktorture.bind_writers= [KNL]
+ Specify the list of CPUs to which the writers are
+ to be bound.
+
+ locktorture.call_rcu_chains= [KNL]
+ Specify the number of self-propagating call_rcu()
+ chains to set up. These are used to ensure that
+ there is a high probability of an RCU grace period
+ in progress at any given time. Defaults to 0,
+ which disables these call_rcu() chains.
+
+ locktorture.long_hold= [KNL]
+ Specify the duration in milliseconds for the
+ occasional long-duration lock hold time. Defaults
+ to 100 milliseconds. Select 0 to disable.
+
+ locktorture.nested_locks= [KNL]
+ Specify the maximum lock nesting depth that
+ locktorture is to exercise, up to a limit of 8
+ (MAX_NESTED_LOCKS). Specify zero to disable.
+ Note that this parameter is ineffective on types
+ of locks that do not support nested acquisition.
+
locktorture.nreaders_stress= [KNL]
Set the number of locking read-acquisition kthreads.
Defaults to being automatically set based on the
@@ -2934,6 +2966,25 @@
Set time (s) between CPU-hotplug operations, or
zero to disable CPU-hotplug testing.
+ locktorture.rt_boost= [KNL]
+ Do periodic testing of real-time lock priority
+ boosting. Select 0 to disable, 1 to boost
+ only rt_mutex, and 2 to boost unconditionally.
+ Defaults to 2, which might seem to be an
+ odd choice, but which should be harmless for
+ non-real-time spinlocks, due to their disabling
+ of preemption. Note that non-realtime mutexes
+ disable boosting.
+
+ locktorture.rt_boost_factor= [KNL]
+ Number that determines how often and for how
+ long priority boosting is exercised. This is
+ scaled down by the number of writers, so that the
+ number of boosts per unit time remains roughly
+ constant as the number of writers increases.
+ On the other hand, the duration of each boost
+ increases with the number of writers.
+
locktorture.shuffle_interval= [KNL]
Set task-shuffle interval (jiffies). Shuffling
tasks allows some CPUs to go into dyntick-idle
@@ -2956,13 +3007,13 @@
locktorture.torture_type= [KNL]
Specify the locking implementation to test.
+ locktorture.verbose= [KNL]
+ Enable additional printk() statements.
+
locktorture.writer_fifo= [KNL]
Run the write-side locktorture kthreads at
sched_set_fifo() real-time priority.
- locktorture.verbose= [KNL]
- Enable additional printk() statements.
-
logibm.irq= [HW,MOUSE] Logitech Bus Mouse Driver
Format: <irq>
@@ -4775,6 +4826,13 @@
Set maximum number of finished RCU callbacks to
process in one batch.
+ rcutree.do_rcu_barrier= [KNL]
+ Request a call to rcu_barrier(). This is
+ throttled so that userspace tests can safely
+ hammer on the sysfs variable if they so choose.
+ If triggered before the RCU grace-period machinery
+ is fully active, this will error out with EAGAIN.
+
rcutree.dump_tree= [KNL]
Dump the structure of the rcu_node combining tree
out at early boot. This is used for diagnostic
@@ -5428,6 +5486,12 @@
test until boot completes in order to avoid
interference.
+ refscale.lookup_instances= [KNL]
+ Number of data elements to use for the forms of
+ SLAB_TYPESAFE_BY_RCU testing. A negative number
+ is negated and multiplied by nr_cpu_ids, while
+ zero specifies nr_cpu_ids.
+
refscale.loops= [KNL]
Set the number of loops over the synchronization
primitive under test. Increasing this number
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 960b98b43506..196533c362e1 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -215,7 +215,7 @@ asmlinkage notrace void secondary_start_kernel(void)
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
trace_hardirqs_off();
/*
@@ -401,7 +401,7 @@ void __noreturn cpu_die_early(void)
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
- rcu_report_dead(cpu);
+ rcutree_report_cpu_dead();
if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
update_cpu_boot_status(CPU_KILL_ME);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 4e4870031265..ab691c89d787 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1629,7 +1629,7 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a4edb7ea66ea..214a1b67f80a 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -898,7 +898,7 @@ static void smp_start_secondary(void *cpuvoid)
S390_lowcore.restart_flags = 0;
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
init_cpu_timer();
vtime_init();
vdso_getcpu_init();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5468399c5823..c4aca66f0902 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -302,7 +302,7 @@ static void notrace start_secondary(void *unused)
cpu_init();
fpu__init_cpu();
- rcu_cpu_starting(raw_smp_processor_id());
+ rcutree_report_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
ap_starting();
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 4a1dc88ddbff..76121c2bb4f8 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -566,7 +566,7 @@ enum
*
* _ RCU:
* 1) rcutree_migrate_callbacks() migrates the queue.
- * 2) rcu_report_dead() reports the final quiescent states.
+ * 2) rcutree_report_cpu_dead() reports the final quiescent states.
*
* _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue
*
diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h
new file mode 100644
index 000000000000..ebf371364581
--- /dev/null
+++ b/include/linux/rcu_notifier.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Read-Copy Update notifiers, initially RCU CPU stall notifier.
+ * Separate from rcupdate.h to avoid #include loops.
+ *
+ * Copyright (C) 2023 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_RCU_NOTIFIER_H
+#define __LINUX_RCU_NOTIFIER_H
+
+// Actions for RCU CPU stall notifier calls.
+#define RCU_STALL_NOTIFY_NORM 1
+#define RCU_STALL_NOTIFY_EXP 2
+
+#ifdef CONFIG_RCU_STALL_COMMON
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+int rcu_stall_chain_notifier_register(struct notifier_block *n);
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n);
+
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+
+// No RCU CPU stall warnings in Tiny RCU.
+static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }
+static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }
+
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
+#endif /* __LINUX_RCU_NOTIFIER_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5e5f920ade90..f7206b2623c9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -122,8 +122,6 @@ static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
void rcu_init(void);
extern int rcu_scheduler_active;
void rcu_sched_clock_irq(int user);
-void rcu_report_dead(unsigned int cpu);
-void rcutree_migrate_callbacks(int cpu);
#ifdef CONFIG_TASKS_RCU_GENERIC
void rcu_init_tasks_generic(void);
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7b949292908a..d9ac7b136aea 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -171,6 +171,6 @@ static inline void rcu_all_qs(void) { barrier(); }
#define rcutree_offline_cpu NULL
#define rcutree_dead_cpu NULL
#define rcutree_dying_cpu NULL
-static inline void rcu_cpu_starting(unsigned int cpu) { }
+static inline void rcutree_report_cpu_starting(unsigned int cpu) { }
#endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 126f6b418f6a..254244202ea9 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -37,7 +37,6 @@ void synchronize_rcu_expedited(void);
void kvfree_call_rcu(struct rcu_head *head, void *ptr);
void rcu_barrier(void);
-bool rcu_eqs_special_set(int cpu);
void rcu_momentary_dyntick_idle(void);
void kfree_rcu_scheduler_running(void);
bool rcu_gp_might_be_stalled(void);
@@ -111,9 +110,21 @@ void rcu_all_qs(void);
/* RCUtree hotplug events */
int rcutree_prepare_cpu(unsigned int cpu);
int rcutree_online_cpu(unsigned int cpu);
-int rcutree_offline_cpu(unsigned int cpu);
+void rcutree_report_cpu_starting(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
int rcutree_dead_cpu(unsigned int cpu);
int rcutree_dying_cpu(unsigned int cpu);
-void rcu_cpu_starting(unsigned int cpu);
+int rcutree_offline_cpu(unsigned int cpu);
+#else
+#define rcutree_dead_cpu NULL
+#define rcutree_dying_cpu NULL
+#define rcutree_offline_cpu NULL
+#endif
+
+void rcutree_migrate_callbacks(int cpu);
+
+/* Called from hotplug and also arm64 early secondary boot failure */
+void rcutree_report_cpu_dead(void);
#endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 8228d1276a2f..ff56ab804bf6 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -245,8 +245,9 @@ DEFINE_FREE(kfree, void *, if (_T) kfree(_T))
size_t ksize(const void *objp);
#ifdef CONFIG_PRINTK
-bool kmem_valid_obj(void *object);
-void kmem_dump_obj(void *object);
+bool kmem_dump_obj(void *object);
+#else
+static inline bool kmem_dump_obj(void *object) { return false; }
#endif
/*
diff --git a/include/linux/torture.h b/include/linux/torture.h
index bb466eec01e4..c98d0c83d117 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -81,7 +81,8 @@ static inline void torture_random_init(struct torture_random_state *trsp)
}
/* Definitions for high-resolution-timer sleeps. */
-int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp);
+int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode,
+ struct torture_random_state *trsp);
int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state *trsp);
int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state *trsp);
int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp);
@@ -120,10 +121,15 @@ void _torture_stop_kthread(char *m, struct task_struct **tp);
#define torture_stop_kthread(n, tp) \
_torture_stop_kthread("Stopping " #n " task", &(tp))
+/* Scheduler-related definitions. */
#ifdef CONFIG_PREEMPTION
#define torture_preempt_schedule() __preempt_schedule()
#else
#define torture_preempt_schedule() do { } while (0)
#endif
+#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST)
+long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
+#endif
+
#endif /* __LINUX_TORTURE_H */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 303cb0591b4b..69e92ddef5dd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1380,7 +1380,14 @@ static int takedown_cpu(unsigned int cpu)
cpuhp_bp_sync_dead(cpu);
tick_cleanup_dead_cpu(cpu);
+
+ /*
+ * Callbacks must be re-integrated right away to the RCU state machine.
+ * Otherwise an RCU callback could block a further teardown function
+ * waiting for its completion.
+ */
rcutree_migrate_callbacks(cpu);
+
return 0;
}
@@ -1396,10 +1403,10 @@ void cpuhp_report_idle_dead(void)
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
BUG_ON(st->state != CPUHP_AP_OFFLINE);
- rcu_report_dead(smp_processor_id());
+ rcutree_report_cpu_dead();
st->state = CPUHP_AP_IDLE_DEAD;
/*
- * We cannot call complete after rcu_report_dead() so we delegate it
+ * We cannot call complete after rcutree_report_cpu_dead() so we delegate it
* to an online cpu.
*/
smp_call_function_single(cpumask_first(cpu_online_mask),
@@ -1628,7 +1635,7 @@ void notify_cpu_starting(unsigned int cpu)
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
- rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
+ rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
cpumask_set_cpu(cpu, &cpus_booted_once_mask);
/*
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 270c7f80ce84..69d3cd2cfc3b 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -33,21 +33,23 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
-torture_param(int, nwriters_stress, -1, "Number of write-locking stress-test threads");
-torture_param(int, nreaders_stress, -1, "Number of read-locking stress-test threads");
+torture_param(int, acq_writer_lim, 0, "Write_acquisition time limit (jiffies).");
+torture_param(int, call_rcu_chains, 0, "Self-propagate call_rcu() chains during test (0=disable).");
torture_param(int, long_hold, 100, "Do occasional long hold of lock (ms), 0=disable");
+torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
+torture_param(int, nreaders_stress, -1, "Number of read-locking stress-test threads");
+torture_param(int, nwriters_stress, -1, "Number of write-locking stress-test threads");
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (s), 0=disable");
+torture_param(int, rt_boost, 2,
+ "Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types.");
+torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
torture_param(int, shuffle_interval, 3, "Number of jiffies between shuffles, 0=disable");
torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(int, rt_boost, 2,
- "Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types.");
-torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens.");
-torture_param(int, writer_fifo, 0, "Run writers at sched_set_fifo() priority");
torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
-torture_param(int, nested_locks, 0, "Number of nested locks (max = 8)");
+torture_param(int, writer_fifo, 0, "Run writers at sched_set_fifo() priority");
/* Going much higher trips "BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!" errors */
#define MAX_NESTED_LOCKS 8
@@ -56,6 +58,55 @@ module_param(torture_type, charp, 0444);
MODULE_PARM_DESC(torture_type,
"Type of lock to torture (spin_lock, spin_lock_irq, mutex_lock, ...)");
+static cpumask_var_t bind_readers; // Bind the readers to the specified set of CPUs.
+static cpumask_var_t bind_writers; // Bind the writers to the specified set of CPUs.
+
+// Parse a cpumask kernel parameter. If there are more users later on,
+// this might need to got to a more central location.
+static int param_set_cpumask(const char *val, const struct kernel_param *kp)
+{
+ cpumask_var_t *cm_bind = kp->arg;
+ int ret;
+ char *s;
+
+ if (!alloc_cpumask_var(cm_bind, GFP_KERNEL)) {
+ s = "Out of memory";
+ ret = -ENOMEM;
+ goto out_err;
+ }
+ ret = cpulist_parse(val, *cm_bind);
+ if (!ret)
+ return ret;
+ s = "Bad CPU range";
+out_err:
+ pr_warn("%s: %s, all CPUs set\n", kp->name, s);
+ cpumask_setall(*cm_bind);
+ return ret;
+}
+
+// Output a cpumask kernel parameter.
+static int param_get_cpumask(char *buffer, const struct kernel_param *kp)
+{
+ cpumask_var_t *cm_bind = kp->arg;
+
+ return sprintf(buffer, "%*pbl", cpumask_pr_args(*cm_bind));
+}
+
+static bool cpumask_nonempty(cpumask_var_t mask)
+{
+ return cpumask_available(mask) && !cpumask_empty(mask);
+}
+
+static const struct kernel_param_ops lt_bind_ops = {
+ .set = param_set_cpumask,
+ .get = param_get_cpumask,
+};
+
+module_param_cb(bind_readers, &lt_bind_ops, &bind_readers, 0644);
+module_param_cb(bind_writers, &lt_bind_ops, &bind_writers, 0644);
+
+long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
+
static struct task_struct *stats_task;
static struct task_struct **writer_tasks;
static struct task_struct **reader_tasks;
@@ -69,6 +120,12 @@ struct lock_stress_stats {
long n_lock_acquired;
};
+struct call_rcu_chain {
+ struct rcu_head crc_rh;
+ bool crc_stop;
+};
+struct call_rcu_chain *call_rcu_chain;
+
/* Forward reference. */
static void lock_torture_cleanup(void);
@@ -116,12 +173,9 @@ static int torture_lock_busted_write_lock(int tid __maybe_unused)
static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -194,15 +248,14 @@ __acquires(torture_spinlock)
static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
unsigned long j;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * longdelay_ms))) {
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold))) {
j = jiffies;
- mdelay(longdelay_ms);
+ mdelay(long_hold);
pr_alert("%s: delay = %lu jiffies.\n", __func__, jiffies - j);
}
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 200 * shortdelay_us)))
@@ -320,14 +373,12 @@ __acquires(torture_rwlock)
static void torture_rwlock_write_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
else
udelay(shortdelay_us);
}
@@ -348,14 +399,12 @@ __acquires(torture_rwlock)
static void torture_rwlock_read_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 10;
- const unsigned long longdelay_ms = 100;
/* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealreaders_stress * 2000 * long_hold)))
+ mdelay(long_hold);
else
udelay(shortdelay_us);
}
@@ -453,12 +502,9 @@ __acquires(torture_mutex)
static void torture_mutex_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 5);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold * 5);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -626,15 +672,13 @@ __acquires(torture_rtmutex)
static void torture_rtmutex_delay(struct torture_random_state *trsp)
{
const unsigned long shortdelay_us = 2;
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
/*
* We want a short delay mostly to emulate likely code, and
* we want a long delay occasionally to force massive contention.
*/
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold);
if (!(torture_random(trsp) %
(cxt.nrealwriters_stress * 200 * shortdelay_us)))
udelay(shortdelay_us);
@@ -691,12 +735,9 @@ __acquires(torture_rwsem)
static void torture_rwsem_write_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = long_hold ? long_hold : ULONG_MAX;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 10);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealwriters_stress * 2000 * long_hold)))
+ mdelay(long_hold * 10);
if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -716,14 +757,11 @@ __acquires(torture_rwsem)
static void torture_rwsem_read_delay(struct torture_random_state *trsp)
{
- const unsigned long longdelay_ms = 100;
-
/* We want a long delay occasionally to force massive contention. */
- if (!(torture_random(trsp) %
- (cxt.nrealreaders_stress * 2000 * longdelay_ms)))
- mdelay(longdelay_ms * 2);
+ if (long_hold && !(torture_random(trsp) % (cxt.nrealreaders_stress * 2000 * long_hold)))
+ mdelay(long_hold * 2);
else
- mdelay(longdelay_ms / 2);
+ mdelay(long_hold / 2);
if (!(torture_random(trsp) % (cxt.nrealreaders_stress * 20000)))
torture_preempt_schedule(); /* Allow test to be preempted. */
}
@@ -803,11 +841,13 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = {
*/
static int lock_torture_writer(void *arg)
{
+ unsigned long j;
+ unsigned long j1;
+ u32 lockset_mask;
struct lock_stress_stats *lwsp = arg;
- int tid = lwsp - cxt.lwsa;
DEFINE_TORTURE_RANDOM(rand);
- u32 lockset_mask;
bool skip_main_lock;
+ int tid = lwsp - cxt.lwsa;
VERBOSE_TOROUT_STRING("lock_torture_writer task started");
if (!rt_task(current))
@@ -834,17 +874,24 @@ static int lock_torture_writer(void *arg)
cxt.cur_ops->nested_lock(tid, lockset_mask);
if (!skip_main_lock) {
+ if (acq_writer_lim > 0)
+ j = jiffies;
cxt.cur_ops->writelock(tid);
if (WARN_ON_ONCE(lock_is_write_held))
lwsp->n_lock_fail++;
lock_is_write_held = true;
if (WARN_ON_ONCE(atomic_read(&lock_is_read_held)))
lwsp->n_lock_fail++; /* rare, but... */
-
+ if (acq_writer_lim > 0) {
+ j1 = jiffies;
+ WARN_ONCE(time_after(j1, j + acq_writer_lim),
+ "%s: Lock acquisition took %lu jiffies.\n",
+ __func__, j1 - j);
+ }
lwsp->n_lock_acquired++;
- }
- if (!skip_main_lock) {
+
cxt.cur_ops->write_delay(&rand);
+
lock_is_write_held = false;
WRITE_ONCE(last_lock_release, jiffies);
cxt.cur_ops->writeunlock(tid);
@@ -986,16 +1033,69 @@ static int lock_torture_stats(void *arg)
return 0;
}
+
static inline void
lock_torture_print_module_parms(struct lock_torture_ops *cur_ops,
const char *tag)
{
+ static cpumask_t cpumask_all;
+ cpumask_t *rcmp = cpumask_nonempty(bind_readers) ? bind_readers : &cpumask_all;
+ cpumask_t *wcmp = cpumask_nonempty(bind_writers) ? bind_writers : &cpumask_all;
+
+ cpumask_setall(&cpumask_all);
pr_alert("%s" TORTURE_FLAG
- "--- %s%s: nwriters_stress=%d nreaders_stress=%d nested_locks=%d stat_interval=%d verbose=%d shuffle_interval=%d stutter=%d shutdown_secs=%d onoff_interval=%d onoff_holdoff=%d\n",
+ "--- %s%s: acq_writer_lim=%d bind_readers=%*pbl bind_writers=%*pbl call_rcu_chains=%d long_hold=%d nested_locks=%d nreaders_stress=%d nwriters_stress=%d onoff_holdoff=%d onoff_interval=%d rt_boost=%d rt_boost_factor=%d shuffle_interval=%d shutdown_secs=%d stat_interval=%d stutter=%d verbose=%d writer_fifo=%d\n",
torture_type, tag, cxt.debug_lock ? " [debug]": "",
- cxt.nrealwriters_stress, cxt.nrealreaders_stress,
- nested_locks, stat_interval, verbose, shuffle_interval,
- stutter, shutdown_secs, onoff_interval, onoff_holdoff);
+ acq_writer_lim, cpumask_pr_args(rcmp), cpumask_pr_args(wcmp),
+ call_rcu_chains, long_hold, nested_locks, cxt.nrealreaders_stress,
+ cxt.nrealwriters_stress, onoff_holdoff, onoff_interval, rt_boost,
+ rt_boost_factor, shuffle_interval, shutdown_secs, stat_interval, stutter,
+ verbose, writer_fifo);
+}
+
+// If requested, maintain call_rcu() chains to keep a grace period always
+// in flight. These increase the probability of getting an RCU CPU stall
+// warning and associated diagnostics when a locking primitive stalls.
+
+static void call_rcu_chain_cb(struct rcu_head *rhp)
+{
+ struct call_rcu_chain *crcp = container_of(rhp, struct call_rcu_chain, crc_rh);
+
+ if (!smp_load_acquire(&crcp->crc_stop)) {
+ (void)start_poll_synchronize_rcu(); // Start one grace period...
+ call_rcu(&crcp->crc_rh, call_rcu_chain_cb); // ... and later start another.
+ }
+}
+
+// Start the requested number of call_rcu() chains.
+static int call_rcu_chain_init(void)
+{
+ int i;
+
+ if (call_rcu_chains <= 0)
+ return 0;
+ call_rcu_chain = kcalloc(call_rcu_chains, sizeof(*call_rcu_chain), GFP_KERNEL);
+ if (!call_rcu_chain)
+ return -ENOMEM;
+ for (i = 0; i < call_rcu_chains; i++) {
+ call_rcu_chain[i].crc_stop = false;
+ call_rcu(&call_rcu_chain[i].crc_rh, call_rcu_chain_cb);
+ }
+ return 0;
+}
+
+// Stop all of the call_rcu() chains.
+static void call_rcu_chain_cleanup(void)
+{
+ int i;
+
+ if (!call_rcu_chain)
+ return;
+ for (i = 0; i < call_rcu_chains; i++)
+ smp_store_release(&call_rcu_chain[i].crc_stop, true);
+ rcu_barrier();
+ kfree(call_rcu_chain);
+ call_rcu_chain = NULL;
}
static void lock_torture_cleanup(void)
@@ -1048,6 +1148,8 @@ static void lock_torture_cleanup(void)
kfree(cxt.lrsa);
cxt.lrsa = NULL;
+ call_rcu_chain_cleanup();
+
end:
if (cxt.init_called) {
if (cxt.cur_ops->exit)
@@ -1177,6 +1279,10 @@ static int __init lock_torture_init(void)
}
}
+ firsterr = call_rcu_chain_init();
+ if (torture_init_error(firsterr))
+ goto unwind;
+
lock_torture_print_module_parms(cxt.cur_ops, "Start of test");
/* Prepare torture context. */
@@ -1250,6 +1356,8 @@ static int __init lock_torture_init(void)
writer_fifo ? sched_set_fifo : NULL);
if (torture_init_error(firsterr))
goto unwind;
+ if (cpumask_nonempty(bind_writers))
+ torture_sched_setaffinity(writer_tasks[i]->pid, bind_writers);
create_reader:
if (cxt.cur_ops->readlock == NULL || (j >= cxt.nrealreaders_stress))
@@ -1259,6 +1367,8 @@ static int __init lock_torture_init(void)
reader_tasks[j]);
if (torture_init_error(firsterr))
goto unwind;
+ if (cpumask_nonempty(bind_readers))
+ torture_sched_setaffinity(reader_tasks[j]->pid, bind_readers);
}
if (stat_interval > 0) {
firsterr = torture_create_kthread(lock_torture_stats, NULL,
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 98e13be411af..0d866eaa4cc8 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -10,6 +10,7 @@
#ifndef __LINUX_RCU_H
#define __LINUX_RCU_H
+#include <linux/slab.h>
#include <trace/events/rcu.h>
/*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_callback(struct rcu_head *rhp)
+{
+ if (unlikely(!rhp->func))
+ kmem_dump_obj(rhp);
+}
+
extern int rcu_cpu_stall_suppress_at_boot;
static inline bool rcu_stall_is_suppressed_at_boot(void)
@@ -568,10 +575,6 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
static inline void rcu_gp_set_torture_wait(int duration) { }
#endif
-#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
-long rcutorture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask);
-#endif
-
#ifdef CONFIG_TINY_SRCU
static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
@@ -654,4 +657,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; }
bool rcu_cpu_beenfullyonline(int cpu);
#endif
+#ifdef CONFIG_RCU_STALL_COMMON
+int rcu_stall_notifier_call_chain(unsigned long val, void *v);
+#else // #ifdef CONFIG_RCU_STALL_COMMON
+static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }
+#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON
+
#endif /* __LINUX_RCU_H */
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index f71fac422c8f..1693ea22ef1b 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -368,7 +368,7 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
- if (rsclp->tails[i] != rsclp->tails[i - 1])
+ if (!rcu_segcblist_segempty(rsclp, i))
break;
rcu_segcblist_inc_seglen(rsclp, i);
WRITE_ONCE(*rsclp->tails[i], rhp);
@@ -551,7 +551,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
* as their ->gp_seq[] grace-period completion sequence number.
*/
for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
- if (rsclp->tails[i] != rsclp->tails[i - 1] &&
+ if (!rcu_segcblist_segempty(rsclp, i) &&
ULONG_CMP_LT(rsclp->gp_seq[i], seq))
break;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index ade42d6a9d9b..30fc9d34e329 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -21,6 +21,7 @@
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate_wait.h>
+#include <linux/rcu_notifier.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <uapi/linux/sched/types.h>
@@ -810,7 +811,7 @@ static void synchronize_rcu_trivial(void)
int cpu;
for_each_online_cpu(cpu) {
- rcutorture_sched_setaffinity(current->pid, cpumask_of(cpu));
+ torture_sched_setaffinity(current->pid, cpumask_of(cpu));
WARN_ON_ONCE(raw_smp_processor_id() != cpu);
}
}
@@ -1149,7 +1150,7 @@ static int rcu_torture_boost(void *arg)
mutex_unlock(&boost_mutex);
break;
}
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
}
/* Go do the stutter. */
@@ -1160,7 +1161,7 @@ checkwait: if (stutter_wait("rcu_torture_boost"))
/* Clean up and exit. */
while (!kthread_should_stop()) {
torture_shutdown_absorb("rcu_torture_boost");
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
}
torture_kthread_stopping("rcu_torture_boost");
return 0;
@@ -1183,7 +1184,7 @@ rcu_torture_fqs(void *arg)
fqs_resume_time = jiffies + fqs_stutter * HZ;
while (time_before(jiffies, fqs_resume_time) &&
!kthread_should_stop()) {
- schedule_timeout_interruptible(1);
+ schedule_timeout_interruptible(HZ / 20);
}
fqs_burst_remaining = fqs_duration;
while (fqs_burst_remaining > 0 &&
@@ -2126,7 +2127,7 @@ static int rcu_nocb_toggle(void *arg)
VERBOSE_TOROUT_STRING("rcu_nocb_toggle task started");
while (!rcu_inkernel_boot_has_ended())
schedule_timeout_interruptible(HZ / 10);
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
maxcpu = cpu;
WARN_ON(maxcpu < 0);
if (toggle_interval > ULONG_MAX)
@@ -2428,6 +2429,16 @@ static int rcutorture_booster_init(unsigned int cpu)
return 0;
}
+static int rcu_torture_stall_nf(struct notifier_block *nb, unsigned long v, void *ptr)
+{
+ pr_info("%s: v=%lu, duration=%lu.\n", __func__, v, (unsigned long)ptr);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block rcu_torture_stall_block = {
+ .notifier_call = rcu_torture_stall_nf,
+};
+
/*
* CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then
* induces a CPU stall for the time specified by stall_cpu.
@@ -2435,9 +2446,14 @@ static int rcutorture_booster_init(unsigned int cpu)
static int rcu_torture_stall(void *args)
{
int idx;
+ int ret;
unsigned long stop_at;
VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
+ ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);
+ if (ret)
+ pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",
+ __func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");
if (stall_cpu_holdoff > 0) {
VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");
schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2481,6 +2497,11 @@ static int rcu_torture_stall(void *args)
cur_ops->readunlock(idx);
}
pr_alert("%s end.\n", __func__);
+ if (!ret) {
+ ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);
+ if (ret)
+ pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);
+ }
torture_shutdown_absorb("rcu_torture_stall");
while (!kthread_should_stop())
schedule_timeout_interruptible(10 * HZ);
@@ -2899,7 +2920,7 @@ static int rcu_torture_fwd_prog(void *args)
WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1);
} else {
while (READ_ONCE(rcu_fwd_seq) == oldseq && !torture_must_stop())
- schedule_timeout_interruptible(1);
+ schedule_timeout_interruptible(HZ / 20);
oldseq = READ_ONCE(rcu_fwd_seq);
}
pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
@@ -3200,7 +3221,7 @@ static int rcu_torture_read_exit_child(void *trsp_in)
set_user_nice(current, MAX_NICE);
// Minimize time between reading and exiting.
while (!kthread_should_stop())
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
(void)rcu_torture_one_read(trsp, -1);
return 0;
}
@@ -3248,7 +3269,7 @@ static int rcu_torture_read_exit(void *unused)
smp_mb(); // Store before wakeup.
wake_up(&read_exit_wq);
while (!torture_must_stop())
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_uninterruptible(HZ / 20);
torture_kthread_stopping("rcu_torture_read_exit");
return 0;
}
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 91a0fd0d4d9a..2c2648a3ad30 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -655,12 +655,12 @@ retry:
goto retry;
}
un_delay(udl, ndl);
+ b = READ_ONCE(rtsp->a);
// Remember, seqlock read-side release can fail.
if (!rts_release(rtsp, start)) {
rcu_read_unlock();
goto retry;
}
- b = READ_ONCE(rtsp->a);
WARN_ONCE(a != b, "Re-read of ->a changed from %u to %u.\n", a, b);
b = rtsp->b;
rcu_read_unlock();
@@ -1025,8 +1025,8 @@ static void
ref_scale_print_module_parms(struct ref_scale_ops *cur_ops, const char *tag)
{
pr_alert("%s" SCALE_FLAG
- "--- %s: verbose=%d shutdown=%d holdoff=%d loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
- verbose, shutdown, holdoff, loops, nreaders, nruns, readdelay);
+ "--- %s: verbose=%d verbose_batched=%d shutdown=%d holdoff=%d lookup_instances=%ld loops=%ld nreaders=%d nruns=%d readdelay=%d\n", scale_type, tag,
+ verbose, verbose_batched, shutdown, holdoff, lookup_instances, loops, nreaders, nruns, readdelay);
}
static void
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 336af24e0fe3..c38e5933a5d6 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)
while (lh) {
rhp = lh;
lh = lh->next;
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 20d7a238d675..560e99ec5333 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags)
snp->grplo = cpu;
snp->grphi = cpu;
}
- sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+ sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo);
}
smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER);
return true;
@@ -255,29 +255,31 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
ssp->srcu_sup->sda_is_static = is_static;
if (!is_static)
ssp->sda = alloc_percpu(struct srcu_data);
- if (!ssp->sda) {
- if (!is_static)
- kfree(ssp->srcu_sup);
- return -ENOMEM;
- }
+ if (!ssp->sda)
+ goto err_free_sup;
init_srcu_struct_data(ssp);
ssp->srcu_sup->srcu_gp_seq_needed_exp = 0;
ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns();
if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) {
- if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) {
- if (!ssp->srcu_sup->sda_is_static) {
- free_percpu(ssp->sda);
- ssp->sda = NULL;
- kfree(ssp->srcu_sup);
- return -ENOMEM;
- }
- } else {
- WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
- }
+ if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC))
+ goto err_free_sda;
+ WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG);
}
ssp->srcu_sup->srcu_ssp = ssp;
smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */
return 0;
+
+err_free_sda:
+ if (!is_static) {
+ free_percpu(ssp->sda);
+ ssp->sda = NULL;
+ }
+err_free_sup:
+ if (!is_static) {
+ kfree(ssp->srcu_sup);
+ ssp->srcu_sup = NULL;
+ }
+ return -ENOMEM;
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -782,8 +784,7 @@ static void srcu_gp_start(struct srcu_struct *ssp)
spin_lock_rcu_node(sdp); /* Interrupts already disabled. */
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
+ WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */
WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies);
WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0);
@@ -833,7 +834,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp
int cpu;
for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
- if (!(mask & (1 << (cpu - snp->grplo))))
+ if (!(mask & (1UL << (cpu - snp->grplo))))
continue;
srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay);
}
@@ -1242,10 +1243,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
spin_lock_irqsave_sdp_contention(sdp, &flags);
if (rhp)
rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
+ /*
+ * The snapshot for acceleration must be taken _before_ the read of the
+ * current gp sequence used for advancing, otherwise advancing may fail
+ * and acceleration may then fail too.
+ *
+ * This could happen if:
+ *
+ * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the
+ * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8).
+ *
+ * 2) The grace period for RCU_WAIT_TAIL is seen as started but not
+ * completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1.
+ *
+ * 3) This value is passed to rcu_segcblist_advance() which can't move
+ * any segment forward and fails.
+ *
+ * 4) srcu_gp_start_if_needed() still proceeds with callback acceleration.
+ * But then the call to rcu_seq_snap() observes the grace period for the
+ * RCU_WAIT_TAIL segment as completed and the subsequent one for the
+ * RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1)
+ * so it returns a snapshot of the next grace period, which is X + 12.
+ *
+ * 5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the
+ * freshly enqueued callback in RCU_NEXT_TAIL can't move to
+ * RCU_NEXT_READY_TAIL which already has callbacks for a previous grace
+ * period (gp_num = X + 8). So acceleration fails.
+ */
+ s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
- s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq);
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+ WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp);
if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
sdp->srcu_gp_seq_needed = s;
needgp = true;
@@ -1692,6 +1720,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
ssp = sdp->ssp;
rcu_cblist_init(&ready_cbs);
spin_lock_irq_rcu_node(sdp);
+ WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL));
rcu_segcblist_advance(&sdp->srcu_cblist,
rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq));
if (sdp->srcu_cblist_invoking ||
@@ -1708,6 +1737,7 @@ static void srcu_invoke_callbacks(struct work_struct *work)
rhp = rcu_cblist_dequeue(&ready_cbs);
for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
debug_rcu_head_unqueue(rhp);
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
@@ -1720,8 +1750,6 @@ static void srcu_invoke_callbacks(struct work_struct *work)
*/
spin_lock_irq_rcu_node(sdp);
rcu_segcblist_add_len(&sdp->srcu_cblist, -len);
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
- rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq));
sdp->srcu_cblist_invoking = false;
more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
spin_unlock_irq_rcu_node(sdp);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 8d65f7d576a3..1fa631168594 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -432,6 +432,7 @@ static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp)
static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
{
int cpu;
+ int dequeue_limit;
unsigned long flags;
bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq);
long n;
@@ -439,7 +440,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
long ncbsnz = 0;
int needgpcb = 0;
- for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) {
+ dequeue_limit = smp_load_acquire(&rtp->percpu_dequeue_lim);
+ for (cpu = 0; cpu < dequeue_limit; cpu++) {
struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
/* Advance and accelerate any new callbacks. */
@@ -538,6 +540,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu
raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
len = rcl.len;
for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ debug_rcu_head_callback(rhp);
local_bh_disable();
rhp->func(rhp);
local_bh_enable();
@@ -1084,7 +1087,7 @@ void rcu_barrier_tasks(void)
}
EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
-int rcu_tasks_lazy_ms = -1;
+static int rcu_tasks_lazy_ms = -1;
module_param(rcu_tasks_lazy_ms, int, 0444);
static int __init rcu_spawn_tasks_kthread(void)
@@ -1979,20 +1982,22 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp)
static void rcu_tasks_initiate_self_tests(void)
{
- pr_info("Running RCU-tasks wait API self tests\n");
#ifdef CONFIG_TASKS_RCU
+ pr_info("Running RCU Tasks wait API self tests\n");
tests[0].runstart = jiffies;
synchronize_rcu_tasks();
call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_RUDE_RCU
+ pr_info("Running RCU Tasks Rude wait API self tests\n");
tests[1].runstart = jiffies;
synchronize_rcu_tasks_rude();
call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
#endif
#ifdef CONFIG_TASKS_TRACE_RCU
+ pr_info("Running RCU Tasks Trace wait API self tests\n");
tests[2].runstart = jiffies;
synchronize_rcu_tasks_trace();
call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 42f7589e51e0..fec804b79080 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)
trace_rcu_invoke_callback("", head);
f = head->func;
+ debug_rcu_head_callback(head);
WRITE_ONCE(head->func, (rcu_callback_t)0L);
f(head);
rcu_lock_release(&rcu_callback_map);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb1caefa8bd0..700524726079 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -31,6 +31,7 @@
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/completion.h>
+#include <linux/kmemleak.h>
#include <linux/moduleparam.h>
#include <linux/panic.h>
#include <linux/panic_notifier.h>
@@ -1260,7 +1261,7 @@ EXPORT_SYMBOL_GPL(rcu_gp_slow_register);
/* Unregister a counter, with NULL for not caring which. */
void rcu_gp_slow_unregister(atomic_t *rgssp)
{
- WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress);
+ WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress && rcu_gp_slow_suppress != NULL);
WRITE_ONCE(rcu_gp_slow_suppress, NULL);
}
@@ -1556,10 +1557,22 @@ static bool rcu_gp_fqs_check_wake(int *gfp)
*/
static void rcu_gp_fqs(bool first_time)
{
+ int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall);
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
+
+ WARN_ON_ONCE(nr_fqs > 3);
+ /* Only countdown nr_fqs for stall purposes if jiffies moves. */
+ if (nr_fqs) {
+ if (nr_fqs == 1) {
+ WRITE_ONCE(rcu_state.jiffies_stall,
+ jiffies + rcu_jiffies_till_stall_check());
+ }
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs);
+ }
+
if (first_time) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(dyntick_save_progress_counter);
@@ -2135,6 +2148,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
trace_rcu_invoke_callback(rcu_state.name, rhp);
f = rhp->func;
+ debug_rcu_head_callback(rhp);
WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
f(rhp);
@@ -2713,7 +2727,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
*/
void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
{
- return __call_rcu_common(head, func, false);
+ __call_rcu_common(head, func, false);
}
EXPORT_SYMBOL_GPL(call_rcu_hurry);
#endif
@@ -2764,7 +2778,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry);
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
- return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+ __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
}
EXPORT_SYMBOL_GPL(call_rcu);
@@ -3388,6 +3402,14 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
success = true;
}
+ /*
+ * The kvfree_rcu() caller considers the pointer freed at this point
+ * and likely removes any references to it. Since the actual slab
+ * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore
+ * this object (no scanning or false positives reporting).
+ */
+ kmemleak_ignore(ptr);
+
// Set timer to drain after KFREE_DRAIN_JIFFIES.
if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING)
schedule_delayed_monitor_work(krcp);
@@ -4083,6 +4105,82 @@ retry:
}
EXPORT_SYMBOL_GPL(rcu_barrier);
+static unsigned long rcu_barrier_last_throttle;
+
+/**
+ * rcu_barrier_throttled - Do rcu_barrier(), but limit to one per second
+ *
+ * This can be thought of as guard rails around rcu_barrier() that
+ * permits unrestricted userspace use, at least assuming the hardware's
+ * try_cmpxchg() is robust. There will be at most one call per second to
+ * rcu_barrier() system-wide from use of this function, which means that
+ * callers might needlessly wait a second or three.
+ *
+ * This is intended for use by test suites to avoid OOM by flushing RCU
+ * callbacks from the previous test before starting the next. See the
+ * rcutree.do_rcu_barrier module parameter for more information.
+ *
+ * Why not simply make rcu_barrier() more scalable? That might be
+ * the eventual endpoint, but let's keep it simple for the time being.
+ * Note that the module parameter infrastructure serializes calls to a
+ * given .set() function, but should concurrent .set() invocation ever be
+ * possible, we are ready!
+ */
+static void rcu_barrier_throttled(void)
+{
+ unsigned long j = jiffies;
+ unsigned long old = READ_ONCE(rcu_barrier_last_throttle);
+ unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
+
+ while (time_in_range(j, old, old + HZ / 16) ||
+ !try_cmpxchg(&rcu_barrier_last_throttle, &old, j)) {
+ schedule_timeout_idle(HZ / 16);
+ if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
+ smp_mb(); /* caller's subsequent code after above check. */
+ return;
+ }
+ j = jiffies;
+ old = READ_ONCE(rcu_barrier_last_throttle);
+ }
+ rcu_barrier();
+}
+
+/*
+ * Invoke rcu_barrier_throttled() when a rcutree.do_rcu_barrier
+ * request arrives. We insist on a true value to allow for possible
+ * future expansion.
+ */
+static int param_set_do_rcu_barrier(const char *val, const struct kernel_param *kp)
+{
+ bool b;
+ int ret;
+
+ if (rcu_scheduler_active != RCU_SCHEDULER_RUNNING)
+ return -EAGAIN;
+ ret = kstrtobool(val, &b);
+ if (!ret && b) {
+ atomic_inc((atomic_t *)kp->arg);
+ rcu_barrier_throttled();
+ atomic_dec((atomic_t *)kp->arg);
+ }
+ return ret;
+}
+
+/*
+ * Output the number of outstanding rcutree.do_rcu_barrier requests.
+ */
+static int param_get_do_rcu_barrier(char *buffer, const struct kernel_param *kp)
+{
+ return sprintf(buffer, "%d\n", atomic_read((atomic_t *)kp->arg));
+}
+
+static const struct kernel_param_ops do_rcu_barrier_ops = {
+ .set = param_set_do_rcu_barrier,
+ .get = param_get_do_rcu_barrier,
+};
+static atomic_t do_rcu_barrier;
+module_param_cb(do_rcu_barrier, &do_rcu_barrier_ops, &do_rcu_barrier, 0644);
+
/*
* Compute the mask of online CPUs for the specified rcu_node structure.
* This will not be stable unless the rcu_node structure's ->lock is
@@ -4130,7 +4228,7 @@ bool rcu_lockdep_current_cpu_online(void)
rdp = this_cpu_ptr(&rcu_data);
/*
* Strictly, we care here about the case where the current CPU is
- * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask
+ * in rcutree_report_cpu_starting() and thus has an excuse for rdp->grpmask
* not being up to date. So arch_spin_is_locked() might have a
* false positive if it's held by some *other* CPU, but that's
* OK because that just means a false *negative* on the warning.
@@ -4152,25 +4250,6 @@ static bool rcu_init_invoked(void)
}
/*
- * Near the end of the offline process. Trace the fact that this CPU
- * is going offline.
- */
-int rcutree_dying_cpu(unsigned int cpu)
-{
- bool blkd;
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
- struct rcu_node *rnp = rdp->mynode;
-
- if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return 0;
-
- blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
- trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
- blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
- return 0;
-}
-
-/*
* All CPUs for the specified rcu_node structure have gone offline,
* and all tasks that were preempted within an RCU read-side critical
* section while running on one of those CPUs have since exited their RCU
@@ -4216,23 +4295,6 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
}
/*
- * The CPU has been completely removed, and some other CPU is reporting
- * this fact from process context. Do the remainder of the cleanup.
- * There can only be one CPU hotplug operation at a time, so no need for
- * explicit locking.
- */
-int rcutree_dead_cpu(unsigned int cpu)
-{
- if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
- return 0;
-
- WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
- // Stop-machine done, so allow nohz_full to disable tick.
- tick_dep_clear(TICK_DEP_BIT_RCU);
- return 0;
-}
-
-/*
* Propagate ->qsinitmask bits up the rcu_node tree to account for the
* first CPU in a given leaf rcu_node structure coming online. The caller
* must hold the corresponding leaf rcu_node ->lock with interrupts
@@ -4385,29 +4447,6 @@ int rcutree_online_cpu(unsigned int cpu)
}
/*
- * Near the beginning of the process. The CPU is still very much alive
- * with pretty much all services enabled.
- */
-int rcutree_offline_cpu(unsigned int cpu)
-{
- unsigned long flags;
- struct rcu_data *rdp;
- struct rcu_node *rnp;
-
- rdp = per_cpu_ptr(&rcu_data, cpu);
- rnp = rdp->mynode;
- raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->ffmask &= ~rdp->grpmask;
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
- rcutree_affinity_setting(cpu, cpu);
-
- // nohz_full CPUs need the tick for stop-machine to work quickly
- tick_dep_set(TICK_DEP_BIT_RCU);
- return 0;
-}
-
-/*
* Mark the specified CPU as being online so that subsequent grace periods
* (both expedited and normal) will wait on it. Note that this means that
* incoming CPUs are not allowed to use RCU read-side critical sections
@@ -4418,8 +4457,10 @@ int rcutree_offline_cpu(unsigned int cpu)
* from the incoming CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
* This incoming CPU must not have enabled interrupts yet.
+ *
+ * This mirrors the effects of rcutree_report_cpu_dead().
*/
-void rcu_cpu_starting(unsigned int cpu)
+void rcutree_report_cpu_starting(unsigned int cpu)
{
unsigned long mask;
struct rcu_data *rdp;
@@ -4473,14 +4514,21 @@ void rcu_cpu_starting(unsigned int cpu)
* Note that this function is special in that it is invoked directly
* from the outgoing CPU rather than from the cpuhp_step mechanism.
* This is because this function must be invoked at a precise location.
+ *
+ * This mirrors the effect of rcutree_report_cpu_starting().
*/
-void rcu_report_dead(unsigned int cpu)
+void rcutree_report_cpu_dead(void)
{
- unsigned long flags, seq_flags;
+ unsigned long flags;
unsigned long mask;
- struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
+ /*
+ * IRQS must be disabled from now on and until the CPU dies, or an interrupt
+ * may introduce a new READ-side while it is actually off the QS masks.
+ */
+ lockdep_assert_irqs_disabled();
// Do any dangling deferred wakeups.
do_nocb_deferred_wakeup(rdp);
@@ -4488,7 +4536,6 @@ void rcu_report_dead(unsigned int cpu)
/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
mask = rdp->grpmask;
- local_irq_save(seq_flags);
arch_spin_lock(&rcu_state.ofl_lock);
raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4502,8 +4549,6 @@ void rcu_report_dead(unsigned int cpu)
WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
arch_spin_unlock(&rcu_state.ofl_lock);
- local_irq_restore(seq_flags);
-
rdp->cpu_started = false;
}
@@ -4558,7 +4603,60 @@ void rcutree_migrate_callbacks(int cpu)
cpu, rcu_segcblist_n_cbs(&rdp->cblist),
rcu_segcblist_first_cb(&rdp->cblist));
}
-#endif
+
+/*
+ * The CPU has been completely removed, and some other CPU is reporting
+ * this fact from process context. Do the remainder of the cleanup.
+ * There can only be one CPU hotplug operation at a time, so no need for
+ * explicit locking.
+ */
+int rcutree_dead_cpu(unsigned int cpu)
+{
+ WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
+ return 0;
+}
+
+/*
+ * Near the end of the offline process. Trace the fact that this CPU
+ * is going offline.
+ */
+int rcutree_dying_cpu(unsigned int cpu)
+{
+ bool blkd;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ struct rcu_node *rnp = rdp->mynode;
+
+ blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask);
+ trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+ blkd ? TPS("cpuofl-bgp") : TPS("cpuofl"));
+ return 0;
+}
+
+/*
+ * Near the beginning of the process. The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
+int rcutree_offline_cpu(unsigned int cpu)
+{
+ unsigned long flags;
+ struct rcu_data *rdp;
+ struct rcu_node *rnp;
+
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ rnp = rdp->mynode;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rnp->ffmask &= ~rdp->grpmask;
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+ rcutree_affinity_setting(cpu, cpu);
+
+ // nohz_full CPUs need the tick for stop-machine to work quickly
+ tick_dep_set(TICK_DEP_BIT_RCU);
+ return 0;
+}
+#endif /* #ifdef CONFIG_HOTPLUG_CPU */
/*
* On non-huge systems, use expedited RCU grace periods to make suspend
@@ -4990,7 +5088,7 @@ void __init rcu_init(void)
pm_notifier(rcu_pm_notify, 0);
WARN_ON(num_online_cpus() > 1); // Only one CPU this early in boot.
rcutree_prepare_cpu(cpu);
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
rcutree_online_cpu(cpu);
/* Create workqueue for Tree SRCU and for expedited GPs. */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 192536916f9a..e9821a8422db 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -386,6 +386,10 @@ struct rcu_state {
/* in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
+ int nr_fqs_jiffies_stall; /* Number of fqs loops after
+ * which read jiffies and set
+ * jiffies_stall. Stall
+ * warnings disabled if !0. */
unsigned long jiffies_resched; /* Time at which to resched */
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8239b39d945b..6d7cea5d591f 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -621,10 +621,14 @@ static void synchronize_rcu_expedited_wait(void)
}
for (;;) {
+ unsigned long j;
+
if (synchronize_rcu_expedited_wait_once(jiffies_stall))
return;
if (rcu_stall_is_suppressed())
continue;
+ j = jiffies;
+ rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_EXP, (void *)(j - jiffies_start));
trace_rcu_stall_warning(rcu_state.name, TPS("ExpeditedStall"));
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
rcu_state.name);
@@ -647,7 +651,7 @@ static void synchronize_rcu_expedited_wait(void)
}
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
- jiffies - jiffies_start, rcu_state.expedited_sequence,
+ j - jiffies_start, rcu_state.expedited_sequence,
data_race(rnp_root->expmask),
".T"[!!data_race(rnp_root->exp_tasks)]);
if (ndetected) {
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 6f06dc12904a..ac8e86babe44 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -8,6 +8,7 @@
*/
#include <linux/kvm_para.h>
+#include <linux/rcu_notifier.h>
//////////////////////////////////////////////////////////////////////////////
//
@@ -149,12 +150,17 @@ static void panic_on_rcu_stall(void)
/**
* rcu_cpu_stall_reset - restart stall-warning timeout for current grace period
*
+ * To perform the reset request from the caller, disable stall detection until
+ * 3 fqs loops have passed. This is required to ensure a fresh jiffies is
+ * loaded. It should be safe to do from the fqs loop as enough timer
+ * interrupts and context switches should have passed.
+ *
* The caller must disable hard irqs.
*/
void rcu_cpu_stall_reset(void)
{
- WRITE_ONCE(rcu_state.jiffies_stall,
- jiffies + rcu_jiffies_till_stall_check());
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 3);
+ WRITE_ONCE(rcu_state.jiffies_stall, ULONG_MAX);
}
//////////////////////////////////////////////////////////////////////////////
@@ -170,6 +176,7 @@ static void record_gp_stall_check_time(void)
WRITE_ONCE(rcu_state.gp_start, j);
j1 = rcu_jiffies_till_stall_check();
smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+ WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 0);
WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
rcu_state.jiffies_resched = j + j1 / 2;
rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
@@ -534,16 +541,16 @@ static void rcu_check_gp_kthread_starvation(void)
data_race(READ_ONCE(rcu_state.gp_state)),
gpk ? data_race(READ_ONCE(gpk->__state)) : ~0, cpu);
if (gpk) {
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+
pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
pr_err("RCU grace-period kthread stack dump:\n");
sched_show_task(gpk);
- if (cpu >= 0) {
- if (cpu_is_offline(cpu)) {
- pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
- } else {
- pr_err("Stack dump where RCU GP kthread last ran:\n");
- dump_cpu_task(cpu);
- }
+ if (cpu_is_offline(cpu)) {
+ pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
+ } else if (!(data_race(READ_ONCE(rdp->mynode->qsmask)) & rdp->grpmask)) {
+ pr_err("Stack dump where RCU GP kthread last ran:\n");
+ dump_cpu_task(cpu);
}
wake_up_process(gpk);
}
@@ -711,7 +718,7 @@ static void print_cpu_stall(unsigned long gps)
static void check_cpu_stall(struct rcu_data *rdp)
{
- bool didstall = false;
+ bool self_detected;
unsigned long gs1;
unsigned long gs2;
unsigned long gps;
@@ -725,6 +732,16 @@ static void check_cpu_stall(struct rcu_data *rdp)
!rcu_gp_in_progress())
return;
rcu_stall_kick_kthreads();
+
+ /*
+ * Check if it was requested (via rcu_cpu_stall_reset()) that the FQS
+ * loop has to set jiffies to ensure a non-stale jiffies value. This
+ * is required to have good jiffies value after coming out of long
+ * breaks of jiffies updates. Not doing so can cause false positives.
+ */
+ if (READ_ONCE(rcu_state.nr_fqs_jiffies_stall) > 0)
+ return;
+
j = jiffies;
/*
@@ -758,10 +775,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
return; /* No stall or GP completed since entering function. */
rnp = rdp->mynode;
jn = jiffies + ULONG_MAX / 2;
+ self_detected = READ_ONCE(rnp->qsmask) & rdp->grpmask;
if (rcu_gp_in_progress() &&
- (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+ (self_detected || ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) &&
cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
/*
* If a virtual machine is stopped by the host it can look to
* the watchdog like an RCU stall. Check to see if the host
@@ -770,39 +787,28 @@ static void check_cpu_stall(struct rcu_data *rdp)
if (kvm_check_and_clear_guest_paused())
return;
- /* We haven't checked in, so go dump stack. */
- print_cpu_stall(gps);
- if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
- rcu_ftrace_dump(DUMP_ALL);
- didstall = true;
-
- } else if (rcu_gp_in_progress() &&
- ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
- cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
- /*
- * If a virtual machine is stopped by the host it can look to
- * the watchdog like an RCU stall. Check to see if the host
- * stopped the vm.
- */
- if (kvm_check_and_clear_guest_paused())
- return;
+ rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
+ if (self_detected) {
+ /* We haven't checked in, so go dump stack. */
+ print_cpu_stall(gps);
+ } else {
+ /* They had a few time units to dump stack, so complain. */
+ print_other_cpu_stall(gs2, gps);
+ }
- /* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(gs2, gps);
if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
rcu_ftrace_dump(DUMP_ALL);
- didstall = true;
- }
- if (didstall && READ_ONCE(rcu_state.jiffies_stall) == jn) {
- jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
- WRITE_ONCE(rcu_state.jiffies_stall, jn);
+
+ if (READ_ONCE(rcu_state.jiffies_stall) == jn) {
+ jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+ WRITE_ONCE(rcu_state.jiffies_stall, jn);
+ }
}
}
//////////////////////////////////////////////////////////////////////////////
//
-// RCU forward-progress mechanisms, including of callback invocation.
+// RCU forward-progress mechanisms, including for callback invocation.
/*
@@ -1054,3 +1060,58 @@ static int __init rcu_sysrq_init(void)
return 0;
}
early_initcall(rcu_sysrq_init);
+
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU CPU stall-warning notifiers
+
+static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
+
+/**
+ * rcu_stall_chain_notifier_register - Add an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Adds an RCU CPU stall notifier to an atomic notifier chain.
+ * The @action passed to a notifier will be @RCU_STALL_NOTIFY_NORM or
+ * friends. The @data will be the duration of the stalled grace period,
+ * in jiffies, coerced to a void* pointer.
+ *
+ * Returns 0 on success, %-EEXIST on error.
+ */
+int rcu_stall_chain_notifier_register(struct notifier_block *n)
+{
+ return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
+
+/**
+ * rcu_stall_chain_notifier_unregister - Remove an RCU CPU stall notifier
+ * @n: Entry to add.
+ *
+ * Removes an RCU CPU stall notifier from an atomic notifier chain.
+ *
+ * Returns zero on success, %-ENOENT on failure.
+ */
+int rcu_stall_chain_notifier_unregister(struct notifier_block *n)
+{
+ return atomic_notifier_chain_unregister(&rcu_cpu_stall_notifier_list, n);
+}
+EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_unregister);
+
+/*
+ * rcu_stall_notifier_call_chain - Call functions in an RCU CPU stall notifier chain
+ * @val: Value passed unmodified to notifier function
+ * @v: Pointer passed unmodified to notifier function
+ *
+ * Calls each function in the RCU CPU stall notifier chain in turn, which
+ * is an atomic call chain. See atomic_notifier_call_chain() for more
+ * information.
+ *
+ * This is for use within RCU, hence the omission of the extra asterisk
+ * to indicate a non-kerneldoc format header comment.
+ */
+int rcu_stall_notifier_call_chain(unsigned long val, void *v)
+{
+ return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
+}
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 19bf6fa3ee6a..c534d6806d3d 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -25,6 +25,7 @@
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
+#include <linux/torture.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/percpu.h>
@@ -524,17 +525,17 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
do { } while (0)
#endif
-#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
+#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST)
/* Get rcutorture access to sched_setaffinity(). */
-long rcutorture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
int ret;
ret = sched_setaffinity(pid, in_mask);
- WARN_ONCE(ret, "%s: sched_setaffinity() returned %d\n", __func__, ret);
+ WARN_ONCE(ret, "%s: sched_setaffinity(%d) returned %d\n", __func__, pid, ret);
return ret;
}
-EXPORT_SYMBOL_GPL(rcutorture_sched_setaffinity);
+EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
#endif
#ifdef CONFIG_RCU_STALL_COMMON
diff --git a/kernel/torture.c b/kernel/torture.c
index b28b05bbef02..c72ab2d251f4 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -87,14 +87,15 @@ EXPORT_SYMBOL_GPL(verbose_torout_sleep);
* nanosecond random fuzz. This function and its friends desynchronize
* testing from the timer wheel.
*/
-int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp)
+int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode,
+ struct torture_random_state *trsp)
{
ktime_t hto = baset_ns;
if (trsp)
hto += torture_random(trsp) % fuzzt_ns;
set_current_state(TASK_IDLE);
- return schedule_hrtimeout(&hto, HRTIMER_MODE_REL);
+ return schedule_hrtimeout(&hto, mode);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_ns);
@@ -106,7 +107,7 @@ int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state
{
ktime_t baset_ns = baset_us * NSEC_PER_USEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_us);
@@ -123,7 +124,7 @@ int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state
fuzzt_ns = (u32)~0U;
else
fuzzt_ns = fuzzt_us * NSEC_PER_USEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_ms);
@@ -136,7 +137,7 @@ int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp)
{
ktime_t baset_ns = jiffies_to_nsecs(baset_j);
- return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), trsp);
+ return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_jiffies);
@@ -153,7 +154,7 @@ int torture_hrtimeout_s(u32 baset_s, u32 fuzzt_ms, struct torture_random_state *
fuzzt_ns = (u32)~0U;
else
fuzzt_ns = fuzzt_ms * NSEC_PER_MSEC;
- return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp);
+ return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp);
}
EXPORT_SYMBOL_GPL(torture_hrtimeout_s);
@@ -520,9 +521,8 @@ static void torture_shuffle_task_unregister_all(void)
* A special case is when shuffle_idle_cpu = -1, in which case we allow
* the tasks to run on all CPUs.
*/
-static void torture_shuffle_tasks(void)
+static void torture_shuffle_tasks(struct torture_random_state *trp)
{
- DEFINE_TORTURE_RANDOM(rand);
struct shuffle_task *stp;
cpumask_setall(shuffle_tmp_mask);
@@ -543,7 +543,7 @@ static void torture_shuffle_tasks(void)
mutex_lock(&shuffle_task_mutex);
list_for_each_entry(stp, &shuffle_task_list, st_l) {
- if (!random_shuffle || torture_random(&rand) & 0x1)
+ if (!random_shuffle || torture_random(trp) & 0x1)
set_cpus_allowed_ptr(stp->st_t, shuffle_tmp_mask);
}
mutex_unlock(&shuffle_task_mutex);
@@ -562,7 +562,7 @@ static int torture_shuffle(void *arg)
VERBOSE_TOROUT_STRING("torture_shuffle task started");
do {
torture_hrtimeout_jiffies(shuffle_interval, &rand);
- torture_shuffle_tasks();
+ torture_shuffle_tasks(&rand);
torture_shutdown_absorb("torture_shuffle");
} while (!torture_must_stop());
torture_kthread_stopping("torture_shuffle");
@@ -673,7 +673,7 @@ int torture_shutdown_init(int ssecs, void (*cleanup)(void))
if (ssecs > 0) {
shutdown_time = ktime_add(ktime_get(), ktime_set(ssecs, 0));
return torture_create_kthread(torture_shutdown, NULL,
- shutdown_task);
+ shutdown_task);
}
return 0;
}
@@ -720,7 +720,7 @@ static void torture_shutdown_cleanup(void)
* suddenly applied to or removed from the system.
*/
static struct task_struct *stutter_task;
-static int stutter_pause_test;
+static ktime_t stutter_till_abs_time;
static int stutter;
static int stutter_gap;
@@ -730,30 +730,16 @@ static int stutter_gap;
*/
bool stutter_wait(const char *title)
{
- unsigned int i = 0;
bool ret = false;
- int spt;
+ ktime_t till_ns;
cond_resched_tasks_rcu_qs();
- spt = READ_ONCE(stutter_pause_test);
- for (; spt; spt = READ_ONCE(stutter_pause_test)) {
- if (!ret && !rt_task(current)) {
- sched_set_normal(current, MAX_NICE);
- ret = true;
- }
- if (spt == 1) {
- torture_hrtimeout_jiffies(1, NULL);
- } else if (spt == 2) {
- while (READ_ONCE(stutter_pause_test)) {
- if (!(i++ & 0xffff))
- torture_hrtimeout_us(10, 0, NULL);
- cond_resched();
- }
- } else {
- torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL);
- }
- torture_shutdown_absorb(title);
+ till_ns = READ_ONCE(stutter_till_abs_time);
+ if (till_ns && ktime_before(ktime_get(), till_ns)) {
+ torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL);
+ ret = true;
}
+ torture_shutdown_absorb(title);
return ret;
}
EXPORT_SYMBOL_GPL(stutter_wait);
@@ -764,23 +750,16 @@ EXPORT_SYMBOL_GPL(stutter_wait);
*/
static int torture_stutter(void *arg)
{
- DEFINE_TORTURE_RANDOM(rand);
- int wtime;
+ ktime_t till_ns;
VERBOSE_TOROUT_STRING("torture_stutter task started");
do {
if (!torture_must_stop() && stutter > 1) {
- wtime = stutter;
- if (stutter > 2) {
- WRITE_ONCE(stutter_pause_test, 1);
- wtime = stutter - 3;
- torture_hrtimeout_jiffies(wtime, &rand);
- wtime = 2;
- }
- WRITE_ONCE(stutter_pause_test, 2);
- torture_hrtimeout_jiffies(wtime, NULL);
+ till_ns = ktime_add_ns(ktime_get(),
+ jiffies_to_nsecs(stutter));
+ WRITE_ONCE(stutter_till_abs_time, till_ns);
+ torture_hrtimeout_jiffies(stutter - 1, NULL);
}
- WRITE_ONCE(stutter_pause_test, 0);
if (!torture_must_stop())
torture_hrtimeout_jiffies(stutter_gap, NULL);
torture_shutdown_absorb("torture_stutter");
@@ -812,6 +791,13 @@ static void torture_stutter_cleanup(void)
stutter_task = NULL;
}
+static void
+torture_print_module_parms(void)
+{
+ pr_alert("torture module --- %s: disable_onoff_at_boot=%d ftrace_dump_at_shutdown=%d verbose_sleep_frequency=%d verbose_sleep_duration=%d random_shuffle=%d\n",
+ torture_type, disable_onoff_at_boot, ftrace_dump_at_shutdown, verbose_sleep_frequency, verbose_sleep_duration, random_shuffle);
+}
+
/*
* Initialize torture module. Please note that this is -not- invoked via
* the usual module_init() mechanism, but rather by an explicit call from
@@ -834,6 +820,7 @@ bool torture_init_begin(char *ttype, int v)
torture_type = ttype;
verbose = v;
fullstop = FULLSTOP_DONTSTOP;
+ torture_print_module_parms();
return true;
}
EXPORT_SYMBOL_GPL(torture_init_begin);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 9bbffe82d65a..8d431193c273 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -528,26 +528,6 @@ bool slab_is_available(void)
}
#ifdef CONFIG_PRINTK
-/**
- * kmem_valid_obj - does the pointer reference a valid slab object?
- * @object: pointer to query.
- *
- * Return: %true if the pointer is to a not-yet-freed object from
- * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
- * is to an already-freed object, and %false otherwise.
- */
-bool kmem_valid_obj(void *object)
-{
- struct folio *folio;
-
- /* Some arches consider ZERO_SIZE_PTR to be a valid address. */
- if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
- return false;
- folio = virt_to_folio(object);
- return folio_test_slab(folio);
-}
-EXPORT_SYMBOL_GPL(kmem_valid_obj);
-
static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{
if (__kfence_obj_info(kpp, object, slab))
@@ -566,11 +546,11 @@ static void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *
* and, if available, the slab name, return address, and stack trace from
* the allocation and last free path of that object.
*
- * This function will splat if passed a pointer to a non-slab object.
- * If you are not sure what type of object you have, you should instead
- * use mem_dump_obj().
+ * Return: %true if the pointer is to a not-yet-freed object from
+ * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer
+ * is to an already-freed object, and %false otherwise.
*/
-void kmem_dump_obj(void *object)
+bool kmem_dump_obj(void *object)
{
char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc";
int i;
@@ -578,13 +558,13 @@ void kmem_dump_obj(void *object)
unsigned long ptroffset;
struct kmem_obj_info kp = { };
- if (WARN_ON_ONCE(!virt_addr_valid(object)))
- return;
+ /* Some arches consider ZERO_SIZE_PTR to be a valid address. */
+ if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
+ return false;
slab = virt_to_slab(object);
- if (WARN_ON_ONCE(!slab)) {
- pr_cont(" non-slab memory.\n");
- return;
- }
+ if (!slab)
+ return false;
+
kmem_obj_info(&kp, object, slab);
if (kp.kp_slab_cache)
pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name);
@@ -621,6 +601,7 @@ void kmem_dump_obj(void *object)
pr_info(" %pS\n", kp.kp_free_stack[i]);
}
+ return true;
}
EXPORT_SYMBOL_GPL(kmem_dump_obj);
#endif
diff --git a/mm/util.c b/mm/util.c
index 8cbbfd3a3d59..6eddd891198e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1060,10 +1060,8 @@ void mem_dump_obj(void *object)
{
const char *type;
- if (kmem_valid_obj(object)) {
- kmem_dump_obj(object);
+ if (kmem_dump_obj(object))
return;
- }
if (vmalloc_dump_obj(object))
return;
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 7d16f863edf1..25fdb7fda112 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6427,15 +6427,6 @@ sub process {
}
}
-# check for soon-to-be-deprecated single-argument k[v]free_rcu() API
- if ($line =~ /\bk[v]?free_rcu\s*\([^(]+\)/) {
- if ($line =~ /\bk[v]?free_rcu\s*\([^,]+\)/) {
- ERROR("DEPRECATED_API",
- "Single-argument k[v]free_rcu() API is deprecated, please pass rcu_head object or call k[v]free_rcu_mightsleep()." . $herecurr);
- }
- }
-
-
# check for unnecessary "Out of Memory" messages
if ($line =~ /^\+.*\b$logFunctions\s*\(/ &&
$prevline =~ /^[ \+]\s*if\s*\(\s*(\!\s*|NULL\s*==\s*)?($Lval)(\s*==\s*NULL\s*)?\s*\)/ &&
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index b8e2ea23cb3f..6e415ddb206f 100644..100755
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -331,3 +331,32 @@ specify_qemu_net () {
echo $1 -net none
fi
}
+
+# Extract the ftrace output from the console log output
+# The ftrace output in the original logs look like:
+# Dumping ftrace buffer:
+# ---------------------------------
+# [...]
+# ---------------------------------
+extract_ftrace_from_console() {
+ awk < "$1" '
+
+ /Dumping ftrace buffer:/ {
+ buffer_count++
+ print "Ftrace dump " buffer_count ":"
+ capture = 1
+ next
+ }
+
+ /---------------------------------/ {
+ if(capture == 1) {
+ capture = 2
+ next
+ } else if(capture == 2) {
+ capture = 0
+ print ""
+ }
+ }
+
+ capture == 2'
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 5be670dd4009..de65d77b47ff 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -13,7 +13,7 @@
#
# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
-T=/tmp/kvm-recheck.sh.$$
+T="`mktemp ${TMPDIR-/tmp}/kvm-recheck.sh.XXXXXX`"
trap 'rm -f $T' 0 2
configerrors=0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index b0f36a638a69..7af73ddc148d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -49,6 +49,7 @@ TORTURE_SHUTDOWN_GRACE=180
TORTURE_SUITE=rcu
TORTURE_MOD=rcutorture
TORTURE_TRUST_MAKE=""
+debuginfo="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y"
resdir=""
configs=""
cpus=0
@@ -68,6 +69,7 @@ usage () {
echo " --cpus N"
echo " --datestamp string"
echo " --defconfig string"
+ echo " --debug-info"
echo " --dryrun batches|scenarios|sched|script"
echo " --duration minutes | <seconds>s | <hours>h | <days>d"
echo " --gdb"
@@ -135,6 +137,15 @@ do
ds=$2
shift
;;
+ --debug-info|--debuginfo)
+ if test -z "$TORTURE_KCONFIG_KCSAN_ARG" && test -z "$TORTURE_BOOT_GDB_ARG"
+ then
+ TORTURE_KCONFIG_KCSAN_ARG="$debuginfo"; export TORTURE_KCONFIG_KCSAN_ARG
+ TORTURE_BOOT_GDB_ARG="nokaslr"; export TORTURE_BOOT_GDB_ARG
+ else
+ echo "Ignored redundant --debug-info (implied by --kcsan &c)"
+ fi
+ ;;
--defconfig)
checkarg --defconfig "defconfigtype" "$#" "$2" '^[^/][^/]*$' '^--'
TORTURE_DEFCONFIG=$2
@@ -163,7 +174,7 @@ do
shift
;;
--gdb)
- TORTURE_KCONFIG_GDB_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y"; export TORTURE_KCONFIG_GDB_ARG
+ TORTURE_KCONFIG_GDB_ARG="$debuginfo"; export TORTURE_KCONFIG_GDB_ARG
TORTURE_BOOT_GDB_ARG="nokaslr"; export TORTURE_BOOT_GDB_ARG
TORTURE_QEMU_GDB_ARG="-s -S"; export TORTURE_QEMU_GDB_ARG
;;
@@ -179,7 +190,7 @@ do
shift
;;
--kasan)
- TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+ TORTURE_KCONFIG_KASAN_ARG="$debuginfo CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
if test -n "$torture_qemu_mem_default"
then
TORTURE_QEMU_MEM=2G
@@ -191,7 +202,7 @@ do
shift
;;
--kcsan)
- TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO_NONE=n CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
+ TORTURE_KCONFIG_KCSAN_ARG="$debuginfo CONFIG_KCSAN=y CONFIG_KCSAN_STRICT=y CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG
;;
--kmake-arg|--kmake-args)
checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 9ab0f6bc172c..b07c11cf6929 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -11,7 +11,7 @@
#
# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
-T=${TMPDIR-/tmp}/parse-console.sh.$$
+T="`mktemp -d ${TMPDIR-/tmp}/parse-console.sh.XXXXXX`"
file="$1"
title="$2"
@@ -182,3 +182,10 @@ if ! test -s $file.diags
then
rm -f $file.diags
fi
+
+# Call extract_ftrace_from_console function, if the output is empty,
+# don't create $file.ftrace. Otherwise output the results to $file.ftrace
+extract_ftrace_from_console $file > $file.ftrace
+if [ ! -s $file.ftrace ]; then
+ rm -f $file.ftrace
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index 12b50a4a881a..d5a0d8a33c27 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -472,7 +472,7 @@ do
if test -n "$firsttime"
then
torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot"
- torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make
+ torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "refscale.verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make
mv $T/last-resdir-nodebug $T/first-resdir-nodebug || :
if test -f "$T/last-resdir-kasan"
then
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
index 093ea6e8e65c..9003c56cd764 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -11,3 +11,4 @@ CONFIG_FORCE_TASKS_TRACE_RCU=y
#CHECK#CONFIG_TASKS_TRACE_RCU=y
CONFIG_TASKS_TRACE_RCU_READ_MB=n
CONFIG_RCU_EXPERT=y
+CONFIG_DEBUG_OBJECTS=y