Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 7644eda..b71e21f 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -7,7 +7,7 @@
config TREE_RCU
bool
- default y if !PREEMPTION && SMP
+ default y if SMP
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
@@ -17,6 +17,7 @@
config PREEMPT_RCU
bool
default y if PREEMPTION
+ select TREE_RCU
help
This option selects the RCU implementation that is
designed for very large SMP systems with hundreds or
@@ -69,16 +70,40 @@
help
This option selects the full-fledged version of SRCU.
+config TASKS_RCU_GENERIC
+ def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
+ select SRCU
+ help
+ This option enables generic infrastructure code supporting
+ task-based RCU implementations. Not for manual selection.
+
config TASKS_RCU
def_bool PREEMPTION
- select SRCU
help
This option enables a task-based RCU implementation that uses
only voluntary context switch (not preemption!), idle, and
- user-mode execution as quiescent states.
+ user-mode execution as quiescent states. Not for manual selection.
+
+config TASKS_RUDE_RCU
+ def_bool 0
+ help
+ This option enables a task-based RCU implementation that uses
+ only context switch (including preemption) and user-mode
+ execution as quiescent states. It forces IPIs and context
+ switches on all online CPUs, including idle ones, so use
+ with caution.
+
+config TASKS_TRACE_RCU
+ def_bool 0
+ help
+ This option enables a task-based RCU implementation that uses
+ explicit rcu_read_lock_trace() read-side markers, and allows
+ these readers to appear in the idle loop as well as on the CPU
+ hotplug code paths. It can force IPIs on online CPUs, including
+ idle ones, so use with caution.
config RCU_STALL_COMMON
- def_bool ( TREE_RCU || PREEMPT_RCU )
+ def_bool TREE_RCU
help
This option enables RCU CPU stall code that is common between
the TINY and TREE variants of RCU. The purpose is to allow
@@ -86,13 +111,13 @@
making these warnings mandatory for the tree variants.
config RCU_NEED_SEGCBLIST
- def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU )
+ def_bool ( TREE_RCU || TREE_SRCU )
config RCU_FANOUT
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
- depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
+ depends on TREE_RCU && RCU_EXPERT
default 64 if 64BIT
default 32 if !64BIT
help
@@ -110,10 +135,12 @@
config RCU_FANOUT_LEAF
int "Tree-based hierarchical RCU leaf-level fanout value"
- range 2 64 if 64BIT
- range 2 32 if !64BIT
- depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
- default 16
+ range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
+ range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
+ range 2 3 if RCU_STRICT_GRACE_PERIOD
+ depends on TREE_RCU && RCU_EXPERT
+ default 16 if !RCU_STRICT_GRACE_PERIOD
+ default 2 if RCU_STRICT_GRACE_PERIOD
help
This option controls the leaf-level fanout of hierarchical
implementations of RCU, and allows trading off cache misses
@@ -187,7 +214,7 @@
config RCU_NOCB_CPU
bool "Offload RCU callback processing from boot-selected CPUs"
- depends on TREE_RCU || PREEMPT_RCU
+ depends on TREE_RCU
depends on RCU_EXPERT || NO_HZ_FULL
default n
help
@@ -200,8 +227,8 @@
specified at boot time by the rcu_nocbs parameter. For each
such CPU, a kthread ("rcuox/N") will be created to invoke
callbacks, where the "N" is the CPU being offloaded, and where
- the "p" for RCU-preempt (PREEMPT kernels) and "s" for RCU-sched
- (!PREEMPT kernels). Nothing prevents this kthread from running
+ the "p" for RCU-preempt (PREEMPTION kernels) and "s" for RCU-sched
+ (!PREEMPTION kernels). Nothing prevents this kthread from running
on the specified CPUs, but (1) the kthreads may be preempted
between each callback, and (2) affinity or cgroups can be used
to force the kthreads to run on whatever set of CPUs is desired.
@@ -209,4 +236,22 @@
Say Y here if you want to help to debug reduced OS jitter.
Say N here if you are unsure.
+config TASKS_TRACE_RCU_READ_MB
+ bool "Tasks Trace RCU readers use memory barriers in user and idle"
+ depends on RCU_EXPERT
+ default PREEMPT_RT || NR_CPUS < 8
+ help
+ Use this option to further reduce the number of IPIs sent
+ to CPUs executing in userspace or idle during tasks trace
+ RCU grace periods. Given that a reasonable setting of
+ the rcupdate.rcu_task_ipi_delay kernel boot parameter
+ eliminates such IPIs for many workloads, proper setting
+ of this Kconfig option is important mostly for aggressive
+ real-time installations and for battery-powered devices,
+ hence the default chosen above.
+
+ Say Y here if you hate IPIs.
+ Say N here if you hate read-side memory barriers.
+ Take the default if you are unsure.
+
endmenu # "RCU Subsystem"
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 4aa02ee..1942c1f 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -23,12 +23,14 @@
tristate
default n
-config RCU_PERF_TEST
+config RCU_SCALE_TEST
tristate "performance tests for RCU"
depends on DEBUG_KERNEL
select TORTURE_TEST
select SRCU
select TASKS_RCU
+ select TASKS_RUDE_RCU
+ select TASKS_TRACE_RCU
default n
help
This option provides a kernel module that runs performance
@@ -46,6 +48,8 @@
select TORTURE_TEST
select SRCU
select TASKS_RCU
+ select TASKS_RUDE_RCU
+ select TASKS_TRACE_RCU
default n
help
This option provides a kernel module that runs torture tests
@@ -57,6 +61,25 @@
Say M if you want the RCU torture tests to build as a module.
Say N if you are unsure.
+config RCU_REF_SCALE_TEST
+ tristate "Scalability tests for read-side synchronization (RCU and others)"
+ depends on DEBUG_KERNEL
+ select TORTURE_TEST
+ select SRCU
+ select TASKS_RCU
+ select TASKS_RUDE_RCU
+ select TASKS_TRACE_RCU
+ default n
+ help
+ This option provides a kernel module that runs performance tests
+ useful comparing RCU with various read-side synchronization mechanisms.
+ The kernel module may be built after the fact on the running kernel to be
+ tested, if desired.
+
+ Say Y here if you want these performance tests built into the kernel.
+ Say M if you want to build it as a module instead.
+ Say N if you are unsure.
+
config RCU_CPU_STALL_TIMEOUT
int "RCU CPU stall timeout in seconds"
depends on RCU_STALL_COMMON
@@ -91,4 +114,19 @@
Say N here if you need ultimate kernel/user switch latencies
Say Y if you are unsure
+config RCU_STRICT_GRACE_PERIOD
+ bool "Provide debug RCU implementation with short grace periods"
+ depends on DEBUG_KERNEL && RCU_EXPERT
+ default n
+ select PREEMPT_COUNT if PREEMPT=n
+ help
+ Select this option to build an RCU variant that is strict about
+ grace periods, making them as short as it can. This limits
+ scalability, destroys real-time response, degrades battery
+ lifetime and kills performance. Don't try this on large
+ machines, as in systems with more than about 10 or 20 CPUs.
+ But in conjunction with tools like KASAN, it can be helpful
+ when looking for certain types of RCU usage bugs, for example,
+ too-short RCU read-side critical sections.
+
endmenu # "RCU Debugging"
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 020e8b6..0cfb009 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -3,12 +3,16 @@
# and is generally not a function of system call inputs.
KCOV_INSTRUMENT := n
+ifeq ($(CONFIG_KCSAN),y)
+KBUILD_CFLAGS += -g -fno-omit-frame-pointer
+endif
+
obj-y += update.o sync.o
obj-$(CONFIG_TREE_SRCU) += srcutree.o
obj-$(CONFIG_TINY_SRCU) += srcutiny.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
-obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
+obj-$(CONFIG_RCU_SCALE_TEST) += rcuscale.o
+obj-$(CONFIG_RCU_REF_SCALE_TEST) += refscale.o
obj-$(CONFIG_TREE_RCU) += tree.o
-obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TINY_RCU) += tiny.o
obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7fd1c18..fcf95d1 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -167,7 +167,7 @@
# define STATE_RCU_HEAD_READY 0
# define STATE_RCU_HEAD_QUEUED 1
-extern struct debug_obj_descr rcuhead_debug_descr;
+extern const struct debug_obj_descr rcuhead_debug_descr;
static inline int debug_rcu_head_queue(struct rcu_head *head)
{
@@ -198,31 +198,11 @@
}
#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-void kfree(const void *);
+extern int rcu_cpu_stall_suppress_at_boot;
-/*
- * Reclaim the specified callback, either by invoking it (non-lazy case)
- * or freeing it directly (lazy case). Return true if lazy, false otherwise.
- */
-static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
+static inline bool rcu_stall_is_suppressed_at_boot(void)
{
- rcu_callback_t f;
- unsigned long offset = (unsigned long)head->func;
-
- rcu_lock_acquire(&rcu_callback_map);
- if (__is_kfree_rcu_offset(offset)) {
- trace_rcu_invoke_kfree_callback(rn, head, offset);
- kfree((void *)head - offset);
- rcu_lock_release(&rcu_callback_map);
- return true;
- } else {
- trace_rcu_invoke_callback(rn, head);
- f = head->func;
- WRITE_ONCE(head->func, (rcu_callback_t)0L);
- f(head);
- rcu_lock_release(&rcu_callback_map);
- return false;
- }
+ return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();
}
#ifdef CONFIG_RCU_STALL_COMMON
@@ -232,6 +212,11 @@
extern int rcu_cpu_stall_timeout;
int rcu_jiffies_till_stall_check(void);
+static inline bool rcu_stall_is_suppressed(void)
+{
+ return rcu_stall_is_suppressed_at_boot() || rcu_cpu_stall_suppress;
+}
+
#define rcu_ftrace_dump_stall_suppress() \
do { \
if (!rcu_cpu_stall_suppress) \
@@ -245,6 +230,11 @@
} while (0)
#else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
+
+static inline bool rcu_stall_is_suppressed(void)
+{
+ return rcu_stall_is_suppressed_at_boot();
+}
#define rcu_ftrace_dump_stall_suppress()
#define rcu_ftrace_dump_stall_unsuppress()
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
@@ -281,7 +271,7 @@
*/
extern void resched_cpu(int cpu);
-#if defined(SRCU) || !defined(TINY_RCU)
+#if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU)
#include <linux/rcu_node_tree.h>
@@ -299,6 +289,8 @@
{
int i;
+ for (i = 0; i < RCU_NUM_LVLS; i++)
+ levelspread[i] = INT_MIN;
if (rcu_fanout_exact) {
levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
for (i = rcu_num_lvls - 2; i >= 0; i--)
@@ -352,7 +344,8 @@
* Iterate over all possible CPUs in a leaf RCU node.
*/
#define for_each_leaf_node_possible_cpu(rnp, cpu) \
- for ((cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
+ for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+ (cpu) = cpumask_next((rnp)->grplo - 1, cpu_possible_mask); \
(cpu) <= rnp->grphi; \
(cpu) = cpumask_next((cpu), cpu_possible_mask))
@@ -362,7 +355,8 @@
#define rcu_find_next_bit(rnp, cpu, mask) \
((rnp)->grplo + find_next_bit(&(mask), BITS_PER_LONG, (cpu)))
#define for_each_leaf_node_cpu_mask(rnp, cpu, mask) \
- for ((cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
+ for (WARN_ON_ONCE(!rcu_is_leaf_node(rnp)), \
+ (cpu) = rcu_find_next_bit((rnp), 0, (mask)); \
(cpu) <= rnp->grphi; \
(cpu) = rcu_find_next_bit((rnp), (cpu) + 1 - (rnp->grplo), (mask)))
@@ -418,7 +412,7 @@
#define raw_lockdep_assert_held_rcu_node(p) \
lockdep_assert_held(&ACCESS_PRIVATE(p, lock))
-#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
+#endif /* #if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) */
#ifdef CONFIG_SRCU
void srcu_init(void);
@@ -439,6 +433,7 @@
void rcu_expedite_gp(void);
void rcu_unexpedite_gp(void);
void rcupdate_announce_bootup_oddness(void);
+void show_rcu_tasks_gp_kthreads(void);
void rcu_request_urgent_qs_task(struct task_struct *t);
#endif /* #else #ifdef CONFIG_TINY_RCU */
@@ -449,20 +444,22 @@
enum rcutorture_type {
RCU_FLAVOR,
RCU_TASKS_FLAVOR,
+ RCU_TASKS_RUDE_FLAVOR,
+ RCU_TASKS_TRACING_FLAVOR,
RCU_TRIVIAL_FLAVOR,
SRCU_FLAVOR,
INVALID_RCU_FLAVOR
};
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
+#if defined(CONFIG_TREE_RCU)
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
unsigned long *gp_seq);
-void rcutorture_record_progress(unsigned long vernum);
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old,
unsigned long c);
+void rcu_gp_set_torture_wait(int duration);
#else
static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
int *flags, unsigned long *gp_seq)
@@ -470,7 +467,6 @@
*flags = 0;
*gp_seq = 0;
}
-static inline void rcutorture_record_progress(unsigned long vernum) { }
#ifdef CONFIG_RCU_TRACE
void do_trace_rcu_torture_read(const char *rcutorturename,
struct rcu_head *rhp,
@@ -481,6 +477,7 @@
#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
do { } while (0)
#endif
+static inline void rcu_gp_set_torture_wait(int duration) { }
#endif
#if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
@@ -508,6 +505,7 @@
#endif
#ifdef CONFIG_TINY_RCU
+static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
static inline unsigned long rcu_get_gp_seq(void) { return 0; }
static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
static inline unsigned long
@@ -517,6 +515,7 @@
static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
static inline void rcu_fwd_progress_check(unsigned long j) { }
#else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
unsigned long rcu_get_gp_seq(void);
unsigned long rcu_exp_batches_completed(void);
unsigned long srcu_batches_completed(struct srcu_struct *sp);
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 495c58c..2d2a6b6 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -20,14 +20,10 @@
rclp->head = NULL;
rclp->tail = &rclp->head;
rclp->len = 0;
- rclp->len_lazy = 0;
}
/*
* Enqueue an rcu_head structure onto the specified callback list.
- * This function assumes that the callback is non-lazy because it
- * is intended for use by no-CBs CPUs, which do not distinguish
- * between lazy and non-lazy RCU callbacks.
*/
void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp)
{
@@ -54,7 +50,6 @@
else
drclp->tail = &drclp->head;
drclp->len = srclp->len;
- drclp->len_lazy = srclp->len_lazy;
if (!rhp) {
rcu_cblist_init(srclp);
} else {
@@ -62,16 +57,12 @@
srclp->head = rhp;
srclp->tail = &rhp->next;
WRITE_ONCE(srclp->len, 1);
- srclp->len_lazy = 0;
}
}
/*
* Dequeue the oldest rcu_head structure from the specified callback
- * list. This function assumes that the callback is non-lazy, but
- * the caller can later invoke rcu_cblist_dequeued_lazy() if it
- * finds otherwise (and if it cares about laziness). This allows
- * different users to have different ways of determining laziness.
+ * list.
*/
struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
{
@@ -88,7 +79,7 @@
}
/* Set the length of an rcu_segcblist structure. */
-void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v)
{
#ifdef CONFIG_RCU_NOCB_CPU
atomic_long_set(&rsclp->len, v);
@@ -104,7 +95,7 @@
* This increase is fully ordered with respect to the callers accesses
* both before and after.
*/
-void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
+static void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v)
{
#ifdef CONFIG_RCU_NOCB_CPU
smp_mb__before_atomic(); /* Up to the caller! */
@@ -134,7 +125,7 @@
* with the actual number of callbacks on the structure. This exchange is
* fully ordered with respect to the callers accesses both before and after.
*/
-long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
+static long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v)
{
#ifdef CONFIG_RCU_NOCB_CPU
return atomic_long_xchg(&rsclp->len, v);
@@ -161,7 +152,6 @@
for (i = 0; i < RCU_CBLIST_NSEGS; i++)
rsclp->tails[i] = &rsclp->head;
rcu_segcblist_set_len(rsclp, 0);
- rsclp->len_lazy = 0;
rsclp->enabled = 1;
}
@@ -173,7 +163,6 @@
{
WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
- WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
rsclp->enabled = 0;
}
@@ -193,7 +182,7 @@
bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
{
return rcu_segcblist_is_enabled(rsclp) &&
- &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+ &rsclp->head != READ_ONCE(rsclp->tails[RCU_DONE_TAIL]);
}
/*
@@ -253,11 +242,9 @@
* absolutely not OK for it to ever miss posting a callback.
*/
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy)
+ struct rcu_head *rhp)
{
rcu_segcblist_inc_len(rsclp);
- if (lazy)
- rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is enqueued. */
rhp->next = NULL;
WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp);
@@ -275,15 +262,13 @@
* period. You have been warned.
*/
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy)
+ struct rcu_head *rhp)
{
int i;
if (rcu_segcblist_n_cbs(rsclp) == 0)
return false;
rcu_segcblist_inc_len(rsclp);
- if (lazy)
- rsclp->len_lazy++;
smp_mb(); /* Ensure counts are updated before callback is entrained. */
rhp->next = NULL;
for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
@@ -307,8 +292,6 @@
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
- rclp->len_lazy += rsclp->len_lazy;
- rsclp->len_lazy = 0;
rclp->len = rcu_segcblist_xchg_len(rsclp, 0);
}
@@ -361,9 +344,7 @@
void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp)
{
- rsclp->len_lazy += rclp->len_lazy;
rcu_segcblist_add_len(rsclp, rclp->len);
- rclp->len_lazy = 0;
rclp->len = 0;
}
@@ -400,8 +381,6 @@
return; /* Nothing to do. */
WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head);
WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail);
- rclp->head = NULL;
- rclp->tail = &rclp->head;
}
/*
@@ -496,8 +475,16 @@
* Also advance to the oldest segment of callbacks whose
* ->gp_seq[] completion is at or after that passed in via "seq",
* skipping any empty segments.
+ *
+ * Note that segment "i" (and any lower-numbered segments
+ * containing older callbacks) will be unaffected, and their
+ * grace-period numbers remain unchanged. For example, if i ==
+ * WAIT_TAIL, then neither WAIT_TAIL nor DONE_TAIL will be touched.
+ * Instead, the CBs in NEXT_TAIL will be merged with those in
+ * NEXT_READY_TAIL and the grace-period number of NEXT_READY_TAIL
+ * would be updated. NEXT_TAIL would then be empty.
*/
- if (++i >= RCU_NEXT_TAIL)
+ if (rcu_segcblist_restempty(rsclp, i) || ++i >= RCU_NEXT_TAIL)
return false;
/*
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 815c2fd..5c293af 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -15,15 +15,6 @@
return READ_ONCE(rclp->len);
}
-/*
- * Account for the fact that a previously dequeued callback turned out
- * to be marked as lazy.
- */
-static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
-{
- rclp->len_lazy--;
-}
-
void rcu_cblist_init(struct rcu_cblist *rclp);
void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp);
void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp,
@@ -59,18 +50,6 @@
#endif
}
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
-{
- return rsclp->len_lazy;
-}
-
-/* Return number of lazy callbacks in segmented callback list. */
-static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
-{
- return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy;
-}
-
/*
* Is the specified rcu_segcblist enabled, for example, not corresponding
* to an offline CPU?
@@ -106,9 +85,9 @@
struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp);
void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy);
+ struct rcu_head *rhp);
bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
- struct rcu_head *rhp, bool lazy);
+ struct rcu_head *rhp);
void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
struct rcu_cblist *rclp);
void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
deleted file mode 100644
index 5a879d0..0000000
--- a/kernel/rcu/rcuperf.c
+++ /dev/null
@@ -1,702 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Read-Copy Update module-based performance-test facility
- *
- * Copyright (C) IBM Corporation, 2015
- *
- * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
- */
-
-#define pr_fmt(fmt) fmt
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kthread.h>
-#include <linux/err.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/rcupdate.h>
-#include <linux/interrupt.h>
-#include <linux/sched.h>
-#include <uapi/linux/sched/types.h>
-#include <linux/atomic.h>
-#include <linux/bitops.h>
-#include <linux/completion.h>
-#include <linux/moduleparam.h>
-#include <linux/percpu.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/freezer.h>
-#include <linux/cpu.h>
-#include <linux/delay.h>
-#include <linux/stat.h>
-#include <linux/srcu.h>
-#include <linux/slab.h>
-#include <asm/byteorder.h>
-#include <linux/torture.h>
-#include <linux/vmalloc.h>
-
-#include "rcu.h"
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
-
-#define PERF_FLAG "-perf:"
-#define PERFOUT_STRING(s) \
- pr_alert("%s" PERF_FLAG " %s\n", perf_type, s)
-#define VERBOSE_PERFOUT_STRING(s) \
- do { if (verbose) pr_alert("%s" PERF_FLAG " %s\n", perf_type, s); } while (0)
-#define VERBOSE_PERFOUT_ERRSTRING(s) \
- do { if (verbose) pr_alert("%s" PERF_FLAG "!!! %s\n", perf_type, s); } while (0)
-
-/*
- * The intended use cases for the nreaders and nwriters module parameters
- * are as follows:
- *
- * 1. Specify only the nr_cpus kernel boot parameter. This will
- * set both nreaders and nwriters to the value specified by
- * nr_cpus for a mixed reader/writer test.
- *
- * 2. Specify the nr_cpus kernel boot parameter, but set
- * rcuperf.nreaders to zero. This will set nwriters to the
- * value specified by nr_cpus for an update-only test.
- *
- * 3. Specify the nr_cpus kernel boot parameter, but set
- * rcuperf.nwriters to zero. This will set nreaders to the
- * value specified by nr_cpus for a read-only test.
- *
- * Various other use cases may of course be specified.
- */
-
-#ifdef MODULE
-# define RCUPERF_SHUTDOWN 0
-#else
-# define RCUPERF_SHUTDOWN 1
-#endif
-
-torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
-torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
-torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
-torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
-torture_param(int, nreaders, -1, "Number of RCU reader threads");
-torture_param(int, nwriters, -1, "Number of RCU updater threads");
-torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
- "Shutdown at end of performance tests.");
-torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
-torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
-
-static char *perf_type = "rcu";
-module_param(perf_type, charp, 0444);
-MODULE_PARM_DESC(perf_type, "Type of RCU to performance-test (rcu, srcu, ...)");
-
-static int nrealreaders;
-static int nrealwriters;
-static struct task_struct **writer_tasks;
-static struct task_struct **reader_tasks;
-static struct task_struct *shutdown_task;
-
-static u64 **writer_durations;
-static int *writer_n_durations;
-static atomic_t n_rcu_perf_reader_started;
-static atomic_t n_rcu_perf_writer_started;
-static atomic_t n_rcu_perf_writer_finished;
-static wait_queue_head_t shutdown_wq;
-static u64 t_rcu_perf_writer_started;
-static u64 t_rcu_perf_writer_finished;
-static unsigned long b_rcu_perf_writer_started;
-static unsigned long b_rcu_perf_writer_finished;
-static DEFINE_PER_CPU(atomic_t, n_async_inflight);
-
-static int rcu_perf_writer_state;
-#define RTWS_INIT 0
-#define RTWS_ASYNC 1
-#define RTWS_BARRIER 2
-#define RTWS_EXP_SYNC 3
-#define RTWS_SYNC 4
-#define RTWS_IDLE 5
-#define RTWS_STOPPING 6
-
-#define MAX_MEAS 10000
-#define MIN_MEAS 100
-
-/*
- * Operations vector for selecting different types of tests.
- */
-
-struct rcu_perf_ops {
- int ptype;
- void (*init)(void);
- void (*cleanup)(void);
- int (*readlock)(void);
- void (*readunlock)(int idx);
- unsigned long (*get_gp_seq)(void);
- unsigned long (*gp_diff)(unsigned long new, unsigned long old);
- unsigned long (*exp_completed)(void);
- void (*async)(struct rcu_head *head, rcu_callback_t func);
- void (*gp_barrier)(void);
- void (*sync)(void);
- void (*exp_sync)(void);
- const char *name;
-};
-
-static struct rcu_perf_ops *cur_ops;
-
-/*
- * Definitions for rcu perf testing.
- */
-
-static int rcu_perf_read_lock(void) __acquires(RCU)
-{
- rcu_read_lock();
- return 0;
-}
-
-static void rcu_perf_read_unlock(int idx) __releases(RCU)
-{
- rcu_read_unlock();
-}
-
-static unsigned long __maybe_unused rcu_no_completed(void)
-{
- return 0;
-}
-
-static void rcu_sync_perf_init(void)
-{
-}
-
-static struct rcu_perf_ops rcu_ops = {
- .ptype = RCU_FLAVOR,
- .init = rcu_sync_perf_init,
- .readlock = rcu_perf_read_lock,
- .readunlock = rcu_perf_read_unlock,
- .get_gp_seq = rcu_get_gp_seq,
- .gp_diff = rcu_seq_diff,
- .exp_completed = rcu_exp_batches_completed,
- .async = call_rcu,
- .gp_barrier = rcu_barrier,
- .sync = synchronize_rcu,
- .exp_sync = synchronize_rcu_expedited,
- .name = "rcu"
-};
-
-/*
- * Definitions for srcu perf testing.
- */
-
-DEFINE_STATIC_SRCU(srcu_ctl_perf);
-static struct srcu_struct *srcu_ctlp = &srcu_ctl_perf;
-
-static int srcu_perf_read_lock(void) __acquires(srcu_ctlp)
-{
- return srcu_read_lock(srcu_ctlp);
-}
-
-static void srcu_perf_read_unlock(int idx) __releases(srcu_ctlp)
-{
- srcu_read_unlock(srcu_ctlp, idx);
-}
-
-static unsigned long srcu_perf_completed(void)
-{
- return srcu_batches_completed(srcu_ctlp);
-}
-
-static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func)
-{
- call_srcu(srcu_ctlp, head, func);
-}
-
-static void srcu_rcu_barrier(void)
-{
- srcu_barrier(srcu_ctlp);
-}
-
-static void srcu_perf_synchronize(void)
-{
- synchronize_srcu(srcu_ctlp);
-}
-
-static void srcu_perf_synchronize_expedited(void)
-{
- synchronize_srcu_expedited(srcu_ctlp);
-}
-
-static struct rcu_perf_ops srcu_ops = {
- .ptype = SRCU_FLAVOR,
- .init = rcu_sync_perf_init,
- .readlock = srcu_perf_read_lock,
- .readunlock = srcu_perf_read_unlock,
- .get_gp_seq = srcu_perf_completed,
- .gp_diff = rcu_seq_diff,
- .exp_completed = srcu_perf_completed,
- .async = srcu_call_rcu,
- .gp_barrier = srcu_rcu_barrier,
- .sync = srcu_perf_synchronize,
- .exp_sync = srcu_perf_synchronize_expedited,
- .name = "srcu"
-};
-
-static struct srcu_struct srcud;
-
-static void srcu_sync_perf_init(void)
-{
- srcu_ctlp = &srcud;
- init_srcu_struct(srcu_ctlp);
-}
-
-static void srcu_sync_perf_cleanup(void)
-{
- cleanup_srcu_struct(srcu_ctlp);
-}
-
-static struct rcu_perf_ops srcud_ops = {
- .ptype = SRCU_FLAVOR,
- .init = srcu_sync_perf_init,
- .cleanup = srcu_sync_perf_cleanup,
- .readlock = srcu_perf_read_lock,
- .readunlock = srcu_perf_read_unlock,
- .get_gp_seq = srcu_perf_completed,
- .gp_diff = rcu_seq_diff,
- .exp_completed = srcu_perf_completed,
- .async = srcu_call_rcu,
- .gp_barrier = srcu_rcu_barrier,
- .sync = srcu_perf_synchronize,
- .exp_sync = srcu_perf_synchronize_expedited,
- .name = "srcud"
-};
-
-/*
- * Definitions for RCU-tasks perf testing.
- */
-
-static int tasks_perf_read_lock(void)
-{
- return 0;
-}
-
-static void tasks_perf_read_unlock(int idx)
-{
-}
-
-static struct rcu_perf_ops tasks_ops = {
- .ptype = RCU_TASKS_FLAVOR,
- .init = rcu_sync_perf_init,
- .readlock = tasks_perf_read_lock,
- .readunlock = tasks_perf_read_unlock,
- .get_gp_seq = rcu_no_completed,
- .gp_diff = rcu_seq_diff,
- .async = call_rcu_tasks,
- .gp_barrier = rcu_barrier_tasks,
- .sync = synchronize_rcu_tasks,
- .exp_sync = synchronize_rcu_tasks,
- .name = "tasks"
-};
-
-static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
-{
- if (!cur_ops->gp_diff)
- return new - old;
- return cur_ops->gp_diff(new, old);
-}
-
-/*
- * If performance tests complete, wait for shutdown to commence.
- */
-static void rcu_perf_wait_shutdown(void)
-{
- cond_resched_tasks_rcu_qs();
- if (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters)
- return;
- while (!torture_must_stop())
- schedule_timeout_uninterruptible(1);
-}
-
-/*
- * RCU perf reader kthread. Repeatedly does empty RCU read-side
- * critical section, minimizing update-side interference.
- */
-static int
-rcu_perf_reader(void *arg)
-{
- unsigned long flags;
- int idx;
- long me = (long)arg;
-
- VERBOSE_PERFOUT_STRING("rcu_perf_reader task started");
- set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
- set_user_nice(current, MAX_NICE);
- atomic_inc(&n_rcu_perf_reader_started);
-
- do {
- local_irq_save(flags);
- idx = cur_ops->readlock();
- cur_ops->readunlock(idx);
- local_irq_restore(flags);
- rcu_perf_wait_shutdown();
- } while (!torture_must_stop());
- torture_kthread_stopping("rcu_perf_reader");
- return 0;
-}
-
-/*
- * Callback function for asynchronous grace periods from rcu_perf_writer().
- */
-static void rcu_perf_async_cb(struct rcu_head *rhp)
-{
- atomic_dec(this_cpu_ptr(&n_async_inflight));
- kfree(rhp);
-}
-
-/*
- * RCU perf writer kthread. Repeatedly does a grace period.
- */
-static int
-rcu_perf_writer(void *arg)
-{
- int i = 0;
- int i_max;
- long me = (long)arg;
- struct rcu_head *rhp = NULL;
- struct sched_param sp;
- bool started = false, done = false, alldone = false;
- u64 t;
- u64 *wdp;
- u64 *wdpp = writer_durations[me];
-
- VERBOSE_PERFOUT_STRING("rcu_perf_writer task started");
- WARN_ON(!wdpp);
- set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
- sp.sched_priority = 1;
- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
-
- if (holdoff)
- schedule_timeout_uninterruptible(holdoff * HZ);
-
- /*
- * Wait until rcu_end_inkernel_boot() is called for normal GP tests
- * so that RCU is not always expedited for normal GP tests.
- * The system_state test is approximate, but works well in practice.
- */
- while (!gp_exp && system_state != SYSTEM_RUNNING)
- schedule_timeout_uninterruptible(1);
-
- t = ktime_get_mono_fast_ns();
- if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) {
- t_rcu_perf_writer_started = t;
- if (gp_exp) {
- b_rcu_perf_writer_started =
- cur_ops->exp_completed() / 2;
- } else {
- b_rcu_perf_writer_started = cur_ops->get_gp_seq();
- }
- }
-
- do {
- if (writer_holdoff)
- udelay(writer_holdoff);
- wdp = &wdpp[i];
- *wdp = ktime_get_mono_fast_ns();
- if (gp_async) {
-retry:
- if (!rhp)
- rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
- if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
- rcu_perf_writer_state = RTWS_ASYNC;
- atomic_inc(this_cpu_ptr(&n_async_inflight));
- cur_ops->async(rhp, rcu_perf_async_cb);
- rhp = NULL;
- } else if (!kthread_should_stop()) {
- rcu_perf_writer_state = RTWS_BARRIER;
- cur_ops->gp_barrier();
- goto retry;
- } else {
- kfree(rhp); /* Because we are stopping. */
- }
- } else if (gp_exp) {
- rcu_perf_writer_state = RTWS_EXP_SYNC;
- cur_ops->exp_sync();
- } else {
- rcu_perf_writer_state = RTWS_SYNC;
- cur_ops->sync();
- }
- rcu_perf_writer_state = RTWS_IDLE;
- t = ktime_get_mono_fast_ns();
- *wdp = t - *wdp;
- i_max = i;
- if (!started &&
- atomic_read(&n_rcu_perf_writer_started) >= nrealwriters)
- started = true;
- if (!done && i >= MIN_MEAS) {
- done = true;
- sp.sched_priority = 0;
- sched_setscheduler_nocheck(current,
- SCHED_NORMAL, &sp);
- pr_alert("%s%s rcu_perf_writer %ld has %d measurements\n",
- perf_type, PERF_FLAG, me, MIN_MEAS);
- if (atomic_inc_return(&n_rcu_perf_writer_finished) >=
- nrealwriters) {
- schedule_timeout_interruptible(10);
- rcu_ftrace_dump(DUMP_ALL);
- PERFOUT_STRING("Test complete");
- t_rcu_perf_writer_finished = t;
- if (gp_exp) {
- b_rcu_perf_writer_finished =
- cur_ops->exp_completed() / 2;
- } else {
- b_rcu_perf_writer_finished =
- cur_ops->get_gp_seq();
- }
- if (shutdown) {
- smp_mb(); /* Assign before wake. */
- wake_up(&shutdown_wq);
- }
- }
- }
- if (done && !alldone &&
- atomic_read(&n_rcu_perf_writer_finished) >= nrealwriters)
- alldone = true;
- if (started && !alldone && i < MAX_MEAS - 1)
- i++;
- rcu_perf_wait_shutdown();
- } while (!torture_must_stop());
- if (gp_async) {
- rcu_perf_writer_state = RTWS_BARRIER;
- cur_ops->gp_barrier();
- }
- rcu_perf_writer_state = RTWS_STOPPING;
- writer_n_durations[me] = i_max;
- torture_kthread_stopping("rcu_perf_writer");
- return 0;
-}
-
-static void
-rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
-{
- pr_alert("%s" PERF_FLAG
- "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
- perf_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
-}
-
-static void
-rcu_perf_cleanup(void)
-{
- int i;
- int j;
- int ngps = 0;
- u64 *wdp;
- u64 *wdpp;
-
- /*
- * Would like warning at start, but everything is expedited
- * during the mid-boot phase, so have to wait till the end.
- */
- if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
- VERBOSE_PERFOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
- if (rcu_gp_is_normal() && gp_exp)
- VERBOSE_PERFOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
- if (gp_exp && gp_async)
- VERBOSE_PERFOUT_ERRSTRING("No expedited async GPs, so went with async!");
-
- if (torture_cleanup_begin())
- return;
- if (!cur_ops) {
- torture_cleanup_end();
- return;
- }
-
- if (reader_tasks) {
- for (i = 0; i < nrealreaders; i++)
- torture_stop_kthread(rcu_perf_reader,
- reader_tasks[i]);
- kfree(reader_tasks);
- }
-
- if (writer_tasks) {
- for (i = 0; i < nrealwriters; i++) {
- torture_stop_kthread(rcu_perf_writer,
- writer_tasks[i]);
- if (!writer_n_durations)
- continue;
- j = writer_n_durations[i];
- pr_alert("%s%s writer %d gps: %d\n",
- perf_type, PERF_FLAG, i, j);
- ngps += j;
- }
- pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
- perf_type, PERF_FLAG,
- t_rcu_perf_writer_started, t_rcu_perf_writer_finished,
- t_rcu_perf_writer_finished -
- t_rcu_perf_writer_started,
- ngps,
- rcuperf_seq_diff(b_rcu_perf_writer_finished,
- b_rcu_perf_writer_started));
- for (i = 0; i < nrealwriters; i++) {
- if (!writer_durations)
- break;
- if (!writer_n_durations)
- continue;
- wdpp = writer_durations[i];
- if (!wdpp)
- continue;
- for (j = 0; j <= writer_n_durations[i]; j++) {
- wdp = &wdpp[j];
- pr_alert("%s%s %4d writer-duration: %5d %llu\n",
- perf_type, PERF_FLAG,
- i, j, *wdp);
- if (j % 100 == 0)
- schedule_timeout_uninterruptible(1);
- }
- kfree(writer_durations[i]);
- }
- kfree(writer_tasks);
- kfree(writer_durations);
- kfree(writer_n_durations);
- }
-
- /* Do torture-type-specific cleanup operations. */
- if (cur_ops->cleanup != NULL)
- cur_ops->cleanup();
-
- torture_cleanup_end();
-}
-
-/*
- * Return the number if non-negative. If -1, the number of CPUs.
- * If less than -1, that much less than the number of CPUs, but
- * at least one.
- */
-static int compute_real(int n)
-{
- int nr;
-
- if (n >= 0) {
- nr = n;
- } else {
- nr = num_online_cpus() + 1 + n;
- if (nr <= 0)
- nr = 1;
- }
- return nr;
-}
-
-/*
- * RCU perf shutdown kthread. Just waits to be awakened, then shuts
- * down system.
- */
-static int
-rcu_perf_shutdown(void *arg)
-{
- do {
- wait_event(shutdown_wq,
- atomic_read(&n_rcu_perf_writer_finished) >=
- nrealwriters);
- } while (atomic_read(&n_rcu_perf_writer_finished) < nrealwriters);
- smp_mb(); /* Wake before output. */
- rcu_perf_cleanup();
- kernel_power_off();
- return -EINVAL;
-}
-
-static int __init
-rcu_perf_init(void)
-{
- long i;
- int firsterr = 0;
- static struct rcu_perf_ops *perf_ops[] = {
- &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops,
- };
-
- if (!torture_init_begin(perf_type, verbose))
- return -EBUSY;
-
- /* Process args and tell the world that the perf'er is on the job. */
- for (i = 0; i < ARRAY_SIZE(perf_ops); i++) {
- cur_ops = perf_ops[i];
- if (strcmp(perf_type, cur_ops->name) == 0)
- break;
- }
- if (i == ARRAY_SIZE(perf_ops)) {
- pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
- pr_alert("rcu-perf types:");
- for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
- pr_cont(" %s", perf_ops[i]->name);
- pr_cont("\n");
- WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
- firsterr = -EINVAL;
- cur_ops = NULL;
- goto unwind;
- }
- if (cur_ops->init)
- cur_ops->init();
-
- nrealwriters = compute_real(nwriters);
- nrealreaders = compute_real(nreaders);
- atomic_set(&n_rcu_perf_reader_started, 0);
- atomic_set(&n_rcu_perf_writer_started, 0);
- atomic_set(&n_rcu_perf_writer_finished, 0);
- rcu_perf_print_module_parms(cur_ops, "Start of test");
-
- /* Start up the kthreads. */
-
- if (shutdown) {
- init_waitqueue_head(&shutdown_wq);
- firsterr = torture_create_kthread(rcu_perf_shutdown, NULL,
- shutdown_task);
- if (firsterr)
- goto unwind;
- schedule_timeout_uninterruptible(1);
- }
- reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
- GFP_KERNEL);
- if (reader_tasks == NULL) {
- VERBOSE_PERFOUT_ERRSTRING("out of memory");
- firsterr = -ENOMEM;
- goto unwind;
- }
- for (i = 0; i < nrealreaders; i++) {
- firsterr = torture_create_kthread(rcu_perf_reader, (void *)i,
- reader_tasks[i]);
- if (firsterr)
- goto unwind;
- }
- while (atomic_read(&n_rcu_perf_reader_started) < nrealreaders)
- schedule_timeout_uninterruptible(1);
- writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
- GFP_KERNEL);
- writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations),
- GFP_KERNEL);
- writer_n_durations =
- kcalloc(nrealwriters, sizeof(*writer_n_durations),
- GFP_KERNEL);
- if (!writer_tasks || !writer_durations || !writer_n_durations) {
- VERBOSE_PERFOUT_ERRSTRING("out of memory");
- firsterr = -ENOMEM;
- goto unwind;
- }
- for (i = 0; i < nrealwriters; i++) {
- writer_durations[i] =
- kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
- GFP_KERNEL);
- if (!writer_durations[i]) {
- firsterr = -ENOMEM;
- goto unwind;
- }
- firsterr = torture_create_kthread(rcu_perf_writer, (void *)i,
- writer_tasks[i]);
- if (firsterr)
- goto unwind;
- }
- torture_init_end();
- return 0;
-
-unwind:
- torture_init_end();
- rcu_perf_cleanup();
- return firsterr;
-}
-
-module_init(rcu_perf_init);
-module_exit(rcu_perf_cleanup);
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
new file mode 100644
index 0000000..2819b95
--- /dev/null
+++ b/kernel/rcu/rcuscale.c
@@ -0,0 +1,853 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Read-Copy Update module-based scalability-test facility
+ *
+ * Copyright (C) IBM Corporation, 2015
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.ibm.com>
+ */
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <uapi/linux/sched/types.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
+#include <linux/freezer.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <asm/byteorder.h>
+#include <linux/torture.h>
+#include <linux/vmalloc.h>
+
+#include "rcu.h"
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
+
+#define SCALE_FLAG "-scale:"
+#define SCALEOUT_STRING(s) \
+ pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s)
+#define VERBOSE_SCALEOUT_STRING(s) \
+ do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0)
+#define VERBOSE_SCALEOUT_ERRSTRING(s) \
+ do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0)
+
+/*
+ * The intended use cases for the nreaders and nwriters module parameters
+ * are as follows:
+ *
+ * 1. Specify only the nr_cpus kernel boot parameter. This will
+ * set both nreaders and nwriters to the value specified by
+ * nr_cpus for a mixed reader/writer test.
+ *
+ * 2. Specify the nr_cpus kernel boot parameter, but set
+ * rcuscale.nreaders to zero. This will set nwriters to the
+ * value specified by nr_cpus for an update-only test.
+ *
+ * 3. Specify the nr_cpus kernel boot parameter, but set
+ * rcuscale.nwriters to zero. This will set nreaders to the
+ * value specified by nr_cpus for a read-only test.
+ *
+ * Various other use cases may of course be specified.
+ *
+ * Note that this test's readers are intended only as a test load for
+ * the writers. The reader scalability statistics will be overly
+ * pessimistic due to the per-critical-section interrupt disabling,
+ * test-end checks, and the pair of calls through pointers.
+ */
+
+#ifdef MODULE
+# define RCUSCALE_SHUTDOWN 0
+#else
+# define RCUSCALE_SHUTDOWN 1
+#endif
+
+torture_param(bool, gp_async, false, "Use asynchronous GP wait primitives");
+torture_param(int, gp_async_max, 1000, "Max # outstanding waits per reader");
+torture_param(bool, gp_exp, false, "Use expedited GP wait primitives");
+torture_param(int, holdoff, 10, "Holdoff time before test start (s)");
+torture_param(int, nreaders, -1, "Number of RCU reader threads");
+torture_param(int, nwriters, -1, "Number of RCU updater threads");
+torture_param(bool, shutdown, RCUSCALE_SHUTDOWN,
+ "Shutdown at end of scalability tests.");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
+torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
+torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() scale test?");
+torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
+
+static char *scale_type = "rcu";
+module_param(scale_type, charp, 0444);
+MODULE_PARM_DESC(scale_type, "Type of RCU to scalability-test (rcu, srcu, ...)");
+
+static int nrealreaders;
+static int nrealwriters;
+static struct task_struct **writer_tasks;
+static struct task_struct **reader_tasks;
+static struct task_struct *shutdown_task;
+
+static u64 **writer_durations;
+static int *writer_n_durations;
+static atomic_t n_rcu_scale_reader_started;
+static atomic_t n_rcu_scale_writer_started;
+static atomic_t n_rcu_scale_writer_finished;
+static wait_queue_head_t shutdown_wq;
+static u64 t_rcu_scale_writer_started;
+static u64 t_rcu_scale_writer_finished;
+static unsigned long b_rcu_gp_test_started;
+static unsigned long b_rcu_gp_test_finished;
+static DEFINE_PER_CPU(atomic_t, n_async_inflight);
+
+#define MAX_MEAS 10000
+#define MIN_MEAS 100
+
+/*
+ * Operations vector for selecting different types of tests.
+ */
+
+struct rcu_scale_ops {
+ int ptype;
+ void (*init)(void);
+ void (*cleanup)(void);
+ int (*readlock)(void);
+ void (*readunlock)(int idx);
+ unsigned long (*get_gp_seq)(void);
+ unsigned long (*gp_diff)(unsigned long new, unsigned long old);
+ unsigned long (*exp_completed)(void);
+ void (*async)(struct rcu_head *head, rcu_callback_t func);
+ void (*gp_barrier)(void);
+ void (*sync)(void);
+ void (*exp_sync)(void);
+ const char *name;
+};
+
+static struct rcu_scale_ops *cur_ops;
+
+/*
+ * Definitions for rcu scalability testing.
+ */
+
+static int rcu_scale_read_lock(void) __acquires(RCU)
+{
+ rcu_read_lock();
+ return 0;
+}
+
+static void rcu_scale_read_unlock(int idx) __releases(RCU)
+{
+ rcu_read_unlock();
+}
+
+static unsigned long __maybe_unused rcu_no_completed(void)
+{
+ return 0;
+}
+
+static void rcu_sync_scale_init(void)
+{
+}
+
+static struct rcu_scale_ops rcu_ops = {
+ .ptype = RCU_FLAVOR,
+ .init = rcu_sync_scale_init,
+ .readlock = rcu_scale_read_lock,
+ .readunlock = rcu_scale_read_unlock,
+ .get_gp_seq = rcu_get_gp_seq,
+ .gp_diff = rcu_seq_diff,
+ .exp_completed = rcu_exp_batches_completed,
+ .async = call_rcu,
+ .gp_barrier = rcu_barrier,
+ .sync = synchronize_rcu,
+ .exp_sync = synchronize_rcu_expedited,
+ .name = "rcu"
+};
+
+/*
+ * Definitions for srcu scalability testing.
+ */
+
+DEFINE_STATIC_SRCU(srcu_ctl_scale);
+static struct srcu_struct *srcu_ctlp = &srcu_ctl_scale;
+
+static int srcu_scale_read_lock(void) __acquires(srcu_ctlp)
+{
+ return srcu_read_lock(srcu_ctlp);
+}
+
+static void srcu_scale_read_unlock(int idx) __releases(srcu_ctlp)
+{
+ srcu_read_unlock(srcu_ctlp, idx);
+}
+
+static unsigned long srcu_scale_completed(void)
+{
+ return srcu_batches_completed(srcu_ctlp);
+}
+
+static void srcu_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ call_srcu(srcu_ctlp, head, func);
+}
+
+static void srcu_rcu_barrier(void)
+{
+ srcu_barrier(srcu_ctlp);
+}
+
+static void srcu_scale_synchronize(void)
+{
+ synchronize_srcu(srcu_ctlp);
+}
+
+static void srcu_scale_synchronize_expedited(void)
+{
+ synchronize_srcu_expedited(srcu_ctlp);
+}
+
+static struct rcu_scale_ops srcu_ops = {
+ .ptype = SRCU_FLAVOR,
+ .init = rcu_sync_scale_init,
+ .readlock = srcu_scale_read_lock,
+ .readunlock = srcu_scale_read_unlock,
+ .get_gp_seq = srcu_scale_completed,
+ .gp_diff = rcu_seq_diff,
+ .exp_completed = srcu_scale_completed,
+ .async = srcu_call_rcu,
+ .gp_barrier = srcu_rcu_barrier,
+ .sync = srcu_scale_synchronize,
+ .exp_sync = srcu_scale_synchronize_expedited,
+ .name = "srcu"
+};
+
+static struct srcu_struct srcud;
+
+static void srcu_sync_scale_init(void)
+{
+ srcu_ctlp = &srcud;
+ init_srcu_struct(srcu_ctlp);
+}
+
+static void srcu_sync_scale_cleanup(void)
+{
+ cleanup_srcu_struct(srcu_ctlp);
+}
+
+static struct rcu_scale_ops srcud_ops = {
+ .ptype = SRCU_FLAVOR,
+ .init = srcu_sync_scale_init,
+ .cleanup = srcu_sync_scale_cleanup,
+ .readlock = srcu_scale_read_lock,
+ .readunlock = srcu_scale_read_unlock,
+ .get_gp_seq = srcu_scale_completed,
+ .gp_diff = rcu_seq_diff,
+ .exp_completed = srcu_scale_completed,
+ .async = srcu_call_rcu,
+ .gp_barrier = srcu_rcu_barrier,
+ .sync = srcu_scale_synchronize,
+ .exp_sync = srcu_scale_synchronize_expedited,
+ .name = "srcud"
+};
+
+/*
+ * Definitions for RCU-tasks scalability testing.
+ */
+
+static int tasks_scale_read_lock(void)
+{
+ return 0;
+}
+
+static void tasks_scale_read_unlock(int idx)
+{
+}
+
+static struct rcu_scale_ops tasks_ops = {
+ .ptype = RCU_TASKS_FLAVOR,
+ .init = rcu_sync_scale_init,
+ .readlock = tasks_scale_read_lock,
+ .readunlock = tasks_scale_read_unlock,
+ .get_gp_seq = rcu_no_completed,
+ .gp_diff = rcu_seq_diff,
+ .async = call_rcu_tasks,
+ .gp_barrier = rcu_barrier_tasks,
+ .sync = synchronize_rcu_tasks,
+ .exp_sync = synchronize_rcu_tasks,
+ .name = "tasks"
+};
+
+static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old)
+{
+ if (!cur_ops->gp_diff)
+ return new - old;
+ return cur_ops->gp_diff(new, old);
+}
+
+/*
+ * If scalability tests complete, wait for shutdown to commence.
+ */
+static void rcu_scale_wait_shutdown(void)
+{
+ cond_resched_tasks_rcu_qs();
+ if (atomic_read(&n_rcu_scale_writer_finished) < nrealwriters)
+ return;
+ while (!torture_must_stop())
+ schedule_timeout_uninterruptible(1);
+}
+
+/*
+ * RCU scalability reader kthread. Repeatedly does empty RCU read-side
+ * critical section, minimizing update-side interference. However, the
+ * point of this test is not to evaluate reader scalability, but instead
+ * to serve as a test load for update-side scalability testing.
+ */
+static int
+rcu_scale_reader(void *arg)
+{
+ unsigned long flags;
+ int idx;
+ long me = (long)arg;
+
+ VERBOSE_SCALEOUT_STRING("rcu_scale_reader task started");
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ set_user_nice(current, MAX_NICE);
+ atomic_inc(&n_rcu_scale_reader_started);
+
+ do {
+ local_irq_save(flags);
+ idx = cur_ops->readlock();
+ cur_ops->readunlock(idx);
+ local_irq_restore(flags);
+ rcu_scale_wait_shutdown();
+ } while (!torture_must_stop());
+ torture_kthread_stopping("rcu_scale_reader");
+ return 0;
+}
+
+/*
+ * Callback function for asynchronous grace periods from rcu_scale_writer().
+ */
+static void rcu_scale_async_cb(struct rcu_head *rhp)
+{
+ atomic_dec(this_cpu_ptr(&n_async_inflight));
+ kfree(rhp);
+}
+
+/*
+ * RCU scale writer kthread. Repeatedly does a grace period.
+ */
+static int
+rcu_scale_writer(void *arg)
+{
+ int i = 0;
+ int i_max;
+ long me = (long)arg;
+ struct rcu_head *rhp = NULL;
+ bool started = false, done = false, alldone = false;
+ u64 t;
+ u64 *wdp;
+ u64 *wdpp = writer_durations[me];
+
+ VERBOSE_SCALEOUT_STRING("rcu_scale_writer task started");
+ WARN_ON(!wdpp);
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ sched_set_fifo_low(current);
+
+ if (holdoff)
+ schedule_timeout_uninterruptible(holdoff * HZ);
+
+ /*
+ * Wait until rcu_end_inkernel_boot() is called for normal GP tests
+ * so that RCU is not always expedited for normal GP tests.
+ * The system_state test is approximate, but works well in practice.
+ */
+ while (!gp_exp && system_state != SYSTEM_RUNNING)
+ schedule_timeout_uninterruptible(1);
+
+ t = ktime_get_mono_fast_ns();
+ if (atomic_inc_return(&n_rcu_scale_writer_started) >= nrealwriters) {
+ t_rcu_scale_writer_started = t;
+ if (gp_exp) {
+ b_rcu_gp_test_started =
+ cur_ops->exp_completed() / 2;
+ } else {
+ b_rcu_gp_test_started = cur_ops->get_gp_seq();
+ }
+ }
+
+ do {
+ if (writer_holdoff)
+ udelay(writer_holdoff);
+ wdp = &wdpp[i];
+ *wdp = ktime_get_mono_fast_ns();
+ if (gp_async) {
+retry:
+ if (!rhp)
+ rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
+ if (rhp && atomic_read(this_cpu_ptr(&n_async_inflight)) < gp_async_max) {
+ atomic_inc(this_cpu_ptr(&n_async_inflight));
+ cur_ops->async(rhp, rcu_scale_async_cb);
+ rhp = NULL;
+ } else if (!kthread_should_stop()) {
+ cur_ops->gp_barrier();
+ goto retry;
+ } else {
+ kfree(rhp); /* Because we are stopping. */
+ }
+ } else if (gp_exp) {
+ cur_ops->exp_sync();
+ } else {
+ cur_ops->sync();
+ }
+ t = ktime_get_mono_fast_ns();
+ *wdp = t - *wdp;
+ i_max = i;
+ if (!started &&
+ atomic_read(&n_rcu_scale_writer_started) >= nrealwriters)
+ started = true;
+ if (!done && i >= MIN_MEAS) {
+ done = true;
+ sched_set_normal(current, 0);
+ pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n",
+ scale_type, SCALE_FLAG, me, MIN_MEAS);
+ if (atomic_inc_return(&n_rcu_scale_writer_finished) >=
+ nrealwriters) {
+ schedule_timeout_interruptible(10);
+ rcu_ftrace_dump(DUMP_ALL);
+ SCALEOUT_STRING("Test complete");
+ t_rcu_scale_writer_finished = t;
+ if (gp_exp) {
+ b_rcu_gp_test_finished =
+ cur_ops->exp_completed() / 2;
+ } else {
+ b_rcu_gp_test_finished =
+ cur_ops->get_gp_seq();
+ }
+ if (shutdown) {
+ smp_mb(); /* Assign before wake. */
+ wake_up(&shutdown_wq);
+ }
+ }
+ }
+ if (done && !alldone &&
+ atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters)
+ alldone = true;
+ if (started && !alldone && i < MAX_MEAS - 1)
+ i++;
+ rcu_scale_wait_shutdown();
+ } while (!torture_must_stop());
+ if (gp_async) {
+ cur_ops->gp_barrier();
+ }
+ writer_n_durations[me] = i_max;
+ torture_kthread_stopping("rcu_scale_writer");
+ return 0;
+}
+
+static void
+rcu_scale_print_module_parms(struct rcu_scale_ops *cur_ops, const char *tag)
+{
+ pr_alert("%s" SCALE_FLAG
+ "--- %s: nreaders=%d nwriters=%d verbose=%d shutdown=%d\n",
+ scale_type, tag, nrealreaders, nrealwriters, verbose, shutdown);
+}
+
+static void
+rcu_scale_cleanup(void)
+{
+ int i;
+ int j;
+ int ngps = 0;
+ u64 *wdp;
+ u64 *wdpp;
+
+ /*
+ * Would like warning at start, but everything is expedited
+ * during the mid-boot phase, so have to wait till the end.
+ */
+ if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
+ VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+ if (rcu_gp_is_normal() && gp_exp)
+ VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+ if (gp_exp && gp_async)
+ VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+
+ if (torture_cleanup_begin())
+ return;
+ if (!cur_ops) {
+ torture_cleanup_end();
+ return;
+ }
+
+ if (reader_tasks) {
+ for (i = 0; i < nrealreaders; i++)
+ torture_stop_kthread(rcu_scale_reader,
+ reader_tasks[i]);
+ kfree(reader_tasks);
+ }
+
+ if (writer_tasks) {
+ for (i = 0; i < nrealwriters; i++) {
+ torture_stop_kthread(rcu_scale_writer,
+ writer_tasks[i]);
+ if (!writer_n_durations)
+ continue;
+ j = writer_n_durations[i];
+ pr_alert("%s%s writer %d gps: %d\n",
+ scale_type, SCALE_FLAG, i, j);
+ ngps += j;
+ }
+ pr_alert("%s%s start: %llu end: %llu duration: %llu gps: %d batches: %ld\n",
+ scale_type, SCALE_FLAG,
+ t_rcu_scale_writer_started, t_rcu_scale_writer_finished,
+ t_rcu_scale_writer_finished -
+ t_rcu_scale_writer_started,
+ ngps,
+ rcuscale_seq_diff(b_rcu_gp_test_finished,
+ b_rcu_gp_test_started));
+ for (i = 0; i < nrealwriters; i++) {
+ if (!writer_durations)
+ break;
+ if (!writer_n_durations)
+ continue;
+ wdpp = writer_durations[i];
+ if (!wdpp)
+ continue;
+ for (j = 0; j <= writer_n_durations[i]; j++) {
+ wdp = &wdpp[j];
+ pr_alert("%s%s %4d writer-duration: %5d %llu\n",
+ scale_type, SCALE_FLAG,
+ i, j, *wdp);
+ if (j % 100 == 0)
+ schedule_timeout_uninterruptible(1);
+ }
+ kfree(writer_durations[i]);
+ }
+ kfree(writer_tasks);
+ kfree(writer_durations);
+ kfree(writer_n_durations);
+ }
+
+ /* Do torture-type-specific cleanup operations. */
+ if (cur_ops->cleanup != NULL)
+ cur_ops->cleanup();
+
+ torture_cleanup_end();
+}
+
+/*
+ * Return the number if non-negative. If -1, the number of CPUs.
+ * If less than -1, that much less than the number of CPUs, but
+ * at least one.
+ */
+static int compute_real(int n)
+{
+ int nr;
+
+ if (n >= 0) {
+ nr = n;
+ } else {
+ nr = num_online_cpus() + 1 + n;
+ if (nr <= 0)
+ nr = 1;
+ }
+ return nr;
+}
+
+/*
+ * RCU scalability shutdown kthread. Just waits to be awakened, then shuts
+ * down system.
+ */
+static int
+rcu_scale_shutdown(void *arg)
+{
+ wait_event(shutdown_wq,
+ atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters);
+ smp_mb(); /* Wake before output. */
+ rcu_scale_cleanup();
+ kernel_power_off();
+ return -EINVAL;
+}
+
+/*
+ * kfree_rcu() scalability tests: Start a kfree_rcu() loop on all CPUs for number
+ * of iterations and measure total time and number of GP for all iterations to complete.
+ */
+
+torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
+torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
+torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
+
+static struct task_struct **kfree_reader_tasks;
+static int kfree_nrealthreads;
+static atomic_t n_kfree_scale_thread_started;
+static atomic_t n_kfree_scale_thread_ended;
+
+struct kfree_obj {
+ char kfree_obj[8];
+ struct rcu_head rh;
+};
+
+static int
+kfree_scale_thread(void *arg)
+{
+ int i, loop = 0;
+ long me = (long)arg;
+ struct kfree_obj *alloc_ptr;
+ u64 start_time, end_time;
+ long long mem_begin, mem_during = 0;
+
+ VERBOSE_SCALEOUT_STRING("kfree_scale_thread task started");
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ set_user_nice(current, MAX_NICE);
+
+ start_time = ktime_get_mono_fast_ns();
+
+ if (atomic_inc_return(&n_kfree_scale_thread_started) >= kfree_nrealthreads) {
+ if (gp_exp)
+ b_rcu_gp_test_started = cur_ops->exp_completed() / 2;
+ else
+ b_rcu_gp_test_started = cur_ops->get_gp_seq();
+ }
+
+ do {
+ if (!mem_during) {
+ mem_during = mem_begin = si_mem_available();
+ } else if (loop % (kfree_loops / 4) == 0) {
+ mem_during = (mem_during + si_mem_available()) / 2;
+ }
+
+ for (i = 0; i < kfree_alloc_num; i++) {
+ alloc_ptr = kmalloc(kfree_mult * sizeof(struct kfree_obj), GFP_KERNEL);
+ if (!alloc_ptr)
+ return -ENOMEM;
+
+ kfree_rcu(alloc_ptr, rh);
+ }
+
+ cond_resched();
+ } while (!torture_must_stop() && ++loop < kfree_loops);
+
+ if (atomic_inc_return(&n_kfree_scale_thread_ended) >= kfree_nrealthreads) {
+ end_time = ktime_get_mono_fast_ns();
+
+ if (gp_exp)
+ b_rcu_gp_test_finished = cur_ops->exp_completed() / 2;
+ else
+ b_rcu_gp_test_finished = cur_ops->get_gp_seq();
+
+ pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n",
+ (unsigned long long)(end_time - start_time), kfree_loops,
+ rcuscale_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started),
+ (mem_begin - mem_during) >> (20 - PAGE_SHIFT));
+
+ if (shutdown) {
+ smp_mb(); /* Assign before wake. */
+ wake_up(&shutdown_wq);
+ }
+ }
+
+ torture_kthread_stopping("kfree_scale_thread");
+ return 0;
+}
+
+static void
+kfree_scale_cleanup(void)
+{
+ int i;
+
+ if (torture_cleanup_begin())
+ return;
+
+ if (kfree_reader_tasks) {
+ for (i = 0; i < kfree_nrealthreads; i++)
+ torture_stop_kthread(kfree_scale_thread,
+ kfree_reader_tasks[i]);
+ kfree(kfree_reader_tasks);
+ }
+
+ torture_cleanup_end();
+}
+
+/*
+ * shutdown kthread. Just waits to be awakened, then shuts down system.
+ */
+static int
+kfree_scale_shutdown(void *arg)
+{
+ wait_event(shutdown_wq,
+ atomic_read(&n_kfree_scale_thread_ended) >= kfree_nrealthreads);
+
+ smp_mb(); /* Wake before output. */
+
+ kfree_scale_cleanup();
+ kernel_power_off();
+ return -EINVAL;
+}
+
+static int __init
+kfree_scale_init(void)
+{
+ long i;
+ int firsterr = 0;
+
+ kfree_nrealthreads = compute_real(kfree_nthreads);
+ /* Start up the kthreads. */
+ if (shutdown) {
+ init_waitqueue_head(&shutdown_wq);
+ firsterr = torture_create_kthread(kfree_scale_shutdown, NULL,
+ shutdown_task);
+ if (firsterr)
+ goto unwind;
+ schedule_timeout_uninterruptible(1);
+ }
+
+ pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj));
+
+ kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
+ GFP_KERNEL);
+ if (kfree_reader_tasks == NULL) {
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+
+ for (i = 0; i < kfree_nrealthreads; i++) {
+ firsterr = torture_create_kthread(kfree_scale_thread, (void *)i,
+ kfree_reader_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+
+ while (atomic_read(&n_kfree_scale_thread_started) < kfree_nrealthreads)
+ schedule_timeout_uninterruptible(1);
+
+ torture_init_end();
+ return 0;
+
+unwind:
+ torture_init_end();
+ kfree_scale_cleanup();
+ return firsterr;
+}
+
+static int __init
+rcu_scale_init(void)
+{
+ long i;
+ int firsterr = 0;
+ static struct rcu_scale_ops *scale_ops[] = {
+ &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops,
+ };
+
+ if (!torture_init_begin(scale_type, verbose))
+ return -EBUSY;
+
+ /* Process args and announce that the scalability'er is on the job. */
+ for (i = 0; i < ARRAY_SIZE(scale_ops); i++) {
+ cur_ops = scale_ops[i];
+ if (strcmp(scale_type, cur_ops->name) == 0)
+ break;
+ }
+ if (i == ARRAY_SIZE(scale_ops)) {
+ pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type);
+ pr_alert("rcu-scale types:");
+ for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
+ pr_cont(" %s", scale_ops[i]->name);
+ pr_cont("\n");
+ WARN_ON(!IS_MODULE(CONFIG_RCU_SCALE_TEST));
+ firsterr = -EINVAL;
+ cur_ops = NULL;
+ goto unwind;
+ }
+ if (cur_ops->init)
+ cur_ops->init();
+
+ if (kfree_rcu_test)
+ return kfree_scale_init();
+
+ nrealwriters = compute_real(nwriters);
+ nrealreaders = compute_real(nreaders);
+ atomic_set(&n_rcu_scale_reader_started, 0);
+ atomic_set(&n_rcu_scale_writer_started, 0);
+ atomic_set(&n_rcu_scale_writer_finished, 0);
+ rcu_scale_print_module_parms(cur_ops, "Start of test");
+
+ /* Start up the kthreads. */
+
+ if (shutdown) {
+ init_waitqueue_head(&shutdown_wq);
+ firsterr = torture_create_kthread(rcu_scale_shutdown, NULL,
+ shutdown_task);
+ if (firsterr)
+ goto unwind;
+ schedule_timeout_uninterruptible(1);
+ }
+ reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
+ GFP_KERNEL);
+ if (reader_tasks == NULL) {
+ VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealreaders; i++) {
+ firsterr = torture_create_kthread(rcu_scale_reader, (void *)i,
+ reader_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+ while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders)
+ schedule_timeout_uninterruptible(1);
+ writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]),
+ GFP_KERNEL);
+ writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations),
+ GFP_KERNEL);
+ writer_n_durations =
+ kcalloc(nrealwriters, sizeof(*writer_n_durations),
+ GFP_KERNEL);
+ if (!writer_tasks || !writer_durations || !writer_n_durations) {
+ VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ for (i = 0; i < nrealwriters; i++) {
+ writer_durations[i] =
+ kcalloc(MAX_MEAS, sizeof(*writer_durations[i]),
+ GFP_KERNEL);
+ if (!writer_durations[i]) {
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+ firsterr = torture_create_kthread(rcu_scale_writer, (void *)i,
+ writer_tasks[i]);
+ if (firsterr)
+ goto unwind;
+ }
+ torture_init_end();
+ return 0;
+
+unwind:
+ torture_init_end();
+ rcu_scale_cleanup();
+ return firsterr;
+}
+
+module_init(rcu_scale_init);
+module_exit(rcu_scale_cleanup);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 3c9feca..6c1aea4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -7,7 +7,7 @@
* Authors: Paul E. McKenney <paulmck@linux.ibm.com>
* Josh Triplett <josh@joshtriplett.org>
*
- * See also: Documentation/RCU/torture.txt
+ * See also: Documentation/RCU/torture.rst
*/
#define pr_fmt(fmt) fmt
@@ -20,7 +20,7 @@
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <uapi/linux/sched/types.h>
@@ -44,13 +44,14 @@
#include <linux/sched/debug.h>
#include <linux/sched/sysctl.h>
#include <linux/oom.h>
+#include <linux/tick.h>
+#include <linux/rcupdate_trace.h>
#include "rcu.h"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
-
/* Bits for ->extendables field, extendables param, and related definitions. */
#define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */
#define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1)
@@ -86,6 +87,7 @@
"Use normal (non-expedited) GP wait primitives");
torture_param(bool, gp_sync, false, "Use synchronous GP wait primitives");
torture_param(int, irqreader, 1, "Allow RCU readers from irq handlers");
+torture_param(int, leakpointer, 0, "Leak pointer dereferences from readers");
torture_param(int, n_barrier_cbs, 0,
"# of callbacks/kthreads for barrier testing");
torture_param(int, nfakewriters, 4, "Number of RCU fake writer threads");
@@ -95,12 +97,19 @@
torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
torture_param(int, onoff_interval, 0,
"Time between CPU hotplugs (jiffies), 0=disable");
+torture_param(int, read_exit_delay, 13,
+ "Delay between read-then-exit episodes (s)");
+torture_param(int, read_exit_burst, 16,
+ "# of read-then-exit bursts per episode, zero to disable");
torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
torture_param(int, stall_cpu_holdoff, 10,
"Time to wait before starting stall (s).");
torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
+torture_param(int, stall_cpu_block, 0, "Sleep while stalling.");
+torture_param(int, stall_gp_kthread, 0,
+ "Grace-period kthread stall duration (s).");
torture_param(int, stat_interval, 60,
"Number of seconds between stats printk()s");
torture_param(int, stutter, 5, "Number of seconds to run/halt test");
@@ -129,6 +138,7 @@
static struct task_struct *fwd_prog_task;
static struct task_struct **barrier_cbs_tasks;
static struct task_struct *barrier_task;
+static struct task_struct *read_exit_task;
#define RCU_TORTURE_PIPE_LEN 10
@@ -160,8 +170,10 @@
static atomic_long_t n_rcu_torture_timers;
static long n_barrier_attempts;
static long n_barrier_successes; /* did rcu_barrier test succeed? */
+static unsigned long n_read_exits;
static struct list_head rcu_torture_removed;
static unsigned long shutdown_jiffies;
+static unsigned long start_gp_seq;
static int rcu_torture_writer_state;
#define RTWS_FIXED_DELAY 0
@@ -338,7 +350,7 @@
* period, and we want a long delay occasionally to trigger
* force_quiescent_state. */
- if (!rcu_fwd_cb_nodelay &&
+ if (!READ_ONCE(rcu_fwd_cb_nodelay) &&
!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
started = cur_ops->get_gp_seq();
ts = rcu_trace_clock_local();
@@ -374,11 +386,12 @@
{
int i;
- i = rp->rtort_pipe_count;
+ i = READ_ONCE(rp->rtort_pipe_count);
if (i > RCU_TORTURE_PIPE_LEN)
i = RCU_TORTURE_PIPE_LEN;
atomic_inc(&rcu_torture_wcount[i]);
- if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
+ WRITE_ONCE(rp->rtort_pipe_count, i + 1);
+ if (rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
rp->rtort_mbtest = 0;
return true;
}
@@ -663,6 +676,11 @@
call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
}
+static void synchronize_rcu_mult_test(void)
+{
+ synchronize_rcu_mult(call_rcu_tasks, call_rcu);
+}
+
static struct rcu_torture_ops tasks_ops = {
.ttype = RCU_TASKS_FLAVOR,
.init = rcu_sync_torture_init,
@@ -672,7 +690,7 @@
.get_gp_seq = rcu_no_completed,
.deferred_free = rcu_tasks_torture_deferred_free,
.sync = synchronize_rcu_tasks,
- .exp_sync = synchronize_rcu_tasks,
+ .exp_sync = synchronize_rcu_mult_test,
.call = call_rcu_tasks,
.cb_barrier = rcu_barrier_tasks,
.fqs = NULL,
@@ -723,6 +741,72 @@
.name = "trivial"
};
+/*
+ * Definitions for rude RCU-tasks torture testing.
+ */
+
+static void rcu_tasks_rude_torture_deferred_free(struct rcu_torture *p)
+{
+ call_rcu_tasks_rude(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_rude_ops = {
+ .ttype = RCU_TASKS_RUDE_FLAVOR,
+ .init = rcu_sync_torture_init,
+ .readlock = rcu_torture_read_lock_trivial,
+ .read_delay = rcu_read_delay, /* just reuse rcu's version. */
+ .readunlock = rcu_torture_read_unlock_trivial,
+ .get_gp_seq = rcu_no_completed,
+ .deferred_free = rcu_tasks_rude_torture_deferred_free,
+ .sync = synchronize_rcu_tasks_rude,
+ .exp_sync = synchronize_rcu_tasks_rude,
+ .call = call_rcu_tasks_rude,
+ .cb_barrier = rcu_barrier_tasks_rude,
+ .fqs = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .name = "tasks-rude"
+};
+
+/*
+ * Definitions for tracing RCU-tasks torture testing.
+ */
+
+static int tasks_tracing_torture_read_lock(void)
+{
+ rcu_read_lock_trace();
+ return 0;
+}
+
+static void tasks_tracing_torture_read_unlock(int idx)
+{
+ rcu_read_unlock_trace();
+}
+
+static void rcu_tasks_tracing_torture_deferred_free(struct rcu_torture *p)
+{
+ call_rcu_tasks_trace(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_tracing_ops = {
+ .ttype = RCU_TASKS_TRACING_FLAVOR,
+ .init = rcu_sync_torture_init,
+ .readlock = tasks_tracing_torture_read_lock,
+ .read_delay = srcu_read_delay, /* just reuse srcu's version. */
+ .readunlock = tasks_tracing_torture_read_unlock,
+ .get_gp_seq = rcu_no_completed,
+ .deferred_free = rcu_tasks_tracing_torture_deferred_free,
+ .sync = synchronize_rcu_tasks_trace,
+ .exp_sync = synchronize_rcu_tasks_trace,
+ .call = call_rcu_tasks_trace,
+ .cb_barrier = rcu_barrier_tasks_trace,
+ .fqs = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .slow_gps = 1,
+ .name = "tasks-tracing"
+};
+
static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
{
if (!cur_ops->gp_diff)
@@ -732,7 +816,7 @@
static bool __maybe_unused torturing_tasks(void)
{
- return cur_ops == &tasks_ops;
+ return cur_ops == &tasks_ops || cur_ops == &tasks_rude_ops;
}
/*
@@ -800,16 +884,11 @@
unsigned long endtime;
unsigned long oldstarttime;
struct rcu_boost_inflight rbi = { .inflight = 0 };
- struct sched_param sp;
VERBOSE_TOROUT_STRING("rcu_torture_boost started");
/* Set real-time priority. */
- sp.sched_priority = 1;
- if (sched_setscheduler(current, SCHED_FIFO, &sp) < 0) {
- VERBOSE_TOROUT_STRING("rcu_torture_boost RT prio failed!");
- n_rcu_torture_boost_rterror++;
- }
+ sched_set_fifo_low(current);
init_rcu_head_on_stack(&rbi.rcu);
/* Each pass through the following loop does one boost-test cycle. */
@@ -831,7 +910,7 @@
/* Wait for the next test interval. */
oldstarttime = boost_starttime;
- while (ULONG_CMP_LT(jiffies, oldstarttime)) {
+ while (time_before(jiffies, oldstarttime)) {
schedule_timeout_interruptible(oldstarttime - jiffies);
stutter_wait("rcu_torture_boost");
if (torture_must_stop())
@@ -841,7 +920,7 @@
/* Do one boost-test interval. */
endtime = oldstarttime + test_boost_duration * HZ;
call_rcu_time = jiffies;
- while (ULONG_CMP_LT(jiffies, endtime)) {
+ while (time_before(jiffies, endtime)) {
/* If we don't have a callback in flight, post one. */
if (!smp_load_acquire(&rbi.inflight)) {
/* RCU core before ->inflight = 1. */
@@ -912,7 +991,7 @@
VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
do {
fqs_resume_time = jiffies + fqs_stutter * HZ;
- while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
+ while (time_before(jiffies, fqs_resume_time) &&
!kthread_should_stop()) {
schedule_timeout_interruptible(1);
}
@@ -1014,7 +1093,8 @@
if (i > RCU_TORTURE_PIPE_LEN)
i = RCU_TORTURE_PIPE_LEN;
atomic_inc(&rcu_torture_wcount[i]);
- old_rp->rtort_pipe_count++;
+ WRITE_ONCE(old_rp->rtort_pipe_count,
+ old_rp->rtort_pipe_count + 1);
switch (synctype[torture_random(&rand) % nsynctypes]) {
case RTWS_DEF_FREE:
rcu_torture_writer_state = RTWS_DEF_FREE;
@@ -1066,7 +1146,8 @@
if (stutter_wait("rcu_torture_writer") &&
!READ_ONCE(rcu_fwd_cb_nodelay) &&
!cur_ops->slow_gps &&
- !torture_must_stop())
+ !torture_must_stop() &&
+ rcu_inkernel_boot_has_ended())
for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++)
if (list_empty(&rcu_tortures[i].rtort_free) &&
rcu_access_pointer(rcu_torture_current) !=
@@ -1075,6 +1156,7 @@
WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
}
} while (!torture_must_stop());
+ rcu_torture_current = NULL; // Let stats task know that we are done.
/* Reset expediting back to unexpedited. */
if (expediting > 0)
expediting = -expediting;
@@ -1143,6 +1225,7 @@
struct torture_random_state *trsp,
struct rt_read_seg *rtrsp)
{
+ unsigned long flags;
int idxnew = -1;
int idxold = *readstate;
int statesnew = ~*readstate & newstate;
@@ -1155,30 +1238,43 @@
/* First, put new protection in place to avoid critical-section gap. */
if (statesnew & RCUTORTURE_RDR_BH)
local_bh_disable();
+ if (statesnew & RCUTORTURE_RDR_RBH)
+ rcu_read_lock_bh();
if (statesnew & RCUTORTURE_RDR_IRQ)
local_irq_disable();
if (statesnew & RCUTORTURE_RDR_PREEMPT)
preempt_disable();
- if (statesnew & RCUTORTURE_RDR_RBH)
- rcu_read_lock_bh();
if (statesnew & RCUTORTURE_RDR_SCHED)
rcu_read_lock_sched();
if (statesnew & RCUTORTURE_RDR_RCU)
idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
- /* Next, remove old protection, irq first due to bh conflict. */
+ /*
+ * Next, remove old protection, in decreasing order of strength
+ * to avoid unlock paths that aren't safe in the stronger
+ * context. Namely: BH can not be enabled with disabled interrupts.
+ * Additionally PREEMPT_RT requires that BH is enabled in preemptible
+ * context.
+ */
if (statesold & RCUTORTURE_RDR_IRQ)
local_irq_enable();
- if (statesold & RCUTORTURE_RDR_BH)
- local_bh_enable();
if (statesold & RCUTORTURE_RDR_PREEMPT)
preempt_enable();
- if (statesold & RCUTORTURE_RDR_RBH)
- rcu_read_unlock_bh();
if (statesold & RCUTORTURE_RDR_SCHED)
rcu_read_unlock_sched();
- if (statesold & RCUTORTURE_RDR_RCU)
+ if (statesold & RCUTORTURE_RDR_BH)
+ local_bh_enable();
+ if (statesold & RCUTORTURE_RDR_RBH)
+ rcu_read_unlock_bh();
+ if (statesold & RCUTORTURE_RDR_RCU) {
+ bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+
+ if (lockit)
+ raw_spin_lock_irqsave(¤t->pi_lock, flags);
cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+ if (lockit)
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
+ }
/* Delay if neither beginning nor end and there was a change. */
if ((statesnew || statesold) && *readstate && newstate)
@@ -1212,6 +1308,9 @@
int mask = rcutorture_extend_mask_max();
unsigned long randmask1 = torture_random(trsp) >> 8;
unsigned long randmask2 = randmask1 >> 3;
+ unsigned long preempts = RCUTORTURE_RDR_PREEMPT | RCUTORTURE_RDR_SCHED;
+ unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
+ unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
/* Mostly only one bit (need preemption!), sometimes lots of bits. */
@@ -1219,11 +1318,26 @@
mask = mask & randmask2;
else
mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
- /* Can't enable bh w/irq disabled. */
- if ((mask & RCUTORTURE_RDR_IRQ) &&
- ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
- (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
- mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
+
+ /*
+ * Can't enable bh w/irq disabled.
+ */
+ if (mask & RCUTORTURE_RDR_IRQ)
+ mask |= oldmask & bhs;
+
+ /*
+ * Ideally these sequences would be detected in debug builds
+ * (regardless of RT), but until then don't stop testing
+ * them on non-RT.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ /* Can't modify BH in atomic context */
+ if (oldmask & preempts_irq)
+ mask &= ~bhs;
+ if ((oldmask | mask) & preempts_irq)
+ mask |= oldmask & bhs;
+ }
+
return mask ?: RCUTORTURE_RDR_RCU;
}
@@ -1271,6 +1385,7 @@
struct rt_read_seg *rtrsp1;
unsigned long long ts;
+ WARN_ON_ONCE(!rcu_is_watching());
newstate = rcutorture_extend_mask(readstate, trsp);
rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++);
started = cur_ops->get_gp_seq();
@@ -1279,6 +1394,7 @@
rcu_read_lock_bh_held() ||
rcu_read_lock_sched_held() ||
srcu_read_lock_held(srcu_ctlp) ||
+ rcu_read_lock_trace_held() ||
torturing_tasks());
if (p == NULL) {
/* Wait for rcu_torture_writer to get underway */
@@ -1289,7 +1405,7 @@
atomic_inc(&n_rcu_torture_mberror);
rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp);
preempt_disable();
- pipe_count = p->rtort_pipe_count;
+ pipe_count = READ_ONCE(p->rtort_pipe_count);
if (pipe_count > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
@@ -1310,6 +1426,9 @@
preempt_enable();
rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+ // This next splat is expected behavior if leakpointer, especially
+ // for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels.
+ WARN_ON_ONCE(leakpointer && READ_ONCE(p->rtort_pipe_count) > 1);
/* If error or close call, record the sequence of reader protections. */
if ((pipe_count > 1 || completed > 1) && !xchg(&err_segs_recorded, 1)) {
@@ -1363,15 +1482,15 @@
set_user_nice(current, MAX_NICE);
if (irqreader && cur_ops->irq_capable)
timer_setup_on_stack(&t, rcu_torture_timer, 0);
-
+ tick_dep_set_task(current, TICK_DEP_BIT_RCU);
do {
if (irqreader && cur_ops->irq_capable) {
if (!timer_pending(&t))
mod_timer(&t, jiffies + 1);
}
- if (!rcu_torture_one_read(&rand))
+ if (!rcu_torture_one_read(&rand) && !torture_must_stop())
schedule_timeout_interruptible(HZ);
- if (time_after(jiffies, lastsleep)) {
+ if (time_after(jiffies, lastsleep) && !torture_must_stop()) {
schedule_timeout_interruptible(1);
lastsleep = jiffies + 10;
}
@@ -1383,6 +1502,7 @@
del_timer_sync(&t);
destroy_timer_on_stack(&t);
}
+ tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
torture_kthread_stopping("rcu_torture_reader");
return 0;
}
@@ -1402,14 +1522,15 @@
int i;
long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
+ struct rcu_torture *rtcp;
static unsigned long rtcv_snap = ULONG_MAX;
static bool splatted;
struct task_struct *wtp;
for_each_possible_cpu(cpu) {
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
- pipesummary[i] += per_cpu(rcu_torture_count, cpu)[i];
- batchsummary[i] += per_cpu(rcu_torture_batch, cpu)[i];
+ pipesummary[i] += READ_ONCE(per_cpu(rcu_torture_count, cpu)[i]);
+ batchsummary[i] += READ_ONCE(per_cpu(rcu_torture_batch, cpu)[i]);
}
}
for (i = RCU_TORTURE_PIPE_LEN - 1; i >= 0; i--) {
@@ -1418,9 +1539,10 @@
}
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
+ rtcp = rcu_access_pointer(rcu_torture_current);
pr_cont("rtc: %p %s: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
- rcu_torture_current,
- rcu_torture_current ? "ver" : "VER",
+ rtcp,
+ rtcp && !rcu_stall_is_suppressed_at_boot() ? "ver" : "VER",
rcu_torture_current_version,
list_empty(&rcu_torture_freelist),
atomic_read(&n_rcu_torture_alloc),
@@ -1436,21 +1558,25 @@
n_rcu_torture_boosts,
atomic_long_read(&n_rcu_torture_timers));
torture_onoff_stats();
- pr_cont("barrier: %ld/%ld:%ld\n",
- n_barrier_successes,
- n_barrier_attempts,
- n_rcu_torture_barrier_error);
+ pr_cont("barrier: %ld/%ld:%ld ",
+ data_race(n_barrier_successes),
+ data_race(n_barrier_attempts),
+ data_race(n_rcu_torture_barrier_error));
+ pr_cont("read-exits: %ld\n", data_race(n_read_exits));
pr_alert("%s%s ", torture_type, TORTURE_FLAG);
- if (atomic_read(&n_rcu_torture_mberror) != 0 ||
- n_rcu_torture_barrier_error != 0 ||
- n_rcu_torture_boost_ktrerror != 0 ||
- n_rcu_torture_boost_rterror != 0 ||
- n_rcu_torture_boost_failure != 0 ||
+ if (atomic_read(&n_rcu_torture_mberror) ||
+ n_rcu_torture_barrier_error || n_rcu_torture_boost_ktrerror ||
+ n_rcu_torture_boost_rterror || n_rcu_torture_boost_failure ||
i > 1) {
pr_cont("%s", "!!! ");
atomic_inc(&n_rcu_torture_error);
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(atomic_read(&n_rcu_torture_mberror));
+ WARN_ON_ONCE(n_rcu_torture_barrier_error); // rcu_barrier()
+ WARN_ON_ONCE(n_rcu_torture_boost_ktrerror); // no boost kthread
+ WARN_ON_ONCE(n_rcu_torture_boost_rterror); // can't set RT prio
+ WARN_ON_ONCE(n_rcu_torture_boost_failure); // RCU boost failed
+ WARN_ON_ONCE(i > 1); // Too-short grace period
}
pr_cont("Reader Pipe: ");
for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
@@ -1473,7 +1599,8 @@
if (cur_ops->stats)
cur_ops->stats();
if (rtcv_snap == rcu_torture_current_version &&
- rcu_torture_current != NULL) {
+ rcu_access_pointer(rcu_torture_current) &&
+ !rcu_stall_is_suppressed()) {
int __maybe_unused flags = 0;
unsigned long __maybe_unused gp_seq = 0;
@@ -1525,16 +1652,20 @@
"test_boost=%d/%d test_boost_interval=%d "
"test_boost_duration=%d shutdown_secs=%d "
"stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
+ "stall_cpu_block=%d "
"n_barrier_cbs=%d "
- "onoff_interval=%d onoff_holdoff=%d\n",
+ "onoff_interval=%d onoff_holdoff=%d "
+ "read_exit_delay=%d read_exit_burst=%d\n",
torture_type, tag, nrealreaders, nfakewriters,
stat_interval, verbose, test_no_idle_hz, shuffle_interval,
stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
test_boost, cur_ops->can_boost,
test_boost_interval, test_boost_duration, shutdown_secs,
stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
+ stall_cpu_block,
n_barrier_cbs,
- onoff_interval, onoff_holdoff);
+ onoff_interval, onoff_holdoff,
+ read_exit_delay, read_exit_burst);
}
static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -1588,6 +1719,7 @@
*/
static int rcu_torture_stall(void *args)
{
+ int idx;
unsigned long stop_at;
VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
@@ -1596,26 +1728,37 @@
schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
}
- if (!kthread_should_stop()) {
+ if (!kthread_should_stop() && stall_gp_kthread > 0) {
+ VERBOSE_TOROUT_STRING("rcu_torture_stall begin GP stall");
+ rcu_gp_set_torture_wait(stall_gp_kthread * HZ);
+ for (idx = 0; idx < stall_gp_kthread + 2; idx++) {
+ if (kthread_should_stop())
+ break;
+ schedule_timeout_uninterruptible(HZ);
+ }
+ }
+ if (!kthread_should_stop() && stall_cpu > 0) {
+ VERBOSE_TOROUT_STRING("rcu_torture_stall begin CPU stall");
stop_at = ktime_get_seconds() + stall_cpu;
/* RCU CPU stall is expected behavior in following code. */
- rcu_read_lock();
+ idx = cur_ops->readlock();
if (stall_cpu_irqsoff)
local_irq_disable();
- else
+ else if (!stall_cpu_block)
preempt_disable();
pr_alert("rcu_torture_stall start on CPU %d.\n",
- smp_processor_id());
+ raw_smp_processor_id());
while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
stop_at))
- continue; /* Induce RCU CPU stall warning. */
+ if (stall_cpu_block)
+ schedule_timeout_uninterruptible(HZ);
if (stall_cpu_irqsoff)
local_irq_enable();
- else
+ else if (!stall_cpu_block)
preempt_enable();
- rcu_read_unlock();
- pr_alert("rcu_torture_stall end.\n");
+ cur_ops->readunlock(idx);
}
+ pr_alert("rcu_torture_stall end.\n");
torture_shutdown_absorb("rcu_torture_stall");
while (!kthread_should_stop())
schedule_timeout_interruptible(10 * HZ);
@@ -1625,7 +1768,7 @@
/* Spawn CPU-stall kthread, if stall_cpu specified. */
static int __init rcu_torture_stall_init(void)
{
- if (stall_cpu <= 0)
+ if (stall_cpu <= 0 && stall_gp_kthread <= 0)
return 0;
return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
}
@@ -1656,43 +1799,53 @@
struct rcu_fwd_cb {
struct rcu_head rh;
struct rcu_fwd_cb *rfc_next;
+ struct rcu_fwd *rfc_rfp;
int rfc_gps;
};
-static DEFINE_SPINLOCK(rcu_fwd_lock);
-static struct rcu_fwd_cb *rcu_fwd_cb_head;
-static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head;
-static long n_launders_cb;
-static unsigned long rcu_fwd_startat;
-static bool rcu_fwd_emergency_stop;
+
#define MAX_FWD_CB_JIFFIES (8 * HZ) /* Maximum CB test duration. */
#define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */
#define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */
#define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */
+#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
+
struct rcu_launder_hist {
long n_launders;
unsigned long launder_gp_seq;
};
-#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV))
-static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
-static unsigned long rcu_launder_gp_seq_start;
-static void rcu_torture_fwd_cb_hist(void)
+struct rcu_fwd {
+ spinlock_t rcu_fwd_lock;
+ struct rcu_fwd_cb *rcu_fwd_cb_head;
+ struct rcu_fwd_cb **rcu_fwd_cb_tail;
+ long n_launders_cb;
+ unsigned long rcu_fwd_startat;
+ struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
+ unsigned long rcu_launder_gp_seq_start;
+};
+
+static DEFINE_MUTEX(rcu_fwd_mutex);
+static struct rcu_fwd *rcu_fwds;
+static bool rcu_fwd_emergency_stop;
+
+static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
{
unsigned long gps;
unsigned long gps_old;
int i;
int j;
- for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--)
- if (n_launders_hist[i].n_launders > 0)
+ for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--)
+ if (rfp->n_launders_hist[i].n_launders > 0)
break;
pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
- __func__, jiffies - rcu_fwd_startat);
- gps_old = rcu_launder_gp_seq_start;
+ __func__, jiffies - rfp->rcu_fwd_startat);
+ gps_old = rfp->rcu_launder_gp_seq_start;
for (j = 0; j <= i; j++) {
- gps = n_launders_hist[j].launder_gp_seq;
+ gps = rfp->n_launders_hist[j].launder_gp_seq;
pr_cont(" %ds/%d: %ld:%ld",
- j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders,
+ j + 1, FWD_CBS_HIST_DIV,
+ rfp->n_launders_hist[j].n_launders,
rcutorture_seq_diff(gps, gps_old));
gps_old = gps;
}
@@ -1706,65 +1859,72 @@
int i;
struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh);
struct rcu_fwd_cb **rfcpp;
+ struct rcu_fwd *rfp = rfcp->rfc_rfp;
rfcp->rfc_next = NULL;
rfcp->rfc_gps++;
- spin_lock_irqsave(&rcu_fwd_lock, flags);
- rfcpp = rcu_fwd_cb_tail;
- rcu_fwd_cb_tail = &rfcp->rfc_next;
+ spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
+ rfcpp = rfp->rcu_fwd_cb_tail;
+ rfp->rcu_fwd_cb_tail = &rfcp->rfc_next;
WRITE_ONCE(*rfcpp, rfcp);
- WRITE_ONCE(n_launders_cb, n_launders_cb + 1);
- i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
- if (i >= ARRAY_SIZE(n_launders_hist))
- i = ARRAY_SIZE(n_launders_hist) - 1;
- n_launders_hist[i].n_launders++;
- n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
- spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1);
+ i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
+ if (i >= ARRAY_SIZE(rfp->n_launders_hist))
+ i = ARRAY_SIZE(rfp->n_launders_hist) - 1;
+ rfp->n_launders_hist[i].n_launders++;
+ rfp->n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq();
+ spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
}
// Give the scheduler a chance, even on nohz_full CPUs.
static void rcu_torture_fwd_prog_cond_resched(unsigned long iter)
{
- if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+ if (IS_ENABLED(CONFIG_PREEMPTION) && IS_ENABLED(CONFIG_NO_HZ_FULL)) {
// Real call_rcu() floods hit userspace, so emulate that.
if (need_resched() || (iter & 0xfff))
schedule();
- } else {
- // No userspace emulation: CB invocation throttles call_rcu()
- cond_resched();
+ return;
}
+ // No userspace emulation: CB invocation throttles call_rcu()
+ cond_resched();
}
/*
* Free all callbacks on the rcu_fwd_cb_head list, either because the
* test is over or because we hit an OOM event.
*/
-static unsigned long rcu_torture_fwd_prog_cbfree(void)
+static unsigned long rcu_torture_fwd_prog_cbfree(struct rcu_fwd *rfp)
{
unsigned long flags;
unsigned long freed = 0;
struct rcu_fwd_cb *rfcp;
for (;;) {
- spin_lock_irqsave(&rcu_fwd_lock, flags);
- rfcp = rcu_fwd_cb_head;
+ spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
+ rfcp = rfp->rcu_fwd_cb_head;
if (!rfcp) {
- spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
break;
}
- rcu_fwd_cb_head = rfcp->rfc_next;
- if (!rcu_fwd_cb_head)
- rcu_fwd_cb_tail = &rcu_fwd_cb_head;
- spin_unlock_irqrestore(&rcu_fwd_lock, flags);
+ rfp->rcu_fwd_cb_head = rfcp->rfc_next;
+ if (!rfp->rcu_fwd_cb_head)
+ rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head;
+ spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags);
kfree(rfcp);
freed++;
rcu_torture_fwd_prog_cond_resched(freed);
+ if (tick_nohz_full_enabled()) {
+ local_irq_save(flags);
+ rcu_momentary_dyntick_idle();
+ local_irq_restore(flags);
+ }
}
return freed;
}
/* Carry out need_resched()/cond_resched() forward-progress testing. */
-static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries)
+static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
+ int *tested, int *tested_tries)
{
unsigned long cver;
unsigned long dur;
@@ -1794,8 +1954,8 @@
sd = cur_ops->stall_dur() + 1;
sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div;
dur = sd4 + torture_random(&trs) % (sd - sd4);
- WRITE_ONCE(rcu_fwd_startat, jiffies);
- stopat = rcu_fwd_startat + dur;
+ WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
+ stopat = rfp->rcu_fwd_startat + dur;
while (time_before(jiffies, stopat) &&
!shutdown_time_arrived() &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
@@ -1803,7 +1963,7 @@
udelay(10);
cur_ops->readunlock(idx);
if (!fwd_progress_need_resched || need_resched())
- rcu_torture_fwd_prog_cond_resched(1);
+ cond_resched();
}
(*tested_tries)++;
if (!time_before(jiffies, stopat) &&
@@ -1830,9 +1990,10 @@
}
/* Carry out call_rcu() forward-progress testing. */
-static void rcu_torture_fwd_prog_cr(void)
+static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
{
unsigned long cver;
+ unsigned long flags;
unsigned long gps;
int i;
long n_launders;
@@ -1853,22 +2014,23 @@
/* Loop continuously posting RCU callbacks. */
WRITE_ONCE(rcu_fwd_cb_nodelay, true);
cur_ops->sync(); /* Later readers see above write. */
- WRITE_ONCE(rcu_fwd_startat, jiffies);
- stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
+ WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
+ stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
n_launders = 0;
- n_launders_cb = 0;
+ rfp->n_launders_cb = 0; // Hoist initialization for multi-kthread
n_launders_sa = 0;
n_max_cbs = 0;
n_max_gps = 0;
- for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++)
- n_launders_hist[i].n_launders = 0;
+ for (i = 0; i < ARRAY_SIZE(rfp->n_launders_hist); i++)
+ rfp->n_launders_hist[i].n_launders = 0;
cver = READ_ONCE(rcu_torture_current_version);
gps = cur_ops->get_gp_seq();
- rcu_launder_gp_seq_start = gps;
+ rfp->rcu_launder_gp_seq_start = gps;
+ tick_dep_set_task(current, TICK_DEP_BIT_RCU);
while (time_before(jiffies, stopat) &&
!shutdown_time_arrived() &&
!READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) {
- rfcp = READ_ONCE(rcu_fwd_cb_head);
+ rfcp = READ_ONCE(rfp->rcu_fwd_cb_head);
rfcpn = NULL;
if (rfcp)
rfcpn = READ_ONCE(rfcp->rfc_next);
@@ -1876,7 +2038,7 @@
if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS &&
++n_max_gps >= MIN_FWD_CBS_LAUNDERED)
break;
- rcu_fwd_cb_head = rfcpn;
+ rfp->rcu_fwd_cb_head = rfcpn;
n_launders++;
n_launders_sa++;
} else {
@@ -1888,29 +2050,36 @@
n_max_cbs++;
n_launders_sa = 0;
rfcp->rfc_gps = 0;
+ rfcp->rfc_rfp = rfp;
}
cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
+ if (tick_nohz_full_enabled()) {
+ local_irq_save(flags);
+ rcu_momentary_dyntick_idle();
+ local_irq_restore(flags);
+ }
}
stoppedat = jiffies;
- n_launders_cb_snap = READ_ONCE(n_launders_cb);
+ n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb);
cver = READ_ONCE(rcu_torture_current_version) - cver;
gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
- (void)rcu_torture_fwd_prog_cbfree();
+ (void)rcu_torture_fwd_prog_cbfree(rfp);
if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) &&
!shutdown_time_arrived()) {
WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED);
pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n",
__func__,
- stoppedat - rcu_fwd_startat, jiffies - stoppedat,
+ stoppedat - rfp->rcu_fwd_startat, jiffies - stoppedat,
n_launders + n_max_cbs - n_launders_cb_snap,
n_launders, n_launders_sa,
n_max_gps, n_max_cbs, cver, gps);
- rcu_torture_fwd_cb_hist();
+ rcu_torture_fwd_cb_hist(rfp);
}
schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
+ tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
WRITE_ONCE(rcu_fwd_cb_nodelay, false);
}
@@ -1922,23 +2091,32 @@
static int rcutorture_oom_notify(struct notifier_block *self,
unsigned long notused, void *nfreed)
{
+ struct rcu_fwd *rfp;
+
+ mutex_lock(&rcu_fwd_mutex);
+ rfp = rcu_fwds;
+ if (!rfp) {
+ mutex_unlock(&rcu_fwd_mutex);
+ return NOTIFY_OK;
+ }
WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
__func__);
- rcu_torture_fwd_cb_hist();
- rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
+ rcu_torture_fwd_cb_hist(rfp);
+ rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp->rcu_fwd_startat)) / 2);
WRITE_ONCE(rcu_fwd_emergency_stop, true);
smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
pr_info("%s: Freed %lu RCU callbacks.\n",
- __func__, rcu_torture_fwd_prog_cbfree());
+ __func__, rcu_torture_fwd_prog_cbfree(rfp));
rcu_barrier();
pr_info("%s: Freed %lu RCU callbacks.\n",
- __func__, rcu_torture_fwd_prog_cbfree());
+ __func__, rcu_torture_fwd_prog_cbfree(rfp));
rcu_barrier();
pr_info("%s: Freed %lu RCU callbacks.\n",
- __func__, rcu_torture_fwd_prog_cbfree());
+ __func__, rcu_torture_fwd_prog_cbfree(rfp));
smp_mb(); /* Frees before return to avoid redoing OOM. */
(*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
pr_info("%s returning after OOM processing.\n", __func__);
+ mutex_unlock(&rcu_fwd_mutex);
return NOTIFY_OK;
}
@@ -1949,6 +2127,7 @@
/* Carry out grace-period forward-progress testing. */
static int rcu_torture_fwd_prog(void *args)
{
+ struct rcu_fwd *rfp = args;
int tested = 0;
int tested_tries = 0;
@@ -1959,10 +2138,11 @@
do {
schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
WRITE_ONCE(rcu_fwd_emergency_stop, false);
- register_oom_notifier(&rcutorture_oom_nb);
- rcu_torture_fwd_prog_nr(&tested, &tested_tries);
- rcu_torture_fwd_prog_cr();
- unregister_oom_notifier(&rcutorture_oom_nb);
+ if (!IS_ENABLED(CONFIG_TINY_RCU) ||
+ rcu_inkernel_boot_has_ended())
+ rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
+ if (rcu_inkernel_boot_has_ended())
+ rcu_torture_fwd_prog_cr(rfp);
/* Avoid slow periods, better to test when busy. */
stutter_wait("rcu_torture_fwd_prog");
@@ -1977,6 +2157,8 @@
/* If forward-progress checking is requested and feasible, spawn the thread. */
static int __init rcu_torture_fwd_prog_init(void)
{
+ struct rcu_fwd *rfp;
+
if (!fwd_progress)
return 0; /* Not requested, so don't do it. */
if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
@@ -1995,8 +2177,29 @@
fwd_progress_holdoff = 1;
if (fwd_progress_div <= 0)
fwd_progress_div = 4;
- return torture_create_kthread(rcu_torture_fwd_prog,
- NULL, fwd_prog_task);
+ rfp = kzalloc(sizeof(*rfp), GFP_KERNEL);
+ if (!rfp)
+ return -ENOMEM;
+ spin_lock_init(&rfp->rcu_fwd_lock);
+ rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head;
+ mutex_lock(&rcu_fwd_mutex);
+ rcu_fwds = rfp;
+ mutex_unlock(&rcu_fwd_mutex);
+ register_oom_notifier(&rcutorture_oom_nb);
+ return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task);
+}
+
+static void rcu_torture_fwd_prog_cleanup(void)
+{
+ struct rcu_fwd *rfp;
+
+ torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
+ rfp = rcu_fwds;
+ mutex_lock(&rcu_fwd_mutex);
+ rcu_fwds = NULL;
+ mutex_unlock(&rcu_fwd_mutex);
+ unregister_oom_notifier(&rcutorture_oom_nb);
+ kfree(rfp);
}
/* Callback function for RCU barrier testing. */
@@ -2005,11 +2208,19 @@
atomic_inc(&barrier_cbs_invoked);
}
+/* IPI handler to get callback posted on desired CPU, if online. */
+static void rcu_torture_barrier1cb(void *rcu_void)
+{
+ struct rcu_head *rhp = rcu_void;
+
+ cur_ops->call(rhp, rcu_torture_barrier_cbf);
+}
+
/* kthread function to register callbacks used to test RCU barriers. */
static int rcu_torture_barrier_cbs(void *arg)
{
long myid = (long)arg;
- bool lastphase = 0;
+ bool lastphase = false;
bool newphase;
struct rcu_head rcu;
@@ -2028,9 +2239,11 @@
* The above smp_load_acquire() ensures barrier_phase load
* is ordered before the following ->call().
*/
- local_irq_disable(); /* Just to test no-irq call_rcu(). */
- cur_ops->call(&rcu, rcu_torture_barrier_cbf);
- local_irq_enable();
+ if (smp_call_function_single(myid, rcu_torture_barrier1cb,
+ &rcu, 1)) {
+ // IPI failed, so use direct call from current CPU.
+ cur_ops->call(&rcu, rcu_torture_barrier_cbf);
+ }
if (atomic_dec_and_test(&barrier_cbs_count))
wake_up(&barrier_wq);
} while (!torture_must_stop());
@@ -2066,7 +2279,21 @@
pr_err("barrier_cbs_invoked = %d, n_barrier_cbs = %d\n",
atomic_read(&barrier_cbs_invoked),
n_barrier_cbs);
- WARN_ON_ONCE(1);
+ WARN_ON(1);
+ // Wait manually for the remaining callbacks
+ i = 0;
+ do {
+ if (WARN_ON(i++ > HZ))
+ i = INT_MIN;
+ schedule_timeout_interruptible(1);
+ cur_ops->cb_barrier();
+ } while (atomic_read(&barrier_cbs_invoked) !=
+ n_barrier_cbs &&
+ !torture_must_stop());
+ smp_mb(); // Can't trust ordering if broken.
+ if (!torture_must_stop())
+ pr_err("Recovered: barrier_cbs_invoked = %d\n",
+ atomic_read(&barrier_cbs_invoked));
} else {
n_barrier_successes++;
}
@@ -2156,6 +2383,99 @@
return true;
}
+static bool read_exit_child_stop;
+static bool read_exit_child_stopped;
+static wait_queue_head_t read_exit_wq;
+
+// Child kthread which just does an rcutorture reader and exits.
+static int rcu_torture_read_exit_child(void *trsp_in)
+{
+ struct torture_random_state *trsp = trsp_in;
+
+ set_user_nice(current, MAX_NICE);
+ // Minimize time between reading and exiting.
+ while (!kthread_should_stop())
+ schedule_timeout_uninterruptible(1);
+ (void)rcu_torture_one_read(trsp);
+ return 0;
+}
+
+// Parent kthread which creates and destroys read-exit child kthreads.
+static int rcu_torture_read_exit(void *unused)
+{
+ int count = 0;
+ bool errexit = false;
+ int i;
+ struct task_struct *tsp;
+ DEFINE_TORTURE_RANDOM(trs);
+
+ // Allocate and initialize.
+ set_user_nice(current, MAX_NICE);
+ VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of test");
+
+ // Each pass through this loop does one read-exit episode.
+ do {
+ if (++count > read_exit_burst) {
+ VERBOSE_TOROUT_STRING("rcu_torture_read_exit: End of episode");
+ rcu_barrier(); // Wait for task_struct free, avoid OOM.
+ for (i = 0; i < read_exit_delay; i++) {
+ schedule_timeout_uninterruptible(HZ);
+ if (READ_ONCE(read_exit_child_stop))
+ break;
+ }
+ if (!READ_ONCE(read_exit_child_stop))
+ VERBOSE_TOROUT_STRING("rcu_torture_read_exit: Start of episode");
+ count = 0;
+ }
+ if (READ_ONCE(read_exit_child_stop))
+ break;
+ // Spawn child.
+ tsp = kthread_run(rcu_torture_read_exit_child,
+ &trs, "%s",
+ "rcu_torture_read_exit_child");
+ if (IS_ERR(tsp)) {
+ VERBOSE_TOROUT_ERRSTRING("out of memory");
+ errexit = true;
+ tsp = NULL;
+ break;
+ }
+ cond_resched();
+ kthread_stop(tsp);
+ n_read_exits ++;
+ stutter_wait("rcu_torture_read_exit");
+ } while (!errexit && !READ_ONCE(read_exit_child_stop));
+
+ // Clean up and exit.
+ smp_store_release(&read_exit_child_stopped, true); // After reaping.
+ smp_mb(); // Store before wakeup.
+ wake_up(&read_exit_wq);
+ while (!torture_must_stop())
+ schedule_timeout_uninterruptible(1);
+ torture_kthread_stopping("rcu_torture_read_exit");
+ return 0;
+}
+
+static int rcu_torture_read_exit_init(void)
+{
+ if (read_exit_burst <= 0)
+ return -EINVAL;
+ init_waitqueue_head(&read_exit_wq);
+ read_exit_child_stop = false;
+ read_exit_child_stopped = false;
+ return torture_create_kthread(rcu_torture_read_exit, NULL,
+ read_exit_task);
+}
+
+static void rcu_torture_read_exit_cleanup(void)
+{
+ if (!read_exit_task)
+ return;
+ WRITE_ONCE(read_exit_child_stop, true);
+ smp_mb(); // Above write before wait.
+ wait_event(read_exit_wq, smp_load_acquire(&read_exit_child_stopped));
+ torture_stop_kthread(rcutorture_read_exit, read_exit_task);
+}
+
static enum cpuhp_state rcutor_hp;
static void
@@ -2177,8 +2497,9 @@
}
show_rcu_gp_kthreads();
+ rcu_torture_read_exit_cleanup();
rcu_torture_barrier_cleanup();
- torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
+ rcu_torture_fwd_prog_cleanup();
torture_stop_kthread(rcu_torture_stall, stall_task);
torture_stop_kthread(rcu_torture_writer, writer_task);
@@ -2188,7 +2509,6 @@
reader_tasks[i]);
kfree(reader_tasks);
}
- rcu_torture_current = NULL;
if (fakewriter_tasks) {
for (i = 0; i < nfakewriters; i++) {
@@ -2201,8 +2521,9 @@
rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
- pr_alert("%s: End-test grace-period state: g%lu f%#x\n",
- cur_ops->name, gp_seq, flags);
+ pr_alert("%s: End-test grace-period state: g%ld f%#x total-gps=%ld\n",
+ cur_ops->name, (long)gp_seq, flags,
+ rcutorture_seq_diff(gp_seq, start_gp_seq));
torture_stop_kthread(rcu_torture_stats, stats_task);
torture_stop_kthread(rcu_torture_fqs, fqs_task);
if (rcu_torture_can_boost())
@@ -2326,9 +2647,12 @@
long i;
int cpu;
int firsterr = 0;
+ int flags = 0;
+ unsigned long gp_seq = 0;
static struct rcu_torture_ops *torture_ops[] = {
&rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
- &busted_srcud_ops, &tasks_ops, &trivial_ops,
+ &busted_srcud_ops, &tasks_ops, &tasks_rude_ops,
+ &tasks_tracing_ops, &trivial_ops,
};
if (!torture_init_begin(torture_type, verbose))
@@ -2367,6 +2691,11 @@
nrealreaders = 1;
}
rcu_torture_print_module_parms(cur_ops, "Start of test");
+ rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+ start_gp_seq = gp_seq;
+ pr_alert("%s: Start-test grace-period state: g%ld f%#x\n",
+ cur_ops->name, (long)gp_seq, flags);
/* Set up the freelist. */
@@ -2499,6 +2828,9 @@
firsterr = rcu_torture_barrier_init();
if (firsterr)
goto unwind;
+ firsterr = rcu_torture_read_exit_init();
+ if (firsterr)
+ goto unwind;
if (object_debug)
rcu_test_debug_objects();
torture_init_end();
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
new file mode 100644
index 0000000..952595c
--- /dev/null
+++ b/kernel/rcu/refscale.c
@@ -0,0 +1,719 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Scalability test comparing RCU vs other mechanisms
+// for acquiring references on objects.
+//
+// Copyright (C) Google, 2020.
+//
+// Author: Joel Fernandes <joel@joelfernandes.org>
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/completion.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kthread.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/notifier.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rcupdate_trace.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/stat.h>
+#include <linux/srcu.h>
+#include <linux/slab.h>
+#include <linux/torture.h>
+#include <linux/types.h>
+
+#include "rcu.h"
+
+#define SCALE_FLAG "-ref-scale: "
+
+#define SCALEOUT(s, x...) \
+ pr_alert("%s" SCALE_FLAG s, scale_type, ## x)
+
+#define VERBOSE_SCALEOUT(s, x...) \
+ do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)
+
+#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
+ do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");
+
+static char *scale_type = "rcu";
+module_param(scale_type, charp, 0444);
+MODULE_PARM_DESC(scale_type, "Type of test (rcu, srcu, refcnt, rwsem, rwlock.");
+
+torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
+
+// Wait until there are multiple CPUs before starting test.
+torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0,
+ "Holdoff time before test start (s)");
+// Number of loops per experiment, all readers execute operations concurrently.
+torture_param(long, loops, 10000, "Number of loops per experiment.");
+// Number of readers, with -1 defaulting to about 75% of the CPUs.
+torture_param(int, nreaders, -1, "Number of readers, -1 for 75% of CPUs.");
+// Number of runs.
+torture_param(int, nruns, 30, "Number of experiments to run.");
+// Reader delay in nanoseconds, 0 for no delay.
+torture_param(int, readdelay, 0, "Read-side delay in nanoseconds.");
+
+#ifdef MODULE
+# define REFSCALE_SHUTDOWN 0
+#else
+# define REFSCALE_SHUTDOWN 1
+#endif
+
+torture_param(bool, shutdown, REFSCALE_SHUTDOWN,
+ "Shutdown at end of scalability tests.");
+
+struct reader_task {
+ struct task_struct *task;
+ int start_reader;
+ wait_queue_head_t wq;
+ u64 last_duration_ns;
+};
+
+static struct task_struct *shutdown_task;
+static wait_queue_head_t shutdown_wq;
+
+static struct task_struct *main_task;
+static wait_queue_head_t main_wq;
+static int shutdown_start;
+
+static struct reader_task *reader_tasks;
+
+// Number of readers that are part of the current experiment.
+static atomic_t nreaders_exp;
+
+// Use to wait for all threads to start.
+static atomic_t n_init;
+static atomic_t n_started;
+static atomic_t n_warmedup;
+static atomic_t n_cooleddown;
+
+// Track which experiment is currently running.
+static int exp_idx;
+
+// Operations vector for selecting different types of tests.
+struct ref_scale_ops {
+ void (*init)(void);
+ void (*cleanup)(void);
+ void (*readsection)(const int nloops);
+ void (*delaysection)(const int nloops, const int udl, const int ndl);
+ const char *name;
+};
+
+static struct ref_scale_ops *cur_ops;
+
+static void un_delay(const int udl, const int ndl)
+{
+ if (udl)
+ udelay(udl);
+ if (ndl)
+ ndelay(ndl);
+}
+
+static void ref_rcu_read_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ rcu_read_lock();
+ rcu_read_unlock();
+ }
+}
+
+static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ rcu_read_lock();
+ un_delay(udl, ndl);
+ rcu_read_unlock();
+ }
+}
+
+static void rcu_sync_scale_init(void)
+{
+}
+
+static struct ref_scale_ops rcu_ops = {
+ .init = rcu_sync_scale_init,
+ .readsection = ref_rcu_read_section,
+ .delaysection = ref_rcu_delay_section,
+ .name = "rcu"
+};
+
+// Definitions for SRCU ref scale testing.
+DEFINE_STATIC_SRCU(srcu_refctl_scale);
+static struct srcu_struct *srcu_ctlp = &srcu_refctl_scale;
+
+static void srcu_ref_scale_read_section(const int nloops)
+{
+ int i;
+ int idx;
+
+ for (i = nloops; i >= 0; i--) {
+ idx = srcu_read_lock(srcu_ctlp);
+ srcu_read_unlock(srcu_ctlp, idx);
+ }
+}
+
+static void srcu_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+ int idx;
+
+ for (i = nloops; i >= 0; i--) {
+ idx = srcu_read_lock(srcu_ctlp);
+ un_delay(udl, ndl);
+ srcu_read_unlock(srcu_ctlp, idx);
+ }
+}
+
+static struct ref_scale_ops srcu_ops = {
+ .init = rcu_sync_scale_init,
+ .readsection = srcu_ref_scale_read_section,
+ .delaysection = srcu_ref_scale_delay_section,
+ .name = "srcu"
+};
+
+// Definitions for RCU Tasks ref scale testing: Empty read markers.
+// These definitions also work for RCU Rude readers.
+static void rcu_tasks_ref_scale_read_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--)
+ continue;
+}
+
+static void rcu_tasks_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--)
+ un_delay(udl, ndl);
+}
+
+static struct ref_scale_ops rcu_tasks_ops = {
+ .init = rcu_sync_scale_init,
+ .readsection = rcu_tasks_ref_scale_read_section,
+ .delaysection = rcu_tasks_ref_scale_delay_section,
+ .name = "rcu-tasks"
+};
+
+// Definitions for RCU Tasks Trace ref scale testing.
+static void rcu_trace_ref_scale_read_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ rcu_read_lock_trace();
+ rcu_read_unlock_trace();
+ }
+}
+
+static void rcu_trace_ref_scale_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ rcu_read_lock_trace();
+ un_delay(udl, ndl);
+ rcu_read_unlock_trace();
+ }
+}
+
+static struct ref_scale_ops rcu_trace_ops = {
+ .init = rcu_sync_scale_init,
+ .readsection = rcu_trace_ref_scale_read_section,
+ .delaysection = rcu_trace_ref_scale_delay_section,
+ .name = "rcu-trace"
+};
+
+// Definitions for reference count
+static atomic_t refcnt;
+
+static void ref_refcnt_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ atomic_inc(&refcnt);
+ atomic_dec(&refcnt);
+ }
+}
+
+static void ref_refcnt_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ atomic_inc(&refcnt);
+ un_delay(udl, ndl);
+ atomic_dec(&refcnt);
+ }
+}
+
+static struct ref_scale_ops refcnt_ops = {
+ .init = rcu_sync_scale_init,
+ .readsection = ref_refcnt_section,
+ .delaysection = ref_refcnt_delay_section,
+ .name = "refcnt"
+};
+
+// Definitions for rwlock
+static rwlock_t test_rwlock;
+
+static void ref_rwlock_init(void)
+{
+ rwlock_init(&test_rwlock);
+}
+
+static void ref_rwlock_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ read_lock(&test_rwlock);
+ read_unlock(&test_rwlock);
+ }
+}
+
+static void ref_rwlock_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ read_lock(&test_rwlock);
+ un_delay(udl, ndl);
+ read_unlock(&test_rwlock);
+ }
+}
+
+static struct ref_scale_ops rwlock_ops = {
+ .init = ref_rwlock_init,
+ .readsection = ref_rwlock_section,
+ .delaysection = ref_rwlock_delay_section,
+ .name = "rwlock"
+};
+
+// Definitions for rwsem
+static struct rw_semaphore test_rwsem;
+
+static void ref_rwsem_init(void)
+{
+ init_rwsem(&test_rwsem);
+}
+
+static void ref_rwsem_section(const int nloops)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ down_read(&test_rwsem);
+ up_read(&test_rwsem);
+ }
+}
+
+static void ref_rwsem_delay_section(const int nloops, const int udl, const int ndl)
+{
+ int i;
+
+ for (i = nloops; i >= 0; i--) {
+ down_read(&test_rwsem);
+ un_delay(udl, ndl);
+ up_read(&test_rwsem);
+ }
+}
+
+static struct ref_scale_ops rwsem_ops = {
+ .init = ref_rwsem_init,
+ .readsection = ref_rwsem_section,
+ .delaysection = ref_rwsem_delay_section,
+ .name = "rwsem"
+};
+
+static void rcu_scale_one_reader(void)
+{
+ if (readdelay <= 0)
+ cur_ops->readsection(loops);
+ else
+ cur_ops->delaysection(loops, readdelay / 1000, readdelay % 1000);
+}
+
+// Reader kthread. Repeatedly does empty RCU read-side
+// critical section, minimizing update-side interference.
+static int
+ref_scale_reader(void *arg)
+{
+ unsigned long flags;
+ long me = (long)arg;
+ struct reader_task *rt = &(reader_tasks[me]);
+ u64 start;
+ s64 duration;
+
+ VERBOSE_SCALEOUT("ref_scale_reader %ld: task started", me);
+ set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ set_user_nice(current, MAX_NICE);
+ atomic_inc(&n_init);
+ if (holdoff)
+ schedule_timeout_interruptible(holdoff * HZ);
+repeat:
+ VERBOSE_SCALEOUT("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+
+ // Wait for signal that this reader can start.
+ wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
+ torture_must_stop());
+
+ if (torture_must_stop())
+ goto end;
+
+ // Make sure that the CPU is affinitized appropriately during testing.
+ WARN_ON_ONCE(smp_processor_id() != me);
+
+ WRITE_ONCE(rt->start_reader, 0);
+ if (!atomic_dec_return(&n_started))
+ while (atomic_read_acquire(&n_started))
+ cpu_relax();
+
+ VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d started", me, exp_idx);
+
+
+ // To reduce noise, do an initial cache-warming invocation, check
+ // in, and then keep warming until everyone has checked in.
+ rcu_scale_one_reader();
+ if (!atomic_dec_return(&n_warmedup))
+ while (atomic_read_acquire(&n_warmedup))
+ rcu_scale_one_reader();
+ // Also keep interrupts disabled. This also has the effect
+ // of preventing entries into slow path for rcu_read_unlock().
+ local_irq_save(flags);
+ start = ktime_get_mono_fast_ns();
+
+ rcu_scale_one_reader();
+
+ duration = ktime_get_mono_fast_ns() - start;
+ local_irq_restore(flags);
+
+ rt->last_duration_ns = WARN_ON_ONCE(duration < 0) ? 0 : duration;
+ // To reduce runtime-skew noise, do maintain-load invocations until
+ // everyone is done.
+ if (!atomic_dec_return(&n_cooleddown))
+ while (atomic_read_acquire(&n_cooleddown))
+ rcu_scale_one_reader();
+
+ if (atomic_dec_and_test(&nreaders_exp))
+ wake_up(&main_wq);
+
+ VERBOSE_SCALEOUT("ref_scale_reader %ld: experiment %d ended, (readers remaining=%d)",
+ me, exp_idx, atomic_read(&nreaders_exp));
+
+ if (!torture_must_stop())
+ goto repeat;
+end:
+ torture_kthread_stopping("ref_scale_reader");
+ return 0;
+}
+
+static void reset_readers(void)
+{
+ int i;
+ struct reader_task *rt;
+
+ for (i = 0; i < nreaders; i++) {
+ rt = &(reader_tasks[i]);
+
+ rt->last_duration_ns = 0;
+ }
+}
+
+// Print the results of each reader and return the sum of all their durations.
+static u64 process_durations(int n)
+{
+ int i;
+ struct reader_task *rt;
+ char buf1[64];
+ char *buf;
+ u64 sum = 0;
+
+ buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
+ if (!buf)
+ return 0;
+ buf[0] = 0;
+ sprintf(buf, "Experiment #%d (Format: <THREAD-NUM>:<Total loop time in ns>)",
+ exp_idx);
+
+ for (i = 0; i < n && !torture_must_stop(); i++) {
+ rt = &(reader_tasks[i]);
+ sprintf(buf1, "%d: %llu\t", i, rt->last_duration_ns);
+
+ if (i % 5 == 0)
+ strcat(buf, "\n");
+ strcat(buf, buf1);
+
+ sum += rt->last_duration_ns;
+ }
+ strcat(buf, "\n");
+
+ SCALEOUT("%s\n", buf);
+
+ kfree(buf);
+ return sum;
+}
+
+// The main_func is the main orchestrator, it performs a bunch of
+// experiments. For every experiment, it orders all the readers
+// involved to start and waits for them to finish the experiment. It
+// then reads their timestamps and starts the next experiment. Each
+// experiment progresses from 1 concurrent reader to N of them at which
+// point all the timestamps are printed.
+static int main_func(void *arg)
+{
+ bool errexit = false;
+ int exp, r;
+ char buf1[64];
+ char *buf;
+ u64 *result_avg;
+
+ set_cpus_allowed_ptr(current, cpumask_of(nreaders % nr_cpu_ids));
+ set_user_nice(current, MAX_NICE);
+
+ VERBOSE_SCALEOUT("main_func task started");
+ result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
+ buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
+ if (!result_avg || !buf) {
+ VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+ errexit = true;
+ }
+ if (holdoff)
+ schedule_timeout_interruptible(holdoff * HZ);
+
+ // Wait for all threads to start.
+ atomic_inc(&n_init);
+ while (atomic_read(&n_init) < nreaders + 1)
+ schedule_timeout_uninterruptible(1);
+
+ // Start exp readers up per experiment
+ for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
+ if (errexit)
+ break;
+ if (torture_must_stop())
+ goto end;
+
+ reset_readers();
+ atomic_set(&nreaders_exp, nreaders);
+ atomic_set(&n_started, nreaders);
+ atomic_set(&n_warmedup, nreaders);
+ atomic_set(&n_cooleddown, nreaders);
+
+ exp_idx = exp;
+
+ for (r = 0; r < nreaders; r++) {
+ smp_store_release(&reader_tasks[r].start_reader, 1);
+ wake_up(&reader_tasks[r].wq);
+ }
+
+ VERBOSE_SCALEOUT("main_func: experiment started, waiting for %d readers",
+ nreaders);
+
+ wait_event(main_wq,
+ !atomic_read(&nreaders_exp) || torture_must_stop());
+
+ VERBOSE_SCALEOUT("main_func: experiment ended");
+
+ if (torture_must_stop())
+ goto end;
+
+ result_avg[exp] = div_u64(1000 * process_durations(nreaders), nreaders * loops);
+ }
+
+ // Print the average of all experiments
+ SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
+
+ if (!errexit) {
+ buf[0] = 0;
+ strcat(buf, "\n");
+ strcat(buf, "Runs\tTime(ns)\n");
+ }
+
+ for (exp = 0; exp < nruns; exp++) {
+ u64 avg;
+ u32 rem;
+
+ if (errexit)
+ break;
+ avg = div_u64_rem(result_avg[exp], 1000, &rem);
+ sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
+ strcat(buf, buf1);
+ }
+
+ if (!errexit)
+ SCALEOUT("%s", buf);
+
+ // This will shutdown everything including us.
+ if (shutdown) {
+ shutdown_start = 1;
+ wake_up(&shutdown_wq);
+ }
+
+ // Wait for torture to stop us
+ while (!torture_must_stop())
+ schedule_timeout_uninterruptible(1);
+
+end:
+ torture_kthread_stopping("main_func");
+ kfree(result_avg);
+ kfree(buf);
+ return 0;
+}
+
+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);
+}
+
+static void
+ref_scale_cleanup(void)
+{
+ int i;
+
+ if (torture_cleanup_begin())
+ return;
+
+ if (!cur_ops) {
+ torture_cleanup_end();
+ return;
+ }
+
+ if (reader_tasks) {
+ for (i = 0; i < nreaders; i++)
+ torture_stop_kthread("ref_scale_reader",
+ reader_tasks[i].task);
+ }
+ kfree(reader_tasks);
+
+ torture_stop_kthread("main_task", main_task);
+ kfree(main_task);
+
+ // Do scale-type-specific cleanup operations.
+ if (cur_ops->cleanup != NULL)
+ cur_ops->cleanup();
+
+ torture_cleanup_end();
+}
+
+// Shutdown kthread. Just waits to be awakened, then shuts down system.
+static int
+ref_scale_shutdown(void *arg)
+{
+ wait_event(shutdown_wq, shutdown_start);
+
+ smp_mb(); // Wake before output.
+ ref_scale_cleanup();
+ kernel_power_off();
+
+ return -EINVAL;
+}
+
+static int __init
+ref_scale_init(void)
+{
+ long i;
+ int firsterr = 0;
+ static struct ref_scale_ops *scale_ops[] = {
+ &rcu_ops, &srcu_ops, &rcu_trace_ops, &rcu_tasks_ops,
+ &refcnt_ops, &rwlock_ops, &rwsem_ops,
+ };
+
+ if (!torture_init_begin(scale_type, verbose))
+ return -EBUSY;
+
+ for (i = 0; i < ARRAY_SIZE(scale_ops); i++) {
+ cur_ops = scale_ops[i];
+ if (strcmp(scale_type, cur_ops->name) == 0)
+ break;
+ }
+ if (i == ARRAY_SIZE(scale_ops)) {
+ pr_alert("rcu-scale: invalid scale type: \"%s\"\n", scale_type);
+ pr_alert("rcu-scale types:");
+ for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
+ pr_cont(" %s", scale_ops[i]->name);
+ pr_cont("\n");
+ WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST));
+ firsterr = -EINVAL;
+ cur_ops = NULL;
+ goto unwind;
+ }
+ if (cur_ops->init)
+ cur_ops->init();
+
+ ref_scale_print_module_parms(cur_ops, "Start of test");
+
+ // Shutdown task
+ if (shutdown) {
+ init_waitqueue_head(&shutdown_wq);
+ firsterr = torture_create_kthread(ref_scale_shutdown, NULL,
+ shutdown_task);
+ if (firsterr)
+ goto unwind;
+ schedule_timeout_uninterruptible(1);
+ }
+
+ // Reader tasks (default to ~75% of online CPUs).
+ if (nreaders < 0)
+ nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
+ reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
+ GFP_KERNEL);
+ if (!reader_tasks) {
+ VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+ firsterr = -ENOMEM;
+ goto unwind;
+ }
+
+ VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);
+
+ for (i = 0; i < nreaders; i++) {
+ firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
+ reader_tasks[i].task);
+ if (firsterr)
+ goto unwind;
+
+ init_waitqueue_head(&(reader_tasks[i].wq));
+ }
+
+ // Main Task
+ init_waitqueue_head(&main_wq);
+ firsterr = torture_create_kthread(main_func, NULL, main_task);
+ if (firsterr)
+ goto unwind;
+
+ torture_init_end();
+ return 0;
+
+unwind:
+ torture_init_end();
+ ref_scale_cleanup();
+ return firsterr;
+}
+
+module_init(ref_scale_init);
+module_exit(ref_scale_cleanup);
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 44d6606..26344dc 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -34,6 +34,7 @@
ssp->srcu_gp_running = false;
ssp->srcu_gp_waiting = false;
ssp->srcu_idx = 0;
+ ssp->srcu_idx_max = 0;
INIT_WORK(&ssp->srcu_work, srcu_drive_gp);
INIT_LIST_HEAD(&ssp->srcu_work.entry);
return 0;
@@ -84,6 +85,8 @@
WARN_ON(ssp->srcu_gp_waiting);
WARN_ON(ssp->srcu_cb_head);
WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
+ WARN_ON(ssp->srcu_idx != ssp->srcu_idx_max);
+ WARN_ON(ssp->srcu_idx & 0x1);
}
EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
@@ -103,7 +106,7 @@
/*
* Workqueue handler to drive one grace period and invoke any callbacks
- * that become ready as a result. Single-CPU and !PREEMPT operation
+ * that become ready as a result. Single-CPU and !PREEMPTION operation
* means that we get away with murder on synchronization. ;-)
*/
void srcu_drive_gp(struct work_struct *wp)
@@ -114,7 +117,7 @@
struct srcu_struct *ssp;
ssp = container_of(wp, struct srcu_struct, srcu_work);
- if (ssp->srcu_gp_running || !READ_ONCE(ssp->srcu_cb_head))
+ if (ssp->srcu_gp_running || USHORT_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
return; /* Already running or nothing to do. */
/* Remove recently arrived callbacks and wait for readers. */
@@ -124,11 +127,12 @@
ssp->srcu_cb_head = NULL;
ssp->srcu_cb_tail = &ssp->srcu_cb_head;
local_irq_enable();
- idx = ssp->srcu_idx;
- WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx);
+ idx = (ssp->srcu_idx & 0x2) / 2;
+ WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
WRITE_ONCE(ssp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx]));
WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+ WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
/* Invoke the callbacks we removed above. */
while (lh) {
@@ -146,11 +150,27 @@
* straighten that out.
*/
WRITE_ONCE(ssp->srcu_gp_running, false);
- if (READ_ONCE(ssp->srcu_cb_head))
+ if (USHORT_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
schedule_work(&ssp->srcu_work);
}
EXPORT_SYMBOL_GPL(srcu_drive_gp);
+static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
+{
+ unsigned short cookie;
+
+ cookie = get_state_synchronize_srcu(ssp);
+ if (USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
+ return;
+ WRITE_ONCE(ssp->srcu_idx_max, cookie);
+ if (!READ_ONCE(ssp->srcu_gp_running)) {
+ if (likely(srcu_init_done))
+ schedule_work(&ssp->srcu_work);
+ else if (list_empty(&ssp->srcu_work.entry))
+ list_add(&ssp->srcu_work.entry, &srcu_boot_list);
+ }
+}
+
/*
* Enqueue an SRCU callback on the specified srcu_struct structure,
* initiating grace-period processing if it is not already running.
@@ -166,12 +186,7 @@
*ssp->srcu_cb_tail = rhp;
ssp->srcu_cb_tail = &rhp->next;
local_irq_restore(flags);
- if (!READ_ONCE(ssp->srcu_gp_running)) {
- if (likely(srcu_init_done))
- schedule_work(&ssp->srcu_work);
- else if (list_empty(&ssp->srcu_work.entry))
- list_add(&ssp->srcu_work.entry, &srcu_boot_list);
- }
+ srcu_gp_start_if_needed(ssp);
}
EXPORT_SYMBOL_GPL(call_srcu);
@@ -190,6 +205,48 @@
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
+/*
+ * get_state_synchronize_srcu - Provide an end-of-grace-period cookie
+ */
+unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
+{
+ unsigned long ret;
+
+ barrier();
+ ret = (READ_ONCE(ssp->srcu_idx) + 3) & ~0x1;
+ barrier();
+ return ret & USHRT_MAX;
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
+
+/*
+ * start_poll_synchronize_srcu - Provide cookie and start grace period
+ *
+ * The difference between this and get_state_synchronize_srcu() is that
+ * this function ensures that the poll_state_synchronize_srcu() will
+ * eventually return the value true.
+ */
+unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp)
+{
+ unsigned long ret = get_state_synchronize_srcu(ssp);
+
+ srcu_gp_start_if_needed(ssp);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
+
+/*
+ * poll_state_synchronize_srcu - Has cookie's grace period ended?
+ */
+bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
+{
+ bool ret = USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx), cookie);
+
+ barrier();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);
+
/* Lockdep diagnostics. */
void __init rcu_scheduler_starting(void)
{
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 21115ff..b882166 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -5,7 +5,7 @@
* Copyright (C) IBM Corporation, 2006
* Copyright (C) Fujitsu, 2012
*
- * Author: Paul McKenney <paulmck@linux.ibm.com>
+ * Authors: Paul McKenney <paulmck@linux.ibm.com>
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
@@ -453,7 +453,7 @@
spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */
smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
rcu_seq_start(&ssp->srcu_gp_seq);
- state = rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq));
+ state = rcu_seq_state(ssp->srcu_gp_seq);
WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
}
@@ -537,7 +537,7 @@
rcu_seq_end(&ssp->srcu_gp_seq);
gpseq = rcu_seq_current(&ssp->srcu_gp_seq);
if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq))
- ssp->srcu_gp_seq_needed_exp = gpseq;
+ WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, gpseq);
spin_unlock_irq_rcu_node(ssp);
mutex_unlock(&ssp->srcu_gp_mutex);
/* A new grace period can start at this point. But only one. */
@@ -553,7 +553,7 @@
snp->srcu_have_cbs[idx] = gpseq;
rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
- snp->srcu_gp_seq_needed_exp = gpseq;
+ WRITE_ONCE(snp->srcu_gp_seq_needed_exp, gpseq);
mask = snp->srcu_data_have_cbs[idx];
snp->srcu_data_have_cbs[idx] = 0;
spin_unlock_irq_rcu_node(snp);
@@ -617,7 +617,7 @@
}
spin_lock_irqsave_rcu_node(ssp, flags);
if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
- ssp->srcu_gp_seq_needed_exp = s;
+ WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
spin_unlock_irqrestore_rcu_node(ssp, flags);
}
@@ -663,7 +663,7 @@
if (snp == sdp->mynode)
snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
- snp->srcu_gp_seq_needed_exp = s;
+ WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
spin_unlock_irqrestore_rcu_node(snp, flags);
}
@@ -677,7 +677,7 @@
smp_store_release(&ssp->srcu_gp_seq_needed, s); /*^^^*/
}
if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s))
- ssp->srcu_gp_seq_needed_exp = s;
+ WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s);
/* If grace period not already done and none in progress, start it. */
if (!rcu_seq_done(&ssp->srcu_gp_seq, s) &&
@@ -756,7 +756,7 @@
* it, if this function was preempted for enough time for the counters
* to wrap, it really doesn't matter whether or not we expedite the grace
* period. The extra overhead of a needlessly expedited grace period is
- * negligible when amoritized over that time period, and the extra latency
+ * negligible when amortized over that time period, and the extra latency
* of a needlessly non-expedited grace period is similarly negligible.
*/
static bool srcu_might_be_idle(struct srcu_struct *ssp)
@@ -767,14 +767,15 @@
unsigned long t;
unsigned long tlast;
+ check_init_srcu_struct(ssp);
/* If the local srcu_data structure has callbacks, not idle. */
- local_irq_save(flags);
- sdp = this_cpu_ptr(ssp->sda);
+ sdp = raw_cpu_ptr(ssp->sda);
+ spin_lock_irqsave_rcu_node(sdp, flags);
if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
- local_irq_restore(flags);
+ spin_unlock_irqrestore_rcu_node(sdp, flags);
return false; /* Callbacks already present, so not idle. */
}
- local_irq_restore(flags);
+ spin_unlock_irqrestore_rcu_node(sdp, flags);
/*
* No local callbacks, so probabalistically probe global state.
@@ -808,6 +809,46 @@
}
/*
+ * Start an SRCU grace period, and also queue the callback if non-NULL.
+ */
+static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
+ struct rcu_head *rhp, bool do_norm)
+{
+ unsigned long flags;
+ int idx;
+ bool needexp = false;
+ bool needgp = false;
+ unsigned long s;
+ struct srcu_data *sdp;
+
+ check_init_srcu_struct(ssp);
+ idx = srcu_read_lock(ssp);
+ sdp = raw_cpu_ptr(ssp->sda);
+ spin_lock_irqsave_rcu_node(sdp, flags);
+ if (rhp)
+ rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp);
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&ssp->srcu_gp_seq));
+ s = rcu_seq_snap(&ssp->srcu_gp_seq);
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+ if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
+ sdp->srcu_gp_seq_needed = s;
+ needgp = true;
+ }
+ if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
+ sdp->srcu_gp_seq_needed_exp = s;
+ needexp = true;
+ }
+ spin_unlock_irqrestore_rcu_node(sdp, flags);
+ if (needgp)
+ srcu_funnel_gp_start(ssp, sdp, s, do_norm);
+ else if (needexp)
+ srcu_funnel_exp_start(ssp, sdp->mynode, s);
+ srcu_read_unlock(ssp, idx);
+ return s;
+}
+
+/*
* Enqueue an SRCU callback on the srcu_data structure associated with
* the current CPU and the specified srcu_struct structure, initiating
* grace-period processing if it is not already running.
@@ -838,14 +879,6 @@
static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
rcu_callback_t func, bool do_norm)
{
- unsigned long flags;
- int idx;
- bool needexp = false;
- bool needgp = false;
- unsigned long s;
- struct srcu_data *sdp;
-
- check_init_srcu_struct(ssp);
if (debug_rcu_head_queue(rhp)) {
/* Probable double call_srcu(), so leak the callback. */
WRITE_ONCE(rhp->func, srcu_leak_callback);
@@ -853,29 +886,7 @@
return;
}
rhp->func = func;
- idx = srcu_read_lock(ssp);
- local_irq_save(flags);
- sdp = this_cpu_ptr(ssp->sda);
- spin_lock_rcu_node(sdp);
- rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
- rcu_segcblist_advance(&sdp->srcu_cblist,
- rcu_seq_current(&ssp->srcu_gp_seq));
- s = rcu_seq_snap(&ssp->srcu_gp_seq);
- (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
- if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
- sdp->srcu_gp_seq_needed = s;
- needgp = true;
- }
- if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
- sdp->srcu_gp_seq_needed_exp = s;
- needexp = true;
- }
- spin_unlock_irqrestore_rcu_node(sdp, flags);
- if (needgp)
- srcu_funnel_gp_start(ssp, sdp, s, do_norm);
- else if (needexp)
- srcu_funnel_exp_start(ssp, sdp->mynode, s);
- srcu_read_unlock(ssp, idx);
+ (void)srcu_gp_start_if_needed(ssp, rhp, do_norm);
}
/**
@@ -1004,6 +1015,62 @@
}
EXPORT_SYMBOL_GPL(synchronize_srcu);
+/**
+ * get_state_synchronize_srcu - Provide an end-of-grace-period cookie
+ * @ssp: srcu_struct to provide cookie for.
+ *
+ * This function returns a cookie that can be passed to
+ * poll_state_synchronize_srcu(), which will return true if a full grace
+ * period has elapsed in the meantime. It is the caller's responsibility
+ * to make sure that grace period happens, for example, by invoking
+ * call_srcu() after return from get_state_synchronize_srcu().
+ */
+unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
+{
+ // Any prior manipulation of SRCU-protected data must happen
+ // before the load from ->srcu_gp_seq.
+ smp_mb();
+ return rcu_seq_snap(&ssp->srcu_gp_seq);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
+
+/**
+ * start_poll_synchronize_srcu - Provide cookie and start grace period
+ * @ssp: srcu_struct to provide cookie for.
+ *
+ * This function returns a cookie that can be passed to
+ * poll_state_synchronize_srcu(), which will return true if a full grace
+ * period has elapsed in the meantime. Unlike get_state_synchronize_srcu(),
+ * this function also ensures that any needed SRCU grace period will be
+ * started. This convenience does come at a cost in terms of CPU overhead.
+ */
+unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp)
+{
+ return srcu_gp_start_if_needed(ssp, NULL, true);
+}
+EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
+
+/**
+ * poll_state_synchronize_srcu - Has cookie's grace period ended?
+ * @ssp: srcu_struct to provide cookie for.
+ * @cookie: Return value from get_state_synchronize_srcu() or start_poll_synchronize_srcu().
+ *
+ * This function takes the cookie that was returned from either
+ * get_state_synchronize_srcu() or start_poll_synchronize_srcu(), and
+ * returns @true if an SRCU grace period elapsed since the time that the
+ * cookie was created.
+ */
+bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
+{
+ if (!rcu_seq_done(&ssp->srcu_gp_seq, cookie))
+ return false;
+ // Ensure that the end of the SRCU grace period happens before
+ // any subsequent code that the caller might execute.
+ smp_mb(); // ^^^
+ return true;
+}
+EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);
+
/*
* Callback function for srcu_barrier() use.
*/
@@ -1056,7 +1123,7 @@
sdp->srcu_barrier_head.func = srcu_barrier_cb;
debug_rcu_head_queue(&sdp->srcu_barrier_head);
if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
- &sdp->srcu_barrier_head, 0)) {
+ &sdp->srcu_barrier_head)) {
debug_rcu_head_unqueue(&sdp->srcu_barrier_head);
atomic_dec(&ssp->srcu_barrier_cpu_cnt);
}
@@ -1082,7 +1149,7 @@
*/
unsigned long srcu_batches_completed(struct srcu_struct *ssp)
{
- return ssp->srcu_idx;
+ return READ_ONCE(ssp->srcu_idx);
}
EXPORT_SYMBOL_GPL(srcu_batches_completed);
@@ -1133,7 +1200,9 @@
return; /* readers present, retry later. */
}
srcu_flip(ssp);
+ spin_lock_irq_rcu_node(ssp);
rcu_seq_set_state(&ssp->srcu_gp_seq, SRCU_STATE_SCAN2);
+ spin_unlock_irq_rcu_node(ssp);
}
if (rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
@@ -1269,8 +1338,8 @@
struct srcu_data *sdp;
sdp = per_cpu_ptr(ssp->sda, cpu);
- u0 = sdp->srcu_unlock_count[!idx];
- u1 = sdp->srcu_unlock_count[idx];
+ u0 = data_race(sdp->srcu_unlock_count[!idx]);
+ u1 = data_race(sdp->srcu_unlock_count[idx]);
/*
* Make sure that a lock is always counted if the corresponding
@@ -1278,8 +1347,8 @@
*/
smp_rmb();
- l0 = sdp->srcu_lock_count[!idx];
- l1 = sdp->srcu_lock_count[idx];
+ l0 = data_race(sdp->srcu_lock_count[!idx]);
+ l1 = data_race(sdp->srcu_lock_count[idx]);
c0 = l0 - u0;
c1 = l1 - u1;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
new file mode 100644
index 0000000..7c05c5a
--- /dev/null
+++ b/kernel/rcu/tasks.h
@@ -0,0 +1,1249 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Task-based RCU implementations.
+ *
+ * Copyright (C) 2020 Paul E. McKenney
+ */
+
+#ifdef CONFIG_TASKS_RCU_GENERIC
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic data structures.
+
+struct rcu_tasks;
+typedef void (*rcu_tasks_gp_func_t)(struct rcu_tasks *rtp);
+typedef void (*pregp_func_t)(void);
+typedef void (*pertask_func_t)(struct task_struct *t, struct list_head *hop);
+typedef void (*postscan_func_t)(struct list_head *hop);
+typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
+typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
+
+/**
+ * Definition for a Tasks-RCU-like mechanism.
+ * @cbs_head: Head of callback list.
+ * @cbs_tail: Tail pointer for callback list.
+ * @cbs_wq: Wait queue allowning new callback to get kthread's attention.
+ * @cbs_lock: Lock protecting callback list.
+ * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
+ * @gp_func: This flavor's grace-period-wait function.
+ * @gp_state: Grace period's most recent state transition (debugging).
+ * @gp_sleep: Per-grace-period sleep to prevent CPU-bound looping.
+ * @init_fract: Initial backoff sleep interval.
+ * @gp_jiffies: Time of last @gp_state transition.
+ * @gp_start: Most recent grace-period start in jiffies.
+ * @n_gps: Number of grace periods completed since boot.
+ * @n_ipis: Number of IPIs sent to encourage grace periods to end.
+ * @n_ipis_fails: Number of IPI-send failures.
+ * @pregp_func: This flavor's pre-grace-period function (optional).
+ * @pertask_func: This flavor's per-task scan function (optional).
+ * @postscan_func: This flavor's post-task scan function (optional).
+ * @holdout_func: This flavor's holdout-list scan function (optional).
+ * @postgp_func: This flavor's post-grace-period function (optional).
+ * @call_func: This flavor's call_rcu()-equivalent function.
+ * @name: This flavor's textual name.
+ * @kname: This flavor's kthread name.
+ */
+struct rcu_tasks {
+ struct rcu_head *cbs_head;
+ struct rcu_head **cbs_tail;
+ struct wait_queue_head cbs_wq;
+ raw_spinlock_t cbs_lock;
+ int gp_state;
+ int gp_sleep;
+ int init_fract;
+ unsigned long gp_jiffies;
+ unsigned long gp_start;
+ unsigned long n_gps;
+ unsigned long n_ipis;
+ unsigned long n_ipis_fails;
+ struct task_struct *kthread_ptr;
+ rcu_tasks_gp_func_t gp_func;
+ pregp_func_t pregp_func;
+ pertask_func_t pertask_func;
+ postscan_func_t postscan_func;
+ holdouts_func_t holdouts_func;
+ postgp_func_t postgp_func;
+ call_rcu_func_t call_func;
+ char *name;
+ char *kname;
+};
+
+#define DEFINE_RCU_TASKS(rt_name, gp, call, n) \
+static struct rcu_tasks rt_name = \
+{ \
+ .cbs_tail = &rt_name.cbs_head, \
+ .cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq), \
+ .cbs_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_lock), \
+ .gp_func = gp, \
+ .call_func = call, \
+ .name = n, \
+ .kname = #rt_name, \
+}
+
+/* Track exiting tasks in order to allow them to be waited for. */
+DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
+
+/* Avoid IPIing CPUs early in the grace period. */
+#define RCU_TASK_IPI_DELAY (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) ? HZ / 2 : 0)
+static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
+module_param(rcu_task_ipi_delay, int, 0644);
+
+/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
+#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
+static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
+module_param(rcu_task_stall_timeout, int, 0644);
+
+/* RCU tasks grace-period state for debugging. */
+#define RTGS_INIT 0
+#define RTGS_WAIT_WAIT_CBS 1
+#define RTGS_WAIT_GP 2
+#define RTGS_PRE_WAIT_GP 3
+#define RTGS_SCAN_TASKLIST 4
+#define RTGS_POST_SCAN_TASKLIST 5
+#define RTGS_WAIT_SCAN_HOLDOUTS 6
+#define RTGS_SCAN_HOLDOUTS 7
+#define RTGS_POST_GP 8
+#define RTGS_WAIT_READERS 9
+#define RTGS_INVOKE_CBS 10
+#define RTGS_WAIT_CBS 11
+#ifndef CONFIG_TINY_RCU
+static const char * const rcu_tasks_gp_state_names[] = {
+ "RTGS_INIT",
+ "RTGS_WAIT_WAIT_CBS",
+ "RTGS_WAIT_GP",
+ "RTGS_PRE_WAIT_GP",
+ "RTGS_SCAN_TASKLIST",
+ "RTGS_POST_SCAN_TASKLIST",
+ "RTGS_WAIT_SCAN_HOLDOUTS",
+ "RTGS_SCAN_HOLDOUTS",
+ "RTGS_POST_GP",
+ "RTGS_WAIT_READERS",
+ "RTGS_INVOKE_CBS",
+ "RTGS_WAIT_CBS",
+};
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+////////////////////////////////////////////////////////////////////////
+//
+// Generic code.
+
+/* Record grace-period phase and time. */
+static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
+{
+ rtp->gp_state = newstate;
+ rtp->gp_jiffies = jiffies;
+}
+
+#ifndef CONFIG_TINY_RCU
+/* Return state name. */
+static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
+{
+ int i = data_race(rtp->gp_state); // Let KCSAN detect update races
+ int j = READ_ONCE(i); // Prevent the compiler from reading twice
+
+ if (j >= ARRAY_SIZE(rcu_tasks_gp_state_names))
+ return "???";
+ return rcu_tasks_gp_state_names[j];
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+// Enqueue a callback for the specified flavor of Tasks RCU.
+static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
+ struct rcu_tasks *rtp)
+{
+ unsigned long flags;
+ bool needwake;
+
+ rhp->next = NULL;
+ rhp->func = func;
+ raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+ needwake = !rtp->cbs_head;
+ WRITE_ONCE(*rtp->cbs_tail, rhp);
+ rtp->cbs_tail = &rhp->next;
+ raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+ /* We can't create the thread unless interrupts are enabled. */
+ if (needwake && READ_ONCE(rtp->kthread_ptr))
+ wake_up(&rtp->cbs_wq);
+}
+
+// Wait for a grace period for the specified flavor of Tasks RCU.
+static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
+{
+ /* Complain if the scheduler has not started. */
+ RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
+ "synchronize_rcu_tasks called too soon");
+
+ /* Wait for the grace period. */
+ wait_rcu_gp(rtp->call_func);
+}
+
+/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
+static int __noreturn rcu_tasks_kthread(void *arg)
+{
+ unsigned long flags;
+ struct rcu_head *list;
+ struct rcu_head *next;
+ struct rcu_tasks *rtp = arg;
+
+ /* Run on housekeeping CPUs by default. Sysadm can move if desired. */
+ housekeeping_affine(current, HK_FLAG_RCU);
+ WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
+
+ /*
+ * Each pass through the following loop makes one check for
+ * newly arrived callbacks, and, if there are some, waits for
+ * one RCU-tasks grace period and then invokes the callbacks.
+ * This loop is terminated by the system going down. ;-)
+ */
+ for (;;) {
+ set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
+
+ /* Pick up any new callbacks. */
+ raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
+ smp_mb__after_spinlock(); // Order updates vs. GP.
+ list = rtp->cbs_head;
+ rtp->cbs_head = NULL;
+ rtp->cbs_tail = &rtp->cbs_head;
+ raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+
+ /* If there were none, wait a bit and start over. */
+ if (!list) {
+ wait_event_interruptible(rtp->cbs_wq,
+ READ_ONCE(rtp->cbs_head));
+ if (!rtp->cbs_head) {
+ WARN_ON(signal_pending(current));
+ set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS);
+ schedule_timeout_idle(HZ/10);
+ }
+ continue;
+ }
+
+ // Wait for one grace period.
+ set_tasks_gp_state(rtp, RTGS_WAIT_GP);
+ rtp->gp_start = jiffies;
+ rtp->gp_func(rtp);
+ rtp->n_gps++;
+
+ /* Invoke the callbacks. */
+ set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
+ while (list) {
+ next = list->next;
+ local_bh_disable();
+ list->func(list);
+ local_bh_enable();
+ list = next;
+ cond_resched();
+ }
+ /* Paranoid sleep to keep this from entering a tight loop */
+ schedule_timeout_idle(rtp->gp_sleep);
+ }
+}
+
+/* Spawn RCU-tasks grace-period kthread. */
+static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp)
+{
+ struct task_struct *t;
+
+ t = kthread_run(rcu_tasks_kthread, rtp, "%s_kthread", rtp->kname);
+ if (WARN_ONCE(IS_ERR(t), "%s: Could not start %s grace-period kthread, OOM is now expected behavior\n", __func__, rtp->name))
+ return;
+ smp_mb(); /* Ensure others see full kthread. */
+}
+
+#ifndef CONFIG_TINY_RCU
+
+/*
+ * Print any non-default Tasks RCU settings.
+ */
+static void __init rcu_tasks_bootup_oddness(void)
+{
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+ if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
+ pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RCU
+ pr_info("\tTrampoline variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_RUDE_RCU
+ pr_info("\tRude variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+ pr_info("\tTracing variant of Tasks RCU enabled.\n");
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#ifndef CONFIG_TINY_RCU
+/* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
+static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
+{
+ pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
+ rtp->kname,
+ tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
+ jiffies - data_race(rtp->gp_jiffies),
+ data_race(rtp->n_gps),
+ data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
+ ".k"[!!data_race(rtp->kthread_ptr)],
+ ".C"[!!data_race(rtp->cbs_head)],
+ s);
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+static void exit_tasks_rcu_finish_trace(struct task_struct *t);
+
+#if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU)
+
+////////////////////////////////////////////////////////////////////////
+//
+// Shared code between task-list-scanning variants of Tasks RCU.
+
+/* Wait for one RCU-tasks grace period. */
+static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
+{
+ struct task_struct *g, *t;
+ unsigned long lastreport;
+ LIST_HEAD(holdouts);
+ int fract;
+
+ set_tasks_gp_state(rtp, RTGS_PRE_WAIT_GP);
+ rtp->pregp_func();
+
+ /*
+ * There were callbacks, so we need to wait for an RCU-tasks
+ * grace period. Start off by scanning the task list for tasks
+ * that are not already voluntarily blocked. Mark these tasks
+ * and make a list of them in holdouts.
+ */
+ set_tasks_gp_state(rtp, RTGS_SCAN_TASKLIST);
+ rcu_read_lock();
+ for_each_process_thread(g, t)
+ rtp->pertask_func(t, &holdouts);
+ rcu_read_unlock();
+
+ set_tasks_gp_state(rtp, RTGS_POST_SCAN_TASKLIST);
+ rtp->postscan_func(&holdouts);
+
+ /*
+ * Each pass through the following loop scans the list of holdout
+ * tasks, removing any that are no longer holdouts. When the list
+ * is empty, we are done.
+ */
+ lastreport = jiffies;
+
+ // Start off with initial wait and slowly back off to 1 HZ wait.
+ fract = rtp->init_fract;
+ if (fract > HZ)
+ fract = HZ;
+
+ for (;;) {
+ bool firstreport;
+ bool needreport;
+ int rtst;
+
+ if (list_empty(&holdouts))
+ break;
+
+ /* Slowly back off waiting for holdouts */
+ set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
+ schedule_timeout_idle(HZ/fract);
+
+ if (fract > 1)
+ fract--;
+
+ rtst = READ_ONCE(rcu_task_stall_timeout);
+ needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
+ if (needreport)
+ lastreport = jiffies;
+ firstreport = true;
+ WARN_ON(signal_pending(current));
+ set_tasks_gp_state(rtp, RTGS_SCAN_HOLDOUTS);
+ rtp->holdouts_func(&holdouts, needreport, &firstreport);
+ }
+
+ set_tasks_gp_state(rtp, RTGS_POST_GP);
+ rtp->postgp_func(rtp);
+}
+
+#endif /* #if defined(CONFIG_TASKS_RCU) || defined(CONFIG_TASKS_TRACE_RCU) */
+
+#ifdef CONFIG_TASKS_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// Simple variant of RCU whose quiescent states are voluntary context
+// switch, cond_resched_rcu_qs(), user-space execution, and idle.
+// As such, grace periods can take one good long time. There are no
+// read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+// because this implementation is intended to get the system into a safe
+// state for some of the manipulations involved in tracing and the like.
+// Finally, this implementation does not support high call_rcu_tasks()
+// rates from multiple CPUs. If this is required, per-CPU callback lists
+// will be needed.
+
+/* Pre-grace-period preparation. */
+static void rcu_tasks_pregp_step(void)
+{
+ /*
+ * Wait for all pre-existing t->on_rq and t->nvcsw transitions
+ * to complete. Invoking synchronize_rcu() suffices because all
+ * these transitions occur with interrupts disabled. Without this
+ * synchronize_rcu(), a read-side critical section that started
+ * before the grace period might be incorrectly seen as having
+ * started after the grace period.
+ *
+ * This synchronize_rcu() also dispenses with the need for a
+ * memory barrier on the first store to t->rcu_tasks_holdout,
+ * as it forces the store to happen after the beginning of the
+ * grace period.
+ */
+ synchronize_rcu();
+}
+
+/* Per-task initial processing. */
+static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop)
+{
+ if (t != current && READ_ONCE(t->on_rq) && !is_idle_task(t)) {
+ get_task_struct(t);
+ t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+ WRITE_ONCE(t->rcu_tasks_holdout, true);
+ list_add(&t->rcu_tasks_holdout_list, hop);
+ }
+}
+
+/* Processing between scanning taskslist and draining the holdout list. */
+static void rcu_tasks_postscan(struct list_head *hop)
+{
+ /*
+ * Wait for tasks that are in the process of exiting. This
+ * does only part of the job, ensuring that all tasks that were
+ * previously exiting reach the point where they have disabled
+ * preemption, allowing the later synchronize_rcu() to finish
+ * the job.
+ */
+ synchronize_srcu(&tasks_rcu_exit_srcu);
+}
+
+/* See if tasks are still holding out, complain if so. */
+static void check_holdout_task(struct task_struct *t,
+ bool needreport, bool *firstreport)
+{
+ int cpu;
+
+ if (!READ_ONCE(t->rcu_tasks_holdout) ||
+ t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+ !READ_ONCE(t->on_rq) ||
+ (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
+ !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
+ WRITE_ONCE(t->rcu_tasks_holdout, false);
+ list_del_init(&t->rcu_tasks_holdout_list);
+ put_task_struct(t);
+ return;
+ }
+ rcu_request_urgent_qs_task(t);
+ if (!needreport)
+ return;
+ if (*firstreport) {
+ pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
+ *firstreport = false;
+ }
+ cpu = task_cpu(t);
+ pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
+ t, ".I"[is_idle_task(t)],
+ "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
+ t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
+ t->rcu_tasks_idle_cpu, cpu);
+ sched_show_task(t);
+}
+
+/* Scan the holdout lists for tasks no longer holding out. */
+static void check_all_holdout_tasks(struct list_head *hop,
+ bool needreport, bool *firstreport)
+{
+ struct task_struct *t, *t1;
+
+ list_for_each_entry_safe(t, t1, hop, rcu_tasks_holdout_list) {
+ check_holdout_task(t, needreport, firstreport);
+ cond_resched();
+ }
+}
+
+/* Finish off the Tasks-RCU grace period. */
+static void rcu_tasks_postgp(struct rcu_tasks *rtp)
+{
+ /*
+ * Because ->on_rq and ->nvcsw are not guaranteed to have a full
+ * memory barriers prior to them in the schedule() path, memory
+ * reordering on other CPUs could cause their RCU-tasks read-side
+ * critical sections to extend past the end of the grace period.
+ * However, because these ->nvcsw updates are carried out with
+ * interrupts disabled, we can use synchronize_rcu() to force the
+ * needed ordering on all such CPUs.
+ *
+ * This synchronize_rcu() also confines all ->rcu_tasks_holdout
+ * accesses to be within the grace period, avoiding the need for
+ * memory barriers for ->rcu_tasks_holdout accesses.
+ *
+ * In addition, this synchronize_rcu() waits for exiting tasks
+ * to complete their final preempt_disable() region of execution,
+ * cleaning up after the synchronize_srcu() above.
+ */
+ synchronize_rcu();
+}
+
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks");
+
+/**
+ * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks() assumes
+ * that the read-side critical sections end at a voluntary context
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution. As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
+{
+ call_rcu_tasks_generic(rhp, func, &rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks);
+
+/**
+ * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed. These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
+ * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function
+ * preambles and profiling hooks. The synchronize_rcu_tasks() function
+ * is not (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks(void)
+{
+ synchronize_rcu_tasks_generic(&rcu_tasks);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
+
+/**
+ * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks(void)
+{
+ /* There is only one callback queue, so this is easy. ;-) */
+ synchronize_rcu_tasks();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
+
+static int __init rcu_spawn_tasks_kthread(void)
+{
+ rcu_tasks.gp_sleep = HZ / 10;
+ rcu_tasks.init_fract = 10;
+ rcu_tasks.pregp_func = rcu_tasks_pregp_step;
+ rcu_tasks.pertask_func = rcu_tasks_pertask;
+ rcu_tasks.postscan_func = rcu_tasks_postscan;
+ rcu_tasks.holdouts_func = check_all_holdout_tasks;
+ rcu_tasks.postgp_func = rcu_tasks_postgp;
+ rcu_spawn_tasks_kthread_generic(&rcu_tasks);
+ return 0;
+}
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_classic_gp_kthread(void)
+{
+ show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+/* Do the srcu_read_lock() for the above synchronize_srcu(). */
+void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
+{
+ preempt_disable();
+ current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
+ preempt_enable();
+}
+
+/* Do the srcu_read_unlock() for the above synchronize_srcu(). */
+void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
+{
+ struct task_struct *t = current;
+
+ preempt_disable();
+ __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx);
+ preempt_enable();
+ exit_tasks_rcu_finish_trace(t);
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU */
+static inline void show_rcu_tasks_classic_gp_kthread(void) { }
+void exit_tasks_rcu_start(void) { }
+void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
+#endif /* #else #ifdef CONFIG_TASKS_RCU */
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+
+////////////////////////////////////////////////////////////////////////
+//
+// "Rude" variant of Tasks RCU, inspired by Steve Rostedt's trick of
+// passing an empty function to schedule_on_each_cpu(). This approach
+// provides an asynchronous call_rcu_tasks_rude() API and batching
+// of concurrent calls to the synchronous synchronize_rcu_rude() API.
+// This sends IPIs far and wide and induces otherwise unnecessary context
+// switches on all online CPUs, whether idle or not.
+
+// Empty function to allow workqueues to force a context switch.
+static void rcu_tasks_be_rude(struct work_struct *work)
+{
+}
+
+// Wait for one rude RCU-tasks grace period.
+static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp)
+{
+ rtp->n_ipis += cpumask_weight(cpu_online_mask);
+ schedule_on_each_cpu(rcu_tasks_be_rude);
+}
+
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_rude, rcu_tasks_rude_wait_gp, call_rcu_tasks_rude,
+ "RCU Tasks Rude");
+
+/**
+ * call_rcu_tasks_rude() - Queue a callback rude task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_rude()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution. As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_rude(struct rcu_head *rhp, rcu_callback_t func)
+{
+ call_rcu_tasks_generic(rhp, func, &rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_rude);
+
+/**
+ * synchronize_rcu_tasks_rude - wait for a rude rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a rude rcu-tasks
+ * grace period has elapsed, in other words after all currently
+ * executing rcu-tasks read-side critical sections have elapsed. These
+ * read-side critical sections are delimited by calls to schedule(),
+ * cond_resched_tasks_rcu_qs(), userspace execution, and (in theory,
+ * anyway) cond_resched().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks. The synchronize_rcu_tasks_rude() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_rude(void)
+{
+ synchronize_rcu_tasks_generic(&rcu_tasks_rude);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
+
+/**
+ * rcu_barrier_tasks_rude - Wait for in-flight call_rcu_tasks_rude() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_rude(void)
+{
+ /* There is only one callback queue, so this is easy. ;-) */
+ synchronize_rcu_tasks_rude();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
+
+static int __init rcu_spawn_tasks_rude_kthread(void)
+{
+ rcu_tasks_rude.gp_sleep = HZ / 10;
+ rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
+ return 0;
+}
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_rude_gp_kthread(void)
+{
+ show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
+static void show_rcu_tasks_rude_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
+
+////////////////////////////////////////////////////////////////////////
+//
+// Tracing variant of Tasks RCU. This variant is designed to be used
+// to protect tracing hooks, including those of BPF. This variant
+// therefore:
+//
+// 1. Has explicit read-side markers to allow finite grace periods
+// in the face of in-kernel loops for PREEMPT=n builds.
+//
+// 2. Protects code in the idle loop, exception entry/exit, and
+// CPU-hotplug code paths, similar to the capabilities of SRCU.
+//
+// 3. Avoids expensive read-side instruction, having overhead similar
+// to that of Preemptible RCU.
+//
+// There are of course downsides. The grace-period code can send IPIs to
+// CPUs, even when those CPUs are in the idle loop or in nohz_full userspace.
+// It is necessary to scan the full tasklist, much as for Tasks RCU. There
+// is a single callback queue guarded by a single lock, again, much as for
+// Tasks RCU. If needed, these downsides can be at least partially remedied.
+//
+// Perhaps most important, this variant of RCU does not affect the vanilla
+// flavors, rcu_preempt and rcu_sched. The fact that RCU Tasks Trace
+// readers can operate from idle, offline, and exception entry/exit in no
+// way allows rcu_preempt and rcu_sched readers to also do so.
+
+// The lockdep state must be outside of #ifdef to be useful.
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static struct lock_class_key rcu_lock_trace_key;
+struct lockdep_map rcu_trace_lock_map =
+ STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_trace", &rcu_lock_trace_key);
+EXPORT_SYMBOL_GPL(rcu_trace_lock_map);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+
+static atomic_t trc_n_readers_need_end; // Number of waited-for readers.
+static DECLARE_WAIT_QUEUE_HEAD(trc_wait); // List of holdout tasks.
+
+// Record outstanding IPIs to each CPU. No point in sending two...
+static DEFINE_PER_CPU(bool, trc_ipi_to_cpu);
+
+// The number of detections of task quiescent state relying on
+// heavyweight readers executing explicit memory barriers.
+static unsigned long n_heavy_reader_attempts;
+static unsigned long n_heavy_reader_updates;
+static unsigned long n_heavy_reader_ofl_updates;
+
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func);
+DEFINE_RCU_TASKS(rcu_tasks_trace, rcu_tasks_wait_gp, call_rcu_tasks_trace,
+ "RCU Tasks Trace");
+
+/*
+ * This irq_work handler allows rcu_read_unlock_trace() to be invoked
+ * while the scheduler locks are held.
+ */
+static void rcu_read_unlock_iw(struct irq_work *iwp)
+{
+ wake_up(&trc_wait);
+}
+static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw);
+
+/* If we are the last reader, wake up the grace-period kthread. */
+void rcu_read_unlock_trace_special(struct task_struct *t, int nesting)
+{
+ int nq = t->trc_reader_special.b.need_qs;
+
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) &&
+ t->trc_reader_special.b.need_mb)
+ smp_mb(); // Pairs with update-side barriers.
+ // Update .need_qs before ->trc_reader_nesting for irq/NMI handlers.
+ if (nq)
+ WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+ WRITE_ONCE(t->trc_reader_nesting, nesting);
+ if (nq && atomic_dec_and_test(&trc_n_readers_need_end))
+ irq_work_queue(&rcu_tasks_trace_iw);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_trace_special);
+
+/* Add a task to the holdout list, if it is not already on the list. */
+static void trc_add_holdout(struct task_struct *t, struct list_head *bhp)
+{
+ if (list_empty(&t->trc_holdout_list)) {
+ get_task_struct(t);
+ list_add(&t->trc_holdout_list, bhp);
+ }
+}
+
+/* Remove a task from the holdout list, if it is in fact present. */
+static void trc_del_holdout(struct task_struct *t)
+{
+ if (!list_empty(&t->trc_holdout_list)) {
+ list_del_init(&t->trc_holdout_list);
+ put_task_struct(t);
+ }
+}
+
+/* IPI handler to check task state. */
+static void trc_read_check_handler(void *t_in)
+{
+ struct task_struct *t = current;
+ struct task_struct *texp = t_in;
+
+ // If the task is no longer running on this CPU, leave.
+ if (unlikely(texp != t)) {
+ if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+ wake_up(&trc_wait);
+ goto reset_ipi; // Already on holdout list, so will check later.
+ }
+
+ // If the task is not in a read-side critical section, and
+ // if this is the last reader, awaken the grace-period kthread.
+ if (likely(!t->trc_reader_nesting)) {
+ if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+ wake_up(&trc_wait);
+ // Mark as checked after decrement to avoid false
+ // positives on the above WARN_ON_ONCE().
+ WRITE_ONCE(t->trc_reader_checked, true);
+ goto reset_ipi;
+ }
+ // If we are racing with an rcu_read_unlock_trace(), try again later.
+ if (unlikely(t->trc_reader_nesting < 0)) {
+ if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end)))
+ wake_up(&trc_wait);
+ goto reset_ipi;
+ }
+ WRITE_ONCE(t->trc_reader_checked, true);
+
+ // Get here if the task is in a read-side critical section. Set
+ // its state so that it will awaken the grace-period kthread upon
+ // exit from that critical section.
+ WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+ WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+
+reset_ipi:
+ // Allow future IPIs to be sent on CPU and for task.
+ // Also order this IPI handler against any later manipulations of
+ // the intended task.
+ smp_store_release(&per_cpu(trc_ipi_to_cpu, smp_processor_id()), false); // ^^^
+ smp_store_release(&texp->trc_ipi_to_cpu, -1); // ^^^
+}
+
+/* Callback function for scheduler to check locked-down task. */
+static bool trc_inspect_reader(struct task_struct *t, void *arg)
+{
+ int cpu = task_cpu(t);
+ bool in_qs = false;
+ bool ofl = cpu_is_offline(cpu);
+
+ if (task_curr(t)) {
+ WARN_ON_ONCE(ofl && !is_idle_task(t));
+
+ // If no chance of heavyweight readers, do it the hard way.
+ if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ return false;
+
+ // If heavyweight readers are enabled on the remote task,
+ // we can inspect its state despite its currently running.
+ // However, we cannot safely change its state.
+ n_heavy_reader_attempts++;
+ if (!ofl && // Check for "running" idle tasks on offline CPUs.
+ !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting))
+ return false; // No quiescent state, do it the hard way.
+ n_heavy_reader_updates++;
+ if (ofl)
+ n_heavy_reader_ofl_updates++;
+ in_qs = true;
+ } else {
+ in_qs = likely(!t->trc_reader_nesting);
+ }
+
+ // Mark as checked so that the grace-period kthread will
+ // remove it from the holdout list.
+ t->trc_reader_checked = true;
+
+ if (in_qs)
+ return true; // Already in quiescent state, done!!!
+
+ // The task is in a read-side critical section, so set up its
+ // state so that it will awaken the grace-period kthread upon exit
+ // from that critical section.
+ atomic_inc(&trc_n_readers_need_end); // One more to wait on.
+ WARN_ON_ONCE(t->trc_reader_special.b.need_qs);
+ WRITE_ONCE(t->trc_reader_special.b.need_qs, true);
+ return true;
+}
+
+/* Attempt to extract the state for the specified task. */
+static void trc_wait_for_one_reader(struct task_struct *t,
+ struct list_head *bhp)
+{
+ int cpu;
+
+ // If a previous IPI is still in flight, let it complete.
+ if (smp_load_acquire(&t->trc_ipi_to_cpu) != -1) // Order IPI
+ return;
+
+ // The current task had better be in a quiescent state.
+ if (t == current) {
+ t->trc_reader_checked = true;
+ WARN_ON_ONCE(t->trc_reader_nesting);
+ return;
+ }
+
+ // Attempt to nail down the task for inspection.
+ get_task_struct(t);
+ if (try_invoke_on_locked_down_task(t, trc_inspect_reader, NULL)) {
+ put_task_struct(t);
+ return;
+ }
+ put_task_struct(t);
+
+ // If currently running, send an IPI, either way, add to list.
+ trc_add_holdout(t, bhp);
+ if (task_curr(t) &&
+ time_after(jiffies + 1, rcu_tasks_trace.gp_start + rcu_task_ipi_delay)) {
+ // The task is currently running, so try IPIing it.
+ cpu = task_cpu(t);
+
+ // If there is already an IPI outstanding, let it happen.
+ if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0)
+ return;
+
+ atomic_inc(&trc_n_readers_need_end);
+ per_cpu(trc_ipi_to_cpu, cpu) = true;
+ t->trc_ipi_to_cpu = cpu;
+ rcu_tasks_trace.n_ipis++;
+ if (smp_call_function_single(cpu,
+ trc_read_check_handler, t, 0)) {
+ // Just in case there is some other reason for
+ // failure than the target CPU being offline.
+ rcu_tasks_trace.n_ipis_fails++;
+ per_cpu(trc_ipi_to_cpu, cpu) = false;
+ t->trc_ipi_to_cpu = cpu;
+ if (atomic_dec_and_test(&trc_n_readers_need_end)) {
+ WARN_ON_ONCE(1);
+ wake_up(&trc_wait);
+ }
+ }
+ }
+}
+
+/* Initialize for a new RCU-tasks-trace grace period. */
+static void rcu_tasks_trace_pregp_step(void)
+{
+ int cpu;
+
+ // Allow for fast-acting IPIs.
+ atomic_set(&trc_n_readers_need_end, 1);
+
+ // There shouldn't be any old IPIs, but...
+ for_each_possible_cpu(cpu)
+ WARN_ON_ONCE(per_cpu(trc_ipi_to_cpu, cpu));
+
+ // Disable CPU hotplug across the tasklist scan.
+ // This also waits for all readers in CPU-hotplug code paths.
+ cpus_read_lock();
+}
+
+/* Do first-round processing for the specified task. */
+static void rcu_tasks_trace_pertask(struct task_struct *t,
+ struct list_head *hop)
+{
+ // During early boot when there is only the one boot CPU, there
+ // is no idle task for the other CPUs. Just return.
+ if (unlikely(t == NULL))
+ return;
+
+ WRITE_ONCE(t->trc_reader_special.b.need_qs, false);
+ WRITE_ONCE(t->trc_reader_checked, false);
+ t->trc_ipi_to_cpu = -1;
+ trc_wait_for_one_reader(t, hop);
+}
+
+/*
+ * Do intermediate processing between task and holdout scans and
+ * pick up the idle tasks.
+ */
+static void rcu_tasks_trace_postscan(struct list_head *hop)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ rcu_tasks_trace_pertask(idle_task(cpu), hop);
+
+ // Re-enable CPU hotplug now that the tasklist scan has completed.
+ cpus_read_unlock();
+
+ // Wait for late-stage exiting tasks to finish exiting.
+ // These might have passed the call to exit_tasks_rcu_finish().
+ synchronize_rcu();
+ // Any tasks that exit after this point will set ->trc_reader_checked.
+}
+
+/* Show the state of a task stalling the current RCU tasks trace GP. */
+static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
+{
+ int cpu;
+
+ if (*firstreport) {
+ pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
+ *firstreport = false;
+ }
+ // FIXME: This should attempt to use try_invoke_on_nonrunning_task().
+ cpu = task_cpu(t);
+ pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+ t->pid,
+ ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0],
+ ".i"[is_idle_task(t)],
+ ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)],
+ t->trc_reader_nesting,
+ " N"[!!t->trc_reader_special.b.need_qs],
+ cpu);
+ sched_show_task(t);
+}
+
+/* List stalled IPIs for RCU tasks trace. */
+static void show_stalled_ipi_trace(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ if (per_cpu(trc_ipi_to_cpu, cpu))
+ pr_alert("\tIPI outstanding to CPU %d\n", cpu);
+}
+
+/* Do one scan of the holdout list. */
+static void check_all_holdout_tasks_trace(struct list_head *hop,
+ bool needreport, bool *firstreport)
+{
+ struct task_struct *g, *t;
+
+ // Disable CPU hotplug across the holdout list scan.
+ cpus_read_lock();
+
+ list_for_each_entry_safe(t, g, hop, trc_holdout_list) {
+ // If safe and needed, try to check the current task.
+ if (READ_ONCE(t->trc_ipi_to_cpu) == -1 &&
+ !READ_ONCE(t->trc_reader_checked))
+ trc_wait_for_one_reader(t, hop);
+
+ // If check succeeded, remove this task from the list.
+ if (READ_ONCE(t->trc_reader_checked))
+ trc_del_holdout(t);
+ else if (needreport)
+ show_stalled_task_trace(t, firstreport);
+ }
+
+ // Re-enable CPU hotplug now that the holdout list scan has completed.
+ cpus_read_unlock();
+
+ if (needreport) {
+ if (firstreport)
+ pr_err("INFO: rcu_tasks_trace detected stalls? (Late IPI?)\n");
+ show_stalled_ipi_trace();
+ }
+}
+
+/* Wait for grace period to complete and provide ordering. */
+static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
+{
+ bool firstreport;
+ struct task_struct *g, *t;
+ LIST_HEAD(holdouts);
+ long ret;
+
+ // Remove the safety count.
+ smp_mb__before_atomic(); // Order vs. earlier atomics
+ atomic_dec(&trc_n_readers_need_end);
+ smp_mb__after_atomic(); // Order vs. later atomics
+
+ // Wait for readers.
+ set_tasks_gp_state(rtp, RTGS_WAIT_READERS);
+ for (;;) {
+ ret = wait_event_idle_exclusive_timeout(
+ trc_wait,
+ atomic_read(&trc_n_readers_need_end) == 0,
+ READ_ONCE(rcu_task_stall_timeout));
+ if (ret)
+ break; // Count reached zero.
+ // Stall warning time, so make a list of the offenders.
+ rcu_read_lock();
+ for_each_process_thread(g, t)
+ if (READ_ONCE(t->trc_reader_special.b.need_qs))
+ trc_add_holdout(t, &holdouts);
+ rcu_read_unlock();
+ firstreport = true;
+ list_for_each_entry_safe(t, g, &holdouts, trc_holdout_list) {
+ if (READ_ONCE(t->trc_reader_special.b.need_qs))
+ show_stalled_task_trace(t, &firstreport);
+ trc_del_holdout(t); // Release task_struct reference.
+ }
+ if (firstreport)
+ pr_err("INFO: rcu_tasks_trace detected stalls? (Counter/taskslist mismatch?)\n");
+ show_stalled_ipi_trace();
+ pr_err("\t%d holdouts\n", atomic_read(&trc_n_readers_need_end));
+ }
+ smp_mb(); // Caller's code must be ordered after wakeup.
+ // Pairs with pretty much every ordering primitive.
+}
+
+/* Report any needed quiescent state for this exiting task. */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t)
+{
+ WRITE_ONCE(t->trc_reader_checked, true);
+ WARN_ON_ONCE(t->trc_reader_nesting);
+ WRITE_ONCE(t->trc_reader_nesting, 0);
+ if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)))
+ rcu_read_unlock_trace_special(t, 0);
+}
+
+/**
+ * call_rcu_tasks_trace() - Queue a callback trace task-based grace period
+ * @rhp: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all currently executing RCU
+ * read-side critical sections have completed. call_rcu_tasks_trace()
+ * assumes that the read-side critical sections end at context switch,
+ * cond_resched_rcu_qs(), or transition to usermode execution. As such,
+ * there are no read-side primitives analogous to rcu_read_lock() and
+ * rcu_read_unlock() because this primitive is intended to determine
+ * that all tasks have passed through a safe state, not so much for
+ * data-strcuture synchronization.
+ *
+ * See the description of call_rcu() for more detailed information on
+ * memory ordering guarantees.
+ */
+void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func)
+{
+ call_rcu_tasks_generic(rhp, func, &rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(call_rcu_tasks_trace);
+
+/**
+ * synchronize_rcu_tasks_trace - wait for a trace rcu-tasks grace period
+ *
+ * Control will return to the caller some time after a trace rcu-tasks
+ * grace period has elapsed, in other words after all currently executing
+ * rcu-tasks read-side critical sections have elapsed. These read-side
+ * critical sections are delimited by calls to rcu_read_lock_trace()
+ * and rcu_read_unlock_trace().
+ *
+ * This is a very specialized primitive, intended only for a few uses in
+ * tracing and other situations requiring manipulation of function preambles
+ * and profiling hooks. The synchronize_rcu_tasks_trace() function is not
+ * (yet) intended for heavy use from multiple CPUs.
+ *
+ * See the description of synchronize_rcu() for more detailed information
+ * on memory ordering guarantees.
+ */
+void synchronize_rcu_tasks_trace(void)
+{
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_trace_lock_map), "Illegal synchronize_rcu_tasks_trace() in RCU Tasks Trace read-side critical section");
+ synchronize_rcu_tasks_generic(&rcu_tasks_trace);
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace);
+
+/**
+ * rcu_barrier_tasks_trace - Wait for in-flight call_rcu_tasks_trace() callbacks.
+ *
+ * Although the current implementation is guaranteed to wait, it is not
+ * obligated to, for example, if there are no pending callbacks.
+ */
+void rcu_barrier_tasks_trace(void)
+{
+ /* There is only one callback queue, so this is easy. ;-) */
+ synchronize_rcu_tasks_trace();
+}
+EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
+
+static int __init rcu_spawn_tasks_trace_kthread(void)
+{
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
+ rcu_tasks_trace.gp_sleep = HZ / 10;
+ rcu_tasks_trace.init_fract = 10;
+ } else {
+ rcu_tasks_trace.gp_sleep = HZ / 200;
+ if (rcu_tasks_trace.gp_sleep <= 0)
+ rcu_tasks_trace.gp_sleep = 1;
+ rcu_tasks_trace.init_fract = HZ / 5;
+ if (rcu_tasks_trace.init_fract <= 0)
+ rcu_tasks_trace.init_fract = 1;
+ }
+ rcu_tasks_trace.pregp_func = rcu_tasks_trace_pregp_step;
+ rcu_tasks_trace.pertask_func = rcu_tasks_trace_pertask;
+ rcu_tasks_trace.postscan_func = rcu_tasks_trace_postscan;
+ rcu_tasks_trace.holdouts_func = check_all_holdout_tasks_trace;
+ rcu_tasks_trace.postgp_func = rcu_tasks_trace_postgp;
+ rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace);
+ return 0;
+}
+
+#ifndef CONFIG_TINY_RCU
+static void show_rcu_tasks_trace_gp_kthread(void)
+{
+ char buf[64];
+
+ sprintf(buf, "N%d h:%lu/%lu/%lu", atomic_read(&trc_n_readers_need_end),
+ data_race(n_heavy_reader_ofl_updates),
+ data_race(n_heavy_reader_updates),
+ data_race(n_heavy_reader_attempts));
+ show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+#else /* #ifdef CONFIG_TASKS_TRACE_RCU */
+static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
+static inline void show_rcu_tasks_trace_gp_kthread(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
+
+#ifndef CONFIG_TINY_RCU
+void show_rcu_tasks_gp_kthreads(void)
+{
+ show_rcu_tasks_classic_gp_kthread();
+ show_rcu_tasks_rude_gp_kthread();
+ show_rcu_tasks_trace_gp_kthread();
+}
+#endif /* #ifndef CONFIG_TINY_RCU */
+
+void __init rcu_init_tasks_generic(void)
+{
+#ifdef CONFIG_TASKS_RCU
+ rcu_spawn_tasks_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_RUDE_RCU
+ rcu_spawn_tasks_rude_kthread();
+#endif
+
+#ifdef CONFIG_TASKS_TRACE_RCU
+ rcu_spawn_tasks_trace_kthread();
+#endif
+}
+
+#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+static inline void rcu_tasks_bootup_oddness(void) {}
+void show_rcu_tasks_gp_kthreads(void) {}
+#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 477b4eb..aa897c3 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -22,6 +22,8 @@
#include <linux/time.h>
#include <linux/cpu.h>
#include <linux/prefetch.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
#include "rcu.h"
@@ -73,6 +75,31 @@
}
}
+/*
+ * Reclaim the specified callback, either by invoking it for non-kfree cases or
+ * freeing it directly (for kfree). Return true if kfreeing, false otherwise.
+ */
+static inline bool rcu_reclaim_tiny(struct rcu_head *head)
+{
+ rcu_callback_t f;
+ unsigned long offset = (unsigned long)head->func;
+
+ rcu_lock_acquire(&rcu_callback_map);
+ if (__is_kvfree_rcu_offset(offset)) {
+ trace_rcu_invoke_kvfree_callback("", head, offset);
+ kvfree((void *)head - offset);
+ rcu_lock_release(&rcu_callback_map);
+ return true;
+ }
+
+ trace_rcu_invoke_callback("", head);
+ f = head->func;
+ WRITE_ONCE(head->func, (rcu_callback_t)0L);
+ f(head);
+ rcu_lock_release(&rcu_callback_map);
+ return false;
+}
+
/* Invoke the RCU callbacks whose grace period has elapsed. */
static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
{
@@ -100,7 +127,7 @@
prefetch(next);
debug_rcu_head_unqueue(list);
local_bh_disable();
- __rcu_reclaim("", list);
+ rcu_reclaim_tiny(list);
local_bh_enable();
list = next;
}
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 11ae274..844c358 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1,12 +1,12 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * Read-Copy Update mechanism for mutual exclusion
+ * Read-Copy Update mechanism for mutual exclusion (tree-based version)
*
* Copyright IBM Corporation, 2008
*
* Authors: Dipankar Sarma <dipankar@in.ibm.com>
* Manfred Spraul <manfred@colorfullife.com>
- * Paul E. McKenney <paulmck@linux.ibm.com> Hierarchical version
+ * Paul E. McKenney <paulmck@linux.ibm.com>
*
* Based on the original work by Paul McKenney <paulmck@linux.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
@@ -43,7 +43,6 @@
#include <uapi/linux/sched/types.h>
#include <linux/prefetch.h>
#include <linux/delay.h>
-#include <linux/stop_machine.h>
#include <linux/random.h>
#include <linux/trace_events.h>
#include <linux/suspend.h>
@@ -55,8 +54,12 @@
#include <linux/oom.h>
#include <linux/smpboot.h>
#include <linux/jiffies.h>
+#include <linux/slab.h>
#include <linux/sched/isolation.h>
#include <linux/sched/clock.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/kasan.h>
#include "../time/tick-internal.h"
#include "tree.h"
@@ -75,16 +78,13 @@
*/
#define RCU_DYNTICK_CTRL_MASK 0x1
#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
-#ifndef rcu_eqs_special_exit
-#define rcu_eqs_special_exit() do { } while (0)
-#endif
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
.dynticks_nesting = 1,
.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
};
-struct rcu_state rcu_state = {
+static struct rcu_state rcu_state = {
.level = { &rcu_state.node[0] },
.gp_state = RCU_GP_IDLE,
.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT,
@@ -100,7 +100,7 @@
static bool dump_tree;
module_param(dump_tree, bool, 0444);
/* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
-static bool use_softirq = 1;
+static bool use_softirq = true;
module_param(use_softirq, bool, 0444);
/* Control rcu_node-tree auto-balancing at boot time. */
static bool rcu_fanout_exact;
@@ -150,6 +150,7 @@
static void invoke_rcu_core(void);
static void rcu_report_exp_rdp(struct rcu_data *rdp);
static void sync_sched_exp_online_cleanup(int cpu);
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp);
/* rcuc/rcub kthread realtime priority */
static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
@@ -164,6 +165,21 @@
static int gp_cleanup_delay;
module_param(gp_cleanup_delay, int, 0444);
+// Add delay to rcu_read_unlock() for strict grace periods.
+static int rcu_unlock_delay;
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
+/*
+ * This rcu parameter is runtime-read-only. It reflects
+ * a minimum allowed number of objects which can be cached
+ * per-CPU. Object size is equal to one page. This value
+ * can be changed at boot time.
+ */
+static int rcu_min_cached_objs = 5;
+module_param(rcu_min_cached_objs, int, 0444);
+
/* Retrieve RCU kthreads priority for rcutorture */
int rcu_get_gp_kthreads_prio(void)
{
@@ -188,7 +204,7 @@
* held, but the bit corresponding to the current CPU will be stable
* in most contexts.
*/
-unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
+static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
{
return READ_ONCE(rnp->qsmaskinitnext);
}
@@ -224,9 +240,11 @@
/*
* Record entry into an extended quiescent state. This is only to be
- * called when not already in an extended quiescent state.
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
*/
-static void rcu_dynticks_eqs_enter(void)
+static noinstr void rcu_dynticks_eqs_enter(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
@@ -236,8 +254,9 @@
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
- seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
- /* Better be in an extended quiescent state! */
+ rcu_dynticks_task_trace_enter(); // Before ->dynticks update!
+ seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+ // RCU is no longer watching. Better be in extended quiescent state!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
(seq & RCU_DYNTICK_CTRL_CTR));
/* Better not have special action (TLB flush) pending! */
@@ -247,9 +266,10 @@
/*
* Record exit from an extended quiescent state. This is only to be
- * called from an extended quiescent state.
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
*/
-static void rcu_dynticks_eqs_exit(void)
+static noinstr void rcu_dynticks_eqs_exit(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
int seq;
@@ -259,14 +279,14 @@
* and we also must force ordering with the next RCU read-side
* critical section.
*/
- seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+ seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+ // RCU is now watching. Better not be in an extended quiescent state!
+ rcu_dynticks_task_trace_exit(); // After ->dynticks update!
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
!(seq & RCU_DYNTICK_CTRL_CTR));
if (seq & RCU_DYNTICK_CTRL_MASK) {
- atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
+ arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
smp_mb__after_atomic(); /* _exit after clearing mask. */
- /* Prefer duplicate flushes to losing a flush. */
- rcu_eqs_special_exit();
}
}
@@ -294,18 +314,18 @@
*
* No ordering, as we are sampling CPU-local information.
*/
-bool rcu_dynticks_curr_cpu_in_eqs(void)
+static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
- return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+ return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
}
/*
* Snapshot the ->dynticks counter with full ordering so as to allow
* stable comparison of this counter with past and future snapshots.
*/
-int rcu_dynticks_snap(struct rcu_data *rdp)
+static int rcu_dynticks_snap(struct rcu_data *rdp)
{
int snap = atomic_add_return(0, &rdp->dynticks);
@@ -332,6 +352,28 @@
}
/*
+ * Return true if the referenced integer is zero while the specified
+ * CPU remains within a single extended quiescent state.
+ */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
+{
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ int snap;
+
+ // If not quiescent, force back to earlier extended quiescent state.
+ snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
+ RCU_DYNTICK_CTRL_CTR);
+
+ smp_rmb(); // Order ->dynticks and *vp reads.
+ if (READ_ONCE(*vp))
+ return false; // Non-zero, so report failure;
+ smp_rmb(); // Order *vp read and ->dynticks re-read.
+
+ // If still in the same extended quiescent state, we are good!
+ return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
+}
+
+/*
* Set the special (bottom) bit of the specified CPU so that it
* will take special action (such as flushing its TLB) on the
* next exit from an extended quiescent state. Returns true if
@@ -342,14 +384,17 @@
{
int old;
int new;
+ int new_old;
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+ new_old = atomic_read(&rdp->dynticks);
do {
- old = atomic_read(&rdp->dynticks);
+ old = new_old;
if (old & RCU_DYNTICK_CTRL_CTR)
return false;
new = old | RCU_DYNTICK_CTRL_MASK;
- } while (atomic_cmpxchg(&rdp->dynticks, old, new) != old);
+ new_old = atomic_cmpxchg(&rdp->dynticks, old, new);
+ } while (new_old != old);
return true;
}
@@ -364,7 +409,7 @@
*
* The caller must have disabled interrupts and must not be idle.
*/
-static void __maybe_unused rcu_momentary_dyntick_idle(void)
+notrace void rcu_momentary_dyntick_idle(void)
{
int special;
@@ -375,18 +420,26 @@
WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
rcu_preempt_deferred_qs(current);
}
+EXPORT_SYMBOL_GPL(rcu_momentary_dyntick_idle);
/**
- * rcu_is_cpu_rrupt_from_idle - see if interrupted from idle
+ * rcu_is_cpu_rrupt_from_idle - see if 'interrupted' from idle
*
* If the current CPU is idle and running at a first-level (not nested)
- * interrupt from idle, return true. The caller must have at least
- * disabled preemption.
+ * interrupt, or directly, from idle, return true.
+ *
+ * The caller must have at least disabled IRQs.
*/
static int rcu_is_cpu_rrupt_from_idle(void)
{
- /* Called only from within the scheduling-clock interrupt */
- lockdep_assert_in_irq();
+ long nesting;
+
+ /*
+ * Usually called from the tick; but also used from smp_function_call()
+ * for expedited grace periods. This latter can result in running from
+ * the idle task, instead of an actual IPI.
+ */
+ lockdep_assert_irqs_disabled();
/* Check for counter underflows */
RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) < 0,
@@ -395,26 +448,38 @@
"RCU dynticks_nmi_nesting counter underflow/zero!");
/* Are we at first interrupt nesting level? */
- if (__this_cpu_read(rcu_data.dynticks_nmi_nesting) != 1)
+ nesting = __this_cpu_read(rcu_data.dynticks_nmi_nesting);
+ if (nesting > 1)
return false;
+ /*
+ * If we're not in an interrupt, we must be in the idle task!
+ */
+ WARN_ON_ONCE(!nesting && !is_idle_task(current));
+
/* Does CPU appear to be idle from an RCU standpoint? */
return __this_cpu_read(rcu_data.dynticks_nesting) == 0;
}
-#define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch ... */
-#define DEFAULT_MAX_RCU_BLIMIT 10000 /* ... even during callback flood. */
+#define DEFAULT_RCU_BLIMIT (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 1000 : 10)
+ // Maximum callbacks per rcu_do_batch ...
+#define DEFAULT_MAX_RCU_BLIMIT 10000 // ... even during callback flood.
static long blimit = DEFAULT_RCU_BLIMIT;
-#define DEFAULT_RCU_QHIMARK 10000 /* If this many pending, ignore blimit. */
+#define DEFAULT_RCU_QHIMARK 10000 // If this many pending, ignore blimit.
static long qhimark = DEFAULT_RCU_QHIMARK;
-#define DEFAULT_RCU_QLOMARK 100 /* Once only this many pending, use blimit. */
+#define DEFAULT_RCU_QLOMARK 100 // Once only this many pending, use blimit.
static long qlowmark = DEFAULT_RCU_QLOMARK;
+#define DEFAULT_RCU_QOVLD_MULT 2
+#define DEFAULT_RCU_QOVLD (DEFAULT_RCU_QOVLD_MULT * DEFAULT_RCU_QHIMARK)
+static long qovld = DEFAULT_RCU_QOVLD; // If this many pending, hammer QS.
+static long qovld_calc = -1; // No pre-initialization lock acquisitions!
module_param(blimit, long, 0444);
module_param(qhimark, long, 0444);
module_param(qlowmark, long, 0444);
+module_param(qovld, long, 0444);
-static ulong jiffies_till_first_fqs = ULONG_MAX;
+static ulong jiffies_till_first_fqs = IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ? 0 : ULONG_MAX;
static ulong jiffies_till_next_fqs = ULONG_MAX;
static bool rcu_kick_kthreads;
static int rcu_divisor = 7;
@@ -496,7 +561,7 @@
module_param(rcu_kick_kthreads, bool, 0644);
static void force_qs_rnp(int (*f)(struct rcu_data *rdp));
-static int rcu_pending(void);
+static int rcu_pending(int user);
/*
* Return the number of RCU GPs completed thus far for debug & stats.
@@ -528,16 +593,6 @@
}
/*
- * Convert a ->gp_state value to a character string.
- */
-static const char *gp_state_getname(short gs)
-{
- if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
- return "???";
- return gp_state_names[gs];
-}
-
-/*
* Send along grace-period-related data for rcutorture diagnostics.
*/
void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
@@ -562,7 +617,7 @@
* the possibility of usermode upcalls having messed up our count
* of interrupt nesting level during the prior busy period.
*/
-static void rcu_eqs_enter(bool user)
+static noinstr void rcu_eqs_enter(bool user)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -571,18 +626,27 @@
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdp->dynticks_nesting == 0);
if (rdp->dynticks_nesting != 1) {
+ // RCU will still be watching, so just do accounting and leave.
rdp->dynticks_nesting--;
return;
}
lockdep_assert_irqs_disabled();
+ instrumentation_begin();
trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
rdp = this_cpu_ptr(&rcu_data);
rcu_prepare_for_idle();
rcu_preempt_deferred_qs(current);
+
+ // instrumentation for the noinstr rcu_dynticks_eqs_enter()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
+ instrumentation_end();
WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+ // RCU is watching here ...
rcu_dynticks_eqs_enter();
+ // ... but is no longer watching here.
rcu_dynticks_task_enter();
}
@@ -602,6 +666,7 @@
lockdep_assert_irqs_disabled();
rcu_eqs_enter(false);
}
+EXPORT_SYMBOL_GPL(rcu_idle_enter);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -615,7 +680,7 @@
* If you add or remove a call to rcu_user_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_user_enter(void)
+noinstr void rcu_user_enter(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
@@ -629,19 +694,22 @@
}
#endif /* CONFIG_NO_HZ_FULL */
-/*
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ *
* If we are returning from the outermost NMI handler that interrupted an
* RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
*
- * If you add or remove a call to rcu_nmi_exit_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
-static __always_inline void rcu_nmi_exit_common(bool irq)
+noinstr void rcu_nmi_exit(void)
{
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+ instrumentation_begin();
/*
* Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
* (We are exiting an NMI handler, so RCU better be paying attention
@@ -659,6 +727,7 @@
atomic_read(&rdp->dynticks));
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
rdp->dynticks_nmi_nesting - 2);
+ instrumentation_end();
return;
}
@@ -666,27 +735,22 @@
trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
- if (irq)
+ if (!in_nmi())
rcu_prepare_for_idle();
+ // instrumentation for the noinstr rcu_dynticks_eqs_enter()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+ instrumentation_end();
+
+ // RCU is watching here ...
rcu_dynticks_eqs_enter();
+ // ... but is no longer watching here.
- if (irq)
+ if (!in_nmi())
rcu_dynticks_task_enter();
}
/**
- * rcu_nmi_exit - inform RCU of exit from NMI context
- *
- * If you add or remove a call to rcu_nmi_exit(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void rcu_nmi_exit(void)
-{
- rcu_nmi_exit_common(false);
-}
-
-/**
* rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
*
* Exit from an interrupt handler, which might possibly result in entering
@@ -705,12 +769,52 @@
* If you add or remove a call to rcu_irq_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_irq_exit(void)
+void noinstr rcu_irq_exit(void)
{
lockdep_assert_irqs_disabled();
- rcu_nmi_exit_common(true);
+ rcu_nmi_exit();
}
+/**
+ * rcu_irq_exit_preempt - Inform RCU that current CPU is exiting irq
+ * towards in kernel preemption
+ *
+ * Same as rcu_irq_exit() but has a sanity check that scheduling is safe
+ * from RCU point of view. Invoked from return from interrupt before kernel
+ * preemption.
+ */
+void rcu_irq_exit_preempt(void)
+{
+ lockdep_assert_irqs_disabled();
+ rcu_nmi_exit();
+
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+ "RCU dynticks_nesting counter underflow/zero!");
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+ DYNTICK_IRQ_NONIDLE,
+ "Bad RCU dynticks_nmi_nesting counter\n");
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "RCU in extended quiescent state!");
+}
+
+#ifdef CONFIG_PROVE_RCU
+/**
+ * rcu_irq_exit_check_preempt - Validate that scheduling is possible
+ */
+void rcu_irq_exit_check_preempt(void)
+{
+ lockdep_assert_irqs_disabled();
+
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nesting) <= 0,
+ "RCU dynticks_nesting counter underflow/zero!");
+ RCU_LOCKDEP_WARN(__this_cpu_read(rcu_data.dynticks_nmi_nesting) !=
+ DYNTICK_IRQ_NONIDLE,
+ "Bad RCU dynticks_nmi_nesting counter\n");
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "RCU in extended quiescent state!");
+}
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
/*
* Wrapper for rcu_irq_exit() where interrupts are enabled.
*
@@ -734,7 +838,7 @@
* allow for the possibility of usermode upcalls messing up our count of
* interrupt nesting level during the busy period that is just now starting.
*/
-static void rcu_eqs_exit(bool user)
+static void noinstr rcu_eqs_exit(bool user)
{
struct rcu_data *rdp;
long oldval;
@@ -744,17 +848,26 @@
oldval = rdp->dynticks_nesting;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
if (oldval) {
+ // RCU was already watching, so just do accounting and leave.
rdp->dynticks_nesting++;
return;
}
rcu_dynticks_task_exit();
+ // RCU is not watching here ...
rcu_dynticks_eqs_exit();
+ // ... but is watching here.
+ instrumentation_begin();
+
+ // instrumentation for the noinstr rcu_dynticks_eqs_exit()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
rcu_cleanup_after_idle();
trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
WRITE_ONCE(rdp->dynticks_nesting, 1);
WARN_ON_ONCE(rdp->dynticks_nmi_nesting);
WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE);
+ instrumentation_end();
}
/**
@@ -774,6 +887,7 @@
rcu_eqs_exit(false);
local_irq_restore(flags);
}
+EXPORT_SYMBOL_GPL(rcu_idle_exit);
#ifdef CONFIG_NO_HZ_FULL
/**
@@ -785,15 +899,75 @@
* If you add or remove a call to rcu_user_exit(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_user_exit(void)
+void noinstr rcu_user_exit(void)
{
rcu_eqs_exit(1);
}
+
+/**
+ * __rcu_irq_enter_check_tick - Enable scheduler tick on CPU if RCU needs it.
+ *
+ * The scheduler tick is not normally enabled when CPUs enter the kernel
+ * from nohz_full userspace execution. After all, nohz_full userspace
+ * execution is an RCU quiescent state and the time executing in the kernel
+ * is quite short. Except of course when it isn't. And it is not hard to
+ * cause a large system to spend tens of seconds or even minutes looping
+ * in the kernel, which can cause a number of problems, include RCU CPU
+ * stall warnings.
+ *
+ * Therefore, if a nohz_full CPU fails to report a quiescent state
+ * in a timely manner, the RCU grace-period kthread sets that CPU's
+ * ->rcu_urgent_qs flag with the expectation that the next interrupt or
+ * exception will invoke this function, which will turn on the scheduler
+ * tick, which will enable RCU to detect that CPU's quiescent states,
+ * for example, due to cond_resched() calls in CONFIG_PREEMPT=n kernels.
+ * The tick will be disabled once a quiescent state is reported for
+ * this CPU.
+ *
+ * Of course, in carefully tuned systems, there might never be an
+ * interrupt or exception. In that case, the RCU grace-period kthread
+ * will eventually cause one to happen. However, in less carefully
+ * controlled environments, this function allows RCU to get what it
+ * needs without creating otherwise useless interruptions.
+ */
+void __rcu_irq_enter_check_tick(void)
+{
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+ // If we're here from NMI there's nothing to do.
+ if (in_nmi())
+ return;
+
+ RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
+ "Illegal rcu_irq_enter_check_tick() from extended quiescent state");
+
+ if (!tick_nohz_full_cpu(rdp->cpu) ||
+ !READ_ONCE(rdp->rcu_urgent_qs) ||
+ READ_ONCE(rdp->rcu_forced_tick)) {
+ // RCU doesn't need nohz_full help from this CPU, or it is
+ // already getting that help.
+ return;
+ }
+
+ // We get here only when not in an extended quiescent state and
+ // from interrupts (as opposed to NMIs). Therefore, (1) RCU is
+ // already watching and (2) The fact that we are in an interrupt
+ // handler and that the rcu_node lock is an irq-disabled lock
+ // prevents self-deadlock. So we can safely recheck under the lock.
+ // Note that the nohz_full state currently cannot change.
+ raw_spin_lock_rcu_node(rdp->mynode);
+ if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+ // A nohz_full CPU is in the kernel and RCU needs a
+ // quiescent state. Turn on the tick!
+ WRITE_ONCE(rdp->rcu_forced_tick, true);
+ tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+ }
+ raw_spin_unlock_rcu_node(rdp->mynode);
+}
#endif /* CONFIG_NO_HZ_FULL */
/**
- * rcu_nmi_enter_common - inform RCU of entry to NMI context
- * @irq: Is this call from rcu_irq_enter?
+ * rcu_nmi_enter - inform RCU of entry to NMI context
*
* If the CPU was idle from RCU's viewpoint, update rdp->dynticks and
* rdp->dynticks_nmi_nesting to let the RCU grace-period handling know
@@ -801,13 +975,13 @@
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
*
- * If you add or remove a call to rcu_nmi_enter_common(), be sure to test
+ * If you add or remove a call to rcu_nmi_enter(), be sure to test
* with CONFIG_RCU_EQS_DEBUG=y.
*/
-static __always_inline void rcu_nmi_enter_common(bool irq)
+noinstr void rcu_nmi_enter(void)
{
- struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
long incby = 2;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
/* Complain about underflow. */
WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0);
@@ -822,34 +996,43 @@
*/
if (rcu_dynticks_curr_cpu_in_eqs()) {
- if (irq)
+ if (!in_nmi())
rcu_dynticks_task_exit();
+ // RCU is not watching here ...
rcu_dynticks_eqs_exit();
+ // ... but is watching here.
- if (irq)
+ if (!in_nmi()) {
+ instrumentation_begin();
rcu_cleanup_after_idle();
+ instrumentation_end();
+ }
+
+ instrumentation_begin();
+ // instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+ instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+ // instrumentation for the noinstr rcu_dynticks_eqs_exit()
+ instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
incby = 1;
+ } else if (!in_nmi()) {
+ instrumentation_begin();
+ rcu_irq_enter_check_tick();
+ } else {
+ instrumentation_begin();
}
+
trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
rdp->dynticks_nmi_nesting,
rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
+ instrumentation_end();
WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */
rdp->dynticks_nmi_nesting + incby);
barrier();
}
/**
- * rcu_nmi_enter - inform RCU of entry to NMI context
- */
-void rcu_nmi_enter(void)
-{
- rcu_nmi_enter_common(false);
-}
-NOKPROBE_SYMBOL(rcu_nmi_enter);
-
-/**
* rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
*
* Enter an interrupt handler, which might possibly result in exiting
@@ -871,10 +1054,10 @@
* If you add or remove a call to rcu_irq_enter(), be sure to test with
* CONFIG_RCU_EQS_DEBUG=y.
*/
-void rcu_irq_enter(void)
+noinstr void rcu_irq_enter(void)
{
lockdep_assert_irqs_disabled();
- rcu_nmi_enter_common(true);
+ rcu_nmi_enter();
}
/*
@@ -892,6 +1075,22 @@
local_irq_restore(flags);
}
+/*
+ * If any sort of urgency was applied to the current CPU (for example,
+ * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
+ * to get to a quiescent state, disable it.
+ */
+static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
+{
+ raw_lockdep_assert_held_rcu_node(rdp->mynode);
+ WRITE_ONCE(rdp->rcu_urgent_qs, false);
+ WRITE_ONCE(rdp->rcu_need_heavy_qs, false);
+ if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) {
+ tick_dep_clear_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
+ WRITE_ONCE(rdp->rcu_forced_tick, false);
+ }
+}
+
/**
* rcu_is_watching - see if RCU thinks that the current CPU is not idle
*
@@ -899,8 +1098,11 @@
* CPU can safely enter RCU read-side critical sections. In other words,
* if the current CPU is not in its idle loop or is in an interrupt or
* NMI handler, return true.
+ *
+ * Make notrace because it can be called by the internal functions of
+ * ftrace, and making this notrace removes unnecessary recursion calls.
*/
-bool notrace rcu_is_watching(void)
+notrace bool rcu_is_watching(void)
{
bool ret;
@@ -952,12 +1154,12 @@
if (in_nmi() || !rcu_scheduler_fully_active)
return true;
- preempt_disable();
+ preempt_disable_notrace();
rdp = this_cpu_ptr(&rcu_data);
rnp = rdp->mynode;
if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
ret = true;
- preempt_enable();
+ preempt_enable_notrace();
return ret;
}
EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
@@ -1024,13 +1226,28 @@
return 1;
}
- /* If waiting too long on an offline CPU, complain. */
- if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
- time_after(jiffies, rcu_state.gp_start + HZ)) {
+ /*
+ * Complain if a CPU that is considered to be offline from RCU's
+ * perspective has not yet reported a quiescent state. After all,
+ * the offline CPU should have reported a quiescent state during
+ * the CPU-offline process, or, failing that, by rcu_gp_init()
+ * if it ran concurrently with either the CPU going offline or the
+ * last task on a leaf rcu_node structure exiting its RCU read-side
+ * critical section while all CPUs corresponding to that structure
+ * are offline. This added warning detects bugs in any of these
+ * code paths.
+ *
+ * The rcu_node structure's ->lock is held here, which excludes
+ * the relevant portions the CPU-hotplug code, the grace-period
+ * initialization code, and the rcu_read_unlock() code paths.
+ *
+ * For more detail, please refer to the "Hotplug CPU" section
+ * of RCU's Requirements documentation.
+ */
+ if (WARN_ON_ONCE(!(rdp->grpmask & rcu_rnp_online_cpus(rnp)))) {
bool onl;
struct rcu_node *rnp1;
- WARN_ON(1); /* Offline CPUs are supposed to report QS! */
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
(long)rnp->gp_seq, (long)rnp->completedqs);
@@ -1061,7 +1278,8 @@
rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu);
if (!READ_ONCE(*rnhqp) &&
(time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
- time_after(jiffies, rcu_state.jiffies_resched))) {
+ time_after(jiffies, rcu_state.jiffies_resched) ||
+ rcu_state.cbovld)) {
WRITE_ONCE(*rnhqp, true);
/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
smp_store_release(ruqp, true);
@@ -1078,8 +1296,9 @@
* So hit them over the head with the resched_cpu() hammer!
*/
if (tick_nohz_full_cpu(rdp->cpu) &&
- time_after(jiffies,
- READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) {
+ (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
+ rcu_state.cbovld)) {
+ WRITE_ONCE(*ruqp, true);
resched_cpu(rdp->cpu);
WRITE_ONCE(rdp->last_fqs_resched, jiffies);
}
@@ -1101,6 +1320,7 @@
!rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
(rnp->ffmask & rdp->grpmask)) {
init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
+ atomic_set(&rdp->rcu_iw.flags, IRQ_WORK_HARD_IRQ);
rdp->rcu_iw_pending = true;
rdp->rcu_iw_gp_seq = rnp->gp_seq;
irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
@@ -1114,8 +1334,9 @@
static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
unsigned long gp_seq_req, const char *s)
{
- trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req,
- rnp->level, rnp->grplo, rnp->grphi, s);
+ trace_rcu_future_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
+ gp_seq_req, rnp->level,
+ rnp->grplo, rnp->grphi, s);
}
/*
@@ -1162,7 +1383,7 @@
TPS("Prestarted"));
goto unlock_out;
}
- rnp->gp_seq_needed = gp_seq_req;
+ WRITE_ONCE(rnp->gp_seq_needed, gp_seq_req);
if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
/*
* We just marked the leaf or internal node, and a
@@ -1187,18 +1408,18 @@
}
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT);
- rcu_state.gp_req_activity = jiffies;
- if (!rcu_state.gp_kthread) {
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+ if (!READ_ONCE(rcu_state.gp_kthread)) {
trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
goto unlock_out;
}
- trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq"));
+ trace_rcu_grace_period(rcu_state.name, data_race(rcu_state.gp_seq), TPS("newreq"));
ret = true; /* Caller must wake GP kthread. */
unlock_out:
/* Push furthest requested GP to leaf node and rcu_data structure. */
if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
- rnp_start->gp_seq_needed = rnp->gp_seq_needed;
- rdp->gp_seq_needed = rnp->gp_seq_needed;
+ WRITE_ONCE(rnp_start->gp_seq_needed, rnp->gp_seq_needed);
+ WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
}
if (rnp != rnp_start)
raw_spin_unlock_rcu_node(rnp);
@@ -1223,12 +1444,13 @@
}
/*
- * Awaken the grace-period kthread. Don't do a self-awaken (unless in
- * an interrupt or softirq handler), and don't bother awakening when there
- * is nothing for the grace-period kthread to do (as in several CPUs raced
- * to awaken, and we lost), and finally don't try to awaken a kthread that
- * has not yet been created. If all those checks are passed, track some
- * debug information and awaken.
+ * Awaken the grace-period kthread. Don't do a self-awaken (unless in an
+ * interrupt or softirq handler, in which case we just might immediately
+ * sleep upon return, resulting in a grace-period hang), and don't bother
+ * awakening when there is nothing for the grace-period kthread to do
+ * (as in several CPUs raced to awaken, we lost), and finally don't try
+ * to awaken a kthread that has not yet been created. If all those checks
+ * are passed, track some debug information and awaken.
*
* So why do the self-wakeup when in an interrupt or softirq handler
* in the grace-period kthread's context? Because the kthread might have
@@ -1238,10 +1460,10 @@
*/
static void rcu_gp_kthread_wake(void)
{
- if ((current == rcu_state.gp_kthread &&
- !in_irq() && !in_serving_softirq()) ||
- !READ_ONCE(rcu_state.gp_flags) ||
- !rcu_state.gp_kthread)
+ struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
+
+ if ((current == t && !in_irq() && !in_serving_softirq()) ||
+ !READ_ONCE(rcu_state.gp_flags) || !t)
return;
WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
WRITE_ONCE(rcu_state.gp_wake_seq, READ_ONCE(rcu_state.gp_seq));
@@ -1288,9 +1510,10 @@
/* Trace depending on how much we were able to accelerate. */
if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
- trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccWaitCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB"));
else
- trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccReadyCB"));
+ trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB"));
+
return ret;
}
@@ -1309,7 +1532,7 @@
rcu_lockdep_assert_cblist_protected(rdp);
c = rcu_seq_snap(&rcu_state.gp_seq);
- if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+ if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
/* Old request still live, so mark recent callbacks. */
(void)rcu_segcblist_accelerate(&rdp->cblist, c);
return;
@@ -1358,14 +1581,28 @@
struct rcu_data *rdp)
{
rcu_lockdep_assert_cblist_protected(rdp);
- if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
- !raw_spin_trylock_rcu_node(rnp))
+ if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
return;
- WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+ // The grace period cannot end while we hold the rcu_node lock.
+ if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+ WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
raw_spin_unlock_rcu_node(rnp);
}
/*
+ * In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels, attempt to generate a
+ * quiescent state. This is intended to be invoked when the CPU notices
+ * a new grace period.
+ */
+static void rcu_strict_gp_check_qs(void)
+{
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+ rcu_read_lock();
+ rcu_read_unlock();
+ }
+}
+
+/*
* Update CPU-local rcu_data state to record the beginnings and ends of
* grace periods. The caller must hold the ->lock of the leaf rcu_node
* structure corresponding to the current CPU, and must have irqs disabled.
@@ -1374,7 +1611,7 @@
static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
{
bool ret = false;
- bool need_gp;
+ bool need_qs;
const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
rcu_segcblist_is_offloaded(&rdp->cblist);
@@ -1388,10 +1625,13 @@
unlikely(READ_ONCE(rdp->gpwrap))) {
if (!offloaded)
ret = rcu_advance_cbs(rnp, rdp); /* Advance CBs. */
+ rdp->core_needs_qs = false;
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend"));
} else {
if (!offloaded)
ret = rcu_accelerate_cbs(rnp, rdp); /* Recent CBs. */
+ if (rdp->core_needs_qs)
+ rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
}
/* Now handle the beginnings of any new-to-this-CPU grace periods. */
@@ -1403,14 +1643,14 @@
* go looking for one.
*/
trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart"));
- need_gp = !!(rnp->qsmask & rdp->grpmask);
- rdp->cpu_no_qs.b.norm = need_gp;
- rdp->core_needs_qs = need_gp;
+ need_qs = !!(rnp->qsmask & rdp->grpmask);
+ rdp->cpu_no_qs.b.norm = need_qs;
+ rdp->core_needs_qs = need_qs;
zero_cpu_stall_ticks(rdp);
}
rdp->gp_seq = rnp->gp_seq; /* Remember new grace-period state. */
if (ULONG_CMP_LT(rdp->gp_seq_needed, rnp->gp_seq_needed) || rdp->gpwrap)
- rdp->gp_seq_needed = rnp->gp_seq_needed;
+ WRITE_ONCE(rdp->gp_seq_needed, rnp->gp_seq_needed);
WRITE_ONCE(rdp->gpwrap, false);
rcu_gpnum_ovf(rnp, rdp);
return ret;
@@ -1432,6 +1672,7 @@
}
needwake = __note_gp_changes(rnp, rdp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ rcu_strict_gp_check_qs();
if (needwake)
rcu_gp_kthread_wake();
}
@@ -1441,7 +1682,41 @@
if (delay > 0 &&
!(rcu_seq_ctr(rcu_state.gp_seq) %
(rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
- schedule_timeout_uninterruptible(delay);
+ schedule_timeout_idle(delay);
+}
+
+static unsigned long sleep_duration;
+
+/* Allow rcutorture to stall the grace-period kthread. */
+void rcu_gp_set_torture_wait(int duration)
+{
+ if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
+ WRITE_ONCE(sleep_duration, duration);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
+
+/* Actually implement the aforementioned wait. */
+static void rcu_gp_torture_wait(void)
+{
+ unsigned long duration;
+
+ if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
+ return;
+ duration = xchg(&sleep_duration, 0UL);
+ if (duration > 0) {
+ pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
+ schedule_timeout_idle(duration);
+ pr_alert("%s: Wait complete\n", __func__);
+ }
+}
+
+/*
+ * Handler for on_each_cpu() to invoke the target CPU's RCU core
+ * processing.
+ */
+static void rcu_strict_gp_boundary(void *unused)
+{
+ invoke_rcu_core();
}
/*
@@ -1477,14 +1752,18 @@
record_gp_stall_check_time();
/* Record GP times before starting GP, hence rcu_seq_start(). */
rcu_seq_start(&rcu_state.gp_seq);
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start"));
raw_spin_unlock_irq_rcu_node(rnp);
/*
- * Apply per-leaf buffered online and offline operations to the
- * rcu_node tree. Note that this new grace period need not wait
- * for subsequent online CPUs, and that quiescent-state forcing
- * will handle subsequent offline CPUs.
+ * Apply per-leaf buffered online and offline operations to
+ * the rcu_node tree. Note that this new grace period need not
+ * wait for subsequent online CPUs, and that RCU hooks in the CPU
+ * offlining path, when combined with checks in this function,
+ * will handle CPUs that are currently going offline or that will
+ * go offline later. Please also refer to "Hotplug CPU" section
+ * of RCU's Requirements documentation.
*/
rcu_state.gp_state = RCU_GP_ONOFF;
rcu_for_each_leaf_node(rnp) {
@@ -1571,6 +1850,10 @@
WRITE_ONCE(rcu_state.gp_activity, jiffies);
}
+ // If strict, make all CPUs aware of new grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
+
return true;
}
@@ -1582,12 +1865,16 @@
{
struct rcu_node *rnp = rcu_get_root();
- /* Someone like call_rcu() requested a force-quiescent-state scan. */
+ // If under overload conditions, force an immediate FQS scan.
+ if (*gfp & RCU_GP_FLAG_OVLD)
+ return true;
+
+ // Someone like call_rcu() requested a force-quiescent-state scan.
*gfp = READ_ONCE(rcu_state.gp_flags);
if (*gfp & RCU_GP_FLAG_FQS)
return true;
- /* The current grace period has completed. */
+ // The current grace period has completed.
if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
return true;
@@ -1602,7 +1889,7 @@
struct rcu_node *rnp = rcu_get_root();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
- rcu_state.n_force_qs++;
+ WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
if (first_time) {
/* Collect dyntick-idle snapshots. */
force_qs_rnp(dyntick_save_progress_counter);
@@ -1625,13 +1912,15 @@
static void rcu_gp_fqs_loop(void)
{
bool first_gp_fqs;
- int gf;
+ int gf = 0;
unsigned long j;
int ret;
struct rcu_node *rnp = rcu_get_root();
first_gp_fqs = true;
j = READ_ONCE(jiffies_till_first_fqs);
+ if (rcu_state.cbovld)
+ gf = RCU_GP_FLAG_OVLD;
ret = 0;
for (;;) {
if (!ret) {
@@ -1639,12 +1928,12 @@
WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
jiffies + (j ? 3 * j : 2));
}
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqswait"));
rcu_state.gp_state = RCU_GP_WAIT_FQS;
ret = swait_event_idle_timeout_exclusive(
rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+ rcu_gp_torture_wait();
rcu_state.gp_state = RCU_GP_DOING_FQS;
/* Locking provides needed memory barriers. */
/* If grace period done, leave loop. */
@@ -1652,15 +1941,17 @@
!rcu_preempt_blocked_readers_cgp(rnp))
break;
/* If time for quiescent-state forcing, do it. */
- if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) ||
- (gf & RCU_GP_FLAG_FQS)) {
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
+ (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) {
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqsstart"));
rcu_gp_fqs(first_gp_fqs);
- first_gp_fqs = false;
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ gf = 0;
+ if (first_gp_fqs) {
+ first_gp_fqs = false;
+ gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
+ }
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqsend"));
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
@@ -1671,8 +1962,7 @@
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("fqswaitsig"));
ret = 1; /* Keep old FQS timing. */
j = jiffies;
@@ -1680,6 +1970,7 @@
j = 1;
else
j = rcu_state.jiffies_force_qs - j;
+ gf = 0;
}
}
}
@@ -1689,8 +1980,9 @@
*/
static void rcu_gp_cleanup(void)
{
- unsigned long gp_duration;
+ int cpu;
bool needgp = false;
+ unsigned long gp_duration;
unsigned long new_gp_seq;
bool offloaded;
struct rcu_data *rdp;
@@ -1736,6 +2028,12 @@
needgp = __note_gp_changes(rnp, rdp) || needgp;
/* smp_mb() provided by prior unlock-lock pair. */
needgp = rcu_future_gp_cleanup(rnp) || needgp;
+ // Reset overload indication for CPUs no longer overloaded
+ if (rcu_is_leaf_node(rnp))
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->cbovldmask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ check_cb_ovld_locked(rdp, rnp);
+ }
sq = rcu_nocb_gp_get(rnp);
raw_spin_unlock_irq_rcu_node(rnp);
rcu_nocb_gp_cleanup(sq);
@@ -1749,6 +2047,7 @@
/* Declare grace period done, trace first to use old GP number. */
trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
rcu_seq_end(&rcu_state.gp_seq);
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
rcu_state.gp_state = RCU_GP_IDLE;
/* Check for GP requests since above loop. */
rdp = this_cpu_ptr(&rcu_data);
@@ -1762,15 +2061,19 @@
rcu_segcblist_is_offloaded(&rdp->cblist);
if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
- rcu_state.gp_req_activity = jiffies;
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ rcu_state.gp_seq,
TPS("newreq"));
} else {
WRITE_ONCE(rcu_state.gp_flags,
rcu_state.gp_flags & RCU_GP_FLAG_INIT);
}
raw_spin_unlock_irq_rcu_node(rnp);
+
+ // If strict, make all CPUs aware of the end of the old grace period.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ on_each_cpu(rcu_strict_gp_boundary, NULL, 0);
}
/*
@@ -1783,13 +2086,13 @@
/* Handle grace-period start. */
for (;;) {
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwait"));
rcu_state.gp_state = RCU_GP_WAIT_GPS;
swait_event_idle_exclusive(rcu_state.gp_wq,
READ_ONCE(rcu_state.gp_flags) &
RCU_GP_FLAG_INIT);
+ rcu_gp_torture_wait();
rcu_state.gp_state = RCU_GP_DONE_GPS;
/* Locking provides needed memory barrier. */
if (rcu_gp_init())
@@ -1797,8 +2100,7 @@
cond_resched_tasks_rcu_qs();
WRITE_ONCE(rcu_state.gp_activity, jiffies);
WARN_ON(signal_pending(current));
- trace_rcu_grace_period(rcu_state.name,
- READ_ONCE(rcu_state.gp_seq),
+ trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
TPS("reqwaitsig"));
}
@@ -1869,7 +2171,7 @@
WARN_ON_ONCE(oldmask); /* Any child must be all zeroed! */
WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
rcu_preempt_blocked_readers_cgp(rnp));
- rnp->qsmask &= ~mask;
+ WRITE_ONCE(rnp->qsmask, rnp->qsmask & ~mask);
trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq,
mask, rnp->qsmask, rnp->level,
rnp->grplo, rnp->grphi,
@@ -1892,7 +2194,7 @@
rnp_c = rnp;
rnp = rnp->parent;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- oldmask = rnp_c->qsmask;
+ oldmask = READ_ONCE(rnp_c->qsmask);
}
/*
@@ -1919,7 +2221,7 @@
struct rcu_node *rnp_p;
raw_lockdep_assert_held_rcu_node(rnp);
- if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) ||
+ if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) ||
WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
rnp->qsmask != 0) {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1950,7 +2252,7 @@
* structure. This must be called from the specified CPU.
*/
static void
-rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
+rcu_report_qs_rdp(struct rcu_data *rdp)
{
unsigned long flags;
unsigned long mask;
@@ -1959,6 +2261,7 @@
rcu_segcblist_is_offloaded(&rdp->cblist);
struct rcu_node *rnp;
+ WARN_ON_ONCE(rdp->cpu != smp_processor_id());
rnp = rdp->mynode;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
@@ -1986,6 +2289,7 @@
if (!offloaded)
needwake = rcu_accelerate_cbs(rnp, rdp);
+ rcu_disable_urgency_upon_qs(rdp);
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
/* ^^^ Released rnp->lock */
if (needwake)
@@ -2023,7 +2327,7 @@
* Tell RCU we are done (but rcu_report_qs_rdp() will be the
* judge of that).
*/
- rcu_report_qs_rdp(rdp->cpu, rdp);
+ rcu_report_qs_rdp(rdp);
}
/*
@@ -2040,7 +2344,7 @@
return 0;
blkd = !!(rnp->qsmask & rdp->grpmask);
- trace_rcu_grace_period(rcu_state.name, rnp->gp_seq,
+ trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq),
blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
return 0;
}
@@ -2108,6 +2412,9 @@
rcu_boost_kthread_setaffinity(rnp, -1);
/* Do any needed no-CB deferred wakeups from this CPU. */
do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu));
+
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
return 0;
}
@@ -2117,6 +2424,7 @@
*/
static void rcu_do_batch(struct rcu_data *rdp)
{
+ int div;
unsigned long flags;
const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
rcu_segcblist_is_offloaded(&rdp->cblist);
@@ -2128,7 +2436,6 @@
/* If no callbacks are ready, just return. */
if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
trace_rcu_batch_start(rcu_state.name,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), 0);
trace_rcu_batch_end(rcu_state.name, 0,
!rcu_segcblist_empty(&rdp->cblist),
@@ -2146,11 +2453,16 @@
rcu_nocb_lock(rdp);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
pending = rcu_segcblist_n_cbs(&rdp->cblist);
- bl = max(rdp->blimit, pending >> rcu_divisor);
- if (unlikely(bl > 100))
- tlimit = local_clock() + rcu_resched_ns;
+ div = READ_ONCE(rcu_divisor);
+ div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
+ bl = max(rdp->blimit, pending >> div);
+ if (unlikely(bl > 100)) {
+ long rrn = READ_ONCE(rcu_resched_ns);
+
+ rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
+ tlimit = local_clock() + rrn;
+ }
trace_rcu_batch_start(rcu_state.name,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist), bl);
rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
if (offloaded)
@@ -2158,11 +2470,22 @@
rcu_nocb_unlock_irqrestore(rdp, flags);
/* Invoke callbacks. */
+ tick_dep_set_task(current, TICK_DEP_BIT_RCU);
rhp = rcu_cblist_dequeue(&rcl);
for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ rcu_callback_t f;
+
debug_rcu_head_unqueue(rhp);
- if (__rcu_reclaim(rcu_state.name, rhp))
- rcu_cblist_dequeued_lazy(&rcl);
+
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_callback(rcu_state.name, rhp);
+
+ f = rhp->func;
+ WRITE_ONCE(rhp->func, (rcu_callback_t)0L);
+ f(rhp);
+
+ rcu_lock_release(&rcu_callback_map);
+
/*
* Stop only if limit reached and CPU has something to do.
* Note: The rcl structure counts down from zero.
@@ -2191,6 +2514,7 @@
local_irq_save(flags);
rcu_nocb_lock(rdp);
count = -rcl.len;
+ rdp->n_cbs_invoked += count;
trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
is_idle_task(current), rcu_is_callbacks_kthread());
@@ -2207,7 +2531,7 @@
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
- rdp->n_force_qs_snap = rcu_state.n_force_qs;
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
} else if (count < rdp->qlen_last_fqs_check - qhimark)
rdp->qlen_last_fqs_check = count;
@@ -2224,6 +2548,7 @@
/* Re-invoke RCU core processing if there are callbacks remaining. */
if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
+ tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
}
/*
@@ -2237,6 +2562,7 @@
void rcu_sched_clock_irq(int user)
{
trace_rcu_utilization(TPS("Start scheduler-tick"));
+ lockdep_assert_irqs_disabled();
raw_cpu_inc(rcu_data.ticks_this_gp);
/* The load-acquire pairs with the store-release setting to true. */
if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
@@ -2248,8 +2574,9 @@
__this_cpu_write(rcu_data.rcu_urgent_qs, false);
}
rcu_flavor_sched_clock_irq(user);
- if (rcu_pending())
+ if (rcu_pending(user))
invoke_rcu_core();
+ lockdep_assert_irqs_disabled();
trace_rcu_utilization(TPS("End scheduler-tick"));
}
@@ -2266,15 +2593,18 @@
int cpu;
unsigned long flags;
unsigned long mask;
+ struct rcu_data *rdp;
struct rcu_node *rnp;
+ rcu_state.cbovld = rcu_state.cbovldnext;
+ rcu_state.cbovldnext = false;
rcu_for_each_leaf_node(rnp) {
cond_resched_tasks_rcu_qs();
mask = 0;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
+ rcu_state.cbovldnext |= !!rnp->cbovldmask;
if (rnp->qsmask == 0) {
- if (!IS_ENABLED(CONFIG_PREEMPTION) ||
- rcu_preempt_blocked_readers_cgp(rnp)) {
+ if (rcu_preempt_blocked_readers_cgp(rnp)) {
/*
* No point in scanning bits because they
* are all zero. But we might need to
@@ -2287,11 +2617,11 @@
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
continue;
}
- for_each_leaf_node_possible_cpu(rnp, cpu) {
- unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
- if ((rnp->qsmask & bit) != 0) {
- if (f(per_cpu_ptr(&rcu_data, cpu)))
- mask |= bit;
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (f(rdp)) {
+ mask |= rdp->grpmask;
+ rcu_disable_urgency_upon_qs(rdp);
}
}
if (mask != 0) {
@@ -2319,7 +2649,7 @@
rnp = __this_cpu_read(rcu_data.mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
- !raw_spin_trylock(&rnp->fqslock);
+ !raw_spin_trylock(&rnp->fqslock);
if (rnp_old != NULL)
raw_spin_unlock(&rnp_old->fqslock);
if (ret)
@@ -2342,6 +2672,14 @@
}
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+// Workqueue handler for an RCU reader for kernels enforcing struct RCU
+// grace periods.
+static void strict_work_handler(struct work_struct *work)
+{
+ rcu_read_lock();
+ rcu_read_unlock();
+}
+
/* Perform RCU core processing work for the current CPU. */
static __latent_entropy void rcu_core(void)
{
@@ -2386,6 +2724,10 @@
/* Do any needed deferred wakeups of rcuo kthreads. */
do_nocb_deferred_wakeup(rdp);
trace_rcu_utilization(TPS("End RCU core"));
+
+ // If strict GPs, schedule an RCU reader in a clean environment.
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work);
}
static void rcu_core_si(struct softirq_action *h)
@@ -2450,8 +2792,8 @@
char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work);
int spincnt;
+ trace_rcu_utilization(TPS("Start CPU kthread@rcu_run"));
for (spincnt = 0; spincnt < 10; spincnt++) {
- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait"));
local_bh_disable();
*statusp = RCU_KTHREAD_RUNNING;
local_irq_disable();
@@ -2469,7 +2811,7 @@
}
*statusp = RCU_KTHREAD_YIELDING;
trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield"));
- schedule_timeout_interruptible(2);
+ schedule_timeout_idle(2);
trace_rcu_utilization(TPS("End CPU kthread@rcu_yield"));
*statusp = RCU_KTHREAD_WAITING;
}
@@ -2535,10 +2877,10 @@
} else {
/* Give the grace period a kick. */
rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
- if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
+ if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
rcu_force_quiescent_state();
- rdp->n_force_qs_snap = rcu_state.n_force_qs;
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
@@ -2552,13 +2894,50 @@
}
/*
- * Helper function for call_rcu() and friends. The cpu argument will
- * normally be -1, indicating "currently running CPU". It may specify
- * a CPU only if that CPU is a no-CBs CPU. Currently, only rcu_barrier()
- * is expected to specify a CPU.
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks. The caller must hold the leaf rcu_node
+ * structure's ->lock.
*/
+static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp)
+{
+ raw_lockdep_assert_held_rcu_node(rnp);
+ if (qovld_calc <= 0)
+ return; // Early boot and wildcard value set.
+ if (rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc)
+ WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask | rdp->grpmask);
+ else
+ WRITE_ONCE(rnp->cbovldmask, rnp->cbovldmask & ~rdp->grpmask);
+}
+
+/*
+ * Check and if necessary update the leaf rcu_node structure's
+ * ->cbovldmask bit corresponding to the current CPU based on that CPU's
+ * number of queued RCU callbacks. No locks need be held, but the
+ * caller must have disabled interrupts.
+ *
+ * Note that this function ignores the possibility that there are a lot
+ * of callbacks all of which have already seen the end of their respective
+ * grace periods. This omission is due to the need for no-CBs CPUs to
+ * be holding ->nocb_lock to do this check, which is too heavy for a
+ * common-case operation.
+ */
+static void check_cb_ovld(struct rcu_data *rdp)
+{
+ struct rcu_node *const rnp = rdp->mynode;
+
+ if (qovld_calc <= 0 ||
+ ((rcu_segcblist_n_cbs(&rdp->cblist) >= qovld_calc) ==
+ !!(READ_ONCE(rnp->cbovldmask) & rdp->grpmask)))
+ return; // Early boot wildcard value or already set correctly.
+ raw_spin_lock_rcu_node(rnp);
+ check_cb_ovld_locked(rdp, rnp);
+ raw_spin_unlock_rcu_node(rnp);
+}
+
+/* Helper function for call_rcu() and friends. */
static void
-__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy)
+__call_rcu(struct rcu_head *head, rcu_callback_t func)
{
unsigned long flags;
struct rcu_data *rdp;
@@ -2581,6 +2960,7 @@
head->func = func;
head->next = NULL;
local_irq_save(flags);
+ kasan_record_aux_stack(head);
rdp = this_cpu_ptr(&rcu_data);
/* Add the callback to our list. */
@@ -2593,18 +2973,18 @@
if (rcu_segcblist_empty(&rdp->cblist))
rcu_segcblist_init(&rdp->cblist);
}
+
+ check_cb_ovld(rdp);
if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
return; // Enqueued onto ->nocb_bypass, so just leave.
- /* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */
- rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
- if (__is_kfree_rcu_offset((unsigned long)func))
- trace_rcu_kfree_callback(rcu_state.name, head,
+ // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
+ rcu_segcblist_enqueue(&rdp->cblist, head);
+ if (__is_kvfree_rcu_offset((unsigned long)func))
+ trace_rcu_kvfree_callback(rcu_state.name, head,
(unsigned long)func,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
else
trace_rcu_callback(rcu_state.name, head,
- rcu_segcblist_n_lazy_cbs(&rdp->cblist),
rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
@@ -2654,28 +3034,583 @@
*/
void call_rcu(struct rcu_head *head, rcu_callback_t func)
{
- __call_rcu(head, func, 0);
+ __call_rcu(head, func);
}
EXPORT_SYMBOL_GPL(call_rcu);
-/*
- * Queue an RCU callback for lazy invocation after a grace period.
- * This will likely be later named something like "call_rcu_lazy()",
- * but this change will require some way of tagging the lazy RCU
- * callbacks in the list of pending callbacks. Until then, this
- * function may only be called from __kfree_rcu().
+
+/* Maximum number of jiffies to wait before draining a batch. */
+#define KFREE_DRAIN_JIFFIES (HZ / 50)
+#define KFREE_N_BATCHES 2
+#define FREE_N_CHANNELS 2
+
+/**
+ * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers
+ * @nr_records: Number of active pointers in the array
+ * @next: Next bulk object in the block chain
+ * @records: Array of the kvfree_rcu() pointers
*/
-void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+struct kvfree_rcu_bulk_data {
+ unsigned long nr_records;
+ struct kvfree_rcu_bulk_data *next;
+ void *records[];
+};
+
+/*
+ * This macro defines how many entries the "records" array
+ * will contain. It is based on the fact that the size of
+ * kvfree_rcu_bulk_data structure becomes exactly one page.
+ */
+#define KVFREE_BULK_MAX_ENTR \
+ ((PAGE_SIZE - sizeof(struct kvfree_rcu_bulk_data)) / sizeof(void *))
+
+/**
+ * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests
+ * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period
+ * @head_free: List of kfree_rcu() objects waiting for a grace period
+ * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period
+ * @krcp: Pointer to @kfree_rcu_cpu structure
+ */
+
+struct kfree_rcu_cpu_work {
+ struct rcu_work rcu_work;
+ struct rcu_head *head_free;
+ struct kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS];
+ struct kfree_rcu_cpu *krcp;
+};
+
+/**
+ * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
+ * @head: List of kfree_rcu() objects not yet waiting for a grace period
+ * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
+ * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
+ * @lock: Synchronize access to this structure
+ * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES
+ * @monitor_todo: Tracks whether a @monitor_work delayed work is pending
+ * @initialized: The @rcu_work fields have been initialized
+ * @count: Number of objects for which GP not started
+ * @bkvcache:
+ * A simple cache list that contains objects for reuse purpose.
+ * In order to save some per-cpu space the list is singular.
+ * Even though it is lockless an access has to be protected by the
+ * per-cpu lock.
+ * @page_cache_work: A work to refill the cache when it is empty
+ * @work_in_progress: Indicates that page_cache_work is running
+ * @hrtimer: A hrtimer for scheduling a page_cache_work
+ * @nr_bkv_objs: number of allocated objects at @bkvcache.
+ *
+ * This is a per-CPU structure. The reason that it is not included in
+ * the rcu_data structure is to permit this code to be extracted from
+ * the RCU files. Such extraction could allow further optimization of
+ * the interactions with the slab allocators.
+ */
+struct kfree_rcu_cpu {
+ struct rcu_head *head;
+ struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS];
+ struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
+ raw_spinlock_t lock;
+ struct delayed_work monitor_work;
+ bool monitor_todo;
+ bool initialized;
+ int count;
+
+ struct work_struct page_cache_work;
+ atomic_t work_in_progress;
+ struct hrtimer hrtimer;
+
+ struct llist_head bkvcache;
+ int nr_bkv_objs;
+};
+
+static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc) = {
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(krc.lock),
+};
+
+static __always_inline void
+debug_rcu_bhead_unqueue(struct kvfree_rcu_bulk_data *bhead)
{
- __call_rcu(head, func, 1);
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+ int i;
+
+ for (i = 0; i < bhead->nr_records; i++)
+ debug_rcu_head_unqueue((struct rcu_head *)(bhead->records[i]));
+#endif
}
-EXPORT_SYMBOL_GPL(kfree_call_rcu);
+
+static inline struct kfree_rcu_cpu *
+krc_this_cpu_lock(unsigned long *flags)
+{
+ struct kfree_rcu_cpu *krcp;
+
+ local_irq_save(*flags); // For safely calling this_cpu_ptr().
+ krcp = this_cpu_ptr(&krc);
+ raw_spin_lock(&krcp->lock);
+
+ return krcp;
+}
+
+static inline void
+krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
+{
+ raw_spin_unlock(&krcp->lock);
+ local_irq_restore(flags);
+}
+
+static inline struct kvfree_rcu_bulk_data *
+get_cached_bnode(struct kfree_rcu_cpu *krcp)
+{
+ if (!krcp->nr_bkv_objs)
+ return NULL;
+
+ krcp->nr_bkv_objs--;
+ return (struct kvfree_rcu_bulk_data *)
+ llist_del_first(&krcp->bkvcache);
+}
+
+static inline bool
+put_cached_bnode(struct kfree_rcu_cpu *krcp,
+ struct kvfree_rcu_bulk_data *bnode)
+{
+ // Check the limit.
+ if (krcp->nr_bkv_objs >= rcu_min_cached_objs)
+ return false;
+
+ llist_add((struct llist_node *) bnode, &krcp->bkvcache);
+ krcp->nr_bkv_objs++;
+ return true;
+
+}
+
+/*
+ * This function is invoked in workqueue context after a grace period.
+ * It frees all the objects queued on ->bhead_free or ->head_free.
+ */
+static void kfree_rcu_work(struct work_struct *work)
+{
+ unsigned long flags;
+ struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext;
+ struct rcu_head *head, *next;
+ struct kfree_rcu_cpu *krcp;
+ struct kfree_rcu_cpu_work *krwp;
+ int i, j;
+
+ krwp = container_of(to_rcu_work(work),
+ struct kfree_rcu_cpu_work, rcu_work);
+ krcp = krwp->krcp;
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ // Channels 1 and 2.
+ for (i = 0; i < FREE_N_CHANNELS; i++) {
+ bkvhead[i] = krwp->bkvhead_free[i];
+ krwp->bkvhead_free[i] = NULL;
+ }
+
+ // Channel 3.
+ head = krwp->head_free;
+ krwp->head_free = NULL;
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ // Handle two first channels.
+ for (i = 0; i < FREE_N_CHANNELS; i++) {
+ for (; bkvhead[i]; bkvhead[i] = bnext) {
+ bnext = bkvhead[i]->next;
+ debug_rcu_bhead_unqueue(bkvhead[i]);
+
+ rcu_lock_acquire(&rcu_callback_map);
+ if (i == 0) { // kmalloc() / kfree().
+ trace_rcu_invoke_kfree_bulk_callback(
+ rcu_state.name, bkvhead[i]->nr_records,
+ bkvhead[i]->records);
+
+ kfree_bulk(bkvhead[i]->nr_records,
+ bkvhead[i]->records);
+ } else { // vmalloc() / vfree().
+ for (j = 0; j < bkvhead[i]->nr_records; j++) {
+ trace_rcu_invoke_kvfree_callback(
+ rcu_state.name,
+ bkvhead[i]->records[j], 0);
+
+ vfree(bkvhead[i]->records[j]);
+ }
+ }
+ rcu_lock_release(&rcu_callback_map);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (put_cached_bnode(krcp, bkvhead[i]))
+ bkvhead[i] = NULL;
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ if (bkvhead[i])
+ free_page((unsigned long) bkvhead[i]);
+
+ cond_resched_tasks_rcu_qs();
+ }
+ }
+
+ /*
+ * Emergency case only. It can happen under low memory
+ * condition when an allocation gets failed, so the "bulk"
+ * path can not be temporary maintained.
+ */
+ for (; head; head = next) {
+ unsigned long offset = (unsigned long)head->func;
+ void *ptr = (void *)head - offset;
+
+ next = head->next;
+ debug_rcu_head_unqueue((struct rcu_head *)ptr);
+ rcu_lock_acquire(&rcu_callback_map);
+ trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset);
+
+ if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset)))
+ kvfree(ptr);
+
+ rcu_lock_release(&rcu_callback_map);
+ cond_resched_tasks_rcu_qs();
+ }
+}
+
+/*
+ * Schedule the kfree batch RCU work to run in workqueue context after a GP.
+ *
+ * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES
+ * timeout has been reached.
+ */
+static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
+{
+ struct kfree_rcu_cpu_work *krwp;
+ bool repeat = false;
+ int i, j;
+
+ lockdep_assert_held(&krcp->lock);
+
+ for (i = 0; i < KFREE_N_BATCHES; i++) {
+ krwp = &(krcp->krw_arr[i]);
+
+ /*
+ * Try to detach bkvhead or head and attach it over any
+ * available corresponding free channel. It can be that
+ * a previous RCU batch is in progress, it means that
+ * immediately to queue another one is not possible so
+ * return false to tell caller to retry.
+ */
+ if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) ||
+ (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) ||
+ (krcp->head && !krwp->head_free)) {
+ // Channel 1 corresponds to SLAB ptrs.
+ // Channel 2 corresponds to vmalloc ptrs.
+ for (j = 0; j < FREE_N_CHANNELS; j++) {
+ if (!krwp->bkvhead_free[j]) {
+ krwp->bkvhead_free[j] = krcp->bkvhead[j];
+ krcp->bkvhead[j] = NULL;
+ }
+ }
+
+ // Channel 3 corresponds to emergency path.
+ if (!krwp->head_free) {
+ krwp->head_free = krcp->head;
+ krcp->head = NULL;
+ }
+
+ WRITE_ONCE(krcp->count, 0);
+
+ /*
+ * One work is per one batch, so there are three
+ * "free channels", the batch can handle. It can
+ * be that the work is in the pending state when
+ * channels have been detached following by each
+ * other.
+ */
+ queue_rcu_work(system_wq, &krwp->rcu_work);
+ }
+
+ // Repeat if any "free" corresponding channel is still busy.
+ if (krcp->bkvhead[0] || krcp->bkvhead[1] || krcp->head)
+ repeat = true;
+ }
+
+ return !repeat;
+}
+
+static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp,
+ unsigned long flags)
+{
+ // Attempt to start a new batch.
+ krcp->monitor_todo = false;
+ if (queue_kfree_rcu_work(krcp)) {
+ // Success! Our job is done here.
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ return;
+ }
+
+ // Previous RCU batch still in progress, try again later.
+ krcp->monitor_todo = true;
+ schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+/*
+ * This function is invoked after the KFREE_DRAIN_JIFFIES timeout.
+ * It invokes kfree_rcu_drain_unlock() to attempt to start another batch.
+ */
+static void kfree_rcu_monitor(struct work_struct *work)
+{
+ unsigned long flags;
+ struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu,
+ monitor_work.work);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (krcp->monitor_todo)
+ kfree_rcu_drain_unlock(krcp, flags);
+ else
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+}
+
+static enum hrtimer_restart
+schedule_page_work_fn(struct hrtimer *t)
+{
+ struct kfree_rcu_cpu *krcp =
+ container_of(t, struct kfree_rcu_cpu, hrtimer);
+
+ queue_work(system_highpri_wq, &krcp->page_cache_work);
+ return HRTIMER_NORESTART;
+}
+
+static void fill_page_cache_func(struct work_struct *work)
+{
+ struct kvfree_rcu_bulk_data *bnode;
+ struct kfree_rcu_cpu *krcp =
+ container_of(work, struct kfree_rcu_cpu,
+ page_cache_work);
+ unsigned long flags;
+ bool pushed;
+ int i;
+
+ for (i = 0; i < rcu_min_cached_objs; i++) {
+ bnode = (struct kvfree_rcu_bulk_data *)
+ __get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+
+ if (bnode) {
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ pushed = put_cached_bnode(krcp, bnode);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ if (!pushed) {
+ free_page((unsigned long) bnode);
+ break;
+ }
+ }
+ }
+
+ atomic_set(&krcp->work_in_progress, 0);
+}
+
+static void
+run_page_cache_worker(struct kfree_rcu_cpu *krcp)
+{
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+ !atomic_xchg(&krcp->work_in_progress, 1)) {
+ hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ krcp->hrtimer.function = schedule_page_work_fn;
+ hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+ }
+}
+
+static inline bool
+kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+{
+ struct kvfree_rcu_bulk_data *bnode;
+ int idx;
+
+ if (unlikely(!krcp->initialized))
+ return false;
+
+ lockdep_assert_held(&krcp->lock);
+ idx = !!is_vmalloc_addr(ptr);
+
+ /* Check if a new block is required. */
+ if (!krcp->bkvhead[idx] ||
+ krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+ bnode = get_cached_bnode(krcp);
+ /* Switch to emergency path. */
+ if (!bnode)
+ return false;
+
+ /* Initialize the new block. */
+ bnode->nr_records = 0;
+ bnode->next = krcp->bkvhead[idx];
+
+ /* Attach it to the head. */
+ krcp->bkvhead[idx] = bnode;
+ }
+
+ /* Finally insert. */
+ krcp->bkvhead[idx]->records
+ [krcp->bkvhead[idx]->nr_records++] = ptr;
+
+ return true;
+}
+
+/*
+ * Queue a request for lazy invocation of appropriate free routine after a
+ * grace period. Please note there are three paths are maintained, two are the
+ * main ones that use array of pointers interface and third one is emergency
+ * one, that is used only when the main path can not be maintained temporary,
+ * due to memory pressure.
+ *
+ * Each kvfree_call_rcu() request is added to a batch. The batch will be drained
+ * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch will
+ * be free'd in workqueue context. This allows us to: batch requests together to
+ * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load.
+ */
+void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+ unsigned long flags;
+ struct kfree_rcu_cpu *krcp;
+ bool success;
+ void *ptr;
+
+ if (head) {
+ ptr = (void *) head - (unsigned long) func;
+ } else {
+ /*
+ * Please note there is a limitation for the head-less
+ * variant, that is why there is a clear rule for such
+ * objects: it can be used from might_sleep() context
+ * only. For other places please embed an rcu_head to
+ * your data.
+ */
+ might_sleep();
+ ptr = (unsigned long *) func;
+ }
+
+ krcp = krc_this_cpu_lock(&flags);
+
+ // Queue the object but don't yet schedule the batch.
+ if (debug_rcu_head_queue(ptr)) {
+ // Probable double kfree_rcu(), just leak.
+ WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
+ __func__, head);
+
+ // Mark as success and leave.
+ success = true;
+ goto unlock_return;
+ }
+
+ success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+ if (!success) {
+ run_page_cache_worker(krcp);
+
+ if (head == NULL)
+ // Inline if kvfree_rcu(one_arg) call.
+ goto unlock_return;
+
+ head->func = func;
+ head->next = krcp->head;
+ krcp->head = head;
+ success = true;
+ }
+
+ WRITE_ONCE(krcp->count, krcp->count + 1);
+
+ // Set timer to drain after KFREE_DRAIN_JIFFIES.
+ if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+ !krcp->monitor_todo) {
+ krcp->monitor_todo = true;
+ schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES);
+ }
+
+unlock_return:
+ krc_this_cpu_unlock(krcp, flags);
+
+ /*
+ * Inline kvfree() after synchronize_rcu(). We can do
+ * it from might_sleep() context only, so the current
+ * CPU can pass the QS state.
+ */
+ if (!success) {
+ debug_rcu_head_unqueue((struct rcu_head *) ptr);
+ synchronize_rcu();
+ kvfree(ptr);
+ }
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int cpu;
+ unsigned long count = 0;
+
+ /* Snapshot count of all CPUs */
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ count += READ_ONCE(krcp->count);
+ }
+
+ return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+ int cpu, freed = 0;
+ unsigned long flags;
+
+ for_each_possible_cpu(cpu) {
+ int count;
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ count = krcp->count;
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (krcp->monitor_todo)
+ kfree_rcu_drain_unlock(krcp, flags);
+ else
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+ sc->nr_to_scan -= count;
+ freed += count;
+
+ if (sc->nr_to_scan <= 0)
+ break;
+ }
+
+ return freed == 0 ? SHRINK_STOP : freed;
+}
+
+static struct shrinker kfree_rcu_shrinker = {
+ .count_objects = kfree_rcu_shrink_count,
+ .scan_objects = kfree_rcu_shrink_scan,
+ .batch = 0,
+ .seeks = DEFAULT_SEEKS,
+};
+
+void __init kfree_rcu_scheduler_running(void)
+{
+ int cpu;
+ unsigned long flags;
+
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ raw_spin_lock_irqsave(&krcp->lock, flags);
+ if (!krcp->head || krcp->monitor_todo) {
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ continue;
+ }
+ krcp->monitor_todo = true;
+ schedule_delayed_work_on(cpu, &krcp->monitor_work,
+ KFREE_DRAIN_JIFFIES);
+ raw_spin_unlock_irqrestore(&krcp->lock, flags);
+ }
+}
/*
* During early boot, any blocking grace-period wait automatically
- * implies a grace period. Later on, this is never the case for PREEMPT.
+ * implies a grace period. Later on, this is never the case for PREEMPTION.
*
- * Howevr, because a context switch is a grace period for !PREEMPT, any
+ * Howevr, because a context switch is a grace period for !PREEMPTION, any
* blocking grace-period wait automatically implies a grace period if
* there is only one CPU online at any point time during execution of
* either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to
@@ -2792,11 +3727,14 @@
* CPU-local state are performed first. However, we must check for CPU
* stalls first, else we might not get a chance.
*/
-static int rcu_pending(void)
+static int rcu_pending(int user)
{
+ bool gp_in_progress;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
+ lockdep_assert_irqs_disabled();
+
/* Check for CPU stalls, if enabled. */
check_cpu_stall(rdp);
@@ -2804,12 +3742,13 @@
if (rcu_nocb_need_deferred_wakeup(rdp))
return 1;
- /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
- if (rcu_nohz_full_cpu())
+ /* Is this a nohz_full CPU in userspace or idle? (Ignore RCU if so.) */
+ if ((user || rcu_is_cpu_rrupt_from_idle()) && rcu_nohz_full_cpu())
return 0;
/* Is the RCU core waiting for a quiescent state from this CPU? */
- if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm)
+ gp_in_progress = rcu_gp_in_progress();
+ if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm && gp_in_progress)
return 1;
/* Does this CPU have callbacks ready to invoke? */
@@ -2817,8 +3756,7 @@
return 1;
/* Has RCU gone idle with this CPU needing another grace period? */
- if (!rcu_gp_in_progress() &&
- rcu_segcblist_is_enabled(&rdp->cblist) &&
+ if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) ||
!rcu_segcblist_is_offloaded(&rdp->cblist)) &&
!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
@@ -2846,36 +3784,44 @@
/*
* RCU callback function for rcu_barrier(). If we are last, wake
* up the task executing rcu_barrier().
+ *
+ * Note that the value of rcu_state.barrier_sequence must be captured
+ * before the atomic_dec_and_test(). Otherwise, if this CPU is not last,
+ * other CPUs might count the value down to zero before this CPU gets
+ * around to invoking rcu_barrier_trace(), which might result in bogus
+ * data from the next instance of rcu_barrier().
*/
static void rcu_barrier_callback(struct rcu_head *rhp)
{
+ unsigned long __maybe_unused s = rcu_state.barrier_sequence;
+
if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) {
- rcu_barrier_trace(TPS("LastCB"), -1,
- rcu_state.barrier_sequence);
+ rcu_barrier_trace(TPS("LastCB"), -1, s);
complete(&rcu_state.barrier_completion);
} else {
- rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence);
+ rcu_barrier_trace(TPS("CB"), -1, s);
}
}
/*
* Called with preemption disabled, and from cross-cpu IRQ context.
*/
-static void rcu_barrier_func(void *unused)
+static void rcu_barrier_func(void *cpu_in)
{
- struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
+ uintptr_t cpu = (uintptr_t)cpu_in;
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence);
rdp->barrier_head.func = rcu_barrier_callback;
debug_rcu_head_queue(&rdp->barrier_head);
rcu_nocb_lock(rdp);
WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
- if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) {
+ if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
atomic_inc(&rcu_state.barrier_cpu_count);
} else {
debug_rcu_head_unqueue(&rdp->barrier_head);
rcu_barrier_trace(TPS("IRQNQ"), -1,
- rcu_state.barrier_sequence);
+ rcu_state.barrier_sequence);
}
rcu_nocb_unlock(rdp);
}
@@ -2890,7 +3836,7 @@
*/
void rcu_barrier(void)
{
- int cpu;
+ uintptr_t cpu;
struct rcu_data *rdp;
unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence);
@@ -2902,7 +3848,7 @@
/* Did someone else do our work for us? */
if (rcu_seq_done(&rcu_state.barrier_sequence, s)) {
rcu_barrier_trace(TPS("EarlyExit"), -1,
- rcu_state.barrier_sequence);
+ rcu_state.barrier_sequence);
smp_mb(); /* caller's subsequent code after above check. */
mutex_unlock(&rcu_state.barrier_mutex);
return;
@@ -2913,13 +3859,14 @@
rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence);
/*
- * Initialize the count to one rather than to zero in order to
- * avoid a too-soon return to zero in case of a short grace period
- * (or preemption of this task). Exclude CPU-hotplug operations
- * to ensure that no offline CPU has callbacks queued.
+ * Initialize the count to two rather than to zero in order
+ * to avoid a too-soon return to zero in case of an immediate
+ * invocation of the just-enqueued callback (or preemption of
+ * this task). Exclude CPU-hotplug operations to ensure that no
+ * offline non-offloaded CPU has callbacks queued.
*/
init_completion(&rcu_state.barrier_completion);
- atomic_set(&rcu_state.barrier_cpu_count, 1);
+ atomic_set(&rcu_state.barrier_cpu_count, 2);
get_online_cpus();
/*
@@ -2929,16 +3876,26 @@
*/
for_each_possible_cpu(cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
- if (!cpu_online(cpu) &&
+ if (cpu_is_offline(cpu) &&
!rcu_segcblist_is_offloaded(&rdp->cblist))
continue;
- if (rcu_segcblist_n_cbs(&rdp->cblist)) {
+ if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) {
rcu_barrier_trace(TPS("OnlineQ"), cpu,
- rcu_state.barrier_sequence);
- smp_call_function_single(cpu, rcu_barrier_func, NULL, 1);
+ rcu_state.barrier_sequence);
+ smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1);
+ } else if (rcu_segcblist_n_cbs(&rdp->cblist) &&
+ cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu,
+ rcu_state.barrier_sequence);
+ local_irq_disable();
+ rcu_barrier_func((void *)cpu);
+ local_irq_enable();
+ } else if (cpu_is_offline(cpu)) {
+ rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu,
+ rcu_state.barrier_sequence);
} else {
rcu_barrier_trace(TPS("OnlineNQ"), cpu,
- rcu_state.barrier_sequence);
+ rcu_state.barrier_sequence);
}
}
put_online_cpus();
@@ -2947,7 +3904,7 @@
* Now that we have an rcu_barrier_callback() callback on each
* CPU, and thus each counted, remove the initial count.
*/
- if (atomic_dec_and_test(&rcu_state.barrier_cpu_count))
+ if (atomic_sub_and_test(2, &rcu_state.barrier_cpu_count))
complete(&rcu_state.barrier_completion);
/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
@@ -3000,6 +3957,7 @@
/* Set up local state, ensuring consistent view of global state. */
rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
+ INIT_WORK(&rdp->strict_work, strict_work_handler);
WARN_ON_ONCE(rdp->dynticks_nesting != 1);
WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp)));
rdp->rcu_ofl_gp_seq = rcu_state.gp_seq;
@@ -3029,7 +3987,7 @@
/* Set up local state, ensuring consistent view of global state. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
rdp->qlen_last_fqs_check = 0;
- rdp->n_force_qs_snap = rcu_state.n_force_qs;
+ rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
rdp->blimit = blimit;
if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
!rcu_segcblist_is_offloaded(&rdp->cblist))
@@ -3046,12 +4004,12 @@
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
rdp->beenonline = true; /* We have now been online. */
- rdp->gp_seq = rnp->gp_seq;
- rdp->gp_seq_needed = rnp->gp_seq;
+ rdp->gp_seq = READ_ONCE(rnp->gp_seq);
+ rdp->gp_seq_needed = rdp->gp_seq;
rdp->cpu_no_qs.b.norm = true;
rdp->core_needs_qs = false;
rdp->rcu_iw_pending = false;
- rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
+ rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_prepare_kthreads(cpu);
@@ -3089,6 +4047,9 @@
return 0; /* Too early in boot for scheduler work. */
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
+
+ // Stop-machine done, so allow nohz_full to disable tick.
+ tick_dep_clear(TICK_DEP_BIT_RCU);
return 0;
}
@@ -3109,11 +4070,12 @@
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;
}
-static DEFINE_PER_CPU(int, rcu_cpu_started);
-
/*
* 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
@@ -3129,31 +4091,29 @@
{
unsigned long flags;
unsigned long mask;
- int nbits;
- unsigned long oldmask;
struct rcu_data *rdp;
struct rcu_node *rnp;
-
- if (per_cpu(rcu_cpu_started, cpu))
- return;
-
- per_cpu(rcu_cpu_started, cpu) = 1;
+ bool newcpu;
rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (rdp->cpu_started)
+ return;
+ rdp->cpu_started = true;
+
rnp = rdp->mynode;
mask = rdp->grpmask;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rnp->qsmaskinitnext |= mask;
- oldmask = rnp->expmaskinitnext;
+ WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
+ newcpu = !(rnp->expmaskinitnext & mask);
rnp->expmaskinitnext |= mask;
- oldmask ^= rnp->expmaskinitnext;
- nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
/* Allow lockless access for expedited grace periods. */
- smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */
+ smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + newcpu); /* ^^^ */
+ ASSERT_EXCLUSIVE_WRITER(rcu_state.ncpus);
rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+ rcu_disable_urgency_upon_qs(rdp);
/* Report QS -after- changing ->qsmaskinitnext! */
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
} else {
@@ -3194,11 +4154,11 @@
rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
- rnp->qsmaskinitnext &= ~mask;
+ WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
raw_spin_unlock(&rcu_state.ofl_lock);
- per_cpu(rcu_cpu_started, cpu) = 0;
+ rdp->cpu_started = false;
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -3309,7 +4269,10 @@
}
rnp = rcu_get_root();
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- rcu_state.gp_kthread = t;
+ WRITE_ONCE(rcu_state.gp_activity, jiffies);
+ WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
+ // Reset .gp_activity and .gp_req_activity before setting .gp_kthread.
+ smp_store_release(&rcu_state.gp_kthread, t); /* ^^^ */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
wake_up_process(t);
rcu_spawn_nocb_kthreads();
@@ -3539,12 +4502,34 @@
struct workqueue_struct *rcu_gp_wq;
struct workqueue_struct *rcu_par_gp_wq;
+static void __init kfree_rcu_batch_init(void)
+{
+ int cpu;
+ int i;
+
+ for_each_possible_cpu(cpu) {
+ struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+ for (i = 0; i < KFREE_N_BATCHES; i++) {
+ INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
+ krcp->krw_arr[i].krcp = krcp;
+ }
+
+ INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+ INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
+ krcp->initialized = true;
+ }
+ if (register_shrinker(&kfree_rcu_shrinker))
+ pr_err("Failed to register kfree_rcu() shrinker!\n");
+}
+
void __init rcu_init(void)
{
int cpu;
rcu_early_boot_tests();
+ kfree_rcu_batch_init();
rcu_bootup_announce();
rcu_init_geometry();
rcu_init_one();
@@ -3571,6 +4556,13 @@
rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
WARN_ON(!rcu_par_gp_wq);
srcu_init();
+
+ /* Fill in default value for rcutree.qovld boot parameter. */
+ /* -After- the rcu_node ->lock fields are initialized! */
+ if (qovld < 0)
+ qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
+ else
+ qovld_calc = qovld;
}
#include "tree_stall.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index c612f30..e4f66b8 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -16,7 +16,6 @@
#include <linux/cpumask.h>
#include <linux/seqlock.h>
#include <linux/swait.h>
-#include <linux/stop_machine.h>
#include <linux/rcu_node_tree.h>
#include "rcu_segcblist.h"
@@ -42,7 +41,7 @@
raw_spinlock_t __private lock; /* Root rcu_node's lock protects */
/* some rcu_state fields as well as */
/* following. */
- unsigned long gp_seq; /* Track rsp->rcu_gp_seq. */
+ unsigned long gp_seq; /* Track rsp->gp_seq. */
unsigned long gp_seq_needed; /* Track furthest future GP request. */
unsigned long completedqs; /* All QSes done for this node. */
unsigned long qsmask; /* CPUs or groups that need to switch in */
@@ -69,12 +68,14 @@
/* Online CPUs for next expedited GP. */
/* Any CPU that has ever been online will */
/* have its bit set. */
+ unsigned long cbovldmask;
+ /* CPUs experiencing callback overload. */
unsigned long ffmask; /* Fully functional CPUs. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
/* Only one bit will be set in this mask. */
- int grplo; /* lowest-numbered CPU or group here. */
- int grphi; /* highest-numbered CPU or group here. */
- u8 grpnum; /* CPU/group number for next level up. */
+ int grplo; /* lowest-numbered CPU here. */
+ int grphi; /* highest-numbered CPU here. */
+ u8 grpnum; /* group number for next level up. */
u8 level; /* root is at level 0. */
bool wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
/* exit RCU read-side critical sections */
@@ -148,13 +149,14 @@
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
- unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */
+ unsigned long gp_seq; /* Track rsp->gp_seq counter. */
unsigned long gp_seq_needed; /* Track furthest future GP request. */
union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */
bool core_needs_qs; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
bool gpwrap; /* Possible ->gp_seq wrap. */
bool exp_deferred_qs; /* This CPU awaiting a deferred QS? */
+ bool cpu_started; /* RCU watching this onlining CPU. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
unsigned long ticks_this_gp; /* The number of scheduling-clock */
@@ -163,6 +165,7 @@
/* period it is aware of. */
struct irq_work defer_qs_iw; /* Obtain later scheduler attention. */
bool defer_qs_iw_pending; /* Scheduler attention pending? */
+ struct work_struct strict_work; /* Schedule readers for strict GPs. */
/* 2) batch handling */
struct rcu_segcblist cblist; /* Segmented callback list, with */
@@ -170,6 +173,7 @@
/* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
+ unsigned long n_cbs_invoked; /* # callbacks invoked since boot. */
unsigned long n_force_qs_snap;
/* did other CPU force QS recently? */
long blimit; /* Upper limit on a processed batch */
@@ -181,8 +185,9 @@
atomic_t dynticks; /* Even value for idle, else odd. */
bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */
bool rcu_urgent_qs; /* GP old need light quiescent state. */
+ bool rcu_forced_tick; /* Forced tick to provide QS. */
+ bool rcu_forced_tick_exp; /* ... provide QS to expedited GP. */
#ifdef CONFIG_RCU_FAST_NO_HZ
- bool all_lazy; /* All CPU's CBs lazy at idle start? */
unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */
unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */
int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
@@ -299,6 +304,8 @@
u8 boost ____cacheline_internodealigned_in_smp;
/* Subject to priority boost. */
unsigned long gp_seq; /* Grace-period sequence #. */
+ unsigned long gp_max; /* Maximum GP duration in */
+ /* jiffies. */
struct task_struct *gp_kthread; /* Task for grace periods. */
struct swait_queue_head gp_wq; /* Where GP task waits. */
short gp_flags; /* Commands for GP task. */
@@ -321,6 +328,8 @@
atomic_t expedited_need_qs; /* # CPUs left to check in. */
struct swait_queue_head expedited_wq; /* Wait for check-ins. */
int ncpus_snap; /* # CPUs seen last time. */
+ u8 cbovld; /* Callback overload now? */
+ u8 cbovldnext; /* ^ ^ next time? */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
@@ -342,8 +351,6 @@
/* a reluctant CPU. */
unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */
/* GP start. */
- unsigned long gp_max; /* Maximum GP duration in */
- /* jiffies. */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
@@ -355,6 +362,7 @@
/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */
#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */
+#define RCU_GP_FLAG_OVLD 0x4 /* Experiencing callback overload. */
/* Values for rcu_state structure's gp_state field. */
#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */
@@ -367,18 +375,6 @@
#define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */
#define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */
-static const char * const gp_state_names[] = {
- "RCU_GP_IDLE",
- "RCU_GP_WAIT_GPS",
- "RCU_GP_DONE_GPS",
- "RCU_GP_ONOFF",
- "RCU_GP_INIT",
- "RCU_GP_WAIT_FQS",
- "RCU_GP_DOING_FQS",
- "RCU_GP_CLEANUP",
- "RCU_GP_CLEANED",
-};
-
/*
* In order to export the rcu_state name to the tracing tools, it
* needs to be added in the __tracepoint_string section.
@@ -402,8 +398,6 @@
#define RCU_NAME rcu_name
#endif /* #else #ifdef CONFIG_TRACING */
-int rcu_dynticks_snap(struct rcu_data *rdp);
-
/* Forward declarations for tree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
@@ -414,7 +408,6 @@
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_flavor_sched_clock_irq(int user);
-void call_rcu(struct rcu_head *head, rcu_callback_t func);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
@@ -465,6 +458,8 @@
static bool rcu_nohz_full_cpu(void);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
+static void rcu_dynticks_task_trace_enter(void);
+static void rcu_dynticks_task_trace_exit(void);
/* Forward declarations for tree_stall.h */
static void record_gp_stall_check_time(void);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index df90d4d..0dc1634 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -21,7 +21,7 @@
}
/*
- * Return then value that expedited-grace-period counter will have
+ * Return the value that the expedited-grace-period counter will have
* at the end of the current grace period.
*/
static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
@@ -39,7 +39,9 @@
}
/*
- * Take a snapshot of the expedited-grace-period counter.
+ * Take a snapshot of the expedited-grace-period counter, which is the
+ * earliest value that will indicate that a full grace period has
+ * elapsed since the current time.
*/
static unsigned long rcu_exp_gp_seq_snap(void)
{
@@ -143,31 +145,26 @@
* Return non-zero if there is no RCU expedited grace period in progress
* for the specified rcu_node structure, in other words, if all CPUs and
* tasks covered by the specified rcu_node structure have done their bit
- * for the current expedited grace period. Works only for preemptible
- * RCU -- other RCU implementation use other means.
- *
- * Caller must hold the specificed rcu_node structure's ->lock
+ * for the current expedited grace period.
*/
-static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+static bool sync_rcu_exp_done(struct rcu_node *rnp)
{
raw_lockdep_assert_held_rcu_node(rnp);
-
- return rnp->exp_tasks == NULL &&
+ return READ_ONCE(rnp->exp_tasks) == NULL &&
READ_ONCE(rnp->expmask) == 0;
}
/*
- * Like sync_rcu_preempt_exp_done(), but this function assumes the caller
- * doesn't hold the rcu_node's ->lock, and will acquire and release the lock
- * itself
+ * Like sync_rcu_exp_done(), but where the caller does not hold the
+ * rcu_node's ->lock.
*/
-static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
+static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp)
{
unsigned long flags;
bool ret;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ret = sync_rcu_preempt_exp_done(rnp);
+ ret = sync_rcu_exp_done(rnp);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return ret;
@@ -181,8 +178,6 @@
* which the task was queued or to one of that rcu_node structure's ancestors,
* recursively up the tree. (Calm down, calm down, we do the recursion
* iteratively!)
- *
- * Caller must hold the specified rcu_node structure's ->lock.
*/
static void __rcu_report_exp_rnp(struct rcu_node *rnp,
bool wake, unsigned long flags)
@@ -190,8 +185,9 @@
{
unsigned long mask;
+ raw_lockdep_assert_held_rcu_node(rnp);
for (;;) {
- if (!sync_rcu_preempt_exp_done(rnp)) {
+ if (!sync_rcu_exp_done(rnp)) {
if (!rnp->expmask)
rcu_initiate_boost(rnp, flags);
else
@@ -234,7 +230,9 @@
static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
unsigned long mask, bool wake)
{
+ int cpu;
unsigned long flags;
+ struct rcu_data *rdp;
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (!(rnp->expmask & mask)) {
@@ -242,6 +240,13 @@
return;
}
WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
+ for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (!IS_ENABLED(CONFIG_NO_HZ_FULL) || !rdp->rcu_forced_tick_exp)
+ continue;
+ rdp->rcu_forced_tick_exp = false;
+ tick_dep_clear_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+ }
__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
}
@@ -309,7 +314,7 @@
sync_exp_work_done(s));
return true;
}
- rnp->exp_seq_rq = s; /* Followers can wait on us. */
+ WRITE_ONCE(rnp->exp_seq_rq, s); /* Followers can wait on us. */
spin_unlock(&rnp->exp_lock);
trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
rnp->grplo, rnp->grphi, TPS("nxtlvl"));
@@ -345,8 +350,8 @@
/* Each pass checks a CPU for identity, offline, and idle. */
mask_ofl_test = 0;
for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ unsigned long mask = rdp->grpmask;
int snap;
if (raw_smp_processor_id() == cpu ||
@@ -368,13 +373,13 @@
* until such time as the ->expmask bits are cleared.
*/
if (rcu_preempt_has_tasks(rnp))
- rnp->exp_tasks = rnp->blkd_tasks.next;
+ WRITE_ONCE(rnp->exp_tasks, rnp->blkd_tasks.next);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
/* IPI the remaining CPUs for expedited quiescent state. */
for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) {
- unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ unsigned long mask = rdp->grpmask;
retry_ipi:
if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
@@ -382,15 +387,16 @@
continue;
}
if (get_cpu() == cpu) {
+ mask_ofl_test |= mask;
put_cpu();
continue;
}
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
put_cpu();
- if (!ret) {
- mask_ofl_ipi &= ~mask;
+ /* The CPU will report the QS in response to the IPI. */
+ if (!ret)
continue;
- }
+
/* Failed, raced with CPU hotplug operation. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if ((rnp->qsmaskinitnext & mask) &&
@@ -398,16 +404,15 @@
/* Online, so delay for a bit and try again. */
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl"));
- schedule_timeout_uninterruptible(1);
+ schedule_timeout_idle(1);
goto retry_ipi;
}
- /* CPU really is offline, so we can ignore it. */
- if (!(rnp->expmask & mask))
- mask_ofl_ipi &= ~mask;
+ /* CPU really is offline, so we must report its QS. */
+ if (rnp->expmask & mask)
+ mask_ofl_test |= mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/* Report quiescent states for those that went offline. */
- mask_ofl_test |= mask_ofl_ipi;
if (mask_ofl_test)
rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
}
@@ -454,30 +459,67 @@
flush_work(&rnp->rew.rew_work);
}
-static void synchronize_sched_expedited_wait(void)
+/*
+ * Wait for the expedited grace period to elapse, within time limit.
+ * If the time limit is exceeded without the grace period elapsing,
+ * return false, otherwise return true.
+ */
+static bool synchronize_rcu_expedited_wait_once(long tlimit)
+{
+ int t;
+ struct rcu_node *rnp_root = rcu_get_root();
+
+ t = swait_event_timeout_exclusive(rcu_state.expedited_wq,
+ sync_rcu_exp_done_unlocked(rnp_root),
+ tlimit);
+ // Workqueues should not be signaled.
+ if (t > 0 || sync_rcu_exp_done_unlocked(rnp_root))
+ return true;
+ WARN_ON(t < 0); /* workqueues should not be signaled. */
+ return false;
+}
+
+/*
+ * Wait for the expedited grace period to elapse, issuing any needed
+ * RCU CPU stall warnings along the way.
+ */
+static void synchronize_rcu_expedited_wait(void)
{
int cpu;
+ unsigned long j;
unsigned long jiffies_stall;
unsigned long jiffies_start;
unsigned long mask;
int ndetected;
+ struct rcu_data *rdp;
struct rcu_node *rnp;
struct rcu_node *rnp_root = rcu_get_root();
- int ret;
trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
jiffies_stall = rcu_jiffies_till_stall_check();
jiffies_start = jiffies;
+ if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
+ if (synchronize_rcu_expedited_wait_once(1))
+ return;
+ rcu_for_each_leaf_node(rnp) {
+ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+ rdp = per_cpu_ptr(&rcu_data, cpu);
+ if (rdp->rcu_forced_tick_exp)
+ continue;
+ rdp->rcu_forced_tick_exp = true;
+ tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+ }
+ }
+ j = READ_ONCE(jiffies_till_first_fqs);
+ if (synchronize_rcu_expedited_wait_once(j + HZ))
+ return;
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT));
+ }
for (;;) {
- ret = swait_event_timeout_exclusive(
- rcu_state.expedited_wq,
- sync_rcu_preempt_exp_done_unlocked(rnp_root),
- jiffies_stall);
- if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
+ if (synchronize_rcu_expedited_wait_once(jiffies_stall))
return;
- WARN_ON(ret < 0); /* workqueues should not be signaled. */
- if (rcu_cpu_stall_suppress)
+ if (rcu_stall_is_suppressed())
continue;
panic_on_rcu_stall();
pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
@@ -501,19 +543,19 @@
}
pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
jiffies - jiffies_start, rcu_state.expedited_sequence,
- READ_ONCE(rnp_root->expmask),
- ".T"[!!rnp_root->exp_tasks]);
+ data_race(rnp_root->expmask),
+ ".T"[!!data_race(rnp_root->exp_tasks)]);
if (ndetected) {
pr_err("blocking rcu_node structures:");
rcu_for_each_node_breadth_first(rnp) {
if (rnp == rnp_root)
continue; /* printed unconditionally */
- if (sync_rcu_preempt_exp_done_unlocked(rnp))
+ if (sync_rcu_exp_done_unlocked(rnp))
continue;
pr_cont(" l=%u:%d-%d:%#lx/%c",
rnp->level, rnp->grplo, rnp->grphi,
- READ_ONCE(rnp->expmask),
- ".T"[!!rnp->exp_tasks]);
+ data_race(rnp->expmask),
+ ".T"[!!data_race(rnp->exp_tasks)]);
}
pr_cont("\n");
}
@@ -539,7 +581,7 @@
{
struct rcu_node *rnp;
- synchronize_sched_expedited_wait();
+ synchronize_rcu_expedited_wait();
// Switch over to wakeup mode, allowing the next GP to proceed.
// End the previous grace period only after acquiring the mutex
@@ -553,7 +595,7 @@
spin_lock(&rnp->exp_lock);
/* Recheck, avoid hang in case someone just arrived. */
if (ULONG_CMP_LT(rnp->exp_seq_rq, s))
- rnp->exp_seq_rq = s;
+ WRITE_ONCE(rnp->exp_seq_rq, s);
spin_unlock(&rnp->exp_lock);
}
smp_mb(); /* All above changes before wakeup. */
@@ -598,6 +640,7 @@
*/
static void rcu_exp_handler(void *unused)
{
+ int depth = rcu_preempt_depth();
unsigned long flags;
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
@@ -608,7 +651,7 @@
* critical section. If also enabled or idle, immediately
* report the quiescent state, otherwise defer.
*/
- if (!t->rcu_read_lock_nesting) {
+ if (!depth) {
if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
rcu_dynticks_curr_cpu_in_eqs()) {
rcu_report_exp_rdp(rdp);
@@ -632,7 +675,7 @@
* can have caused this quiescent state to already have been
* reported, so we really do need to check ->expmask.
*/
- if (t->rcu_read_lock_nesting > 0) {
+ if (depth > 0) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if (rnp->expmask & rdp->grpmask) {
rdp->exp_deferred_qs = true;
@@ -642,33 +685,11 @@
return;
}
- /*
- * The final and least likely case is where the interrupted
- * code was just about to or just finished exiting the RCU-preempt
- * read-side critical section, and no, we can't tell which.
- * So either way, set ->deferred_qs to flag later code that
- * a quiescent state is required.
- *
- * If the CPU is fully enabled (or if some buggy RCU-preempt
- * read-side critical section is being used from idle), just
- * invoke rcu_preempt_deferred_qs() to immediately report the
- * quiescent state. We cannot use rcu_read_unlock_special()
- * because we are in an interrupt handler, which will cause that
- * function to take an early exit without doing anything.
- *
- * Otherwise, force a context switch after the CPU enables everything.
- */
- rdp->exp_deferred_qs = true;
- if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
- WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
- rcu_preempt_deferred_qs(t);
- } else {
- set_tsk_need_resched(t);
- set_preempt_need_resched();
- }
+ // Finally, negative nesting depth should not happen.
+ WARN_ON_ONCE(1);
}
-/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */
+/* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */
static void sync_sched_exp_online_cleanup(int cpu)
{
}
@@ -680,17 +701,20 @@
*/
static int rcu_print_task_exp_stall(struct rcu_node *rnp)
{
- struct task_struct *t;
+ unsigned long flags;
int ndetected = 0;
+ struct task_struct *t;
- if (!rnp->exp_tasks)
+ if (!READ_ONCE(rnp->exp_tasks))
return 0;
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
t = list_entry(rnp->exp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
pr_cont(" P%d", t->pid);
ndetected++;
}
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return ndetected;
}
@@ -709,11 +733,9 @@
/* Invoked on each online non-idle CPU for expedited quiescent state. */
static void rcu_exp_handler(void *unused)
{
- struct rcu_data *rdp;
- struct rcu_node *rnp;
+ struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+ struct rcu_node *rnp = rdp->mynode;
- rdp = this_cpu_ptr(&rcu_data);
- rnp = rdp->mynode;
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
return;
@@ -738,7 +760,7 @@
my_cpu = get_cpu();
/* Quiescent state either not needed or already requested, leave. */
if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
- __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) {
+ rdp->cpu_no_qs.b.exp) {
put_cpu();
return;
}
@@ -783,7 +805,7 @@
* implementations, it is still unfriendly to real-time workloads, so is
* thus not recommended for any sort of common-case code. In fact, if
* you are using synchronize_rcu_expedited() in a loop, please restructure
- * your code to batch your updates, and then Use a single synchronize_rcu()
+ * your code to batch your updates, and then use a single synchronize_rcu()
* instead.
*
* This has the same semantics as (but is more brutal than) synchronize_rcu().
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a71a4a2..f5ba074 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -36,6 +36,8 @@
pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
if (IS_ENABLED(CONFIG_PROVE_RCU))
pr_info("\tRCU lockdep checking is enabled.\n");
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+ pr_info("\tRCU strict (and thus non-scalable) grace periods enabled.\n");
if (RCU_NUM_LVLS >= 4)
pr_info("\tFour(or more)-level hierarchy is enabled.\n");
if (RCU_FANOUT_LEAF != 16)
@@ -56,6 +58,8 @@
pr_info("\tBoot-time adjustment of callback high-water mark to %ld.\n", qhimark);
if (qlowmark != DEFAULT_RCU_QLOMARK)
pr_info("\tBoot-time adjustment of callback low-water mark to %ld.\n", qlowmark);
+ if (qovld != DEFAULT_RCU_QOVLD)
+ pr_info("\tBoot-time adjustment of callback overload level to %ld.\n", qovld);
if (jiffies_till_first_fqs != ULONG_MAX)
pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs);
if (jiffies_till_next_fqs != ULONG_MAX)
@@ -224,7 +228,7 @@
WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
}
if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
- rnp->exp_tasks = &t->rcu_node_entry;
+ WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry);
WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
!(rnp->qsmask & rdp->grpmask));
WARN_ON_ONCE(!(blkd_state & RCU_EXP_BLKD) !=
@@ -290,8 +294,8 @@
trace_rcu_utilization(TPS("Start context switch"));
lockdep_assert_irqs_disabled();
- WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0);
- if (t->rcu_read_lock_nesting > 0 &&
+ WARN_ON_ONCE(!preempt && rcu_preempt_depth() > 0);
+ if (rcu_preempt_depth() > 0 &&
!t->rcu_read_unlock_special.b.blocked) {
/* Possibly blocking in an RCU read-side critical section. */
@@ -329,6 +333,7 @@
rcu_qs();
if (rdp->exp_deferred_qs)
rcu_report_exp_rdp(rdp);
+ rcu_tasks_qs(current, preempt);
trace_rcu_utilization(TPS("End context switch"));
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -343,11 +348,24 @@
return READ_ONCE(rnp->gp_tasks) != NULL;
}
-/* Bias and limit values for ->rcu_read_lock_nesting. */
-#define RCU_NEST_BIAS INT_MAX
-#define RCU_NEST_NMAX (-INT_MAX / 2)
+/* limit value for ->rcu_read_lock_nesting. */
#define RCU_NEST_PMAX (INT_MAX / 2)
+static void rcu_preempt_read_enter(void)
+{
+ current->rcu_read_lock_nesting++;
+}
+
+static int rcu_preempt_read_exit(void)
+{
+ return --current->rcu_read_lock_nesting;
+}
+
+static void rcu_preempt_depth_set(int val)
+{
+ current->rcu_read_lock_nesting = val;
+}
+
/*
* Preemptible RCU implementation for rcu_read_lock().
* Just increment ->rcu_read_lock_nesting, shared state will be updated
@@ -355,9 +373,11 @@
*/
void __rcu_read_lock(void)
{
- current->rcu_read_lock_nesting++;
+ rcu_preempt_read_enter();
if (IS_ENABLED(CONFIG_PROVE_LOCKING))
- WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX);
+ WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX);
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) && rcu_state.gp_kthread)
+ WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, true);
barrier(); /* critical section after entry code. */
}
EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -373,21 +393,15 @@
{
struct task_struct *t = current;
- if (t->rcu_read_lock_nesting != 1) {
- --t->rcu_read_lock_nesting;
- } else {
+ if (rcu_preempt_read_exit() == 0) {
barrier(); /* critical section before exit code. */
- t->rcu_read_lock_nesting = -RCU_NEST_BIAS;
- barrier(); /* assign before ->rcu_read_unlock_special load */
if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
rcu_read_unlock_special(t);
- barrier(); /* ->rcu_read_unlock_special load before assign */
- t->rcu_read_lock_nesting = 0;
}
if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
- int rrln = t->rcu_read_lock_nesting;
+ int rrln = rcu_preempt_depth();
- WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
+ WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX);
}
}
EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -444,13 +458,13 @@
local_irq_restore(flags);
return;
}
- t->rcu_read_unlock_special.b.deferred_qs = false;
+ t->rcu_read_unlock_special.s = 0;
if (special.b.need_qs) {
- rcu_qs();
- t->rcu_read_unlock_special.b.need_qs = false;
- if (!t->rcu_read_unlock_special.s && !rdp->exp_deferred_qs) {
- local_irq_restore(flags);
- return;
+ if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
+ rcu_report_qs_rdp(rdp);
+ udelay(rcu_unlock_delay);
+ } else {
+ rcu_qs();
}
}
@@ -460,17 +474,11 @@
* tasks are handled when removing the task from the
* blocked-tasks list below.
*/
- if (rdp->exp_deferred_qs) {
+ if (rdp->exp_deferred_qs)
rcu_report_exp_rdp(rdp);
- if (!t->rcu_read_unlock_special.s) {
- local_irq_restore(flags);
- return;
- }
- }
/* Clean up if blocked during RCU read-side critical section. */
if (special.b.blocked) {
- t->rcu_read_unlock_special.b.blocked = false;
/*
* Remove this task from the list it blocked on. The task
@@ -485,7 +493,7 @@
empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
(!empty_norm || rnp->qsmask));
- empty_exp = sync_rcu_preempt_exp_done(rnp);
+ empty_exp = sync_rcu_exp_done(rnp);
smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
np = rcu_next_node_entry(t, rnp);
list_del_init(&t->rcu_node_entry);
@@ -495,12 +503,12 @@
if (&t->rcu_node_entry == rnp->gp_tasks)
WRITE_ONCE(rnp->gp_tasks, np);
if (&t->rcu_node_entry == rnp->exp_tasks)
- rnp->exp_tasks = np;
+ WRITE_ONCE(rnp->exp_tasks, np);
if (IS_ENABLED(CONFIG_RCU_BOOST)) {
/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
if (&t->rcu_node_entry == rnp->boost_tasks)
- rnp->boost_tasks = np;
+ WRITE_ONCE(rnp->boost_tasks, np);
}
/*
@@ -509,7 +517,7 @@
* Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
* so we must take a snapshot of the expedited state.
*/
- empty_exp_now = sync_rcu_preempt_exp_done(rnp);
+ empty_exp_now = sync_rcu_exp_done(rnp);
if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
rnp->gp_seq,
@@ -523,16 +531,17 @@
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
- /* Unboost if we were boosted. */
- if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
- rt_mutex_futex_unlock(&rnp->boost_mtx);
-
/*
* If this was the last task on the expedited lists,
* then we need to report up the rcu_node hierarchy.
*/
if (!empty_exp && empty_exp_now)
rcu_report_exp_rnp(rnp, true);
+
+ /* Unboost if we were boosted. */
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
+ rt_mutex_futex_unlock(&rnp->boost_mtx);
+
} else {
local_irq_restore(flags);
}
@@ -551,7 +560,7 @@
{
return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
READ_ONCE(t->rcu_read_unlock_special.s)) &&
- t->rcu_read_lock_nesting <= 0;
+ rcu_preempt_depth() == 0;
}
/*
@@ -564,16 +573,11 @@
static void rcu_preempt_deferred_qs(struct task_struct *t)
{
unsigned long flags;
- bool couldrecurse = t->rcu_read_lock_nesting >= 0;
if (!rcu_preempt_need_deferred_qs(t))
return;
- if (couldrecurse)
- t->rcu_read_lock_nesting -= RCU_NEST_BIAS;
local_irq_save(flags);
rcu_preempt_deferred_qs_irqrestore(t, flags);
- if (couldrecurse)
- t->rcu_read_lock_nesting += RCU_NEST_BIAS;
}
/*
@@ -610,24 +614,22 @@
struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
struct rcu_node *rnp = rdp->mynode;
- t->rcu_read_unlock_special.b.exp_hint = false;
- exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
- (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
- tick_nohz_full_cpu(rdp->cpu);
+ exp = (t->rcu_blocked_node &&
+ READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
+ (rdp->grpmask & READ_ONCE(rnp->expmask));
// Need to defer quiescent state until everything is enabled.
- if (irqs_were_disabled && use_softirq &&
- (in_interrupt() ||
- (exp && !t->rcu_read_unlock_special.b.deferred_qs))) {
- // Using softirq, safe to awaken, and we get
- // no help from enabling irqs, unlike bh/preempt.
+ if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) {
+ // Using softirq, safe to awaken, and either the
+ // wakeup is free or there is an expedited GP.
raise_softirq_irqoff(RCU_SOFTIRQ);
} else {
// Enabling BH or preempt does reschedule, so...
- // Also if no expediting or NO_HZ_FULL, slow is OK.
+ // Also if no expediting, slow is OK.
+ // Plus nohz_full CPUs eventually get tick enabled.
set_tsk_need_resched(current);
set_preempt_need_resched();
if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
- !rdp->defer_qs_iw_pending && exp) {
+ !rdp->defer_qs_iw_pending && exp && cpu_online(rdp->cpu)) {
// Get scheduler to re-evaluate and call hooks.
// If !IRQ_WORK, FQS scan will eventually IPI.
init_irq_work(&rdp->defer_qs_iw,
@@ -636,11 +638,9 @@
irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
}
}
- t->rcu_read_unlock_special.b.deferred_qs = true;
local_irq_restore(flags);
return;
}
- WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false);
rcu_preempt_deferred_qs_irqrestore(t, flags);
}
@@ -648,8 +648,7 @@
* Check that the list of blocked tasks for the newly completed grace
* period is in fact empty. It is a serious bug to complete a grace
* period that still has RCU readers blocked! This function must be
- * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
- * must be held by the caller.
+ * invoked -before- updating this rnp's ->gp_seq.
*
* Also, if there are blocked tasks on the list, they automatically
* block the newly created grace period, so set up ->gp_tasks accordingly.
@@ -659,6 +658,7 @@
struct task_struct *t;
RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
+ raw_lockdep_assert_held_rcu_node(rnp);
if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
dump_blkd_tasks(rnp, 10);
if (rcu_preempt_has_tasks(rnp) &&
@@ -683,10 +683,11 @@
{
struct task_struct *t = current;
+ lockdep_assert_irqs_disabled();
if (user || rcu_is_cpu_rrupt_from_idle()) {
rcu_note_voluntary_context_switch(current);
}
- if (t->rcu_read_lock_nesting > 0 ||
+ if (rcu_preempt_depth() > 0 ||
(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
/* No QS, force context switch if deferred. */
if (rcu_preempt_need_deferred_qs(t)) {
@@ -696,13 +697,13 @@
} else if (rcu_preempt_need_deferred_qs(t)) {
rcu_preempt_deferred_qs(t); /* Report deferred QS. */
return;
- } else if (!t->rcu_read_lock_nesting) {
+ } else if (!WARN_ON_ONCE(rcu_preempt_depth())) {
rcu_qs(); /* Report immediate QS. */
return;
}
/* If GP is oldish, ask for help from rcu_read_unlock_special(). */
- if (t->rcu_read_lock_nesting > 0 &&
+ if (rcu_preempt_depth() > 0 &&
__this_cpu_read(rcu_data.core_needs_qs) &&
__this_cpu_read(rcu_data.cpu_no_qs.b.norm) &&
!t->rcu_read_unlock_special.b.need_qs &&
@@ -723,11 +724,11 @@
struct task_struct *t = current;
if (unlikely(!list_empty(¤t->rcu_node_entry))) {
- t->rcu_read_lock_nesting = 1;
+ rcu_preempt_depth_set(1);
barrier();
WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
- } else if (unlikely(t->rcu_read_lock_nesting)) {
- t->rcu_read_lock_nesting = 1;
+ } else if (unlikely(rcu_preempt_depth())) {
+ rcu_preempt_depth_set(1);
} else {
return;
}
@@ -752,13 +753,13 @@
raw_lockdep_assert_held_rcu_node(rnp);
pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
__func__, rnp->grplo, rnp->grphi, rnp->level,
- (long)rnp->gp_seq, (long)rnp->completedqs);
+ (long)READ_ONCE(rnp->gp_seq), (long)rnp->completedqs);
for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
- __func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks,
- rnp->exp_tasks);
+ __func__, READ_ONCE(rnp->gp_tasks), data_race(rnp->boost_tasks),
+ READ_ONCE(rnp->exp_tasks));
pr_info("%s: ->blkd_tasks", __func__);
i = 0;
list_for_each(lhp, &rnp->blkd_tasks) {
@@ -780,6 +781,24 @@
#else /* #ifdef CONFIG_PREEMPT_RCU */
/*
+ * If strict grace periods are enabled, and if the calling
+ * __rcu_read_unlock() marks the beginning of a quiescent state, immediately
+ * report that quiescent state and, if requested, spin for a bit.
+ */
+void rcu_read_unlock_strict(void)
+{
+ struct rcu_data *rdp;
+
+ if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) ||
+ irqs_disabled() || preempt_count() || !rcu_state.gp_kthread)
+ return;
+ rdp = this_cpu_ptr(&rcu_data);
+ rcu_report_qs_rdp(rdp);
+ udelay(rcu_unlock_delay);
+}
+EXPORT_SYMBOL_GPL(rcu_read_unlock_strict);
+
+/*
* Tell them what RCU they are running.
*/
static void __init rcu_bootup_announce(void)
@@ -789,7 +808,7 @@
}
/*
- * Note a quiescent state for PREEMPT=n. Because we do not need to know
+ * Note a quiescent state for PREEMPTION=n. Because we do not need to know
* how many quiescent states passed, just if there was at least one since
* the start of the grace period, this just sets a flag. The caller must
* have disabled preemption.
@@ -839,7 +858,7 @@
EXPORT_SYMBOL_GPL(rcu_all_qs);
/*
- * Note a PREEMPT=n context switch. The caller must have disabled interrupts.
+ * Note a PREEMPTION=n context switch. The caller must have disabled interrupts.
*/
void rcu_note_context_switch(bool preempt)
{
@@ -851,8 +870,7 @@
this_cpu_write(rcu_data.rcu_urgent_qs, false);
if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
rcu_momentary_dyntick_idle();
- if (!preempt)
- rcu_tasks_qs(current);
+ rcu_tasks_qs(current, preempt);
out:
trace_rcu_utilization(TPS("End context switch"));
}
@@ -1031,20 +1049,21 @@
trace_rcu_utilization(TPS("Start boost kthread@init"));
for (;;) {
- rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
+ WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_WAITING);
trace_rcu_utilization(TPS("End boost kthread@rcu_wait"));
- rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
+ rcu_wait(READ_ONCE(rnp->boost_tasks) ||
+ READ_ONCE(rnp->exp_tasks));
trace_rcu_utilization(TPS("Start boost kthread@rcu_wait"));
- rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
+ WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_RUNNING);
more2boost = rcu_boost(rnp);
if (more2boost)
spincnt++;
else
spincnt = 0;
if (spincnt > 10) {
- rnp->boost_kthread_status = RCU_KTHREAD_YIELDING;
+ WRITE_ONCE(rnp->boost_kthread_status, RCU_KTHREAD_YIELDING);
trace_rcu_utilization(TPS("End boost kthread@rcu_yield"));
- schedule_timeout_interruptible(2);
+ schedule_timeout_idle(2);
trace_rcu_utilization(TPS("Start boost kthread@rcu_yield"));
spincnt = 0;
}
@@ -1076,12 +1095,12 @@
(rnp->gp_tasks != NULL &&
rnp->boost_tasks == NULL &&
rnp->qsmask == 0 &&
- ULONG_CMP_GE(jiffies, rnp->boost_time))) {
+ (!time_after(rnp->boost_time, jiffies) || rcu_state.cbovld))) {
if (rnp->exp_tasks == NULL)
- rnp->boost_tasks = rnp->gp_tasks;
+ WRITE_ONCE(rnp->boost_tasks, rnp->gp_tasks);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
rcu_wake_cond(rnp->boost_kthread_task,
- rnp->boost_kthread_status);
+ READ_ONCE(rnp->boost_kthread_status));
} else {
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
@@ -1263,10 +1282,9 @@
/*
* This code is invoked when a CPU goes idle, at which point we want
* to have the CPU do everything required for RCU so that it can enter
- * the energy-efficient dyntick-idle mode. This is handled by a
- * state machine implemented by rcu_prepare_for_idle() below.
+ * the energy-efficient dyntick-idle mode.
*
- * The following three proprocessor symbols control this state machine:
+ * The following preprocessor symbol controls this:
*
* RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
* to sleep in dyntick-idle mode with RCU callbacks pending. This
@@ -1275,21 +1293,15 @@
* number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
* system. And if you are -that- concerned about energy efficiency,
* just power the system down and be done with it!
- * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is
- * permitted to sleep in dyntick-idle mode with only lazy RCU
- * callbacks pending. Setting this too high can OOM your system.
*
- * The values below work well in practice. If future workloads require
+ * The value below works well in practice. If future workloads require
* adjustment, they can be converted into kernel config parameters, though
* making the state machine smarter might be a better option.
*/
#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */
-#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
module_param(rcu_idle_gp_delay, int, 0644);
-static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY;
-module_param(rcu_idle_lazy_gp_delay, int, 0644);
/*
* Try to advance callbacks on the current CPU, but only if it has been
@@ -1328,8 +1340,7 @@
/*
* Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
* to invoke. If the CPU has callbacks, try to advance them. Tell the
- * caller to set the timeout based on whether or not there are non-lazy
- * callbacks.
+ * caller about what to set the timeout.
*
* The caller must have disabled interrupts.
*/
@@ -1355,25 +1366,18 @@
}
rdp->last_accelerate = jiffies;
- /* Request timer delay depending on laziness, and round. */
- rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist);
- if (rdp->all_lazy) {
- dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies;
- } else {
- dj = round_up(rcu_idle_gp_delay + jiffies,
- rcu_idle_gp_delay) - jiffies;
- }
+ /* Request timer and round. */
+ dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies;
+
*nextevt = basemono + dj * TICK_NSEC;
return 0;
}
/*
- * Prepare a CPU for idle from an RCU perspective. The first major task
- * is to sense whether nohz mode has been enabled or disabled via sysfs.
- * The second major task is to check to see if a non-lazy callback has
- * arrived at a CPU that previously had only lazy callbacks. The third
- * major task is to accelerate (that is, assign grace-period numbers to)
- * any recently arrived callbacks.
+ * Prepare a CPU for idle from an RCU perspective. The first major task is to
+ * sense whether nohz mode has been enabled or disabled via sysfs. The second
+ * major task is to accelerate (that is, assign grace-period numbers to) any
+ * recently arrived callbacks.
*
* The caller must have disabled interrupts.
*/
@@ -1400,17 +1404,6 @@
return;
/*
- * If a non-lazy callback arrived at a CPU having only lazy
- * callbacks, invoke RCU core for the side-effect of recalculating
- * idle duration on re-entry to idle.
- */
- if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) {
- rdp->all_lazy = false;
- invoke_rcu_core();
- return;
- }
-
- /*
* If we have not yet accelerated this jiffy, accelerate all
* callbacks on this CPU.
*/
@@ -1511,6 +1504,7 @@
* flag the contention.
*/
static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
+ __acquires(&rdp->nocb_bypass_lock)
{
lockdep_assert_irqs_disabled();
if (raw_spin_trylock(&rdp->nocb_bypass_lock))
@@ -1554,6 +1548,7 @@
* Release the specified rcu_data structure's ->nocb_bypass_lock.
*/
static void rcu_nocb_bypass_unlock(struct rcu_data *rdp)
+ __releases(&rdp->nocb_bypass_lock)
{
lockdep_assert_irqs_disabled();
raw_spin_unlock(&rdp->nocb_bypass_lock);
@@ -1602,8 +1597,7 @@
static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp)
{
lockdep_assert_irqs_disabled();
- if (rcu_segcblist_is_offloaded(&rdp->cblist) &&
- cpu_online(rdp->cpu))
+ if (rcu_segcblist_is_offloaded(&rdp->cblist))
lockdep_assert_held(&rdp->nocb_lock);
}
@@ -1653,7 +1647,11 @@
rcu_nocb_unlock_irqrestore(rdp, flags);
return;
}
- del_timer(&rdp->nocb_timer);
+
+ if (READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT) {
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
+ del_timer(&rdp->nocb_timer);
+ }
rcu_nocb_unlock_irqrestore(rdp, flags);
raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
if (force || READ_ONCE(rdp_gp->nocb_gp_sleep)) {
@@ -1955,12 +1953,14 @@
struct rcu_data *rdp;
struct rcu_node *rnp;
unsigned long wait_gp_seq = 0; // Suppress "use uninitialized" warning.
+ bool wasempty = false;
/*
* Each pass through the following loop checks for CBs and for the
* nearest grace period (if any) to wait for next. The CB kthreads
* and the global grace-period kthread are awakened if needed.
*/
+ WARN_ON_ONCE(my_rdp->nocb_gp_rdp != my_rdp);
for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) {
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
rcu_nocb_lock_irqsave(rdp, flags);
@@ -1994,10 +1994,13 @@
rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) {
raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
needwake_gp = rcu_advance_cbs(rnp, rdp);
+ wasempty = rcu_segcblist_restempty(&rdp->cblist,
+ RCU_NEXT_READY_TAIL);
raw_spin_unlock_rcu_node(rnp); /* irqs disabled. */
}
// Need to wait on some grace period?
- WARN_ON_ONCE(!rcu_segcblist_restempty(&rdp->cblist,
+ WARN_ON_ONCE(wasempty &&
+ !rcu_segcblist_restempty(&rdp->cblist,
RCU_NEXT_READY_TAIL));
if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) {
if (!needwait_gp ||
@@ -2037,7 +2040,7 @@
/* Polling, so trace if first poll in the series. */
if (gotcbs)
trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
- schedule_timeout_interruptible(1);
+ schedule_timeout_idle(1);
} else if (!needwait_gp) {
/* Wait for callbacks to appear. */
trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep"));
@@ -2166,7 +2169,6 @@
return;
}
ndw = READ_ONCE(rdp->nocb_defer_wakeup);
- WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT);
wake_nocb_gp(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags);
trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake"));
}
@@ -2448,13 +2450,12 @@
return;
waslocked = raw_spin_is_locked(&rdp->nocb_gp_lock);
- wastimer = timer_pending(&rdp->nocb_timer);
+ wastimer = timer_pending(&rdp->nocb_bypass_timer);
wassleep = swait_active(&rdp->nocb_gp_wq);
- if (!rdp->nocb_defer_wakeup && !rdp->nocb_gp_sleep &&
- !waslocked && !wastimer && !wassleep)
+ if (!rdp->nocb_gp_sleep && !waslocked && !wastimer && !wassleep)
return; /* Nothing untowards. */
- pr_info(" !!! %c%c%c%c %c\n",
+ pr_info(" nocb GP activity on CB-only CPU!!! %c%c%c%c %c\n",
"lL"[waslocked],
"dD"[!!rdp->nocb_defer_wakeup],
"tT"[wastimer],
@@ -2559,7 +2560,7 @@
#ifdef CONFIG_NO_HZ_FULL
if (tick_nohz_full_cpu(smp_processor_id()) &&
(!rcu_gp_in_progress() ||
- ULONG_CMP_LT(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
+ time_before(jiffies, READ_ONCE(rcu_state.gp_start) + HZ)))
return true;
#endif /* #ifdef CONFIG_NO_HZ_FULL */
return false;
@@ -2576,7 +2577,7 @@
}
/* Record the current task on dyntick-idle entry. */
-static void rcu_dynticks_task_enter(void)
+static __always_inline void rcu_dynticks_task_enter(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
@@ -2584,9 +2585,27 @@
}
/* Record no current task on dyntick-idle exit. */
-static void rcu_dynticks_task_exit(void)
+static __always_inline void rcu_dynticks_task_exit(void)
{
#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
}
+
+/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
+static __always_inline void rcu_dynticks_task_trace_enter(void)
+{
+#ifdef CONFIG_TASKS_TRACE_RCU
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ current->trc_reader_special.b.need_mb = true;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
+
+/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
+static __always_inline void rcu_dynticks_task_trace_exit(void)
+{
+#ifdef CONFIG_TASKS_TRACE_RCU
+ if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+ current->trc_reader_special.b.need_mb = false;
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
+}
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index b8c9744..251a9af 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -17,10 +17,12 @@
int sysctl_panic_on_rcu_stall __read_mostly;
#ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA (5 * HZ)
+#define RCU_STALL_DELAY_DELTA (5 * HZ)
#else
-#define RCU_STALL_DELAY_DELTA 0
+#define RCU_STALL_DELAY_DELTA 0
#endif
+#define RCU_STALL_MIGHT_DIV 8
+#define RCU_STALL_MIGHT_MIN (2 * HZ)
/* Limit-check stall timeouts specified at boottime and runtime. */
int rcu_jiffies_till_stall_check(void)
@@ -42,6 +44,36 @@
}
EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
+/**
+ * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
+ *
+ * Returns @true if the current grace period is sufficiently old that
+ * it is reasonable to assume that it might be stalled. This can be
+ * useful when deciding whether to allocate memory to enable RCU-mediated
+ * freeing on the one hand or just invoking synchronize_rcu() on the other.
+ * The latter is preferable when the grace period is stalled.
+ *
+ * Note that sampling of the .gp_start and .gp_seq fields must be done
+ * carefully to avoid false positives at the beginnings and ends of
+ * grace periods.
+ */
+bool rcu_gp_might_be_stalled(void)
+{
+ unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
+ unsigned long j = jiffies;
+
+ if (d < RCU_STALL_MIGHT_MIN)
+ d = RCU_STALL_MIGHT_MIN;
+ smp_mb(); // jiffies before .gp_seq to avoid false positives.
+ if (!rcu_gp_in_progress())
+ return false;
+ // Long delays at this point avoids false positive, but a delay
+ // of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
+ smp_mb(); // .gp_seq before second .gp_start
+ // And ditto here.
+ return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
+}
+
/* Don't do RCU CPU stall warnings during long sysrq printouts. */
void rcu_sysrq_start(void)
{
@@ -104,10 +136,10 @@
unsigned long j = jiffies;
unsigned long j1;
- rcu_state.gp_start = j;
+ WRITE_ONCE(rcu_state.gp_start, j);
j1 = rcu_jiffies_till_stall_check();
- /* Record ->gp_start before ->jiffies_stall. */
- smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+ smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+ 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);
}
@@ -128,7 +160,7 @@
{
unsigned long j;
- if (!rcu_kick_kthreads)
+ if (!READ_ONCE(rcu_kick_kthreads))
return;
j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
if (time_after(jiffies, j) && rcu_state.gp_kthread &&
@@ -165,7 +197,7 @@
//
// Printing RCU CPU stall warnings
-#ifdef CONFIG_PREEMPTION
+#ifdef CONFIG_PREEMPT_RCU
/*
* Dump detailed information for all tasks blocking the current RCU
@@ -194,30 +226,78 @@
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+// Communicate task state back to the RCU CPU stall warning request.
+struct rcu_stall_chk_rdr {
+ int nesting;
+ union rcu_special rs;
+ bool on_blkd_list;
+};
+
+/*
+ * Report out the state of a not-running task that is stalling the
+ * current RCU grace period.
+ */
+static bool check_slow_task(struct task_struct *t, void *arg)
+{
+ struct rcu_stall_chk_rdr *rscrp = arg;
+
+ if (task_curr(t))
+ return false; // It is running, so decline to inspect it.
+ rscrp->nesting = t->rcu_read_lock_nesting;
+ rscrp->rs = t->rcu_read_unlock_special;
+ rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
+ return true;
+}
+
/*
* Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+ __releases(rnp->lock)
{
- struct task_struct *t;
+ int i = 0;
int ndetected = 0;
+ struct rcu_stall_chk_rdr rscr;
+ struct task_struct *t;
+ struct task_struct *ts[8];
- if (!rcu_preempt_blocked_readers_cgp(rnp))
+ lockdep_assert_irqs_disabled();
+ if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return 0;
+ }
pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
rnp->level, rnp->grplo, rnp->grphi);
t = list_entry(rnp->gp_tasks->prev,
struct task_struct, rcu_node_entry);
list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
- pr_cont(" P%d", t->pid);
+ get_task_struct(t);
+ ts[i++] = t;
+ if (i >= ARRAY_SIZE(ts))
+ break;
+ }
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ while (i) {
+ t = ts[--i];
+ if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
+ pr_cont(" P%d", t->pid);
+ else
+ pr_cont(" P%d/%d:%c%c%c%c",
+ t->pid, rscr.nesting,
+ ".b"[rscr.rs.b.blocked],
+ ".q"[rscr.rs.b.need_qs],
+ ".e"[rscr.rs.b.exp_hint],
+ ".l"[rscr.on_blkd_list]);
+ lockdep_assert_irqs_disabled();
+ put_task_struct(t);
ndetected++;
}
pr_cont("\n");
return ndetected;
}
-#else /* #ifdef CONFIG_PREEMPTION */
+#else /* #ifdef CONFIG_PREEMPT_RCU */
/*
* Because preemptible RCU does not exist, we never have to check for
@@ -231,11 +311,12 @@
* Because preemptible RCU does not exist, we never have to check for
* tasks blocked within RCU read-side critical sections.
*/
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
{
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return 0;
}
-#endif /* #else #ifdef CONFIG_PREEMPTION */
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
/*
* Dump stacks of all tasks running on stalled CPUs. First try using
@@ -265,11 +346,9 @@
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
- sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+ sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
rdp->last_accelerate & 0xffff, jiffies & 0xffff,
- ".l"[rdp->all_lazy],
- ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
- ".D"[!!rdp->tick_nohz_enabled_snap]);
+ !!rdp->tick_nohz_enabled_snap);
}
#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
@@ -281,6 +360,38 @@
#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
+static const char * const gp_state_names[] = {
+ [RCU_GP_IDLE] = "RCU_GP_IDLE",
+ [RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS",
+ [RCU_GP_DONE_GPS] = "RCU_GP_DONE_GPS",
+ [RCU_GP_ONOFF] = "RCU_GP_ONOFF",
+ [RCU_GP_INIT] = "RCU_GP_INIT",
+ [RCU_GP_WAIT_FQS] = "RCU_GP_WAIT_FQS",
+ [RCU_GP_DOING_FQS] = "RCU_GP_DOING_FQS",
+ [RCU_GP_CLEANUP] = "RCU_GP_CLEANUP",
+ [RCU_GP_CLEANED] = "RCU_GP_CLEANED",
+};
+
+/*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+ if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+ return "???";
+ return gp_state_names[gs];
+}
+
+/* Is the RCU grace-period kthread being starved of CPU time? */
+static bool rcu_is_gp_kthread_starving(unsigned long *jp)
+{
+ unsigned long j = jiffies - READ_ONCE(rcu_state.gp_activity);
+
+ if (jp)
+ *jp = j;
+ return j > 2 * HZ;
+}
+
/*
* Print out diagnostic information for the specified stalled CPU.
*
@@ -295,6 +406,7 @@
static void print_cpu_stall_info(int cpu)
{
unsigned long delta;
+ bool falsepositive;
char fast_no_hz[72];
struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
char *ticks_title;
@@ -315,7 +427,9 @@
}
print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
- pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+ falsepositive = rcu_is_gp_kthread_starving(NULL) &&
+ rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+ pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
cpu,
"O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -327,8 +441,9 @@
rcu_dynticks_snap(rdp) & 0xfff,
rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
- READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
- fast_no_hz);
+ data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+ fast_no_hz,
+ falsepositive ? " (false positive?)" : "");
}
/* Complain about starvation of grace-period kthread. */
@@ -337,15 +452,15 @@
struct task_struct *gpk = rcu_state.gp_kthread;
unsigned long j;
- j = jiffies - READ_ONCE(rcu_state.gp_activity);
- if (j > 2 * HZ) {
+ if (rcu_is_gp_kthread_starving(&j)) {
pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
rcu_state.name, j,
(long)rcu_seq_current(&rcu_state.gp_seq),
- READ_ONCE(rcu_state.gp_flags),
+ data_race(rcu_state.gp_flags),
gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
if (gpk) {
+ 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);
wake_up_process(gpk);
@@ -353,7 +468,7 @@
}
}
-static void print_other_cpu_stall(unsigned long gp_seq)
+static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
{
int cpu;
unsigned long flags;
@@ -363,20 +478,21 @@
struct rcu_node *rnp;
long totqlen = 0;
+ lockdep_assert_irqs_disabled();
+
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
- if (rcu_cpu_stall_suppress)
+ if (rcu_stall_is_suppressed())
return;
/*
* OK, time to rat on our buddy...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
+ * See Documentation/RCU/stallwarn.rst for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
rcu_for_each_leaf_node(rnp) {
raw_spin_lock_irqsave_rcu_node(rnp, flags);
- ndetected += rcu_print_task_stall(rnp);
if (rnp->qsmask != 0) {
for_each_leaf_node_possible_cpu(rnp, cpu)
if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -384,13 +500,14 @@
ndetected++;
}
}
- raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+ ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
+ lockdep_assert_irqs_disabled();
}
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
- smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+ smp_processor_id(), (long)(jiffies - gps),
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
if (ndetected) {
rcu_dump_cpu_stacks();
@@ -403,13 +520,11 @@
pr_err("INFO: Stall ended before state dump start\n");
} else {
j = jiffies;
- gpa = READ_ONCE(rcu_state.gp_activity);
+ gpa = data_race(rcu_state.gp_activity);
pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
rcu_state.name, j - gpa, j, gpa,
- READ_ONCE(jiffies_till_next_fqs),
+ data_race(jiffies_till_next_fqs),
rcu_get_root()->qsmask);
- /* In this case, the current CPU might be at fault. */
- sched_show_task(current);
}
}
/* Rewrite if needed in case of slow consoles. */
@@ -424,7 +539,7 @@
rcu_force_quiescent_state(); /* Kick them all. */
}
-static void print_cpu_stall(void)
+static void print_cpu_stall(unsigned long gps)
{
int cpu;
unsigned long flags;
@@ -432,14 +547,16 @@
struct rcu_node *rnp = rcu_get_root();
long totqlen = 0;
+ lockdep_assert_irqs_disabled();
+
/* Kick and suppress, if so configured. */
rcu_stall_kick_kthreads();
- if (rcu_cpu_stall_suppress)
+ if (rcu_stall_is_suppressed())
return;
/*
* OK, time to rat on ourselves...
- * See Documentation/RCU/stallwarn.txt for info on how to debug
+ * See Documentation/RCU/stallwarn.rst for info on how to debug
* RCU CPU stall warnings.
*/
pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
@@ -449,7 +566,7 @@
for_each_possible_cpu(cpu)
totqlen += rcu_get_n_cbs_cpu(cpu);
pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
- jiffies - rcu_state.gp_start,
+ jiffies - gps,
(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
rcu_check_gp_kthread_starvation();
@@ -486,7 +603,8 @@
unsigned long js;
struct rcu_node *rnp;
- if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+ lockdep_assert_irqs_disabled();
+ if ((rcu_stall_is_suppressed() && !READ_ONCE(rcu_kick_kthreads)) ||
!rcu_gp_in_progress())
return;
rcu_stall_kick_kthreads();
@@ -536,8 +654,8 @@
return;
/* We haven't checked in, so go dump stack. */
- print_cpu_stall();
- if (rcu_cpu_stall_ftrace_dump)
+ print_cpu_stall(gps);
+ if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
rcu_ftrace_dump(DUMP_ALL);
} else if (rcu_gp_in_progress() &&
@@ -553,8 +671,8 @@
return;
/* They had a few time units to dump stack, so complain. */
- print_other_cpu_stall(gs2);
- if (rcu_cpu_stall_ftrace_dump)
+ print_other_cpu_stall(gs2, gps);
+ if (READ_ONCE(rcu_cpu_stall_ftrace_dump))
rcu_ftrace_dump(DUMP_ALL);
}
}
@@ -569,6 +687,7 @@
*/
void show_rcu_gp_kthreads(void)
{
+ unsigned long cbs = 0;
int cpu;
unsigned long j;
unsigned long ja;
@@ -576,43 +695,46 @@
unsigned long jw;
struct rcu_data *rdp;
struct rcu_node *rnp;
+ struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
j = jiffies;
- ja = j - READ_ONCE(rcu_state.gp_activity);
- jr = j - READ_ONCE(rcu_state.gp_req_activity);
- jw = j - READ_ONCE(rcu_state.gp_wake_time);
+ ja = j - data_race(rcu_state.gp_activity);
+ jr = j - data_race(rcu_state.gp_req_activity);
+ jw = j - data_race(rcu_state.gp_wake_time);
pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state,
- rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
- ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
- (long)READ_ONCE(rcu_state.gp_seq),
- (long)READ_ONCE(rcu_get_root()->gp_seq_needed),
- READ_ONCE(rcu_state.gp_flags));
+ rcu_state.gp_state, t ? t->state : 0x1ffffL,
+ ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
+ (long)data_race(rcu_state.gp_seq),
+ (long)data_race(rcu_get_root()->gp_seq_needed),
+ data_race(rcu_state.gp_flags));
rcu_for_each_node_breadth_first(rnp) {
- if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+ if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+ READ_ONCE(rnp->gp_seq_needed)))
continue;
pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
- rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
- (long)rnp->gp_seq_needed);
+ rnp->grplo, rnp->grphi, (long)data_race(rnp->gp_seq),
+ (long)data_race(rnp->gp_seq_needed));
if (!rcu_is_leaf_node(rnp))
continue;
for_each_leaf_node_possible_cpu(rnp, cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
- if (rdp->gpwrap ||
- ULONG_CMP_GE(rcu_state.gp_seq,
- rdp->gp_seq_needed))
+ if (READ_ONCE(rdp->gpwrap) ||
+ ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
+ READ_ONCE(rdp->gp_seq_needed)))
continue;
pr_info("\tcpu %d ->gp_seq_needed %ld\n",
- cpu, (long)rdp->gp_seq_needed);
+ cpu, (long)data_race(rdp->gp_seq_needed));
}
}
for_each_possible_cpu(cpu) {
rdp = per_cpu_ptr(&rcu_data, cpu);
+ cbs += data_race(rdp->n_cbs_invoked);
if (rcu_segcblist_is_offloaded(&rdp->cblist))
show_rcu_nocb_state(rdp);
}
- /* sched_show_task(rcu_state.gp_kthread); */
+ pr_info("RCU callbacks invoked since boot: %lu\n", cbs);
+ show_rcu_tasks_gp_kthreads();
}
EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
@@ -629,7 +751,9 @@
static atomic_t warned = ATOMIC_INIT(0);
if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+ ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+ READ_ONCE(rnp_root->gp_seq_needed)) ||
+ !smp_load_acquire(&rcu_state.gp_kthread)) // Get stable kthread.
return;
j = jiffies; /* Expensive access, and in common case don't get here. */
if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
@@ -640,7 +764,8 @@
raw_spin_lock_irqsave_rcu_node(rnp, flags);
j = jiffies;
if (rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+ ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+ READ_ONCE(rnp_root->gp_seq_needed)) ||
time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_read(&warned)) {
@@ -653,9 +778,10 @@
raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
j = jiffies;
if (rcu_gp_in_progress() ||
- ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
- time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
- time_before(j, rcu_state.gp_activity + gpssdelay) ||
+ ULONG_CMP_GE(READ_ONCE(rnp_root->gp_seq),
+ READ_ONCE(rnp_root->gp_seq_needed)) ||
+ time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+ time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
atomic_xchg(&warned, 1)) {
if (rnp_root != rnp)
/* irqs remain disabled. */
@@ -722,7 +848,7 @@
show_rcu_gp_kthreads();
}
-static struct sysrq_key_op sysrq_rcudump_op = {
+static const struct sysrq_key_op sysrq_rcudump_op = {
.handler = sysrq_show_rcu,
.help_msg = "show-rcu(y)",
.action_msg = "Show RCU tree",
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1861103..849f0aa 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -40,6 +40,9 @@
#include <linux/rcupdate_wait.h>
#include <linux/sched/isolation.h>
#include <linux/kprobes.h>
+#include <linux/slab.h>
+#include <linux/irq_work.h>
+#include <linux/rcupdate_trace.h>
#define CREATE_TRACE_POINTS
@@ -51,9 +54,7 @@
#define MODULE_PARAM_PREFIX "rcupdate."
#ifndef CONFIG_TINY_RCU
-extern int rcu_expedited; /* from sysctl */
module_param(rcu_expedited, int, 0);
-extern int rcu_normal; /* from sysctl */
module_param(rcu_normal, int, 0);
static int rcu_normal_after_boot;
module_param(rcu_normal_after_boot, int, 0);
@@ -64,12 +65,12 @@
* rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section?
* @ret: Best guess answer if lockdep cannot be relied on
*
- * Returns true if lockdep must be ignored, in which case *ret contains
+ * Returns true if lockdep must be ignored, in which case ``*ret`` contains
* the best guess described below. Otherwise returns false, in which
- * case *ret tells the caller nothing and the caller should instead
+ * case ``*ret`` tells the caller nothing and the caller should instead
* consult lockdep.
*
- * If CONFIG_DEBUG_LOCK_ALLOC is selected, set *ret to nonzero iff in an
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, set ``*ret`` to nonzero iff in an
* RCU-sched read-side critical section. In absence of
* CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
* critical section unless it can prove otherwise. Note that disabling
@@ -83,7 +84,7 @@
*
* Note that if the CPU is in the idle loop from an RCU point of view (ie:
* that we are in the section between rcu_idle_enter() and rcu_idle_exit())
- * then rcu_read_lock_held() sets *ret to false even if the CPU did an
+ * then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an
* rcu_read_lock(). The reason for this is that RCU ignores CPUs that are
* in such a section, considering these as in extended quiescent state,
* so such a CPU is effectively never in an RCU read-side critical section
@@ -99,15 +100,15 @@
static bool rcu_read_lock_held_common(bool *ret)
{
if (!debug_lockdep_rcu_enabled()) {
- *ret = 1;
+ *ret = true;
return true;
}
if (!rcu_is_watching()) {
- *ret = 0;
+ *ret = false;
return true;
}
if (!rcu_lockdep_current_cpu_online()) {
- *ret = 0;
+ *ret = false;
return true;
}
return false;
@@ -184,6 +185,8 @@
}
EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
+static bool rcu_boot_ended __read_mostly;
+
/*
* Inform RCU of the end of the in-kernel boot sequence.
*/
@@ -192,8 +195,18 @@
rcu_unexpedite_gp();
if (rcu_normal_after_boot)
WRITE_ONCE(rcu_normal, 1);
+ rcu_boot_ended = true;
}
+/*
+ * Let rcutorture know when it is OK to turn it up to eleven.
+ */
+bool rcu_inkernel_boot_has_ended(void)
+{
+ return rcu_boot_ended;
+}
+EXPORT_SYMBOL_GPL(rcu_inkernel_boot_has_ended);
+
#endif /* #ifndef CONFIG_TINY_RCU */
/*
@@ -218,6 +231,7 @@
{
rcu_test_sync_prims();
rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ kfree_rcu_scheduler_running();
rcu_test_sync_prims();
return 0;
}
@@ -227,32 +241,44 @@
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static struct lock_class_key rcu_lock_key;
-struct lockdep_map rcu_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
+struct lockdep_map rcu_lock_map = {
+ .name = "rcu_read_lock",
+ .key = &rcu_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_CONFIG, /* XXX PREEMPT_RCU ? */
+};
EXPORT_SYMBOL_GPL(rcu_lock_map);
static struct lock_class_key rcu_bh_lock_key;
-struct lockdep_map rcu_bh_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
+struct lockdep_map rcu_bh_lock_map = {
+ .name = "rcu_read_lock_bh",
+ .key = &rcu_bh_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_LOCK also makes BH preemptible */
+};
EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
static struct lock_class_key rcu_sched_lock_key;
-struct lockdep_map rcu_sched_lock_map =
- STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
+struct lockdep_map rcu_sched_lock_map = {
+ .name = "rcu_read_lock_sched",
+ .key = &rcu_sched_lock_key,
+ .wait_type_outer = LD_WAIT_FREE,
+ .wait_type_inner = LD_WAIT_SPIN,
+};
EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
+// Tell lockdep when RCU callbacks are being invoked.
static struct lock_class_key rcu_callback_key;
struct lockdep_map rcu_callback_map =
STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
EXPORT_SYMBOL_GPL(rcu_callback_map);
-int notrace debug_lockdep_rcu_enabled(void)
+noinstr int notrace debug_lockdep_rcu_enabled(void)
{
- return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&
+ return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && READ_ONCE(debug_locks) &&
current->lockdep_recursion == 0;
}
EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
-NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled);
/**
* rcu_read_lock_held() - might we be in RCU read-side critical section?
@@ -353,13 +379,14 @@
might_sleep();
continue;
}
- init_rcu_head_on_stack(&rs_array[i].head);
- init_completion(&rs_array[i].completion);
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
break;
- if (j == i)
+ if (j == i) {
+ init_rcu_head_on_stack(&rs_array[i].head);
+ init_completion(&rs_array[i].completion);
(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
+ }
}
/* Wait for all callbacks to be invoked. */
@@ -370,9 +397,10 @@
for (j = 0; j < i; j++)
if (crcu_array[j] == crcu_array[i])
break;
- if (j == i)
+ if (j == i) {
wait_for_completion(&rs_array[i].completion);
- destroy_rcu_head_on_stack(&rs_array[i].head);
+ destroy_rcu_head_on_stack(&rs_array[i].head);
+ }
}
}
EXPORT_SYMBOL_GPL(__wait_rcu_gp);
@@ -428,14 +456,14 @@
}
EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
-struct debug_obj_descr rcuhead_debug_descr = {
+const struct debug_obj_descr rcuhead_debug_descr = {
.name = "rcu_head",
.is_static_object = rcuhead_is_static_object,
};
EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
-#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
+#if defined(CONFIG_TREE_RCU) || defined(CONFIG_RCU_TRACE)
void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old, unsigned long c)
@@ -464,376 +492,18 @@
#ifdef CONFIG_RCU_STALL_COMMON
int rcu_cpu_stall_ftrace_dump __read_mostly;
module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
-int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
module_param(rcu_cpu_stall_suppress, int, 0644);
int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
module_param(rcu_cpu_stall_timeout, int, 0644);
#endif /* #ifdef CONFIG_RCU_STALL_COMMON */
-#ifdef CONFIG_TASKS_RCU
-
-/*
- * Simple variant of RCU whose quiescent states are voluntary context
- * switch, cond_resched_rcu_qs(), user-space execution, and idle.
- * As such, grace periods can take one good long time. There are no
- * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
- * because this implementation is intended to get the system into a safe
- * state for some of the manipulations involved in tracing and the like.
- * Finally, this implementation does not support high call_rcu_tasks()
- * rates from multiple CPUs. If this is required, per-CPU callback lists
- * will be needed.
- */
-
-/* Global list of callbacks and associated lock. */
-static struct rcu_head *rcu_tasks_cbs_head;
-static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
-static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
-
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-
-/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */
-#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
-static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
-module_param(rcu_task_stall_timeout, int, 0644);
-
-static struct task_struct *rcu_tasks_kthread_ptr;
-
-/**
- * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
- * @rhp: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks() assumes
- * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
- * or transition to usermode execution. As such, there are no read-side
- * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
- * this primitive is intended to determine that all tasks have passed
- * through a safe state, not so much for data-strcuture synchronization.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
-{
- unsigned long flags;
- bool needwake;
-
- rhp->next = NULL;
- rhp->func = func;
- raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
- needwake = !rcu_tasks_cbs_head;
- *rcu_tasks_cbs_tail = rhp;
- rcu_tasks_cbs_tail = &rhp->next;
- raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
- /* We can't create the thread unless interrupts are enabled. */
- if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
- wake_up(&rcu_tasks_cbs_wq);
-}
-EXPORT_SYMBOL_GPL(call_rcu_tasks);
-
-/**
- * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed. These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
- * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
- *
- * This is a very specialized primitive, intended only for a few uses in
- * tracing and other situations requiring manipulation of function
- * preambles and profiling hooks. The synchronize_rcu_tasks() function
- * is not (yet) intended for heavy use from multiple CPUs.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
- * each CPU is guaranteed to have executed a full memory barrier since the
- * end of its last RCU-tasks read-side critical section whose beginning
- * preceded the call to synchronize_rcu_tasks(). In addition, each CPU
- * having an RCU-tasks read-side critical section that extends beyond
- * the return from synchronize_rcu_tasks() is guaranteed to have executed
- * a full memory barrier after the beginning of synchronize_rcu_tasks()
- * and before the beginning of that RCU-tasks read-side critical section.
- * Note that these guarantees include CPUs that are offline, idle, or
- * executing in user mode, as well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
- * (but again only if the system has more than one CPU).
- */
-void synchronize_rcu_tasks(void)
-{
- /* Complain if the scheduler has not started. */
- RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
- "synchronize_rcu_tasks called too soon");
-
- /* Wait for the grace period. */
- wait_rcu_gp(call_rcu_tasks);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
-
-/**
- * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
- *
- * Although the current implementation is guaranteed to wait, it is not
- * obligated to, for example, if there are no pending callbacks.
- */
-void rcu_barrier_tasks(void)
-{
- /* There is only one callback queue, so this is easy. ;-) */
- synchronize_rcu_tasks();
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
-
-/* See if tasks are still holding out, complain if so. */
-static void check_holdout_task(struct task_struct *t,
- bool needreport, bool *firstreport)
-{
- int cpu;
-
- if (!READ_ONCE(t->rcu_tasks_holdout) ||
- t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
- !READ_ONCE(t->on_rq) ||
- (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
- !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
- WRITE_ONCE(t->rcu_tasks_holdout, false);
- list_del_init(&t->rcu_tasks_holdout_list);
- put_task_struct(t);
- return;
- }
- rcu_request_urgent_qs_task(t);
- if (!needreport)
- return;
- if (*firstreport) {
- pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
- *firstreport = false;
- }
- cpu = task_cpu(t);
- pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
- t, ".I"[is_idle_task(t)],
- "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
- t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
- t->rcu_tasks_idle_cpu, cpu);
- sched_show_task(t);
-}
-
-/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
-static int __noreturn rcu_tasks_kthread(void *arg)
-{
- unsigned long flags;
- struct task_struct *g, *t;
- unsigned long lastreport;
- struct rcu_head *list;
- struct rcu_head *next;
- LIST_HEAD(rcu_tasks_holdouts);
- int fract;
-
- /* Run on housekeeping CPUs by default. Sysadm can move if desired. */
- housekeeping_affine(current, HK_FLAG_RCU);
-
- /*
- * Each pass through the following loop makes one check for
- * newly arrived callbacks, and, if there are some, waits for
- * one RCU-tasks grace period and then invokes the callbacks.
- * This loop is terminated by the system going down. ;-)
- */
- for (;;) {
-
- /* Pick up any new callbacks. */
- raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
- list = rcu_tasks_cbs_head;
- rcu_tasks_cbs_head = NULL;
- rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
- raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-
- /* If there were none, wait a bit and start over. */
- if (!list) {
- wait_event_interruptible(rcu_tasks_cbs_wq,
- rcu_tasks_cbs_head);
- if (!rcu_tasks_cbs_head) {
- WARN_ON(signal_pending(current));
- schedule_timeout_interruptible(HZ/10);
- }
- continue;
- }
-
- /*
- * Wait for all pre-existing t->on_rq and t->nvcsw
- * transitions to complete. Invoking synchronize_rcu()
- * suffices because all these transitions occur with
- * interrupts disabled. Without this synchronize_rcu(),
- * a read-side critical section that started before the
- * grace period might be incorrectly seen as having started
- * after the grace period.
- *
- * This synchronize_rcu() also dispenses with the
- * need for a memory barrier on the first store to
- * ->rcu_tasks_holdout, as it forces the store to happen
- * after the beginning of the grace period.
- */
- synchronize_rcu();
-
- /*
- * There were callbacks, so we need to wait for an
- * RCU-tasks grace period. Start off by scanning
- * the task list for tasks that are not already
- * voluntarily blocked. Mark these tasks and make
- * a list of them in rcu_tasks_holdouts.
- */
- rcu_read_lock();
- for_each_process_thread(g, t) {
- if (t != current && READ_ONCE(t->on_rq) &&
- !is_idle_task(t)) {
- get_task_struct(t);
- t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
- WRITE_ONCE(t->rcu_tasks_holdout, true);
- list_add(&t->rcu_tasks_holdout_list,
- &rcu_tasks_holdouts);
- }
- }
- rcu_read_unlock();
-
- /*
- * Wait for tasks that are in the process of exiting.
- * This does only part of the job, ensuring that all
- * tasks that were previously exiting reach the point
- * where they have disabled preemption, allowing the
- * later synchronize_rcu() to finish the job.
- */
- synchronize_srcu(&tasks_rcu_exit_srcu);
-
- /*
- * Each pass through the following loop scans the list
- * of holdout tasks, removing any that are no longer
- * holdouts. When the list is empty, we are done.
- */
- lastreport = jiffies;
-
- /* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
- fract = 10;
-
- for (;;) {
- bool firstreport;
- bool needreport;
- int rtst;
- struct task_struct *t1;
-
- if (list_empty(&rcu_tasks_holdouts))
- break;
-
- /* Slowly back off waiting for holdouts */
- schedule_timeout_interruptible(HZ/fract);
-
- if (fract > 1)
- fract--;
-
- rtst = READ_ONCE(rcu_task_stall_timeout);
- needreport = rtst > 0 &&
- time_after(jiffies, lastreport + rtst);
- if (needreport)
- lastreport = jiffies;
- firstreport = true;
- WARN_ON(signal_pending(current));
- list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
- rcu_tasks_holdout_list) {
- check_holdout_task(t, needreport, &firstreport);
- cond_resched();
- }
- }
-
- /*
- * Because ->on_rq and ->nvcsw are not guaranteed
- * to have a full memory barriers prior to them in the
- * schedule() path, memory reordering on other CPUs could
- * cause their RCU-tasks read-side critical sections to
- * extend past the end of the grace period. However,
- * because these ->nvcsw updates are carried out with
- * interrupts disabled, we can use synchronize_rcu()
- * to force the needed ordering on all such CPUs.
- *
- * This synchronize_rcu() also confines all
- * ->rcu_tasks_holdout accesses to be within the grace
- * period, avoiding the need for memory barriers for
- * ->rcu_tasks_holdout accesses.
- *
- * In addition, this synchronize_rcu() waits for exiting
- * tasks to complete their final preempt_disable() region
- * of execution, cleaning up after the synchronize_srcu()
- * above.
- */
- synchronize_rcu();
-
- /* Invoke the callbacks. */
- while (list) {
- next = list->next;
- local_bh_disable();
- list->func(list);
- local_bh_enable();
- list = next;
- cond_resched();
- }
- /* Paranoid sleep to keep this from entering a tight loop */
- schedule_timeout_uninterruptible(HZ/10);
- }
-}
-
-/* Spawn rcu_tasks_kthread() at core_initcall() time. */
-static int __init rcu_spawn_tasks_kthread(void)
-{
- struct task_struct *t;
-
- t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
- if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
- return 0;
- smp_mb(); /* Ensure others see full kthread. */
- WRITE_ONCE(rcu_tasks_kthread_ptr, t);
- return 0;
-}
-core_initcall(rcu_spawn_tasks_kthread);
-
-/* Do the srcu_read_lock() for the above synchronize_srcu(). */
-void exit_tasks_rcu_start(void)
-{
- preempt_disable();
- current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
- preempt_enable();
-}
-
-/* Do the srcu_read_unlock() for the above synchronize_srcu(). */
-void exit_tasks_rcu_finish(void)
-{
- preempt_disable();
- __srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
- preempt_enable();
-}
-
-#endif /* #ifdef CONFIG_TASKS_RCU */
-
-#ifndef CONFIG_TINY_RCU
-
-/*
- * Print any non-default Tasks RCU settings.
- */
-static void __init rcu_tasks_bootup_oddness(void)
-{
-#ifdef CONFIG_TASKS_RCU
- if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
- pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
- else
- pr_info("\tTasks RCU enabled.\n");
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
-#endif /* #ifndef CONFIG_TINY_RCU */
+// Suppress boot-time RCU CPU stall warnings and rcutorture writer stall
+// warnings. Also used by rcutorture even if stall warnings are excluded.
+int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
+module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
#ifdef CONFIG_PROVE_RCU
@@ -853,14 +523,22 @@
DEFINE_STATIC_SRCU(early_srcu);
+struct early_boot_kfree_rcu {
+ struct rcu_head rh;
+};
+
static void early_boot_test_call_rcu(void)
{
static struct rcu_head head;
static struct rcu_head shead;
+ struct early_boot_kfree_rcu *rhp;
call_rcu(&head, test_callback);
if (IS_ENABLED(CONFIG_SRCU))
call_srcu(&early_srcu, &shead, test_callback);
+ rhp = kmalloc(sizeof(*rhp), GFP_KERNEL);
+ if (!WARN_ON_ONCE(!rhp))
+ kfree_rcu(rhp, rh);
}
void rcu_early_boot_tests(void)
@@ -897,6 +575,8 @@
void rcu_early_boot_tests(void) {}
#endif /* CONFIG_PROVE_RCU */
+#include "tasks.h"
+
#ifndef CONFIG_TINY_RCU
/*