apfs/linux-apfs
0
0
Fork 0
mirror of https://github.com/linux-apfs/linux-apfs.git synced 2026-05-01 15:00:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'rcu/next' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu into core/rcu

Browse Source 
Pull RCU updates from Paul E. McKenney:

"
 * Update RCU documentation.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/611.

 * Miscellaneous fixes.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/619.

 * Full-system idle detection.  This is for use by Frederic
   Weisbecker's adaptive-ticks mechanism.  Its purpose is
   to allow the timekeeping CPU to shut off its tick when
   all other CPUs are idle.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/648.

 * Improve rcutorture test coverage.  These were posted to LKML at
   https://lkml.org/lkml/2013/8/19/675.
"

Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
2013-09-03 07:41:11 +02:00
parent 6e4664525b 25f27ce4a6
commit 7d992feb76
25 changed files with 1609 additions and 832 deletions
Download Patch File Download Diff File Expand all files Collapse all files
kernel/rcu.h
+8 -4
View File
@@ -67,12 +67,15 @@
extern struct debug_obj_descr rcuhead_debug_descr;
static inline void debug_rcu_head_queue(struct rcu_head *head)
static inline int debug_rcu_head_queue(struct rcu_head *head)
{
debug_object_activate(head, &rcuhead_debug_descr);
int r1;
r1 = debug_object_activate(head, &rcuhead_debug_descr);
debug_object_active_state(head, &rcuhead_debug_descr,
STATE_RCU_HEAD_READY,
STATE_RCU_HEAD_QUEUED);
return r1;
}
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -83,8 +86,9 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
debug_object_deactivate(head, &rcuhead_debug_descr);
}
#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
static inline void debug_rcu_head_queue(struct rcu_head *head)
static inline int debug_rcu_head_queue(struct rcu_head *head)
{
return 0;
}
static inline void debug_rcu_head_unqueue(struct rcu_head *head)
@@ -94,7 +98,7 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
extern void kfree(const void *);
static inline bool __rcu_reclaim(char *rn, struct rcu_head *head)
static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
{
unsigned long offset = (unsigned long)head->func;
kernel/rcupdate.c
+1 -101
View File
@@ -211,43 +211,6 @@ static inline void debug_rcu_head_free(struct rcu_head *head)
debug_object_free(head, &rcuhead_debug_descr);
}
/*
* fixup_init is called when:
* - an active object is initialized
*/
static int rcuhead_fixup_init(void *addr, enum debug_obj_state state)
{
struct rcu_head *head = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
/*
* Ensure that queued callbacks are all executed.
* If we detect that we are nested in a RCU read-side critical
* section, we should simply fail, otherwise we would deadlock.
* In !PREEMPT configurations, there is no way to tell if we are
* in a RCU read-side critical section or not, so we never
* attempt any fixup and just print a warning.
*/
#ifndef CONFIG_PREEMPT
WARN_ON_ONCE(1);
return 0;
#endif
if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
irqs_disabled()) {
WARN_ON_ONCE(1);
return 0;
}
rcu_barrier();
rcu_barrier_sched();
rcu_barrier_bh();
debug_object_init(head, &rcuhead_debug_descr);
return 1;
default:
return 0;
}
}
/*
* fixup_activate is called when:
* - an active object is activated
@@ -268,69 +231,8 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state)
debug_object_init(head, &rcuhead_debug_descr);
debug_object_activate(head, &rcuhead_debug_descr);
return 0;
case ODEBUG_STATE_ACTIVE:
/*
* Ensure that queued callbacks are all executed.
* If we detect that we are nested in a RCU read-side critical
* section, we should simply fail, otherwise we would deadlock.
* In !PREEMPT configurations, there is no way to tell if we are
* in a RCU read-side critical section or not, so we never
* attempt any fixup and just print a warning.
*/
#ifndef CONFIG_PREEMPT
WARN_ON_ONCE(1);
return 0;
#endif
if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
irqs_disabled()) {
WARN_ON_ONCE(1);
return 0;
}
rcu_barrier();
rcu_barrier_sched();
rcu_barrier_bh();
debug_object_activate(head, &rcuhead_debug_descr);
return 1;
default:
return 0;
}
}
/*
* fixup_free is called when:
* - an active object is freed
*/
static int rcuhead_fixup_free(void *addr, enum debug_obj_state state)
{
struct rcu_head *head = addr;
switch (state) {
case ODEBUG_STATE_ACTIVE:
/*
* Ensure that queued callbacks are all executed.
* If we detect that we are nested in a RCU read-side critical
* section, we should simply fail, otherwise we would deadlock.
* In !PREEMPT configurations, there is no way to tell if we are
* in a RCU read-side critical section or not, so we never
* attempt any fixup and just print a warning.
*/
#ifndef CONFIG_PREEMPT
WARN_ON_ONCE(1);
return 0;
#endif
if (rcu_preempt_depth() != 0 || preempt_count() != 0 ||
irqs_disabled()) {
WARN_ON_ONCE(1);
return 0;
}
rcu_barrier();
rcu_barrier_sched();
rcu_barrier_bh();
debug_object_free(head, &rcuhead_debug_descr);
return 1;
default:
return 0;
}
}
@@ -369,15 +271,13 @@ EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack);
struct debug_obj_descr rcuhead_debug_descr = {
.name = "rcu_head",
.fixup_init = rcuhead_fixup_init,
.fixup_activate = rcuhead_fixup_activate,
.fixup_free = rcuhead_fixup_free,
};
EXPORT_SYMBOL_GPL(rcuhead_debug_descr);
#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE)
void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp,
void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp,
unsigned long secs,
unsigned long c_old, unsigned long c)
{
kernel/rcutiny.c
+1 -1
View File
@@ -264,7 +264,7 @@ void rcu_check_callbacks(int cpu, int user)
*/
static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
{
char *rn = NULL;
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
RCU_TRACE(int cb_count = 0);
kernel/rcutiny_plugin.h
+1 -1
View File
@@ -36,7 +36,7 @@ struct rcu_ctrlblk {
RCU_TRACE(unsigned long gp_start); /* Start time for stalls. */
RCU_TRACE(unsigned long ticks_this_gp); /* Statistic for stalls. */
RCU_TRACE(unsigned long jiffies_stall); /* Jiffies at next stall. */
RCU_TRACE(char *name); /* Name of RCU type. */
RCU_TRACE(const char *name); /* Name of RCU type. */
};
/* Definition for rcupdate control block. */
kernel/rcutorture.c
+180 -218
View File
File diff suppressed because it is too large Load Diff
kernel/rcutree.c
+153 -102
View File
File diff suppressed because it is too large Load Diff
kernel/rcutree.h
+18 -1
View File
@@ -88,6 +88,14 @@ struct rcu_dynticks {
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
long long dynticks_idle_nesting;
/* irq/process nesting level from idle. */
atomic_t dynticks_idle; /* Even value for idle, else odd. */
/* "Idle" excludes userspace execution. */
unsigned long dynticks_idle_jiffies;
/* End of last non-NMI non-idle period. */
#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
#ifdef CONFIG_RCU_FAST_NO_HZ
bool all_lazy; /* Are all CPU's CBs lazy? */
unsigned long nonlazy_posted;
@@ -445,7 +453,7 @@ struct rcu_state {
/* for CPU stalls. */
unsigned long gp_max; /* Maximum GP duration in */
/* jiffies. */
char *name; /* Name of structure. */
const char *name; /* Name of structure. */
char abbr; /* Abbreviated name. */
struct list_head flavors; /* List of RCU flavors. */
struct irq_work wakeup_work; /* Postponed wakeups */
@@ -545,6 +553,15 @@ static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
static void rcu_kick_nohz_cpu(int cpu);
static bool init_nocb_callback_list(struct rcu_data *rdp);
static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
unsigned long *maxj);
static bool is_sysidle_rcu_state(struct rcu_state *rsp);
static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
unsigned long maxj);
static void rcu_bind_gp_kthread(void);
static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
#endif /* #ifndef RCU_TREE_NONCORE */
kernel/rcutree_plugin.h
+440 -20
View File
File diff suppressed because it is too large Load Diff
kernel/time/Kconfig
+50
View File
@@ -134,6 +134,56 @@ config NO_HZ_FULL_ALL
Note the boot CPU will still be kept outside the range to
handle the timekeeping duty.
config NO_HZ_FULL_SYSIDLE
bool "Detect full-system idle state for full dynticks system"
depends on NO_HZ_FULL
default n
help
At least one CPU must keep the scheduling-clock tick running for
timekeeping purposes whenever there is a non-idle CPU, where
"non-idle" also includes dynticks CPUs as long as they are
running non-idle tasks. Because the underlying adaptive-tick
support cannot distinguish between all CPUs being idle and
all CPUs each running a single task in dynticks mode, the
underlying support simply ensures that there is always a CPU
handling the scheduling-clock tick, whether or not all CPUs
are idle. This Kconfig option enables scalable detection of
the all-CPUs-idle state, thus allowing the scheduling-clock
tick to be disabled when all CPUs are idle. Note that scalable
detection of the all-CPUs-idle state means that larger systems
will be slower to declare the all-CPUs-idle state.
Say Y if you would like to help debug all-CPUs-idle detection.
Say N if you are unsure.
config NO_HZ_FULL_SYSIDLE_SMALL
int "Number of CPUs above which large-system approach is used"
depends on NO_HZ_FULL_SYSIDLE
range 1 NR_CPUS
default 8
help
The full-system idle detection mechanism takes a lazy approach
on large systems, as is required to attain decent scalability.
However, on smaller systems, scalability is not anywhere near as
large a concern as is energy efficiency. The sysidle subsystem
therefore uses a fast but non-scalable algorithm for small
systems and a lazier but scalable algorithm for large systems.
This Kconfig parameter defines the number of CPUs in the largest
system that will be considered to be "small".
The default value will be fine in most cases. Battery-powered
systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
numbers of CPUs, and (3) are suffering from battery-lifetime
problems due to long sysidle latencies might wish to experiment
with larger values for this Kconfig parameter. On the other
hand, they might be even better served by disabling NO_HZ_FULL
entirely, given that NO_HZ_FULL is intended for HPC and
real-time workloads that at present do not tend to be run on
battery-powered systems.
Take the default if you are unsure.
config NO_HZ
bool "Old Idle dynticks config"
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
kernel/trace/trace.h
+3
View File
@@ -1022,6 +1022,9 @@ extern struct list_head ftrace_events;
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
extern const char *__start___tracepoint_str[];
extern const char *__stop___tracepoint_str[];
void trace_printk_init_buffers(void);
void trace_printk_start_comm(void);
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
kernel/trace/trace_printk.c
+19
View File
@@ -244,12 +244,31 @@ static const char **find_next(void *v, loff_t *pos)
{
const char **fmt = v;
int start_index;
int last_index;
start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt;
if (*pos < start_index)
return __start___trace_bprintk_fmt + *pos;
/*
* The __tracepoint_str section is treated the same as the
* __trace_printk_fmt section. The difference is that the
* __trace_printk_fmt section should only be used by trace_printk()
* in a debugging environment, as if anything exists in that section
* the trace_prink() helper buffers are allocated, which would just
* waste space in a production environment.
*
* The __tracepoint_str sections on the other hand are used by
* tracepoints which need to map pointers to their strings to
* the ASCII text for userspace.
*/
last_index = start_index;
start_index = __stop___tracepoint_str - __start___tracepoint_str;
if (*pos < last_index + start_index)
return __start___tracepoint_str + (*pos - last_index);
return find_next_mod_format(start_index, v, fmt, pos);
}