AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Browse Source 
Pull core updates (RCU and locking) from Ingo Molnar:
 "Most of the diffstat comes from the RCU slow boot regression fixes,
  but there's also a debuggability improvements/fixes."

* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  memblock: Document memblock_is_region_{memory,reserved}()
  rcu: Precompute RCU_FAST_NO_HZ timer offsets
  rcu: Move RCU_FAST_NO_HZ per-CPU variables to rcu_dynticks structure
  rcu: Update RCU_FAST_NO_HZ tracing for lazy callbacks
  rcu: RCU_FAST_NO_HZ detection of callback adoption
  spinlock: Indicate that a lockup is only suspected
  kdump: Execute kmsg_dump(KMSG_DUMP_PANIC) after smp_send_stop()
  panic: Make panic_on_oops configurable
This commit is contained in:
Linus Torvalds 2012-06-15 16:52:35 -07:00
commit a95f9b6e09
11 changed files with 160 additions and 85 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
include/linux/rcutiny.h
View File

@ -87,8 +87,9 @@ static inline void kfree_call_rcu(struct rcu_head *head,
#ifdef CONFIG_TINY_RCU
static inline int rcu_needs_cpu(int cpu)
static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return 0;
}
@ -96,8 +97,9 @@ static inline int rcu_needs_cpu(int cpu)
int rcu_preempt_needs_cpu(void);
static inline int rcu_needs_cpu(int cpu)
static inline int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return rcu_preempt_needs_cpu();
}

2
include/linux/rcutree.h
View File

@ -32,7 +32,7 @@
extern void rcu_init(void);
extern void rcu_note_context_switch(int cpu);
extern int rcu_needs_cpu(int cpu);
extern int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
extern void rcu_cpu_stall_reset(void);
/*

1
include/trace/events/rcu.h
View File

@ -289,6 +289,7 @@ TRACE_EVENT(rcu_dyntick,
* "In holdoff": Nothing to do, holding off after unsuccessful attempt.
* "Begin holdoff": Attempt failed, don't retry until next jiffy.
* "Dyntick with callbacks": Entering dyntick-idle despite callbacks.
* "Dyntick with lazy callbacks": Entering dyntick-idle w/lazy callbacks.
* "More callbacks": Still more callbacks, try again to clear them out.
* "Callbacks drained": All callbacks processed, off to dyntick idle!
* "Timer": Timer fired to cause CPU to continue processing callbacks.

6
kernel/panic.c
View File

@ -27,7 +27,7 @@
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
int panic_on_oops;
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
@ -108,8 +108,6 @@ void panic(const char *fmt, ...)
*/
crash_kexec(NULL);
kmsg_dump(KMSG_DUMP_PANIC);
/*
* Note smp_send_stop is the usual smp shutdown function, which
* unfortunately means it may not be hardened to work in a panic
@ -117,6 +115,8 @@ void panic(const char *fmt, ...)
*/
smp_send_stop();
kmsg_dump(KMSG_DUMP_PANIC);
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
bust_spinlocks(0);

2
kernel/rcutree.c
View File

@ -1397,6 +1397,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
rdp->qlen_lazy += rsp->qlen_lazy;
rdp->qlen += rsp->qlen;
rdp->n_cbs_adopted += rsp->qlen;
if (rsp->qlen_lazy != rsp->qlen)
rcu_idle_count_callbacks_posted();
rsp->qlen_lazy = 0;
rsp->qlen = 0;

14
kernel/rcutree.h
View File

@ -84,6 +84,20 @@ 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_RCU_FAST_NO_HZ
int dyntick_drain; /* Prepare-for-idle state variable. */
unsigned long dyntick_holdoff;
/* No retries for the jiffy of failure. */
struct timer_list idle_gp_timer;
/* Wake up CPU sleeping with callbacks. */
unsigned long idle_gp_timer_expires;
/* When to wake up CPU (for repost). */
bool idle_first_pass; /* First pass of attempt to go idle? */
unsigned long nonlazy_posted;
/* # times non-lazy CBs posted to CPU. */
unsigned long nonlazy_posted_snap;
/* idle-period nonlazy_posted snapshot. */
#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
/* RCU's kthread states for tracing. */

165
kernel/rcutree_plugin.h
View File

@ -1886,8 +1886,9 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
int rcu_needs_cpu(int cpu)
int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
*delta_jiffies = ULONG_MAX;
return rcu_cpu_has_callbacks(cpu);
}
@ -1962,41 +1963,6 @@ static void rcu_idle_count_callbacks_posted(void)
#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */
#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
/* Loop counter for rcu_prepare_for_idle(). */
static DEFINE_PER_CPU(int, rcu_dyntick_drain);
/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
/* Enable special processing on first attempt to enter dyntick-idle mode. */
static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
/* Running count of non-lazy callbacks posted, never decremented. */
static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
/*
* Allow the CPU to enter dyntick-idle mode if either: (1) There are no
* callbacks on this CPU, (2) this CPU has not yet attempted to enter
* dyntick-idle mode, or (3) this CPU is in the process of attempting to
* enter dyntick-idle mode. Otherwise, if we have recently tried and failed
* to enter dyntick-idle mode, we refuse to try to enter it. After all,
* it is better to incur scheduling-clock interrupts than to spin
* continuously for the same time duration!
*/
int rcu_needs_cpu(int cpu)
{
/* Flag a new idle sojourn to the idle-entry state machine. */
per_cpu(rcu_idle_first_pass, cpu) = 1;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(cpu))
return 0;
/* Otherwise, RCU needs the CPU only if it recently tried and failed. */
return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
}
/*
* Does the specified flavor of RCU have non-lazy callbacks pending on
* the specified CPU? Both RCU flavor and CPU are specified by the
@ -2039,6 +2005,47 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
rcu_preempt_cpu_has_nonlazy_callbacks(cpu);
}
/*
* Allow the CPU to enter dyntick-idle mode if either: (1) There are no
* callbacks on this CPU, (2) this CPU has not yet attempted to enter
* dyntick-idle mode, or (3) this CPU is in the process of attempting to
* enter dyntick-idle mode. Otherwise, if we have recently tried and failed
* to enter dyntick-idle mode, we refuse to try to enter it. After all,
* it is better to incur scheduling-clock interrupts than to spin
* continuously for the same time duration!
*
* The delta_jiffies argument is used to store the time when RCU is
* going to need the CPU again if it still has callbacks. The reason
* for this is that rcu_prepare_for_idle() might need to post a timer,
* but if so, it will do so after tick_nohz_stop_sched_tick() has set
* the wakeup time for this CPU. This means that RCU's timer can be
* delayed until the wakeup time, which defeats the purpose of posting
* a timer.
*/
int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
/* Flag a new idle sojourn to the idle-entry state machine. */
rdtp->idle_first_pass = 1;
/* If no callbacks, RCU doesn't need the CPU. */
if (!rcu_cpu_has_callbacks(cpu)) {
*delta_jiffies = ULONG_MAX;
return 0;
}
if (rdtp->dyntick_holdoff == jiffies) {
/* RCU recently tried and failed, so don't try again. */
*delta_jiffies = 1;
return 1;
}
/* Set up for the possibility that RCU will post a timer. */
if (rcu_cpu_has_nonlazy_callbacks(cpu))
*delta_jiffies = RCU_IDLE_GP_DELAY;
else
*delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
return 0;
}
/*
* Handler for smp_call_function_single(). The only point of this
* handler is to wake the CPU up, so the handler does only tracing.
@ -2075,21 +2082,24 @@ static void rcu_idle_gp_timer_func(unsigned long cpu_in)
*/
static void rcu_prepare_for_idle_init(int cpu)
{
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
rcu_idle_gp_timer_func, cpu);
per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
per_cpu(rcu_idle_first_pass, cpu) = 1;
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
rdtp->dyntick_holdoff = jiffies - 1;
setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
rdtp->idle_gp_timer_expires = jiffies - 1;
rdtp->idle_first_pass = 1;
}
/*
* Clean up for exit from idle. Because we are exiting from idle, there
* is no longer any point to rcu_idle_gp_timer, so cancel it. This will
* is no longer any point to ->idle_gp_timer, so cancel it. This will
* do nothing if this timer is not active, so just cancel it unconditionally.
*/
static void rcu_cleanup_after_idle(int cpu)
{
del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
del_timer(&rdtp->idle_gp_timer);
trace_rcu_prep_idle("Cleanup after idle");
}
@ -2108,42 +2118,41 @@ static void rcu_cleanup_after_idle(int cpu)
* Because it is not legal to invoke rcu_process_callbacks() with irqs
* disabled, we do one pass of force_quiescent_state(), then do a
* invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
* later. The per-cpu rcu_dyntick_drain variable controls the sequencing.
* later. The ->dyntick_drain field controls the sequencing.
*
* The caller must have disabled interrupts.
*/
static void rcu_prepare_for_idle(int cpu)
{
struct timer_list *tp;
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
/*
* If this is an idle re-entry, for example, due to use of
* RCU_NONIDLE() or the new idle-loop tracing API within the idle
* loop, then don't take any state-machine actions, unless the
* momentary exit from idle queued additional non-lazy callbacks.
* Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
* Instead, repost the ->idle_gp_timer if this CPU has callbacks
* pending.
*/
if (!per_cpu(rcu_idle_first_pass, cpu) &&
(per_cpu(rcu_nonlazy_posted, cpu) ==
per_cpu(rcu_nonlazy_posted_snap, cpu))) {
if (!rdtp->idle_first_pass &&
(rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
if (rcu_cpu_has_callbacks(cpu)) {
tp = &per_cpu(rcu_idle_gp_timer, cpu);
mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
tp = &rdtp->idle_gp_timer;
mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
}
return;
}
per_cpu(rcu_idle_first_pass, cpu) = 0;
per_cpu(rcu_nonlazy_posted_snap, cpu) =
per_cpu(rcu_nonlazy_posted, cpu) - 1;
rdtp->idle_first_pass = 0;
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
/*
* If there are no callbacks on this CPU, enter dyntick-idle mode.
* Also reset state to avoid prejudicing later attempts.
*/
if (!rcu_cpu_has_callbacks(cpu)) {
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
per_cpu(rcu_dyntick_drain, cpu) = 0;
rdtp->dyntick_holdoff = jiffies - 1;
rdtp->dyntick_drain = 0;
trace_rcu_prep_idle("No callbacks");
return;
}
@ -2152,36 +2161,37 @@ static void rcu_prepare_for_idle(int cpu)
* If in holdoff mode, just return. We will presumably have
* refrained from disabling the scheduling-clock tick.
*/
if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
if (rdtp->dyntick_holdoff == jiffies) {
trace_rcu_prep_idle("In holdoff");
return;
}
/* Check and update the rcu_dyntick_drain sequencing. */
if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
/* Check and update the ->dyntick_drain sequencing. */
if (rdtp->dyntick_drain <= 0) {
/* First time through, initialize the counter. */
per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
} else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
} else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
!rcu_pending(cpu) &&
!local_softirq_pending()) {
/* Can we go dyntick-idle despite still having callbacks? */
trace_rcu_prep_idle("Dyntick with callbacks");
per_cpu(rcu_dyntick_drain, cpu) = 0;
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
if (rcu_cpu_has_nonlazy_callbacks(cpu))
per_cpu(rcu_idle_gp_timer_expires, cpu) =
rdtp->dyntick_drain = 0;
rdtp->dyntick_holdoff = jiffies;
if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
trace_rcu_prep_idle("Dyntick with callbacks");
rdtp->idle_gp_timer_expires =
jiffies + RCU_IDLE_GP_DELAY;
else
per_cpu(rcu_idle_gp_timer_expires, cpu) =
} else {
rdtp->idle_gp_timer_expires =
jiffies + RCU_IDLE_LAZY_GP_DELAY;
tp = &per_cpu(rcu_idle_gp_timer, cpu);
mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
per_cpu(rcu_nonlazy_posted_snap, cpu) =
per_cpu(rcu_nonlazy_posted, cpu);
trace_rcu_prep_idle("Dyntick with lazy callbacks");
}
tp = &rdtp->idle_gp_timer;
mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
return; /* Nothing more to do immediately. */
} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
} else if (--(rdtp->dyntick_drain) <= 0) {
/* We have hit the limit, so time to give up. */
per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
rdtp->dyntick_holdoff = jiffies;
trace_rcu_prep_idle("Begin holdoff");
invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */
return;
@ -2227,7 +2237,7 @@ static void rcu_prepare_for_idle(int cpu)
*/
static void rcu_idle_count_callbacks_posted(void)
{
__this_cpu_add(rcu_nonlazy_posted, 1);
__this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
}
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
@ -2238,11 +2248,12 @@ static void rcu_idle_count_callbacks_posted(void)
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
struct timer_list *tltp = &rdtp->idle_gp_timer;
sprintf(cp, "drain=%d %c timer=%lu",
per_cpu(rcu_dyntick_drain, cpu),
per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
rdtp->dyntick_drain,
rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
timer_pending(tltp) ? tltp->expires - jiffies : -1);
}

7
kernel/time/tick-sched.c
View File

@ -274,6 +274,7 @@ EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
unsigned long rcu_delta_jiffies;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
@ -322,7 +323,7 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
@ -330,6 +331,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
if (rcu_delta_jiffies < delta_jiffies) {
next_jiffies = last_jiffies + rcu_delta_jiffies;
delta_jiffies = rcu_delta_jiffies;
}
}
/*
* Do not stop the tick, if we are only one off

20
lib/Kconfig.debug
View File

@ -241,6 +241,26 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
config PANIC_ON_OOPS
bool "Panic on Oops" if EXPERT
default n
help
Say Y here to enable the kernel to panic when it oopses. This
has the same effect as setting oops=panic on the kernel command
line.
This feature is useful to ensure that the kernel does not do
anything erroneous after an oops which could result in data
corruption or other issues.
Say N if unsure.
config PANIC_ON_OOPS_VALUE
int
range 0 1
default 0 if !PANIC_ON_OOPS
default 1 if PANIC_ON_OOPS
config DETECT_HUNG_TASK
bool "Detect Hung Tasks"
depends on DEBUG_KERNEL

2
lib/spinlock_debug.c
View File

@ -118,7 +118,7 @@ static void __spin_lock_debug(raw_spinlock_t *lock)
/* lockup suspected: */
if (print_once) {
print_once = 0;
spin_dump(lock, "lockup");
spin_dump(lock, "lockup suspected");
#ifdef CONFIG_SMP
trigger_all_cpu_backtrace();
#endif

20
mm/memblock.c
View File

@ -867,6 +867,16 @@ int __init_memblock memblock_is_memory(phys_addr_t addr)
return memblock_search(&memblock.memory, addr) != -1;
}
/**
* memblock_is_region_memory - check if a region is a subset of memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base+@size) is a subset of a memory block.
*
* RETURNS:
* 0 if false, non-zero if true
*/
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
{
int idx = memblock_search(&memblock.memory, base);
@ -879,6 +889,16 @@ int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size
memblock.memory.regions[idx].size) >= end;
}
/**
* memblock_is_region_reserved - check if a region intersects reserved memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base+@size) intersects a reserved memory block.
*
* RETURNS:
* 0 if false, non-zero if true
*/
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
memblock_cap_size(base, &size);