Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 6d876693 authored by Paul E. McKenney's avatar Paul E. McKenney
Browse files

Merge branches 'doc.2013.03.12a', 'fixes.2013.03.13a' and 'idlenocb.2013.03.26b' into HEAD 

doc.2013.03.12a: Documentation changes.

fixes.2013.03.13a: Miscellaneous fixes.

idlenocb.2013.03.26b: Remove restrictions on no-CBs CPUs, make
	RCU_FAST_NO_HZ take advantage of numbered callbacks, add
	callback acceleration based on numbered callbacks.
parents 3f944adb 81e59494 910ee45d

Documentation/RCU/stallwarn.txt

+24 −9
Original line number Original line Diff line number Diff line
@@ -92,14 +92,14 @@ If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set, 
more information is printed with the stall-warning message, for example:

more information is printed with the stall-warning message, for example:





	INFO: rcu_preempt detected stall on CPU

	INFO: rcu_preempt detected stall on CPU

	0: (63959 ticks this GP) idle=241/3fffffffffffffff/0

	0: (63959 ticks this GP) idle=241/3fffffffffffffff/0 softirq=82/543

	   (t=65000 jiffies)

	   (t=65000 jiffies)





In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is

In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is

printed:

printed:





	INFO: rcu_preempt detected stall on CPU

	INFO: rcu_preempt detected stall on CPU

	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 drain=0 . timer not pending

	0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 nonlazy_posted: 25 .D

	   (t=65000 jiffies)

	   (t=65000 jiffies)





The "(64628 ticks this GP)" indicates that this CPU has taken more

The "(64628 ticks this GP)" indicates that this CPU has taken more
@@ -116,13 +116,28 @@ number between the two "/"s is the value of the nesting, which will 
be a small positive number if in the idle loop and a very large positive

be a small positive number if in the idle loop and a very large positive

number (as shown above) otherwise.

number (as shown above) otherwise.





For CONFIG_RCU_FAST_NO_HZ kernels, the "drain=0" indicates that the CPU is

The "softirq=" portion of the message tracks the number of RCU softirq

not in the process of trying to force itself into dyntick-idle state, the

handlers that the stalled CPU has executed.  The number before the "/"

"." indicates that the CPU has not given up forcing RCU into dyntick-idle

is the number that had executed since boot at the time that this CPU

mode (it would be "H" otherwise), and the "timer not pending" indicates

last noted the beginning of a grace period, which might be the current

that the CPU has not recently forced RCU into dyntick-idle mode (it

(stalled) grace period, or it might be some earlier grace period (for

would otherwise indicate the number of microseconds remaining in this

example, if the CPU might have been in dyntick-idle mode for an extended

forced state).

time period.  The number after the "/" is the number that have executed

since boot until the current time.  If this latter number stays constant

across repeated stall-warning messages, it is possible that RCU's softirq

handlers are no longer able to execute on this CPU.  This can happen if

the stalled CPU is spinning with interrupts are disabled, or, in -rt

kernels, if a high-priority process is starving RCU's softirq handler.



For CONFIG_RCU_FAST_NO_HZ kernels, the "last_accelerate:" prints the

low-order 16 bits (in hex) of the jiffies counter when this CPU last

invoked rcu_try_advance_all_cbs() from rcu_needs_cpu() or last invoked

rcu_accelerate_cbs() from rcu_prepare_for_idle().  The "nonlazy_posted:"

prints the number of non-lazy callbacks posted since the last call to

rcu_needs_cpu().  Finally, an "L" indicates that there are currently

no non-lazy callbacks ("." is printed otherwise, as shown above) and

"D" indicates that dyntick-idle processing is enabled ("." is printed

otherwise, for example, if disabled via the "nohz=" kernel boot parameter).









Multiple Warnings From One Stall

Multiple Warnings From One Stall

Documentation/kernel-parameters.txt

+24 −11
Original line number Original line Diff line number Diff line
@@ -2461,9 +2461,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. 
			In kernels built with CONFIG_RCU_NOCB_CPU=y, set

			In kernels built with CONFIG_RCU_NOCB_CPU=y, set

			the specified list of CPUs to be no-callback CPUs.

			the specified list of CPUs to be no-callback CPUs.

			Invocation of these CPUs' RCU callbacks will

			Invocation of these CPUs' RCU callbacks will

			be offloaded to "rcuoN" kthreads created for

			be offloaded to "rcuox/N" kthreads created for

			that purpose.  This reduces OS jitter on the

			that purpose, where "x" is "b" for RCU-bh, "p"

			for RCU-preempt, and "s" for RCU-sched, and "N"

			is the CPU number.  This reduces OS jitter on the

			offloaded CPUs, which can be useful for HPC and

			offloaded CPUs, which can be useful for HPC and



			real-time workloads.  It can also improve energy

			real-time workloads.  It can also improve energy

			efficiency for asymmetric multiprocessors.

			efficiency for asymmetric multiprocessors.
@@ -2487,6 +2490,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted. 
			leaf rcu_node structure.  Useful for very large

			leaf rcu_node structure.  Useful for very large

			systems.

			systems.





	rcutree.jiffies_till_first_fqs= [KNL,BOOT]

			Set delay from grace-period initialization to

			first attempt to force quiescent states.

			Units are jiffies, minimum value is zero,

			and maximum value is HZ.



	rcutree.jiffies_till_next_fqs= [KNL,BOOT]

			Set delay between subsequent attempts to force

			quiescent states.  Units are jiffies, minimum

			value is one, and maximum value is HZ.



	rcutree.qhimark=	[KNL,BOOT]

	rcutree.qhimark=	[KNL,BOOT]

			Set threshold of queued

			Set threshold of queued

			RCU callbacks over which batch limiting is disabled.

			RCU callbacks over which batch limiting is disabled.
@@ -2501,16 +2515,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. 
	rcutree.rcu_cpu_stall_timeout= [KNL,BOOT]

	rcutree.rcu_cpu_stall_timeout= [KNL,BOOT]

			Set timeout for RCU CPU stall warning messages.

			Set timeout for RCU CPU stall warning messages.





	rcutree.jiffies_till_first_fqs= [KNL,BOOT]

	rcutree.rcu_idle_gp_delay=	[KNL,BOOT]

			Set delay from grace-period initialization to

			Set wakeup interval for idle CPUs that have

			first attempt to force quiescent states.

			RCU callbacks (RCU_FAST_NO_HZ=y).

			Units are jiffies, minimum value is zero,

			and maximum value is HZ.





	rcutree.jiffies_till_next_fqs= [KNL,BOOT]

	rcutree.rcu_idle_lazy_gp_delay=	[KNL,BOOT]

			Set delay between subsequent attempts to force

			Set wakeup interval for idle CPUs that have

			quiescent states.  Units are jiffies, minimum

			only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y).

			value is one, and maximum value is HZ.

			Lazy RCU callbacks are those which RCU can

			prove do nothing more than free memory.





	rcutorture.fqs_duration= [KNL,BOOT]

	rcutorture.fqs_duration= [KNL,BOOT]

			Set duration of force_quiescent_state bursts.

			Set duration of force_quiescent_state bursts.

include/linux/list_bl.h

+5 −0
Original line number Original line Diff line number Diff line
@@ -125,6 +125,11 @@ static inline void hlist_bl_unlock(struct hlist_bl_head *b) 
	__bit_spin_unlock(0, (unsigned long *)b);

	__bit_spin_unlock(0, (unsigned long *)b);

}

}





static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)

{

	return bit_spin_is_locked(0, (unsigned long *)b);

}



/**

/**

 * hlist_bl_for_each_entry	- iterate over list of given type

 * hlist_bl_for_each_entry	- iterate over list of given type

 * @tpos:	the type * to use as a loop cursor.

 * @tpos:	the type * to use as a loop cursor.

include/linux/rculist_bl.h

+1 −1
Original line number Original line Diff line number Diff line
@@ -20,7 +20,7 @@ static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, 
static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)

static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h)

{

{

	return (struct hlist_bl_node *)

	return (struct hlist_bl_node *)

		((unsigned long)rcu_dereference(h->first) & ~LIST_BL_LOCKMASK);

		((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK);

}

}





/**

/**

include/linux/rcupdate.h

+1 −0
Original line number Original line Diff line number Diff line
@@ -80,6 +80,7 @@ extern void do_trace_rcu_torture_read(char *rcutorturename, 
#define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))

#define UINT_CMP_LT(a, b)	(UINT_MAX / 2 < (a) - (b))

#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))

#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))

#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))

#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))

#define ulong2long(a)		(*(long *)(&(a)))





/* Exported common interfaces */

/* Exported common interfaces */