leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

"Tree RCU": scalable classic RCU implementation

Browse Source 
This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs.  Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.

This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion.  This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.

Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.

Updates from v9 (http://lkml.org/lkml/2008/12/2/334):

o	Fixes from remainder of line-by-line code walkthrough,
	including comment spelling, initialization, undesirable
	narrowing due to type conversion, removing redundant memory
	barriers, removing redundant local-variable initialization,
	and removing redundant local variables.

	I do not believe that any of these fixes address the CPU-hotplug
	issues that Andi Kleen was seeing, but please do give it a whirl
	in case the machine is smarter than I am.

	A writeup from the walkthrough may be found at the following
	URL, in case you are suffering from terminal insomnia or
	masochism:

	http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf

o	Made rcutree tracing use seq_file, as suggested some time
	ago by Lai Jiangshan.

o	Added a .csv variant of the rcudata debugfs trace file, to allow
	people having thousands of CPUs to drop the data into
	a spreadsheet.	Tested with oocalc and gnumeric.  Updated
	documentation to suit.

Updates from v8 (http://lkml.org/lkml/2008/11/15/139):

o	Fix a theoretical race between grace-period initialization and
	force_quiescent_state() that could occur if more than three
	jiffies were required to carry out the grace-period
	initialization.  Which it might, if you had enough CPUs.

o	Apply Ingo's printk-standardization patch.

o	Substitute local variables for repeated accesses to global
	variables.

o	Fix comment misspellings and redundant (but harmless) increments
	of ->n_rcu_pending (this latter after having explicitly added it).

o	Apply checkpatch fixes.

Updates from v7 (http://lkml.org/lkml/2008/10/10/291):

o	Fixed a number of problems noted by Gautham Shenoy, including
	the cpu-stall-detection bug that he was having difficulty
	convincing me was real.  ;-)

o	Changed cpu-stall detection to wait for ten seconds rather than
	three in order to reduce false positive, as suggested by Ingo
	Molnar.

o	Produced a design document (http://lwn.net/Articles/305782/).
	The act of writing this document uncovered a number of both
	theoretical and "here and now" bugs as noted below.

o	Fix dynticks_nesting accounting confusion, simplify WARN_ON()
	condition, fix kerneldoc comments, and add memory barriers
	in dynticks interface functions.

o	Add more data to tracing.

o	Remove unused "rcu_barrier" field from rcu_data structure.

o	Count calls to rcu_pending() from scheduling-clock interrupt
	to use as a surrogate timebase should jiffies stop counting.

o	Fix a theoretical race between force_quiescent_state() and
	grace-period initialization.  Yes, initialization does have to
	go on for some jiffies for this race to occur, but given enough
	CPUs...

Updates from v6 (http://lkml.org/lkml/2008/9/23/448):

o	Fix a number of checkpatch.pl complaints.

o	Apply review comments from Ingo Molnar and Lai Jiangshan
	on the stall-detection code.

o	Fix several bugs in !CONFIG_SMP builds.

o	Fix a misspelled config-parameter name so that RCU now announces
	at boot time if stall detection is configured.

o	Run tests on numerous combinations of configurations parameters,
	which after the fixes above, now build and run correctly.

Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):

o	Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
	changeset some time ago, and finally got around to retesting
	this option).

o	Fix some tracing bugs in rcupreempt that caused incorrect
	totals to be printed.

o	I now test with a more brutal random-selection online/offline
	script (attached).  Probably more brutal than it needs to be
	on the people reading it as well, but so it goes.

o	A number of optimizations and usability improvements:

	o	Make rcu_pending() ignore the grace-period timeout when
		there is no grace period in progress.

	o	Make force_quiescent_state() avoid going for a global
		lock in the case where there is no grace period in
		progress.

	o	Rearrange struct fields to improve struct layout.

	o	Make call_rcu() initiate a grace period if RCU was
		idle, rather than waiting for the next scheduling
		clock interrupt.

	o	Invoke rcu_irq_enter() and rcu_irq_exit() only when
		idle, as suggested by Andi Kleen.  I still don't
		completely trust this change, and might back it out.

	o	Make CONFIG_RCU_TRACE be the single config variable
		manipulated for all forms of RCU, instead of the prior
		confusion.

	o	Document tracing files and formats for both rcupreempt
		and rcutree.

Updates from v4 for those missing v5 given its bad subject line:

o	Separated dynticks interface so that NMIs and irqs call separate
	functions, greatly simplifying it.  In particular, this code
	no longer requires a proof of correctness.  ;-)

o	Separated dynticks state out into its own per-CPU structure,
	avoiding the duplicated accounting.

o	The case where a dynticks-idle CPU runs an irq handler that
	invokes call_rcu() is now correctly handled, forcing that CPU
	out of dynticks-idle mode.

o	Review comments have been applied (thank you all!!!).
	For but one example, fixed the dynticks-ordering issue that
	Manfred pointed out, saving me much debugging.  ;-)

o	Adjusted rcuclassic and rcupreempt to handle dynticks changes.

Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel.  It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space.  That said,
I have already gratefully stolen quite a few of Manfred's ideas.

This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy.  Defaults to 32 on 32-bit machines and 64 on
64-bit machines.  If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy.  By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware.  Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems.  I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future.  (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)

In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors.  This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.

Some shortcomings:

o	More bugs will probably surface as a result of an ongoing
	line-by-line code inspection.

	Patches will be provided as required.

o	There are probably hangs, rcutorture failures, &c.  Seems
	quite stable on a 128-CPU machine, but that is kind of small
	compared to 4096 CPUs.  However, seems to do better than
	mainline.

	Patches will be provided as required.

o	The memory footprint of this version is several KB larger
	than rcuclassic.

	A separate UP-only rcutiny patch will be provided, which will
	reduce the memory footprint significantly, even compared
	to the old rcuclassic.  One such patch passes light testing,
	and has a memory footprint smaller even than rcuclassic.
	Initial reaction from various embedded guys was "it is not
	worth it", so am putting it aside.

Credits:

o	Manfred Spraul for ideas, review comments, and bugs spotted,
	as well as some good friendly competition.  ;-)

o	Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
	Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
	for reviews and comments.

o	Thomas Gleixner for much-needed help with some timer issues
	(see patches below).

o	Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
	Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
	Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
	alive despite my heavy abuse^Wtesting.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Paul E. McKenney 2008-12-18 21:55:32 +01:00 committed by Ingo Molnar
parent d110ec3a1e
commit 64db4cfff9
15 changed files with 2671 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Documentation/RCU/00-INDEX
View File

@ -16,6 +16,8 @@ RTFP.txt
- List of RCU papers (bibliography) going back to 1980.
torture.txt
- RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
trace.txt
- CONFIG_RCU_TRACE debugfs files and formats
UP.txt
- RCU on Uniprocessor Systems
whatisRCU.txt

413
Documentation/RCU/trace.txt Normal file
View File

@ -0,0 +1,413 @@
CONFIG_RCU_TRACE debugfs Files and Formats
The rcupreempt and rcutree implementations of RCU provide debugfs trace
output that summarizes counters and state. This information is useful for
debugging RCU itself, and can sometimes also help to debug abuses of RCU.
Note that the rcuclassic implementation of RCU does not provide debugfs
trace output.
The following sections describe the debugfs files and formats for
preemptable RCU (rcupreempt) and hierarchical RCU (rcutree).
Preemptable RCU debugfs Files and Formats
This implementation of RCU provides three debugfs files under the
top-level directory RCU: rcu/rcuctrs (which displays the per-CPU
counters used by preemptable RCU) rcu/rcugp (which displays grace-period
counters), and rcu/rcustats (which internal counters for debugging RCU).
The output of "cat rcu/rcuctrs" looks as follows:
CPU last cur F M
0 5 -5 0 0
1 -1 0 0 0
2 0 1 0 0
3 0 1 0 0
4 0 1 0 0
5 0 1 0 0
6 0 2 0 0
7 0 -1 0 0
8 0 1 0 0
ggp = 26226, state = waitzero
The per-CPU fields are as follows:
o "CPU" gives the CPU number. Offline CPUs are not displayed.
o "last" gives the value of the counter that is being decremented
for the current grace period phase. In the example above,
the counters sum to 4, indicating that there are still four
RCU read-side critical sections still running that started
before the last counter flip.
o "cur" gives the value of the counter that is currently being
both incremented (by rcu_read_lock()) and decremented (by
rcu_read_unlock()). In the example above, the counters sum to
1, indicating that there is only one RCU read-side critical section
still running that started after the last counter flip.
o "F" indicates whether RCU is waiting for this CPU to acknowledge
a counter flip. In the above example, RCU is not waiting on any,
which is consistent with the state being "waitzero" rather than
"waitack".
o "M" indicates whether RCU is waiting for this CPU to execute a
memory barrier. In the above example, RCU is not waiting on any,
which is consistent with the state being "waitzero" rather than
"waitmb".
o "ggp" is the global grace-period counter.
o "state" is the RCU state, which can be one of the following:
o "idle": there is no grace period in progress.
o "waitack": RCU just incremented the global grace-period
counter, which has the effect of reversing the roles of
the "last" and "cur" counters above, and is waiting for
all the CPUs to acknowledge the flip. Once the flip has
been acknowledged, CPUs will no longer be incrementing
what are now the "last" counters, so that their sum will
decrease monotonically down to zero.
o "waitzero": RCU is waiting for the sum of the "last" counters
to decrease to zero.
o "waitmb": RCU is waiting for each CPU to execute a memory
barrier, which ensures that instructions from a given CPU's
last RCU read-side critical section cannot be reordered
with instructions following the memory-barrier instruction.
The output of "cat rcu/rcugp" looks as follows:
oldggp=48870 newggp=48873
Note that reading from this file provokes a synchronize_rcu(). The
"oldggp" value is that of "ggp" from rcu/rcuctrs above, taken before
executing the synchronize_rcu(), and the "newggp" value is also the
"ggp" value, but taken after the synchronize_rcu() command returns.
The output of "cat rcu/rcugp" looks as follows:
na=1337955 nl=40 wa=1337915 wl=44 da=1337871 dl=0 dr=1337871 di=1337871
1=50989 e1=6138 i1=49722 ie1=82 g1=49640 a1=315203 ae1=265563 a2=49640
z1=1401244 ze1=1351605 z2=49639 m1=5661253 me1=5611614 m2=49639
These are counters tracking internal preemptable-RCU events, however,
some of them may be useful for debugging algorithms using RCU. In
particular, the "nl", "wl", and "dl" values track the number of RCU
callbacks in various states. The fields are as follows:
o "na" is the total number of RCU callbacks that have been enqueued
since boot.
o "nl" is the number of RCU callbacks waiting for the previous
grace period to end so that they can start waiting on the next
grace period.
o "wa" is the total number of RCU callbacks that have started waiting
for a grace period since boot. "na" should be roughly equal to
"nl" plus "wa".
o "wl" is the number of RCU callbacks currently waiting for their
grace period to end.
o "da" is the total number of RCU callbacks whose grace periods
have completed since boot. "wa" should be roughly equal to
"wl" plus "da".
o "dr" is the total number of RCU callbacks that have been removed
from the list of callbacks ready to invoke. "dr" should be roughly
equal to "da".
o "di" is the total number of RCU callbacks that have been invoked
since boot. "di" should be roughly equal to "da", though some
early versions of preemptable RCU had a bug so that only the
last CPU's count of invocations was displayed, rather than the
sum of all CPU's counts.
o "1" is the number of calls to rcu_try_flip(). This should be
roughly equal to the sum of "e1", "i1", "a1", "z1", and "m1"
described below. In other words, the number of times that
the state machine is visited should be equal to the sum of the
number of times that each state is visited plus the number of
times that the state-machine lock acquisition failed.
o "e1" is the number of times that rcu_try_flip() was unable to
acquire the fliplock.
o "i1" is the number of calls to rcu_try_flip_idle().
o "ie1" is the number of times rcu_try_flip_idle() exited early
due to the calling CPU having no work for RCU.
o "g1" is the number of times that rcu_try_flip_idle() decided
to start a new grace period. "i1" should be roughly equal to
"ie1" plus "g1".
o "a1" is the number of calls to rcu_try_flip_waitack().
o "ae1" is the number of times that rcu_try_flip_waitack() found
that at least one CPU had not yet acknowledge the new grace period
(AKA "counter flip").
o "a2" is the number of time rcu_try_flip_waitack() found that
all CPUs had acknowledged. "a1" should be roughly equal to
"ae1" plus "a2". (This particular output was collected on
a 128-CPU machine, hence the smaller-than-usual fraction of
calls to rcu_try_flip_waitack() finding all CPUs having already
acknowledged.)
o "z1" is the number of calls to rcu_try_flip_waitzero().
o "ze1" is the number of times that rcu_try_flip_waitzero() found
that not all of the old RCU read-side critical sections had
completed.
o "z2" is the number of times that rcu_try_flip_waitzero() finds
the sum of the counters equal to zero, in other words, that
all of the old RCU read-side critical sections had completed.
The value of "z1" should be roughly equal to "ze1" plus
"z2".
o "m1" is the number of calls to rcu_try_flip_waitmb().
o "me1" is the number of times that rcu_try_flip_waitmb() finds
that at least one CPU has not yet executed a memory barrier.
o "m2" is the number of times that rcu_try_flip_waitmb() finds that
all CPUs have executed a memory barrier.
Hierarchical RCU debugfs Files and Formats
This implementation of RCU provides three debugfs files under the
top-level directory RCU: rcu/rcudata (which displays fields in struct
rcu_data), rcu/rcugp (which displays grace-period counters), and
rcu/rcuhier (which displays the struct rcu_node hierarchy).
The output of "cat rcu/rcudata" looks as follows:
rcu:
0 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=1 rp=3c2a dt=23301/73 dn=2 df=1882 of=0 ri=2126 ql=2 b=10
1 c=4011 g=4012 pq=1 pqc=4011 qp=0 rpfq=3 rp=39a6 dt=78073/1 dn=2 df=1402 of=0 ri=1875 ql=46 b=10
2 c=4010 g=4010 pq=1 pqc=4010 qp=0 rpfq=-5 rp=1d12 dt=16646/0 dn=2 df=3140 of=0 ri=2080 ql=0 b=10
3 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=2b50 dt=21159/1 dn=2 df=2230 of=0 ri=1923 ql=72 b=10
4 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1644 dt=5783/1 dn=2 df=3348 of=0 ri=2805 ql=7 b=10
5 c=4012 g=4013 pq=0 pqc=4011 qp=1 rpfq=3 rp=1aac dt=5879/1 dn=2 df=3140 of=0 ri=2066 ql=10 b=10
6 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=ed8 dt=5847/1 dn=2 df=3797 of=0 ri=1266 ql=10 b=10
7 c=4012 g=4013 pq=1 pqc=4012 qp=1 rpfq=3 rp=1fa2 dt=6199/1 dn=2 df=2795 of=0 ri=2162 ql=28 b=10
rcu_bh:
0 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-145 rp=21d6 dt=23301/73 dn=2 df=0 of=0 ri=0 ql=0 b=10
1 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-170 rp=20ce dt=78073/1 dn=2 df=26 of=0 ri=5 ql=0 b=10
2 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-83 rp=fbd dt=16646/0 dn=2 df=28 of=0 ri=4 ql=0 b=10
3 c=-268 g=-268 pq=1 pqc=-268 qp=0 rpfq=-105 rp=178c dt=21159/1 dn=2 df=28 of=0 ri=2 ql=0 b=10
4 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-30 rp=b54 dt=5783/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
5 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-29 rp=df5 dt=5879/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
6 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-28 rp=788 dt=5847/1 dn=2 df=32 of=0 ri=0 ql=0 b=10
7 c=-268 g=-268 pq=1 pqc=-268 qp=1 rpfq=-53 rp=1098 dt=6199/1 dn=2 df=30 of=0 ri=3 ql=0 b=10
The first section lists the rcu_data structures for rcu, the second for
rcu_bh. Each section has one line per CPU, or eight for this 8-CPU system.
The fields are as follows:
o The number at the beginning of each line is the CPU number.
CPUs numbers followed by an exclamation mark are offline,
but have been online at least once since boot. There will be
no output for CPUs that have never been online, which can be
a good thing in the surprisingly common case where NR_CPUS is
substantially larger than the number of actual CPUs.
o "c" is the count of grace periods that this CPU believes have
completed. CPUs in dynticks idle mode may lag quite a ways
behind, for example, CPU 4 under "rcu" above, which has slept
through the past 25 RCU grace periods. It is not unusual to
see CPUs lagging by thousands of grace periods.
o "g" is the count of grace periods that this CPU believes have
started. Again, CPUs in dynticks idle mode may lag behind.
If the "c" and "g" values are equal, this CPU has already
reported a quiescent state for the last RCU grace period that
it is aware of, otherwise, the CPU believes that it owes RCU a
quiescent state.
o "pq" indicates that this CPU has passed through a quiescent state
for the current grace period. It is possible for "pq" to be
"1" and "c" different than "g", which indicates that although
the CPU has passed through a quiescent state, either (1) this
CPU has not yet reported that fact, (2) some other CPU has not
yet reported for this grace period, or (3) both.
o "pqc" indicates which grace period the last-observed quiescent
state for this CPU corresponds to. This is important for handling
the race between CPU 0 reporting an extended dynticks-idle
quiescent state for CPU 1 and CPU 1 suddenly waking up and
reporting its own quiescent state. If CPU 1 was the last CPU
for the current grace period, then the CPU that loses this race
will attempt to incorrectly mark CPU 1 as having checked in for
the next grace period!
o "qp" indicates that RCU still expects a quiescent state from
this CPU.
o "rpfq" is the number of rcu_pending() calls on this CPU required
to induce this CPU to invoke force_quiescent_state().
o "rp" is low-order four hex digits of the count of how many times
rcu_pending() has been invoked on this CPU.
o "dt" is the current value of the dyntick counter that is incremented
when entering or leaving dynticks idle state, either by the
scheduler or by irq. The number after the "/" is the interrupt
nesting depth when in dyntick-idle state, or one greater than
the interrupt-nesting depth otherwise.
This field is displayed only for CONFIG_NO_HZ kernels.
o "dn" is the current value of the dyntick counter that is incremented
when entering or leaving dynticks idle state via NMI. If both
the "dt" and "dn" values are even, then this CPU is in dynticks
idle mode and may be ignored by RCU. If either of these two
counters is odd, then RCU must be alert to the possibility of
an RCU read-side critical section running on this CPU.
This field is displayed only for CONFIG_NO_HZ kernels.
o "df" is the number of times that some other CPU has forced a
quiescent state on behalf of this CPU due to this CPU being in
dynticks-idle state.
This field is displayed only for CONFIG_NO_HZ kernels.
o "of" is the number of times that some other CPU has forced a
quiescent state on behalf of this CPU due to this CPU being
offline. In a perfect world, this might neve happen, but it
turns out that offlining and onlining a CPU can take several grace
periods, and so there is likely to be an extended period of time
when RCU believes that the CPU is online when it really is not.
Please note that erring in the other direction (RCU believing a
CPU is offline when it is really alive and kicking) is a fatal
error, so it makes sense to err conservatively.
o "ri" is the number of times that RCU has seen fit to send a
reschedule IPI to this CPU in order to get it to report a
quiescent state.
o "ql" is the number of RCU callbacks currently residing on
this CPU. This is the total number of callbacks, regardless
of what state they are in (new, waiting for grace period to
start, waiting for grace period to end, ready to invoke).
o "b" is the batch limit for this CPU. If more than this number
of RCU callbacks is ready to invoke, then the remainder will
be deferred.
The output of "cat rcu/rcugp" looks as follows:
rcu: completed=33062 gpnum=33063
rcu_bh: completed=464 gpnum=464
Again, this output is for both "rcu" and "rcu_bh". The fields are
taken from the rcu_state structure, and are as follows:
o "completed" is the number of grace periods that have completed.
It is comparable to the "c" field from rcu/rcudata in that a
CPU whose "c" field matches the value of "completed" is aware
that the corresponding RCU grace period has completed.
o "gpnum" is the number of grace periods that have started. It is
comparable to the "g" field from rcu/rcudata in that a CPU
whose "g" field matches the value of "gpnum" is aware that the
corresponding RCU grace period has started.
If these two fields are equal (as they are for "rcu_bh" above),
then there is no grace period in progress, in other words, RCU
is idle. On the other hand, if the two fields differ (as they
do for "rcu" above), then an RCU grace period is in progress.
The output of "cat rcu/rcuhier" looks as follows, with very long lines:
c=6902 g=6903 s=2 jfq=3 j=72c7 nfqs=13142/nfqsng=0(13142) fqlh=6
1/1 0:127 ^0
3/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3
3/3f 0:5 ^0 2/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3
rcu_bh:
c=-226 g=-226 s=1 jfq=-5701 j=72c7 nfqs=88/nfqsng=0(88) fqlh=0
0/1 0:127 ^0
0/3 0:35 ^0 0/0 36:71 ^1 0/0 72:107 ^2 0/0 108:127 ^3
0/3f 0:5 ^0 0/3 6:11 ^1 0/0 12:17 ^2 0/0 18:23 ^3 0/0 24:29 ^4 0/0 30:35 ^5 0/0 36:41 ^0 0/0 42:47 ^1 0/0 48:53 ^2 0/0 54:59 ^3 0/0 60:65 ^4 0/0 66:71 ^5 0/0 72:77 ^0 0/0 78:83 ^1 0/0 84:89 ^2 0/0 90:95 ^3 0/0 96:101 ^4 0/0 102:107 ^5 0/0 108:113 ^0 0/0 114:119 ^1 0/0 120:125 ^2 0/0 126:127 ^3
This is once again split into "rcu" and "rcu_bh" portions. The fields are
as follows:
o "c" is exactly the same as "completed" under rcu/rcugp.
o "g" is exactly the same as "gpnum" under rcu/rcugp.
o "s" is the "signaled" state that drives force_quiescent_state()'s
state machine.
o "jfq" is the number of jiffies remaining for this grace period
before force_quiescent_state() is invoked to help push things
along. Note that CPUs in dyntick-idle mode thoughout the grace
period will not report on their own, but rather must be check by
some other CPU via force_quiescent_state().
o "j" is the low-order four hex digits of the jiffies counter.
Yes, Paul did run into a number of problems that turned out to
be due to the jiffies counter no longer counting. Why do you ask?
o "nfqs" is the number of calls to force_quiescent_state() since
boot.
o "nfqsng" is the number of useless calls to force_quiescent_state(),
where there wasn't actually a grace period active. This can
happen due to races. The number in parentheses is the difference
between "nfqs" and "nfqsng", or the number of times that
force_quiescent_state() actually did some real work.
o "fqlh" is the number of calls to force_quiescent_state() that
exited immediately (without even being counted in nfqs above)
due to contention on ->fqslock.
o Each element of the form "1/1 0:127 ^0" represents one struct
rcu_node. Each line represents one level of the hierarchy, from
root to leaves. It is best to think of the rcu_data structures
as forming yet another level after the leaves. Note that there
might be either one, two, or three levels of rcu_node structures,
depending on the relationship between CONFIG_RCU_FANOUT and
CONFIG_NR_CPUS.
o The numbers separated by the "/" are the qsmask followed
by the qsmaskinit. The qsmask will have one bit
set for each entity in the next lower level that
has not yet checked in for the current grace period.
The qsmaskinit will have one bit for each entity that is
currently expected to check in during each grace period.
The value of qsmaskinit is assigned to that of qsmask
at the beginning of each grace period.
For example, for "rcu", the qsmask of the first entry
of the lowest level is 0x14, meaning that we are still
waiting for CPUs 2 and 4 to check in for the current
grace period.
o The numbers separated by the ":" are the range of CPUs
served by this struct rcu_node. This can be helpful
in working out how the hierarchy is wired together.
For example, the first entry at the lowest level shows
"0:5", indicating that it covers CPUs 0 through 5.
o The number after the "^" indicates the bit in the
next higher level rcu_node structure that this
rcu_node structure corresponds to.
For example, the first entry at the lowest level shows
"^0", indicating that it corresponds to bit zero in
the first entry at the middle level.

4
arch/powerpc/platforms/pseries/rtasd.c
View File

@ -208,6 +208,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
break;
case ERR_TYPE_KERNEL_PANIC:
default:
WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
spin_unlock_irqrestore(&rtasd_log_lock, s);
return;
}
@ -227,6 +228,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
/* Check to see if we need to or have stopped logging */
if (fatal || !logging_enabled) {
logging_enabled = 0;
WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
spin_unlock_irqrestore(&rtasd_log_lock, s);
return;
}
@ -249,11 +251,13 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
else
rtas_log_start += 1;
WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
spin_unlock_irqrestore(&rtasd_log_lock, s);
wake_up_interruptible(&rtas_log_wait);
break;
case ERR_TYPE_KERNEL_PANIC:
default:
WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
spin_unlock_irqrestore(&rtasd_log_lock, s);
return;
}

14
include/linux/hardirq.h
View File

@ -118,13 +118,17 @@ static inline void account_system_vtime(struct task_struct *tsk)
}
#endif
#if defined(CONFIG_PREEMPT_RCU) && defined(CONFIG_NO_HZ)
#if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU)
extern void rcu_irq_enter(void);
extern void rcu_irq_exit(void);
extern void rcu_nmi_enter(void);
extern void rcu_nmi_exit(void);
#else
# define rcu_irq_enter() do { } while (0)
# define rcu_irq_exit() do { } while (0)
#endif /* CONFIG_PREEMPT_RCU */
# define rcu_nmi_enter() do { } while (0)
# define rcu_nmi_exit() do { } while (0)
#endif /* #if defined(CONFIG_NO_HZ) && !defined(CONFIG_CLASSIC_RCU) */
/*
* It is safe to do non-atomic ops on ->hardirq_context,
@ -134,7 +138,6 @@ extern void rcu_irq_exit(void);
*/
#define __irq_enter() \
do { \
rcu_irq_enter(); \
account_system_vtime(current); \
add_preempt_count(HARDIRQ_OFFSET); \
trace_hardirq_enter(); \
@ -153,7 +156,6 @@ extern void irq_enter(void);
trace_hardirq_exit(); \
account_system_vtime(current); \
sub_preempt_count(HARDIRQ_OFFSET); \
rcu_irq_exit(); \
} while (0)
/*
@ -161,7 +163,7 @@ extern void irq_enter(void);
*/
extern void irq_exit(void);
#define nmi_enter() do { lockdep_off(); __irq_enter(); } while (0)
#define nmi_exit() do { __irq_exit(); lockdep_on(); } while (0)
#define nmi_enter() do { lockdep_off(); rcu_nmi_enter(); __irq_enter(); } while (0)
#define nmi_exit() do { __irq_exit(); rcu_nmi_exit(); lockdep_on(); } while (0)
#endif /* LINUX_HARDIRQ_H */

10
include/linux/rcupdate.h
View File

@ -52,11 +52,15 @@ struct rcu_head {
void (*func)(struct rcu_head *head);
};
#ifdef CONFIG_CLASSIC_RCU
#if defined(CONFIG_CLASSIC_RCU)
#include <linux/rcuclassic.h>
#else /* #ifdef CONFIG_CLASSIC_RCU */
#elif defined(CONFIG_TREE_RCU)
#include <linux/rcutree.h>
#elif defined(CONFIG_PREEMPT_RCU)
#include <linux/rcupreempt.h>
#endif /* #else #ifdef CONFIG_CLASSIC_RCU */
#else
#error "Unknown RCU implementation specified to kernel configuration"
#endif /* #else #if defined(CONFIG_CLASSIC_RCU) */
#define RCU_HEAD_INIT { .next = NULL, .func = NULL }
#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT

329
include/linux/rcutree.h Normal file
View File

@ -0,0 +1,329 @@
/*
* Read-Copy Update mechanism for mutual exclusion (tree-based version)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright IBM Corporation, 2008
*
* Author: Dipankar Sarma <dipankar@in.ibm.com>
* Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical algorithm
*
* Based on the original work by Paul McKenney <paulmck@us.ibm.com>
* and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*/
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/threads.h>
#include <linux/percpu.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
/*
* Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT.
* In theory, it should be possible to add more levels straightforwardly.
* In practice, this has not been tested, so there is probably some
* bug somewhere.
*/
#define MAX_RCU_LVLS 3
#define RCU_FANOUT (CONFIG_RCU_FANOUT)
#define RCU_FANOUT_SQ (RCU_FANOUT * RCU_FANOUT)
#define RCU_FANOUT_CUBE (RCU_FANOUT_SQ * RCU_FANOUT)
#if NR_CPUS <= RCU_FANOUT
# define NUM_RCU_LVLS 1
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (NR_CPUS)
# define NUM_RCU_LVL_2 0
# define NUM_RCU_LVL_3 0
#elif NR_CPUS <= RCU_FANOUT_SQ
# define NUM_RCU_LVLS 2
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT - 1) / RCU_FANOUT)
# define NUM_RCU_LVL_2 (NR_CPUS)
# define NUM_RCU_LVL_3 0
#elif NR_CPUS <= RCU_FANOUT_CUBE
# define NUM_RCU_LVLS 3
# define NUM_RCU_LVL_0 1
# define NUM_RCU_LVL_1 (((NR_CPUS) + RCU_FANOUT_SQ - 1) / RCU_FANOUT_SQ)
# define NUM_RCU_LVL_2 (((NR_CPUS) + (RCU_FANOUT) - 1) / (RCU_FANOUT))
# define NUM_RCU_LVL_3 NR_CPUS
#else
# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
#endif /* #if (NR_CPUS) <= RCU_FANOUT */
#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
/*
* Dynticks per-CPU state.
*/
struct rcu_dynticks {
int dynticks_nesting; /* Track nesting level, sort of. */
int dynticks; /* Even value for dynticks-idle, else odd. */
int dynticks_nmi; /* Even value for either dynticks-idle or */
/* not in nmi handler, else odd. So this */
/* remains even for nmi from irq handler. */
};
/*
* Definition for node within the RCU grace-period-detection hierarchy.
*/
struct rcu_node {
spinlock_t lock;
unsigned long qsmask; /* CPUs or groups that need to switch in */
/* order for current grace period to proceed.*/
unsigned long qsmaskinit;
/* Per-GP initialization for qsmask. */
unsigned long grpmask; /* Mask to apply to parent qsmask. */
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. */
u8 level; /* root is at level 0. */
struct rcu_node *parent;
} ____cacheline_internodealigned_in_smp;
/* Index values for nxttail array in struct rcu_data. */
#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
#define RCU_NEXT_TAIL 3
#define RCU_NEXT_SIZE 4
/* Per-CPU data for read-copy update. */
struct rcu_data {
/* 1) quiescent-state and grace-period handling : */
long completed; /* Track rsp->completed gp number */
/* in order to detect GP end. */
long gpnum; /* Highest gp number that this CPU */
/* is aware of having started. */
long passed_quiesc_completed;
/* Value of completed at time of qs. */
bool passed_quiesc; /* User-mode/idle loop etc. */
bool qs_pending; /* Core waits for quiesc state. */
bool beenonline; /* CPU online at least once. */
struct rcu_node *mynode; /* This CPU's leaf of hierarchy */
unsigned long grpmask; /* Mask to apply to leaf qsmask. */
/* 2) batch handling */
/*
* If nxtlist is not NULL, it is partitioned as follows.
* Any of the partitions might be empty, in which case the
* pointer to that partition will be equal to the pointer for
* the following partition. When the list is empty, all of
* the nxttail elements point to nxtlist, which is NULL.
*
* [*nxttail[RCU_NEXT_READY_TAIL], NULL = *nxttail[RCU_NEXT_TAIL]):
* Entries that might have arrived after current GP ended
* [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
* Entries known to have arrived before current GP ended
* [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
* Entries that batch # <= ->completed - 1: waiting for current GP
* [nxtlist, *nxttail[RCU_DONE_TAIL]):
* Entries that batch # <= ->completed
* The grace period for these entries has completed, and
* the other grace-period-completed entries may be moved
* here temporarily in rcu_process_callbacks().
*/
struct rcu_head *nxtlist;
struct rcu_head **nxttail[RCU_NEXT_SIZE];
long qlen; /* # of queued callbacks */
long blimit; /* Upper limit on a processed batch */
#ifdef CONFIG_NO_HZ
/* 3) dynticks interface. */
struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */
int dynticks_snap; /* Per-GP tracking for dynticks. */
int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */
#endif /* #ifdef CONFIG_NO_HZ */
/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
#ifdef CONFIG_NO_HZ
unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */
#endif /* #ifdef CONFIG_NO_HZ */
unsigned long offline_fqs; /* Kicked due to being offline. */
unsigned long resched_ipi; /* Sent a resched IPI. */
/* 5) state to allow this CPU to force_quiescent_state on others */
long n_rcu_pending; /* rcu_pending() calls since boot. */
long n_rcu_pending_force_qs; /* when to force quiescent states. */
int cpu;
};
/* Values for signaled field in struct rcu_state. */
#define RCU_GP_INIT 0 /* Grace period being initialized. */
#define RCU_SAVE_DYNTICK 1 /* Need to scan dyntick state. */
#define RCU_FORCE_QS 2 /* Need to force quiescent state. */
#ifdef CONFIG_NO_HZ
#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK
#else /* #ifdef CONFIG_NO_HZ */
#define RCU_SIGNAL_INIT RCU_FORCE_QS
#endif /* #else #ifdef CONFIG_NO_HZ */
#define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
#define RCU_SECONDS_TILL_STALL_CHECK (10 * HZ) /* for rsp->jiffies_stall */
#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ) /* for rsp->jiffies_stall */
#define RCU_STALL_RAT_DELAY 2 /* Allow other CPUs time */
/* to take at least one */
/* scheduling clock irq */
/* before ratting on them. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
/*
* RCU global state, including node hierarchy. This hierarchy is
* represented in "heap" form in a dense array. The root (first level)
* of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
* level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
* and the third level in ->node[m+1] and following (->node[m+1] referenced
* by ->level[2]). The number of levels is determined by the number of
* CPUs and by CONFIG_RCU_FANOUT. Small systems will have a "hierarchy"
* consisting of a single rcu_node.
*/
struct rcu_state {
struct rcu_node node[NUM_RCU_NODES]; /* Hierarchy. */
struct rcu_node *level[NUM_RCU_LVLS]; /* Hierarchy levels. */
u32 levelcnt[MAX_RCU_LVLS + 1]; /* # nodes in each level. */
u8 levelspread[NUM_RCU_LVLS]; /* kids/node in each level. */
struct rcu_data *rda[NR_CPUS]; /* array of rdp pointers. */
/* The following fields are guarded by the root rcu_node's lock. */
u8 signaled ____cacheline_internodealigned_in_smp;
/* Force QS state. */
long gpnum; /* Current gp number. */
long completed; /* # of last completed gp. */
spinlock_t onofflock; /* exclude on/offline and */
/* starting new GP. */
spinlock_t fqslock; /* Only one task forcing */
/* quiescent states. */
unsigned long jiffies_force_qs; /* Time at which to invoke */
/* force_quiescent_state(). */
unsigned long n_force_qs; /* Number of calls to */
/* force_quiescent_state(). */
unsigned long n_force_qs_lh; /* ~Number of calls leaving */
/* due to lock unavailable. */
unsigned long n_force_qs_ngp; /* Number of calls leaving */
/* due to no GP active. */
#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
unsigned long gp_start; /* Time at which GP started, */
/* but in jiffies. */
unsigned long jiffies_stall; /* Time at which to check */
/* for CPU stalls. */
#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
#ifdef CONFIG_NO_HZ
long dynticks_completed; /* Value of completed @ snap. */
#endif /* #ifdef CONFIG_NO_HZ */
};
extern struct rcu_state rcu_state;
DECLARE_PER_CPU(struct rcu_data, rcu_data);
extern struct rcu_state rcu_bh_state;
DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
/*
* Increment the quiescent state counter.
* The counter is a bit degenerated: 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. Thus just a flag.
*/
static inline void rcu_qsctr_inc(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
rdp->passed_quiesc = 1;
rdp->passed_quiesc_completed = rdp->completed;
}
static inline void rcu_bh_qsctr_inc(int cpu)
{
struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
rdp->passed_quiesc = 1;
rdp->passed_quiesc_completed = rdp->completed;
}
extern int rcu_pending(int cpu);
extern int rcu_needs_cpu(int cpu);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern struct lockdep_map rcu_lock_map;
# define rcu_read_acquire() \
lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_)
# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_)
#else
# define rcu_read_acquire() do { } while (0)
# define rcu_read_release() do { } while (0)
#endif
static inline void __rcu_read_lock(void)
{
preempt_disable();
__acquire(RCU);
rcu_read_acquire();
}
static inline void __rcu_read_unlock(void)
{
rcu_read_release();
__release(RCU);
preempt_enable();
}
static inline void __rcu_read_lock_bh(void)
{
local_bh_disable();
__acquire(RCU_BH);
rcu_read_acquire();
}
static inline void __rcu_read_unlock_bh(void)
{
rcu_read_release();
__release(RCU_BH);
local_bh_enable();
}
#define __synchronize_sched() synchronize_rcu()
#define call_rcu_sched(head, func) call_rcu(head, func)
static inline void rcu_init_sched(void)
{
}
extern void __rcu_init(void);
extern void rcu_check_callbacks(int cpu, int user);
extern void rcu_restart_cpu(int cpu);
extern long rcu_batches_completed(void);
extern long rcu_batches_completed_bh(void);
#ifdef CONFIG_NO_HZ
void rcu_enter_nohz(void);
void rcu_exit_nohz(void);
#else /* CONFIG_NO_HZ */
static inline void rcu_enter_nohz(void)
{
}
static inline void rcu_exit_nohz(void)
{
}
#endif /* CONFIG_NO_HZ */
#endif /* __LINUX_RCUTREE_H */

18
init/Kconfig
View File

@ -928,10 +928,16 @@ source "block/Kconfig"
config PREEMPT_NOTIFIERS
bool
config CLASSIC_RCU
def_bool !PREEMPT_RCU
config TREE_RCU_TRACE
def_bool RCU_TRACE && TREE_RCU
select DEBUG_FS
help
This option selects the classic RCU implementation that is
designed for best read-side performance on non-realtime
systems. Classic RCU is the default. Note that the
PREEMPT_RCU symbol is used to select/deselect this option.
This option provides tracing for the TREE_RCU implementation,
permitting Makefile to trivially select kernel/rcutree_trace.c.
config PREEMPT_RCU_TRACE
def_bool RCU_TRACE && PREEMPT_RCU
select DEBUG_FS
help
This option provides tracing for the PREEMPT_RCU implementation,
permitting Makefile to trivially select kernel/rcupreempt_trace.c.

62
kernel/Kconfig.preempt
View File

@ -52,10 +52,29 @@ config PREEMPT
endchoice
choice
prompt "RCU Implementation"
default CLASSIC_RCU
config CLASSIC_RCU
bool "Classic RCU"
help
This option selects the classic RCU implementation that is
designed for best read-side performance on non-realtime
systems.
Select this option if you are unsure.
config TREE_RCU
bool "Tree-based hierarchical RCU"
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
thousands of CPUs.
config PREEMPT_RCU
bool "Preemptible RCU"
depends on PREEMPT
default n
help
This option reduces the latency of the kernel by making certain
RCU sections preemptible. Normally RCU code is non-preemptible, if
@ -64,16 +83,47 @@ config PREEMPT_RCU
now-naive assumptions about each RCU read-side critical section
remaining on a given CPU through its execution.
Say N if you are unsure.
endchoice
config RCU_TRACE
bool "Enable tracing for RCU - currently stats in debugfs"
depends on PREEMPT_RCU
select DEBUG_FS
default y
bool "Enable tracing for RCU"
depends on TREE_RCU || PREEMPT_RCU
help
This option provides tracing in RCU which presents stats
in debugfs for debugging RCU implementation.
Say Y here if you want to enable RCU tracing
Say N if you are unsure.
config RCU_FANOUT
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
depends on TREE_RCU
default 64 if 64BIT
default 32 if !64BIT
help
This option controls the fanout of hierarchical implementations
of RCU, allowing RCU to work efficiently on machines with
large numbers of CPUs. This value must be at least the cube
root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
systems and up to 262,144 for 64-bit systems.
Select a specific number if testing RCU itself.
Take the default if unsure.
config RCU_FANOUT_EXACT
bool "Disable tree-based hierarchical RCU auto-balancing"
depends on TREE_RCU
default n
help
This option forces use of the exact RCU_FANOUT value specified,
regardless of imbalances in the hierarchy. This is useful for
testing RCU itself, and might one day be useful on systems with
strong NUMA behavior.
Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
Say n if unsure.

6
kernel/Makefile
View File

@ -74,10 +74,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
obj-$(CONFIG_TREE_RCU) += rcutree.o
obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
ifeq ($(CONFIG_PREEMPT_RCU),y)
obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o
endif
obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
obj-$(CONFIG_RELAY) += relay.o
obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o

10
kernel/rcupreempt.c
View File

@ -551,6 +551,16 @@ void rcu_irq_exit(void)
}
}
void rcu_nmi_enter(void)
{
rcu_irq_enter();
}
void rcu_nmi_exit(void)
{
rcu_irq_exit();
}
static void dyntick_save_progress_counter(int cpu)
{
struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);

10
kernel/rcupreempt_trace.c
View File

@ -149,12 +149,12 @@ static void rcupreempt_trace_sum(struct rcupreempt_trace *sp)
sp->done_length += cp->done_length;
sp->done_add += cp->done_add;
sp->done_remove += cp->done_remove;
atomic_set(&sp->done_invoked, atomic_read(&cp->done_invoked));
atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked);
sp->rcu_check_callbacks += cp->rcu_check_callbacks;
atomic_set(&sp->rcu_try_flip_1,
atomic_read(&cp->rcu_try_flip_1));
atomic_set(&sp->rcu_try_flip_e1,
atomic_read(&cp->rcu_try_flip_e1));
atomic_add(atomic_read(&cp->rcu_try_flip_1),
&sp->rcu_try_flip_1);
atomic_add(atomic_read(&cp->rcu_try_flip_e1),
&sp->rcu_try_flip_e1);
sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1;
sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1;
sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1;

1535
kernel/rcutree.c Normal file
View File

File diff suppressed because it is too large Load Diff

271
kernel/rcutree_trace.c Normal file
View File

@ -0,0 +1,271 @@
/*
* Read-Copy Update tracing for classic implementation
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright IBM Corporation, 2008
*
* Papers: http://www.rdrop.com/users/paulmck/RCU
*
* For detailed explanation of Read-Copy Update mechanism see -
* Documentation/RCU
*
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/smp.h>
#include <linux/rcupdate.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <asm/atomic.h>
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/completion.h>
#include <linux/moduleparam.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
{
if (!rdp->beenonline)
return;
seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x",
rdp->cpu,
cpu_is_offline(rdp->cpu) ? '!' : ' ',
rdp->completed, rdp->gpnum,
rdp->passed_quiesc, rdp->passed_quiesc_completed,
rdp->qs_pending,
rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
(int)(rdp->n_rcu_pending & 0xffff));
#ifdef CONFIG_NO_HZ
seq_printf(m, " dt=%d/%d dn=%d df=%lu",
rdp->dynticks->dynticks,
rdp->dynticks->dynticks_nesting,
rdp->dynticks->dynticks_nmi,
rdp->dynticks_fqs);
#endif /* #ifdef CONFIG_NO_HZ */
seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit);
}
#define PRINT_RCU_DATA(name, func, m) \
do { \
int _p_r_d_i; \
\
for_each_possible_cpu(_p_r_d_i) \
func(m, &per_cpu(name, _p_r_d_i)); \
} while (0)
static int show_rcudata(struct seq_file *m, void *unused)
{
seq_puts(m, "rcu:\n");
PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m);
seq_puts(m, "rcu_bh:\n");
PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m);
return 0;
}
static int rcudata_open(struct inode *inode, struct file *file)
{
return single_open(file, show_rcudata, NULL);
}
static struct file_operations rcudata_fops = {
.owner = THIS_MODULE,
.open = rcudata_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
{
if (!rdp->beenonline)
return;
seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld",
rdp->cpu,
cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
rdp->completed, rdp->gpnum,
rdp->passed_quiesc, rdp->passed_quiesc_completed,
rdp->qs_pending,
rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
rdp->n_rcu_pending);
#ifdef CONFIG_NO_HZ
seq_printf(m, ",%d,%d,%d,%lu",
rdp->dynticks->dynticks,
rdp->dynticks->dynticks_nesting,
rdp->dynticks->dynticks_nmi,
rdp->dynticks_fqs);
#endif /* #ifdef CONFIG_NO_HZ */
seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit);
}
static int show_rcudata_csv(struct seq_file *m, void *unused)
{
seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\",");
#ifdef CONFIG_NO_HZ
seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
#endif /* #ifdef CONFIG_NO_HZ */
seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
seq_puts(m, "\"rcu:\"\n");
PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m);
seq_puts(m, "\"rcu_bh:\"\n");
PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m);
return 0;
}
static int rcudata_csv_open(struct inode *inode, struct file *file)
{
return single_open(file, show_rcudata_csv, NULL);
}
static struct file_operations rcudata_csv_fops = {
.owner = THIS_MODULE,
.open = rcudata_csv_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
{
int level = 0;
struct rcu_node *rnp;
seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
"nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
rsp->completed, rsp->gpnum, rsp->signaled,
(long)(rsp->jiffies_force_qs - jiffies),
(int)(jiffies & 0xffff),
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
rsp->n_force_qs_lh);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
level = rnp->level;
}
seq_printf(m, "%lx/%lx %d:%d ^%d ",
rnp->qsmask, rnp->qsmaskinit,
rnp->grplo, rnp->grphi, rnp->grpnum);
}
seq_puts(m, "\n");
}
static int show_rcuhier(struct seq_file *m, void *unused)
{
seq_puts(m, "rcu:\n");
print_one_rcu_state(m, &rcu_state);
seq_puts(m, "rcu_bh:\n");
print_one_rcu_state(m, &rcu_bh_state);
return 0;
}
static int rcuhier_open(struct inode *inode, struct file *file)
{
return single_open(file, show_rcuhier, NULL);
}
static struct file_operations rcuhier_fops = {
.owner = THIS_MODULE,
.open = rcuhier_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int show_rcugp(struct seq_file *m, void *unused)
{
seq_printf(m, "rcu: completed=%ld gpnum=%ld\n",
rcu_state.completed, rcu_state.gpnum);
seq_printf(m, "rcu_bh: completed=%ld gpnum=%ld\n",
rcu_bh_state.completed, rcu_bh_state.gpnum);
return 0;
}
static int rcugp_open(struct inode *inode, struct file *file)
{
return single_open(file, show_rcugp, NULL);
}
static struct file_operations rcugp_fops = {
.owner = THIS_MODULE,
.open = rcugp_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
static int __init rcuclassic_trace_init(void)
{
rcudir = debugfs_create_dir("rcu", NULL);
if (!rcudir)
goto out;
datadir = debugfs_create_file("rcudata", 0444, rcudir,
NULL, &rcudata_fops);
if (!datadir)
goto free_out;
datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir,
NULL, &rcudata_csv_fops);
if (!datadir_csv)
goto free_out;
gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
if (!gpdir)
goto free_out;
hierdir = debugfs_create_file("rcuhier", 0444, rcudir,
NULL, &rcuhier_fops);
if (!hierdir)
goto free_out;
return 0;
free_out:
if (datadir)
debugfs_remove(datadir);
if (datadir_csv)
debugfs_remove(datadir_csv);
if (gpdir)
debugfs_remove(gpdir);
debugfs_remove(rcudir);
out:
return 1;
}
static void __exit rcuclassic_trace_cleanup(void)
{
debugfs_remove(datadir);
debugfs_remove(datadir_csv);
debugfs_remove(gpdir);
debugfs_remove(hierdir);
debugfs_remove(rcudir);
}
module_init(rcuclassic_trace_init);
module_exit(rcuclassic_trace_cleanup);
MODULE_AUTHOR("Paul E. McKenney");
MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
MODULE_LICENSE("GPL");

5
kernel/softirq.c
View File

@ -269,6 +269,7 @@ void irq_enter(void)
{
int cpu = smp_processor_id();
rcu_irq_enter();
if (idle_cpu(cpu) && !in_interrupt()) {
__irq_enter();
tick_check_idle(cpu);
@ -295,9 +296,9 @@ void irq_exit(void)
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
tick_nohz_stop_sched_tick(0);
rcu_irq_exit();
if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
tick_nohz_stop_sched_tick(0);
#endif
preempt_enable_no_resched();
}

13
lib/Kconfig.debug
View File

@ -619,6 +619,19 @@ config RCU_CPU_STALL_DETECTOR
Say N if you are unsure.
config RCU_CPU_STALL_DETECTOR
bool "Check for stalled CPUs delaying RCU grace periods"
depends on CLASSIC_RCU || TREE_RCU
default n
help
This option causes RCU to printk information on which
CPUs are delaying the current grace period, but only when
the grace period extends for excessive time periods.
Say Y if you want RCU to perform such checks.
Say N if you are unsure.
config KPROBES_SANITY_TEST
bool "Kprobes sanity tests"
depends on DEBUG_KERNEL