Fix cpu masks for 'topology=off' case. Folding of the scheduling domains
happen in such a way that everything belongs to the MC domain instead
of the CPU doimain.
This should fix a performance regression introduced with
eafd2b6d "[S390] topology: use default MC domain initializer" and also
makes sure we have the same behavious as if CONFIG_SCHED_MC was not
selected at all.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Export the cpu configuration topology via sysinfo. Two new lines are
introduced:
CPU Topology HW: 0 0 0 4 6 4
CPU Topology SW: 0 0 0 0 4 24
The HW line describes the cpu topology nesting levels when the maximum
nesting level is used to get the corresponding SYSIB.
The SW line describes what Linux is actually using. In this case it
supports only two levels (CONFIG_SCHED_BOOK off) and therefore the
hardware folded the two lower levels in the SYSIB response block.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Move the topology sysinfo SYSIB definitions to the proper place in
asm/sysinfo.h where they should be.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Move cpu topology facility detection to early setup code where it
should be.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Store the facility list once at system startup with stfl/stfle and
reuse the result for all facility tests.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Switch default value of the kernel parameter 'topology' from off to on.
Various performance measurements have finally shown that there are no
(known) regressions anywhere.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Use the extended cpu topology information that z11 machines provide
to improve the scheduler's decision making.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100831082844.604956770@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Provide a topology_core_id define which makes sure that the contents of
/sys/devices/system/cpu/cpuX/topology/core_id
indeed do contain the core id and not always 0.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
In the default case the lock is not unlocked. The return is
converted to a goto, to share the unlock at the end of the function.
A simplified version of the semantic patch that finds this problem is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@r exists@
expression E1;
identifier f;
@@
f (...) { <+...
* spin_lock_irq (E1,...);
... when != E1
* return ...;
...+> }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Finally move it to the place where it belongs to and make get rid of
it for !CONFIG_SMP.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Impact: cleanup
cpu_coregroup_mask is the New Hotness.
As S/390 uses theirs internally, so we just make it static.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Like cpu_coregroup_map, but returns a (const) pointer.
Compile-tested on s390 (defconfig).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Interrupts haven't been implemented. So remove the dead code.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Introduce a topology=[on|off] kernel parameter which allows to switch
cpu topology on/off. Default will be off, since it looks like that for
some workloards this doesn't behave very well (on s390).
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Call rebuild_sched_domains instead of arch_reinit_sched_domains if
cpu topology changes. This leaves cpu sets alone which otherwise would
be destroyed.
If and how it makes sense to define cpu sets on a virtualized
architecture is another question.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Common code doesn't call arch_update_cpu_topology() anymore on
cpu hotplug. But our architecture backend relied on that in order to
update the cpu_core_map. For machines without cpu topology support
this leads uninitialized cpu_core_maps for later on added cpus.
To solve this just initialize the maps with cpu_possible_map, since
that will be always valid for machines without topology support.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Change arch_update_cpu_topology so it returns 1 if the cpu topology changed
and 0 if it didn't change. This will be useful for the next patch which adds
a call to this function in partition_sched_domains.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
cpu_coregroup_map used to grab a mutex on s390 since it was only
called from process context.
Since c7c22e4d5c "block: add support
for IO CPU affinity" this is not true anymore.
It now also gets called from softirq context.
To prevent possible deadlocks change this in architecture code and
use a spinlock instead of a mutex.
Cc: stable@kernel.org
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Now that it is safe to use get_online_cpus() we can revert
[S390] cpu topology: Fix possible deadlock.
commit: fd781fa25c
and call arch_reinit_sched_domains() directly from topology_work_fn().
Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Gautham R Shenoy <ego@in.ibm.com>
Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
As noted by Akinobu Mita in patch b1fceac2b9,
alloc_bootmem and related functions never return NULL and always return a
zeroed region of memory. Thus a NULL test or memset after calls to these
functions is unnecessary.
arch/s390/kernel/topology.c | 2 --
1 file changed, 2 deletions(-)
This was fixed using the following semantic patch.
(http://www.emn.fr/x-info/coccinelle/)
// <smpl>
@@
expression E;
statement S;
@@
E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\)(...)
... when != E
(
- BUG_ON (E == NULL);
|
- if (E == NULL) S
)
@@
expression E,E1;
@@
E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\)(...)
... when != E
- memset(E,0,E1);
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
When we get a notification that cpu topology changed, we schedule a
work struct which just calls arch_reinit_sched_domains. This function
in turn calls get_online_cpus() which results int the lockdep warning
below.
After all it turnded out that it's not legal to call get_online_cpus()
from the context of a multi-threaded work queue.
It could deadlock this way:
process 0 (events/cpu-x):
-> run_workqueue
-> removes my work_struct from the work queue
-> calls work_struct->fn
-> get_online_cpus()
-> locks on cpu_hotplug.lock since process 1 below is doing cpu hotplug
process 1:
-> cpu_down (for cpu-x)
-> cpu_hotplug_begin (holds cpu_hotplug.lock now)
-> cpu-x dead
-> notifier_call_chain with CPU_DEAD
-> cleanup_workqueue_thread
-> flush_cpu_workqueue (succeeds)
-> kthread_stop for events/cpu-x
-> now kthread_stop waits for my work_struct to complete from within
process 0. -> dead.
A single threaded workqueue wouldn't have such problems, however there is
no such common queue available and it's not worth to create one for the
very rare calls to arch_reinit_sched_domains.
So we just create a kernel thread from our work struct which calls
arch_reinit_sched_domains and are done with it.
Thanks to Oleg Nesterov and Peter Zijlstra for helping me figuring out
that this isn't a false positive lockdep warning:
=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.25-03562-g3dc5063-dirty #12
-------------------------------------------------------
events/3/14 is trying to acquire lock:
(&cpu_hotplug.lock){--..}, at: [<0000000000076094>] get_online_cpus+0x50/0x78
but task is already holding lock:
(topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (topology_work){--..}:
[<000000000006fc74>] __lock_acquire+0x1010/0x111c
[<000000000006fe40>] lock_acquire+0xc0/0xf8
[<0000000000059d48>] run_workqueue+0x170/0x278
[<0000000000059edc>] worker_thread+0x8c/0xf0
[<000000000005f5bc>] kthread+0x68/0xa0
[<000000000001a33e>] kernel_thread_starter+0x6/0xc
[<000000000001a338>] kernel_thread_starter+0x0/0xc
-> #1 (events){--..}:
[<000000000006fc74>] __lock_acquire+0x1010/0x111c
[<000000000006fe40>] lock_acquire+0xc0/0xf8
[<000000000005a23c>] cleanup_workqueue_thread+0x60/0xa8
[<00000000003b2ab8>] workqueue_cpu_callback+0xbc/0x170
[<00000000003bba80>] notifier_call_chain+0x5c/0xa4
[<00000000000655a2>] __raw_notifier_call_chain+0x26/0x38
[<00000000000655e2>] raw_notifier_call_chain+0x2e/0x40
[<0000000000075e00>] cpu_down+0x228/0x31c
[<00000000003b1dd8>] store_online+0x64/0xb8
[<00000000001e7128>] sysdev_store+0x48/0x58
[<0000000000121cd2>] sysfs_write_file+0x126/0x1c0
[<00000000000c1944>] vfs_write+0xb0/0x15c
[<00000000000c20e6>] sys_write+0x56/0x88
[<0000000000027a68>] sys32_write+0x34/0x4c
[<0000000000023f70>] sysc_noemu+0x10/0x16
[<0000000077f3f186>] 0x77f3f186
-> #0 (&cpu_hotplug.lock){--..}:
[<000000000006fa84>] __lock_acquire+0xe20/0x111c
[<000000000006fe40>] lock_acquire+0xc0/0xf8
[<00000000003b701c>] mutex_lock_nested+0xd0/0x364
[<0000000000076094>] get_online_cpus+0x50/0x78
[<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58
[<000000000002700e>] topology_work_fn+0x26/0x34
[<0000000000059d4e>] run_workqueue+0x176/0x278
[<0000000000059edc>] worker_thread+0x8c/0xf0
[<000000000005f5bc>] kthread+0x68/0xa0
[<000000000001a33e>] kernel_thread_starter+0x6/0xc
[<000000000001a338>] kernel_thread_starter+0x0/0xc
other info that might help us debug this:
2 locks held by events/3/14:
#0: (events){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278
#1: (topology_work){--..}, at: [<0000000000059cde>] run_workqueue+0x106/0x278
stack backtrace:
CPU: 3 Not tainted 2.6.25-03562-g3dc5063-dirty #12
Process events/3 (pid: 14, task: 000000002fb04038, ksp: 000000002fb0bd70)
0400000000000000 000000002fb0ba40 0000000000000002 0000000000000000
000000002fb0bae0 000000002fb0ba58 000000002fb0ba58 0000000000016488
0000000000000000 000000002fb0bd70 0000000000000000 0000000000000000
000000002fb0ba40 000000000000000c 000000002fb0ba40 000000002fb0bab0
00000000003c99e0 0000000000016488 000000002fb0ba40 000000002fb0ba90
Call Trace:
([<00000000000163fc>] show_trace+0x138/0x158)
[<00000000000164e2>] show_stack+0xc6/0xf8
[<0000000000016624>] dump_stack+0xb0/0xc0
[<000000000006cd36>] print_circular_bug_tail+0xa2/0xb4
[<000000000006fa84>] __lock_acquire+0xe20/0x111c
[<000000000006fe40>] lock_acquire+0xc0/0xf8
[<00000000003b701c>] mutex_lock_nested+0xd0/0x364
[<0000000000076094>] get_online_cpus+0x50/0x78
[<000000000003a03e>] arch_reinit_sched_domains+0x26/0x58
[<000000000002700e>] topology_work_fn+0x26/0x34
[<0000000000059d4e>] run_workqueue+0x176/0x278
[<0000000000059edc>] worker_thread+0x8c/0xf0
[<000000000005f5bc>] kthread+0x68/0xa0
[<000000000001a33e>] kernel_thread_starter+0x6/0xc
[<000000000001a338>] kernel_thread_starter+0x0/0xc
INFO: lockdep is turned off.
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
If vertical cpu polarization is active then the hypervisor will
dispatch certain cpus for a longer time than other cpus for maximum
performance. For example if a guest would have three virtual cpus,
each of them with a share of 33 percent, then in case of vertical
cpu polarization all of the processing time would be combined to a
single cpu which would run all the time, while the other two cpus
would get nearly no cpu time.
There are three different types of vertical cpus: high, medium and
low. Low cpus hardly get any real cpu time, while high cpus get a
full real cpu. Medium cpus get something in between.
In order to switch between the two possible modes (default is
horizontal) a 0 for horizontal polarization or a 1 for vertical
polarization must be written to the dispatching sysfs attribute:
/sys/devices/system/cpu/dispatching
The polarization of each single cpu can be figured out by the
polarization sysfs attribute of each cpu:
/sys/devices/system/cpu/cpuX/polarization
horizontal, vertical:high, vertical:medium, vertical:low or unknown.
When switching polarization the polarization attribute may contain
the value unknown until the configuration change is done and the
kernel has figured out the new polarization of each cpu.
Note that running a system with different types of vertical cpus may
result in significant performance regressions. If possible only one
type of vertical cpus should be used. All other cpus should be
offlined.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Add s390 backend so we can give the scheduler some hints about the
cpu topology.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Heiko Carstens
Martin Schwidefsky
Julia Lawall
Rusty Russell
Linus Torvalds
Oleg Nesterov