Commit Graph

93 Commits

Author SHA1 Message Date
Heiko Carstens
88e012856d [S390] smp: fix cpu_possible_map initialization
The cpu_possible_map by default is initialized with all ones in s390.
If the kernel paramert possible_cpus=<x> is passed the cpu_possible_map
is supposed to have x bits set.
However the current code just sets the x bits without clearing the NR_CPUS
bits that were already set. So we end up with an unchanged map that has
all bits set.
To fix this just clear the map before setting any new bits.

This broke with def6cfb70b
"[S390] cpumask: Use accessors code."

Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-04-14 15:37:26 +02:00
Christian Ehrhardt
25097bf153 [S390] s390: move machine flags to lowcore
Currently the storage of the machine flags is a globally exported unsigned
long long variable. By moving the storage location into the lowcore struct we
allow assembler code to check machine_flags directly even without needing a
register. Addtionally the lowcore and therefore the machine flags too will be
in cache most of the time.

Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-04-14 15:37:21 +02:00
Rusty Russell
def6cfb70b [S390] cpumask: Use accessors code.
Impact: use new API

Use the accessors rather than frobbing bits directly.  Most of this is
in arch code I haven't even compiled, but is straightforward.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:33 +01:00
Rusty Russell
93632d1bf7 [S390] cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.
Impact: cleanup, futureproof

In fact, all cpumask ops will only be valid (in general) for bit
numbers < nr_cpu_ids.  So use that instead of NR_CPUS in various
places (I also updated the immediate sites to use the new cpumask_
operators).

This is always safe: no cpu number can be >= nr_cpu_ids, and
nr_cpu_ids is initialized to NR_CPUS at boot.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:33 +01:00
Heiko Carstens
d0d3cdf4c2 [S390] smp: perform initial cpu reset before starting a cpu
Performing an initial cpu reset makes sure all registers and tlbs of
the targeted cpu are initialized and flushed.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:30 +01:00
Heiko Carstens
6d54c5a3fb [S390] smp: fix memory leak on __cpu_up
If sigp_set_prefix fails on __cpu_up we leak the lowcore structures
and async+panic stacks for the failed cpu.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:30 +01:00
Michael Holzheu
59f2e69d0f [S390] zfcpdump: Prevent zcore from beeing built as a kernel module.
The zcore code switches to real addressing mode when creating a kernel dump.
This is not possible, if it is built as a kernel module. With this patch
zcore (zfcpdump) can't be built as a kernel module any more.

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:28 +01:00
Martin Schwidefsky
da292bbe1f [S390] eliminate ipl_device from lowcore
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:27 +01:00
Martin Schwidefsky
7b4684880d [S390] eliminate cpuinfo_S390 structure
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:26 +01:00
Christian Borntraeger
3324e60aaf [S390] lockdep: trace hardirq off in smp_send_stop
With lockdep we got the following trace after a panic:

Badness at /home/autobuild/BUILD/linux-2.6.28-20090204/kernel/lockdep.c:2878
[...]
Call Trace:
 [<0000000000176334>] lock_acquire+0x54/0xbc
 [<000000000050b4fe>] __atomic_notifier_call_chain+0x6e/0xdc
 [<000000000050b59c>] atomic_notifier_call_chain+0x30/0x44
 [<0000000000504274>] panic+0xd0/0x1e8
[...]
INFO: lockdep is turned off.
Last Breaking-Event-Address:
 [<0000000000170e62>] check_flags+0xae/0x15c
possible reason: unannotated irqs-off.

lockdep is right. We missed a trace_hardirq_off in our smp_send_stop
function and smp_send_stop is called before the panic call chain.

Reported-by: Mijo <Safradin mijo@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-03-26 15:24:08 +01:00
Frank Munzert
099b765139 [S390] Automatic IPL after dump
Provide new shutdown action "dump_reipl" for automatic ipl after dump.

Signed-off-by: Frank Munzert <munzert@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2009-03-26 15:24:03 +01:00
Heiko Carstens
81ffa0415b [S390] vdso: compile fix
!CONFIG_SMP:

arch/s390/kernel/vdso.c: In function 'vdso_init':
arch/s390/kernel/vdso.c:325: error: incompatible type for argument 2 of 'vdso_alloc_per_cpu'

Also move the code out of the BUG_ON statement since it won't be
executed on !CONFIG_BUG. And that would be a bug.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2009-01-09 12:15:06 +01:00
Linus Torvalds
61420f59a5 Merge branch 'cputime' of git://git390.osdl.marist.edu/pub/scm/linux-2.6
* 'cputime' of git://git390.osdl.marist.edu/pub/scm/linux-2.6:
  [PATCH] fast vdso implementation for CLOCK_THREAD_CPUTIME_ID
  [PATCH] improve idle cputime accounting
  [PATCH] improve precision of idle time detection.
  [PATCH] improve precision of process accounting.
  [PATCH] idle cputime accounting
  [PATCH] fix scaled & unscaled cputime accounting
2009-01-03 11:56:24 -08:00
Linus Torvalds
b840d79631 Merge branch 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'cpus4096-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (66 commits)
  x86: export vector_used_by_percpu_irq
  x86: use logical apicid in x2apic_cluster's x2apic_cpu_mask_to_apicid_and()
  sched: nominate preferred wakeup cpu, fix
  x86: fix lguest used_vectors breakage, -v2
  x86: fix warning in arch/x86/kernel/io_apic.c
  sched: fix warning in kernel/sched.c
  sched: move test_sd_parent() to an SMP section of sched.h
  sched: add SD_BALANCE_NEWIDLE at MC and CPU level for sched_mc>0
  sched: activate active load balancing in new idle cpus
  sched: bias task wakeups to preferred semi-idle packages
  sched: nominate preferred wakeup cpu
  sched: favour lower logical cpu number for sched_mc balance
  sched: framework for sched_mc/smt_power_savings=N
  sched: convert BALANCE_FOR_xx_POWER to inline functions
  x86: use possible_cpus=NUM to extend the possible cpus allowed
  x86: fix cpu_mask_to_apicid_and to include cpu_online_mask
  x86: update io_apic.c to the new cpumask code
  x86: Introduce topology_core_cpumask()/topology_thread_cpumask()
  x86: xen: use smp_call_function_many()
  x86: use work_on_cpu in x86/kernel/cpu/mcheck/mce_amd_64.c
  ...

Fixed up trivial conflict in kernel/time/tick-sched.c manually
2009-01-02 11:44:09 -08:00
Martin Schwidefsky
c742b31c03 [PATCH] fast vdso implementation for CLOCK_THREAD_CPUTIME_ID
The extract cpu time instruction (ectg) instruction allows the user
process to get the current thread cputime without calling into the
kernel. The code that uses the instruction needs to switch to the
access registers mode to get access to the per-cpu info page that
contains the two base values that are needed to calculate the current
cputime from the CPU timer with the ectg instruction.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-31 15:11:49 +01:00
Martin Schwidefsky
6f43092441 [PATCH] improve precision of idle time detection.
Increase the precision of the idle time calculation that is exported
to user space via /sys/devices/system/cpu/cpu<x>/idle_time_us

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-31 15:11:47 +01:00
Martin Schwidefsky
395d31d40c [S390] convert cpu related printks to pr_xxx macros.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-25 13:39:25 +01:00
Martin Schwidefsky
33b1d09ef3 [S390] panic_stack leak in smp_alloc_lowcore
Fix freeing of the panic_stack if the allocation of async_stack failed.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-25 13:39:16 +01:00
Martin Schwidefsky
c185b783b0 [S390] Remove config options.
On s390 we always want to run with precise cputime accounting.
Remove the config options VIRT_TIMER and VIRT_CPU_ACCOUNTING.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-25 13:39:15 +01:00
Heiko Carstens
ca9fc75a68 [S390] convert s390 to generic IPI infrastructure
Since etr/stp don't need the old smp_call_function semantics anymore
we can convert s390 to the generic IPI infrastructure.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-12-25 13:38:56 +01:00
Rusty Russell
98a79d6a50 cpumask: centralize cpu_online_map and cpu_possible_map
Impact: cleanup

Each SMP arch defines these themselves.  Move them to a central
location.

Twists:
1) Some archs (m32, parisc, s390) set possible_map to all 1, so we add a
   CONFIG_INIT_ALL_POSSIBLE for this rather than break them.

2) mips and sparc32 '#define cpu_possible_map phys_cpu_present_map'.
   Those archs simply have phys_cpu_present_map replaced everywhere.

3) Alpha defined cpu_possible_map to cpu_present_map; this is tricky
   so I just manipulate them both in sync.

4) IA64, cris and m32r have gratuitous 'extern cpumask_t cpu_possible_map'
   declarations.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Reviewed-by: Grant Grundler <grundler@parisc-linux.org>
Tested-by: Tony Luck <tony.luck@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Mike Travis <travis@sgi.com>
Cc: ink@jurassic.park.msu.ru
Cc: rmk@arm.linux.org.uk
Cc: starvik@axis.com
Cc: tony.luck@intel.com
Cc: takata@linux-m32r.org
Cc: ralf@linux-mips.org
Cc: grundler@parisc-linux.org
Cc: paulus@samba.org
Cc: schwidefsky@de.ibm.com
Cc: lethal@linux-sh.org
Cc: wli@holomorphy.com
Cc: davem@davemloft.net
Cc: jdike@addtoit.com
Cc: mingo@redhat.com
2008-12-13 21:19:41 +10:30
Heiko Carstens
da5aae7036 [S390] Fix sysdev class file creation.
Use sysdev_class_create_file() to create create sysdev class attributes
instead of sysfs_create_file(). Using sysfs_create_file() wasn't a very
good idea since the show and store functions have a different amount of
parameters for sysfs files and sysdev class files.
In particular the pointer to the buffer is the last argument and
therefore accesses to random memory regions happened.
Still worked surprisingly well until we got a kernel panic.

Cc: stable@kernel.org
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-10-28 11:12:03 +01:00
Manfred Spraul
e545a6140b kernel/cpu.c: create a CPU_STARTING cpu_chain notifier
Right now, there is no notifier that is called on a new cpu, before the new
cpu begins processing interrupts/softirqs.
Various kernel function would need that notification, e.g. kvm works around
by calling smp_call_function_single(), rcu polls cpu_online_map.

The patch adds a CPU_STARTING notification. It also adds a helper function
that sends the message to all cpu_chain handlers.

Tested on x86-64.
All other archs are untested. Especially on sparc, I'm not sure if I got
it right.

Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-08 19:25:24 +02:00
Heiko Carstens
8853e505a1 [S390] Remove unneeded spinlock initialization.
Remove the now unneeded s390_idle.lock spinlock initialization after
Josef Sipek did it the right way in arch/s390/kernel/process.c.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-08-21 19:46:39 +02:00
Andi Kleen
4a0b2b4dbe sysdev: Pass the attribute to the low level sysdev show/store function
This allow to dynamically generate attributes and share show/store
functions between attributes. Right now most attributes are generated
by special macros and lots of duplicated code. With the attribute
passed it's instead possible to attach some data to the attribute
and then use that in shared low level functions to do different things.

I need this for the dynamically generated bank attributes in the x86
machine check code, but it'll allow some further cleanups.

I converted all users in tree to the new show/store prototype. It's a single
huge patch to avoid unbisectable sections.

Runtime tested: x86-32, x86-64
Compiled only: ia64, powerpc
Not compile tested/only grep converted: sh, arm, avr32

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-07-21 21:55:02 -07:00
Jens Axboe
15c8b6c1aa on_each_cpu(): kill unused 'retry' parameter
It's not even passed on to smp_call_function() anymore, since that
was removed. So kill it.

Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-06-26 11:24:38 +02:00
Jens Axboe
8691e5a8f6 smp_call_function: get rid of the unused nonatomic/retry argument
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.

Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-06-26 11:24:35 +02:00
Segher Boessenkool
24d3e210c1 [S390] Fix build failure in __cpu_up()
The first argument to __ctl_store() should be the array to store
stuff in, not just the first element of that array.  With the
current code in __cpu_up(), mainline GCC dies with an internal
compiler error.  I didn't diagnose that further, but just fixed
the kernel bug.

Signed-off-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-06-10 10:03:28 +02:00
Heiko Carstens
67060d9c1f [S390] Fix section mismatch warnings.
This fixes the last remaining section mismatch warnings in s390
architecture code. It reveals also a real bug introduced by... me
with git commit 2069e978d5
("[S390] sparsemem vmemmap: initialize memmap.")

Calling the generic vmemmap_alloc_block() function to get initialized
memory is a nice idea, however that function is __meminit annotated
and therefore the function might be gone if we try to call it later.
This can happen if a DCSS segment gets added.

So basically revert the patch and clear the memmap explicitly to fix
the original bug.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-05-30 10:03:34 +02:00
Heiko Carstens
85cb185dad [S390] smp: __smp_call_function_map vs cpu_online_map fix.
Both smp_call_function() and __smp_call_function_map() access
cpu_online_map. Both functions run with preemption disabled which
protects for cpus going offline. However new cpus can be added and
therefore the cpu_online_map can change unexpectedly.
So use the call_lock to protect against changes to the cpu_online_map
in start_secondary() and all smp_call_* functions.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-05-15 16:52:40 +02:00
Heiko Carstens
1e489518da [S390] Automatically detect added cpus.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-04-30 13:38:44 +02:00
Heiko Carstens
0b18d318b8 [S390] smp: Fix locking order.
On some smp sysfs store attributes get_online_cpus() may block on
cpu_hotplug.lock, but we hold already smp_cpu_state_mutex. Since the
locking order on cpu hotplug via arch_update_cpu_topology is inverse
this might lead to deadlocks.
So make sure locking order is always the same.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-04-30 13:38:44 +02:00
Heiko Carstens
a806170e29 [S390] Fix a lot of sparse warnings.
Most noteable part of this commit is the new local header file entry.h
which contains all the function declarations of functions that get only
called from asm code or are arch internal. That way we can avoid extern
declarations in C files.
This is more or less the same that was done for sparc64.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 07:47:06 +02:00
Heiko Carstens
43ca5c3a1c [S390] Convert monitor calls to function calls.
Remove the program check generating monitor calls and use function
calls instead. Theres is no real advantage in using monitor calls,
but they do make debugging harder, because of all the program checks
it generates.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2008-04-17 07:47:05 +02:00
Heiko Carstens
c10fde0d9e [S390] Vertical cpu management.
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>
2008-04-17 07:47:01 +02:00
Heiko Carstens
dbd70fb499 [S390] cpu topology support for s390.
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>
2008-04-17 07:47:01 +02:00
Heiko Carstens
98c7b388af [S390] Get rid of memcpy gcc warning workaround.
Compile smp.o with -Wno-nonnull so gcc stops warning about memcpy
being used with a null parameter. Also remove the workaround code
and use a char * cast instead of a void * cast to do computations.

Cc: Bastian Blank <bastian@waldi.eu.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-03-05 12:37:17 +01:00
Heiko Carstens
591bb4f637 [S390] Initialize per cpu lowcores on cpu hotplug.
Just copy the first 512 read-only bytes of the current cpu lowcore if
a new cpu gets onlined. The rest is zeroed out and must be explicitly
initialized. Current code just copies the entire lowcore and
initializes the needed fields.
This should reveal bugs in future enhancements quite early.
Also when the lowcore of the first cpu is replaced this is now done
atomically (no interrupts, no machine checks).

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-02-19 15:29:33 +01:00
Heiko Carstens
2bc89b5ece [S390] Fix couple of section mismatches.
Fix couple of section mismatches. And since we touch the code
anyway change the IPL code to use C99 initializers.

Cc: Michael Holzheu <holzheu@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-02-05 16:50:56 +01:00
Heiko Carstens
37c5f719e7 [S390] Fix smp_call_function_mask semantics.
Make sure func isn't called on the local cpu just like on all other
architectures that implement this function.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-02-05 16:50:55 +01:00
Martin Schwidefsky
9d40d2e395 [S390] replace lock_cpu_hotplug with get_online_cpus
Git commit 86ef5c9a8e forgot a few
lock_cpu_hotplug/unlock_cpu_hotplug pairs in arch/s390/kernel/smp.c

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:33 +01:00
Carsten Otte
dab5209cd8 [S390] add smp_call_function_mask
This patch adds the s390 variant for smp_call_function_mask(). The
implementation is pretty straight forward using the wrapper
__smp_call_function_map() which already takes a cpumask_t argument.

Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:31 +01:00
Heiko Carstens
1cb6bb4bbd [S390] Allocate and free cpu lowcores and stacks when needed/possible.
No need to preallocate the per cpu lowcores and stacks.
Savings are 28-32k per offline cpu.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:22 +01:00
Michael Holzheu
99ca4e582d [S390] kernel: Shutdown Actions Interface
In case of a kernel panic it is currently possible to specify that a dump
should be created, the system should be rebooted or stopped. Virtual sysfs
files under the directory /sys/firmware/ are used for that configuration.
In addition to that, there are kernel parameters 'vmhalt', 'vmpoff'
and 'vmpanic', which can be used to specify z/VM commands, which are
automatically executed in case of halt, power off or a kernel panic.
This patch combines both functionalities and allows to specify the z/VM CP
commands also via sysfs attributes. In addition to that, it enhances the
existing handling of shutdown triggers (e.g. halt or panic) and associated
shutdown actions (e.g. dump or reipl) and makes it more flexible.

Signed-off-by: Michael Holzheu <holzheu@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:19 +01:00
Heiko Carstens
48483b3290 [S390] Get rid of additional_cpus kernel parameter.
It caused only a lot of confusion. From now on cpu hotplug of up to
NR_CPUS will work by default. If somebody wants to limit that then
the possible_cpus parameter can be used.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:15 +01:00
Heiko Carstens
08d0796827 [S390] Standby cpu activation/deactivation.
Add a new interface so that cpus can be put into standby state and
configured state.
Only offline cpus can be put into standby state or configured state.
For that the new percpu sysfs attribute "configure" must be used.
To put a cpu in standby state a "0" must be written to the attribute.
In order to switch it into configured state a "1" must be written to
the attribute.
Only cpus in configured state can be brought online.
In addition this patch introduces a static mapping of physical to
logical cpus. As a result only the sysfs directories of present cpus
will be created. To scan for new cpus the new sysfs attribute "rescan"
must be used.
Writing to /sys/devices/system/cpu/rescan will trigger a rescan of
cpus and will create directories for new cpus.

On IPL only configured cpus will be used. And on reboot/shutdown all
cpus will remain in their current state (configured/standby).

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2008-01-26 14:11:09 +01:00
Heiko Carstens
677d762319 [S390] Dont overwrite lowcores on smp_send_stop().
Don't perform a sigp store-status-at-address on smp_send_stop().
It will overwrite the lowcores of other cpus and destroys valueable
debug informations.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-11-20 11:13:47 +01:00
Heiko Carstens
69d39d6669 [S390] Rename "idle_time" attribute to "idle_time_us".
Seems that people prefer to have the unit encoded in the attribute
name. Also makes parsing easier.

Now we have:

# cat /sys/devices/system/cpu/cpu0/idle_time_us
131473592

instead of

# cat /sys/devices/system/cpu/cpu0/idle_time
131473592 us

Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-11-05 11:10:17 +01:00
Martin Schwidefsky
ba8a9229ab [S390] tlb flush fix.
The current tlb flushing code for page table entries violates the
s390 architecture in a small detail. The relevant section from the
principles of operation (SA22-7832-02 page 3-47):

   "A valid table entry must not be changed while it is attached
   to any CPU and may be used for translation by that CPU except to
   (1) invalidate the entry by using INVALIDATE PAGE TABLE ENTRY or
   INVALIDATE DAT TABLE ENTRY, (2) alter bits 56-63 of a page-table
   entry, or (3) make a change by means of a COMPARE AND SWAP AND
   PURGE instruction that purges the TLB."

That means if one thread of a multithreaded applciation uses a vma
while another thread does an unmap on it, the page table entries of
that vma needs to get removed with IPTE, IDTE or CSP. In some strange
and rare situations a cpu could check-stop (die) because a entry has
been pushed out of the TLB that is still needed to complete a
(milli-coded) instruction. I've never seen it happen with the current
code on any of the supported machines, so right now this is a
theoretical problem. But I want to fix it nevertheless, to avoid
headaches in the futures.

To get this implemented correctly without changing common code the
primitives ptep_get_and_clear, ptep_get_and_clear_full and
ptep_set_wrprotect need to use the IPTE instruction to invalidate the
pte before the new pte value gets stored. If IPTE is always used for
the three primitives three important operations will have a performace
hit: fork, mprotect and exit_mmap. Time for some workarounds:

* 1: ptep_get_and_clear_full is used in unmap_vmas to remove page
tables entries in a batched tlb gather operation. If the mmu_gather
context passed to unmap_vmas has been started with full_mm_flush==1
or if only one cpu is online or if the only user of a mm_struct is the
current process then the fullmm indication in the mmu_gather context is
set to one. All TLBs for mm_struct are flushed by the tlb_gather_mmu
call. No new TLBs can be created while the unmap is in progress. In
this case ptep_get_and_clear_full clears the ptes with a simple store.

* 2: ptep_get_and_clear is used in change_protection to clear the
ptes from the page tables before they are reentered with the new
access flags. At the end of the update flush_tlb_range clears the
remaining TLBs. In general the ptep_get_and_clear has to issue IPTE
for each pte and flush_tlb_range is a nop. But if there is only one
user of the mm_struct then ptep_get_and_clear uses simple stores
to do the update and flush_tlb_range will flush the TLBs.

* 3: Similar to 2, ptep_set_wrprotect is used in copy_page_range
for a fork to make all ptes of a cow mapping read-only. At the end of
of copy_page_range dup_mmap will flush the TLBs with a call to
flush_tlb_mm.  Check for mm->mm_users and if there is only one user
avoid using IPTE in ptep_set_wrprotect and let flush_tlb_mm clear the
TLBs.

Overall for single threaded programs the tlb flush code now performs
better, for multi threaded programs it is slightly worse. In particular
exit_mmap() now does a single IDTE for the mm and then just frees every
page cache reference and every page table page directly without a delay
over the mmu_gather structure.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-10-22 12:52:48 +02:00
Heiko Carstens
fae8b22d3e [S390] Add per-cpu idle time / idle count sysfs attributes.
Add two new sysfs entries per cpu: idle_count and idle_time.
idle_count contains the number of times a cpu went into idle state.
idle_time contains the time a cpu spent in idle state in microseconds.
This can be used e.g. by powertop to tell how often idle state is
entered and left.

# cat /sys/devices/system/cpu/cpu0/idle_count
504
# cat /sys/devices/system/cpu/cpu0/idle_time
469734037 us

Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2007-10-22 12:52:47 +02:00