Replace all lock_cpu_hotplug/unlock_cpu_hotplug from the kernel and use
get_online_cpus and put_online_cpus instead as it highlights the
refcount semantics in these operations.

The new API guarantees protection against the cpu-hotplug operation, but
it doesn't guarantee serialized access to any of the local data
structures. Hence the changes needs to be reviewed.

In case of pseries_add_processor/pseries_remove_processor, use
cpu_maps_update_begin()/cpu_maps_update_done() as we're modifying the
cpu_present_map there.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch implements a Refcount + Waitqueue based model for
cpu-hotplug.

Now, a thread which wants to prevent cpu-hotplug, will bump up a global
refcount and the thread which wants to perform a cpu-hotplug operation
will block till the global refcount goes to zero.

The readers, if any, during an ongoing cpu-hotplug operation are blocked
until the cpu-hotplug operation is over.
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Paul Jackson <pj@sgi.com> [For !CONFIG_HOTPLUG_CPU ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

make randconfig bootup testing found that the cpufreq code
crashes on bootup, if the powernow-k8 driver is enabled and
if maxcpus=1 passed on the boot line to a !CONFIG_HOTPLUG_CPU
kernel.

First lockdep found out that there's an inconsistent unlock
sequence:

 =====================================
 [ BUG: bad unlock balance detected! ]
 -------------------------------------
 swapper/1 is trying to release lock (&per_cpu(cpu_policy_rwsem, cpu)) at:
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 but there are no more locks to release!

Call Trace:
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 [<ffffffff80251c29>] print_unlock_inbalance_bug+0x104/0x12c
 [<ffffffff80252f3a>] mark_held_locks+0x56/0x94
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 [<ffffffff807008b6>] cpufreq_add_dev+0x2a8/0x5c4
 ...

then shortly afterwards the cpufreq code crashed on an assert:

 ------------[ cut here ]------------
 kernel BUG at drivers/cpufreq/cpufreq.c:1068!
 invalid opcode: 0000 [1] SMP
 [...]
 Call Trace:
  [<ffffffff805145d6>] sysdev_driver_unregister+0x5b/0x91
  [<ffffffff806ff520>] cpufreq_register_driver+0x15d/0x1a2
  [<ffffffff80cc0596>] powernowk8_init+0x86/0x94
 [...]
 ---[ end trace 1e9219be2b4431de ]---

the bug was caused by maxcpus=1 bootup, which brought up the
secondary core as !cpu_online() but !cpu_is_offline() either,
which on on !CONFIG_HOTPLUG_CPU is always 0 (include/linux/cpu.h):

  /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */
  static inline int cpu_is_offline(int cpu) { return 0; }

but the cpufreq code uses cpu_online() and cpu_is_offline() in
a mixed way - the low-level drivers use cpu_online(), while
the cpufreq core uses cpu_is_offline(). This opened up the
possibility to add the non-initialized sysdev device of the
secondary core:

 cpufreq-core: trying to register driver powernow-k8
 cpufreq-core: adding CPU 0
 powernow-k8: BIOS error - no PSB or ACPI _PSS objects
 cpufreq-core: initialization failed
 cpufreq-core: adding CPU 1
 cpufreq-core: initialization failed

which then blew up. The fix is to make cpu_is_offline() always
the negation of cpu_online(). With that fix applied the kernel
boots up fine without crashing:

 Calling initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94()
 powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ processors (1 cpu cores) (version 2.20.00)
 powernow-k8: BIOS error - no PSB or ACPI _PSS objects
 initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94() returned -19.
 initcall 0xffffffff80cc0510 ran for 19 msecs: powernowk8_init+0x0/0x94()
 Calling initcall 0xffffffff80cc328f: init_lapic_nmi_sysfs+0x0/0x39()

We could fix this by making CPU enumeration aware of max_cpus, but that
would be more fragile IMO, and the cpu_online(cpu) != cpu_is_offline(cpu)
possibility was quite confusing and a continuous source of bugs too.

Most distributions have kernels with CPU hotplug enabled, so this bug
remained hidden for a long time.

Bug forensics:

The broken cpu_is_offline() API variant was introduced via:

 commit a59d2e4e6977e7b94e003c96a41f07e96cddc340
 Author: Rusty Russell <rusty@rustcorp.com.au>
 Date:   Mon Mar 8 06:06:03 2004 -0800

     [PATCH] minor cleanups for hotplug CPUs

( this predates linux-2.6.git, this commit is available from Thomas's
  historic git tree. )

Then 1.5 years later the cpufreq code made use of it:

 commit c32b6b8e
 Author: Ashok Raj <ashok.raj@intel.com>
 Date:   Sun Oct 30 14:59:54 2005 -0800

     [PATCH] create and destroy cpufreq sysfs entries based on cpu notifiers

 +       if (cpu_is_offline(cpu))
 +               return 0;

which is a correct use of the subtly broken new API. v2.6.15 then
shipped with this bug included.

then it took two more years for random-kernel qa to hit it.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The return of the present "do {} while" based stub definition of
register_hotcpu_notifier() cannot be checked.  This makes the stub
asymmetric w.r.t.  the real HOTPLUG_CPU=y implementation that is
int-returning.  So let us redefine this to be consistent with the full
version.  Also do the same for unregister_hotcpu_notifier().

We cannot define these as static inline functions due to an existing GCC
bug (#33172).  So define as macros that return appropriately instead (int
'0' for the register_hotcpu_notifier case and void for
unregister_hotcpu_notifier).
Signed-off-by: NSatyam Sharma <satyam@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Dependencies of CONFIG_SUSPEND and CONFIG_HIBERNATION introduced by commit
296699de "Introduce CONFIG_SUSPEND for
suspend-to-Ram and standby" are incorrect, as they don't cover the facts that
(1) not all architectures support suspend and (2) SMP hibernation is only
possible on X86 and PPC64 (if CONFIG_PPC64_SWSUSP is set).
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch makes the following needlessly global code static:

- arch_reinit_sched_domains()
- struct attr_sched_mc_power_savings
- struct attr_sched_smt_power_savings
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

aa953877 removed the implementation of
lock_cpu_hotplug_interruptible and all users of it.  This stub definition
for !CONFIG_HOTPLUG_CPU was left over -- kill it now.
Signed-off-by: NNathan Lynch <ntl@pobox.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

sysdev.h uses THIS_MODULE so should include <linux/module.h>.

[akpm@linux-foundation.org: couple of fixes]
Signed-off-by: NRalf Baechle <ralf@linux-mips.org>
Cc: Andi Kleen <ak@suse.de>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix the regression resulting from the recent change of suspend code
ordering that causes systems based on Intel x86 CPUs using the microcode
driver to hang during the resume.

The problem occurs since the microcode driver uses request_firmware() in
its CPU hotplug notifier, which is called after tasks has been frozen and
hangs.  It can be fixed by telling the microcode driver to use the
microcode stored in memory during the resume instead of trying to load it
from disk.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Adrian Bunk <bunk@stusta.de>
Cc: Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Maxim <maximlevitsky@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The following patchset allows a host with running virtual machines to be
suspended and, on at least a subset of the machines tested, resumed.  Note
that this is orthogonal to suspending and resuming an individual guest to a
file.

A side effect of implementing suspend/resume is that cpu hotplug is now
supported.  This should please the owners of big iron.

This patch:

KVM wants the cpu hotplug notifications, both for cpu hotplug itself, but more
commonly for host suspend/resume.

In order to avoid extensive #ifdefs, provide stubs when CONFIG_CPU_HOTPLUG is
not defined.

In all, we have four cases:

- UP: register and unregister stubbed out
- SMP+hotplug: full register and unregister
- SMP, no hotplug, core: register as __init, unregister stubbed
      (cpus are brought up during core initialization)
- SMP, no hotplug, module: register and unregister stubbed out
      (cpus cannot be brought up during module lifetime)
Signed-off-by: NAvi Kivity <avi@qumranet.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Provide a common interface for all the subsystems to lock and unlock their
per-subsystem hotcpu mutexes.

When CONFIG_HOTPLUG_CPU is not set, these operations would be no-ops.

[akpm@osdl.org: macros -> inlines]
Signed-off-by: NGautham R Shenoy <ego@in.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

There was lots of #ifdef noise in the kernel due to hotcpu_notifier(fn,
prio) not correctly marking 'fn' as used in the !HOTPLUG_CPU case, and thus
generating compiler warnings of unused symbols, hence forcing people to add
#ifdefs.

the compiler can skip truly unused functions just fine:

    text    data     bss     dec     hex filename
 1624412  728710 3674856 6027978  5bfaca vmlinux.before
 1624412  728710 3674856 6027978  5bfaca vmlinux.after

[akpm@osdl.org: topology.c fix]
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Change the 'no_control' field in the cpu struct to a more positive
and better term 'hotpluggable'. And change(/cleanup) the logic accordingly.
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: NAndi Kleen <ak@suse.de>
Cc: Andi Kleen <ak@suse.de>
Cc: "Li, Shaohua" <shaohua.li@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>

This patch adds two functions to create and remove sysfs attributes and
attribute_group to all cpus.  That allows to register sysfs attributes in
a subdirectory like: /sys/devices/system/cpu/cpuX/group_name/what_ever
This will be used by cbe_thermal to group all attributes dealing with
thermal support in one directory.
Signed-of-by: NChristian Krafft <krafft@de.ibm.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>

The current suspend code has to be run on one CPU, so we use the CPU
hotplug to take the non-boot CPUs offline on SMP machines.  However, we
should also make sure that these CPUs will not be enabled by someone else
after we have disabled them.

The functions disable_nonboot_cpus() and enable_nonboot_cpus() are moved to
kernel/cpu.c, because they now refer to some stuff in there that should
better be static.  Also it's better if disable_nonboot_cpus() returns an
error instead of panicking if something goes wrong, and
enable_nonboot_cpus() has no reason to panic(), because the CPUs may have
been enabled by the userland before it tries to take them online.
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Acked-by: NPavel Machek <pavel@ucw.cz>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The CPU hotplug locking was quite messy, with a recursive lock to
handle the fact that both the actual up/down sequence wanted to
protect itself from being re-entered, but the callbacks that it
called also tended to want to protect themselves from CPU events.

This splits the lock into two (one to serialize the whole hotplug
sequence, the other to protect against the CPU present bitmaps
changing). The latter still allows recursive usage because some
subsystems (ondemand policy for cpufreq at least) had already gotten
too used to the lax locking, but the locking mistakes are hopefully
now less fundamental, and we now warn about recursive lock usage
when we see it, in the hope that it can be fixed.
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Always use do {} while (0).  Failing to do so can cause subtle compile
failures or bugs.

Cc: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Define new macros register_hotcpu_notifier() and unregister_hotcpu_notifier()
that redefines register_cpu_notifier() and unregister_cpu_notifier() for use
only when HOTPLUG_CPU is defined.
Signed-off-by: NChandra Seetharaman <sekharan@us.ibm.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

CPUs come online only at init time (unless CONFIG_HOTPLUG_CPU is defined).
So, cpu_notifier functionality need to be available only at init time.

This patch makes register_cpu_notifier() available only at init time, unless
CONFIG_HOTPLUG_CPU is defined.

This patch exports register_cpu_notifier() and unregister_cpu_notifier() only
if CONFIG_HOTPLUG_CPU is defined.
Signed-off-by: NChandra Seetharaman <sekharan@us.ibm.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

With Goto-san's patch, we can add new pgdat/node at runtime.  I'm now
considering node-hot-add with cpu + memory on ACPI.

I found acpi container, which describes node, could evaluate cpu before
memory. This means cpu-hot-add occurs before memory hot add.

In most part, cpu-hot-add doesn't depend on node hot add.  But register_cpu(),
which creates symbolic link from node to cpu, requires that node should be
onlined before register_cpu().  When a node is onlined, its pgdat should be
there.

This patch-set holds off creating symbolic link from node to cpu
until node is onlined.

This removes node arguments from register_cpu().

Now, register_cpu() requires 'struct node' as its argument.  But the array of
struct node is now unified in driver/base/node.c now (By Goto's node hotplug
patch).  We can get struct node in generic way.  So, this argument is not
necessary now.

This patch also guarantees add cpu under node only when node is onlined.  It
is necessary for node-hot-add vs.  cpu-hot-add patch following this.

Moreover, register_cpu calculates cpu->node_id by cpu_to_node() without regard
to its 'struct node *root' argument.  This patch removes it.

Also modify callers of register_cpu()/unregister_cpu, whose args are changed
by register-cpu-remove-node-struct patch.

[Brice.Goglin@ens-lyon.org: fix it]
Signed-off-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: NBrice Goglin <Brice.Goglin@ens-lyon.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

- Moved check for online cpu out of smp_prepare_cpu()

- Moved default declaration of smp_prepare_cpu() to kernel/cpu.c

- Removed lock_cpu_hotplug() from smp_prepare_cpu() to around it, since
  its called from cpu_up() as well now.

- Removed clearing from cpu_present_map during cpu_offline as it breaks
  using cpu_up() directly during a subsequent online operation.
Signed-off-by: NAshok Raj <ashok.raj@intel.com>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: "Li, Shaohua" <shaohua.li@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Doing (int < NR_CPUS) doesn't dtrt if it's negative..
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

There are some callers in cpufreq hotplug notify path that the lowest
function calls lock_cpu_hotplug().  The lock is already held during
cpu_up() and cpu_down() calls when the notify calls are broadcast to
registered clients.

Ideally if possible, we could disable_preempt() at the highest caller and
make sure we dont sleep in the path down in cpufreq->driver_target() calls
but the calls are so intertwined and cumbersome to cleanup.

Hence we consistently use lock_cpu_hotplug() and unlock_cpu_hotplug() in
all places.

 - Removed export of cpucontrol semaphore and made it static.
 - removed explicit uses of up/down with lock_cpu_hotplug()
   so we can keep track of the the callers in same thread context and
   just keep refcounts without calling a down() that causes a deadlock.
 - Removed current_in_hotplug() uses
 - Removed PF_HOTPLUG_CPU in sched.h introduced for the current_in_hotplug()
   temporary workaround.

Tested with insmod of cpufreq_stat.ko, and logical online/offline
to make sure we dont have any hang situations.
Signed-off-by: NAshok Raj <ashok.raj@intel.com>
Cc: Zwane Mwaikambo <zwane@linuxpower.ca>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: "Siddha, Suresh B" <suresh.b.siddha@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

When calling target drivers to set frequency, we take cpucontrol lock.
When we modified the code to accomodate CPU hotplug, there was an attempt
to take a double lock of cpucontrol leading to a deadlock.  Since the
current thread context is already holding the cpucontrol lock, we dont need
to make another attempt to acquire it.

Now we leave a trace in current->flags indicating current thread already is
under cpucontrol lock held, so we dont attempt to do this another time.

Thanks to Andrew Morton for the beating:-)

From: Brice Goglin <Brice.Goglin@ens-lyon.org>

  Build fix

(akpm: this patch is still unpleasant.  Ashok continues to look for a cleaner
solution, doesn't he?  ;))
Signed-off-by: NAshok Raj <ashok.raj@intel.com>
Signed-off-by: NBrice Goglin <Brice.Goglin@ens-lyon.org>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Some modules creating sysfs entries under /sys/devices/system/cpu/cpuX/
need to know the parent sysfs entry to make devices under them.  This will
just return the sysfs entry for a given cpu.

sysfs entries showing under each cpu sysfs can be easily created if such
entries can be created by registering a sysfs driver for cpuclass.  The
issue is when the entry is created the CPU may not be online, hence we
would need to defer the creation until the online notification comes.

Current users: cache entries for Intel CPU's and cpufreq subsystem.
Signed-off-by: NAshok Raj <ashok.raj@intel.com>
Signed-off-by: NVenkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Zwane Mwaikambo <zwane@holomorphy.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch is against 2.6.10, but still applies cleanly. It's just
s/driverfs/sysfs/ in these two files.
Signed-off-by: NRolf Eike Beer <eike-kernel@sf-tec.de>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

I really wish smp_prepare_cpu() would disappear eventually.  In the interim
this is ideally a weak function, so we dont end up changing several places
to define this dummy in headers.

Today since the dummy declaration is done only in drivers/base/cpu.c but
the function is called in kernel/power/smp.c i get undefined reference in
my cpu hotplug code for x86_64 under development.
Signed-off-by: NAshok Raj <ashok.raj@intel.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!