Stop using kobject_register, as this way we can control the sending of
the uevent properly, after everything is properly initialized.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Stop using kobject_register, as this way we can control the sending of
the uevent properly, after everything is properly initialized.
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
/sys/power should not be a kset, that's overkill. This patch renames it
to power_kset and fixes up all usages of it in the tree.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
There is no firmware "subsystem" it's just a directory in /sys that
other portions of the kernel want to hook into. So make it a kobject
not a kset to help alivate anyone who tries to do some odd kset-like
things with this.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Dynamically create the kset instead of declaring it statically.
This makes the kobject attributes now work properly that I broke in the
previous patch.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Michael Holzheu <holzheu@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Volker Sameske <sameske@de.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This makes the code a bit simpler and and gets us one step closer to
deleting the deprecated subsys_attr code.
NOTE, this needs the next patch in the series in order to work properly.
This will build, but the sysfs files will not properly operate.
Thanks to Cornelia for the build fix on this patch.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Michael Holzheu <holzheu@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Volker Sameske <sameske@de.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This makes the code a bit simpler and and gets us one step closer to
deleting the deprecated subsys_attr code.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Manish Ahuja <mahuja@us.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This makes the code a bit simpler and and gets us one step closer to
deleting the deprecated subsys_attr code.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Cliff Brake <cbrake@accelent.com>
Cc: Dirk Behme <dirk.behme@de.bosch.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Dynamically create the kset instead of declaring it statically. We also
rename power_subsys to power_kset to catch all users of the variable and
we properly export it so that people don't have to guess that it really
is present in the system.
The pseries code is wierd, why is it createing /sys/power if CONFIG_PM
is disabled? Oh well, stupid big boxes ignoring config options...
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
We don't need a kset here, a simple kobject will do just fine, so
dynamically create the kobject and use it.
Thanks to Cornelia for the build fix.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Michael Holzheu <holzheu@de.ibm.com>
Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
We don't need a kset here, a simple kobject will do just fine, so
dynamically create the kobject and use it.
We also rename hypervisor_subsys to hypervisor_kset to catch all users
of the variable.
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
We don't need a "default" ktype for a kset. We should set this
explicitly every time for each kset. This change is needed so that we
can make ksets dynamic, and cleans up one of the odd, undocumented
assumption that the kset/kobject/ktype model has.
This patch is based on a lot of help from Kay Sievers.
Nasty bug in the block code was found by Dave Young
<hidave.darkstar@gmail.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Dave Young <hidave.darkstar@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
This patch reorganizes the way suspend and resume notifications are
sent to drivers. The major changes are that now the PM core acquires
every device semaphore before calling the methods, and calls to
device_add() during suspends will fail, while calls to device_del()
during suspends will block.
It also provides a way to safely remove a suspended device with the
help of the PM core, by using the device_pm_schedule_removal() callback
introduced specifically for this purpose, and updates two drivers (msr
and cpuid) that need to use it.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
: Stefan Roese <sr@denx.de> said:
> ppc: 4xx: sysctl table check failed: /kernel/l2cr .1.31 Missing strategy
>
> I'm seeing this error message when booting an recent arch/ppc kernel on
> 4xx platforms (tested on Ocotea and other 4xx platforms). Booting NFS
> rootfs still works fine, but this message kind of makes me "nervous".
> This is not seen on 4xx arch/powerpc platforms. Here the bootlog:
Because the data field was never filled and a binary sysctl handler was
never written this sysctl has never been usable through the sys_sysctl
interface. So just remove the binary sysctl number. Making the kernel
sanity checks happy.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Reported-by: Stefan Roese <sr@denx.de>
Cc: Josh Boyer <jwboyer@gmail.com>
Cc: Wolfgang Denk <wd@denx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This partially reverts 872e2be7c4
(Constify function pointer tables.)
The solaris/socksys.c transformation wasn't valid:
arch/sparc64/solaris/socksys.c:192: error: assignment of read-only variable ‘socksys_file_ops’
arch/sparc64/solaris/socksys.c:195: error: assignment of read-only variable ‘socksys_file_ops’
arch/sparc64/solaris/socksys.c:196: error: assignment of read-only variable ‘socksys_file_ops’
Signed-off-by: David S. Miller <davem@davemloft.net>
There have been several reports of Xen guest domains locking up when
using vcpu_info structure placement. Disable it for now.
Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When we set the MFGPT timer tick, there is a chance that we'll
immediately assert an event. If for some reason the IRQ routing
for this clock has been setup for some other purpose, then we
could end up firing an interrupt into the SMM handler or worse.
This rearranges the timer tick init function to initalize the handler
before we set up the MFGPT clock to make sure that even if we get
an event, it will go to the handler.
Furthermore, in the handler we need to make sure that we clear the
event, even if the timer isn't running.
Signed-off-by: Jordan Crouse <jordan.crouse@amd.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Arnd Hannemann <hannemann@i4.informatik.rwth-aachen.de>
Fix typo in arch/powerpc/boot/flatdevtree_env.h.
There is no Documentation/networking/ixgbe.txt.
README.cycladesZ is now in Documentation/.
wavelan.p.h is now in drivers/net/wireless/.
HFS.txt is now Documentation/filesystems/hfs.txt.
OSS-files are now in sound/oss/.
Signed-off-by: Johann Felix Soden <johfel@users.sourceforge.net>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit d4d25deca4.
It tried to fix long standing bugzilla entries, but the solution was
reported to break other systems. The reporter of
http://bugzilla.kernel.org/show_bug.cgi?id=9791
tracked it down to this commit and confirmed that reverting the patch
restores the correct behaviour. It's too late in the release cycle to
find a better solution than reverting the commit to avoid regressions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Fix following Section mismatch warning in sparc64:
WARNING: arch/sparc64/kernel/built-in.o(.text+0x13dec): Section mismatch: reference to .devinit.text:pci_scan_one_pbm (between 'psycho_scan_bus' and 'psycho_pbm_init')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x14b58): Section mismatch: reference to .devinit.text:pci_scan_one_pbm (between 'sabre_scan_bus' and 'sabre_init')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x15ea4): Section mismatch: reference to .devinit.text:pci_scan_one_pbm (between 'schizo_scan_bus' and 'schizo_pbm_init')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x17780): Section mismatch: reference to .devinit.text:pci_scan_one_pbm (between 'pci_sun4v_scan_bus' and 'pci_sun4v_get_head')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x17d5c): Section mismatch: reference to .devinit.text:pci_scan_one_pbm (between 'pci_fire_scan_bus' and 'pci_fire_get_head')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x23860): Section mismatch: reference to .devinit.text:vio_dev_release (between 'vio_create_one' and 'vio_add')
WARNING: arch/sparc64/kernel/built-in.o(.text+0x23868): Section mismatch: reference to .devinit.text:vio_dev_release (between 'vio_create_one' and 'vio_add')
The pci_* were all missing __init annotations.
For the vio.c case it was a function with a wrong annotation which was removed.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The tc35815-mac platform device used a pci bus number and a devfn to
identify its target device, but the pci bus number may vary if some
bus-bridges are found. Use irq number which is be unique for embedded
controllers.
Signed-off-by: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The JMPRS register on Malta boards keeps a 32-bit CPU-endian
value. The readw() function assumes that the value it reads is a
little-endian 16-bit number. Therefore, using readw() to obtain
the value of the JMPRS register is a mistake. This error leads
to incorrect reading of the PCI clock frequency on big-endian
during board start-up.
Change readw() to __raw_readl().
This was tested by injecting a call to printk() and verifying
that the value of the jmpr variable was consistent with current
setting of the JP4 "PCI CLK" jumper.
Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@gmail.com>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
'select' used by config symbol 'INTEL_IOATDMA' refers to undefined symbol 'DCA'
Although drivers/dma is currently the only user future drivers outside of
drivers/dma may select this option so it is better to add this to
arch/arm/Kconfig than move DCA to drivers/dma/Kconfig.
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
r2 is not guaranteed to be preserved over a function call, so relying
on it to store the link register over the call to sleep_phys_sp() is
unreliable. Store the link register on the stack instead.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The i386 and x86_64 arch directories contain nothing but a generated symlink
to arch/x86/boot/bzImage when a tree a built.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Anvin <hpa@zytor.com>
Signed-off-by: Josef 'Jeff' Sipek <jeffpc@josefsipek.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The latest Intel processors (the 45nm ones) have a model number of 23
(old ones had 15); they're otherwise compatible on the oprofile side.
This patch adds the new model number to the oprofile code.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The trap handler does properly update the fraction,
but not the exponent...
Thanks to Paolo Bonzini for the bug report and the testcase.
Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Paolo Bonzini <bonzini@gnu.org>
Cc: Richard Henderson <rth@twiddle.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- Move alignment to page size of init data outside ifdef for BLK_DEV_INITRD.
The reservation up to page size of memory after init data was previously
not done if BLK_DEV_INITRD was undefined.
This caused a kernel oops when init memory pages were freed after startup,
data placed in the same page as the last init memory would also be freed
and reused, with disastrous results.
- Use macros for initcalls and .text sections.
- Replace hardcoded page size constant with PAGE_SIZE define.
- Change include/asm-cris/page.h to use the _AC macro to instead
of testing __ASSEMBLY__.
Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Mikael Starvik <mikael.starvik@axis.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1) Trap level wasn't being passed down properly, we need to
move it from %l4 into the correct outgoing arg register.
2) Although the TPC often provides the most direct clue, we
have the caller PC so we should provide that as well.
Signed-off-by: David S. Miller <davem@davemloft.net>
The compiler team did the hard work for this distilling a problem in
large fortran application which showed up when applied to a 290MB input
data set down to this instruction:
ldfd f34=[r17],-8
Which they noticed incremented r17 by 0x10 rather than decrementing it
by 8 when the value in r17 caused an unaligned data fault. I tracked
it down to some bad instruction decoding in unaligned.c. The code
assumes that the 'x' bit can determine whether the instruction is
an "ldf" or "ldfp" ... which it is for opcode=6 (see table 4-29 on
page 3:302 of the SDM). But for opcode=7 the 'x' bit is irrelevent,
all variants are "ldf" instructions (see table 4-36 on page 3:306).
Note also that interpreting the instruction as "ldfp" means that the
"paired" floating point register (f35 in the example here) will also
be corrupted.
Signed-off-by: Tony Luck <tony.luck@intel.com>
This patch restores the blackfin Hardware Performance Monitor Profiling
support that was killed by the combining of instrumentation menus in
commit 09cadedbdc.
Since there seems to be no good reason to behave differently from other
architectures, it now automatically selects the hardware performance
counters whenever the profiling is activated.
mach-common/irqpanic.c: pm_overflow calls pm_overflow_handler which is
in oprofile/op_model_bf533.c. I doubt that setting HARDWARE_PM as "m"
will work at all, since the pm_overflow_handler should be in the core
kernel image because it is called by irqpanic.c.
Therefore, I change HARDWARE_PM from a tristate to a bool.
The whole arch/$(ARCH)/oprofile/ is built depending on CONFIG_OPROFILE. Since
part of the HARDWARE_PM support files sits in this directory, it makes sense to
also depend on OPROFILE, not only PROFILING. Since OPROFILE already depends on
PROFILING, it is correct to only depend on OPROFILE only.
Thanks to Adrian Bunk for finding this bug and providing an initial
patch.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Adrian Bunk <adrian.bunk@movial.fi>
CC: Randy Dunlap <randy.dunlap@oracle.com>
CC: bryan.wu@analog.com
Acked-by: Robin Getz <rgetz@blackfin.uclinux.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 09cadedbdc ("Combine
instrumentation menus in kernel/Kconfig.instrumentation") broke ARM
profiling support, since ARM has some extra Kconfig options and doesn't
just use the common OPROFILE/KPROBES config options.
Rather than just revert the thing outright, or add ARM-specific
knowledge to the generic Kconfig.instrumentation file (where the only
and whole point was to be generic, not too architecture-specific), this
just makes ARM not use the generic version, since it doesn't suit it.
So create an arm-specific version of Kconfig.instrumentation instead,
and use that.
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Russell King <rmk+lkml@arm.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In the current code, RTC_AIE doesn't work if the RTC relies on
CONFIG_HPET_EMULATE_RTC because the code sets the RTC_AIE flag in
hpet_set_rtc_irq_bit(). The interrupt handles does accidentally check
for RTC_PIE and not RTC_AIE when comparing the time which was set in
hpet_set_alarm_time().
I now verified on a test system here that without the patch applied,
the attached test program fails on a system that has HPET with
2.6.24-rc7-default. That's not critical since I guess the problem has
been there for several kernel releases, but as the fix is quite
obvious.
Configuration is CONFIG_RTC=y and CONFIG_HPET_EMULATE_RTC=y.
Signed-off-by: Bernhard Walle <bwalle@suse.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Denys Fedoryshchenko reported a bootup crash when he upgraded
his system from 3GB to 4GB RAM:
http://lkml.org/lkml/2008/1/7/9
the bug is due to HIGHMEM4G && SPARSEMEM kernels making pfn_to_page()
to return an invalid pointer when the pfn is in a memory hole. The
256 MB PCI aperture at the end of RAM was not mapped by sparsemem,
and hence the pfn was not valid. But set_highmem_pages_init() iterated
this range without checking the pfn's validity first.
this bug was probably present in the sparsemem code ever since sparsemem
has been introduced in v2.6.13. It was masked due to HIGHMEM64G using
larger memory regions in sparsemem_32.h:
#ifdef CONFIG_X86_PAE
#define SECTION_SIZE_BITS 30
#define MAX_PHYSADDR_BITS 36
#define MAX_PHYSMEM_BITS 36
#else
#define SECTION_SIZE_BITS 26
#define MAX_PHYSADDR_BITS 32
#define MAX_PHYSMEM_BITS 32
#endif
which creates 1GB sparsemem regions instead of 64MB sparsemem regions.
So in practice we only ever created true sparsemem holes on x86 with
HIGHMEM4G - but that was rarely used by distros.
( btw., we could probably save 2MB of mem_map[]s on X86_PAE if we reduced
the sparsemem region size to 256 MB. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Commit 473980a993 added a call to clear
the SLB shadow buffer before registering it. Unfortunately this means
that we clear out the entries that slb_initialize has previously set in
there. On POWER6, the hypervisor uses the SLB shadow buffer when doing
partition switches, and that means that after the next partition switch,
each non-boot CPU has no SLB entries to map the kernel text and data,
which causes it to crash.
This fixes it by reverting most of 473980a9 and instead clearing the
3rd entry explicitly in slb_initialize. This fixes the problem that
473980a9 was trying to solve, but without breaking POWER6.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Commit 5d2efba64b changed our iommu code
so that it always uses an iommu page size of 4kB. That means with our
current code, drivers may do a dma_map_sg() of a 64kB page and obtain
a dma_addr_t that is only 4k aligned.
This works fine in most cases except for some infiniband HW it seems,
where they tell the HW about the page size and it ignores the low bits
of the DMA address.
This works around it by making our IOMMU code enforce a PAGE_SIZE alignment
for mappings of objects that are page aligned in the first place and whose
size is larger or equal to a page.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Because Qube1 doesn't have a serial chip waiting for transmit fifo empty
takes forever, which isn't a good idea. No prom_putchar/early console
for Qube1 fixes this.
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Acked-by: Yoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
RAQ1 uses the same interrupt routing as Qube2.
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
The patch below fixes two problems for Kconfig on the BCM47xx platform:
- arch/mips/bcm47xx/gpio.c uses ssb_extif_* functions. Selecting
SSB_DRIVER_EXTIF makes sure those functions are available.
- arch/mips/pci/pci.c needs, when enabled, platform specific functions,
which are defined when SSB_PCICORE_HOSTMODE is enabled.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
This fixes compilation error where i2c_init wasn't defined.
Also, remove the CVS log and version tags, they are no longer useful.
Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Mikael Starvik <mikael.starvik@axis.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes compile error when nr_free_pages() from linux/swap.h
expands to global_page_state(NR_FREE_PAGES), but linux/vmstat.h isn't
included to declare global_page_state().
Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Mikael Starvik <mikael.starvik@axis.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes a kernel panic on boot due to do_signal not being compatible
with it's callers.
- do_signal now returns void, and does not have the previous signal set
as a parameter.
- Remove sys_rt_sigsuspend, we can use the common one instead.
- Change sys_sigsuspend to be more like x86, don't call do_signal here.
- handle_signal, setup_frame and setup_rt_frame now return -EFAULT
if we've delivered a segfault, which is used by callers to perform
necessary cleanup.
- Break long lines, correct whitespace and formatting errors.
Signed-off-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Mikael Starvik <mikael.starvik@axis.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Sometimes cpu_idle_wait gets stuck because it might miss CPUS that are
already in idle, have no tasks waiting to run and have no interrupts going
to them. This is common on bootup when switching cpu idle governors.
This patch gives those CPUS that don't check in an IPI kick.
Background:
-----------
I notice this while developing the mcount patches, that every once in a
while the system would hang. Looking deeper, the hang was always at boot
up when registering init_menu of the cpu_idle menu governor. Talking
with Thomas Gliexner, we discovered that one of the CPUS had no timer
events scheduled for it and it was in idle (running with NO_HZ). So the
CPU would not set the cpu_idle_state bit.
Hitting sysrq-t a few times would eventually route the interrupt to the
stuck CPU and the system would continue.
Note, I would have used the PDA isidle but that is set after the
cpu_idle_state bit is cleared, and would leave a window open where we
may miss being kicked.
hmm, looking closer at this, we still have a small race window between
clearing the cpu_idle_state and disabling interrupts (hence the RFC).
CPU0: CPU 1:
--------- ---------
cpu_idle_wait(): cpu_idle():
| __cpu_cpu_var(is_idle) = 1;
| if (__get_cpu_var(cpu_idle_state)) /* == 0 */
per_cpu(cpu_idle_state, 1) = 1; |
if (per_cpu(is_idle, 1)) /* == 1 */ |
smp_call_function(1) |
| receives ipi and runs do_nothing.
wait on map == empty idle();
/* waits forever */
So really we need interrupts off for most of this then. One might think
that we could simply clear the cpu_idle_state from do_nothing, but I'm
assuming that cpu_idle governors can be removed, and this might cause a
race that a governor might be used after the module was removed.
Venki said:
I think your RFC patch is the right solution here. As I see it, there is
no race with your RFC patch. As long as you call a dummy smp_call_function
on all CPUs, we should be OK. We can get rid of cpu_idle_state and the
current wait forever logic altogether with dummy smp_call_function. And so
there wont be any wait forever scenario.
The whole point of cpu_idle_wait() is to make all CPUs come out of idle
loop atleast once. The caller will use cpu_idle_wait something like this.
// Want to change idle handler
- Switch global idle handler to always present default_idle
- call cpu_idle_wait so that all cpus come out of idle for an instant
and stop using old idle pointer and start using default idle
- Change the idle handler to a new handler
- optional cpu_idle_wait if you want all cpus to start using the new
handler immediately.
Maybe the below 1s patch is safe bet for .24. But for .25, I would say we
just replace all complicated logic by simple dummy smp_call_function and
remove cpu_idle_state altogether.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andi Kleen <ak@suse.de>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There is almost no difference between 32 & 64 bit glue code.
Signed-off-by: Sebastian Siewior <sebastian@breakpoint.cc>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Greg Kroah-Hartman