The basic idea behind cross memory attach is to allow MPI programs doing
intra-node communication to do a single copy of the message rather than a
double copy of the message via shared memory.
The following patch attempts to achieve this by allowing a destination
process, given an address and size from a source process, to copy memory
directly from the source process into its own address space via a system
call. There is also a symmetrical ability to copy from the current
process's address space into a destination process's address space.
- Use of /proc/pid/mem has been considered, but there are issues with
using it:
- Does not allow for specifying iovecs for both src and dest, assuming
preadv or pwritev was implemented either the area read from or
written to would need to be contiguous.
- Currently mem_read allows only processes who are currently
ptrace'ing the target and are still able to ptrace the target to read
from the target. This check could possibly be moved to the open call,
but its not clear exactly what race this restriction is stopping
(reason appears to have been lost)
- Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix
domain socket is a bit ugly from a userspace point of view,
especially when you may have hundreds if not (eventually) thousands
of processes that all need to do this with each other
- Doesn't allow for some future use of the interface we would like to
consider adding in the future (see below)
- Interestingly reading from /proc/pid/mem currently actually
involves two copies! (But this could be fixed pretty easily)
As mentioned previously use of vmsplice instead was considered, but has
problems. Since you need the reader and writer working co-operatively if
the pipe is not drained then you block. Which requires some wrapping to
do non blocking on the send side or polling on the receive. In all to all
communication it requires ordering otherwise you can deadlock. And in the
example of many MPI tasks writing to one MPI task vmsplice serialises the
copying.
There are some cases of MPI collectives where even a single copy interface
does not get us the performance gain we could. For example in an
MPI_Reduce rather than copy the data from the source we would like to
instead use it directly in a mathops (say the reduce is doing a sum) as
this would save us doing a copy. We don't need to keep a copy of the data
from the source. I haven't implemented this, but I think this interface
could in the future do all this through the use of the flags - eg could
specify the math operation and type and the kernel rather than just
copying the data would apply the specified operation between the source
and destination and store it in the destination.
Although we don't have a "second user" of the interface (though I've had
some nibbles from people who may be interested in using it for intra
process messaging which is not MPI). This interface is something which
hardware vendors are already doing for their custom drivers to implement
fast local communication. And so in addition to this being useful for
OpenMPI it would mean the driver maintainers don't have to fix things up
when the mm changes.
There was some discussion about how much faster a true zero copy would
go. Here's a link back to the email with some testing I did on that:
http://marc.info/?l=linux-mm&m=130105930902915&w=2
There is a basic man page for the proposed interface here:
http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt
This has been implemented for x86 and powerpc, other architecture should
mainly (I think) just need to add syscall numbers for the process_vm_readv
and process_vm_writev. There are 32 bit compatibility versions for
64-bit kernels.
For arch maintainers there are some simple tests to be able to quickly
verify that the syscalls are working correctly here:
http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz
Signed-off-by: Chris Yeoh <yeohc@au1.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: <linux-man@vger.kernel.org>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Recent commit "irq: Track the owner of irq descriptor" in
commit ID b6873807a7 placed module.h into linux/irq.h
but we are trying to limit module.h inclusion to just C files
that really need it, due to its size and number of children
includes. This targets just reversing that include.
Add in the basic "struct module" since that is all we really need
to ensure things compile. In theory, b687380 should have added the
module.h include to the irqdesc.h header as well, but the implicit
module.h everywhere presence masked this from showing up. So give
it the "struct module" as well.
As for the C files, irqdesc.c is only using THIS_MODULE, so it
does not need module.h - give it export.h instead. The C file
irq/manage.c is now (as of b687380) using try_module_get and
module_put and so it needs module.h (which it already has).
Also convert the irq_alloc_descs variants to macros, since all
they really do is is call the __irq_alloc_descs primitive.
This avoids including export.h and no debug info is lost.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
These files were getting <linux/module.h> via an implicit non-obvious
path, but we want to crush those out of existence since they cost
time during compiles of processing thousands of lines of headers
for no reason. Give them the lightweight header that just contains
the EXPORT_SYMBOL infrastructure.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
The file rcutiny.c does not need moduleparam.h header, as
there are no modparams in this file.
However rcutiny_plugin.h does define a module_init() and
a module_exit() and it uses the various MODULE_ macros, so
it really does need module.h included.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Through various other implicit include paths, some files were
getting the full module.h file, and hence living the illusion
that they really only needed moduleparam.h -- but the reality
is that once you remove the module.h presence, these show up:
kernel/params.c:583: warning: ‘struct module_kobject’ declared inside parameter list
Such files really require module.h so simply make it so. As the
file module.h grabs moduleparam.h on the fly, all will be well.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
With the module.h usage cleanup, we'll get this:
kernel/ksysfs.c:161: error: ‘S_IRUGO’ undeclared here (not in a function)
make[2]: *** [kernel/ksysfs.o] Error 1
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Up until now, this file was getting percpu.h because nearly every
file was implicitly getting module.h (and all its sub-includes).
But we want to clean that up, so call out percpu.h explicitly.
Otherwise we'll get things like this on an ARM build:
kernel/irq_work.c:48: error: expected declaration specifiers or '...' before 'irq_work_list'
kernel/irq_work.c:48: warning: type defaults to 'int' in declaration of 'DEFINE_PER_CPU'
The same thing was happening for builds on ARM for asm/processor.h
kernel/irq_work.c: In function 'irq_work_sync':
kernel/irq_work.c:166: error: implicit declaration of function 'cpu_relax'
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
These files were implicitly relying on <linux/kmod.h> coming in via
module.h, as without it we get things like:
kernel/power/suspend.c💯 error: implicit declaration of function ‘usermodehelper_disable’
kernel/power/suspend.c:109: error: implicit declaration of function ‘usermodehelper_enable’
kernel/power/user.c:254: error: implicit declaration of function ‘usermodehelper_disable’
kernel/power/user.c:261: error: implicit declaration of function ‘usermodehelper_enable’
kernel/sys.c:317: error: implicit declaration of function ‘usermodehelper_disable’
kernel/sys.c:1816: error: implicit declaration of function ‘call_usermodehelper_setup’
kernel/sys.c:1822: error: implicit declaration of function ‘call_usermodehelper_setfns’
kernel/sys.c:1824: error: implicit declaration of function ‘call_usermodehelper_exec’
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
These files are doing things like module_put and try_module_get
so they need to call out the module.h for explicit inclusion,
rather than getting it via <linux/device.h> which we ideally want
to remove the module.h inclusion from.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
The changed files were only including linux/module.h for the
EXPORT_SYMBOL infrastructure, and nothing else. Revector them
onto the isolated export header for faster compile times.
Nothing to see here but a whole lot of instances of:
-#include <linux/module.h>
+#include <linux/export.h>
This commit is only changing the kernel dir; next targets
will probably be mm, fs, the arch dirs, etc.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
This file isn't doing anything with modules and so it should
not be including <linux/module.h> just to get basic stuff
like printk() and min/max. Revector it to <linux/kernel.h>.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Interrupt controllers can have non-zero starting value for h/w irq numbers.
Adding support in irq_domain allows the domain hwirq numbering to match
the interrupt controllers' numbering.
As this makes looping over irqs for a domain more complicated, add loop
iterators to iterate over all hwirqs and irqs for a domain.
Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Reviewed-by: Jamie Iles <jamie@jamieiles.com>
Tested-by: Thomas Abraham <thomas.abraham@linaro.org>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
This patch introduces a mechanism that allows architecture backends to
remove page tables for the crashkernel memory. This can protect the loaded
kdump kernel from being overwritten by broken kernel code. Two new
functions crash_map_reserved_pages() and crash_unmap_reserved_pages() are
added that can be implemented by architecture code. The
crash_map_reserved_pages() function is called before and
crash_unmap_reserved_pages() after the crashkernel segments are loaded. The
functions are also called in crash_shrink_memory() to create/remove page
tables when the crashkernel memory size is reduced.
To support architectures that have large pages this patch also introduces
a new define KEXEC_CRASH_MEM_ALIGN. The crashkernel start and size must
always be aligned with KEXEC_CRASH_MEM_ALIGN.
Cc: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Currently the vmcoreinfo note is only initialized in case of kdump. On s390
it is possible to create kernel dumps with other dump mechanisms than kdump
(e.g. via hypervisor dump or stand-alone dump tools). For those dumps it
would also be desirable to include the vmcoreinfo data. To accomplish this,
with this patch the vmcoreinfo ELF note is always initialized, not only in
case of a (kdump) crash. On s390 we will add an ABI defined pointer at
a well known address to vmcoreinfo so that dump analysis tools are able to
find this information.
In particular on s390 we have a tool named zgetdump. With this tool it is
possible to convert dump formats on the fly using fuse. E.g. you can mount a
s390 stand-alone dump as ELF dump. When this is done, the tool finds the
vmcoreinfo in the stand-alone dump via the well known ABI defined address and
it creates the respective VMCOREINFO ELF note in the output ELF dump. This then
can be used e.g. by makedumpfile for dump filtering. No more need for a
vmlinux file with debug information.
So this will look like the following:
$ zgetdump --mount standalone.dump -f elf /mnt
$ ls /mnt
dump.elf
$ readelf -n /mnt/dump.elf
$ ...
VMCOREINFO 0x00000474 Unknown note type: (0x00000000)
$ makedumpfile -c -d 31 /mnt/dump.elf dump.kdump
Cc: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Currently only the address of the pre-allocated ELF header is passed with
the elfcorehdr= kernel parameter. In order to reserve memory for the header
in the 2nd kernel also the size is required. Current kdump architecture
backends use different methods to do that, e.g. x86 uses the memmap= kernel
parameter. On s390 there is no easy way to transfer this information.
Therefore the elfcorehdr kernel parameter is extended to also pass the size.
This now can also be used as standard mechanism by all future kdump
architecture backends.
The syntax of the kernel parameter is extended as follows:
elfcorehdr=[size[KMG]@]offset[KMG]
This change is backward compatible because elfcorehdr=size is still allowed.
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
On s390 there is a different KEXEC_CONTROL_MEMORY_LIMIT for the normal and
the kdump kexec case. Therefore this patch introduces a new macro
KEXEC_CRASH_CONTROL_MEMORY_LIMIT. This is set to
KEXEC_CONTROL_MEMORY_LIMIT for all architectures that do not define
KEXEC_CRASH_CONTROL_MEMORY_LIMIT.
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
* 'gpio/next' of git://git.secretlab.ca/git/linux-2.6:
h8300: Move gpio.h to gpio-internal.h
gpio: pl061: add DT binding support
gpio: fix build error in include/asm-generic/gpio.h
gpiolib: Ensure struct gpio is always defined
irq: Add EXPORT_SYMBOL_GPL to function of irq generic-chip
gpio-ml-ioh: Use NUMA_NO_NODE not GFP_KERNEL
gpio-pch: Use NUMA_NO_NODE not GFP_KERNEL
gpio: langwell: ensure alternate function is cleared
gpio-pch: Support interrupt function
gpio-pch: Save register value in suspend()
gpio-pch: modify gpio_nums and mask
gpio-pch: support ML7223 IOH n-Bus
gpio-pch: add spinlock in suspend/resume processing
gpio-pch: Delete invalid "restore" code in suspend()
gpio-ml-ioh: Fix suspend/resume issue
gpio-ml-ioh: Support interrupt function
gpio-ml-ioh: Delete unnecessary code
gpio/mxc: add chained_irq_enter/exit() to mx3_gpio_irq_handler()
gpio/nomadik: use genirq core to track enablement
gpio/nomadik: disable clocks when unused
After getting a number of questions in private emails about the
math around admittedly very complex timekeeping_adjust() and
timekeeping_big_adjust(), I figure the code needs some better
comments.
Hopefully the explanations are clear enough and don't muddy the
water any worse.
Still needs documentation for ntp_error, but I couldn't recall
exactly the full explanation behind the code that's there
(although I do recall once working it out when Roman first
proposed it). Given a bit more time I can probably work it out,
but I don't want to hold back this documentation until then.
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Chen Jie <chenj@lemote.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1319764362-32367-1-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
time, s390: Get rid of compile warning
dw_apb_timer: constify clocksource name
time: Cleanup old CONFIG_GENERIC_TIME references that snuck in
time: Change jiffies_to_clock_t() argument type to unsigned long
alarmtimers: Fix error handling
clocksource: Make watchdog reset lockless
posix-cpu-timers: Cure SMP accounting oddities
s390: Use direct ktime path for s390 clockevent device
clockevents: Add direct ktime programming function
clockevents: Make minimum delay adjustments configurable
nohz: Remove "Switched to NOHz mode" debugging messages
proc: Consider NO_HZ when printing idle and iowait times
nohz: Make idle/iowait counter update conditional
nohz: Fix update_ts_time_stat idle accounting
cputime: Clean up cputime_to_usecs and usecs_to_cputime macros
alarmtimers: Rework RTC device selection using class interface
alarmtimers: Add try_to_cancel functionality
alarmtimers: Add more refined alarm state tracking
alarmtimers: Remove period from alarm structure
alarmtimers: Remove interval cap limit hack
...
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
llist: Add back llist_add_batch() and llist_del_first() prototypes
sched: Don't use tasklist_lock for debug prints
sched: Warn on rt throttling
sched: Unify the ->cpus_allowed mask copy
sched: Wrap scheduler p->cpus_allowed access
sched: Request for idle balance during nohz idle load balance
sched: Use resched IPI to kick off the nohz idle balance
sched: Fix idle_cpu()
llist: Remove cpu_relax() usage in cmpxchg loops
sched: Convert to struct llist
llist: Add llist_next()
irq_work: Use llist in the struct irq_work logic
llist: Return whether list is empty before adding in llist_add()
llist: Move cpu_relax() to after the cmpxchg()
llist: Remove the platform-dependent NMI checks
llist: Make some llist functions inline
sched, tracing: Show PREEMPT_ACTIVE state in trace_sched_switch
sched: Remove redundant test in check_preempt_tick()
sched: Add documentation for bandwidth control
sched: Return unused runtime on group dequeue
...
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (121 commits)
perf symbols: Increase symbol KSYM_NAME_LEN size
perf hists browser: Refuse 'a' hotkey on non symbolic views
perf ui browser: Use libslang to read keys
perf tools: Fix tracing info recording
perf hists browser: Elide DSO column when it is set to just one DSO, ditto for threads
perf hists: Don't consider filtered entries when calculating column widths
perf hists: Don't decay total_period for filtered entries
perf hists browser: Honour symbol_conf.show_{nr_samples,total_period}
perf hists browser: Do not exit on tab key with single event
perf annotate browser: Don't change selection line when returning from callq
perf tools: handle endianness of feature bitmap
perf tools: Add prelink suggestion to dso update message
perf script: Fix unknown feature comment
perf hists browser: Apply the dso and thread filters when merging new batches
perf hists: Move the dso and thread filters from hist_browser
perf ui browser: Honour the xterm colors
perf top tui: Give color hints just on the percentage, like on --stdio
perf ui browser: Make the colors configurable and change the defaults
perf tui: Remove unneeded call to newtCls on startup
perf hists: Don't format the percentage on hist_entry__snprintf
...
Fix up conflicts in arch/x86/kernel/kprobes.c manually.
Ingo's tree did the insane "add volatile to const array", which just
doesn't make sense ("volatile const"?). But we could remove the const
*and* make the array volatile to make doubly sure that gcc doesn't
optimize it away..
Also fix up kernel/trace/ring_buffer.c non-data-conflicts manually: the
reader_lock has been turned into a raw lock by the core locking merge,
and there was a new user of it introduced in this perf core merge. Make
sure that new use also uses the raw accessor functions.
* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq: Add IRQF_RESUME_EARLY and resume such IRQs earlier
genirq: Fix fatfinered fixup really
genirq: percpu: allow interrupt type to be set at enable time
genirq: Add support for per-cpu dev_id interrupts
genirq: Add IRQCHIP_SKIP_SET_WAKE flag
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
rcu: Move propagation of ->completed from rcu_start_gp() to rcu_report_qs_rsp()
rcu: Remove rcu_needs_cpu_flush() to avoid false quiescent states
rcu: Wire up RCU_BOOST_PRIO for rcutree
rcu: Make rcu_torture_boost() exit loops at end of test
rcu: Make rcu_torture_fqs() exit loops at end of test
rcu: Permit rt_mutex_unlock() with irqs disabled
rcu: Avoid having just-onlined CPU resched itself when RCU is idle
rcu: Suppress NMI backtraces when stall ends before dump
rcu: Prohibit grace periods during early boot
rcu: Simplify unboosting checks
rcu: Prevent early boot set_need_resched() from __rcu_pending()
rcu: Dump local stack if cannot dump all CPUs' stacks
rcu: Move __rcu_read_unlock()'s barrier() within if-statement
rcu: Improve rcu_assign_pointer() and RCU_INIT_POINTER() documentation
rcu: Make rcu_assign_pointer() unconditionally insert a memory barrier
rcu: Make rcu_implicit_dynticks_qs() locals be correct size
rcu: Eliminate in_irq() checks in rcu_enter_nohz()
nohz: Remove nohz_cpu_mask
rcu: Document interpretation of RCU-lockdep splats
rcu: Allow rcutorture's stat_interval parameter to be changed at runtime
...
* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
rtmutex: Add missing rcu_read_unlock() in debug_rt_mutex_print_deadlock()
lockdep: Comment all warnings
lib: atomic64: Change the type of local lock to raw_spinlock_t
locking, lib/atomic64: Annotate atomic64_lock::lock as raw
locking, x86, iommu: Annotate qi->q_lock as raw
locking, x86, iommu: Annotate irq_2_ir_lock as raw
locking, x86, iommu: Annotate iommu->register_lock as raw
locking, dma, ipu: Annotate bank_lock as raw
locking, ARM: Annotate low level hw locks as raw
locking, drivers/dca: Annotate dca_lock as raw
locking, powerpc: Annotate uic->lock as raw
locking, x86: mce: Annotate cmci_discover_lock as raw
locking, ACPI: Annotate c3_lock as raw
locking, oprofile: Annotate oprofilefs lock as raw
locking, video: Annotate vga console lock as raw
locking, latencytop: Annotate latency_lock as raw
locking, timer_stats: Annotate table_lock as raw
locking, rwsem: Annotate inner lock as raw
locking, semaphores: Annotate inner lock as raw
locking, sched: Annotate thread_group_cputimer as raw
...
Fix up conflicts in kernel/posix-cpu-timers.c manually: making
cputimer->cputime a raw lock conflicted with the ABBA fix in commit
bcd5cff721 ("cputimer: Cure lock inversion").
* git://github.com/rustyrussell/linux:
params: make dashes and underscores in parameter names truly equal
kmod: prevent kmod_loop_msg overflow in __request_module()
The user may use "foo-bar" for a kernel parameter defined as "foo_bar".
Make sure it works the other way around too.
Apply the equality of dashes and underscores on early_params and __setup
params as well.
The example given in Documentation/kernel-parameters.txt indicates that
this is the intended behaviour.
With the patch the kernel accepts "log-buf-len=1M" as expected.
https://bugzilla.redhat.com/show_bug.cgi?id=744545
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (neatened implementations)
Due to post-increment in condition of kmod_loop_msg in __request_module(),
the system log can be spammed by much more than 5 instances of the 'runaway
loop' message if the number of events triggering it makes the kmod_loop_msg
to overflow.
Fix that by making sure we never increment it past the threshold.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
CC: stable@kernel.org
Initialize jump_labels much, much earlier, so they're available for use
during system setup.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
When updating a newly loaded module, the code is definitely not yet
executing on any processor, so it can be updated with no need for any
heavyweight synchronization.
This patch adds arch_jump_label_static() which is implemented as
arch_jump_label_transform() by default, but architectures can override
it if it avoids, say, a call to stop_machine().
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
If a key has been enabled before jump_label_init() is called, don't
nop it out.
This removes arch_jump_label_text_poke_early() (which can only nop
out a site) and uses arch_jump_label_transform() instead.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Make stop_machine() safe to call early in boot, before stop_machine()
has been set up, by simply calling the callback function directly if
there's only one CPU online.
[ Fixes from AKPM:
- add comment
- local_irq_flags, not save_flags
- also call hard_irq_disable() for systems which need it
Tejun suggested using an explicit flag rather than just looking at
the online cpu count. ]
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
* 'pm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (63 commits)
PM / Clocks: Remove redundant NULL checks before kfree()
PM / Documentation: Update docs about suspend and CPU hotplug
ACPI / PM: Add Sony VGN-FW21E to nonvs blacklist.
ARM: mach-shmobile: sh7372 A4R support (v4)
ARM: mach-shmobile: sh7372 A3SP support (v4)
PM / Sleep: Mark devices involved in wakeup signaling during suspend
PM / Hibernate: Improve performance of LZO/plain hibernation, checksum image
PM / Hibernate: Do not initialize static and extern variables to 0
PM / Freezer: Make fake_signal_wake_up() wake TASK_KILLABLE tasks too
PM / Hibernate: Add resumedelay kernel param in addition to resumewait
MAINTAINERS: Update linux-pm list address
PM / ACPI: Blacklist Vaio VGN-FW520F machine known to require acpi_sleep=nonvs
PM / ACPI: Blacklist Sony Vaio known to require acpi_sleep=nonvs
PM / Hibernate: Add resumewait param to support MMC-like devices as resume file
PM / Hibernate: Fix typo in a kerneldoc comment
PM / Hibernate: Freeze kernel threads after preallocating memory
PM: Update the policy on default wakeup settings
PM / VT: Cleanup #if defined uglyness and fix compile error
PM / Suspend: Off by one in pm_suspend()
PM / Hibernate: Include storage keys in hibernation image on s390
...
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1745 commits)
dp83640: free packet queues on remove
dp83640: use proper function to free transmit time stamping packets
ipv6: Do not use routes from locally generated RAs
|PATCH net-next] tg3: add tx_dropped counter
be2net: don't create multiple RX/TX rings in multi channel mode
be2net: don't create multiple TXQs in BE2
be2net: refactor VF setup/teardown code into be_vf_setup/clear()
be2net: add vlan/rx-mode/flow-control config to be_setup()
net_sched: cls_flow: use skb_header_pointer()
ipv4: avoid useless call of the function check_peer_pmtu
TCP: remove TCP_DEBUG
net: Fix driver name for mdio-gpio.c
ipv4: tcp: fix TOS value in ACK messages sent from TIME_WAIT
rtnetlink: Add missing manual netlink notification in dev_change_net_namespaces
ipv4: fix ipsec forward performance regression
jme: fix irq storm after suspend/resume
route: fix ICMP redirect validation
net: hold sock reference while processing tx timestamps
tcp: md5: add more const attributes
Add ethtool -g support to virtio_net
...
Fix up conflicts in:
- drivers/net/Kconfig:
The split-up generated a trivial conflict with removal of a
stale reference to Documentation/networking/net-modules.txt.
Remove it from the new location instead.
- fs/sysfs/dir.c:
Fairly nasty conflicts with the sysfs rb-tree usage, conflicting
with Eric Biederman's changes for tagged directories.
* 'usb-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (260 commits)
usb: renesas_usbhs: fixup inconsistent return from usbhs_pkt_push()
usb/isp1760: Allow to optionally trigger low-level chip reset via GPIOLIB.
USB: gadget: midi: memory leak in f_midi_bind_config()
USB: gadget: midi: fix range check in f_midi_out_open()
QE/FHCI: fixed the CONTROL bug
usb: renesas_usbhs: tidyup for smatch warnings
USB: Fix USB Kconfig dependency problem on 85xx/QoirQ platforms
EHCI: workaround for MosChip controller bug
usb: gadget: file_storage: fix race on unloading
USB: ftdi_sio.c: Use ftdi async_icount structure for TIOCMIWAIT, as in other drivers
USB: ftdi_sio.c:Fill MSR fields of the ftdi async_icount structure
USB: ftdi_sio.c: Fill LSR fields of the ftdi async_icount structure
USB: ftdi_sio.c:Fill TX field of the ftdi async_icount structure
USB: ftdi_sio.c: Fill the RX field of the ftdi async_icount structure
USB: ftdi_sio.c: Basic icount infrastructure for ftdi_sio
usb/isp1760: Let OF bindings depend on general CONFIG_OF instead of PPC_OF .
USB: ftdi_sio: Support TI/Luminary Micro Stellaris BD-ICDI Board
USB: Fix runtime wakeup on OHCI
xHCI/USB: Make xHCI driver have a BOS descriptor.
usb: gadget: add new usb gadget for ACM and mass storage
...
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (59 commits)
MAINTAINERS: linux-m32r is moderated for non-subscribers
linux@lists.openrisc.net is moderated for non-subscribers
Drop default from "DM365 codec select" choice
parisc: Kconfig: cleanup Kernel page size default
Kconfig: remove redundant CONFIG_ prefix on two symbols
cris: remove arch/cris/arch-v32/lib/nand_init.S
microblaze: add missing CONFIG_ prefixes
h8300: drop puzzling Kconfig dependencies
MAINTAINERS: microblaze-uclinux@itee.uq.edu.au is moderated for non-subscribers
tty: drop superfluous dependency in Kconfig
ARM: mxc: fix Kconfig typo 'i.MX51'
Fix file references in Kconfig files
aic7xxx: fix Kconfig references to READMEs
Fix file references in drivers/ide/
thinkpad_acpi: Fix printk typo 'bluestooth'
bcmring: drop commented out line in Kconfig
btmrvl_sdio: fix typo 'btmrvl_sdio_sd6888'
doc: raw1394: Trivial typo fix
CIFS: Don't free volume_info->UNC until we are entirely done with it.
treewide: Correct spelling of successfully in comments
...
* 'next' of git://selinuxproject.org/~jmorris/linux-security: (95 commits)
TOMOYO: Fix incomplete read after seek.
Smack: allow to access /smack/access as normal user
TOMOYO: Fix unused kernel config option.
Smack: fix: invalid length set for the result of /smack/access
Smack: compilation fix
Smack: fix for /smack/access output, use string instead of byte
Smack: domain transition protections (v3)
Smack: Provide information for UDS getsockopt(SO_PEERCRED)
Smack: Clean up comments
Smack: Repair processing of fcntl
Smack: Rule list lookup performance
Smack: check permissions from user space (v2)
TOMOYO: Fix quota and garbage collector.
TOMOYO: Remove redundant tasklist_lock.
TOMOYO: Fix domain transition failure warning.
TOMOYO: Remove tomoyo_policy_memory_lock spinlock.
TOMOYO: Simplify garbage collector.
TOMOYO: Fix make namespacecheck warnings.
target: check hex2bin result
encrypted-keys: check hex2bin result
...
Some functions of irq generic-chip is undefined, because
EXPORT_SYMBOL_GPL is not set to these.
ERROR: "irq_setup_generic_chip" [drivers/gpio/gpio-pch.ko] undefined!
ERROR: "irq_alloc_generic_chip" [drivers/gpio/gpio-pch.ko] undefined!
ERROR: "irq_setup_generic_chip" [drivers/gpio/gpio-ml-ioh.ko] undefined!
ERROR: "irq_alloc_generic_chip" [drivers/gpio/gpio-ml-ioh.ko] undefined!
This is revised that EXPORT_SYMBOL_GPL can be added and referred
to in functions.
Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
There's a lock inversion between the cputimer->lock and rq->lock;
notably the two callchains involved are:
update_rlimit_cpu()
sighand->siglock
set_process_cpu_timer()
cpu_timer_sample_group()
thread_group_cputimer()
cputimer->lock
thread_group_cputime()
task_sched_runtime()
->pi_lock
rq->lock
scheduler_tick()
rq->lock
task_tick_fair()
update_curr()
account_group_exec()
cputimer->lock
Where the first one is enabling a CLOCK_PROCESS_CPUTIME_ID timer, and
the second one is keeping up-to-date.
This problem was introduced by e8abccb719 ("posix-cpu-timers: Cure
SMP accounting oddities").
Cure the problem by removing the cputimer->lock and rq->lock nesting,
this leaves concurrent enablers doing duplicate work, but the time
wasted should be on the same order otherwise wasted spinning on the
lock and the greater-than assignment filter should ensure we preserve
monotonicity.
Reported-by: Dave Jones <davej@redhat.com>
Reported-by: Simon Kirby <sim@hostway.ca>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: stable@kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/1318928713.21167.4.camel@twins
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The size is always valid, but variable-length arrays generate worse code
for no good reason (unless the function happens to be inlined and the
compiler sees the length for the simple constant it is).
Also, there seems to be some code generation problem on POWER, where
Henrik Bakken reports that register r28 can get corrupted under some
subtle circumstances (interrupt happening at the wrong time?). That all
indicates some seriously broken compiler issues, but since variable
length arrays are bad regardless, there's little point in trying to
chase it down.
"Just don't do that, then".
Reported-by: Henrik Grindal Bakken <henribak@cisco.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds a mechanism to resume selected IRQs during syscore_resume
instead of dpm_resume_noirq.
Under Xen we need to resume IRQs associated with IPIs early enough
that the resched IPI is unmasked and we can therefore schedule
ourselves out of the stop_machine where the suspend/resume takes
place.
This issue was introduced by 676dc3cf5b "xen: Use IRQF_FORCE_RESUME".
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Jeremy Fitzhardinge <Jeremy.Fitzhardinge@citrix.com>
Cc: xen-devel <xen-devel@lists.xensource.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/1318713254.11016.52.camel@dagon.hellion.org.uk
Cc: stable@kernel.org (at least to 2.6.32.y)
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Use threads for LZO compression/decompression on hibernate/thaw.
Improve buffering on hibernate/thaw.
Calculate/verify CRC32 of the image pages on hibernate/thaw.
In my testing, this improved write/read speed by a factor of about two.
Signed-off-by: Bojan Smojver <bojan@rexursive.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Static and extern variables in kernel/power/hibernate.c need not be
initialized to 0 explicitly, so remove those initializations.
[rjw: Modified subject, added changelog.]
Signed-off-by: Barry Song <Baohua.Song@csr.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
TASK_KILLABLE is often used to put tasks to sleep for quite some time.
One of the most common uses is to put tasks to sleep while waiting for
replies from a server on a networked filesystem (such as CIFS or NFS).
Unfortunately, fake_signal_wake_up does not currently wake up tasks
that are sleeping in TASK_KILLABLE state. This means that even if the
code were in place to allow them to freeze while in this sleep, it
wouldn't work anyway.
This patch changes this function to wake tasks in this state as well.
This should be harmless -- if the code doing the sleeping doesn't have
handling to deal with freezer events, it should just go back to sleep.
If it does, then this will allow that code to do the right thing.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Patch "PM / Hibernate: Add resumewait param to support MMC-like
devices as resume file" added the resumewait kernel command line
option. The present patch adds resumedelay so that
resumewait/delay were analogous to rootwait/delay.
[rjw: Modified the subject and changelog slightly.]
Signed-off-by: Barry Song <baohua.song@csr.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Some devices like MMC are async detected very slow. For example,
drivers/mmc/host/sdhci.c launches a 200ms delayed work to detect
MMC partitions then add disk.
We have wait_for_device_probe() and scsi_complete_async_scans()
before calling swsusp_check(), but it is not enough to wait for MMC.
This patch adds resumewait kernel param just like rootwait so
that we have enough time to wait until MMC is ready. The difference is
that we wait for resume partition whereas rootwait waits for rootfs
partition (which may be on a different device).
This patch will make hibernation support many embedded products
without SCSI devices, but with devices like MMC.
[rjw: Modified the changelog slightly.]
Signed-off-by: Barry Song <Baohua.Song@csr.com>
Reviewed-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Fix a typo in a function name in the kerneldoc comment next to
resume_target_kernel().
[rjw: Changed the subject slightly, added the changelog.]
Signed-off-by: Barry Song <Baohua.Song@csr.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
There is a problem with the current ordering of hibernate code which
leads to deadlocks in some filesystems' memory shrinkers. Namely,
some filesystems use freezable kernel threads that are inactive when
the hibernate memory preallocation is carried out. Those same
filesystems use memory shrinkers that may be triggered by the
hibernate memory preallocation. If those memory shrinkers wait for
the frozen kernel threads, the hibernate process deadlocks (this
happens with XFS, for one example).
Apparently, it is not technically viable to redesign the filesystems
in question to avoid the situation described above, so the only
possible solution of this issue is to defer the freezing of kernel
threads until the hibernate memory preallocation is done, which is
implemented by this change.
Unfortunately, this requires the memory preallocation to be done
before the "prepare" stage of device freeze, so after this change the
only way drivers can allocate additional memory for their freeze
routines in a clean way is to use PM notifiers.
Reported-by: Christoph <cr2005@u-club.de>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Introduce the config option CONFIG_VT_CONSOLE_SLEEP in order to cleanup
the #if defined ugliness for the vt suspend support functions. Note that
CONFIG_VT_CONSOLE is already dependant on CONFIG_VT.
The function pm_set_vt_switch is actually dependant on CONFIG_VT and not
CONFIG_PM_SLEEP. This fixes a compile error when CONFIG_PM_SLEEP is
not set:
drivers/tty/vt/vt_ioctl.c:1794: error: redefinition of 'pm_set_vt_switch'
include/linux/suspend.h:17: error: previous definition of 'pm_set_vt_switch' was here
Also, remove the incorrect path from the comment in console.c.
[rjw: Replaced #if defined() with #ifdef in suspend.h.]
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
In enter_state() we use "state" as an offset for the pm_states[]
array. The pm_states[] array only has PM_SUSPEND_MAX elements so
this test is off by one.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: stable@kernel.org
For s390 there is one additional byte associated with each page,
the storage key. This byte contains the referenced and changed
bits and needs to be included into the hibernation image.
If the storage keys are not restored to their previous state all
original pages would appear to be dirty. This can cause
inconsistencies e.g. with read-only filesystems.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Record S3 failure time about each reason and the latest two failed
devices' names in S3 progress.
We can check it through 'suspend_stats' entry in debugfs.
The motivation of the patch:
We are enabling power features on Medfield. Comparing with PC/notebook,
a mobile enters/exits suspend-2-ram (we call it s3 on Medfield) far
more frequently. If it can't enter suspend-2-ram in time, the power
might be used up soon.
We often find sometimes, a device suspend fails. Then, system retries
s3 over and over again. As display is off, testers and developers
don't know what happens.
Some testers and developers complain they don't know if system
tries suspend-2-ram, and what device fails to suspend. They need
such info for a quick check. The patch adds suspend_stats under
debugfs for users to check suspend to RAM statistics quickly.
If not using this patch, we have other methods to get info about
what device fails. One is to turn on CONFIG_PM_DEBUG, but users
would get too much info and testers need recompile the system.
In addition, dynamic debug is another good tool to dump debug info.
But it still doesn't match our utilization scenario closely.
1) user need write a user space parser to process the syslog output;
2) Our testing scenario is we leave the mobile for at least hours.
Then, check its status. No serial console available during the
testing. One is because console would be suspended, and the other
is serial console connecting with spi or HSU devices would consume
power. These devices are powered off at suspend-2-ram.
Signed-off-by: ShuoX Liu <shuox.liu@intel.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
The trace_pipe_raw handler holds a cached page from the time the file
is opened to the time it is closed. The cached page is used to handle
the case of the user space buffer being smaller than what was read from
the ring buffer. The left over buffer is held in the cache so that the
next read will continue where the data left off.
After EOF is returned (no more data in the buffer), the index of
the cached page is set to zero. If a user app reads the page again
after EOF, the check in the buffer will see that the cached page
is less than page size and will return the cached page again. This
will cause reading the trace_pipe_raw again after EOF to return
duplicate data, making the output look like the time went backwards
but instead data is just repeated.
The fix is to not reset the index right after all data is read
from the cache, but to reset it after all data is read and more
data exists in the ring buffer.
Cc: stable <stable@kernel.org>
Reported-by: Jeremy Eder <jeder@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
tracing_enabled option is deprecated.
To start/stop tracing, write to /sys/kernel/debug/tracing/tracing_on
without tracing_enabled. This patch is based on Linux 3.1.0-rc1
Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com>
Link: http://lkml.kernel.org/r/1313127022-23830-1-git-send-email-leemgs1@gmail.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
When doing intense tracing, the kmalloc inside trace_marker can
introduce side effects to what is being traced.
As trace_marker() is used by userspace to inject data into the
kernel ring buffer, it needs to do so with the least amount
of intrusion to the operations of the kernel or the user space
application.
As the ring buffer is designed to write directly into the buffer
without the need to make a temporary buffer, and userspace already
went through the hassle of knowing how big the write will be,
we can simply pin the userspace pages and write the data directly
into the buffer. This improves the impact of tracing via trace_marker
tremendously!
Thanks to Peter Zijlstra and Thomas Gleixner for pointing out the
use of get_user_pages_fast() and kmap_atomic().
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
As the function tracer is very intrusive, lots of self checks are
performed on the tracer and if something is found to be strange
it will shut itself down keeping it from corrupting the rest of the
kernel. This shutdown may still allow functions to be traced, as the
tracing only stops new modifications from happening. Trying to stop
the function tracer itself can cause more harm as it requires code
modification.
Although a WARN_ON() is executed, a user may not notice it. To help
the user see that something isn't right with the tracing of the system
a big warning is added to the output of the tracer that lets the user
know that their data may be incomplete.
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Fix kprobe-tracer not to delete a probe if the probe is in use.
In that case, delete operation will return -EBUSY.
This bug can cause a kernel panic if enabled probes are deleted
during perf record.
(Add some probes on functions)
sh-4.2# perf probe --del probe:\*
sh-4.2# exit
(kernel panic)
This is originally reported on the fedora bugzilla:
https://bugzilla.redhat.com/show_bug.cgi?id=742383
I've also checked that this problem doesn't happen on
tracepoints when module removing because perf event
locks target module.
$ sudo ./perf record -e xfs:\* -aR sh
sh-4.2# rmmod xfs
ERROR: Module xfs is in use
sh-4.2# exit
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.203 MB perf.data (~8862 samples) ]
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/20111004104438.14591.6553.stgit@fedora15
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
* pm-runtime:
PM / Tracing: build rpm-traces.c only if CONFIG_PM_RUNTIME is set
PM / Runtime: Replace dev_dbg() with trace_rpm_*()
PM / Runtime: Introduce trace points for tracing rpm_* functions
PM / Runtime: Don't run callbacks under lock for power.irq_safe set
USB: Add wakeup info to debugging messages
PM / Runtime: pm_runtime_idle() can be called in atomic context
PM / Runtime: Add macro to test for runtime PM events
PM / Runtime: Add might_sleep() to runtime PM functions
Avoid taking locks from debug prints, this avoids latencies on -rt,
and improves reliability of the debug code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The default rt-throttling is a source of never ending questions. Warn
once when we go into throttling so folks have that info in dmesg.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1110051331480.18778@ionos
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently every sched_class::set_cpus_allowed() implementation has to
copy the cpumask into task_struct::cpus_allowed, this is pointless,
put this copy in the generic code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-jhl5s9fckd9ptw1fzbqqlrd3@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This task is preparatory for the migrate_disable() implementation, but
stands on its own and provides a cleanup.
It currently only converts those sites required for task-placement.
Kosaki-san once mentioned replacing cpus_allowed with a proper
cpumask_t instead of the NR_CPUS sized array it currently is, that
would also require something like this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Link: http://lkml.kernel.org/n/tip-e42skvaddos99psip0vce41o@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
rq's idle_at_tick is set to idle/busy during the timer tick
depending on the cpu was idle or not. This will be used later in the load
balance that will be done in the softirq context (which is a process
context in -RT kernels).
For nohz kernels, for the cpu doing nohz idle load balance on behalf of
all the idle cpu's, its rq->idle_at_tick might have a stale value (which is
recorded when it got the timer tick presumably when it is busy).
As the nohz idle load balancing is also being done at the same place
as the regular load balancing, nohz idle load balancing was bailing out
when it sees rq's idle_at_tick not set.
Thus leading to poor system utilization.
Rename rq's idle_at_tick to idle_balance and set it when someone requests
for nohz idle balance on an idle cpu.
Reported-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111003220934.892350549@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Current use of smp call function to kick the nohz idle balance can deadlock
in this scenario.
1. cpu-A did a generic_exec_single() to cpu-B and after queuing its call single
data (csd) to the call single queue, cpu-A took a timer interrupt. Actual IPI
to cpu-B to process the call single queue is not yet sent.
2. As part of the timer interrupt handler, cpu-A decided to kick cpu-B
for the idle load balancing (sets cpu-B's rq->nohz_balance_kick to 1)
and __smp_call_function_single() with nowait will queue the csd to the
cpu-B's queue. But the generic_exec_single() won't send an IPI to cpu-B
as the call single queue was not empty.
3. cpu-A is busy with lot of interrupts
4. Meanwhile cpu-B is entering and exiting idle and noticed that it has
it's rq->nohz_balance_kick set to '1'. So it will go ahead and do the
idle load balancer and clear its rq->nohz_balance_kick.
5. At this point, csd queued as part of the step-2 above is still locked
and waiting to be serviced on cpu-B.
6. cpu-A is still busy with interrupt load and now it got another timer
interrupt and as part of it decided to kick cpu-B for another idle load
balancing (as it finds cpu-B's rq->nohz_balance_kick cleared in step-4
above) and does __smp_call_function_single() with the same csd that is
still locked.
7. And we get a deadlock waiting for the csd_lock() in the
__smp_call_function_single().
Main issue here is that cpu-B can service the idle load balancer kick
request from cpu-A even with out receiving the IPI and this lead to
doing multiple __smp_call_function_single() on the same csd leading to
deadlock.
To kick a cpu, scheduler already has the reschedule vector reserved. Use
that mechanism (kick_process()) instead of using the generic smp call function
mechanism to kick off the nohz idle load balancing and avoid the deadlock.
[ This issue is present from 2.6.35+ kernels, but marking it -stable
only from v3.0+ as the proposed fix depends on the scheduler_ipi()
that is introduced recently. ]
Reported-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: stable@kernel.org # v3.0+
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111003220934.834943260@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On -rt we observed hackbench waking all 400 tasks to a single cpu.
This is because of select_idle_sibling()'s interaction with the new
ipi based wakeup scheme.
The existing idle_cpu() test only checks to see if the current task on
that cpu is the idle task, it does not take already queued tasks into
account, nor does it take queued to be woken tasks into account.
If the remote wakeup IPIs come hard enough, there won't be time to
schedule away from the idle task, and would thus keep thinking the cpu
was in fact idle, regardless of the fact that there were already
several hundred tasks runnable.
We couldn't reproduce on mainline, but there's no reason it couldn't
happen.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-3o30p18b2paswpc9ohy2gltp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the generic llist primitives.
We had a private lockless list implementation in the scheduler in the wake-list
code, now that we have a generic llist implementation that provides all required
operations, switch to it.
This patch is not expected to change any behavior.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1315836353.26517.42.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
So we don't have to expose the struct list_node member.
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1315836348.26517.41.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use llist in irq_work instead of the lock-less linked list
implementation in irq_work to avoid the code duplication.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1315461646-1379-6-git-send-email-ying.huang@intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
removing obsoleted sysctl,
ip_rt_gc_interval variable no longer used since 2.6.38
Signed-off-by: Vasily Averin <vvs@sw.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
As request_percpu_irq() doesn't allow for a percpu interrupt to have
its type configured (it is generally impossible to configure it on all
CPUs at once), add a 'type' argument to enable_percpu_irq().
This allows some low-level, board specific init code to be switched to
a generic API.
[ tglx: Added WARN_ON argument ]
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Abhijeet Dharmapurikar <adharmap@codeaurora.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The ARM GIC interrupt controller offers per CPU interrupts (PPIs),
which are usually used to connect local timers to each core. Each CPU
has its own private interface to the GIC, and only sees the PPIs that
are directly connect to it.
While these timers are separate devices and have a separate interrupt
line to a core, they all use the same IRQ number.
For these devices, request_irq() is not the right API as it assumes
that an IRQ number is visible by a number of CPUs (through the
affinity setting), but makes it very awkward to express that an IRQ
number can be handled by all CPUs, and yet be a different interrupt
line on each CPU, requiring a different dev_id cookie to be passed
back to the handler.
The *_percpu_irq() functions is designed to overcome these
limitations, by providing a per-cpu dev_id vector:
int request_percpu_irq(unsigned int irq, irq_handler_t handler,
const char *devname, void __percpu *percpu_dev_id);
void free_percpu_irq(unsigned int, void __percpu *);
int setup_percpu_irq(unsigned int irq, struct irqaction *new);
void remove_percpu_irq(unsigned int irq, struct irqaction *act);
void enable_percpu_irq(unsigned int irq);
void disable_percpu_irq(unsigned int irq);
The API has a number of limitations:
- no interrupt sharing
- no threading
- common handler across all the CPUs
Once the interrupt is requested using setup_percpu_irq() or
request_percpu_irq(), it must be enabled by each core that wishes its
local interrupt to be delivered.
Based on an initial patch by Thomas Gleixner.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1316793788-14500-2-git-send-email-marc.zyngier@arm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Add two fields to task_struct.
1) account dirtied pages in the individual tasks, for accuracy
2) per-task balance_dirty_pages() call intervals, for flexibility
The balance_dirty_pages() call interval (ie. nr_dirtied_pause) will
scale near-sqrt to the safety gap between dirty pages and threshold.
The main problem of per-task nr_dirtied is, if 1k+ tasks start dirtying
pages at exactly the same time, each task will be assigned a large
initial nr_dirtied_pause, so that the dirty threshold will be exceeded
long before each task reached its nr_dirtied_pause and hence call
balance_dirty_pages().
The solution is to watch for the number of pages dirtied on each CPU in
between the calls into balance_dirty_pages(). If it exceeds ratelimit_pages
(3% dirty threshold), force call balance_dirty_pages() for a chance to
set bdi->dirty_exceeded. In normal situations, this safeguarding
condition is not expected to trigger at all.
On the sqrt in dirty_poll_interval():
It will serve as an initial guess when dirty pages are still in the
freerun area.
When dirty pages are floating inside the dirty control scope [freerun,
limit], a followup patch will use some refined dirty poll interval to
get the desired pause time.
thresh-dirty (MB) sqrt
1 16
2 22
4 32
8 45
16 64
32 90
64 128
128 181
256 256
512 362
1024 512
The above table means, given 1MB (or 1GB) gap and the dd tasks polling
balance_dirty_pages() on every 16 (or 512) pages, the dirty limit won't
be exceeded as long as there are less than 16 (or 512) concurrent dd's.
So sqrt naturally leads to less overheads and more safe concurrent tasks
for large memory servers, which have large (thresh-freerun) gaps.
peter: keep the per-CPU ratelimit for safeguarding the 1k+ tasks case
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Andrea Righi <andrea@betterlinux.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
* 'irq-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip:
irq: Fix check for already initialized irq_domain in irq_domain_add
irq: Add declaration of irq_domain_simple_ops to irqdomain.h
* 'x86-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip:
x86/rtc: Don't recursively acquire rtc_lock
* 'sched-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip:
posix-cpu-timers: Cure SMP wobbles
sched: Fix up wchan borkage
sched/rt: Migrate equal priority tasks to available CPUs
David reported:
Attached below is a watered-down version of rt/tst-cpuclock2.c from
GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or
similar.
Run it several times, and you will see cases where the main thread
will measure a process clock difference before and after the nanosleep
which is smaller than the cpu-burner thread's individual thread clock
difference. This doesn't make any sense since the cpu-burner thread
is part of the top-level process's thread group.
I've reproduced this on both x86-64 and sparc64 (using both 32-bit and
64-bit binaries).
For example:
[davem@boricha build-x86_64-linux]$ ./test
process: before(0.001221967) after(0.498624371) diff(497402404)
thread: before(0.000081692) after(0.498316431) diff(498234739)
self: before(0.001223521) after(0.001240219) diff(16698)
[davem@boricha build-x86_64-linux]$
The diff of 'process' should always be >= the diff of 'thread'.
I make sure to wrap the 'thread' clock measurements the most tightly
around the nanosleep() call, and that the 'process' clock measurements
are the outer-most ones.
---
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <fcntl.h>
#include <string.h>
#include <errno.h>
#include <pthread.h>
static pthread_barrier_t barrier;
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1)
__asm__ __volatile__("" : : : "memory");
return NULL;
}
int main(void)
{
clockid_t process_clock, my_thread_clock, th_clock;
struct timespec process_before, process_after;
struct timespec me_before, me_after;
struct timespec th_before, th_after;
struct timespec sleeptime;
unsigned long diff;
pthread_t th;
int err;
err = clock_getcpuclockid(0, &process_clock);
if (err)
return 1;
err = pthread_getcpuclockid(pthread_self(), &my_thread_clock);
if (err)
return 1;
pthread_barrier_init(&barrier, NULL, 2);
err = pthread_create(&th, NULL, chew_cpu, NULL);
if (err)
return 1;
err = pthread_getcpuclockid(th, &th_clock);
if (err)
return 1;
pthread_barrier_wait(&barrier);
err = clock_gettime(process_clock, &process_before);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_before);
if (err)
return 1;
err = clock_gettime(th_clock, &th_before);
if (err)
return 1;
sleeptime.tv_sec = 0;
sleeptime.tv_nsec = 500000000;
nanosleep(&sleeptime, NULL);
err = clock_gettime(th_clock, &th_after);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_after);
if (err)
return 1;
err = clock_gettime(process_clock, &process_after);
if (err)
return 1;
diff = process_after.tv_nsec - process_before.tv_nsec;
printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
process_before.tv_sec, process_before.tv_nsec,
process_after.tv_sec, process_after.tv_nsec, diff);
diff = th_after.tv_nsec - th_before.tv_nsec;
printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
th_before.tv_sec, th_before.tv_nsec,
th_after.tv_sec, th_after.tv_nsec, diff);
diff = me_after.tv_nsec - me_before.tv_nsec;
printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
me_before.tv_sec, me_before.tv_nsec,
me_after.tv_sec, me_after.tv_nsec, diff);
return 0;
}
This is due to us using p->se.sum_exec_runtime in
thread_group_cputime() where we iterate the thread group and sum all
data. This does not take time since the last schedule operation (tick
or otherwise) into account. We can cure this by using
task_sched_runtime() at the cost of having to take locks.
This also means we can (and must) do away with
thread_group_sched_runtime() since the modified thread_group_cputime()
is now more accurate and would deadlock when called from
thread_group_sched_runtime().
Aside of that it makes the function safe on 32 bit systems. The old
code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a
64bit value and could be changed on another cpu at the same time.
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins
Tested-by: David Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
__find_resource() incorrectly returns a resource window which overlaps
an existing allocated window. This happens when the parent's
resource-window spans 0x00000000 to 0xffffffff and is entirely allocated
to all its children resource-windows.
__find_resource() looks for gaps in resource allocation among the
children resource windows. When it encounters the last child window it
blindly tries the range next to one allocated to the last child. Since
the last child's window ends at 0xffffffff the calculation overflows,
leading the algorithm to believe that any window in the range 0x0000000
to 0xfffffff is available for allocation. This leads to a conflicting
window allocation.
Michal Ludvig reported this issue seen on his platform. The following
patch fixes the problem and has been verified by Michal. I believe this
bug has been there for ages. It got exposed by git commit 2bbc694227
("PCI : ability to relocate assigned pci-resources")
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Tested-by: Michal Ludvig <mludvig@logix.net.nz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add to the dev_state and alloc_async structures the user namespace
corresponding to the uid and euid. Pass these to kill_pid_info_as_uid(),
which can then implement a proper, user-namespace-aware uid check.
Changelog:
Sep 20: Per Oleg's suggestion: Instead of caching and passing user namespace,
uid, and euid each separately, pass a struct cred.
Sep 26: Address Alan Stern's comments: don't define a struct cred at
usbdev_open(), and take and put a cred at async_completed() to
ensure it lasts for the duration of kill_pid_info_as_cred().
Signed-off-by: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Do not build kernel/trace/rpm-traces.c if CONFIG_PM_RUNTIME is not
set, which avoids a build failure.
[rjw: Added the changelog and modified the subject slightly.]
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
It is possible for the CPU that noted the end of the prior grace period
to not need a new one, and therefore to decide to propagate ->completed
throughout the rcu_node tree without starting another grace period.
However, in so doing, it releases the root rcu_node structure's lock,
which can allow some other CPU to start another grace period. The first
CPU will be propagating ->completed in parallel with the second CPU
initializing the rcu_node tree for the new grace period. In theory
this is harmless, but in practice we need to keep things simple.
This commit therefore moves the propagation of ->completed to
rcu_report_qs_rsp(), and refrains from marking the old grace period
as having been completed until it has finished doing this. This
prevents anyone from starting a new grace period concurrently with
marking the old grace period as having been completed.
Of course, the optimization where a CPU needing a new grace period
doesn't bother marking the old one completed is still in effect:
In that case, the marking happens implicitly as part of initializing
the new grace period.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The purpose of rcu_needs_cpu_flush() was to iterate on pushing the
current grace period in order to help the current CPU enter dyntick-idle
mode. However, this can result in failures if the CPU starts entering
dyntick-idle mode, but then backs out. In this case, the call to
rcu_pending() from rcu_needs_cpu_flush() might end up announcing a
non-existing quiescent state.
This commit therefore removes rcu_needs_cpu_flush() in favor of letting
the dyntick-idle machinery at the end of the softirq handler push the
loop along via its call to rcu_pending().
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
RCU boost threads start life at RCU_BOOST_PRIO, while others remain
at RCU_KTHREAD_PRIO. While here, change thread names to match other
kthreads, and adjust rcu_yield() to not override the priority set by
the user. This last change sets the stage for runtime changes to
priority in the -rt tree.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
One of the loops in rcu_torture_boost() fails to check kthread_should_stop(),
and thus might be slowing or even stopping completion of rcutorture tests
at rmmod time. This commit adds the kthread_should_stop() check to the
offending loop.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The rcu_torture_fqs() function can prevent the rcutorture tests from
completing, resulting in a hang. This commit therefore ensures that
rcu_torture_fqs() will exit its inner loops at the end of the test,
and also applies the newish ULONG_CMP_LT() macro to time comparisons.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Create a separate lockdep class for the rt_mutex used for RCU priority
boosting and enable use of rt_mutex_lock() with irqs disabled. This
prevents RCU priority boosting from falling prey to deadlocks when
someone begins an RCU read-side critical section in preemptible state,
but releases it with an irq-disabled lock held.
Unfortunately, the scheduler's runqueue and priority-inheritance locks
still must either completely enclose or be completely enclosed by any
overlapping RCU read-side critical section.
This version removes a redundant local_irq_restore() noted by
Yong Zhang.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CPUs set rdp->qs_pending when coming online to resolve races with
grace-period start. However, this means that if RCU is idle, the
just-onlined CPU might needlessly send itself resched IPIs. Adjust
the online-CPU initialization to avoid this, and also to correctly
cause the CPU to respond to the current grace period if needed.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Josh Boyer <jwboyer@redhat.com>
Tested-by: Christian Hoffmann <email@christianhoffmann.info>
It is possible for an RCU CPU stall to end just as it is detected, in
which case the current code will uselessly dump all CPU's stacks.
This commit therefore checks for this condition and refrains from
sending needless NMIs.
And yes, the stall might also end just after we checked all CPUs and
tasks, but in that case we would at least have given some clue as
to which CPU/task was at fault.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
