03 Feb, 2009
3 commits
-
Conflicts:
drivers/net/Kconfig -
…l/git/tip/linux-2.6-tip
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
sched_rt: don't use first_cpu on cpumask created with cpumask_and
sched: fix buddie group latency
sched: clear buddies more aggressively
sched: symmetric sync vs avg_overlap
sched: fix sync wakeups
cpuset: fix possible deadlock in async_rebuild_sched_domains -
Current refcounting for modules (done if CONFIG_MODULE_UNLOAD=y) is
using a lot of memory.Each 'struct module' contains an [NR_CPUS] array of full cache lines.
This patch uses existing infrastructure (percpu_modalloc() &
percpu_modfree()) to allocate percpu space for the refcount storage.Instead of wasting NR_CPUS*128 bytes (on i386), we now use
nr_cpu_ids*sizeof(local_t) bytes.On a typical distro, where NR_CPUS=8, shiping 2000 modules, we reduce
size of module files by about 2 Mbytes. (1Kb per module)Instead of having all refcounters in the same memory node - with TLB misses
because of vmalloc() - this new implementation permits to have better
NUMA properties, since each CPU will use storage on its preferred node,
thanks to percpu storage.Signed-off-by: Eric Dumazet
Signed-off-by: Rusty Russell
Signed-off-by: Linus Torvalds
01 Feb, 2009
10 commits
-
cpumask_and() only initializes nr_cpu_ids bits, so the (deprecated)
first_cpu() might find one of those uninitialized bits if nr_cpu_ids
is less than NR_CPUS (as it can be for CONFIG_CPUMASK_OFFSTACK).Signed-off-by: Rusty Russell
Signed-off-by: Ingo Molnar -
Similar to the previous patch, by not clearing buddies we can select entities
past their run quota, which can increase latency. This means we have to clear
group buddies as well.Do not use the group clear for pick_next_task(), otherwise that'll get O(n^2).
Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar -
It was noticed that a task could get re-elected past its run quota due to buddy
affinities. This could increase latency a little. Cure it by more aggresively
clearing buddy state.We do so in two situations:
- when we force preempt
- when we select a buddy to runSigned-off-by: Mike Galbraith
Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar -
Reinstate the weakening of the sync hint if set. This yields a more
symmetric usage of avg_overlap.Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar -
Pawel Dziekonski reported that the openssl benchmark and his
quantum chemistry application both show slowdowns due to the
scheduler under-parallelizing execution.The reason are pipe wakeups still doing 'sync' wakeups which
overrides the normal buddy wakeup logic - even if waker and
wakee are loosely coupled.Fix an inversion of logic in the buddy wakeup code.
Reported-by: Pawel Dziekonski
Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar -
This adds another inet device option to enable gratuitous ARP
when device is brought up or address change. This is handy for
clusters or virtualization.Signed-off-by: Stephen Hemminger
Signed-off-by: Jeremy Fitzhardinge
Signed-off-by: David S. Miller -
…/git/tip/linux-2.6-tip
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
generic-ipi: use per cpu data for single cpu ipi calls
cpumask: convert lib/smp_processor_id to new cpumask ops
signals, debug: fix BUG: using smp_processor_id() in preemptible code in print_fatal_signal() -
…git/tip/linux-2.6-tip
* 'irq-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
irq: export __set_irq_handler() and handle_level_irq() -
…el/git/tip/linux-2.6-tip
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
hrtimer: prevent negative expiry value after clock_was_set()
hrtimers: allow the hot-unplugging of all cpus
hrtimers: increase clock min delta threshold while interrupt hanging -
…nel/git/tip/linux-2.6-tip
* 'tracing-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, ds, bts: cleanup/fix DS configuration
ring-buffer: reset timestamps when ring buffer is reset
trace: set max latency variable to zero on default
trace: stop all recording to ring buffer on ftrace_dump
trace: print ftrace_dump at KERN_EMERG log level
ring_buffer: reset write when reserve buffer fail
tracing/function-graph-tracer: fix a regression while suspend to disk
ring-buffer: fix alignment problem
31 Jan, 2009
4 commits
-
Impact: prevent false positive WARN_ON() in clockevents_program_event()
clock_was_set() changes the base->offset of CLOCK_REALTIME and
enforces the reprogramming of the clockevent device to expire timers
which are based on CLOCK_REALTIME. If the clock change is large enough
then the subtraction of the timer expiry value and base->offset can
become negative which triggers the warning in
clockevents_program_event().Check the subtraction result and set a negative value to 0.
Signed-off-by: Thomas Gleixner
-
Impact: fix CPU hotplug hang on Power6 testbox
On architectures that support offlining all cpus (at least powerpc/pseries),
hot-unpluging the tick_do_timer_cpu can result in a system hang.This comes from the fact that if the cpu going down happens to be the
cpu doing the tick, then as the tick_do_timer_cpu handover happens after the
cpu is dead (via the CPU_DEAD notification), we're left without ticks,
jiffies are frozen and any task relying on timers (msleep, ...) is stuck.
That's particularly the case for the cpu looping in __cpu_die() waiting
for the dying cpu to be dead.This patch addresses this by having the tick_do_timer_cpu handover happen
earlier during the CPU_DYING notification. For this, a new clockevent
notification type is introduced (CLOCK_EVT_NOTIFY_CPU_DYING) which is triggered
in hrtimer_cpu_notify().Signed-off-by: Sebastien Dugue
Cc:
Signed-off-by: Ingo Molnar -
Impact: avoid timer IRQ hanging slow systems
While using the function graph tracer on a virtualized system, the
hrtimer_interrupt can hang the system on an infinite loop.This can be caused in several situations:
- the hardware is very slow and HZ is set too high
- something intrusive is slowing the system down (tracing under emulation)
... and the next clock events to program are always before the current time.
This patch implements a reasonable compromise: if such a situation is
detected, we share the CPUs time in 1/4 to process the hrtimer interrupts.
This is enough to let the system running without serious starvation.It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ
with function graph tracer launched. On both cases, the clock events were
increased until about 25 ms periodic ticks, which means 40 HZ.So we change a hard to debug hang into a warning message and a system that
still manages to limp along.Signed-off-by: Frederic Weisbecker
Signed-off-by: Ingo Molnar -
The smp_call_function can be passed a wait parameter telling it to
wait for all the functions running on other CPUs to complete before
returning, or to return without waiting. Unfortunately, this is
currently just a suggestion and not manditory. That is, the
smp_call_function can decide not to return and wait instead.The reason for this is because it uses kmalloc to allocate storage
to send to the called CPU and that CPU will free it when it is done.
But if we fail to allocate the storage, the stack is used instead.
This means we must wait for the called CPU to finish before
continuing.Unfortunatly, some callers do no abide by this hint and act as if
the non-wait option is mandatory. The MTRR code for instance will
deadlock if the smp_call_function is set to wait. This is because
the smp_call_function will wait for the other CPUs to finish their
called functions, but those functions are waiting on the caller to
continue.This patch changes the generic smp_call_function code to use per cpu
variables if the allocation of the data fails for a single CPU call. The
smp_call_function_many will fall back to the smp_call_function_single
if it fails its alloc. The smp_call_function_single is modified
to not force the wait state.Since we now are using a single data per cpu we must synchronize the
callers to prevent a second caller modifying the data before the
first called IPI functions complete. To do so, I added a flag to
the call_single_data called CSD_FLAG_LOCK. When the single CPU is
called (which can be called when a many call fails an alloc), we
set the LOCK bit on this per cpu data. When the caller finishes
it clears the LOCK bit.The caller must wait till the LOCK bit is cleared before setting
it. When it is cleared, there is no IPI function using it.Signed-off-by: Steven Rostedt
Signed-off-by: Peter Zijlstra
Acked-by: Jens Axboe
Acked-by: Linus Torvalds
Signed-off-by: Ingo Molnar
30 Jan, 2009
4 commits
-
root_count was being incremented in cgroup_get_sb() after all error
checking was complete, but decremented in cgroup_kill_sb(), which can be
called on a superblock that we gave up on due to an error. This patch
changes cgroup_kill_sb() to only decrement root_count if the root was
previously linked into the list of roots.Signed-off-by: Paul Menage
Tested-by: Serge Hallyn
Cc: Ingo Molnar
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
css_tryget() and cgroup_clear_css_refs() contain polling loops; these
loops should have cpu_relax calls in them to reduce cross-cache traffic.Signed-off-by: Paul Menage
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
I fixed a bug in cgroup_clone() in Linus' tree in commit 7b574b7
("cgroups: fix a race between cgroup_clone and umount") without noticing
there was a cleanup patch in -mm tree that should be rebased (now commit
104cbd5, "cgroups: use task_lock() for access tsk->cgroups safe in
cgroup_clone()"), thus resulted in lock inconsistency.Signed-off-by: Li Zefan
Acked-by: Paul Menage
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Now, cgrp->sibling is handled under hierarchy mutex.
error route should do so, too.Signed-off-by: KAMEZAWA Hiroyuki
Cc: Li Zefan
Acked-by Paul Menage
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
28 Jan, 2009
2 commits
-
Move the initialization of irq_default_affinity to early_irq_init as
core_initcall is too late.irq_default_affinity can be used in init_IRQ and potentially timer and
SMP init as well. All of these happen before core_initcall. Moving
the initialization to early_irq_init ensures that it is initialized
before it is used.Signed-off-by: David Daney
Acked-by: Mike Travis
Signed-off-by: Linus Torvalds -
In interrupt.h these functions are declared only if
CONFIG_GENERIC_HARDIRQS is set. We should define them under identical
conditions.Signed-off-by: David Daney
Signed-off-by: Linus Torvalds
27 Jan, 2009
8 commits
-
* 'hibern_fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev:
SATA PIIX: Blacklist system that spins off disks during ACPI power off
SATA Sil: Blacklist system that spins off disks during ACPI power off
SATA AHCI: Blacklist system that spins off disks during ACPI power off
SATA: Blacklisting of systems that spin off disks during ACPI power off
DMI: Introduce dmi_first_match to make the interface more flexible
Hibernation: Introduce system_entering_hibernation -
Introduce boolean function system_entering_hibernation() returning
'true' during the last phase of hibernation, in which devices are
being put into low power states and the sleep state (for example,
ACPI S4) is finally entered.Some device drivers need such a function to check if the system is
in the final phase of hibernation. In particular, some SATA drivers
are going to use it for blacklisting systems in which the disks
should not be spun down during the last phase of hibernation (the
BIOS will do that anyway).Signed-off-by: Rafael J. Wysocki
Signed-off-by: Jeff Garzik -
With print-fatal-signals=1 on a kernel with CONFIG_PREEMPT=y, sending an
unexpected signal to a process causes a BUG: using smp_processor_id() in
preemptible code.get_signal_to_deliver() releases the siglock before calling
print_fatal_signal(), which calls show_regs(), which calls
smp_processor_id(), which is not supposed to be called from a
preemptible thread.Make sure show_regs() runs with preemption disabled.
Signed-off-by: Ed Swierk
Signed-off-by: Ingo Molnar -
* git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes:
kbuild: fix kbuild.txt typos
kbuild: print usage with no arguments in scripts/config
Revert "kbuild: strip generated symbols from *.ko" -
* 'sh/for-2.6.29' of git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (22 commits)
dma-coherent: Restore dma_alloc_from_coherent() large alloc fall back policy.
dma-coherent: per-device coherent area is in pages, not bytes.
sh: fix unaligned and nonexistent address handling
nommu: Stub in vm_map_ram()/vm_unmap_ram()/vm_unmap_aliases().
sh: fix sh-sci / early printk build on sh7723
sh: export the sh7343 JPU to user space
sh: update defconfigs.
serial: sh-sci: Fix up SH7720/SH7721 SCI build.
sh: Kill off obsolete busses from arch/sh/Kconfig.
sh: sh7785lcr/highlander/hp6xx need linux/irq.h.
sh: Migo-R MMC support using spi_gpio and mmc_spi.
sh: ap325rxa MMC support using spi_gpio and mmc_spi
sh: mach-x3proto: needs linux/irq.h.
sh: Drop the BKL from sys_execve() on SH-5.
sh: convert rsk7203 to use smsc911x.
sh: convert magicpanelr2 platform to use smsc911x.
sh: convert ap325rxa platform to use smsc911x.
sh: mach-migor: Add tw9910 support.
sh: mach-migor: Delete soc_camera_platform setup.
sh: mach-migor: Add ov772x support.
... -
…/git/tip/linux-2.6-tip
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
debugobjects: add and use INIT_WORK_ON_STACK
rcu: remove duplicate CONFIG_RCU_CPU_STALL_DETECTOR
relay: fix lock imbalance in relay_late_setup_files
oprofile: fix uninitialized use of struct op_entry
rcu: move Kconfig menu
softlock: fix false panic which can occur if softlockup_thresh is reduced
rcu: add __cpuinit to rcu_init_percpu_data() -
…el/git/tip/linux-2.6-tip
* 'timers-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
hrtimers: fix inconsistent lock state on resume in hres_timers_resume
time-sched.c: tick_nohz_update_jiffies should be static
locking, hpet: annotate false positive warning
kernel/fork.c: unused variable 'ret'
itimers: remove the per-cpu-ish-ness -
…git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (29 commits)
xen: unitialised return value in xenbus_write_transaction
x86: fix section mismatch warning
x86: unmask CPUID levels on Intel CPUs, fix
x86: work around PAGE_KERNEL_WC not getting WC in iomap_atomic_prot_pfn.
x86: use standard PIT frequency
xen: handle highmem pages correctly when shrinking a domain
x86, mm: fix pte_free()
xen: actually release memory when shrinking domain
x86: unmask CPUID levels on Intel CPUs
x86: add MSR_IA32_MISC_ENABLE bits to <asm/msr-index.h>
x86: fix PTE corruption issue while mapping RAM using /dev/mem
x86: mtrr fix debug boot parameter
x86: fix page attribute corruption with cpa()
Revert "x86: signal: change type of paramter for sys_rt_sigreturn()"
x86: use early clobbers in usercopy*.c
x86: remove kernel_physical_mapping_init() from init section
fix: crash: IP: __bitmap_intersects+0x48/0x73
cpufreq: use work_on_cpu in acpi-cpufreq.c for drv_read and drv_write
work_on_cpu: Use our own workqueue.
work_on_cpu: don't try to get_online_cpus() in work_on_cpu.
...
22 Jan, 2009
2 commits
-
Impact: fix bad times of recent resets
The ring buffer needs to reset its timestamps when reseting of the
buffer, otherwise the timestamps are stale and might be used to
calculate times in the buffer causing funny timestamps to appear.Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar
21 Jan, 2009
7 commits
-
Impact: trace max latencies on start of latency tracing
This patch sets the max latency to zero whenever one of the
irq variant tracers or the wakeup tracer is set to current tracer.Most developers expect to see output when starting up a latency
tracer. But since the max_latency is already set to max, and
it takes a latency greater than max_latency to be recorded, there
is no trace. This is not the expected behavior and has even confused
myself.Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar -
Impact: limit ftrace dump output
Currently ftrace_dump only calls ftrace_kill that is a fast way
to prevent the function tracer functions from being called (just sets
a flag and clears the function to call, nothing else). It is better
to also turn off any recording to the ring buffers as well.Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar -
Impact: fix to print out ftrace_dump when expected
I was debugging a hard race condition to only find out that
after I hit the race, my log level was not at level to show
KERN_INFO. The time it took to trigger the race was wasted because
I did not capture the trace.Since ftrace_dump is only called from kernel oops (and only when
it is set in the kernel command line to do so), or when a
developer adds it to their own local tree, the log level of
the print should be at KERN_EMERG to make sure the print appears.ftrace_dump is not called by a normal user setup, and will not
add extra unwanted print out to the console. There is no reason
it should be at KERN_INFO.Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar -
Impact: reset struct buffer_page.write when interrupt storm
if struct buffer_page.write is not reset, any succedent committing
will corrupted ring_buffer:static inline void
rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
......
cpu_buffer->commit_page->commit =
cpu_buffer->commit_page->write;
......
}when "if (RB_WARN_ON(cpu_buffer, next_page == reader_page))", ring_buffer
is disabled, but some reserved buffers may haven't been committed.
we need reset struct buffer_page.write.when "if (unlikely(next_page == cpu_buffer->commit_page))", ring_buffer
is still available, we should not corrupt it.Signed-off-by: Lai Jiangshan
Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar -
Impact: fix a crash while kernel image restore
When the function graph tracer is running and while suspend to disk, some racy
and dangerous things happen against this tracer.The current task will save its registers including the stack pointer which
contains the return address hooked by the tracer. But the current task will
continue to enter other functions after that to save the memory, and then
it will store other return addresses, and finally loose the old depth which
matches the return address saved in the old stack (during the registers saving).So on image restore, the code will return to wrong addresses.
And there are other things: on restore, the task will have it's "current"
pointer overwritten during registers restoring....switching from one task to
another... That would be insane to try to trace function graphs at these
stages.This patch makes the function graph tracer listening on power events, making
it's tracing disabled for the current task (the one that performs the
hibernation work) while suspend/resume to disk, making the tracing safe
during hibernation.Signed-off-by: Frederic Weisbecker
Signed-off-by: Steven Rostedt
Signed-off-by: Ingo Molnar -
When doing large allocations (larger than the per-device coherent area)
the generic memory allocators are silently fallen back on regardless of
consideration for the per-device constraints.In the DMA_MEMORY_EXCLUSIVE case falling back on generic memory is not
an option, as it tends not to be addressable by the DMA hardware in
question. This issue showed up with the 8139too breakage on the
Dreamcast, where non-addressable buffers were silently allocated due to
the size mismatch calculation -- while it should have simply errored out
upon being unable to satisfy the allocation with the given device
constraints.This restores fall back behaviour to what it was before the oversized
request change caused multiple regressions.Signed-off-by: Paul Mundt
-
Commit 58c6d3dfe436eb8cfb451981d8fdc9044eaf42da ("dma-coherent: catch
oversized requests to dma_alloc_from_coherent()") attempted to add a
sanity check to bail out on allocations larger than the coherent area.Unfortunately when this was implemented, the fact the coherent area
is tracked in pages rather than bytes was overlooked, which subsequently
broke every single dma_alloc_from_coherent() user, forcing the allocation
silently through generic memory instead.Signed-off-by: Adrian McMenamin
Signed-off-by: Paul Mundt
