gcc noticed (when using -Wempty-body) that our use of
lock_cmos() and unlock_cmos() in
arch/x86/include/asm/mach_traps.h is potentially problematic :
arch/x86/include/asm/mach_traps.h:32:15: warning: suggest braces around empty body in an ¡else¢ statement [-Wempty-body]
arch/x86/include/asm/mach_traps.h:40:16: warning: suggest braces around empty body in an ¡else¢ statement [-Wempty-body]
Let's just use the standard 'do {} while (0)' solution. That
shuts up gcc and also prevents future problems if the macros
should end up being used in a similar situation elsewhere.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1112180103130.21784@swampdragon.chaosbits.net
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If one builds the kernel with -Wempty-body one gets this
warning:
mm/memory.c:3432:46: warning: suggest braces around empty body in an ¡if¢ statement [-Wempty-body]
due to the fact that 'flush_tlb_fix_spurious_fault' is a macro
that can sometimes be defined to nothing.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: linux-mm@kvack.org
Cc: Michel Lespinasse <walken@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1112180128070.21784@swampdragon.chaosbits.net
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add an upper limit to balanced_rate according to the below inequality.
This filters out some rare but huge singular points, which at least
enables more readable gnuplot figures.
When there are N dd dirtiers,
balanced_dirty_ratelimit = write_bw / N
So it holds that
balanced_dirty_ratelimit <= write_bw
The singular points originate from dirty_rate in the below formular:
balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate
where
dirty_rate = (number of page dirties in the past 200ms) / 200ms
In the extreme case, if all dd tasks suddenly get blocked on something
else and hence no pages are dirtied at all, dirty_rate will be 0 and
balanced_dirty_ratelimit will be inf. This could happen in reality.
Note that these huge singular points are not a real threat, since they
are _guaranteed_ to be filtered out by the
min(balanced_dirty_ratelimit, task_ratelimit)
line in bdi_update_dirty_ratelimit(). task_ratelimit is based on the
number of dirty pages, which will never _suddenly_ fly away like
balanced_dirty_ratelimit. So any weirdly large balanced_dirty_ratelimit
will be cut down to the level of task_ratelimit.
There won't be tiny singular points though, as long as the dirty pages
lie inside the dirty throttling region (above the freerun region).
Because there the dd tasks will be throttled by balanced_dirty_pages()
and won't be able to suddenly dirty much more pages than average.
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
This helps to reduce dirty throttling polls and hence CPU overheads.
bdi->dirty_exceeded typically only helps when suddenly starting 100+
dd's on a disk, in which case the dd's may need to poll
balance_dirty_pages() earlier than tsk->nr_dirtied_pause.
CC: Jan Kara <jack@suse.cz>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
The LKP tests see big 56% regression for the case fio_mmap_randwrite_64k.
Shaohua manages to root cause it to be the much smaller dirty pause times
and hence much more frequent invocations to the IO-less balance_dirty_pages().
Since fio_mmap_randwrite_64k effectively contains both reads and writes,
the more frequent pauses triggered more idling in the cfq IO scheduler.
The solution is to increase pause time all the way up to the max 200ms
in this case, which is found to restore most performance. This will help
reduce CPU overheads in other cases, too.
Note that I don't expect many performance critical workloads to run this
access pattern: the mmap read-on-write is rather inefficient and could
be avoided by doing normal writes syscalls.
CC: Jan Kara <jack@suse.cz>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reported-by: Li Shaohua <shaohua.li@intel.com>
Tested-by: Li Shaohua <shaohua.li@intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Control the pause time and the call intervals to balance_dirty_pages()
with three parameters:
1) max_pause, limited by bdi_dirty and MAX_PAUSE
2) the target pause time, grows with the number of dd tasks
and is normally limited by max_pause/2
3) the minimal pause, set to half the target pause
and is used to skip short sleeps and accumulate them into bigger ones
The typical behaviors after patch:
- if ever task_ratelimit is far below dirty_ratelimit, the pause time
will remain constant at max_pause and nr_dirtied_pause will be
fluctuating with task_ratelimit
- in the normal cases, nr_dirtied_pause will remain stable (keep in the
same pace with dirty_ratelimit) and the pause time will be fluctuating
with task_ratelimit
In summary, someone has to fluctuate with task_ratelimit, because
task_ratelimit = nr_dirtied_pause / pause
We normally prefer a stable nr_dirtied_pause, until reaching max_pause.
The notable behavior changes are:
- in stable workloads, there will no longer be sudden big trajectory
switching of nr_dirtied_pause as concerned by Peter. It will be as
smooth as dirty_ratelimit and changing proportionally with it (as
always, assuming bdi bandwidth does not fluctuate across 2^N lines,
otherwise nr_dirtied_pause will show up in 2+ parallel trajectories)
- in the rare cases when something keeps task_ratelimit far below
dirty_ratelimit, the smoothness can no longer be retained and
nr_dirtied_pause will be "dancing" with task_ratelimit. This fixes a
(not that destructive but still not good) bug that
dirty_ratelimit gets brought down undesirably
<= balanced_dirty_ratelimit is under estimated
<= weakly executed task_ratelimit
<= pause goes too large and gets trimmed down to max_pause
<= nr_dirtied_pause (based on dirty_ratelimit) is set too large
<= dirty_ratelimit being much larger than task_ratelimit
- introduce min_pause to avoid small pause sleeps
- when pause is trimmed down to max_pause, try to compensate it at the
next pause time
The "refactor" type of changes are:
The max_pause equation is slightly transformed to make it slightly more
efficient.
We now scale target_pause by (N * 10ms) on 2^N concurrent tasks, which
is effectively equal to the original scaling max_pause by (N * 20ms)
because the original code does implicit target_pause ~= max_pause / 2.
Based on the same implicit ratio, target_pause starts with 10ms on 1 dd.
CC: Jan Kara <jack@suse.cz>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Compensate the task's think time when computing the final pause time,
so that ->dirty_ratelimit can be executed accurately.
think time := time spend outside of balance_dirty_pages()
In the rare case that the task slept longer than the 200ms period time
(result in negative pause time), the sleep time will be compensated in
the following periods, too, if it's less than 1 second.
Accumulated errors are carefully avoided as long as the max pause area
is not hitted.
Pseudo code:
period = pages_dirtied / task_ratelimit;
think = jiffies - dirty_paused_when;
pause = period - think;
1) normal case: period > think
pause = period - think
dirty_paused_when = jiffies + pause
nr_dirtied = 0
period time
|===============================>|
think time pause time
|===============>|==============>|
------|----------------|---------------|------------------------
dirty_paused_when jiffies
2) no pause case: period <= think
don't pause; reduce future pause time by:
dirty_paused_when += period
nr_dirtied = 0
period time
|===============================>|
think time
|===================================================>|
------|--------------------------------+-------------------|----
dirty_paused_when jiffies
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
When doing 1KB sequential writes to the same page,
balance_dirty_pages_ratelimited_nr() should be called once instead of 4
times, the latter makes the dirtier tasks be throttled much too heavy.
Fix it with proper de-accounting on clear_page_dirty_for_io().
CC: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
De-account the accumulative dirty counters on page redirty.
Page redirties (very common in ext4) will introduce mismatch between
counters (a) and (b)
a) NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied
b) NR_WRITTEN, BDI_WRITTEN
This will introduce systematic errors in balanced_rate and result in
dirty page position errors (ie. the dirty pages are no longer balanced
around the global/bdi setpoints).
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
When dd in 512bytes, generic_perform_write() calls
balance_dirty_pages_ratelimited() 8 times for the same page, but
obviously the page is only dirtied once.
Fix it by accounting tsk->nr_dirtied and bdp_ratelimits at page dirty time.
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
It's a years long problem that a large number of short-lived dirtiers
(eg. gcc instances in a fast kernel build) may starve long-run dirtiers
(eg. dd) as well as pushing the dirty pages to the global hard limit.
The solution is to charge the pages dirtied by the exited gcc to the
other random dirtying tasks. It sounds not perfect, however should
behave good enough in practice, seeing as that throttled tasks aren't
actually running so those that are running are more likely to pick it up
and get throttled, therefore promoting an equal spread.
Randy: fix compile error: 'dirty_throttle_leaks' undeclared in exit.c
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Current livelock avoidance code makes background work to include only inodes
that were dirtied before background writeback has started. However background
writeback can be running for a long time and thus excluding newly dirtied
inodes can eventually exclude significant portion of dirty inodes making
background writeback inefficient. Since background writeback avoids livelocking
the flusher thread by yielding to any other work, there is no real reason why
background work should not include all dirty inodes so change the logic in
wb_writeback().
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
This makes the binary trace understandable by trace-cmd.
CC: Dave Chinner <david@fromorbit.com>
CC: Curt Wohlgemuth <curtw@google.com>
CC: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Add support for the tegra30 based cardhu development board. Cardhu is a tablet
formfactor reference design for tegra30. The patch provides a device tree for
the board, updates Makefile.boot to build the dtb, includes the platform in
Kconfig and updates board-dt.c.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Add support for tegra30 SoC. This includes a device tree compatible type for
this SoC ("nvidia,tegra30") and adds L2 cache initialization for this new SoC.
The clock framework is still missing, which prevents most drivers from working.
The basic IRQs are the same, so remove the dependency on
CONFIG_ARCH_TEGRA_2x_SOC.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Define the pinmuxing and pindrive tables for tegra30. The pinmux table defines
the available functions for each pinmux group. The pindrive table defines the
default pullup or pulldowns for each group.
Derived from code by Scott Williams (scwilliams@nvidia.com)
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Add new fields to struct tegra_pingroup_desc to support new hardware features
introduced in the tegra30 SoC. The pinmux driver won't use those fields yet,
but the tegra30 pinmux tables will already provide the necessary data.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
This patch modifies the pinmux code to be useable for multiple tegra variants.
Some tegra20 specific constants will be replaced by variables which will be
initialized to the appropriate value at runtime.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Rename pinmux-t2.h and pinmux-t2-tables.c to the new tegra naming. This file
will be reworked somewhat in the next patch to support multiple tegra SoC
types.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Generalize L2 cache initialization and discover L2 cache associativity at
runtime.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Use PMC reset rather then CAR system reset as recommended by the hardware
team.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Tegra20 based boards will be handled by the current board-dt.c file. Tegra30
based boards will be handled by a new board-dt-tegra30.c file. Hence rename
the existing board-dt.c to board-dt-tegra20.c to reflect its use.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
This patch splits the early init code in a common and a tegra20 specific part.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
don't export clk_measure_input_freq as its functionality is also available
using clk_get_rate().
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Rework the tegra20 clock code to support multiple tegra variants :
* remove tegra2_periph_reset_assert/tegra2_periph_reset_deassert. This
functionality should be in clock.c.
* remove tegra_sdmmc_tap_delay and export tegra2_sdmmc_tap_delay
directly. This feature is handled inside the sdmmc block from tegra30
onwards. So there is no need for support in the clock code beyond
tegra20. There are no in tree users of this function.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
* add a dependency to ARCH_TEGRA_2x_SOC in Kconfig to all tegra20 based boards
and TEGRA_PCI
* make powergating dependent on ARCH_TEGRA_2x_SOC
* remove dependency on ARCH_TEGRA_2x_SOC for clock.c
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
The timer and rtc-timer clocks aren't gated by default, so there is no reason
to crash the system if the dummy enable call failed.
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Use the expect tuple (if possible) instead of the master tuple for
the get operation. If two or more expectations come from the same
master, the returned expectation may not be the one that user-space
is requesting.
This is how it works for the expect deletion operation.
Although I think that nobody has been seriously using this. We
accept both possibilities, using the expect tuple if possible.
I decided to do it like this to avoid breaking backward
compatibility.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
We can use atomic64_t infrastructure to avoid taking a spinlock in fast
path, and remove inaccuracies while reading values in
ctnetlink_dump_counters() and connbytes_mt() on 32bit arches.
Suggested by Pablo.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Hauppauge RC-5 tables require the full scancodes. The code at budget-ci
handles it right, however, it request the rc-code to mask them with 0xff,
breaking support for some remote controllers.
Fix it by not selecting a scancode mask when the driver is on full_rc5 mode.
Reported-by: Brian May <brian@microcomaustralia.com.au>
Tested-by: Brian May <brian@microcomaustralia.com.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
This patch adds the initial device tree for tegra30
Signed-off-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Stephen Warren <swarren@nvidia.com>
Acked-by: Colin Cross <ccross@android.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
After the change that removed the code related to runtime PM
from __pm_generic_call() and __pm_generic_resume() these two
functions need not be separate any more, so merge them.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
The pm_runtime_suspended() check in __pm_generic_call() doesn't
really help and may cause problems to happen, because in some cases
the system suspend callbacks need to be called even if the given
device has been suspended by runtime PM. For example, if the device
generally supports remote wakeup and is not enabled to wake up
the system from sleep, it should be prevented from generating wakeup
signals during system suspend and that has to be done by the
suspend callbacks that the pm_runtime_suspended() check prevents from
being executed.
Similarly, it may not be a good idea to unconditionally change
the runtime PM status of the device to 'active' in
__pm_generic_resume(), because the driver may want to leave the
device in the 'suspended' state, depending on what happened to it
before the system suspend and whether or not it is enabled to
wake up the system.
For the above reasons, remove the pm_runtime_suspended()
check from __pm_generic_call() and remove the code changing the
device's runtime PM status from __pm_generic_resume().
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf events: Fix ring_buffer_wakeup() brown paperbag bug
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: Fix select_idle_sibling() regression in selecting an idle SMT sibling
MAINTAINERS: Update tip.git related git trees
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci:
PCI: Set device power state to PCI_D0 for device without native PM support
PCI hotplug: Always allow acpiphp to handle non-PCIe bridges
PCI: fix ats compile failure
PCI: defer enablement of SRIOV BARS
We write the reset register with the default value so it should not be
mistakenly written.
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Use snd_soc_register_card() instead of creating a "soc-audio" platform device.
Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
