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>
As proposed by Chris, Dave and Jan, don't start foreground writeback IO
inside balance_dirty_pages(). Instead, simply let it idle sleep for some
time to throttle the dirtying task. In the mean while, kick off the
per-bdi flusher thread to do background writeback IO.
RATIONALS
=========
- disk seeks on concurrent writeback of multiple inodes (Dave Chinner)
If every thread doing writes and being throttled start foreground
writeback, it leads to N IO submitters from at least N different
inodes at the same time, end up with N different sets of IO being
issued with potentially zero locality to each other, resulting in
much lower elevator sort/merge efficiency and hence we seek the disk
all over the place to service the different sets of IO.
OTOH, if there is only one submission thread, it doesn't jump between
inodes in the same way when congestion clears - it keeps writing to
the same inode, resulting in large related chunks of sequential IOs
being issued to the disk. This is more efficient than the above
foreground writeback because the elevator works better and the disk
seeks less.
- lock contention and cache bouncing on concurrent IO submitters (Dave Chinner)
With this patchset, the fs_mark benchmark on a 12-drive software RAID0 goes
from CPU bound to IO bound, freeing "3-4 CPUs worth of spinlock contention".
* "CPU usage has dropped by ~55%", "it certainly appears that most of
the CPU time saving comes from the removal of contention on the
inode_wb_list_lock" (IMHO at least 10% comes from the reduction of
cacheline bouncing, because the new code is able to call much less
frequently into balance_dirty_pages() and hence access the global
page states)
* the user space "App overhead" is reduced by 20%, by avoiding the
cacheline pollution by the complex writeback code path
* "for a ~5% throughput reduction", "the number of write IOs have
dropped by ~25%", and the elapsed time reduced from 41:42.17 to
40:53.23.
* On a simple test of 100 dd, it reduces the CPU %system time from 30% to 3%,
and improves IO throughput from 38MB/s to 42MB/s.
- IO size too small for fast arrays and too large for slow USB sticks
The write_chunk used by current balance_dirty_pages() cannot be
directly set to some large value (eg. 128MB) for better IO efficiency.
Because it could lead to more than 1 second user perceivable stalls.
Even the current 4MB write size may be too large for slow USB sticks.
The fact that balance_dirty_pages() starts IO on itself couples the
IO size to wait time, which makes it hard to do suitable IO size while
keeping the wait time under control.
Now it's possible to increase writeback chunk size proportional to the
disk bandwidth. In a simple test of 50 dd's on XFS, 1-HDD, 3GB ram,
the larger writeback size dramatically reduces the seek count to 1/10
(far beyond my expectation) and improves the write throughput by 24%.
- long block time in balance_dirty_pages() hurts desktop responsiveness
Many of us may have the experience: it often takes a couple of seconds
or even long time to stop a heavy writing dd/cp/tar command with
Ctrl-C or "kill -9".
- IO pipeline broken by bumpy write() progress
There are a broad class of "loop {read(buf); write(buf);}" applications
whose read() pipeline will be under-utilized or even come to a stop if
the write()s have long latencies _or_ don't progress in a constant rate.
The current threshold based throttling inherently transfers the large
low level IO completion fluctuations to bumpy application write()s,
and further deteriorates with increasing number of dirtiers and/or bdi's.
For example, when doing 50 dd's + 1 remote rsync to an XFS partition,
the rsync progresses very bumpy in legacy kernel, and throughput is
improved by 67% by this patchset. (plus the larger write chunk size,
it will be 93% speedup).
The new rate based throttling can support 1000+ dd's with excellent
smoothness, low latency and low overheads.
For the above reasons, it's much better to do IO-less and low latency
pauses in balance_dirty_pages().
Jan Kara, Dave Chinner and me explored the scheme to let
balance_dirty_pages() wait for enough writeback IO completions to
safeguard the dirty limit. However it's found to have two problems:
- in large NUMA systems, the per-cpu counters may have big accounting
errors, leading to big throttle wait time and jitters.
- NFS may kill large amount of unstable pages with one single COMMIT.
Because NFS server serves COMMIT with expensive fsync() IOs, it is
desirable to delay and reduce the number of COMMITs. So it's not
likely to optimize away such kind of bursty IO completions, and the
resulted large (and tiny) stall times in IO completion based throttling.
So here is a pause time oriented approach, which tries to control the
pause time in each balance_dirty_pages() invocations, by controlling
the number of pages dirtied before calling balance_dirty_pages(), for
smooth and efficient dirty throttling:
- avoid useless (eg. zero pause time) balance_dirty_pages() calls
- avoid too small pause time (less than 4ms, which burns CPU power)
- avoid too large pause time (more than 200ms, which hurts responsiveness)
- avoid big fluctuations of pause times
It can control pause times at will. The default policy (in a followup
patch) will be to do ~10ms pauses in 1-dd case, and increase to ~100ms
in 1000-dd case.
BEHAVIOR CHANGE
===============
(1) dirty threshold
Users will notice that the applications will get throttled once crossing
the global (background + dirty)/2=15% threshold, and then balanced around
17.5%. Before patch, the behavior is to just throttle it at 20% dirtyable
memory in 1-dd case.
Since the task will be soft throttled earlier than before, it may be
perceived by end users as performance "slow down" if his application
happens to dirty more than 15% dirtyable memory.
(2) smoothness/responsiveness
Users will notice a more responsive system during heavy writeback.
"killall dd" will take effect instantly.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
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>
There are some imperfections in balanced_dirty_ratelimit.
1) large fluctuations
The dirty_rate used for computing balanced_dirty_ratelimit is merely
averaged in the past 200ms (very small comparing to the 3s estimation
period for write_bw), which makes rather dispersed distribution of
balanced_dirty_ratelimit.
It's pretty hard to average out the singular points by increasing the
estimation period. Considering that the averaging technique will
introduce very undesirable time lags, I give it up totally. (btw, the 3s
write_bw averaging time lag is much more acceptable because its impact
is one-way and therefore won't lead to oscillations.)
The more practical way is filtering -- most singular
balanced_dirty_ratelimit points can be filtered out by remembering some
prev_balanced_rate and prev_prev_balanced_rate. However the more
reliable way is to guard balanced_dirty_ratelimit with task_ratelimit.
2) due to truncates and fs redirties, the (write_bw <=> dirty_rate)
match could become unbalanced, which may lead to large systematical
errors in balanced_dirty_ratelimit. The truncates, due to its possibly
bumpy nature, can hardly be compensated smoothly. So let's face it. When
some over-estimated balanced_dirty_ratelimit brings dirty_ratelimit
high, dirty pages will go higher than the setpoint. task_ratelimit will
in turn become lower than dirty_ratelimit. So if we consider both
balanced_dirty_ratelimit and task_ratelimit and update dirty_ratelimit
only when they are on the same side of dirty_ratelimit, the systematical
errors in balanced_dirty_ratelimit won't be able to bring
dirty_ratelimit far away.
The balanced_dirty_ratelimit estimation may also be inaccurate near
@limit or @freerun, however is less an issue.
3) since we ultimately want to
- keep the fluctuations of task ratelimit as small as possible
- keep the dirty pages around the setpoint as long time as possible
the update policy used for (2) also serves the above goals nicely:
if for some reason the dirty pages are high (task_ratelimit < dirty_ratelimit),
and dirty_ratelimit is low (dirty_ratelimit < balanced_dirty_ratelimit),
there is no point to bring up dirty_ratelimit in a hurry only to hurt
both the above two goals.
So, we make use of task_ratelimit to limit the update of dirty_ratelimit
in two ways:
1) avoid changing dirty rate when it's against the position control target
(the adjusted rate will slow down the progress of dirty pages going
back to setpoint).
2) limit the step size. task_ratelimit is changing values step by step,
leaving a consistent trace comparing to the randomly jumping
balanced_dirty_ratelimit. task_ratelimit also has the nice smaller
errors in stable state and typically larger errors when there are big
errors in rate. So it's a pretty good limiting factor for the step
size of dirty_ratelimit.
Note that bdi->dirty_ratelimit is always tracking balanced_dirty_ratelimit.
task_ratelimit is merely used as a limiting factor.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
It's all about bdi->dirty_ratelimit, which aims to be (write_bw / N)
when there are N dd tasks.
On write() syscall, use bdi->dirty_ratelimit
============================================
balance_dirty_pages(pages_dirtied)
{
task_ratelimit = bdi->dirty_ratelimit * bdi_position_ratio();
pause = pages_dirtied / task_ratelimit;
sleep(pause);
}
On every 200ms, update bdi->dirty_ratelimit
===========================================
bdi_update_dirty_ratelimit()
{
task_ratelimit = bdi->dirty_ratelimit * bdi_position_ratio();
balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate;
bdi->dirty_ratelimit = balanced_dirty_ratelimit
}
Estimation of balanced bdi->dirty_ratelimit
===========================================
balanced task_ratelimit
-----------------------
balance_dirty_pages() needs to throttle tasks dirtying pages such that
the total amount of dirty pages stays below the specified dirty limit in
order to avoid memory deadlocks. Furthermore we desire fairness in that
tasks get throttled proportionally to the amount of pages they dirty.
IOW we want to throttle tasks such that we match the dirty rate to the
writeout bandwidth, this yields a stable amount of dirty pages:
dirty_rate == write_bw (1)
The fairness requirement gives us:
task_ratelimit = balanced_dirty_ratelimit
== write_bw / N (2)
where N is the number of dd tasks. We don't know N beforehand, but
still can estimate balanced_dirty_ratelimit within 200ms.
Start by throttling each dd task at rate
task_ratelimit = task_ratelimit_0 (3)
(any non-zero initial value is OK)
After 200ms, we measured
dirty_rate = # of pages dirtied by all dd's / 200ms
write_bw = # of pages written to the disk / 200ms
For the aggressive dd dirtiers, the equality holds
dirty_rate == N * task_rate
== N * task_ratelimit_0 (4)
Or
task_ratelimit_0 == dirty_rate / N (5)
Now we conclude that the balanced task ratelimit can be estimated by
write_bw
balanced_dirty_ratelimit = task_ratelimit_0 * ---------- (6)
dirty_rate
Because with (4) and (5) we can get the desired equality (1):
write_bw
balanced_dirty_ratelimit == (dirty_rate / N) * ----------
dirty_rate
== write_bw / N
Then using the balanced task ratelimit we can compute task pause times like:
task_pause = task->nr_dirtied / task_ratelimit
task_ratelimit with position control
------------------------------------
However, while the above gives us means of matching the dirty rate to
the writeout bandwidth, it at best provides us with a stable dirty page
count (assuming a static system). In order to control the dirty page
count such that it is high enough to provide performance, but does not
exceed the specified limit we need another control.
The dirty position control works by extending (2) to
task_ratelimit = balanced_dirty_ratelimit * pos_ratio (7)
where pos_ratio is a negative feedback function that subjects to
1) f(setpoint) = 1.0
2) df/dx < 0
That is, if the dirty pages are ABOVE the setpoint, we throttle each
task a bit more HEAVY than balanced_dirty_ratelimit, so that the dirty
pages are created less fast than they are cleaned, thus DROP to the
setpoints (and the reverse).
Based on (7) and the assumption that both dirty_ratelimit and pos_ratio
remains CONSTANT for the past 200ms, we get
task_ratelimit_0 = balanced_dirty_ratelimit * pos_ratio (8)
Putting (8) into (6), we get the formula used in
bdi_update_dirty_ratelimit():
write_bw
balanced_dirty_ratelimit *= pos_ratio * ---------- (9)
dirty_rate
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Based on a patch from Arnd Bergmann this fixes up the build
problem of assigning a non-existing global when the ux500 PRCMU
timer is not linked in by passing its base address to the init
function. We also add a missing <linux/errno.h> inclusion and
staticize the dummy function.
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Allow the sas-transport-class to update events for local phys via a new
PHY_FUNC_GET_EVENTS command to ->lldd_control_phy(). Fixup drivers that
are not prepared for new enum phy_func values, and unify
->lldd_control_phy() error codes.
These are the SAS defined phy events that are reported in a
smp-report-phy-error-log command:
* /sys/class/sas_phy/<phyX>/invalid_dword_count
* /sys/class/sas_phy/<phyX>/running_disparity_error_count
* /sys/class/sas_phy/<phyX>/loss_of_dword_sync_count
* /sys/class/sas_phy/<phyX>/phy_reset_problem_count
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Based on original implementation from Jiangbi Liu and Maciej Trela.
ATAPI transfers happen in two-to-three stages. The two stage atapi
commands are those that include a dma data transfer. The data transfer
portion of these operations is handled by the hardware packet-dma
acceleration. The three-stage commands do not have a data transfer and
are handled without hardware assistance in raw frame mode.
stage1: transmit host-to-device fis to notify the device of an incoming
atapi cdb. Upon reception of the pio-setup-fis repost the task_context
to perform the dma transfer of the cdb+data (go to stage3), or repost
the task_context to transmit the cdb as a raw frame (go to stage 2).
stage2: wait for hardware notification of the cdb transmission and then
go to stage 3.
stage3: wait for the arrival of the terminating device-to-host fis and
terminate the command.
To keep the implementation simple we only support ATAPI packet-dma
protocol (for commands with data) to avoid needing to handle the data
transfer manually (like we do for SATA-PIO). This may affect
compatibility for a small number of devices (see
ATA_HORKAGE_ATAPI_MOD16_DMA).
If the data-transfer underruns, or encounters an error the
device-to-host fis is expected to arrive in the unsolicited frame queue
to pass to libata for disposition. However, in the DONE_UNEXP_FIS (data
underrun) case it appears we need to craft a response. In the
DONE_REG_ERR case we do receive the UF and propagate it to libsas.
Signed-off-by: Maciej Trela <maciej.trela@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Re-arrange its fields to avoid padding and have better
cacheline alignments.
Removed not used start_time, end_time and last_pkt_time
fields.
This all reduced this struct size to 448 from 480 and
that also reduced one cacheline on x86_64 beside
eliminating 8 pads. However kept logical fields together.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Yi Zou <yi.zou@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Several sas drivers legitimately check the protocol against the union of
SAS_PROTOCOL_SATA and SAS_PROTOCOL_STP. Provide a SAS_PROTOCOL_STP_ALL
to silence warnings like:
drivers/scsi/pm8001/pm8001_sas.c:438:3: warning: case value ‘5’ not in enumerated type ‘enum sas_protocol’ [-Wswitch]
drivers/scsi/mvsas/mv_sas.c:798:2: warning: case value ‘5’ not in enumerated type ‘enum sas_protocol’ [-Wswitch]
drivers/scsi/mvsas/mv_sas.c:1783:2: warning: case value ‘5’ not in enumerated type ‘enum sas_protocol’ [-Wswitch]
drivers/scsi/mvsas/mv_sas.c:1886:2: warning: case value ‘5’ not in enumerated type ‘enum sas_protocol’ [-Wswitch]
drivers/scsi/isci/request.c:3565:2: warning: case value ‘5’ not in enumerated type ‘enum sas_protocol’ [-Wswitch]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Pass queue_depth change requests to libata, and prevent queue_type
changes for ATA devices.
Otherwise:
1/ we do not honor the libata specific restrictions on the queue depth
2/ libsas drivers that do not set sdev->tagged_supported are unable to
change the queue_depth of ata devices via sysfs
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Allow expander table-to-table attachments for
expanders that support it.
Signed-off-by: Luben Tuikov <ltuikov@yahoo.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Four cpufreq-like governors are provided as examples.
powersave: use the lowest frequency possible. The user (device) should
set the polling_ms as 0 because polling is useless for this governor.
performance: use the highest freqeuncy possible. The user (device)
should set the polling_ms as 0 because polling is useless for this
governor.
userspace: use the user specified frequency stored at
devfreq.user_set_freq. With sysfs support in the following patch, a user
may set the value with the sysfs interface.
simple_ondemand: simplified version of cpufreq's ondemand governor.
When a user updates OPP entries (enable/disable/add), OPP framework
automatically notifies devfreq to update operating frequency
accordingly. Thus, devfreq users (device drivers) do not need to update
devfreq manually with OPP entry updates or set polling_ms for powersave
, performance, userspace, or any other "static" governors.
Note that these are given only as basic examples for governors and any
devices with devfreq may implement their own governors with the drivers
and use them.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: Mike Turquette <mturquette@ti.com>
Acked-by: Kevin Hilman <khilman@ti.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
With OPPs, a device may have multiple operable frequency and voltage
sets. However, there can be multiple possible operable sets and a system
will need to choose one from them. In order to reduce the power
consumption (by reducing frequency and voltage) without affecting the
performance too much, a Dynamic Voltage and Frequency Scaling (DVFS)
scheme may be used.
This patch introduces the DVFS capability to non-CPU devices with OPPs.
DVFS is a techique whereby the frequency and supplied voltage of a
device is adjusted on-the-fly. DVFS usually sets the frequency as low
as possible with given conditions (such as QoS assurance) and adjusts
voltage according to the chosen frequency in order to reduce power
consumption and heat dissipation.
The generic DVFS for devices, devfreq, may appear quite similar with
/drivers/cpufreq. However, cpufreq does not allow to have multiple
devices registered and is not suitable to have multiple heterogenous
devices with different (but simple) governors.
Normally, DVFS mechanism controls frequency based on the demand for
the device, and then, chooses voltage based on the chosen frequency.
devfreq also controls the frequency based on the governor's frequency
recommendation and let OPP pick up the pair of frequency and voltage
based on the recommended frequency. Then, the chosen OPP is passed to
device driver's "target" callback.
When PM QoS is going to be used with the devfreq device, the device
driver should enable OPPs that are appropriate with the current PM QoS
requests. In order to do so, the device driver may call opp_enable and
opp_disable at the notifier callback of PM QoS so that PM QoS's
update_target() call enables the appropriate OPPs. Note that at least
one of OPPs should be enabled at any time; be careful when there is a
transition.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: Mike Turquette <mturquette@ti.com>
Acked-by: Kevin Hilman <khilman@ti.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
* '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
The patch enables to register notifier_block for an OPP-device in order
to get notified for any changes in the availability of OPPs of the
device. For example, if a new OPP is inserted or enable/disable status
of an OPP is changed, the notifier is executed.
This enables the usage of opp_add, opp_enable, and opp_disable to
directly take effect with any connected entities such as cpufreq or
devfreq.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: Mike Turquette <mturquette@ti.com>
Reviewed-by: Kevin Hilman <khilman@ti.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
With the addition of uAPSD and driver buffering
the powersave handling has gotten quite complex.
Add a section to the documentation to explain it
for anyone wanting to implement it.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
iwlwifi has a separate EOSP notification from
the device, and to make use of that properly
it needs to be passed to mac80211. To be able
to mix with tx_status_irqsafe and rx_irqsafe
it also needs to be an "_irqsafe" version in
the sense that it goes through the tasklet,
the actual flag clearing would be IRQ-safe
but doing it directly would cause reordering
issues.
This is needed in the case of a P2P GO going
into an absence period without transmitting
any frames that should be driver-released as
in this case there's no other way to inform
mac80211 that the service period ended. Note
that for drivers that don't use the _irqsafe
functions another version of this function
will be required.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
iwlwifi needs to know the number of frames that are
going to be sent to a station while it is asleep so
it can properly handle the uCode blocking of that
station.
Before uAPSD, we got by by telling the device that
a single frame was going to be released whenever we
encountered IEEE80211_TX_CTL_POLL_RESPONSE. With
uAPSD, however, that is no longer possible since
there could be more than a single frame.
To support this model, add a new callback to notify
drivers when frames are going to be released.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
If a PS-poll frame is retried (but was received)
there is no way to detect that since it has no
sequence number. As a consequence, the standard
asks us to not react to PS-poll frames until the
response to one made it out (was ACKed or lost).
Implement this by using the WLAN_STA_SP flags to
also indicate a PS-Poll "service period" and the
IEEE80211_TX_STATUS_EOSP flag for the response
packet to indicate the end of the "SP" as usual.
We could use separate flags, but that will most
likely completely confuse drivers, and while the
standard doesn't exclude simultaneously polling
using uAPSD and PS-Poll, doing that seems quite
problematic.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add uAPSD support to mac80211. This is probably not
possible with all devices, so advertising it with
the cfg80211 flag will be left up to drivers that
want it.
Due to my previous patches it is now a fairly
straight-forward extension. Drivers need to have
accurate TX status reporting for the EOSP frame.
For drivers that buffer themselves, the provided
APIs allow releasing the right number of frames,
but then drivers need to set EOSP and more-data
themselves. This is documented in more detail in
the new code itself.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
If there are frames for a station buffered in
the driver, mac80211 announces those in the TIM
IE but there's no way to release them. Add new
API to release such frames and use it when the
station polls for a frame.
Since the API will soon also be used for uAPSD
it is easily extensible.
Note that before this change drivers announcing
driver-buffered frames in the TIM bit actually
will respond to a PS-Poll with a potentially
lower priority frame (if there are any frames
buffered in mac80211), after this patch a driver
that hasn't been changed will no longer respond
at all. This only affects ath9k, which will need
to be fixed to implement the new API.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
For uAPSD support we'll need to have per-AC PS
buffers. As this is a major undertaking, split
the buffers before really adding support for
uAPSD. This already makes some reference to the
uapsd_queues variable, but for now that will
never be non-zero.
Since book-keeping is complicated, also change
the logic for keeping a maximum of frames only
and allow 64 frames per AC (up from 128 for a
station).
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
For uAPSD implementation, it is necessary to know on
which ACs frames are buffered. mac80211 obviously
knows about the frames it has buffered itself, but
with aggregation many drivers buffer frames. Thus,
mac80211 needs to be informed about this.
For now, since we don't have APSD in any form, this
will unconditionally set the TIM bit for the station
but later with uAPSD only some ACs might cause the
TIM bit to be set.
ath9k is the only driver using this API and I only
modify it in the most basic way, it won't be able
to implement uAPSD with this yet. But it can't do
that anyway since there's no way to selectively
release frames to the peer yet.
Since drivers will buffer frames per TID, let them
inform mac80211 on a per TID basis, mac80211 will
then sort out the AC mapping itself.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When adding a TDLS peer STA, mark it with a new flag in both nl80211 and
mac80211. Before adding a peer, make sure the wiphy supports TDLS and
our operating mode is appropriate (managed).
In addition, make sure all peers are removed on disassociation.
A TDLS peer is first added just before link setup is initiated. In later
setup stages we have more info about peer supported rates, capabilities,
etc. This info is reported via nl80211_set_station().
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Cc: Kalyan C Gaddam <chakkal@iit.edu>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Register and implement the TDLS cfg80211 callback functions.
Internally prepare and send TDLS management frames. We incorporate
local STA capabilities and supported rates with extra IEs given by
usermode. The resulting packet is either encapsulated in a data frame,
or assembled as an action frame. It is transmitted either directly or
through the AP, as mandated by the TDLS specification.
Declare support for the TDLS external setup wiphy capability. This
tells usermode to handle link setup and discovery on its own, and use the
kernel driver for sending TDLS mgmt packets.
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Cc: Kalyan C Gaddam <chakkal@iit.edu>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Relocate the mesh implementation of adding the (extended) supported
rates IE to util.c, anticipating its use by other parts of mac80211.
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Cc: Kalyan C Gaddam <chakkal@iit.edu>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add support for sending high-level TDLS commands and TDLS frames via
NL80211_CMD_TDLS_OPER and NL80211_CMD_TDLS_MGMT, respectively. Add
appropriate cfg80211 callbacks for lower level drivers.
Add wiphy capability flags for TDLS support and advertise them via
nl80211.
Signed-off-by: Arik Nemtsov <arik@wizery.com>
Cc: Kalyan C Gaddam <chakkal@iit.edu>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Currently, when hostapd sets the station as authorized
we also overwrite its uAPSD parameter. This obviously
leads to buggy behaviour (later, with my patches that
actually add uAPSD support). To fix this, only apply
those parameters if they were actually set in nl80211,
and to achieve that add a bitmap of things to apply.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Make report_iommu_fault() return -ENOSYS whenever an iommu fault
handler isn't installed, so IOMMU drivers can then do their own
platform-specific default behavior if they wanted.
Fault handlers can still return -ENOSYS in case they want to elicit the
default behavior of the IOMMU drivers.
Signed-off-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
overlay_info struct, used to configure overlays, currently includes both
physical and virtual addresses for the pixels. The vaddr was added to
support more exotic configurations where CPU would be used to update a
display, but it is not currently used and there has been no interest in
the feature. Using CPU to update a screen is also less interesting now
that OMAP4 has two LCD outputs.
This patch removes the vaddr field, and modifies the users of omapdss
accordingly. This makes the use of omapdss a bit simpler, as the user
doesn't need to think if it needs to give the vaddr.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
This is a driver for N800's display, ported from the old omapfb. This is
a slightly lighter version of the driver as not all features of the old
driver can be ported without big changes to DSS2, and also because some
of the HW features used in the old driver are unclear (e.g. the power
management part).
That said, the new driver works fine for basic use.
Architecturally the driver is not as neat as it could be. N800's display
HW consists of a display buffer chip and a panel, and ideally they would
be represented by separate, independent drivers. This is not currently
possible, and this driver contains both buffer chip and panel driver.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Taal panel driver supports two kinds of backlight control: 1) using DSI
commands sent to the panel to control the backlight, 2) calling function
pointers going to the board file to control the backlight.
The second option is a bit hacky, and will no longer be needed when the
PWM driver supports the backlight features. After that we can use the
standard PWM backlight driver.
This patch removes the second backlight control mechanism, and adds a
boolean field, use_dsi_backlight, to nokia_dsi_panel_data which the
board file can use to inform whether the panel driver should use DSI
commands to control the backlight.
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
We have currently panel-generic-dpi driver, which is a combined driver
for dummy panels and also for DVI output.
The aim is to split the panel-generic-dpi into two, one for fixed size
dummy panels connected via DPI, and the other (this) for variable
resolution output which supports DDC channel (in practice a DVI framer
chip connected to DPI output).
Original i2c code by: Ricardo Salveti de Araujo
<ricardo.salveti@canonical.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
regn divider is currently programmed to the registers without change,
but when calculating clock frequencies it is used as regn+1.
To make this similar to how DSI handles the dividers this patch changes
the regn value to be used as such for calculations, but the value
programmed to registers is regn-1.
This simplifies the clock frequency calculations, makes it similar to
DSI, and also allows us to use regn value 0 as undefined.
Cc: Mythri P K <mythripk@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Add initial support for DSI video mode panels:
- Add a new structure omap_dss_dsi_videomode_data in the member "panel" in
omap_dss_device struct. This allows panel driver to configure dsi video_mode
specific parameters.
- Configure basic DSI video mode timing parameters: HBP, HFP, HSA, VBP, VFP, VSA,
TL and VACT.
- Configure DSI protocol engine registers for video_mode support.
- Introduce functions dsi_video_mode_enable() and dsi_video_mode_disable() which
enable/disable video mode for a given virtual channel and a given pixel format
type.
Things left for later
- Add functions to check for errors in video mode timings provided by panel.
- Configure timing registers required for command mode interleaving.
Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Currently, DSI pixel info is only represented by the pixel size in bits using
the pixel_size parameter in omap_dss_device struct's ctrl member.
This is not sufficient information for DSI video mode usage, as two of the
supported formats(RGB666 loosely packed, and RGB888) have the same pixel
container size, but different data_type values for the video mode packet header.
Create enum "omap_dss_dsi_pixel_format" which describes the pixel data format
the panel is configured for. Create helper function dsi_get_pixel_size() which
returns the pixel size of the given pixel format.
Modify functions omapdss_default_get_recommended_bpp() and dss_use_replication()
to use dsi_get_pixel_size().
Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Introduce read functions which use generic Processor-to-Peripheral
transaction types. These are needed by some devices which may not support
corresponding DCS commands.
Add function dsi_vc_generic_send_read_request() which can send
a short packet with 0, 1 or 2 bytes of request data and the corresponding
generic data type.
Rename function dsi_vc_dcs_read_rx_fifo() to dsi_vc_read_rx_fifo() and modify
it to take the enum "dss_dsi_content_type" as an argument to use either DCS
or GENERIC Peripheral-to-Processor transaction types while parsing data read
from the device.
Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Remove functions dsi_vc_dcs_read_1() and dsi_vc_dcs_read_2(), these are used
when the panel is expected to return 1 and 2 bytes respecitvely. This was manily
used for debugging purposes. These functions should be implemented in the panel
driver if needed.
Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Intoduce enum "dss_dsi_content_type" to differentiate between DCS and generic
content types.
Introduce short and long packet write functions which use generic
Processor-to-Peripheral transaction types. These are needed by some devices
which may not support corresponding DCS commands. Create common write functions
which allow code reuse between DCS and generic write functions.
Signed-off-by: Archit Taneja <archit@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
