Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 28 5月, 2019 1 次提交
    • V
      drm/i915: Make sure we have enough memory bandwidth on ICL · c457d9cf
      由 Ville Syrjälä 提交于 
      ICL has so many planes that it can easily exceed the maximum
effective memory bandwidth of the system. We must therefore check
that we don't exceed that limit.

The algorithm is very magic number heavy and lacks sufficient
explanation for now. We also have no sane way to query the
memory clock and timings, so we must rely on a combination of
raw readout from the memory controller and hardcoded assumptions.
The memory controller values obviously change as the system
jumps between the different SAGV points, so we try to stabilize
it first by disabling SAGV for the duration of the readout.

The utilized bandwidth is tracked via a device wide atomic
private object. That is actually not robust because we can't
afford to enforce strict global ordering between the pipes.
Thus I think I'll need to change this to simply chop up the
available bandwidth between all the active pipes. Each pipe
can then do whatever it wants as long as it doesn't exceed
its budget. That scheme will also require that we assume that
any number of planes could be active at any time.

TODO: make it robust and deal with all the open questions

v2: Sleep longer after disabling SAGV
v3: Poll for the dclk to get raised (seen it take 250ms!)
    If the system has 2133MT/s memory then we pointlessly
    wait one full second :(
v4: Use the new pcode interface to get the qgv points rather
    that using hardcoded numbers
v5: Move the pcode stuff into intel_bw.c (Matt)
    s/intel_sagv_info/intel_qgv_info/
    Do the NV12/P010 as per spec for now (Matt)
    s/IS_ICELAKE/IS_GEN11/
v6: Ignore bandwidth limits if the pcode query fails
Signed-off-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: NMatt Roper <matthew.d.roper@intel.com>
Acked-by: NClint Taylor <Clinton.A.Taylor@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190524153614.32410-1-ville.syrjala@linux.intel.com
      c457d9cf
  3. 25 5月, 2019 1 次提交
  5. 23 5月, 2019 1 次提交
  7. 20 5月, 2019 1 次提交
  9. 14 5月, 2019 1 次提交
    • I
      drm/i915: Add support for asynchronous display power disabling · e0da2d63
      由 Imre Deak 提交于 
      By disabling a power domain asynchronously we can restrict holding a
reference on that power domain to the actual code sequence that
requires the power to be on for the HW access it's doing, by also
avoiding unneeded on-off-on togglings of the power domain (since the
disabling happens with a delay).

One benefit is potential power saving due to the following two reasons:
1. The fact that we will now be holding the reference only for the
   necessary duration by the end of the patchset. While simply not
   delaying the disabling has the same benefit, it has the problem that
   frequent on-off-on power switching has its own power cost (see the 2.
   point below) and the debug trace for power well on/off events will
   cause a lot of dmesg spam (see details about this further below).
2. Avoiding the power cost of freuqent on-off-on power switching. This
   requires us to find the optimal disabling delay based on the measured
   power cost of on->off and off->on switching of each power well vs.
   the power of keeping the given power well on.

   In this patchset I'm not providing this optimal delay for two
   reasons:
   a) I don't have the means yet to perform the measurement (with high
      enough signal-to-noise ratio, or with the help of an energy
      counter that takes switching into account). I'm currently looking
      for a way to measure this.

   b) Before reducing the disabling delay we need an alternative way for
      debug tracing powerwell on/off events. Simply avoiding/throttling
      the debug messages is not a solution, see further below.

   Note that even in the case where we can't measure any considerable
   power cost of frequent on-off switching of powerwells, it still would
   make sense to do the disabling asynchronously (with 0 delay) to avoid
   blocking on the disabling. On VLV I measured this disabling time
   overhead to be 1ms on average with a worst case of 4ms.

In the case of the AUX power domains on ICL we would also need to keep
the sequence where we hold the power reference short, the way it would
be by the end of this patchset where we hold it only for the actual AUX
transfer. Anything else would make the locking we need for ICL TypeC
ports (whenever we hold a reference on any AUX power domain) rather
problematic, adding for instance unnecessary lockdep dependencies to
the required TypeC port lock.

I chose the disabling delay to be 100msec for now to avoid the unneeded
toggling (and so not to introduce dmesg spamming) in the DP MST sideband
signaling code. We could optimize this delay later, once we have the
means to measure the switching power cost (see above).

Note that simply removing/throttling the debug tracing for power well
on/off events is not a solution. We need to know the exact spots of
these events and cannot rely only on incorrect register accesses caught
(due to not holding a wakeref at the time of access). Incorrect
powerwell enabling/disabling could lead to other problems, for instance
we need to keep certain powerwells enabled for the duration of modesets
and AUX transfers.

v2:
- Clarify the commit log parts about power cost measurement and the
  problem of simply removing/throttling debug tracing. (Chris)
- Optimize out local wakeref vars at intel_runtime_pm_put_raw() and
  intel_display_power_put_async() call sites if
  CONFIG_DRM_I915_DEBUG_RUNTIME_PM=n. (Chris)
- Rebased on v2 of the wakeref w/o power-on guarantee patch.
- Add missing docbook headers.
v3:
- Checkpatch spelling/missing-empty-line fix.
v4:
- Fix unintended local wakeref var optimization when using
  call-arguments with side-effects, by using inline funcs instead of
  macros. In this patch in particular this will fix the
  intel_display_power_grab_async_put_ref()->intel_runtime_pm_put_raw()
  call).

  No size change in practice (would be the same disregarding the
  corresponding change in intel_display_power_grab_async_put_ref()):
  $ size i915-macro.ko
     text	   data	    bss	    dec	    hex	filename
  2455190	 105890	  10272	2571352	 273c58	i915-macro.ko
  $ size i915-inline.ko
     text	   data	    bss	    dec	    hex	filename
  2455195	 105890	  10272	2571357	 273c5d	i915-inline.ko

  Kudos to Stan for reporting the raw-wakeref WARNs this issue caused. His
  config has CONFIG_DRM_I915_DEBUG_RUNTIME_PM=n, which I didn't retest
  after v1, and we are also not testing this config in CI.

  Now tested both with CONFIG_DRM_I915_DEBUG_RUNTIME_PM=y/n on ICL,
  connecting both Chamelium and regular DP, HDMI sinks.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190513192533.12586-1-imre.deak@intel.com
      e0da2d63
  11. 08 5月, 2019 3 次提交
  13. 03 5月, 2019 8 次提交
  15. 02 5月, 2019 1 次提交
  17. 01 5月, 2019 1 次提交
  19. 30 4月, 2019 8 次提交
  21. 26 4月, 2019 5 次提交
  23. 25 4月, 2019 4 次提交
  25. 24 4月, 2019 1 次提交
  27. 20 4月, 2019 1 次提交
    • C
      drm/i915: Start writeback from the shrinker · 2d6692e6
      由 Chris Wilson 提交于 
      When we are called to relieve mempressue via the shrinker, the only way
we can make progress is either by discarding unwanted pages (those
objects that userspace has marked MADV_DONTNEED) or by reclaiming the
dirty objects via swap. As we know that is the only way to make further
progress, we can initiate the writeback as we invalidate the objects.
This means the objects we put onto the inactive anon lru list are
already marked for reclaim+writeback and so will trigger a wait upon the
writeback inside direct reclaim, greatly improving the success rate of
direct reclaim on i915 objects.

The corollary is that we may start a slow swap on opportunistic
mempressure from the likes of the compaction + migration kthreads. This
is limited by those threads only being allowed to shrink idle pages, but
also that if we reactivate the page before it is swapped out by gpu
activity, we only page the cost of repinning the page. The cost is most
felt when an object is reused after mempressure, which hopefully
excludes the latency sensitive tasks (as we are just extending the
impact of swap thrashing to them).

Apparently this is not the first time we've had this idea. Back in
commit 5537252b ("drm/i915: Invalidate our pages under memory
pressure") we wanted to start writeback but settled on invalidate after
Hugh Dickins warned us about a possibility of a deadlock within shmemfs
if we started writeback from shrink_slab. Looking at the callchain,
using writeback from i915_gem_shrink should be equivalent to the pageout
also employed by shrink_slab, i.e. it should not be any riskier afaict.

v2: Leave mmapings intact. At this point, the only mmapings of our
objects will be via CPU mmaps on the shmemfs filp, which are
out-of-scope for our LRU tracking. Instead leave those pages to the
inactive anon LRU page list for aging and pageout as normal.

v3: Be selective on which paths trigger writeback, in particular
excluding paths shrinking just to reclaim vm space (e.g. mmap, vmap
reapers) and avoid starting writeback on the entire process space from
within the pm freezer.

References: https://bugs.freedesktop.org/show_bug.cgi?id=108686Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Michal Hocko <mhocko@suse.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20190420115539.29081-1-chris@chris-wilson.co.uk
      2d6692e6
  29. 19 4月, 2019 1 次提交
  31. 17 4月, 2019 1 次提交
  33. 11 4月, 2019 1 次提交