Praveen Paneri [Mon, 2 May 2016 08:40:29 +0000 (14:10 +0530)]
drm/i915: Add rpm get/put in oom and vmap notifier
i915_gem_shrink() will scan the bound list only if device is not
suspended but in OOM failure scenario it becomes absolutely necessary
to release as much memory as possible. Also in allocation failure from
vmap address space, it is incumbent on the Driver to reap all its
vmaps. So, adding rpm get/put in i915_gem_shrinker_oom() and
i915_gem_shrinker_vmap() to ensure shrinking of bound objects as well.
Praveen Paneri [Mon, 2 May 2016 08:40:28 +0000 (14:10 +0530)]
drm/i915: Unbind objects in shrinker only if device is runtime active
When the system is running low on memory, gem shrinker is invoked.
In this process objects will be unbounded from GTT and unbinding process
will require access to GTT(GTTADR) and also to fence register potentially.
That requires a resume of gfx device, if suspended, in the shrinker path.
Considering the power leakage due to intermediate resume, perform unbinding
operation only if device is already runtime active.
v2: Use newly implemented intel_runtime_pm_get_if_in_use (Chris)
Jani Nikula [Fri, 29 Apr 2016 12:34:02 +0000 (15:34 +0300)]
drm/i915/lvds: separate border enable readout from panel fitter
The LVDS border enable is independent from the panel fitter. Move the
readout of the "border bits" from i9xx_get_pfit_config() to
intel_lvds_get_config(), where it will be read if LVDS is enabled even
if the panel fitter is not.
This fixes the state checker warning:
[drm:intel_pipe_config_compare [i915]] *ERROR* mismatch in
gmch_pfit.lvds_border_bits (expected 0x00008000, found 0x00000000)
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: drm-intel-fixes@lists.freedesktop.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87632 Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1461933243-2140-1-git-send-email-jani.nikula@intel.com
Chris Wilson [Fri, 29 Apr 2016 11:20:22 +0000 (12:20 +0100)]
drm/i915: Enable semaphores for legacy submission on gen8
We have sufficient evidence from igt to support that semaphores are in
a working state. Enabling semaphores now for legacy provides a better
comparison of execlists against legacy ring submission.
Chris Wilson [Fri, 29 Apr 2016 12:18:24 +0000 (13:18 +0100)]
drm/i915: Fix serialisation of pipecontrol write vs semaphore signal
In order for the MI_SEMAPHORE_SIGNAL command to wait until after the
pipecontrol writing the signal value is complete, we have to pause the
CS inside the PIPE_CONTROL with the CS_STALL bit.
Chris Wilson [Fri, 29 Apr 2016 12:18:23 +0000 (13:18 +0100)]
drm/i915: Fix gen8 semaphores id for legacy mode
With the introduction of a distinct engine->id vs the hardware id, we need
to fix up the value we use for selecting the target engine when signaling
a semaphore. Note that these values can be merged with engine->guc_id.
Chris Wilson [Fri, 29 Apr 2016 12:18:21 +0000 (13:18 +0100)]
drm/i915: Apply strongly ordered RCS breadcrumb to gen8/legacy
For legacy ringbuffer mode, we need the new ordered breadcrumb emission
tried and tested on execlists in order to avoid the dreaded "missed
interrupt" syndrome. A secondary advantage of the execlists method is
that it writes to an arbitrary address, useful if one wants to write a
breadcrumb elsewhere.
This fix is taken from commit 7c17d377374dd (drm/i915: Use ordered seqno
write interrupt generation on gen8+ execlists).
Chris Wilson [Fri, 29 Apr 2016 08:07:06 +0000 (09:07 +0100)]
drm/i915: Trim the flush for the execlists request emission
At the start of request emission, we flush some space for the request,
estimating the typical size for the request body. The common tail is now
much larger than the typical body, so we can shrink the flush
substantially.
Chris Wilson [Fri, 29 Apr 2016 08:07:05 +0000 (09:07 +0100)]
drm/i915: Trim the flush for the legacy request emission
At the start of request emission, we flush some space for the request,
estimating the typical size for the request body. The tail is now much
larger than the typical body, so we can shrink the flush slightly.
Chris Wilson [Fri, 29 Apr 2016 08:07:04 +0000 (09:07 +0100)]
drm/i915: Bump reserved size for legacy gen8 semaphore emission
With 5 rings and a flush, we need 192 bytes of space to emit the
breadcrumb and semaphores. However, we need some spare room the size of
the single largest packet (36 dwords, 144 bytes) to accommodate
wraparound giving a grand total of 336 bytes
drm/i915: Unduplicate VLV phy pre pll enabling code
The code used by the DP and HDMI paths was very similar, so make them
share it. Note that this removes the write to signal level registers
from the HDMI pre pll enable path, but that's OK since those are set
in vlv_hdmi_pre_enable() function.
The logic for setting signal levels is used for both HDMI and DP with
small variations. But it is similar enough to put behind a function
called from the encoders.
v2: Remove unrelated MST changes due to rebase fumble. (Jim Bride)
Fix typo in the commit message. (Jim Bride)
drm/i915: Unduplicate CHV encoders' post pll disable code
The exact same code was used by HDMI and DP encoders, so move it to
intel_dpio_phy.c.
v2: Fix typo in the commit message. (Jim Bride)
v3: Call the new function chv_phy_post_pll_disable() instead of
chv_phy_post_disable(), as it should be called after the pll
is disabled. (Ville)
The only difference between the DP and HDMI versions was the lane count.
Since lane_count is now set appropriately for HDMI too, get rid of the
duplication and move this to intel_dpio_phy.c
Set the lane count for HDMI to 4. This will make it easier to
unduplicate CHV phy code.
This also fixes the the soft reset programming for HDMI with CHV. After
commit a8f327fb8464 ("drm/i915: Clean up CHV lane soft reset
programming"), it wouldn't set the right bits for PCS23 since it relied
on a lane count that was never set.
v2: Set lane_count in *_get_config() to please state checker. (0day)
v3: Set lane_count for DDI in DVI mode too. (CI)
v4: Add note about CHV soft lane reset. (Ander)
Ville Syrjälä [Tue, 26 Apr 2016 16:46:34 +0000 (19:46 +0300)]
drm/i915: Fix comments about GMBUSFREQ register
The comment about GMBUSFREQ is confused. The spec actually explains
the 4MHz thing perfectly by noting that the 4MHz divider values is
actually just bits [9:2] not [9:0], hence the divide by 1000 correct.
Replace the confused note with a quote from the spec, and eliminate
the duplicated comment that snuck in.
Ville Syrjälä [Tue, 26 Apr 2016 16:46:33 +0000 (19:46 +0300)]
drm/i915: Use cached cdclk value in i915_audio_component_get_cdclk_freq()
No point in reading the cdclk out from the hardware every single time
since we have it cached already. Just return the cached value to the
audio driver.
Ville Syrjälä [Tue, 26 Apr 2016 16:46:32 +0000 (19:46 +0300)]
drm/i915: Update CDCLK_FREQ register on BDW after changing cdclk frequency
Update CDCLK_FREQ on BDW after changing the cdclk frequency. Not sure
if this is a late addition to the spec, or if I simply overlooked this
step when writing the original code.
This is what Bspec has to say about CDCLK_FREQ:
"Program this field to the CD clock frequency minus one. This is used to
generate a divided down clock for miscellaneous timers in display."
And the "Broadwell Sequences for Changing CD Clock Frequency" section
clarifies this further:
"For CD clock 337.5 MHz, program 337 decimal.
For CD clock 450 MHz, program 449 decimal.
For CD clock 540 MHz, program 539 decimal.
For CD clock 675 MHz, program 674 decimal."
Ramalingam C [Tue, 19 Apr 2016 08:18:14 +0000 (13:48 +0530)]
drm/i915/bxt: Adjusting the error in horizontal timings retrieval
In BXT DSI there is no regs programmed with few horizontal timings
in Pixels but txbyteclkhs.. So retrieval process adds some
ROUND_UP ERRORS in the process of PIXELS<==>txbyteclkhs.
Actually here for the given adjusted_mode, we are calculating the
value programmed to the port and then back to the horizontal timing
param in pixels. This is the expected value at the end of get_config,
including roundup errors. And if that is same as retrieved value
from port, then retrieved (HW state) adjusted_mode's horizontal
timings are corrected to match with SW state to nullify the errors.
Chris Wilson [Thu, 28 Apr 2016 08:56:59 +0000 (09:56 +0100)]
drm/i915: Unify GPU resets upon shutdown
Both execlists and legacy need to reset the context (and mode) of the
GPU before we lose control of the system. By resetting the GPU, we
revert back to default settings. This simplifies the life of any
subsequent driver (in particular for virtualized setups) as it does not
then have to try and recover from an unknown condition. As both paths
need to reset for the same reason, move the reset to a common point.
This unifies the resets added in a647828afc (drm/i915: Also perform gpu
reset under execlist mode) and 8e96d9c4d9 (drm/i915: reset the GPU on
context fini).
v2: Restrict the reset to "modern" gen (where we enable HW contexts) to
try and avoid leaving the machine in an unusable state with a risky
reset on older GPU. This should keep the status quo as to who performs
resets (i.e. currently only GPUs with HW contexts perform a reset on
shutdown).
With the previous patch having extended the pinned lifetime of
contexts by referencing the previous context from the current
request until the latter is retired (completed by the GPU),
we can now remove usage of execlist retired queue entirely.
This is because the above now guarantees that all execlist
object access requirements are satisfied by this new tracking,
and we can stop taking additional references and stop keeping
request on the execlists retired queue.
The latter was a source of significant scalability issues in
the driver causing performance hits on some tests. Most
dramatical of which was igt/gem_close_race which had run time
in tens of minutes which is now reduced to tens of seconds.
Chris Wilson [Thu, 28 Apr 2016 08:56:56 +0000 (09:56 +0100)]
drm/i915: Track the previous pinned context inside the request
As the contexts are accessed by the hardware until the switch is completed
to a new context, the hardware may still be writing to the context object
after the breadcrumb is visible. We must not unpin/unbind/prune that
object whilst still active and so we keep the previous context pinned until
the following request. We can generalise the tracking we already do via
the engine->last_context and move it to the request so that it works
equally for execlists and GuC.
v2: Drop the execlists double pin as that exposes a race inside the lrc
irq handler as it tries to access the context after it may be retired.
Chris Wilson [Thu, 28 Apr 2016 08:56:55 +0000 (09:56 +0100)]
drm/i915: Move releasing of the GEM request from free to retire/cancel
If we move the release of the GEM request (i.e. decoupling it from the
various lists used for client and context tracking) after it is complete
(either by the GPU retiring the request, or by the caller cancelling the
request), we can remove the requirement that the final unreference of
the GEM request need to be under the struct_mutex.
The careful reader may notice that one or two impossible NULL pointer
tests are dropped for readability. These pointers cannot be NULL since
they are assigned during request construction and never unset.
v2,v3: Rebalance execlists by moving the context unpinning.
v4: Rebase onto -nightly
v5: Avoid trying to rebalance execlist/GuC context pinning, leave that
to the next step
Chris Wilson [Thu, 28 Apr 2016 08:56:54 +0000 (09:56 +0100)]
drm/i915: Move the magical deferred context allocation into the request
We can hide more details of execlists from higher level code by removing
the explicit call to create an execlist context from execbuffer and
into its first use by execlists.
Refactor pinning and unpinning of contexts, such that the default
context for an engine is pinned during initialisation and unpinned
during teardown (pinning of the context handles the reference counting).
Thus we can eliminate the special case handling of the default context
that was required to mask that it was not being pinned normally.
v2: Rebalance context_queue after rebasing.
v3: Rebase to -nightly (not 40 patches in)
v4: Rebase onto request_alloc unwinding
Chris Wilson [Thu, 28 Apr 2016 08:56:52 +0000 (09:56 +0100)]
drm/i915: Replace the pinned context address with its unique ID
Rather than reuse the current location of the context in the global GTT
for its hardware identifier, use the context's unique ID assigned to it
for its whole lifetime.
Chris Wilson [Thu, 28 Apr 2016 08:56:51 +0000 (09:56 +0100)]
drm/i915: Assign every HW context a unique ID
The hardware tracks contexts and expects all live contexts (those active
on the hardware) to have a unique identifier. This is used by the
hardware to assign pagefaults and the like to a particular context.
v2: Reorder to make sure ctx->link is not left dangling if the
assignment of a hw_id fails (Mika).
Chris Wilson [Thu, 28 Apr 2016 08:56:49 +0000 (09:56 +0100)]
drm/i915: Preallocate enough space for the average request
Rather than being interrupted when we run out of space halfway through
the request, and having to restart from the beginning (and returning to
userspace), flush a little more free space when we prepare the request.
Chris Wilson [Thu, 28 Apr 2016 08:56:48 +0000 (09:56 +0100)]
drm/i915: Manually unwind after a failed request allocation
In the next patches, we want to move the work out of freeing the request
and into its retirement (so that we can free the request without
requiring the struct_mutex). This means that we cannot rely on
unreferencing the request to completely teardown the request any more
and so we need to manually unwind the failed allocation. In doing so, we
reorder the allocation in order to make the unwind simple (and ensure
that we don't try to unwind a partial request that may have modified
global state) and so we end up pushing the initial preallocation down
into the engine request initialisation functions where we have the
requisite control over the state of the request.
Moving the initial preallocation into the engine is less than ideal: it
moves logic to handle a specific problem with request handling out of
the common code. On the other hand, it does allow those backends
significantly more flexibility in performing its allocations.
Chris Wilson [Thu, 28 Apr 2016 08:56:47 +0000 (09:56 +0100)]
drm/i915: Remove the identical implementations of request space reservation
Now that we share intel_ring_begin(), reserving space for the tail of
the request is identical between legacy/execlists and so the tautology
can be removed. In the process, we move the reserved space tracking
from the ringbuffer on to the request. This is to enable us to reorder
the reserved space allocation in the next patch.
Chris Wilson [Thu, 28 Apr 2016 08:56:46 +0000 (09:56 +0100)]
drm/i915: Unify intel_ring_begin()
Combine the near identical implementations of intel_logical_ring_begin()
and intel_ring_begin() - the only difference is that the logical wait
has to check for a matching ring (which is assumed by legacy).
In the process some debug messages are culled as there were following a
WARN if we hit an actual error.
Chris Wilson [Thu, 28 Apr 2016 08:56:45 +0000 (09:56 +0100)]
drm/i915: Rearrange switch_context to load the aliasing ppgtt on first use
The code to switch_mm() is already handled by i915_switch_context(), the
only difference required to setup the aliasing ppgtt is that we need to
emit te switch_mm() on the first context, i.e. when transitioning from
engine->last_context == NULL. This allows us to defer the
initialisation of the GPU from early device initialisation to first use,
which should marginally speed up both. The caveat is that we then defer
the context initialisation until first use - i.e. we cannot assume that
the GPU engines are initialised. For example, this means that power
contexts for rc6 (Ironlake) need to explicitly loaded, as they are.
Chris Wilson [Thu, 28 Apr 2016 08:56:43 +0000 (09:56 +0100)]
drm/i915: Consolidate L3 remapping LRI
We can use a single MI_LOAD_REGISTER_IMM command packet to write all the
L3 remapping registers, shrinking the number of bytes required to emit
the context switch.
Chris Wilson [Thu, 28 Apr 2016 08:56:41 +0000 (09:56 +0100)]
drm/i915: Mark the current context as lost on suspend
In order to force a reload of the context image upon resume, we first
need to mark its absence on suspend. Currently we are failing to restore
the golden context state and any context w/a to the default context
after resume.
One oversight corrected, is that we had forgotten to reapply the L3
remapping when restoring the lost default context.
Chris Wilson [Thu, 28 Apr 2016 08:56:40 +0000 (09:56 +0100)]
drm/i915: Use i915_vma_pin_iomap on the ringbuffer object
Similarly to i915_gem_object_pin_map on LLC platforms, we can
use the new VMA based io mapping on !LLC to amoritize the cost
of ringbuffer pinning and unpinning.
Chris Wilson [Thu, 28 Apr 2016 08:56:39 +0000 (09:56 +0100)]
drm/i915: Move ioremap_wc tracking onto VMA
By tracking the iomapping on the VMA itself, we can share that area
between multiple users. Also by only revoking the iomapping upon
unbinding from the mappable portion of the GGTT, we can keep that iomap
across multiple invocations (e.g. execlists context pinning).
Note that by moving the iounnmap tracking to the VMA, we actually end up
fixing a leak of the iomapping in intel_fbdev.
v1.5: Rebase prompted by Tvrtko
v2: Drop dev_priv parameter, we can recover the i915_ggtt from the vma.
v3: Move handling of ioremap space exhaustion to vmap_purge and also
allow vmallocs to recover old iomaps. Add Tvrtko's kerneldoc.
v4: Fix a use-after-free in shrinker and rearrange i915_vma_iomap
v5: Back to i915_vm_to_ggtt
v6: Use i915_vma_pin_iomap and i915_vma_unpin_iomap to mark critical
sections and ensure the VMA cannot be reaped whilst mapped.
v7: Move i915_vma_iounmap so that consumers of the API are not tempted,
and add iomem annotations
Chris Wilson [Thu, 28 Apr 2016 08:56:38 +0000 (09:56 +0100)]
drm/i915: Introduce i915_vm_to_ggtt()
In a couple of places, we have an i915_address_space that we know is
really an i915_ggtt that we want to use. Create an inline helper to
convert from the i915_address_space subclass into its container.
Chris Wilson [Thu, 28 Apr 2016 08:56:37 +0000 (09:56 +0100)]
io-mapping: Specify mapping size for io_mapping_map_wc()
The ioremap() hidden behind the io_mapping_map_wc() convenience helper
can be used for remapping multiple pages. Extend the helper so that
future callers can use it for larger ranges.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Daniel Vetter <daniel.vetter@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: David Airlie <airlied@linux.ie> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: David Hildenbrand <dahi@linux.vnet.ibm.com> Cc: Luis R. Rodriguez <mcgrof@kernel.org> Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: netdev@vger.kernel.org Cc: linux-rdma@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Luis R. Rodriguez <mcgrof@kernel.org> Link: http://patchwork.freedesktop.org/patch/msgid/1461833819-3991-3-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 28 Apr 2016 08:56:36 +0000 (09:56 +0100)]
drm/i915/overlay: Replace i915_gem_obj_ggtt_offset() with the known flip_addr
When setting up the overlay page, we pin it into the GGTT (when using
virtual addresses) and store the offset as overlay->flip_addr. Rather
than doing a lookup of the GGTT address everytime, we can use the known
address instead.
Chris Wilson [Mon, 25 Apr 2016 12:32:13 +0000 (13:32 +0100)]
drm/i915: Propagate error from drm_gem_object_init()
Propagate the real error from drm_gem_object_init(). Note this also
fixes some confusion in the error return from i915_gem_alloc_object...
v2:
(Matthew Auld)
- updated new users of gem_alloc_object from latest drm-nightly
- replaced occurrences of IS_ERR_OR_NULL() with IS_ERR()
v3:
(Joonas Lahtinen)
- fix double "From:" in commit message
- add goto teardown path
v4:
(Matthew Auld)
- rebase with i915_gem_alloc_object name change
Signed-off-by: Matthew Auld <matthew.auld@intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1461587533-8841-1-git-send-email-matthew.auld@intel.com
[Joonas: Removed spurious " = NULL" from _init() function] Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Chris Wilson [Wed, 27 Apr 2016 08:02:01 +0000 (09:02 +0100)]
drm/i915: Protect gen7 irq_seqno_barrier with uncore lock
Faced with sporadic machine hangs on gen7, that mimic the issue of
concurrent writes to the same cacheline and seem to start with
commit 9b9ed3093613 (drm/i915: Remove forcewake dance from seqno/irq
barrier on legacy gen6+), let us restore the spinlock around the mmio
read.
Ville Syrjälä [Wed, 27 Apr 2016 14:43:22 +0000 (17:43 +0300)]
drm/i915: Update RAWCLK_FREQ register on VLV/CHV
I just noticed that VLV/CHV have a RAWCLK_FREQ register just like PCH
platforms. It lives in the display power well, so we should update it
when enabling the power well.
Interestingly the BIOS seems to leave it at the reset value (125) which
doesn't match the rawclk frequency on VLV/CHV (200 MHz). As always with
these register, the spec is extremely vague what the register does. All
it says is: "This is used to generate a divided down clock for
miscellaneous timers in display." Based on a quick test, at least AUX
and PWM appear to be unaffected by this.
But since the register is there, let's configure it in accordance with
the spec.
Note that we have to move intel_update_rawclk() to occur before we
touch the power wells, so that the dev_priv->rawclk_freq is already
populated when the disp2 enable hook gets called for the first time.
I think this should be safe to do on other platforms as well.
Check for VLV/CHV instead if !BXT when re-enabling DPOunit clock gating
after DSI disable. That's what we checked when disabling the clock
gating when enabling DSI.
Also use the same temporary variable name in both cases, and toss in a
bit of dev vs. dev_priv cleanup while at it.
Deepak M [Wed, 30 Mar 2016 14:03:40 +0000 (17:03 +0300)]
drm/i915: Parsing the PWM cntrl and CABC ON/OFF fields in VBT
For dual link panel scenarios there are new fields added in the
VBT which indicate on which port the PWM cntrl and CABC ON/OFF
commands needs to be sent.
drm/i915: Add Backlight Control using DPCD for eDP connectors (v9)
This patch adds support for eDP backlight control using DPCD registers to
backlight hooks in intel_panel.
It checks for backlight control over AUX channel capability and sets up
function pointers to get and set the backlight brightness level if
supported.
v2: Moved backlight functions from intel_dp.c into a new file
intel_dp_aux_backlight.c. Also moved reading of eDP display control
registers to intel_dp_get_dpcd
v3: Correct some formatting mistakes
v4: Updated to use AUX backlight control if PWM control is not possible
(Jani)
v5: Moved call to initialize backlight registers to dp_aux_setup_backlight
v6: Check DP_EDP_BACKLIGHT_PIN_ENABLE_CAP is disabled before setting up AUX
backlight control. To fix BLM_PWM_ENABLE igt test warnings on bdw_ultra
v7: Add enable_dpcd_backlight module parameter.
v8: Rebase onto latest drm-intel-nightly branch
v9: Remove changes to intel_dp_dpcd_read_wake
Split addition edp_dpcd variable into a separate patch
Dave Gordon [Fri, 22 Apr 2016 18:14:32 +0000 (19:14 +0100)]
drm/i915: rename i915_gem_alloc_object() to i915_gem_object_create()
Because having both i915_gem_object_alloc() and i915_gem_alloc_object()
(with different return conventions) is just too confusing!
(i915_gem_object_alloc() is the low-level memory allocator, and remains
unchanged, whereas i915_gem_alloc_object() is a constructor that ALSO
initialises the newly-allocated object.)
Move graphics stolen memory related early quirk into a function to
allow easy adding of other graphics quirks to fix memory maps on
machines running old BIOS versions.
While at it;
- _funcs -> _ops to follow de facto naming
- make the iteration code tad more readable
- remove unused variables
Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Move the better constructs/comments from i915_gem_stolen.c to
early-quirks.c and increase readability in preparation of only
having one set of functions.
- intel_stolen_base -> gen3_stolen_base
- use phys_addr_t instead of u32 for address for future proofing
v2:
- Print the invalid register values (Chris)
(Omitting the register prefix as it's visible from backtrace.)
Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
This patch applies a performance enhancement workaround
based on analysis of DX and OCL S-Curve workloads. We
increase the General Priority Credits for L3SQ from the
hardware default of 56 to the max value 62, and decrease
the High Priority credits from 8 to 2.
v2: Only apply to B0 onwards
v3: Move w/a to per engine init, ie bxt_init_workarounds
drm/i915/bxt: Explicitly clear the Turbo control register
As a part of WaGsvDisableTurbo, Driver makes an early exit from the
Gen9 Turbo enabling function, so doesn't program the Turbo Control register.
But BIOS could leave the Hw Turbo as enabled, so need to explicitly clear
out the Control register just to avoid inconsitency with debugfs
interface, which will show Turbo as enabled only and that is not expected
after adding the WaGsvDisableTurbo. Apart from this there is no problem
even if the Turbo is left enabled in the Control register, as the Up/Down
interrupts would remain masked.
v2: Add explicit clearing of Turbo Control register to *_disable_rps()
also for the similar consistency (Chris)
drm/i915: Correct the i915_frequency_info debugfs output
There are certain registers, which captures the time elapsed in the
in current Up/Down EI, for how long GT has been Idle/Busy/Avg in the
current Up/Down EI and also in the previous Up/Down EI.
These register values are reported by the i915_frequency_info debugfs
interface. The Driver prints the 'us' suffix after the values, albeit
they are actually in raw form & not in microsecond units.
This patch removes the 'us' suffix so that its clear to User that values
are indeed in raw form.
v2: Present the values in microseconds unit also, after platform
specific conversion (Chris)
v3: Add a space between raw & microsecond value (Chris)
Ville Syrjälä [Wed, 20 Apr 2016 13:43:56 +0000 (16:43 +0300)]
drm/i915: Make RPS EI/thresholds multiple of 25 on SNB-BDW
Somehow my SNB GT1 (Dell XPS 8300) gets very unhappy around
GPU hangs if the RPS EI/thresholds aren't suitably aligned.
It seems like scheduling/timer interupts stop working somehow
and things get stuck eg. in usleep_range().
I bisected the problem down to
commit 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function")
I observed that before all the values were at least multiples of 25,
but afterwards they are not. And rounding things up to the next multiple
of 25 does seem to help, so lets' do that. I also tried roundup(..., 5)
but that wasn't sufficient. Also I have no idea if we might need this sort of
thing on gen9+ as well.
These are the original EI/thresholds:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11800
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10250
GEN6_RP_UP_THRESHOLD 9225
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 8000
GEN6_RP_UP_THRESHOLD 6800
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
These are after 8a5864377b12:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11875
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10156
GEN6_RP_UP_THRESHOLD 9140
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 7812
GEN6_RP_UP_THRESHOLD 6640
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
And these are what we have after this patch:
LOW_POWER
GEN6_RP_UP_EI 12500
GEN6_RP_UP_THRESHOLD 11875
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 21250
BETWEEN
GEN6_RP_UP_EI 10175
GEN6_RP_UP_THRESHOLD 9150
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 18750
HIGH_POWER
GEN6_RP_UP_EI 7825
GEN6_RP_UP_THRESHOLD 6650
GEN6_RP_DOWN_EI 25000
GEN6_RP_DOWN_THRESHOLD 15000
Cc: stable@vger.kernel.org Cc: Akash Goel <akash.goel@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk>
Testcase: igt/kms_pipe_crc_basic/hang-read-crc-pipe-B Fixes: 8a5864377b12 ("drm/i915/skl: Restructured the gen6_set_rps_thresholds function") Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1461159836-9108-1-git-send-email-ville.syrjala@linux.intel.com Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Patrik Jakobsson <patrik.jakobsson@linux.intel.com>
This patch does the following:
- Fakes live status of HDMI as connected (even if that's not).
While testing certain (monitor + cable) combinations with
various intel platforms, it seems that live status register
doesn't work reliably on some older devices. So limit the
live_status check for HDMI detection, only for platforms
from gen7 onwards.
V2: restrict faking live_status to certain platforms
V3: (Ville)
- keep the debug message for !live_status case
- fix indentation of comment
- remove "warning" from the debug message
(Jani)
- Change format of fix details in the commit message
Imre Deak [Wed, 20 Apr 2016 17:46:06 +0000 (20:46 +0300)]
drm/i915/bxt: Force reprogramming a PHY with invalid HW state
It's possible that BIOS enables PHY0, but it programmes only the first
channel on it. Since we program the PHYs only during driver loading this
is an incorrect configuration from the driver's point of view, since we
may use both channels eventually. Detect this scenario and force
reprogramming the PHY in this case.
The actual scenario for me was that the lane optimization for the second
channel in PHY0 was not setup by BIOS and so a state verification
warning was triggered. Everything else was setup properly.
Imre Deak [Thu, 21 Apr 2016 16:19:21 +0000 (19:19 +0300)]
drm/i915/bxt: Wait for PHY1 GRC done if PHY0 was already enabled
If we skipped PHY0 initialization because it was already enabled by
BIOS, we still have to wait for the PHY1 GRC calibration as that is
done as part of the PHY0 init.
v2:
- Use the actual PHY index in the debug message in
broxton_phy_wait_grc_done() (Ville)
Imre Deak [Wed, 20 Apr 2016 17:46:04 +0000 (20:46 +0300)]
drm/i915/bxt: Use PHY0 GRC value for HW state verification
It's possible that BIOS enables PHY1 only to read out the GRC value from
it to be used in PHY0 and then disables PHY1. In this case we can't use
the PHY1 GRC value for state verification, so use instead the one in PHY0
always.
Imre Deak [Wed, 20 Apr 2016 17:27:57 +0000 (20:27 +0300)]
drm/i915/bxt: Enable DC5 during runtime resume
Right after runtime resume we know that we can re-enable DC5, since we
just disabled DC9 and power well 2 is disabled. So enable DC5 explicitly
instead of delaying this until the next time we disable power well 2.
Imre Deak [Wed, 20 Apr 2016 17:27:56 +0000 (20:27 +0300)]
drm/i915/bxt: Sanitize DC state tracking during system resume
After suspend-to-ram or -disk we don't know what power state the display
HW will be, DC0 or DC9 are both possible states, so reset the software
DC state tracking in these cases. This gets rid of 'DC state mismatch'
error messages during resuming from ram or disk where we expected to be
in DC9 (as set by the suspend handler) but we are in DC0.
v2:
- Remove extra WS in gen9_sanitize_dc_state() (Bob)
Imre Deak [Wed, 20 Apr 2016 17:27:55 +0000 (20:27 +0300)]
drm/i915/bxt: Don't uninit/init display core twice during system suspend/resume
Atm, we run the BSpec display core uninit/init sequences twice during
system suspend/resume. While this shouldn't cause any problem, it's
redundant, so get rid of the duplicate call.
Imre Deak [Wed, 20 Apr 2016 17:27:54 +0000 (20:27 +0300)]
drm/i915: Inline intel_suspend_complete
Initially we thought that the platform specific suspend/resume sequences
can be shared between the runtime and system suspend/resume handlers.
This turned out to be not true, we have quite a few differences on most
of the platforms. This was realized already earlier by Paulo who
inlined the platform specific resume_prepare handlers. We have the
same problem with the corresponding suspend_complete handlers, there are
platform differences that make it unfeasible to share the code between
the runtime and system suspend paths. Also now we call functions that
need to be paired like hsw_enable_pc8()/hsw_disable_pc8() from different
levels of the call stack, which is confusing. Fix this by inlining the
suspend_complete handlers too.
This is also needed by the next patch that removes a redundant
uninit/init call during system suspend/resume on BXT.
Imre Deak [Tue, 19 Apr 2016 10:00:36 +0000 (13:00 +0300)]
drm/i915/kbl: Don't WARN for expected secondary MISC IO power well request
In commit 5f304c873634 ("drm/i915/kbl: Reset secondary power well requests
left on by DMC/KVMR") I forgot about the fact that SKL==KBL most of the
time and that a secondary MISC IO power well request left on by the DMC is
"expected". Tune down the corresponding WARN to be a debug message. This
was caught by CI suspend tests.
Mika Kahola [Wed, 20 Apr 2016 12:39:02 +0000 (15:39 +0300)]
drm/i915: Fix eDP low vswing for Broadwell
It was noticed on bug #94087 that module parameter
i915.edp_vswing=2 that should override the VBT setting
to use default voltage swing (400 mV) was not applied
for Broadwell.
This patch provides a fix for this by checking if default
i.e. higher voltage swing is requested to be used and
applies the DDI translations table for DP instead of eDP
(low vswing) table.
v2: Combine two if statements into one (Jani)
v3: Change dev_priv->edp_low_vswing to use dev_priv->vbt.edp.low_vswing
Dave Gordon [Tue, 12 Apr 2016 13:46:16 +0000 (14:46 +0100)]
drm/i915: check for ERR_PTR from i915_gem_object_pin_map()
The newly-introduced function i915_gem_object_pin_map() returns an
ERR_PTR (not NULL) if the pin-and-map opertaion fails, so that's what we
must check for. And it's nicer not to assign such a pointer-or-error to
a structure being filled in until after it's been validated, so we
should keep it local and avoid exporting a bogus pointer. Also, for
clarity and symmetry, we should clear 'virtual_start' along with 'vma'
when unmapping a ringbuffer.
Signed-off-by: Dave Gordon <david.s.gordon@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Alex Dai [Tue, 19 Apr 2016 15:08:35 +0000 (16:08 +0100)]
drm/i915/guc: drop cached copy of 'wq_head'
Now that we keep the GuC client process descriptor permanently mapped,
we don't really need to keep a local copy of the GuC's work-queue-head.
So we can simplify the code a little by not doing this.
Signed-off-by: Alex Dai <yu.dai@intel.com> Signed-off-by: Dave Gordon <david.s.gordon@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Dave Gordon [Tue, 19 Apr 2016 15:08:34 +0000 (16:08 +0100)]
drm/i915/guc: keep GuC doorbell & process descriptor mapped in kernel
Don't use kmap_atomic() for doorbell & process descriptor access.
This patch fixes the BUG shown below, where the thread could sleep
while holding a kmap_atomic mapping. In order not to need to call
kmap_atomic() in this code path, we now set up a permanent kernel
mapping of the shared doorbell and process-descriptor page, and
use that in all doorbell and process-descriptor related code.
Chris Wilson [Wed, 20 Apr 2016 11:09:52 +0000 (12:09 +0100)]
drm/i915/shrinker: Only shmemfs objects are backed by swap
Since we can only swap out shmemfs objects, those are the only ones that
can influence the ability of the shrinker to free pages. Currently, all
non-shmemfs objects have a raised pages_pin_count to protect them from
the shrinker, so this just makes the logic for can_release_pages()
clearer (and safer in future so that we don't over estimate our ability
to free up pages from future non-swappable objects).
Chris Wilson [Wed, 20 Apr 2016 11:09:51 +0000 (12:09 +0100)]
drm/i915/shrinker: Report "unevictable" pages
Inside the shrinker we call can_release_pages() to indicate whether or
not we can make forward progress in freeing up memory by unbinding that
object. When adding our report to oom, we should be using the same
logic.
Whilst here, change the reporting from bytes to pages so that it looks
smaller to the user!, is consistent with the neighbouring oom report
itself which displays counts in pages, and makes the unsigned long
overflow less likely.
Chris Wilson [Wed, 20 Apr 2016 11:09:50 +0000 (12:09 +0100)]
drm/i915/shrinker: Only report objects with extra pinned pages as pinned
When iterating over the bound list, we expect all objects there to have
their pages pinned (by the bound VMA). So only report those objects with
additional pin count on their pages as "pinned". These should be those
objects used for display and hardware access.
drm/i915/gen8+: Do not enable DPF interrupt since the handler does not exist
Looks like DPF was not implemented for gen8+ but the IER and IMR
are still enabled on initialization.
Since there is no code to handle this interrupt, gate the irq
enablement behind HAS_L3_DPF in case the feature gets enabled
in the future.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
projects / linux-beck.git / log