OSDN Git Service
Chris Wilson [Sun, 14 Aug 2016 17:44:41 +0000 (18:44 +0100)]
drm/i915: Unbind closed vma for i915_gem_object_unbind()
Closed vma are removed from the obj->vma_list so that they cannot be
found by userspace. However, this means that when forcibly unbinding an
object, we have to wait upon all rendering to that object first in order
for the closed, but active, vma to be reaped and their bindings removed.
Reported-by: Matthew Auld <matthew.auld@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97343
Fixes:
aa653a685d81 ("drm/i915: Be more careful when unbinding vma")
Fixes:
8a3b3d576c93 (" drm/i915: Convert non-blocking userptr waits...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471196681-30043-2-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Tested-by: Matthew Auld <matthew.auld@intel.com>
Chris Wilson [Sun, 14 Aug 2016 17:44:40 +0000 (18:44 +0100)]
drm/i915: Initialize return value for empty i915_gem_object_unbind()
If the obj->vma_list is empty, we immediately return ret. However, we
are doing so having never set it to any value, it should be zero!
Reported-by: Matthew Auld <matthew.auld@intel.com>
References: https://bugs.freedesktop.org/show_bug.cgi?id=97343
Fixes:
aa653a685d81 ("drm/i915: Be more careful when unbinding vma")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471196681-30043-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Chris Wilson [Fri, 12 Aug 2016 11:39:59 +0000 (12:39 +0100)]
drm/i915: Use SSE4.1 movntdqa to accelerate reads from WC memory
This patch provides the infrastructure for performing a 16-byte aligned
read from WC memory using non-temporal instructions introduced with sse4.1.
Using movntdqa we can bypass the CPU caches and read directly from memory
and ignoring the page attributes set on the CPU PTE i.e. negating the
impact of an otherwise UC access. Copying using movntdqa from WC is almost
as fast as reading from WB memory, modulo the possibility of both hitting
the CPU cache or leaving the data in the CPU cache for the next consumer.
(The CPU cache itself my be flushed for the region of the movntdqa and on
later access the movntdqa reads from a separate internal buffer for the
cacheline.) The write back to the memory is however cached.
This will be used in later patches to accelerate accessing WC memory.
v2: Report whether the accelerated copy is successful/possible.
v3: Function alignment override was only necessary when using the
function target("sse4.1") - which is not necessary for emitting movntdqa
from __asm__.
v4: Improve notes on CPU cache behaviour vs non-temporal stores.
v5: Fix byte offsets for unrolled moves.
v6: Find all remaining typos of "movntqda", use kernel_fpu_begin.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Damien Lespiau <damien.lespiau@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471001999-17787-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 12 Aug 2016 11:39:58 +0000 (12:39 +0100)]
drm/i915: Support for creating write combined type vmaps
vmaps has a provision for controlling the page protection bits, with which
we can use to control the mapping type, e.g. WB, WC, UC or even WT.
To allow the caller to choose their mapping type, we add a parameter to
i915_gem_object_pin_map - but we still only allow one vmap to be cached
per object. If the object is currently not pinned, then we recreate the
previous vmap with the new access type, but if it was pinned we report an
error. This effectively limits the access via i915_gem_object_pin_map to a
single mapping type for the lifetime of the object. Not usually a problem,
but something to be aware of when setting up the object's vmap.
We will want to vary the access type to enable WC mappings of ringbuffer
and context objects on !llc platforms, as well as other objects where we
need coherent access to the GPU's pages without going through the GTT
v2: Remove the redundant braces around pin count check and fix the marker
in documentation (Chris)
v3:
- Add a new enum for the vmalloc mapping type & pass that as an argument to
i915_object_pin_map. (Tvrtko)
- Use PAGE_MASK to extract or filter the mapping type info and remove a
superfluous BUG_ON.(Tvrtko)
v4:
- Rename the enums and clean up the pin_map function. (Chris)
v5: Drop the VM_NO_GUARD, minor cosmetics.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471001999-17787-1-git-send-email-chris@chris-wilson.co.uk
Ville Syrjälä [Thu, 28 Jan 2016 14:30:28 +0000 (16:30 +0200)]
drm/i915: Deal with NV12 CbCr plane AUX surface on SKL+
With NV12 we have two color planes to deal with so we must compute the
surface and x/y offsets for the second plane as well.
What makes this a bit nasty is that the hardware expects the surface
offset to be specified as a distance from the main surface offset.
What's worse, the distance must be non-negative (no neat wraparound or
anything). So we must make sure that the main surface offset is always
less or equal to the AUX surface offset. We do that by computing the AUX
offset first and the main surface offset second. If the main surface
offset ends up being above the AUX offset, we just push it down as far
as is required while still maintaining the required alignment etc.
Fortunately the AUX offset only reuqires 4K alignment, so we don't need
to do any of the backwards searching for an acceptable offset that we
must do for the main surface. And X tiled + NV12 isn't a supported
combination anyway.
Note that this just computes aux surface offsets, we do not yet program
them into the actual hardware registers, and hence we can't yet expose
NV12.
v2: Rebase due to drm_plane_state src/dst rects
s/TODO.../something else/ in the commit message/ (Daniel)
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-12-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Thu, 28 Jan 2016 14:53:54 +0000 (16:53 +0200)]
drm/i915: Compute display surface offset in the plane check hook for SKL+
SKL has nasty limitations with the display surface offsets:
* source x offset + width must be less than the stride for X tiled
surfaces or the display engine falls over
* the surface offset requires lots of alignment (256K or 1M)
These facts mean that we can't just pick any suitably aligned tile
boundary as the offset and expect the resulting x offset to be useable.
The solution is to start with the closest boundary as before, but then
keep searching backwards until we find one that works, or don't. This
means we must be prepared to fail, hence the whole surface offset
calculation needs to be moved to the .check_plane() hook from the
.update_plane() hook.
While at it we can check that the source width/height don't exceed
maximum plane size limits.
We'll store the results of the computation in the plane state to make
it easy for the .update_plane() hook to do its thing.
v2: Replace for+break loop with while loop
Rebase due to drm_plane_state src/dst rects
Rebase due to plane_check_state()
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-11-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Fri, 5 Feb 2016 16:44:05 +0000 (18:44 +0200)]
drm/i915: Make intel_adjust_tile_offset() work for linear buffers
To make life less surprising we can make intel_adjust_tile_offset()
deal with linear buffers as well. Currently it doesn't seem like there's
a real need for this since only X tiling and NV12 (which would always
be tiled currently) should need it. But I've used it for some debug
hacks already so seems like a reasonable thing to have.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-10-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Mon, 8 Feb 2016 16:28:00 +0000 (18:28 +0200)]
drm/i915: Allow calling intel_adjust_tile_offset() multiple times
Minimize the resulting X coordinate after intel_adjust_tile_offset() is
done with it's offset adjustment. This allows calling
intel_adjust_tile_offset() multiple times in case we need to adjust
the offset several times.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-9-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Fri, 22 Jan 2016 16:41:24 +0000 (18:41 +0200)]
drm/i915: Limit fb x offset due to fences
If there's a fence on the object it will be aligned to the start
of the object, and hence CPU rendering to any fb that straddles
the fence edge will come out wrong due to lines wrapping at the
wrong place.
We have no API to manage fences on a sub-object level, so we can't
really fix this in any way. Additonally gen2/3 fences are rather
coarse grained so adjusting the offset migth not even be possible.
Avoid these problems by requiring the fb layout to agree with the
fence layout (if present).
v2: Rebase due to i915_gem_object_get_tiling() & co.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-8-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Thu, 11 Feb 2016 17:16:37 +0000 (19:16 +0200)]
drm/i915: Adjust obj tiling vs. fb modifier rules
Currently we require the object to be X tiled if the fb is X
tiled. The argument is supposedly FBC GTT tracking. But
actually that no longer holds water since FBC supports
Y tiling as well on SKL+.
A better rule IMO is to require that if there is a fence, the
fb modifier match the object tiling mode. But if the object is linear,
we can allow the fb modifier to be anything. The idea being that
if the user set the tiling mode on the object, presumably the intention
is to actually use the fence for CPU access. But if the tiling mode is
not set, the user has no intention of using a fence (and can't actually
since we disallow tiling mode changes when there are framebuffers
associated with the object).
On gen2/3 we must keep to the rule that the object and fb
must be either both linear or both X tiled. No mixing allowed
since the display engine itself will use the fence if it's present.
v2: Fix typos
v3: Rebase due to i915_gem_object_get_tiling() & co.
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-7-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Thu, 4 Feb 2016 18:38:20 +0000 (20:38 +0200)]
drm/i915: Use fb modifiers for display tiling decisions
Soon the fence tiling mode may not always match the fb modifier
even for X tiled buffers. So let's use the fb modifier
consistently for all display tiling decisions.
v2: Rebased due to s/ring/engine/
v3: Rebased due to s/engine/ring/ O_o
v4: Rebase due to i915_gem_object_get_tiling() & co.
Reviewed-by: Matthew Auld <matthew.auld@intel.com> (v1)
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-6-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Wed, 20 Jan 2016 16:02:50 +0000 (18:02 +0200)]
drm/i915: Pass around plane_state instead of fb+rotation
intel_compute_tile_offset() and intel_add_fb_offsets() get passed the fb
and the rotation. As both of those come from the plane state we can just
pass that in instead.
For extra consitency pass the plane state to intel_fb_xy_to_linear() as
well even though it only really needs the fb.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-5-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Thu, 28 Jan 2016 16:33:11 +0000 (18:33 +0200)]
drm/i915: Move SKL hw stride calculation into a helper
We repeat the SKL stride register value calculations a several places.
Move it into a small helper function.
v2: Rebase due to drm_plane_state src/dst rects
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-4-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Tue, 13 Oct 2015 19:48:39 +0000 (22:48 +0300)]
drm/i915: Don't pass pitch to intel_compute_page_offset()
intel_compute_page_offset() can dig up the correct pitch from the fb
itself, no need for the caller to pass it in.
A bit of extra care is needed for the lower level
_intel_compute_page_offset() since that one gets called before the
rotated pitch under intel_fb is populated. Note that we don't actually
call it with anything but DRM_ROTATE_0 there so we wouldn't actually
look up the rotated pitch there, but still, leave the pitch as something
the caller has to pass to _intel_compute_page_offset() as an
indicator that something is a bit special.
This leaves 'stride_div' in the skl plane update hooks as a mostly useless
variable so just get rid of it.
v2: Add a note why stride_div got nuked
v3: Extract intel_fb_pitch() since it can be useful later
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v2)
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-3-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Tue, 15 Sep 2015 10:16:41 +0000 (13:16 +0300)]
drm/i915: Rewrite fb rotation GTT handling
Redo the fb rotation handling in order to:
- eliminate the NV12 special casing
- handle fb->offsets[] properly
- make the rotation handling easier for the plane code
To achieve these goals we reduce intel_rotation_info to only contain
(for each plane) the rotated view width,height,stride in tile units,
and the page offset into the object where the plane starts. Each plane
is handled exactly the same way, no special casing for NV12 or other
formats. We then store the computed rotation_info under
intel_framebuffer so that we don't have to recompute it again.
To handle fb->offsets[] we treat them as a linear offsets and convert
them to x/y offsets from the start of the relevant GTT mapping (either
normal or rotated). We store the x/y offsets under intel_framebuffer,
and for some extra convenience we also store the rotated pitch (ie.
tile aligned plane height). So for each plane we have the normal
x/y offsets, rotated x/y offsets, and the rotated pitch. The normal
pitch is available already in fb->pitches[].
While we're gathering up all that extra information, we can also easily
compute the storage requirements for the framebuffer, so that we can
check that the object is big enough to hold it.
When it comes time to deal with the plane source coordinates, we first
rotate the clipped src coordinates to match the relevant GTT view
orientation, then add to them the fb x/y offsets. Next we compute
the aligned surface page offset, and as a result we're left with some
residual x/y offsets. Finally, if required by the hardware, we convert
the remaining x/y offsets into a linear offset.
For gen2/3 we simply skip computing the final page offset, and just
convert the src+fb x/y offsets directly into a linear offset since
that's what the hardware wants.
After this all platforms, incluing SKL+, compute these things in exactly
the same way (excluding alignemnt differences).
v2: Use BIT(DRM_ROTATE_270) instead of ROTATE_270 when rotating
plane src coordinates
Drop some spurious changes that got left behind during
development
v3: Split out more changes to prep patches (Daniel)
s/intel_fb->plane[].foo.bar/intel_fb->foo[].bar/ for brevity
Rename intel_surf_gtt_offset to intel_fb_gtt_offset
Kill the pointless 'plane' parameter from intel_fb_gtt_offset()
v4: Fix alignment vs. alignment-1 when calling
_intel_compute_tile_offset() from intel_fill_fb_info()
Pass the pitch in tiles in
stad of pixels to intel_adjust_tile_offset() from intel_fill_fb_info()
Pass the full width/height of the rotated area to
drm_rect_rotate() for clarity
Use u32 for more offsets
v5: Preserve the upper_32_bits()/lower_32_bits() handling for the
fb ggtt offset (Sivakumar)
v6: Rebase due to drm_plane_state src/dst rects
Cc: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470821001-25272-2-git-send-email-ville.syrjala@linux.intel.com
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Mon, 8 Aug 2016 10:58:39 +0000 (13:58 +0300)]
drm/i915: Account for TSEG size when determining 865G stolen base
Looks like the TSEG lives just above TOUD, stolen comes after TSEG.
The spec seems somewhat self-contradictory in places, in the ESMRAMC
register desctription it says:
TSEG Size:
10=(TOUD + 512 KB) to TOUD
11 =(TOUD + 1 MB) to TOUD
so that agrees with TSEG being at TOUD. But the example given
elsehwere in the spec says:
TOUD equals 62.5 MB = 03E7FFFFh
TSEG selected as 512 KB in size,
Graphics local memory selected as 1 MB in size
General System RAM available in system = 62.5 MB
General system RAM range00000000h to 03E7FFFFh
TSEG address range03F80000h to 03FFFFFFh
TSEG pre-allocated from03F80000h to 03FFFFFFh
Graphics local memory pre-allocated from03E80000h to 03F7FFFFh
so here we have TSEG above stolen.
Real world evidence agrees with the TOUD->TSEG->stolen order however, so
let's fix up the code to account for the TSEG size.
Cc: Taketo Kabe <fdporg@vega.pgw.jp>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: stable@vger.kernel.org
Fixes:
0ad98c74e093 ("drm/i915: Determine the stolen memory base address on gen2")
Fixes:
a4dff76924fe ("x86/gpu: Add Intel graphics stolen memory quirk for gen2 platforms")
Reported-by: Taketo Kabe <fdporg@vega.pgw.jp>
Tested-by: Taketo Kabe <fdporg@vega.pgw.jp>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=96473
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470653919-27251-1-git-send-email-ville.syrjala@linux.intel.com
Link: http://download.intel.com/design/chipsets/datashts/25251405.pdf
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tvrtko Ursulin [Wed, 10 Aug 2016 15:16:46 +0000 (16:16 +0100)]
drm/i915/guc: Consolidate firmware major-minor to one place
Currently to change the firmware one has to update the exported
module firmware string and the major-minor versions used for
verification after load. Consolidate that to a single place
defining correct major and minor versions per platform.
v2: Rebased for KBL.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Dave Gordon <david.s.gordon@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Peter Antoine <peter.antoine@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470842206-35685-1-git-send-email-tvrtko.ursulin@linux.intel.com
Tvrtko Ursulin [Wed, 10 Aug 2016 15:22:10 +0000 (16:22 +0100)]
drm/i915: Store number of active engines in device info
Until now code was calling hweight32 to figure out the
number from device_info->ring_mask at runtime. Instead
we can cache it at engine init time and use directly.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1470842530-35854-1-git-send-email-tvrtko.ursulin@linux.intel.com
Chris Wilson [Wed, 10 Aug 2016 12:41:46 +0000 (13:41 +0100)]
drm/i915: Move setting of request->batch into its single callsite
request->batch_obj is only set by execbuffer for the convenience of
debugging hangs. By moving that operation to the callsite, we can
simplify all other callers and future patches. We also move the
complications of reference handling of the request->batch_obj next to
where the active tracking is set up for the request.
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/1470832906-13972-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Wed, 10 Aug 2016 12:41:45 +0000 (13:41 +0100)]
drm/i915: Mark unmappable GGTT entries as PIN_HIGH
We allocate a few objects into the GGTT that we never need to access via
the mappable aperture (such as contexts, status pages). We can request
that these are bound high in the VM to increase the amount of mappable
aperture available. However, anything that may be frequently pinned
(such as logical contexts) we want to use the fast search & insert.
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/1470832906-13972-1-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Wed, 10 Aug 2016 12:58:24 +0000 (13:58 +0100)]
drm/i915: Fix nesting of rps.mutex and struct_mutex during powersave init
During intel_gt_powersave_init() we take the RPS mutex to ensure that
all locking requirements are met as we talk to the punit, but we also
require the struct_mutex for allocating a slice of the global GTT for a
power context on Valleyview. struct_mutex must be the outer lock here,
as we nest rps.mutex inside later on.
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Fixes:
773ea9a80132 ("drm/i915: Perform static RPS frequency setup before...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470833904-29886-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Imre Deak [Wed, 10 Aug 2016 11:07:34 +0000 (14:07 +0300)]
drm/i915: Remove LVDS and PPS suspend time save/restore
In the preceding patches we made sure that:
- the LVDS encoder takes care of reiniting both the LVDS register
and its PPS
- the eDP encoder takes care of reiniting its PPS
- the PPS register unlocking workaround is applied explicitly whenever
the PPS context is lost
Based on the above we can safely remove the opaque LVDS and PPS save /
restore from generic code.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-6-git-send-email-imre.deak@intel.com
Imre Deak [Wed, 10 Aug 2016 11:07:33 +0000 (14:07 +0300)]
drm/i915: Apply the PPS register unlock workaround more consistently
Atm, we apply this workaround somewhat inconsistently at the following
points: driver loading, LVDS init, eDP PPS init, system resume. As this
workaround also affects registers other than PPS (timing, PLL) a more
consistent way is to apply it early after the PPS HW context is known to
be lost: driver loading, system resume and on VLV/CHV/BXT when turning
on power domains.
This is needed by the next patch that removes saving/restoring of the
PP_CONTROL register.
This also removes the incorrect programming of the workaround on HSW+
PCH platforms which don't have the register locking mechanism.
v2: (Ville)
- Don't apply the workaround on BXT.
- Simplify platform checks using HAS_DDI().
v3:
- Move the call of intel_pps_unlock_regs_wa() to the more
logical vlv_display_power_well_init() (also fixing CHV) (Ville).
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-5-git-send-email-imre.deak@intel.com
Imre Deak [Wed, 10 Aug 2016 11:07:32 +0000 (14:07 +0300)]
drm/i915/dp: Restore PPS HW state from the encoder resume hook
Similarly to the previous patch, initialize the PPS from the DP
encoder's resume hook. Note that as opposed to LVDS we can't do this
during encoder enabling, since we need the PPS for DP detection as well.
The PPS init code is now the same for init and resume, so factor out a
new intel_dp_pps_init() helper for this.
v2:
- Factor out intel_dp_pps_init() (Ville).
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-4-git-send-email-imre.deak@intel.com
Imre Deak [Wed, 10 Aug 2016 11:07:31 +0000 (14:07 +0300)]
drm/i915/lvds: Restore initial HW state during encoder enabling
Atm the LVDS encoder depends on the PPS HW context being saved/restored
from generic suspend/resume code. Since the PPS is specific to the LVDS
and eDP encoders a cleaner way is to reinitialize it during encoder
enabling, so do this here for LVDS. Follow-up patches will init the PPS
for the eDP encoder similarly and remove the suspend/resume time save /
restore.
v2:
- Apply BSpec +1 offset and use DIV_ROUND_UP() when programming the
power cycle delay. (Ville)
v3: (Ville)
- Fix +1 vs. round-up order.
- s/reset_on_powerdown/powerdown_on_reset/
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-3-git-send-email-imre.deak@intel.com
Imre Deak [Wed, 10 Aug 2016 11:07:30 +0000 (14:07 +0300)]
drm/i915: Merge TARGET_POWER_ON and PANEL_POWER_ON flag definitions
These two flags mean the same thing, so remove the duplication.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-2-git-send-email-imre.deak@intel.com
Imre Deak [Wed, 10 Aug 2016 11:07:29 +0000 (14:07 +0300)]
drm/i915: Merge the PPS register definitions
The PPS registers are pretty much the same everywhere, the differences
being:
- Register fields appearing, disappearing from one platform to the
next: panel-reset-on-powerdown, backlight-on, panel-port,
register-unlock
- Different register base addresses
- Different number of PPS instances: 2 on VLV/CHV/BXT, 1 everywhere
else.
We can merge the separate set of PPS definitions by extending the PPS
instance argument to all platforms and using instance 0 on platforms
with a single instance. This means we'll need to calculate the register
addresses dynamically based on the given platform and PPS instance.
v2:
- Simplify if ladder in intel_pps_get_registers(). (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470827254-21954-1-git-send-email-imre.deak@intel.com
Dave Gordon [Tue, 9 Aug 2016 14:19:23 +0000 (15:19 +0100)]
drm/i915/guc: re-optimise i915_guc_client layout
As we're tweaking the GuC-related code in debugfs, we can
drop the no-longer-used 'q_fail' and repack the structure.
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, 9 Aug 2016 14:19:22 +0000 (15:19 +0100)]
drm/i915/guc: use for_each_engine_id() where appropriate
Now that host structures are indexed by host engine-id rather than
guc_id, we can usefully convert some for_each_engine() loops to use
for_each_engine_id() and avoid multiple dereferences of engine->id.
Also a few related tweaks to cache structure members locally wherever
they're used more than once or twice, hopefully eliminating memory
references.
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, 9 Aug 2016 14:19:21 +0000 (15:19 +0100)]
drm/i915/guc: add engine mask to GuC client & pass to GuC
The Context Descriptor passed by the kernel to the GuC contains a field
specifying which engine(s) the context will use. Historically, this was
always set to "all of them", but if we had a separate client for each
engine, we could be more precise, and set only the bit for the engine
that the client was associated with. So this patch enables this usage,
in preparation for having multiple clients, though at this point there
is still only a single client used for all supported engines.
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, 9 Aug 2016 14:19:20 +0000 (15:19 +0100)]
drm/i915/guc: refactor guc_init_doorbell_hw()
We have essentially the same code in each of two different
loops, so we can refactor it into a little helper function.
This also reduces the amount of work done during startup,
as we now only reprogram h/w found to be in a state other
than that expected, and so avoid the overhead of setting
doorbell registers to the state they're already in.
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, 9 Aug 2016 14:19:19 +0000 (15:19 +0100)]
drm/i915/guc: doorbell reset should avoid used doorbells
guc_init_doorbell_hw() borrows the (currently single) GuC client to use
in reinitialising ALL the doorbell registers (as the hardware doesn't
reset them when the GuC is reset). As a prerequisite for accommodating
multiple clients, it should only reset doorbells that are supposed to be
disabled, avoiding those that are marked as in use by any client.
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>
Chris Wilson [Tue, 9 Aug 2016 16:47:52 +0000 (17:47 +0100)]
drm/i915: Use RCU to annotate and enforce protection for breadcrumb's bh
The bottom-half we use for processing the breadcrumb interrupt is a
task, which is an RCU protected struct. When accessing this struct, we
need to be holding the RCU read lock to prevent it disappearing beneath
us. We can use the RCU annotation to mark our irq_seqno_bh pointer as
being under RCU guard and then use the RCU accessors to both provide
correct ordering of access through the pointer.
Most notably, this fixes the access from hard irq context to use the RCU
read lock, which both Daniel and Tvrtko complained about.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470761272-1245-3-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 16:47:51 +0000 (17:47 +0100)]
drm/i915: Move missed interrupt detection from hangcheck to breadcrumbs
In commit
2529d57050af ("drm/i915: Drop racy markup of missed-irqs from
idle-worker") the racy detection of missed interrupts was removed when
we went idle. This however opened up the issue that the stuck waiters
were not being reported, causing a test case failure. If we move the
stuck waiter detection out of hangcheck and into the breadcrumb
mechanims (i.e. the waiter) itself, we can avoid this issue entirely.
This leaves hangcheck looking for a stuck GPU (inspecting for request
advancement and HEAD motion), and breadcrumbs looking for a stuck
waiter - hopefully make both easier to understand by their segregation.
v2: Reduce the error message as we now run independently of hangcheck,
and the hanging batch used by igt also counts as a stuck waiter causing
extra warnings in dmesg.
v3: Move the breadcrumb's hangcheck kickstart to the first missed wait.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97104
Fixes:
2529d57050af (waiter"drm/i915: Drop racy markup of missed-irqs...")
Testcase: igt/drv_missed_irq
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470761272-1245-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 17:08:25 +0000 (18:08 +0100)]
drm/i915: Always mark the writer as also a read for busy ioctl
One of the few guarantees we want the busy ioctl to provide is that the
reported busy writer is included in the set of busy read engines. This
should be provided by the ordering of setting and retiring the active
trackers, but we can do better by explicitly setting the busy read
engine flag for the last writer.
v2: More comments inside __busy_write_id() to explain why both fields
are set.
Fixes:
3fdc13c7a3cb ("drm/i915: Remove (struct_mutex) locking for busy-ioctl")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470762505-12799-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Dave Gordon [Tue, 9 Aug 2016 17:35:10 +0000 (18:35 +0100)]
drm: avoid "possible bad bitmask?" warning
Recent versions of gcc say this:
include/drm/i915_drm.h:96:34: warning: result of ‘65535 << 20’
requires 37 bits to represent, but ‘int’ only has 32 bits
[-Wshift-overflow=]
Reported-by: David Binderman <linuxdev.baldrick@gmail.com>
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Cc: Dave Airlie <airlied@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470764110-23855-1-git-send-email-david.s.gordon@intel.com
Chris Wilson [Tue, 9 Aug 2016 16:03:22 +0000 (17:03 +0100)]
drm/i915: Correct typo for __i915_gem_active_get_rcu in a comment
I mistyped and added an extra _request_ to __i915_gem_active_get_rcu()
Also, the same happened to another comment for i915_gem_active_get_rcu()
Reported-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470758602-1338-1-git-send-email-chris@chris-wilson.co.uk
Ville Syrjälä [Fri, 5 Aug 2016 20:28:30 +0000 (23:28 +0300)]
drm/i915: Use the g4x+ approach on gen2 for handling display stuff around GPU reset
We don't have GPU reset support for gen2, which means the display
hardware is unaffected when a GPU hang is handled. However as the ring
has in fact stopped, any flips still in the ring will never complete,
and thus the display base address updates will never happen. So we
really need to fix that up manually just like we do on g4x+.
In fact, let's just use intel_has_gpu_reset() instead of IS_GEN2()
since that'll also handle cases where someone would disable the GPU
reset support on gen3/4 for whatever reason.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470428910-12125-5-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Fri, 5 Aug 2016 20:28:29 +0000 (23:28 +0300)]
drm/i915: Introduce gpu_reset_clobbers_display()
Factor out the "does the GPU reset clobber the display?" check into a
small helper.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470428910-12125-4-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Maarten Lankhorst [Fri, 5 Aug 2016 20:28:28 +0000 (23:28 +0300)]
drm/i915: Add a way to test the modeset done during gpu reset, v3.
Add force_reset_modeset_test as a parameter to force the modeset path during gpu reset.
This allows a IGT test to set the knob and trigger a hang to force the gpu reset,
even on platforms that wouldn't otherwise require it.
Changes since v1:
- Split out fix to separate commit.
Changes since v2:
- This commit is purely about force_reset_modeset_test now.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Testcase: drv_hangman.reset-with-forced-modeset
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470428910-12125-3-git-send-email-ville.syrjala@linux.intel.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Maarten Lankhorst [Fri, 5 Aug 2016 20:28:27 +0000 (23:28 +0300)]
drm/i915: Fix modeset handling during gpu reset, v5.
This function would call drm_modeset_lock_all, while the suspend/resume
functions already have their own locking. Fix this by factoring out
__intel_display_resume, and calling the atomic helpers for duplicating
atomic state and disabling all crtc's during suspend.
Changes since v1:
- Deal with -EDEADLK right after lock_all and clean up calls
to hw readout.
- Always take all modeset locks so updates during gpu reset are blocked.
Changes since v2:
- Fix deadlock in intel_update_primary_planes.
- Move WARN_ON(EDEADLK) to __intel_display_resume.
- pctx -> ctx
- only call __intel_display_resume on success in intel_display_resume.
Changes since v3:
- Rebase on top of dev_priv -> dev change.
- Use drm_modeset_lock_all_ctx instead of drm_modeset_lock_all.
Changes since v4 [by vsyrjala]:
- Deal with skip_intermediate_wm
- Update comment w.r.t. mode_config.mutex vs. ->detect()
- Rebase due to INTEL_GEN() etc.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes:
e2c8b8701e2d ("drm/i915: Use atomic helpers for suspend, v2.")
Cc: stable@vger.kernel.org
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470428910-12125-2-git-send-email-ville.syrjala@linux.intel.com
Ville Syrjälä [Fri, 5 Aug 2016 17:00:17 +0000 (20:00 +0300)]
drm/i915: Don't mark PCH underrun reporting as disabled for transcoder B/C on LPT-H
Marking PCH transcoder FIFO underrun reporting as disabled for
transcoder B/C on LPT-H will block us from enabling the south error
interrupt. So let's only mark transcoder A underrun reporting as
disabled initially.
This is a little tricky to hit since you need a machine with LPT-H, and
the BIOS must enable either pipe B or C at boot. Then i915 would mark
the "transcoder B/C" underrun reporting as disabled and never enable it
again, meaning south interrupts would never get enabled either. The only
other interrupt in there is actually the poison interrupt which, if we
could ever trigger it, would just result in a little error in dmesg.
Here's the resulting change in SDEIMR on my HSW when I boot it with
multiple displays attached:
- (0x000c4004): 0xf115ffff
+ (0x000c4004): 0xf114ffff
My previous attempt [1] tried to fix this a little differently, but
Daniel requested I do this instead.
[1] https://lists.freedesktop.org/archives/intel-gfx/2015-November/081420.html
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470416417-15021-1-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ville Syrjälä [Fri, 5 Aug 2016 17:41:34 +0000 (20:41 +0300)]
drm/i915: Add some curly braces
intel_enable_pipe() looks rather confusing when one side doesn't have
the curly braces, and the other one does. And what's even worse,
there's another if-else inside the braceless side. Let's put braces
around it to make it clear which branch goes where.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470418894-1249-1-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Chris Wilson [Tue, 9 Aug 2016 08:23:34 +0000 (09:23 +0100)]
drm/i915: Do not overwrite the request with zero on reallocation
When using RCU lookup for the request, commit
0eafec6d3244 ("drm/i915:
Enable lockless lookup of request tracking via RCU"), we acknowledge that
we may race with another thread that could have reallocated the request.
In order for the first thread not to blow up, the second thread must not
clear the request completed before overwriting it. In the RCU lookup, we
allow for the engine/seqno to be replaced but we do not allow for it to
be zeroed.
The choice we make is to either add extra checking to the RCU lookup, or
embrace the inherent races (as intended). It is more complicated as we
need to manually clear everything we depend upon being zero initialised,
but we benefit from not emiting the memset() to clear the entire
frequently allocated structure (that memset turns up in throughput
profiles). And at the same time, the lookup remains flexible for future
adjustments.
v2: Old style LRC requires another variable to be initialize. (The
danger inherent in not zeroing everything.)
v3: request->batch also needs to be cleared
v4: signaling.tsk is no long used unset, but pid still exists
Fixes:
0eafec6d3244 ("drm/i915: Enable lockless lookup of request...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: "Goel, Akash" <akash.goel@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470731014-6894-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 08:23:33 +0000 (09:23 +0100)]
drm/i915: Add smp_rmb() to busy ioctl's RCU dance
In the debate as to whether the second read of active->request is
ordered after the dependent reads of the first read of active->request,
just give in and throw a smp_rmb() in there so that ordering of loads is
assured.
v2: Explain the manual smp_rmb()
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470731014-6894-1-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 07:37:02 +0000 (08:37 +0100)]
drm/i915: Don't check for idleness before retiring after a GPU hang
When we force the cleanup after a GPU hang, we want to retire all
requests, or else we may leak them if truly wedged (and the GPU never
advances again). Converting to the active request helpers had the issue
of doing the check against busyness before reporting the request, so if
we claim the GPU had hung but this engine hadn't we could potential skip
the request cleanup - triggering the self-check BUG.
Fixes:
dcff85c8443e ("drm/i915: Enable i915_gem_wait_for_idle() ...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470728222-10243-3-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 07:37:01 +0000 (08:37 +0100)]
drm/i915: Wrap the protected active RCU dereference in a helper
As we do the lockdep protected RCU lookup in a couple of places,
refactor that code to a common helper i915_gem_active_raw().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470728222-10243-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Tue, 9 Aug 2016 07:37:00 +0000 (08:37 +0100)]
drm/i915: Remove unused i915_gem_active_peek_rcu()
This was originally introduced to be used by the busy-ioctl, but in the
end busy ioctl performed a different dance. Since there are no users,
and no likely users, remove an unwanted chunk of the API.
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470728222-10243-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel Vetter [Mon, 8 Aug 2016 07:37:31 +0000 (09:37 +0200)]
drm/i915: Update DRIVER_DATE to
20160808
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Matthew Auld [Fri, 5 Aug 2016 18:04:40 +0000 (19:04 +0100)]
drm/i915: fix aliasing_ppgtt leak
In i915_ggtt_cleanup_hw we need to remember to free aliasing_ppgtt. This
fixes the following kmemleak message:
unreferenced object 0xffff880213cca000 (size 8192):
comm "modprobe", pid 1298, jiffies
4294745402 (age 703.930s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<
ffffffff817c808e>] kmemleak_alloc+0x4e/0xb0
[<
ffffffff8121f9c2>] kmem_cache_alloc_trace+0x142/0x1d0
[<
ffffffffa06d11ef>] i915_gem_init_ggtt+0x10f/0x210 [i915]
[<
ffffffffa06d71bb>] i915_gem_init+0x5b/0xd0 [i915]
[<
ffffffffa069749a>] i915_driver_load+0x97a/0x1460 [i915]
[<
ffffffffa06a26ef>] i915_pci_probe+0x4f/0x70 [i915]
[<
ffffffff81423015>] local_pci_probe+0x45/0xa0
[<
ffffffff81424463>] pci_device_probe+0x103/0x150
[<
ffffffff81515e6c>] driver_probe_device+0x22c/0x440
[<
ffffffff81516151>] __driver_attach+0xd1/0xf0
[<
ffffffff8151379c>] bus_for_each_dev+0x6c/0xc0
[<
ffffffff8151555e>] driver_attach+0x1e/0x20
[<
ffffffff81514fa3>] bus_add_driver+0x1c3/0x280
[<
ffffffff81516aa0>] driver_register+0x60/0xe0
[<
ffffffff8142297c>] __pci_register_driver+0x4c/0x50
[<
ffffffffa013605b>] 0xffffffffa013605b
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Fixes:
b18b6bde300e ("drm/i915/bdw: Free PPGTT struct")
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470420280-21417-1-git-send-email-matthew.auld@intel.com
Daniel Vetter [Fri, 5 Aug 2016 16:11:24 +0000 (18:11 +0200)]
drm/i915: Update comment before i915_spin_request
~jiffie and a few usecs is 3 orders of magnitude different. A bit
much. This was changed in
commit
ca5b721e238226af1d767103ac852aeb8e4c0764
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Dec 11 11:32:58 2015 +0000
drm/i915: Limit the busy wait on requests to 5us not 10ms!
But probably missed the comment since the change was non-local to the
comment.
v2: Polish comment more (Chris).
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470413484-23775-1-git-send-email-daniel.vetter@ffwll.ch
Rodrigo Vivi [Wed, 3 Aug 2016 17:00:56 +0000 (10:00 -0700)]
drm/i915: Use drm official vblank_no_hw_counter callback.
No functional change. Instead of defining a new empty function
let's use what is available on drm.
It gets cleaner, and easy to read, and understand.
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Rodrigo Vivi [Wed, 3 Aug 2016 15:22:57 +0000 (08:22 -0700)]
drm/i915: Fix copy_to_user usage for pipe_crc
Copy to user return the number of bytes it couldn't write
and zero on success. So any number different than 0 should
be considered a fault, not only when it doesn't write
the full size.
v2: fixed the inverted logic. (Ville)
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Ville Syrjälä [Fri, 5 Aug 2016 16:05:42 +0000 (19:05 +0300)]
Revert "drm/i915: Track active streams also for DP SST"
This reverts commit
f64425a82bdb5c3d7e09ba765716da88a9b00eec.
active_streams will get totally out of whack with SST unless we
sync up with the hw state at readout, obviously! We don't yet
do that, so now the WARNs fire all the time. Let's revert :(
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470413142-26402-1-git-send-email-ville.syrjala@linux.intel.com
References: https://bugs.freedesktop.org/show_bug.cgi?id=95472#c14
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Matthew Auld [Tue, 2 Aug 2016 08:36:53 +0000 (09:36 +0100)]
drm/i915: fix WaInsertDummyPushConstPs
As pointed out by Chris Harris, we are using the wrong WA name, it
should in fact be WaToEnableHwFixForPushConstHWBug, also it should be
applied from C0 onwards for both BXT and KBL.
Fixes:
7b9005cd45f3 ("drm/i915: Add WaInsertDummyPushConstP for bxt and kbl")
Cc: Chris Harris <chris.harris@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reported-by: Chris Harris <chris.harris@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470127013-29653-1-git-send-email-matthew.auld@intel.com
Chris Wilson [Fri, 5 Aug 2016 09:14:24 +0000 (10:14 +0100)]
drm/i915: Assert that the request hasn't been retired
With all callers now not playing tricks with dropping the struct_mutex
between waiting and retiring, we can assert that the request is ready to
be retired.
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/1470388464-28458-19-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:23 +0000 (10:14 +0100)]
drm/i915: Repack fence tiling mode and stride into a single integer
In the previous commit, we moved the obj->tiling_mode out of a bitfield
and into its own integer so that we could safely use READ_ONCE(). Let us
now repair some of that damage by sharing the tiling_mode with its
companion, the fence stride.
v2: New magic
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/1470388464-28458-18-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:22 +0000 (10:14 +0100)]
drm/i915: Document and reject invalid tiling modes
Through the GTT interface to the fence registers, we can only handle
linear, X and Y tiling. The more esoteric tiling patterns are ignored.
Document that the tiling ABI only supports upto Y tiling, and reject any
attempts to set a tiling mode other than NONE, X or Y.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-17-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:21 +0000 (10:14 +0100)]
drm/i915: Remove locking for get_tiling
Since we are not concerned with userspace racing itself with set-tiling
(the order is indeterminant even if we take a lock), then we can safely
read back the single obj->tiling_mode and do the static lookup of
swizzle mode without having to take a lock.
get-tiling is reasonably frequent due to the back-channel passing around
of tiling parameters in DRI2/DRI3.
v2: Make tiling_mode a full unsigned int so that we can trivially use it
with READ_ONCE(). Separating it out into manual control over the flags
field was too noisy for a simple patch. Note that we could use the lower
bits of obj->stride for the tiling mode.
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/1470388464-28458-16-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:20 +0000 (10:14 +0100)]
drm/i915: Remove pinned check from madvise ioctl
We don't need to incur the overhead of checking whether the object is
pinned prior to changing its madvise. If the object is pinned, the
madvise will not take effect until it is unpinned and so we cannot free
the pages being pointed at by hardware. Marking a pinned object with
allocated pages as DONTNEED will not trigger any undue warnings. The check
is therefore superfluous, and by removing it we can remove a linear walk
over all the vma the object has.
Still despite it being an overzealous check, that error code is part of
the current ABI and so we must proceed with caution.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-15-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:19 +0000 (10:14 +0100)]
drm/i915: Reduce locking inside swfinish ioctl
We only need to take the struct_mutex if the object is pinned to the
display engine and so requires checking for clflush. (The race with
userspace pinning the object to a framebuffer is irrelevant.)
v2: Use access once for compiler hints (or not as it is a bitfield)
v3: READ_ONCE, obj->pin_display is not a bitfield anymore
v4: Don't be creative with goto.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-14-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:18 +0000 (10:14 +0100)]
drm/i915: Remove (struct_mutex) locking for busy-ioctl
By applying the same logic as for wait-ioctl, we can query whether a
request has completed without holding struct_mutex. The biggest impact
system-wide is removing the flush_active and the contention that causes.
Testcase: igt/gem_busy
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-13-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:17 +0000 (10:14 +0100)]
drm/i915: Remove (struct_mutex) locking for wait-ioctl
With a bit of care (and leniency) we can iterate over the object and
wait for previous rendering to complete with judicial use of atomic
reference counting. The ABI requires us to ensure that an active object
is eventually flushed (like the busy-ioctl) which is guaranteed by our
management of requests (i.e. everything that is submitted to hardware is
flushed in the same request). All we have to do is ensure that we can
detect when the requests are complete for reporting when the object is
idle (without triggering ETIME), locklessly - this is handled by
i915_gem_active_wait_unlocked().
The impact of this is actually quite small - the return to userspace
following the wait was already lockless and so we don't see much gain in
latency improvement upon completing the wait. What we do achieve here is
completing an already finished wait without hitting the struct_mutex,
our hold is quite short and so we are typically just a victim of
contention rather than a cause - but it is still one less contention
point!
v2: Break up a long line.
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/1470388464-28458-12-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:16 +0000 (10:14 +0100)]
drm/i915: Do a nonblocking wait first in pread/pwrite
If we try and read or write to an active request, we first must wait
upon the GPU completing that request. Let's do that without holding the
mutex (and so allow someone else to access the GPU whilst we wait). Upon
completion, we will acquire the mutex and only then start the operation
(i.e. we do not rely on state from before the initial wait).
v2: Repaint the goto labels
v3: Move the tracepoints back to the start of the ioctls
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/1470388464-28458-11-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:15 +0000 (10:14 +0100)]
drm/i915: Remove unused no-shrinker-steal
After removing the user of this wart, we can remove the wart entirely.
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/1470388464-28458-10-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:14 +0000 (10:14 +0100)]
drm/i915: Tidy generation of the GTT mmap offset
If we make the observation that mmap-offsets are only released when we
free an object, we can then deduce that the shrinker only creates free
space in the mmap arena indirectly by flushing the request list and
freeing expired objects. If we combine this with the lockless
vma-manager and lockless idling, we can avoid taking our big struct_mutex
until we need to actually free the requests.
One side-effect is that we defer the madvise checking until we need the
pages (i.e. the fault handler). This brings us into line with the other
delayed checks (and madvise in general).
v2: s/ret/err/ and use if (!err) rather than if (ret == 0)
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/1470388464-28458-9-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:13 +0000 (10:14 +0100)]
drm/i915/shrinker: Wait before acquiring struct_mutex under oom
We can now wait for the GPU (all engines) to become idle without
requiring the struct_mutex. Inside the shrinker, we need to currently
take the struct_mutex in order to purge objects and to purge the objects
we need the GPU to be idle - causing a stall whilst we hold the
struct_mutex. We can hide most of that stall by performing the wait
before taking the struct_mutex and only doing essential waits for
new rendering on objects to be freed.
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/1470388464-28458-8-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:12 +0000 (10:14 +0100)]
drm/i915: Simplify do_idling() (Ironlake vt-d w/a)
Now that we pass along the expected interruptible nature for the
wait-for-idle, we do not need to modify the global
i915->mm.interruptible for this single call. (Only the immediate call to
i915_gem_wait_for_idle() takes the interruptible status as the other
action, dma_map_sg(), is independent of i915.ko)
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/1470388464-28458-7-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:11 +0000 (10:14 +0100)]
drm/i915: Enable i915_gem_wait_for_idle() without holding struct_mutex
The principal motivation for this was to try and eliminate the
struct_mutex from i915_gem_suspend - but we still need to hold the mutex
current for the i915_gem_context_lost(). (The issue there is that there
may be an indirect lockdep cycle between cpu_hotplug (i.e. suspend) and
struct_mutex via the stop_machine().) For the moment, enabling last
request tracking for the engine, allows us to do busyness checking and
waiting without requiring the struct_mutex - which is useful in its own
right.
As a side-effect of having a robust means for tracking engine busyness,
we can replace our other busyness heuristic, that of comparing against
the last submitted seqno. For paranoid reasons, we have a semi-ordered
check of that seqno inside the hangchecker, which we can now improve to
an ordered check of the engine's busyness (removing a locked xchg in the
process).
v2: Pass along "bool interruptible" as being unlocked we cannot rely on
i915->mm.interruptible being stable or even under our control.
v3: Replace check Ironlake i915_gpu_busy() with the common precalculated value
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/1470388464-28458-6-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:10 +0000 (10:14 +0100)]
drm/i915: Remove forced stop ring on suspend/unload
Before suspending (or unloading), we would first wait upon all rendering
to be completed and then disable the rings. This later step is a remanent
from DRI1 days when we did not use request tracking for all operations
upon the ring. Now that we are sure we are waiting upon the very last
operation by the engine, we can forgo clobbering the ring registers,
though we do keep the assert that the engine is indeed idle before
sleeping.
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/1470388464-28458-5-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:09 +0000 (10:14 +0100)]
drm/i915/userptr: Remove superfluous interruptible=false on waiting
Inside the kthread context, we can't be interrupted by signals so
touching the mm.interruptible flag is pointless and wait-request now
consumes EIO itself.
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/1470388464-28458-4-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:08 +0000 (10:14 +0100)]
drm/i915: Convert non-blocking userptr waits for requests over to using RCU
We can completely avoid taking the struct_mutex around the non-blocking
waits by switching over to the RCU request management (trading the mutex
for a RCU read lock and some complex atomic operations). The improvement
is that we gain further contention reduction, and overall the code
become simpler due to the reduced mutex dancing.
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/1470388464-28458-3-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:07 +0000 (10:14 +0100)]
drm/i915: Convert non-blocking waits for requests over to using RCU
We can completely avoid taking the struct_mutex around the non-blocking
waits by switching over to the RCU request management (trading the mutex
for a RCU read lock and some complex atomic operations). The improvement
is that we gain further contention reduction, and overall the code
become simpler due to the reduced mutex dancing.
v2: Move i915_gem_fault tracepoint back to the start of the function,
before the unlocked wait.
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/1470388464-28458-2-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Fri, 5 Aug 2016 09:14:06 +0000 (10:14 +0100)]
drm/i915: Introduce i915_gem_active_wait_unlocked()
It is useful to be able to wait on pending rendering without grabbing
the struct_mutex. We can do this by using the i915_gem_active_get_rcu()
primitive to acquire a reference to the pending request without
requiring struct_mutex, just the RCU read lock, and then call
i915_wait_request().
v2: Rebase onto new i915_gem_active_get_unlocked() semantics that take
the RCU read lock on behalf of the caller.
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/1470388464-28458-1-git-send-email-chris@chris-wilson.co.uk
Daniel Vetter [Fri, 5 Aug 2016 08:36:15 +0000 (10:36 +0200)]
Merge remote-tracking branch 'airlied/drm-next' into drm-intel-next-queued
Backmerge the 4.8 pull request state from Dave - conflicts were
getting out of hand, and Chris has some patches which outright don't
apply without everything merged together again.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Ville Syrjälä [Tue, 2 Aug 2016 12:21:57 +0000 (15:21 +0300)]
drm/i915: Fix iboost setting for SKL Y/U DP DDI buffer translation entry 2
The spec was recently fixed to have the correct iboost setting for the
SKL Y/U DP DDI buffer translation table entry 2. Update our tables
to match.
Cc: David Weinehall <david.weinehall@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470140517-13011-1-git-send-email-ville.syrjala@linux.intel.com
Cc: stable@vger.kernel.org
Reviewed-by: David Weinehall <david.weinehall@linux.intel.com>
Matt Roper [Thu, 4 Aug 2016 21:08:00 +0000 (14:08 -0700)]
drm/i915/gen9: Give one extra block per line for SKL plane WM calculations
The bspec was updated a couple weeks ago to add an extra block per line
to plane watermark calculations for linear pixel formats.
Bspec update 115327 description:
"Gen9+ - Updated the plane blocks per line calculation for linear
cases. Adds +1 for all linear cases to handle the non-block aligned
stride cases."
Cc: Lyude <cpaul@redhat.com>
Cc: drm-intel-fixes@lists.freedesktop.org
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470344880-27394-1-git-send-email-matthew.d.roper@intel.com
Reviewed-by: Lyude <cpaul@redhat.com>
Chris Wilson [Thu, 4 Aug 2016 15:32:42 +0000 (16:32 +0100)]
drm/i915: Export our request as a dma-buf fence on the reservation object
If the GEM objects being rendered with in this request have been
exported via dma-buf to a third party, hook ourselves into the dma-buf
reservation object so that the third party can serialise with our
rendering via the dma-buf fences.
Testcase: igt/prime_busy
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-26-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:41 +0000 (16:32 +0100)]
drm/i915: Enable lockless lookup of request tracking via RCU
If we enable RCU for the requests (providing a grace period where we can
inspect a "dead" request before it is freed), we can allow callers to
carefully perform lockless lookup of an active request.
However, by enabling deferred freeing of requests, we can potentially
hog a lot of memory when dealing with tens of thousands of requests per
second - with a quick insertion of a synchronize_rcu() inside our
shrinker callback, that issue disappears.
v2: Currently, it is our responsibility to handle reclaim i.e. to avoid
hogging memory with the delayed slab frees. At the moment, we wait for a
grace period in the shrinker, and block for all RCU callbacks on oom.
Suggested alternatives focus on flushing our RCU callback when we have a
certain number of outstanding request frees, and blocking on that flush
after a second high watermark. (So rather than wait for the system to
run out of memory, we stop issuing requests - both are nondeterministic.)
Paul E. McKenney wrote:
Another approach is synchronize_rcu() after some largish number of
requests. The advantage of this approach is that it throttles the
production of callbacks at the source. The corresponding disadvantage
is that it slows things up.
Another approach is to use call_rcu(), but if the previous call_rcu()
is still in flight, block waiting for it. Yet another approach is
the get_state_synchronize_rcu() / cond_synchronize_rcu() pair. The
idea is to do something like this:
cond_synchronize_rcu(cookie);
cookie = get_state_synchronize_rcu();
You would of course do an initial get_state_synchronize_rcu() to
get things going. This would not block unless there was less than
one grace period's worth of time between invocations. But this
assumes a busy system, where there is almost always a grace period
in flight. But you can make that happen as follows:
cond_synchronize_rcu(cookie);
cookie = get_state_synchronize_rcu();
call_rcu(&my_rcu_head, noop_function);
Note that you need additional code to make sure that the old callback
has completed before doing a new one. Setting and clearing a flag
with appropriate memory ordering control suffices (e.g,. smp_load_acquire()
and smp_store_release()).
v3: More comments on compiler and processor order of operations within
the RCU lookup and discover we can use rcu_access_pointer() here instead.
v4: Wrap i915_gem_active_get_rcu() to take the rcu_read_lock itself.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: "Goel, Akash" <akash.goel@intel.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-25-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:40 +0000 (16:32 +0100)]
drm/i915: Move i915_gem_object_wait_rendering()
Just move it earlier so that we can use the companion nonblocking
version in a couple of more callsites without having to add a forward
declaration.
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/1470324762-2545-24-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:39 +0000 (16:32 +0100)]
drm/i915: Move obj->active:5 to obj->flags
We are motivated to avoid using a bitfield for obj->active for a couple
of reasons. Firstly, we wish to document our lockless read of obj->active
using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
when presented with a bitfield and that shows up high on the profiles of
request tracking (mainly due to excess memory traffic as it converts
the bitfield to a register and back and generates frequent AGI in the
process).
v2: BIT, break up a long line in compute the other engines, new paint
for i915_gem_object_is_active (now i915_gem_object_get_active).
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/1470324762-2545-23-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:38 +0000 (16:32 +0100)]
drm/i915: Use dev_priv consistently through the intel_frontbuffer interface
Rather than a mismash of struct drm_device *dev and struct
drm_i915_private *dev_priv being used freely within a function, be
consistent and only pass along dev_priv.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-22-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:37 +0000 (16:32 +0100)]
drm/i915: Use atomics to manipulate obj->frontbuffer_bits
The individual bits inside obj->frontbuffer_bits are protected by each
plane->mutex, but the whole bitfield may be accessed by multiple KMS
operations simultaneously and so the RMW need to be under atomics.
However, for updating the single field we do not need to mandate that it
be under the struct_mutex, one more step towards its removal as the de
facto BKL.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-21-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:36 +0000 (16:32 +0100)]
drm/i915: Make fb_tracking.lock a spinlock
We only need a very lightweight mechanism here as the locking is only
used for co-ordinating a bitfield.
v2: Move the cheap unlikely tests into the caller
v3: Move the kerneldoc into the header (now separated out into
intel_fronbuffer.h for better kerneldoc and readability)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtien <joonas.lahtinen@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-20-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:35 +0000 (16:32 +0100)]
drm/i915: Separate intel_frontbuffer into its own header
In view of adding inline functions into the intel_frontbuffer section,
we first split the header into its own file so that we can integrate it
more easily with kerneldoc.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-19-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:34 +0000 (16:32 +0100)]
drm/i915: Remove highly confusing i915_gem_obj_ggtt_pin()
Since i915_gem_obj_ggtt_pin() is an idiom breaking curry function for
i915_gem_object_ggtt_pin(), spare us the confusion and remove it.
Removing it now simplifies later patches to change the i915_vma_pin()
(and friends) interface.
v2: Add a redundant GEM_BUG_ON(!view) to
i915_gem_obj_lookup_or_create_ggtt_vma()
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/1470324762-2545-18-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:33 +0000 (16:32 +0100)]
drm/i915: Make i915_vma_pin() small and inline
Not only is i915_vma_pin() called for every single object on every single
execbuf, it is usually a simple increment as the VMA is already bound for
execution by the GPU. Rearrange the tests for unbound and pin_count
overflow so that we can do the increment and test very cheaply and
compact enough to inline the operation into execbuf. The trick used is
to note that we can check for an overflow bit (keeping space available
for it inside the flags) at the same time as checking the binding bits.
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/1470324762-2545-17-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:32 +0000 (16:32 +0100)]
drm/i915: Combine all i915_vma bitfields into a single set of flags
In preparation to perform some magic to speed up i915_vma_pin(), which
is among the hottest of hot paths in execbuf, refactor all the bitfields
accessed by i915_vma_pin() into a single unified set of flags.
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/1470324762-2545-16-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:31 +0000 (16:32 +0100)]
drm/i915: Start passing around i915_vma from execbuffer
During execbuffer we look up the i915_vma in order to reserve them in
the VM. However, we then do a double lookup of the vma in order to then
pin them, all because we lack the necessary interfaces to operate on
i915_vma - so introduce i915_vma_pin()!
v2: Tidy parameter lists to remove one level of redirection in the hot
path.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-15-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:30 +0000 (16:32 +0100)]
drm/i915: Wrap vma->pin_count accessors with small inline helpers
In the next few patches, the VMA pinning API is overhauled and to reduce
the churn we pull out the update to the accessors into a prep patch.
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/1470324762-2545-14-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:29 +0000 (16:32 +0100)]
drm/i915: Record allocated vma size
Tracking the size of the VMA as allocated allows us to dramatically
reduce the complexity of later functions (like inserting the VMA in to
the drm_mm range manager).
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/1470324762-2545-13-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:28 +0000 (16:32 +0100)]
drm/i915: Update i915_gem_get_ggtt_size/_alignment to use drm_i915_private
For consistency, internal functions should take drm_i915_private rather
than drm_device. Now that we are subclassing drm_device, there are no
more size wins, but being consistent is its own blessing.
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/1470324762-2545-12-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:27 +0000 (16:32 +0100)]
drm/i915: Update the GGTT size/alignment query functions
In order to be consistent with other address space functions, we want to
pass around 64-bit sizes, even though all known global GTT are limited
to 4GiB. Similarly, we are trying to be consistent in using the _ggtt_
nomenclature when referring to the special global GTT.
v2: Update docs to consistently state "global GTT".
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/1470324762-2545-11-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:26 +0000 (16:32 +0100)]
drm/i915: Convert 4096 alignment request to 0 for drm_mm allocations
As we always allocate in chunks of 4096 (that being both the PAGE_SIZE
and our own GTT_PAGE_SIZE), we know that all results from the drm_mm are
aligned to at least 4096. The drm_mm allocator itself is optimised for
alignment == 0, and so by converting alignments of 4096 to 0 we can
satisfy our own requirements and still hit the faster path.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-10-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:25 +0000 (16:32 +0100)]
drm/i915: Split insertion/binding of an object into the VM
Split the insertion into the address space's range manager and binding
of that object into the GTT to simplify the code flow when pinning a
VMA.
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/1470324762-2545-9-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:24 +0000 (16:32 +0100)]
drm/i915: Reduce WARN(i915_gem_valid_gtt_space) to a debug-only check
i915_gem_valid_gtt_space() is used after inserting the VMA to double
check the list - the location should have been chosen to pass all the
restrictions.
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/1470324762-2545-8-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:23 +0000 (16:32 +0100)]
drm/i915: Pad GTT views of exec objects up to user specified size
Our GPUs impose certain requirements upon buffers that depend upon how
exactly they are used. Typically this is expressed as that they require
a larger surface than would be naively computed by pitch * height.
Normally such requirements are hidden away in the userspace driver, but
when we accept pointers from strangers and later impose extra conditions
on them, the original client allocator has no idea about the
monstrosities in the GPU and we require the userspace driver to inform
the kernel how many padding pages are required beyond the client
allocation.
v2: Long time, no see
v3: Try an anonymous union for uapi struct compatibility
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-7-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:22 +0000 (16:32 +0100)]
drm/i915: Fix up vma alignment to be u64
This is not the full fix, as we are required to percolate the u64 nature
down through the drm_mm stack, but this is required now to prevent
explosions due to mismatch between execbuf (eb_vma_misplaced) and vma
binding (i915_vma_misplaced) - and reduces the risk of spurious changes
as we adjust the vma interface in the next patches.
v2: long long casts not required for u64 printk (%llx)
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/1470324762-2545-6-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:21 +0000 (16:32 +0100)]
drm/i915: Remove i915_gem_execbuffer_retire_commands()
Move the single line to the callsite as the name is now misleading, and
the purpose is solely to add the request to the execution queue. Here,
we can see that if we failed to dispatch the batch from the request, we
can forgo flushing the GPU when closing the request.
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/1470324762-2545-5-git-send-email-chris@chris-wilson.co.uk
Chris Wilson [Thu, 4 Aug 2016 15:32:20 +0000 (16:32 +0100)]
drm/i915: Remove request retirement before each batch
This reimplements the denial-of-service protection against igt from
commit
227f782e4667 ("drm/i915: Retire requests before creating a new
one") and transfers the stall from before each batch into get_pages().
The issue is that the stall is increasing latency between batches which
is detrimental in some cases (especially coupled with execlists) to
keeping the GPU well fed. Also we have made the observation that retiring
requests can of itself free objects (and requests) and therefore makes
a good first step when shrinking.
v2: Recycle objects prior to i915_gem_object_get_pages()
v3: Remove the reference to the ring from i915_gem_requests_ring() as it
operates on an intel_engine_cs.
v4: Since commit
9b5f4e5ed6fd ("drm/i915: Retire oldest completed request
before allocating next") we no longer need the safeguard to retire
requests before get_pages(). We no longer see the huge latencies when
hitting the shrinker between allocations.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-4-git-send-email-chris@chris-wilson.co.uk