Force the use of cached memory when evicting from vram on non agp
hardware. Also force write combine on agp hw. This is to insure
the minimum cache type change when allocating memory and improving
memory eviction especialy on pci/pcie hw.
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Redirect invalid memory accesses to the default page
instead of locking up the memory controller. Also
enable the invalid memory access interrupts and
start spamming system log with it.
v2 (agd5f): fix up against 2 level PT changes
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Before queuing the flip but crucially after attaching the unpin-work to
the crtc, we continue to setup the unpin-work. However, should the
hardware fire early, we see the connected unpin-work and queue the task.
The task then promptly runs and unpins the fb before we finish taking
the required references or even pinning it... Havoc.
To close the race, we use the flip-pending atomic to indicate when the
flip is finally setup and enqueued. So during the flip-done processing,
we can check more accurately whether the flip was expected.
v2: Add the appropriate mb() to ensure that the writes to the page-flip
worker are complete prior to marking it active and emitting the MI_FLIP.
On the read side, the mb should be enforced by the spinlocks.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
[danvet: Review the barriers a bit, we need a write barrier both
before and after updating ->pending. Similarly we need a read barrier
in the interrupt handler both before and after reading ->pending. With
well-ordered irqs only one barrier in each place should be required,
but since this patch explicitly sets out to combat spurious interrupts
with is staged activation of the unpin work we need to go full-bore on
the barriers, too. Discussed with Chris Wilson on irc and changes
acked by him.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When l3 parity support for Haswell was enabled in
commit f27b92651d
Author: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Tue Jul 24 20:47:32 2012 -0700
drm/i915: Expand DPF support to Haswell
no one noticed that the patch which introduced this macro
commit e1ef7cc299
Author: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Tue Jul 24 20:47:31 2012 -0700
drm/i915: Macro to determine DPF support
missed one spot. Fix this.
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=57441
Reviewed-by: Ben Widawsky <benjamin.widawsky@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch adds code for composing AVI and AUI info frames
and send them every VSYNC.
This patch is important for hdmi certification.
v3:
- Moved enums, macros to exynos_hdmi.c.
- Corrected hex format.
- Added static to hdmi_reg_infoframe.
v2:
- Added few blank lines.
- Corrected comments format.
- Added comments for 2's Complement calculation for check sum.
v1:
- Remove un-necessary blank lines.
- Change the case of hex constants.
Signed-off-by: Rahul Sharma <rahul.sharma@samsung.com>
Signed-off-by: Fahad Kunnathadi <fahad.k@samsung.com>
Signed-off-by: Shirish S <s.shirish@samsung.com>
Acked-by: Seung-Woo Kim <sw0312.kim@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
devm_clk_get is device managed and makes error handling and exit code
simpler.
Also fixes an error related to returning 'ret' without initialising
with error code.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
devm_* functions are device managed and make error handling and exit code
simpler.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
devm_clk_get is device managed and makes error handling and exit code
simpler.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Pointer was being dereferenced after freeing.
Fixes the following error:
drivers/gpu/drm/exynos/exynos_drm_g2d.c:323 g2d_userptr_put_dma_addr() error:
dereferencing freed memory 'g2d_userptr'
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
devm_clk_get is device managed and makes error handling and exit code
simpler.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
The 'pages' structure in the exynos gem buffer has been
removed. So we get the fix.smem_start from the first sgl
of the scatter gather table.
Signed-off-by: Prathyush K <prathyush.k@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
This patch is to preserve the display mode header during the mode adjustment.
Display mode header is overwritten with the adjusted mode header which is
throwing the stack dump.
Signed-off-by: Rahul Sharma <rahul.sharma@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
drm_get_edid() returns a pointer to an EDID block. The caller
is responsible to free this pointer itself.
Here the pointer gets assigned to the local variable raw_edid.
Therefore it should be freed before the variable goes out of
scope.
Signed-off-by: Egbert Eich <eich@suse.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Changelog v2:
Removed redundant check for invalid sgl.
Added check for valid page_offset in the beginning of exynos_drm_gem_map_buf.
Changelog v1:
The 'pages' structure is not required since we can use the 'sgt'. Even for
CONTIG buffers, a SGT is created (which will have just one sgl). This SGT
can be used during mmap instead of 'pages'. The 'page_size' element of the
structure is also not used anywhere and is removed.
This patch also fixes a memory leak where the 'pages' structure was being
allocated during gem buffer allocation but not being freed during deallocate.
Signed-off-by: Prathyush K <prathyush.k@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Changelog v3:
Passing the actual buffer size instead of vm_size to dma_mmap_attrs.
Changelog v2:
Extracting the private data from fb_info structure to obtain the exynos
gem buffer structure. Now, dma address is obtained from the exynos gem
buffer structure and not from smem_start. Also calling dma_mmap_attrs
(instead of dma_mmap_writecombine) with the same attributes used
during allocation.
Changelog v1:
This patch adds a exynos drm specific implementation of fb_mmap
which supports mapping a non-contiguous buffer to user space.
This new function does not assume that the frame buffer is contiguous
and calls dma_mmap_writecombine for mapping the buffer to user space.
dma_mmap_writecombine will be able to map a contiguous buffer as well
as non-contig buffer depending on whether an IOMMU mapping is created
for drm or not.
Signed-off-by: Prathyush K <prathyush.k@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Changelog v2:
fix a little bit performance issue to previous patch.
- When drm framebuffer is destroyed, make sure that overlay
data are updated to real hardwrae for all encoders
instead of waiting for vblank every page flip request.
For this, it adds a new function,
exynos_drm_encoder_complete_scanout function.
Changelog v1:
This patch removes wait_for_vblank call from
exynos_drm_encoder_plane_disable function and move it to
exynos_drm_encoder_plane_commit function.
Disabling dma channel to each plane doens't need vblank
signal to update data to real hardware. But updating
overlay data to real hardware does need vblank signal.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
In a couple of places we attempt to adjust the existing watermark
registers to update them for the new cursor watermarks. This goes
horribly wrong as instead of clearing the cursor bits prior to or'ing in
the new values, we clear the rest of the register with the result that
the watermark registers contain bogus values.
References: https://bugs.freedesktop.org/show_bug.cgi?id=47034
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The BLC_PWM_CTL2 register does not exist before gen4. While at it, do a
slight drive by cleanup of the code.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Changelog v3:
use drm_file's file object instead of gem object's
- gem object's file represents the shmem storage so
process-unique file object should be used instead.
Changelog v2:
call mutex_lock before drm_vm_open_locked is called.
Changelog v1:
This patch makes it takes a reference to gem object when
specific gem mmap is requested. For this, it sets
dev->driver->gem_vm_ops to vma->vm_ops.
And this patch is based on exynos-drm-next-iommu branch of
git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
This patch adds userptr feautre for G2D module.
The userptr means user space address allocated by malloc().
And the purpose of this feature is to make G2D's dma able
to access the user space region.
To user this feature, user should flag G2D_BUF_USRPTR to
offset variable of struct drm_exynos_g2d_cmd and fill
struct drm_exynos_g2d_userptr with user space address
and size for it and then should set a pointer to
drm_exynos_g2d_userptr object to data variable of struct
drm_exynos_g2d_cmd. The last bit of offset variable is used
to check if the cmdlist's buffer type is userptr or not.
If userptr, the g2d driver gets user space address and size
and then gets pages through get_user_pages().
(another case is counted as gem handle)
Below is sample codes:
static void set_cmd(struct drm_exynos_g2d_cmd *cmd,
unsigned long offset, unsigned long data)
{
cmd->offset = offset;
cmd->data = data;
}
static int solid_fill_test(int x, int y, unsigned long userptr)
{
struct drm_exynos_g2d_cmd cmd_gem[5];
struct drm_exynos_g2d_userptr g2d_userptr;
unsigned int gem_nr = 0;
...
g2d_userptr.userptr = userptr;
g2d_userptr.size = x * y * 4;
set_cmd(&cmd_gem[gem_nr++], DST_BASE_ADDR_REG |
G2D_BUF_USERPTR,
(unsigned long)&g2d_userptr);
...
}
int main(int argc, char **argv)
{
unsigned long addr;
...
addr = malloc(x * y * 4);
...
solid_fill_test(x, y, addr);
...
}
And next, the pages are mapped with iommu table and the device
address is set to cmdlist so that G2D's dma can access it.
As you may know, the pages from get_user_pages() are pinned.
In other words, they CAN NOT be migrated and also swapped out.
So the dma access would be safe.
But the use of userptr feature has performance overhead so
this patch also has memory pool to the userptr feature.
Please, assume that user sends cmdlist filled with userptr
and size every time to g2d driver, and the get_user_pages
funcion will be called every time.
The memory pool has maximum 64MB size and the userptr that
user had ever sent, is holded in the memory pool.
This meaning is that if the userptr from user is same as one
in the memory pool, device address to the userptr in the memory
pool is set to cmdlist.
And last, the pages from get_user_pages() will be freed once
user calls free() and the dma access is completed. Actually,
get_user_pages() takes 2 reference counts if the user process
has never accessed user region allocated by malloc(). Then, if
the user calls free(), the page reference count becomes 1 and
becomes 0 with put_page() call. And the reverse holds as well.
This means how the pages backed are used by dma and freed.
This patch is based on "drm/exynos: add iommu support for g2d",
https://patchwork.kernel.org/patch/1629481/
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
The function dma_get_sgtable will allocate a sg table internally so
it is not necessary to allocate a sg table before it. The unnecessary
'sg_alloc_table' call is removed.
Signed-off-by: Prathyush K <prathyush.k@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
This patch fixes the problem of mapping contigous and non contigous dma buffers.
Currently page struct is calculated from the buf->dma_addr which is not the
physical address. It is replaced by buf->pages which points to the page struct
of the first page of contigous memory chunk. This gives the correct page frame
number for mapping.
Non-contigous dma buffers are described using SG table and SG lists. Each
valid SG List is pointing to a single page or group of pages which are
physically contigous. Current implementation just maps the first page of each
SG List and leave the other pages unmapped, leading to a crash. Given solution
finds the page struct for the faulting page through parsing SG table and map it.
Signed-off-by: Rahul Sharma <rahul.sharma@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
With iommu support, non-continuous buffer also is supported so
this patch removes these checking from exynos_drm_gem_get/put_dma_addr
funciton.
This patch is based on the below patch set, "drm/exynos: add
iommu support for -next".
http://www.spinics.net/lists/dri-devel/msg29041.html
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Chagelog v2:
removed unnecessary structure, struct g2d_gem_node.
Chagelog v1:
This patch adds iommu support for g2d driver. For this, it
adds subdrv_probe/remove callback to enable or disable
g2d iommu. And with this patch, in case of using g2d iommu,
we can get or put device address to a gem handle from user
through exynos_drm_gem_get/put_dma_addr(). Actually, these
functions take a reference to a gem handle so that the gem
object used by g2d dma is released properly.
And runqueue_node has a pointer to drm_file object of current
process to manage gem handles to owner.
This patch is based on the below patch set, "drm/exynos: add
iommu support for -next".
http://www.spinics.net/lists/dri-devel/msg29041.html
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Changelog v2:
move iommu support feature to mixer side.
And below is Prathyush's comment.
According to the new IOMMU framework for exynos sysmmus,
the owner of the sysmmu-tv is mixer (which is the actual
device that does DMA) and not hdmi.
The mmu-master in sysmmu-tv node is set as below in exynos5250.dtsi
sysmmu-tv {
-
mmu-master = <&mixer>;
};
Changelog v1:
The iommu will be enabled when hdmi sub driver is probed and
will be disabled when removed.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
From BSpec:
"If the Ring Buffer Head Pointer and the Tail Pointer are on the same
cacheline, the Head Pointer must not be greater than the Tail
Pointer."
The easiest way to enforce this is to reduce the reported ring space.
References:
Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
Gen4+ BSpec "vol1c Memory Interface and Command Stream" / 5.3.4.5 "Ring Buffer Use"
v2: Include the exact BSpec references in the description
v3: s/64/I915_RING_FREE_SPACE, and add the BSpec information to the code
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we may actually allocate in order to save the physical swizzling bits
during the free, we have to be careful not to trigger the shrinker on
the same object.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Added a small comment in the code to really drive the
scariness of this patch home.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Replace references to and remove the connector property fxns, which
have been superseded with the more general object property fxns:
+ drm_connector_attach_property -> drm_object_attach_property
+ drm_connector_property_set_value -> drm_object_property_set_value
+ drm_connector_property_get_value -> drm_object_property_get_value
Signed-off-by: Rob Clark <rob@ti.com>
The iommu will be enabled when fimd sub driver is probed and
will be disabled when removed.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Changelog v4:
- fix condition to drm_iommu_detach_device funtion.
Changelog v3:
- add dma_parms->max_segment_size setting of drm_device->dev.
- use devm_kzalloc instead of kzalloc.
Changelog v2:
- fix iommu attach condition.
. check archdata.dma_ops of drm device instead of
subdrv device's one.
- code clean to exynos_drm_iommu.c file.
. remove '#ifdef CONFIG_ARM_DMA_USE_IOMMU' from exynos_drm_iommu.c
and add it to driver/gpu/drm/exynos/Kconfig.
Changelog v1:
This patch adds iommu support for exynos drm framework with dma mapping
api. In this patch, we used dma mapping api to allocate physical memory
and maps it with iommu table and removed some existing codes and added
new some codes for iommu support.
GEM allocation requires one device object to use dma mapping api so
this patch uses one iommu mapping for all sub drivers. In other words,
all sub drivers have same iommu mapping.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Currently the only users of drm_vblank_off() are i915 and gma500,
neither of which holds the event_lock when calling this function.
Fix this by holding the event_lock while traversing the list.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Currently the exynos driver calls drm_vblank_off() with the event_lock
held, while drm_vblank_off() will lock vbl_time and vblank_time_lock.
This lock dependency chain conflicts with the one in drm_handle_vblank()
where we first lock vblank_time_lock and then the event_lock.
Fix this by removing the above drm_vblank_off() calls which are in fact
never executed: drm_dev->vblank_disable_allowed is only ever non-zero
during driver init, until it's set in {fimd,vidi}_subdrv_probe. Both the
driver init and open code is protected by drm_global_mutex, so the
earliest page flip ioctl can happen only after vblank_disable_allowed is
set to 1. Thus {fimd,vidi}_finish_pageflip - with pending flip events -
will always get called with vblank_disable_allowed being 1.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
It's guaranteed that for each event on pageflip_event_list we have
called drm_vblank_get() - see exynos_drm_crtc_page_flip() - so checking
for this is redundant.
Also we need to call drm_vblank_put() for each event on the list, not
only once, otherwise we'd leak vblank references if there are multiple
events on the list.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Check overlay_ops is not NULL as checked in the previous 'if' condition.
Fixes the following smatch error:
drivers/gpu/drm/exynos/exynos_drm_encoder.c:509 exynos_drm_encoder_plane_disable()
error: we previously assumed 'overlay_ops' could be null (see line 499)
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Fixes the following sparse warnings:
drivers/gpu/drm/exynos/exynos_drm_fimd.c:65:25: warning:
symbol 'exynos4_fimd_driver_data' was not declared. Should it be static?
drivers/gpu/drm/exynos/exynos_drm_fimd.c:69:25: warning:
symbol 'exynos5_fimd_driver_data' was not declared. Should it be static?
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Chagelog v2:
Move encoder's dpms updating into exynos_drm_encoder_commit
function because when crtc's dpms is updated, encoder's dpms
is updated also. This would induce the issue that encoder
isn't disabled after crtc is disabled.
Changelog v1:
This patch fixes a issue that overlay data aren't applied
to real hardware when dpms off goes to on after setcrtc
was requested like below,
dpms off -> setcrtc -> dpms off -> dpms on
For this, it makes encoder's dpms to be updated when
setcrtc is requested.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
plane->fb will be set to new fb after update_plane callback is called
by drm_mode_set_plane()
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
With iommu, buffer->dma_addr has device addres so this patch
fixes for physical address to be set to fix.smem_start always.
Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
i915_gem_handle_seqno_wrap() will zero all sync_seqnos but as the
wrap can happen inside ring->sync_to(), pre wrap seqno was
carried over and overwrote the zeroed sync_seqno.
When wrap is handled, all outstanding requests will be retired and
objects moved to inactive queue, causing their last_read_seqno to be zero.
Use this to update the sync_seqno correctly.
RING_SYNC registers after wrap will contain pre wrap values which
are >= seqno. So injecting the semaphore wait into ring completes
immediately.
Original idea for using last_read_seqno from Chris Wilson.
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Should be useful to know what the driver thought the other ring's seqno
was when it last used a semaphore.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Replace the wait for the ring to be clear with the more common wait for
the ring to be idle. The principle advantage is one less exported
intel_ring_wait function, and the removal of a hardcoded value.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we now always preallocate the seqno before writing to the ring, we
can trivially test if we have any pending activity on the ring by
inspecting the olr. This makes it then possible to flush operations that
are not normally associated with a request, like power-management.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Based on the work by Mika Kuoppala, we realised that we need to handle
seqno wraparound prior to committing our changes to the ring. The most
obvious point then is to grab the seqno inside intel_ring_begin(), and
then to reuse that seqno for all ring operations until the next request.
As intel_ring_begin() can fail, the callers must already be prepared to
handle such failure and so we can safely add further checks.
This patch looks like it should be split up into the interface
changes and the tweaks to move seqno wrapping from the execbuffer into
the core seqno increment. However, I found no easy way to break it into
incremental steps without introducing further broken behaviour.
v2: Mika found a silly mistake and a subtle error in the existing code;
inside i915_gem_retire_requests() we were resetting the sync_seqno of
the target ring based on the seqno from this ring - which are only
related by the order of their allocation, not retirement. Hence we were
applying the optimisation that the rings were synchronised too early,
fortunately the only real casualty there is the handling of seqno
wrapping.
v3: Do not forget to reset the sync_seqno upon module reinitialisation,
ala resume.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=863861
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> [v2]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There seem to be indeed some awkwards machines around, mostly those
without OpRegion support, where the firmware changes the display hw
state behind our backs when closing the lid.
This force-restore logic has been originally introduced in
commit c1c7af6089
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Thu Sep 10 15:28:03 2009 -0700
drm/i915: force mode set at lid open time
but after the modeset-rework we've disabled it in the vain hope that
it's no longer required:
commit 3b7a89fce3
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon Sep 17 22:27:21 2012 +0200
drm/i915: fix OOPS in lid_notify
Alas, no.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=54677
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=57434
Tested-by: Krzysztof Mazur <krzysiek@podlesie.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In commit 69c2fc8913
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Jul 20 12:41:03 2012 +0100
drm/i915: Remove the per-ring write list
the explicit flush was removed from i915_ring_idle(). However, we
continued to wait upon the next seqno which now did not correspond to
any request (except for the unusual condition of a failure to queue a
request after execbuffer) and so would wait indefinitely.
This has an important side-effect that i915_gpu_idle() does not cause
the seqno to be incremented. This is vital if we are to be able to idle
the GPU to handle seqno wraparound, as in subsequent patches.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Dereference dev_priv only after we know it is valid.
Found with smatch.
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Some devices may respond very slowly and only flag that the reply is
pending within the first 15us response window. Be kind to such devices
and wait a further 15ms, before checking for the pending reply. This
moves the existing special case delay of 30ms down from the detection
routine into the common path and pretends to explain it...
v2: Simplify the loop constructs as suggested by Jani Nikula.
References: https://bugs.freedesktop.org/show_bug.cgi?id=36997
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We currently set "0" as the VIC value of the AVI InfoFrames. According
to the specs this should be fine and work for every mode, so to my
point of view we can't consider the current behavior as a bug. The
problem is that we recently received a bug report (Kernel bug #50371)
from a user that has an AV receiver that gives a black screen for any
mode with VIC set to 0.
So in order to make at least some modes work for him, this patch sets
the correct VIC number when sending AVI InfoFrames.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=50371
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This function returns the VIC of the mode. This value can be used when
creating AVI InfoFrames.
Cc: Thierry Reding <thierry.reding@avionic-design.de>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=50371
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Thierry Reding <thierry.reding@avionic-design.de>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
Besides the big item of lifting the "preliminary hw support" tag from the
Haswell code, just small bits&pieces all over:
- Leftover Haswell patches and some fixes from Paulo
- LyncPoint PCH support (for hsw)
- OOM handling improvements from Chris Wilson
- connector property and send_vblank_event refactorings from Rob Clark
- random pile of small fixes
Note that the send_vblank refactorings will cause some locking WARNs to
show up. Imre has fixed that up, but since all the driver changes outside
of the drm core have been for exonys, those four patches are merged
through the exonys-next tree.
Meh, I've forgotten to cherry-pick an important fix from Ben for a
regression in the 3.8 gen6+ gtt code. New pull request below. While I'm at
it, the hdmi VIC patch for the drm edid code is still in my queue, I'll
send you that in the next 3.8-fixes pull.
* 'for-airlied' of git://people.freedesktop.org/~danvet/drm-intel: (33 commits)
drm/i915: Fix pte updates in ggtt clear range
drm/i915: promote Haswell to full support
drm/i915: Report the origin of the LVDS fixed panel mode
drm/i915: LVDS fallback to fixed-mode if EDID not present
drm/i915/sdvo: kfree the intel_sdvo_connector, not drm_connector, on destroy
drm/i915: drm_connector_property -> drm_object_property
drm/i915: use drm_send_vblank_event() helper
drm/i915: Use pci_resource functions for BARs.
drm/i915: Borrow our struct_mutex for the direct reclaim
drm/i915: Defer assignment of obj->gtt_space until after all possible mallocs
drm/i915: Apply the IBX transcoder A w/a for HDMI to SDVO as well
drm/i915: implement WaMbcDriverBootEnable on Haswell
drm/i915: fix intel_ddi_get_cdclk_freq for ULT machines
drm/i915: make the panel fitter work on pipes B and C on Haswell
drm/i915: make the panel fitter work on pipes B and C on IVB
drm/i915: don't intel_crt_init if DDI A has 4 lanes
drm/i915: make DP work on LPT-LP machines
drm/i915: fix false positive "Unclaimed write" messages
drm/i915: use cpu/pch transcoder on intel_enable_pipe
drm/i915: don't limit Haswell CRT encoder to pipe A
...
This bug was introduced by me:
commit e76e9aebcd
Author: Ben Widawsky <ben@bwidawsk.net>
Date: Sun Nov 4 09:21:27 2012 -0800
drm/i915: Stop using AGP layer for GEN6+
The existing code uses memset_io which follows memset semantics in only
guaranteeing a write of individual bytes. Since a PTE entry is 4 bytes,
this can only be correct if the scratch page address is 0.
This caused unsightly errors when we clear the range at load time,
though I'm not really sure what the heck is referencing that memory
anyway. I caught this is because I believe we have some other bug where
the display is doing reads of memory we feel should be cleared (or we
are relying on scratch pages to be a specific value).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Fixed build warning as below:
drivers/gpu/drm/drm_pci.c: In function 'drm_pcie_get_speed_cap_mask':
drivers/gpu/drm/drm_pci.c:496:9: warning: 'lnkcap' may be used uninitialized in this function [-Wuninitialized]
drivers/gpu/drm/drm_pci.c:497:10: warning: 'lnkcap2' may be used uninitialized in this function [-Wuninitialized]
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
On 3.7-rc6, add missing newline to to prevent the following kernel log
line getting appended to the current one after switching the integrated
GPU and suspending the discrete GPU.
Signed-off-by: Daniel J Blueman <daniel@quora.org>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
These objects leak VRAM - but only on module unload.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Fixes GART leak (as accounted by nouveau_drm.gem.gart_available).
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
It fixes a bug that would have been introduced when adding more
sudevs/engines.
Signed-off-by: Martin Peres <martin.peres@labri.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
NVIDIA also appear to use the same class on Fermi/Kepler for PPP.
Will allow use of the engine if firmware (nvXX_fuc086) provided.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will allow use of the engine if firmware (nvXX_fuc086) provided.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will allow use of the engine if firmware (nvXX_fuc085) provided.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will allow use of the engine if firmware (nvXX_fuc084) provided.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Later chipsets use falcon anyway, and I can't currently see a good need
for a shared base class.
PPP will get the same treatment once Maarten's patches are merged.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
No support for the class yet, but will be pulled in with Maarten's Fermi
vdec patches. The Kepler PPP class is identical.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Previously, if either vram/gart handles were specified as ~0, the ioctl
call would fail. In order to hack engine selection into the ioctl for
kepler, we now define (fb_ctxdma_handle == ~0) to mean "engine mask is
in tt_ctxdma_handle".
This approach also allows new userspace to detect lack of support for
non-PGRAPH channels on older kernels.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
nv50_fb_trap() will now be called automagically by the mc intr handler,
rather than each engine's handler having to check for traps manually.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is a precursor to dynamic power management support for nouveau,
we need to use pm ops for that, so first convert the driver to using pm ops
interfaces.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is required to decide if we can auto-powerdown and how to implement it.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is like we do on nv50:nvd9 already. There's been no problems seen
yet with using this *seemingly* scratch register to store the value, but
we won't be able to do this anymore once nv50's code is merged.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
EVO channels still handled "manually", this won't be ported here, and
will instead be held off until nv50_display/nvd0_display are merged.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This is what we've done forever in nv50_display.c, and also allows the
last direct MMIO accesses to be removed from nvd0_display.c.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
nv_call() just allows mthd+u32 submission, nv_exec() exposes the
mthd+data+size interface which will be used in future commits.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Later changes will depend on being able to pull down CRTCs etc with the
master display state still intact.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
This will be used instead of storing a heap of per-head data (such as evo
channels) in nvd0_display in some other way.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Currently unused, and rudimentary. Lots to figure out here still, but
this is sufficient for what disp will need.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Otherwise when nvc0- gains a bind() method (disp needs it), the fifo
engine will attempt to create a dma object for the push buffer, which
is unnecessary on fermi.
The only sane place to put these checks is in the bind method itself,
and have it unconditionally called from wherever it might be needed.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Will be required by future work. Make the API change now to catch any
(but hopefully none) unexpected fallout.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Jerome Glisse