Let's bring a bit of clarity on this 'region' field that is
part of vm_bind operation struct. Rename and document to make
it more than obvious that it is a region instance and not a
mask and also that it should only be used with the prefetch
operation itself.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matt Roper <[email protected]>
On one hand the WAIT_OP represents the operation use for waiting such
as ==, !=, > and so on. On the other hand, the mask is applied to the
value used for comparision. Split those two to bring clarity to the uapi.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matt Roper <[email protected]>
Only cosmetic things. No functional change on this patch.
Define every flag with (1 << n) and use singular FLAG name.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
'Usage' gives an impression of telemetry information where someone
would query to see how the memory is currently used and available
size, etc. However this API is more than this. It is about a global
view of all the memory regions available in the system and user
space needs to have this information so they can then use the
mem_region masks that are returned for the engine access.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matt Roper <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
- 'native' doesn't make much sense on integrated devices.
- 'slow' is not necessarily true and doesn't go well with opposition
to 'native'.
Instead, let's use 'near' vs 'far'. It makes sense with all the current
Intel GPUs and it is future proof. Right now, there's absolutely no need
to define among the 'far' memory, which ones are slower, either in terms
of latency, nunmber of hops or bandwidth.
In case of this might become a requirement in the future, a new query
could be added to indicate the certain 'distance' between a given engine
and a memory_region. But for now, this fulfill all of the current
requirements in the most straightforward way for the userspace drivers.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matt Roper <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Change rsvd to pad in struct drm_xe_class_instance to prevent the field
from being used in future.
v2: Change from fixup to regular commit because this touches the
uAPI (Francois Dugast)
Signed-off-by: Umesh Nerlige Ramappa <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Most constants defined in xe_drm.h which can be used for flags are
named DRM_XE_*_FLAG_*, which is helpful to identify them. Make this
systematic and add _FLAG where it was missing.
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Most constants defined in xe_drm.h use DRM_XE_ as prefix which is
helpful to identify the name space. Make this systematic and add
this prefix where it was missing.
v2:
- fix vertical alignment of define values
- remove double DRM_ in some variables (José Roberto de Souza)
v3: Rebase
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
During xe_mmio_probe_vram(), we already store the values returned from
xe_mmio_tile_vram_size() into the xe_tile structures.
There is no need to call xe_mmio_tile_vram_size() again later during
setup of the STOLEN region. Just use the values stored in the root tile.
Signed-off-by: Brian Welty <[email protected]>
Reviewed-by: Matt Roper <matthew.d.roper at intel.com>
Signed-off-by: Rodrigo Vivi <[email protected]>
As part of uAPI cleanup, remove this constant which is not used. Number
of GTs are provided as num_gt in drm_xe_query_gt_list.
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
As part of uAPI cleanup, remove this constant which is not used. Memory
regions can be queried with DRM_XE_DEVICE_QUERY_MEM_USAGE.
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
This is not used and also the negative of the other 2 regions:
native_mem_regions and slow_mem_regions.
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Remove unused IOCTL.
Without any userspace using it we need to remove before we
can be accepted upstream.
At this point we are breaking the compatibility for good,
so we don't need to break when we are in-tree. So, let's
also use this breakage to sort out the IOCTL entries and
fix all the small indentation and line issues.
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
With the split between tile and gt, this is currently unused.
Also it is bringing confusion because main vs remote would be
more a concept of the tile itself and not about GT.
So, the MAIN one is the traditional GT used for every operation
in older platforms, and for render/graphics and compute on platforms
that contains the stand-alone Media GT.
Cc: Matt Roper <[email protected]>
Cc: Francois Dugast <[email protected]>
Cc: Carl Zhang <[email protected]>
Cc: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
num_params can be used to retrieve the size of the info array
for the specific version of the kernel being used.
v2: Also remove XE_QUERY_CONFIG_NUM_PARAM (José Roberto de Souza)
Signed-off-by: Francois Dugast <[email protected]>
Reviewed-by: José Roberto de Souza <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Duplicating these helpers in almost every .c file is a bad idea.
Define them as inlines in .h file to allow proper reuse.
Signed-off-by: Michal Wajdeczko <[email protected]>
Cc: Rodrigo Vivi <[email protected]>
Cc: Jani Nikula <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Xe need to use remapped display page table for tiled framebuffers
on anywhere else than DG2. Here add function to write such dpt and
enable usage of remapped display page tables where needed.
Signed-off-by: Juha-Pekka Heikkila <[email protected]>
Reviewed-by: Michael J. Ruhl <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Trying to get bo from vram when vram not available will cause
WARN_ON() hence avoid touching vram if not available.
Signed-off-by: Juha-Pekka Heikkila <[email protected]>
Reviewed-by: Michael J. Ruhl <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Define intel_hdcp_gsc_check_status in Xe to account
for changes in i915 and Xe.
intel_hdcp_check_status always returns false as gsc cs
interface is not yet ported.
intel_hdcp_gsc_cs_required always returns true as going
forward gsc cs will always be required by upcoming
platforms
--v5
-Define intel_hdcp_gsc_cs_required()
--v6
-Explain reasons for the return values [Chaitanya]
Signed-off-by: Suraj Kandpal <[email protected]>
Reviewed-by: Chaitanya Kumar Borah <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
This introduces an exclusive version of vga decode for xe.
Rest of the display changes will be re-used from i915.
Currently it adds just a dummy implementation. VGA decode
needs to be handled correctly in i915, proper implementation
will be adopted once the i915 changes are finalized and merged
in upstream.
v2: Addressed Arun's review comments
Signed-off-by: Uma Shankar <[email protected]>
Reviewed-by: Arun R Murthy <[email protected]>
Acked-by: Jani Nikula <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Xe is not carrying frontbuffer pointer in xe_bo. Define it's getter as
NULL. Setter simply returns pointer which was provided as a
parameter.
v3: Do not take any references
v2: Handle xe_bo_put as well
Signed-off-by: Jouni Högander <[email protected]>
Reviewed-by: Maarten Lankhorst <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Upon device probe failure, rolling back the initialization
should be done in reversed order.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Ohad Sharabi <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Add a "private:" comment to the part of the struct that is not expected
to be documented, the one with display-related fields. This silence the
following warnings:
$ find drivers/gpu/drm/xe -name '*.[ch]' -not -path 'drivers/gpu/drm/xe/display/*' | xargs ./scripts/kernel-doc -Werror -none
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'display' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'pch_type' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'pch_id' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'wm_lv_0_adjust_needed' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'num_channels' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'symmetric_memory' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'type' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'num_qgv_points' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'num_psf_gv_points' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'dram_info' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'runtime_pm' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'sb_lock' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'skl_preferred_vco_freq' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'max_dotclk_freq' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'hti_state' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'snps_phy_failed_calibration' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'modeset_restore_state' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'global_obj_list' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'de_irq_mask' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'display_irqs_enabled' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'enabled_irq_mask' not described in 'xe_device'
drivers/gpu/drm/xe/xe_device_types.h:316: warning: Function parameter or member 'params' not described in 'xe_device'
22 warnings as Errors
Fixes: 44e694958b ("drm/xe/display: Implement display support")
Signed-off-by: Lucas De Marchi <[email protected]>
Acked-by: Jani Nikula <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Rodrigo Vivi <[email protected]>
We accidentally always pass true as s2idle argument, instead of
calculating it in the same way as i915.
Suspend modes were removed to achieve compatibility with i915, but
accidentally left in the source code.
While at it, fix all other cases too, s2idle will go into a D1 state and
setting a lower power state should be handled by PCI core.
Maybe my laptop stops draining so much power during suspend now? I can
only hope..
Signed-off-by: Maarten Lankhorst <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
As for display, the intent is to share the display code with the i915
driver so that there is maximum reuse there.
We do this by recompiling i915/display code twice.
Now that i915 has been adapted to support the Xe build, we can add
the xe/display support.
This initial work is a collaboration of many people and unfortunately
this squashed patch won't fully honor the proper credits.
But let's try to add a few from the squashed patches:
Co-developed-by: Matthew Brost <[email protected]>
Co-developed-by: Jani Nikula <[email protected]>
Co-developed-by: Lucas De Marchi <[email protected]>
Co-developed-by: Matt Roper <[email protected]>
Co-developed-by: Mauro Carvalho Chehab <[email protected]>
Co-developed-by: Rodrigo Vivi <[email protected]>
Co-developed-by: Dave Airlie <[email protected]>
Signed-off-by: Maarten Lankhorst <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Lucas De Marchi <[email protected]>
To appease lockdep, use a pool of ordered wq for GuC submission rather
tha leaving the ordered wq allocation to the drm sched. Without this change
eventually lockdep runs out of hash entries (MAX_LOCKDEP_CHAINS is
exceeded) as each user allocated exec queue adds more hash table entries
to lockdep. A pool old of 256 ordered wq should be enough to have
similar behavior with and without lockdep enabled.
Signed-off-by: Matthew Brost <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Starting GT freq is usually RPn. Raising freq to RP0 will
help speed up GuC load times. As an example, this data was
collected on DG2-
GuC Load time @RPn ~ 41 ms
GuC Load time @RP0 ~ 11 ms
v2: Raise GT freq before hwconfig init. This will speed up
both HuC and GuC loads. Address review comments (Rodrigo).
Also add a small usleep after requesting frequency which gives
pcode some time to react.
v3: Address checkpatch issue
Cc: Rodrigo Vivi <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Vinay Belgaumkar <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Due to the current integration between "live" xe kunit tests and kunit,
it's not possible to have a build with the following combination:
CONFIG_DRM_XE=y
CONFIG_KUNIT=m
... even if kconfig doesn't block it. The reason for the failure is that
some compilation units are pulled in xe.ko:
drivers/gpu/drm/xe/xe_bo.c:#include "tests/xe_bo.c"
drivers/gpu/drm/xe/xe_dma_buf.c:#include "tests/xe_dma_buf.c"
drivers/gpu/drm/xe/xe_migrate.c:#include "tests/xe_migrate.c"
drivers/gpu/drm/xe/xe_pci.c:#include "tests/xe_pci.c"
Those files shouldn't use symbols from kunit, which should be reserved
to the tests/*_test.c files. Detangling this dependency doesn't seem
very straightforward, so fix the immediate issue instructing kconfig to
block the problematic configuration.
Reviewed-by: Rodrigo Vivi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Lucas De Marchi <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Pass a valid vm to xe_migrate_update_pgtables.
Resolves NPD crash seen with igt@xe_live_ktest@migrate
Reviewed-by: Brian Welty <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Pallavi Mishra <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
The spec for this register, like many other interrupt related ones,
asks software to write back '1' to clear the serviced bits. Let's
respect the spec.
v2:
- Update commit message
- Add missing CC
Signed-off-by: Jonathan Cavitt <[email protected]>
CC: Daniele Spurio Ceraolo <[email protected]>
CC: Lucas De Marchi <[email protected]>
CC: Rodrigo Vivi <[email protected]>
CC: Paulo Zanoni <[email protected]>
Reviewed-by: Rodrigo Vivi <[email protected]>
Signed-off-by: Lucas De Marchi <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
If lmem (VRAM) is not fully initialized, the punit will power down
the GT, which will prevent register access from the driver side.
That code moved into a corresponding function (xe_verify_lmem_ready)
to make the code clearer.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Lucas De Marchi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Rodrigo Vivi <[email protected]>
In fault mode, page table binding is deferred until fault handler.
Thus vma->tile_present will be unset unless the VMA is accessed by GPU.
During a later unbind, the logic doesn't account for the fact that local
fence variable will be NULL in this case, leading to pass NULL into
dma_fence_add_callback() and causing few WARN_ONs to print to console.
The fix is already present in the code, just hoist the fence variable
computation to be done earlier.
Resolves warnings seen with igt@xe_exec_fault_mode@once-invalid-fault
Signed-off-by: Brian Welty <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
When processing G2H messages for pagefault or access counters, we queue a
work item and call queue_work(). This fails if the worker thread is already
queued to run.
The expectation is that the worker function will do more than process a
single item and return. It needs to either process all pending items or
requeue itself if items are pending. But requeuing will add latency and
potential context switch can occur.
We don't want to add unnecessary latency and so the worker should process
as many faults as it can within a reasonable duration of time.
We also do not want to hog the cpu core, so here we execute in a loop
and requeue if still running after more than 20 ms.
This seems reasonable framework and easy to tune this futher if needed.
This resolves issues seen with several igt@xe_exec_fault_mode subtests
where the GPU will hang when KMD ignores a pending pagefault.
v2: requeue the worker instead of having an internal processing loop.
v3: implement hybrid model of v1 and v2
now, run for 20 msec before we will requeue if still running
v4: only requeue in worker if queue is non-empty (Matt B)
Signed-off-by: Brian Welty <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Reviewed-by: Stuart Summers <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Driver initiated function-reset (FLR) is the highest level of reset
that we can trigger from within the driver. In contrast to PCI FLR it
doesn't require re-enumeration of PCI BAR. It can be useful in case
GT fails to reset. It is also the only way to trigger GSC reset from
the driver and can be used in future addition of GSC support.
v2:
- use regs from xe_regs.h
- move the flag to xe.mmio
- call flr only on root gt
- use BIOS protection check
- copy/paste comments from i915
v3:
- flr code moved to xe_device.c
v4:
- needs_flr_on_fini moved to xe_device
Signed-off-by: Andrzej Hajda <[email protected]>
Reviewed-by: Daniele Ceraolo Spurio <[email protected]>
Signed-off-by: Rodrigo Vivi <[email protected]>
Rodrigo Vivi