Rodrigo Vivi
6dbd43dced
drm/{i915, xe}: Avoid direct inspection of dpt_vma from outside dpt
...
DPT code is so dependent on i915 vma implementation and it is not
ported yet to Xe.
This patch limits inspection to DPT's VMA struct to intel_dpt
component only, so the Xe GGTT code can evolve.
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com >
Cc: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com >
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821193842.352557-4-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
2024-08-22 14:00:44 -04:00
Rodrigo Vivi
df99acc7ba
drm/xe: Remove unnecessary drm_mm.h includes
...
These includes are no longer necessary, and where appropriate
are replaced by the linux/types.h one.
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821193842.352557-3-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
2024-08-22 14:00:44 -04:00
Rodrigo Vivi
244fe16663
drm/xe: Introduce GGTT documentation
...
Document xe_ggtt and ensure it is part of the built kernel docs.
v2: - Accepted all Michal's suggestions
- Rebased on top of new set_pte per platform/wa function pointer
v3: - Typos and other acronym fixes (Michal)
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com >
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com > #v1
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821193842.352557-2-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
2024-08-22 14:00:44 -04:00
Rodrigo Vivi
69f0925c67
drm/xe: Removed unused xe_ggtt_printk
...
Apparently this was only useful when enabling ggtt support
for the very first time and never used again.
It is also not useful now that we have the ggtt_dump available
through debugfs.
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821193842.352557-1-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
2024-08-22 14:00:44 -04:00
Jani Nikula
1684481112
drm/xe: remove display stepping handling
...
The code is now unused. Remove.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/19bc7a3197f2bc6f3c0d337487ab19f3b7f5612a.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:48:21 +03:00
Jani Nikula
dfc88eac97
drm/i915/display: switch to display detected steppings
...
Move the stepping related macros over to display. We can proceed to
remove the compat macros from xe.
Note: Looks like we've failed to actually initialize the display
stepping for GMD ID based platforms in the xe driver. It does get set in
display runtime info, but until now the compat macro used
xe->info.step.display which was not set for GMD ID.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/ce8bb94e1a801d3c345f1810837bdd1964c3af75.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:48:13 +03:00
Jani Nikula
4446387572
drm/i915/display: identify display steppings in display probe
...
Both i915 and xe have code to identify display steppings. Start
deduplicating this by, uh, adding a third copy in display code. This is
not yet used for anything other than debug logging. We'll switch over
later.
For platforms before GMD ID, attach the mapping from PCI revision to
stepping in the platform and subplatform descriptors. This is a
considerably cleaner approach than having it completely separate.
Also add a separate field for stepping in display runtime info,
preserving the value from GMD ID.
v2: Handle NULL subdesc (Matt)
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821095036.2044654-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:48:08 +03:00
Jani Nikula
85878978fc
drm/xe/step: define more steppings E-J
...
These are primarily needed for compat reasons with display code in
upcoming changes. There's no harm in having them.
While at it, add a comment about the requirement to match against GMD ID
value spacing.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/88074394509d4849f8ec6ab5776394b961032cd0.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:47:55 +03:00
Jani Nikula
7bb98ca654
drm/xe/display: remove the unused compat HAS_GMD_ID()
...
The display code no longer needs or uses HAS_GMD_ID(). Remove it from
the compat header.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/67571bb0b10fb5c99dba57757f2213ef39bdedbb.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:47:51 +03:00
Jani Nikula
fa509a33e3
drm/xe/display: remove intel_display_step_name() to simplify
...
The intel_display_step_name() is an unnecessary extra
indirection. Simplify by just adding a macro to map intel_step_name() to
xe_step_name().
We'll need to temporarily add a compat INTEL_DISPLAY_STEP() for this.
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/cbea7def331cc9d2438da49ae344b9987f27cd12.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:47:46 +03:00
Jani Nikula
453afb1a43
drm/xe/display: fix compat IS_DISPLAY_STEP() range end
...
It's supposed to be an open range at the end like in i915. Fingers
crossed that nobody relies on this definition.
Fixes: 44e694958blucas.demarchi@intel.com >
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/fe8743770694e429f6902491cdb306c97bdf701a.1724180287.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-22 15:47:35 +03:00
Matthew Auld
321d6b4b9c
drm/xe: fixup xe_alloc_pf_queue
...
kzalloc expects number of bytes, therefore we should convert the number
of dw into bytes, otherwise we are likely just accessing beyond the
array causing all kinds of carnage. Also fixup the error handling while
we are here.
v2:
- Prefer kcalloc (dim)
Fixes: 3338e4f90cmatthew.auld@intel.com >
Cc: Stuart Summers <stuart.summers@intel.com >
Cc: Matthew Brost <matthew.brost@intel.com >
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240821171917.417386-2-matthew.auld@intel.com
2024-08-21 19:38:24 -07:00
Matthew Brost
40520283e0
drm/xe: Invalidate media_gt TLBs in PT code
...
Testing on LNL has shown media GT's TLBs need to be invalidated via the
GuC, update PT code appropriately.
v2:
- Do dma_fence_get before first call of invalidation_fence_init (Himal)
- No need to check for valid chain fence (Himal)
Fixes: 3330361543matthew.brost@intel.com >
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240820161632.987369-1-matthew.brost@intel.com
2024-08-21 19:34:07 -07:00
Matthew Brost
77cc3f6c58
drm/xe: Invalidate media_gt TLBs
...
Testing on LNL has shown media TLBs need to be invalidated via the GuC,
update xe_vm_invalidate_vma appropriately.
v2: Fix 2 tile case
v3: Include missing local change
Fixes: 3330361543matthew.brost@intel.com >
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240820160129.986889-1-matthew.brost@intel.com
2024-08-21 08:53:50 -07:00
Matthew Brost
9e7f305636
drm/xe: Free job before xe_exec_queue_put
...
Free job depends on job->vm being valid, the last xe_exec_queue_put can
destroy the VM. Prevent UAF by freeing job before xe_exec_queue_put.
Fixes: dd08ebf6c3matthew.brost@intel.com >
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com >
Reviewed-by: Jagmeet Randhawa <jagmeet.randhawa@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240820202309.1260755-1-matthew.brost@intel.com
(cherry picked from commit 32a42c93b7rodrigo.vivi@intel.com >
2024-08-21 11:53:15 -04:00
Matthew Brost
dd3e840a33
drm/xe: Drop HW fence pointer to HW fence ctx
...
The HW fence ctx objects are not ref counted rather tied to the life of
an LRC object. HW fences reference the HW fence ctx, HW fences can
outlive LRCs thus resulting in UAF. Drop the HW fence pointer to HW
fence ctx rather just store what is needed directly in HW fence.
v2:
- Fix typo in commit (Ashutosh)
- Use snprintf (Ashutosh)
Fixes: dd08ebf6c3matthew.brost@intel.com >
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240815193522.16008-1-matthew.brost@intel.com
(cherry picked from commit 60db6f540arodrigo.vivi@intel.com >
2024-08-21 11:53:12 -04:00
Stuart Summers
a6f78359ac
drm/xe: Fix missing workqueue destroy in xe_gt_pagefault
...
On driver reload we never free up the memory for the pagefault and
access counter workqueues. Add those destroy calls here.
Fixes: dd08ebf6c3stuart.summers@intel.com >
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/c9a951505271dc3a7aee76de7656679f69c11518.1723862633.git.stuart.summers@intel.com
(cherry picked from commit 7586fc52b1rodrigo.vivi@intel.com >
2024-08-21 11:53:02 -04:00
Matthew Brost
32a42c93b7
drm/xe: Free job before xe_exec_queue_put
...
Free job depends on job->vm being valid, the last xe_exec_queue_put can
destroy the VM. Prevent UAF by freeing job before xe_exec_queue_put.
Fixes: dd08ebf6c3matthew.brost@intel.com >
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com >
Reviewed-by: Jagmeet Randhawa <jagmeet.randhawa@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240820202309.1260755-1-matthew.brost@intel.com
2024-08-21 08:38:37 -07:00
Jani Nikula
f15e558744
drm/xe/display: drop unused rawclk_freq and RUNTIME_INFO()
...
With rawclk_freq moved to display runtime info, xe has no users left for
them.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com >
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/9f09274bddc14f555c0102f37af6df23b4433102.1724144570.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com >
2024-08-21 10:25:16 +03:00
Matthew Brost
60db6f540a
drm/xe: Drop HW fence pointer to HW fence ctx
...
The HW fence ctx objects are not ref counted rather tied to the life of
an LRC object. HW fences reference the HW fence ctx, HW fences can
outlive LRCs thus resulting in UAF. Drop the HW fence pointer to HW
fence ctx rather just store what is needed directly in HW fence.
v2:
- Fix typo in commit (Ashutosh)
- Use snprintf (Ashutosh)
Fixes: dd08ebf6c3matthew.brost@intel.com >
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240815193522.16008-1-matthew.brost@intel.com
2024-08-20 13:06:00 -07:00
Stuart Summers
df2dbc925f
drm/xe/guc: Bump the G2H queue size to account for page faults
...
With the increase in the size of the recoverable page fault
queue, we want to ensure the initial messages from GuC in
the G2H buffer have space while we transfer those out to the
actual pf_queue. Bump the G2H queue size to account for this
increase in the pf_queue size.
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Stuart Summers <stuart.summers@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/4c2b6974801bcffd8a010d838c8733fa4092573d.1723862633.git.stuart.summers@intel.com
2024-08-20 09:45:54 -07:00
Stuart Summers
3338e4f90c
drm/xe: Use topology to determine page fault queue size
...
Currently the page fault queue size is hard coded. However
the hardware supports faulting for each EU and each CS.
For some applications running on hardware with a large
number of EUs and CSs, this can result in an overflow of
the page fault queue.
Add a small calculation to determine the page fault queue
size based on the number of EUs and CSs in the platform as
detmined by fuses.
Signed-off-by: Stuart Summers <stuart.summers@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/24d582a3b48c97793b8b6a402f34b4b469471636.1723862633.git.stuart.summers@intel.com
2024-08-20 09:45:51 -07:00
Stuart Summers
7586fc52b1
drm/xe: Fix missing workqueue destroy in xe_gt_pagefault
...
On driver reload we never free up the memory for the pagefault and
access counter workqueues. Add those destroy calls here.
Fixes: dd08ebf6c3stuart.summers@intel.com >
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/c9a951505271dc3a7aee76de7656679f69c11518.1723862633.git.stuart.summers@intel.com
2024-08-20 09:40:30 -07:00
Daniele Ceraolo Spurio
a06a7b3429
drm/xe/uc: Use devm to register cleanup that includes exec_queues
...
Exec_queue cleanup requires HW access, so we need to use devm instead of
drmm for it.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com >
Cc: John Harrison <John.C.Harrison@Intel.com >
Cc: Alan Previn <alan.previn.teres.alexis@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Reviewed-by: Matthew Auld <matthew.auld@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240815230541.3828206-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com >
(cherry picked from commit 5a891a0e69rodrigo.vivi@intel.com >
2024-08-19 13:38:42 -04:00
Daniele Ceraolo Spurio
8636a5c29b
drm/xe: use devm instead of drmm for managed bo
...
The BO cleanup touches the GGTT and therefore requires the HW to be
available, so we need to use devm instead of drmm.
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/1160
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com >
Cc: Lucas De Marchi <lucas.demarchi@intel.com >
Cc: Matthew Auld <matthew.auld@intel.com >
Reviewed-by: Matthew Auld <matthew.auld@intel.com >
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809231237.1503796-2-daniele.ceraolospurio@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com >
(cherry picked from commit 8d3a2d3d76rodrigo.vivi@intel.com >
2024-08-19 13:37:50 -04:00
Tejas Upadhyay
8776b0234e
drm/xe/xe2hpg: Add Wa_14021821874
...
Wa_14021821874 applies to xe2_hpg
V2(Himal):
- Use space after define
Cc: Matt Roper <matthew.d.roper@intel.com >
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com >
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Signed-off-by: Matt Roper <matthew.d.roper@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240812134117.813670-1-tejas.upadhyay@intel.com
(cherry picked from commit 21ff3a16e9rodrigo.vivi@intel.com >
2024-08-19 13:34:58 -04:00
Daniele Ceraolo Spurio
f5cb1275c8
drm/xe: fix WA 14018094691
...
This WA is applied while initializing the media GT, but it a primary
GT WA (because it modifies a register on the primary GT), so the XE_WA
macro is returning false even when the WA should be applied.
Fix this by using the primary GT in the macro.
Note that this WA only applies to PXP and we don't yet support that in
Xe, so there are no negative effects to this bug, which is why we didn't
see any errors in testing.
v2: use the primary GT in the macro instead of marking the WA as
platform-wide (Lucas, Matt).
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com >
Cc: Matt Roper <matthew.d.roper@intel.com >
Cc: Lucas De Marchi <lucas.demarchi@intel.com >
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240807235333.1370915-1-daniele.ceraolospurio@intel.com
(cherry picked from commit e422c0bfd9rodrigo.vivi@intel.com >
2024-08-19 13:34:05 -04:00
Tejas Upadhyay
cbc6e98ab1
drm/xe/xe2: Add Wa_15015404425
...
Wa_15015404425 asks us to perform four "dummy" writes to a
non-existent register offset before every real register read.
Although the specific offset of the writes doesn't directly
matter, the workaround suggests offset 0x130030 as a good target
so that these writes will be easy to recognize and filter out in
debugging traces.
V5(MattR):
- Avoid negating an equality comparison
V4(MattR):
- Use writel and remove xe_reg usage
V3(MattR):
- Define dummy reg local to function
- Avoid tracing dummy writes
- Update commit message
V2:
- Add WA to 8/16/32bit reads also - MattR
- Corrected dummy reg address - MattR
- Use for loop to avoid mental pause - JaniN
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com >
Signed-off-by: Matt Roper <matthew.d.roper@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240709155606.2998941-1-tejas.upadhyay@intel.com
(cherry picked from commit 86c5b70a9crodrigo.vivi@intel.com >
2024-08-19 13:30:47 -04:00
Tejas Upadhyay
7e81285380
drm/xe/xe2: Make subsequent L2 flush sequential
...
Issuing the flush on top of an ongoing flush is not desirable.
Lets use lock to make it sequential.
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com >
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240710052750.3031586-1-tejas.upadhyay@intel.com
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com >
(cherry picked from commit 71733b8d7frodrigo.vivi@intel.com >
2024-08-19 13:30:47 -04:00
Bommu Krishnaiah
b196e6fcc7
drm/xe/xe2lpg: Extend workaround 14021402888
...
workaround 14021402888 also applies to Xe2_LPG.
Replicate the existing entry to one specific for Xe2_LPG.
Signed-off-by: Bommu Krishnaiah <krishnaiah.bommu@intel.com >
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com >
Cc: Matt Roper <matthew.d.roper@intel.com >
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240703090754.1323647-1-krishnaiah.bommu@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com >
(cherry picked from commit 56ab698699rodrigo.vivi@intel.com >
2024-08-19 13:30:41 -04:00
Ngai-Mint Kwan
03a2dc84f5
drm/xe/xe2lpm: Extend Wa_16021639441
...
Wa_16021639441 applies to Xe2_LPM.
Signed-off-by: Ngai-Mint Kwan <ngai-mint.kwan@linux.intel.com >
Reviewed-by: Matt Roper <matthew.d.roper@intel.com >
Signed-off-by: Matt Roper <matthew.d.roper@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240701184637.531794-1-ngai-mint.kwan@linux.intel.com
(cherry picked from commit 74e3076800rodrigo.vivi@intel.com >
2024-08-19 13:30:41 -04:00
Matthew Auld
27cb2b7fec
drm/xe/bmg: implement Wa_16023588340
...
This involves enabling l2 caching of host side memory access to VRAM
through the CPU BAR. The main fallout here is with display since VRAM
writes from CPU can now be cached in GPU l2, and display is never
coherent with caches, so needs various manual flushing. In the case of
fbc we disable it due to complications in getting this to work
correctly (in a later patch).
Signed-off-by: Matthew Auld <matthew.auld@intel.com >
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com >
Cc: Matt Roper <matthew.d.roper@intel.com >
Cc: Lucas De Marchi <lucas.demarchi@intel.com >
Cc: Vinod Govindapillai <vinod.govindapillai@intel.com >
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240703124338.208220-3-matthew.auld@intel.com
(cherry picked from commit 01570b4469rodrigo.vivi@intel.com >
2024-08-19 13:30:41 -04:00
Nirmoy Das
2368306180
drm/xe/lnl: Offload system clear page activity to GPU
...
On LNL because of flat CCS, driver creates migrates job to clear
CCS meta data. Extend that to also clear system pages using GPU.
Inform TTM to allocate pages without __GFP_ZERO to avoid double page
clearing by clearing out TTM_TT_FLAG_ZERO_ALLOC flag and set
TTM_TT_FLAG_CLEARED_ON_FREE while freeing to skip ttm pool's clear
on free as XE now takes care of clearing pages. If a bo is in system
placement such as BO created with DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING
and there is a cpu map then for such BO gpu clear will be avoided as
there is no dma mapping for such BO at that moment to create migration
jobs.
Tested this patch api_overhead_benchmark_l0 from
https://github.com/intel/compute-benchmarks
Without the patch:
api_overhead_benchmark_l0 --testFilter=UsmMemoryAllocation:
UsmMemoryAllocation(api=l0 type=Host size=4KB) 84.206 us
UsmMemoryAllocation(api=l0 type=Host size=1GB) 105775.56 us
erf tool top 5 entries:
71.44% api_overhead_be [kernel.kallsyms] [k] clear_page_erms
6.34% api_overhead_be [kernel.kallsyms] [k] __pageblock_pfn_to_page
2.24% api_overhead_be [kernel.kallsyms] [k] cpa_flush
2.15% api_overhead_be [kernel.kallsyms] [k] pages_are_mergeable
1.94% api_overhead_be [kernel.kallsyms] [k] find_next_iomem_res
With the patch:
api_overhead_benchmark_l0 --testFilter=UsmMemoryAllocation:
UsmMemoryAllocation(api=l0 type=Host size=4KB) 79.439 us
UsmMemoryAllocation(api=l0 type=Host size=1GB) 98677.75 us
Perf tool top 5 entries:
11.16% api_overhead_be [kernel.kallsyms] [k] __pageblock_pfn_to_page
7.85% api_overhead_be [kernel.kallsyms] [k] cpa_flush
7.59% api_overhead_be [kernel.kallsyms] [k] find_next_iomem_res
7.24% api_overhead_be [kernel.kallsyms] [k] pages_are_mergeable
5.53% api_overhead_be [kernel.kallsyms] [k] lookup_address_in_pgd_attr
Without this patch clear_page_erms() dominates execution time which is
also not pipelined with migration jobs. With this patch page clearing
will get pipelined with migration job and will free CPU for more work.
v2: Handle regression on dgfx(Himal)
Update commit message as no ttm API changes needed.
v3: Fix Kunit test.
v4: handle data leak on cpu mmap(Thomas)
v5: s/gpu_page_clear/gpu_page_clear_sys and move setting
it to xe_ttm_sys_mgr_init() and other nits (Matt Auld)
v6: Disable it when init_on_alloc and/or init_on_free is active(Matt)
Use compute-benchmarks as reporter used it to report this
allocation latency issue also a proper test application than mime.
In v5, the test showed significant reduction in alloc latency but
that is not the case any more, I think this was mostly because
previous test was done on IFWI which had low mem BW from CPU.
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Cc: Matthew Auld <matthew.auld@intel.com >
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com >
Reviewed-by: Matthew Auld <matthew.auld@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240816135154.19678-2-nirmoy.das@intel.com
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com >
2024-08-19 17:49:00 +02:00
Thorsten Blum
6841a26e2c
drm/xe/oa: Use vma_pages() helper function in xe_oa_mmap()
...
Use the vma_pages() helper function and remove the following
Coccinelle/coccicheck warning reported by vma_pages.cocci:
WARNING: Consider using vma_pages helper on vma
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com >
Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com >
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240819095751.539645-2-thorsten.blum@toblux.com
2024-08-19 07:41:56 -07:00
Maarten Lankhorst
ddf6492e0e
drm/xe/display: Make display suspend/resume work on discrete
...
We should unpin before evicting all memory, and repin after GT resume.
This way, we preserve the contents of the framebuffers, and won't hang
on resume due to migration engine not being restored yet.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com >
Fixes: dd08ebf6c3stable@vger.kernel.org # v6.8+
Reviewed-by: Uma Shankar <uma.shankar@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240806105044.596842-3-maarten.lankhorst@linux.intel.com
Signed-off-by: Maarten Lankhorst,,, <maarten.lankhorst@linux.intel.com >
(cherry picked from commit cb8f81c175rodrigo.vivi@intel.com >
2024-08-19 10:39:36 -04:00
Matthew Auld
730b72480e
drm/xe: prevent UAF around preempt fence
...
The fence lock is part of the queue, therefore in the current design
anything locking the fence should then also hold a ref to the queue to
prevent the queue from being freed.
However, currently it looks like we signal the fence and then drop the
queue ref, but if something is waiting on the fence, the waiter is
kicked to wake up at some later point, where upon waking up it first
grabs the lock before checking the fence state. But if we have already
dropped the queue ref, then the lock might already be freed as part of
the queue, leading to uaf.
To prevent this, move the fence lock into the fence itself so we don't
run into lifetime issues. Alternative might be to have device level
lock, or only release the queue in the fence release callback, however
that might require pushing to another worker to avoid locking issues.
Fixes: dd08ebf6c3https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2454
References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2342
References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2020
Signed-off-by: Matthew Auld <matthew.auld@intel.com >
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: <stable@vger.kernel.org > # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240814110129.825847-2-matthew.auld@intel.com
(cherry picked from commit 7116c35aacrodrigo.vivi@intel.com >
2024-08-19 10:39:28 -04:00
Matthew Brost
15939ca77d
drm/xe: Fix tile fini sequence
...
Only set tile->mmio.regs to NULL if not the root tile in tile_fini. The
root tile mmio regs is setup ealier in MMIO init thus it should be set
to NULL in mmio_fini.
Fixes: dd08ebf6c3matthew.brost@intel.com >
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com >
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809232830.3302251-1-matthew.brost@intel.com
(cherry picked from commit 3396900aa2rodrigo.vivi@intel.com >
2024-08-19 10:39:11 -04:00
Matthew Brost
7090d7fc96
drm/xe: Move VM dma-resv lock from xe_exec_queue_create to __xe_exec_queue_init
...
The critical section which requires the VM dma-resv is the call
xe_lrc_create in __xe_exec_queue_init. Move this lock to
__xe_exec_queue_init holding it just around xe_lrc_create. Not only is
good practice, this also fixes a locking double of the VM dma-resv in
the error paths of __xe_exec_queue_init as xe_lrc_put tries to acquire
this too resulting in a deadlock.
Fixes: dd08ebf6c3maarten.lankhorst@linux.intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240724152831.1848325-1-matthew.brost@intel.com
(cherry picked from commit 549dd786b6rodrigo.vivi@intel.com >
2024-08-19 10:39:04 -04:00
Ashutosh Dixit
c621f70539
drm/xe/observation: Drop empty sysctl table entry
...
An empty sysctl table entry was inadvertently left behind for observation
sysctl. The breaks on 6.11 with the following errors:
[ 219.654850] sysctl table check failed: dev/xe/(null) procname is null
[ 219.654862] sysctl table check failed: dev/xe/(null) No proc_handler
Drop the empty entry.
Fixes: 63347fe031https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2419
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com >
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240805062057.3547560-1-ashutosh.dixit@intel.com
(cherry picked from commit be1dec570brodrigo.vivi@intel.com >
2024-08-19 10:38:58 -04:00
Lucas De Marchi
f4b2a0ae1a
drm/xe: Fix opregion leak
...
Being part o the display, ideally the setup and cleanup would be done by
display itself. However this is a bigger refactor that needs to be done
on both i915 and xe. For now, just fix the leak:
unreferenced object 0xffff8881a0300008 (size 192):
comm "modprobe", pid 4354, jiffies 4295647021
hex dump (first 32 bytes):
00 00 87 27 81 88 ff ff 18 80 9b 00 00 c9 ff ff ...'............
18 81 9b 00 00 c9 ff ff 00 00 00 00 00 00 00 00 ................
backtrace (crc 99260e31):
[<ffffffff823ce65b>] kmemleak_alloc+0x4b/0x80
[<ffffffff81493be2>] kmalloc_trace_noprof+0x312/0x3d0
[<ffffffffa1345679>] intel_opregion_setup+0x89/0x700 [xe]
[<ffffffffa125bfaf>] xe_display_init_noirq+0x2f/0x90 [xe]
[<ffffffffa1199ec3>] xe_device_probe+0x7a3/0xbf0 [xe]
[<ffffffffa11f3713>] xe_pci_probe+0x333/0x5b0 [xe]
[<ffffffff81af6be8>] local_pci_probe+0x48/0xb0
[<ffffffff81af8778>] pci_device_probe+0xc8/0x280
[<ffffffff81d09048>] really_probe+0xf8/0x390
[<ffffffff81d0937a>] __driver_probe_device+0x8a/0x170
[<ffffffff81d09503>] driver_probe_device+0x23/0xb0
[<ffffffff81d097b7>] __driver_attach+0xc7/0x190
[<ffffffff81d0628d>] bus_for_each_dev+0x7d/0xd0
[<ffffffff81d0851e>] driver_attach+0x1e/0x30
[<ffffffff81d07ac7>] bus_add_driver+0x117/0x250
Fixes: 44e694958brodrigo.vivi@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240724215309.644423-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com >
(cherry picked from commit 6f4e43a2f7rodrigo.vivi@intel.com >
2024-08-19 10:38:51 -04:00
Maarten Lankhorst
cb8f81c175
drm/xe/display: Make display suspend/resume work on discrete
...
We should unpin before evicting all memory, and repin after GT resume.
This way, we preserve the contents of the framebuffers, and won't hang
on resume due to migration engine not being restored yet.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com >
Fixes: dd08ebf6c3stable@vger.kernel.org # v6.8+
Reviewed-by: Uma Shankar <uma.shankar@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240806105044.596842-3-maarten.lankhorst@linux.intel.com
Signed-off-by: Maarten Lankhorst,,, <maarten.lankhorst@linux.intel.com >
2024-08-19 15:17:04 +02:00
Maarten Lankhorst
492be2a070
drm/xe/display: Match i915 driver suspend/resume sequences better
...
Suspend fbdev sooner, and disable user access before suspending to
prevent some races. I've noticed this when comparing xe suspend to
i915's.
Matches the following commits from i915:
24b412b1bf1ef28d86bebd738d859emaarten.lankhorst@linux.intel.com >
Cc: Imre Deak <imre.deak@intel.com >
Reviewed-by: Uma Shankar <uma.shankar@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240806105044.596842-2-maarten.lankhorst@linux.intel.com
Signed-off-by: Maarten Lankhorst,,, <maarten.lankhorst@linux.intel.com >
2024-08-19 15:16:52 +02:00
Matthew Auld
7116c35aac
drm/xe: prevent UAF around preempt fence
...
The fence lock is part of the queue, therefore in the current design
anything locking the fence should then also hold a ref to the queue to
prevent the queue from being freed.
However, currently it looks like we signal the fence and then drop the
queue ref, but if something is waiting on the fence, the waiter is
kicked to wake up at some later point, where upon waking up it first
grabs the lock before checking the fence state. But if we have already
dropped the queue ref, then the lock might already be freed as part of
the queue, leading to uaf.
To prevent this, move the fence lock into the fence itself so we don't
run into lifetime issues. Alternative might be to have device level
lock, or only release the queue in the fence release callback, however
that might require pushing to another worker to avoid locking issues.
Fixes: dd08ebf6c3https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2454
References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2342
References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2020
Signed-off-by: Matthew Auld <matthew.auld@intel.com >
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: <stable@vger.kernel.org > # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240814110129.825847-2-matthew.auld@intel.com
2024-08-19 12:38:09 +01:00
Nirmoy Das
6b77dab5da
drm/xe: Remove redundant param from xe_bo_create_user
...
BO from xe_bo_create_user() will always be of type,
ttm_bo_type_device. So remove that redundant parameter.
Cc: Matthew Auld <matthew.auld@intel.com >
Cc: Matthew Brost <matthew.brost@intel.com >
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240816102248.25628-1-nirmoy.das@intel.com
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com >
2024-08-19 09:38:16 +02:00
Francois Dugast
4099cfda9d
drm/xe/device: Remove unused xe_device::usm::num_vm_in_*
...
Those counters were used to keep track of the numbers VMs in fault mode
and in non-fault mode, to determine if the whole device was in fault mode
or not. This is no longer needed so remove those variables and their
usages.
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-12-francois.dugast@intel.com
2024-08-17 18:31:59 -07:00
Francois Dugast
226d92e49a
drm/xe/vm: Remove restriction that all VMs must be faulting if one is
...
With this restriction, all VMs on the device must be faulting VMs if there
is already one faulting VM, in which case the device is considered in
fault mode. This prevents for example an application from running 3D jobs
for the compositor while submitting a SVM compute job on the same device.
Now that mutual exclusion of faulting LR jobs and dma fence jobs is
ensured on the hw engine group, remove this restriction to allow running
faulting and non-faulting VMs on the same device.
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-11-francois.dugast@intel.com
2024-08-17 18:31:58 -07:00
Francois Dugast
d16ef1a18e
drm/xe/exec: Switch hw engine group execution mode upon job submission
...
If the job about to be submitted is a dma-fence job, update the current
execution mode of the hw engine group. This triggers an immediate suspend
of the exec queues running faulting long-running jobs.
If the job about to be submitted is a long-running job, kick a new worker
used to resume the exec queues running faulting long-running jobs once
the dma-fence jobs have completed.
v2: Kick the resume worker from exec IOCTL, switch to unordered workqueue,
destroy it after use (Matt Brost)
v3: Do not resume if no exec queue was suspended (Matt Brost)
v4: Squash commits (Matt Brost)
v5: Do not kick the worker when xe_vm_in_preempt_fence_mode (Matt Brost)
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-10-francois.dugast@intel.com
2024-08-17 18:31:57 -07:00
Francois Dugast
770bd1d341
drm/xe/hw_engine_group: Ensure safe transition between execution modes
...
Provide a way to safely transition execution modes of the hw engine group
ahead of the actual execution. When necessary, either wait for running
jobs to complete or preempt them, thus ensuring mutual exclusion between
execution modes.
Unlike a mutex, the rw_semaphore used in this context allows multiple
submissions in the same mode.
v2: Use lockdep_assert_held_write, add annotations (Matt Brost)
v3: Fix kernel doc, remove redundant code (Matt Brost)
v4: Now that xe_hw_engine_group_suspend_faulting_lr_jobs can fail,
propagate the error to the caller (Matt Brost)
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-9-francois.dugast@intel.com
2024-08-17 18:31:56 -07:00
Francois Dugast
2750ff97ee
drm/xe/hw_engine_group: Add helper to wait for dma fence jobs
...
This is a required feature for faulting long running jobs not to be
submitted while dma fence jobs are running on the hw engine group.
v2: Switch to lockdep_assert_held_write in worker, get a proper reference
for the last fence (Matt Brost)
v3: Directly call dma_fence_put with the fence ref (Matt Brost)
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-8-francois.dugast@intel.com
2024-08-17 18:31:55 -07:00
Francois Dugast
0d92cd8935
drm/xe/exec_queue: Prepare last fence for hw engine group resume context
...
Ensure we can safely take a ref of the exec queue's last fence from the
context of resuming jobs from the hw engine group. The locking requirements
differ from the general case, hence the introduction of this new function.
v2: Add kernel doc, rework the code to prevent code duplication
v3: Fix kernel doc, remove now unnecessary lockdep variants (Matt Brost)
v4: Remove new put function (Matt Brost)
Signed-off-by: Francois Dugast <francois.dugast@intel.com >
Reviewed-by: Matthew Brost <matthew.brost@intel.com >
Signed-off-by: Matthew Brost <matthew.brost@intel.com >
Link: https://patchwork.freedesktop.org/patch/msgid/20240809155156.1955925-7-francois.dugast@intel.com
2024-08-17 18:31:54 -07:00
