An xe file can outlive the associated process as the GPU cleanup is just
triggered upon file close (process kill) and completes sometime later.
If the file close triggers error conditions (GPU hangs) the process
cannot be safely referenced to retrieve the name and pid for debug
information. Store the process name and pid directly in the xe file to
be safe.
v2:
- Access file->pid via rcu_access_pointer (Matthew Auld)
Fixes: b10d0c5e9d ("drm/xe: Add process name to devcoredump")
Fixes: f6ca930d97 ("drm/xe: Add process name and PID to job timedout message")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240723151045.1725417-1-matthew.brost@intel.com
eu_type_to_str() relies on -Wswitch to warn (and -Werror) to make sure
it handles all enum values. However it's perfectly legal to pass an int
to that function so in the end that function may happen to return
nothing. There's too much implicit knowledge about the initialization
of eu_type for a compiler to notice eu_type is never assigned to
anything other than those values.
Trying to reproduce this issue, none of gcc-9, gcc-10 and gcc-13
triggered for me, but this was reported in a different system with
gcc-10:
drivers/gpu/drm/xe/xe.o: warning: objtool: xe_gt_topology_dump() falls through to next function xe_gt_topology_init()
Also it was reported these warnings when building with clang:
drivers/gpu/drm/xe/xe.o: warning: objtool: xe_gt_topology_dump+0x77: sibling call from callable instruction with modified stack frame
drivers/gpu/drm/xe/xe.o: warning: objtool: xe_gt_topology_dump() falls through to next function xe_dss_mask_group_ffs()
drivers/gpu/drm/xe/xe.o: warning: objtool: xe_gt_topology_dump+0x77: can't find jump dest instruction at .text.xe_gt_topology_dump+0xc0
Since that value is not really possible in real world, just take the
simple approach and return NULL.
Fixes: 7108b4a589 ("drm/xe/uapi: Expose SIMD16 EU mask in topology query")
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240719191534.3845469-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
There is no point to run those tests on VFs devices as they can't
access any of the MOCS registers. Skip testing on the VF device.
[ ] =================== xe_mocs (1 subtest) ====================
[ ] ================ xe_live_mocs_kernel_kunit ================
[ ] [PASSED] 0000:4d:00.0
[ ] [SKIPPED] 0000:4d:00.1
[ ] ============ [PASSED] xe_live_mocs_kernel_kunit ============
[ ] ===================== [PASSED] xe_mocs =====================
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240720142528.530-8-michal.wajdeczko@intel.com
Instead of iterating over available Xe devices within a testcase,
without being able to distinguish potential failures from different
devices on system with many Xe devices, introduce helpers that will
allow to treat each Xe device as a parameter for the testcase like:
static void bar(struct kunit *test)
{
struct xe_device *xe = test->priv;
...
}
struct kunit_case foo_live_tests[] = {
KUNIT_CASE_PARAM(bar, xe_pci_live_device_gen_param),
{}
};
struct kunit_suite foo_suite = {
.name = "foo_live",
.test_cases = foo_live_tests,
.init = xe_kunit_helper_xe_device_live_test_init,
};
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240720142528.530-3-michal.wajdeczko@intel.com
Having two methods to wait on GT TLB invalidations is not ideal. Remove
xe_gt_tlb_invalidation_wait and only use GT TLB invalidation fences.
In addition to two methods being less than ideal, once GT TLB
invalidations are coalesced the seqno cannot be assigned during
xe_gt_tlb_invalidation_ggtt/range. Thus xe_gt_tlb_invalidation_wait
would not have a seqno to wait one. A fence however can be armed and
later signaled.
v3:
- Add explaination about coalescing to commit message
v4:
- Don't put dma fence if defined on stack (CI)
v5:
- Initialize ret to zero (CI)
v6:
- Use invalidation_fence_signal helper in tlb timeout (Matthew Auld)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240719172905.1527927-3-matthew.brost@intel.com
xe_file_close triggers an asynchronous queue cleanup and then frees up
the xef object. Since queue cleanup flushes all pending jobs and the KMD
stores client usage stats into the xef object after jobs are flushed, we
see a use-after-free for the xef object. Resolve this by taking a
reference to xef from xe_exec_queue.
While at it, revert an earlier change that contained a partial work
around for this issue.
v2:
- Take a ref to xef even for the VM bind queue (Matt)
- Squash patches relevant to that fix and work around (Lucas)
v3: Fix typo (Lucas)
Fixes: ce62827bc2 ("drm/xe: Do not access xe file when updating exec queue run_ticks")
Fixes: 6109f24f87 ("drm/xe: Add helper to accumulate exec queue runtime")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1908
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-5-umesh.nerlige.ramappa@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
PVC, Xe2 and later platforms have 16-wide EUs. We were implicitly
reporting for PVC the number of 16-wide EUs without giving userspace any
hint that they were different than for other platforms. Xe2 and later
also have 16-wide, but in those cases the reported number would
correspond to the 8-wide count.
To avoid confusion and make sure the right number is used by userspace
depending on the platform, add a new item to the topology query and drop
the one that is not available. The new mask reported for both PVC and
Xe2 should now match the numbers reported via hwconfig.
v2: Use a different topo item with EU type in its name to report the
new mask instead of adding the type itself as the item (Matt Roper)
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
Acked-by: Wenbin Lu <wenbin.lu@intel.com>
Acked-by: Effie Yu <effie.yu@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240710220446.2169797-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Pull drm updates from Dave Airlie:
"There's a lot of stuff in here, amd, i915 and xe have new platform
work, lots of core rework around EDID handling, some new COMPILE_TEST
options, maintainer changes and a lots of other stuff. Summary:
core:
- deprecate DRM data and return 0 date
- connector: Create a set of helpers to help with HDMI support
- Remove driver owner assignments
- Allow more drivers to compile with COMPILE_TEST
- Conversions to drm_edid
- Sprinkle MODULE_DESCRIPTIONS everywhere they are missing
- Remove drm_mm_replace_node
- print: Add a drm prefix to warn level messages too, remove
___drm_dbg, consolidate prefix handling
- New monochrome TV mode variant
ttm:
- improve number of page faults on some platforms
- fix test builds under PREEMPT_RT
- more test coverage
ci:
- Require a more recent version of mesa
- improve farm setup and test generation
dma-buf:
- warn if reserving 0 fence slots
- internal API heap enhancements
fbdev:
- Create memory manager optimized fbdev emulation
panic:
- Allow to select fonts
- improve drm_fb_dma_get_scanout_buffer
- Allow to dump kmsg to the screen
bridge:
- Remove redundant checks on bridge->encoder
- Remove drm_bridge_chain_mode_fixup
- bridge-connector: Plumb in the new HDMI helper
- analogix_dp: Various improvements, handle AUX transfers timeout
- samsung-dsim: Fix timings calculation
- tc358767: Plenty of small fixes, fix no connector attach, fix
clocks
- sii902x: state validation improvements
panels:
- Switch panels from register table initialization to proper code
- Now that the panel code tracks the panel state, remove every ad-hoc
implementation in the panel drivers
- More cleanup of prepare / enable state tracking in drivers
- edp: Drop legacy panel compatibles
- simple-bridge: Switch to devm_drm_bridge_add
- New panels: Lincoln Tech Sol LCD185-101CT, Microtips Technology
13-101HIEBCAF0-C, Microtips Technology MF-103HIEB0GA0,
BOE nv110wum-l60, IVO t109nw41, WL-355608-A8, PrimeView
PM070WL4, Lincoln Technologies LCD197, Ortustech
COM35H3P70ULC, AUO G104STN01, K&d kd101ne3-40ti
amdgpu:
- DCN 4.0.x support
- GC 12.0 support
- GMC 12.0 support
- SDMA 7.0 support
- MES12 support
- MMHUB 4.1 support
- GFX12 modifier and DCC support
- lots of IP fixes/updates
amdkfd:
- Contiguous VRAM allocations
- GC 12.0 support
- SDMA 7.0 support
- SR-IOV fixes
- KFD GFX ALU exceptions
i915:
- Battlemage Xe2 HPD display enablement
- Panel Replay enabling
- DP AUX-less ALPM/LOBF
- Enable link training failure fallback for DP MST links
- CMRR (Content Match Refresh Rate) enabling
- Increase ADL-S/ADL-P/DG2+ max TMDS bitrate to 6 Gbps
- Enable eDP AUX based HDR backlight
- Support replaying GPU hangs with captured context image
- Automate CCS Mode setting during engine resets
- lots of refactoring
- Support replaying GPU hangs with captured context image
- Increase FLR timeout from 3s to 9s
- Enable w/a 16021333562 for DG2, MTL and ARL [guc]
xe:
- update MAINATINERS
- New uapi adding OA functionality to Xe
- expose l3 bank mask
- fix display detect on ADL-N
- runtime PM Fixes
- Fix silent backmerge issues
- More prep for SR-IOV
- HWmon additions
- per client usage info
- Rework GPU page fault handling
- Drop EXEC_QUEUE_FLAG_BANNED
- Add BMG PCI IDs
- Scheduler fixes and improvements
- Rename xe_exec_queue::compute to xe_exec_queue::lr
- Use ttm_uncached for BO with NEEDS_UC flag
- Rename xe perf layer as xe observation layer
- lots of refactoring
radeon:
- Backlight workaround for iMac
- Silence UBSAN flex array warnings
msm:
- Validate registers XML description against schema in CI
- core/dpu: SM7150 support
- mdp5: Add support for MSM8937
- gpu: Add param for userspace to know if raytracing is supported
- gpu: X185 support (aka gpu in X1 laptop chips)
- gpu: a505 support
ivpu:
- hardware scheduler support
- profiling support
- improvements to the platform support layer
- firmware handling improvements
- clocks/power mgmt improvements
- scheduler/logging improvements
habanalabs:
- Gradual sleep in polling memory macro
- Reduce Gaudi2 MSI-X interrupt count to 128
- Add Gaudi2-D revision support
- Add timestamp to CPLD info
- Gaudi2: Assume hard-reset by firmware upon MC SEI severe error
- Align Gaudi2 interrupt names
- Check for errors after preboot is ready
- Change habanalabs maintainer and git repo path
mgag200:
- refactoring and improvements
- Add BMC output
- enable polling
nouveau:
- add registry command line
v3d:
- perf counters improvements
zynqmp:
- irq and debugfs improvements
atmel-hlcdc:
- Support XLCDC in sam9x7
mipi-dbi:
- Remove mipi_dbi_machine_little_endian
- make SPI bits per word configurable
- support RGB888
- allow pixel formats to be specified in the DT
sun4i:
- Rework the blender setup for DE2
panfrost:
- Enable MT8188 support
vc4:
- Monochrome TV support
exynos:
- fix fallback mode regression
- fix memory leak
- Use drm_edid_duplicate() instead of kmemdup()
etnaviv:
- fix i.MX8MP NPU clock gating
- workaround FE register cdc issues on some cores
- fix DMA sync handling for cached buffers
- fix job timeout handling
- keep TS enabled on MMUv2 cores for improved performance
mediatek:
- Convert to platform remove callback returning void-
- Drop chain_mode_fixup call in mode_valid()
- Fixes the errors of MediaTek display driver found by IGT
- Add display support for the MT8365-EVK board
- Fix bit depth overwritten for mtk_ovl_set bit_depth()
- Fix possible_crtcs calculation
- Fix spurious kfree()
ast:
- refactor mode setting code
stm:
- Add LVDS support
- DSI PHY updates"
* tag 'drm-next-2024-07-18' of https://gitlab.freedesktop.org/drm/kernel: (2501 commits)
drm/amdgpu/mes12: add missing opcode string
drm/amdgpu/mes11: update opcode strings
Revert "drm/amd/display: Reset freesync config before update new state"
drm/omap: Restrict compile testing to PAGE_SIZE less than 64KB
drm/xe: Drop trace_xe_hw_fence_free
drm/xe/uapi: Rename xe perf layer as xe observation layer
drm/amdgpu: remove exp hw support check for gfx12
drm/amdgpu: timely save bad pages to eeprom after gpu ras reset is completed
drm/amdgpu: flush all cached ras bad pages to eeprom
drm/amdgpu: select compute ME engines dynamically
drm/amd/display: Allow display DCC for DCN401
drm/amdgpu: select compute ME engines dynamically
drm/amdgpu/job: Replace DRM_INFO/ERROR logging
drm/amdgpu: select compute ME engines dynamically
drm/amd/pm: Ignore initial value in smu response register
drm/amdgpu: Initialize VF partition mode
drm/amd/amdgpu: fix SDMA IRQ client ID <-> req mapping
MAINTAINERS: fix Xinhui's name
MAINTAINERS: update powerplay and swsmu
drm/qxl: Pin buffer objects for internal mappings
...
Wedge the entire device, not just GT which may have triggered the wedge.
To implement this, cleanup the layering so xe_device_declare_wedged()
calls into the lower layers (GT) to ensure entire device is wedged.
While we are here, also signal any pending GT TLB invalidations upon
wedging device.
Lastly, short circuit reset wait if device is wedged.
v2:
- Short circuit reset wait if device is wedged (Local testing)
Fixes: 8ed9aaae39 ("drm/xe: Force wedged state and block GT reset upon any GPU hang")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240716063902.1390130-1-matthew.brost@intel.com
(cherry picked from commit 7dbe8af13c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Due to the current design of the BO and VRAM manager, any object
with XE_BO_FLAG_PINNED flag, which the PF driver uses during VF
LMEM provisionining, is created with the TTM_PL_FLAG_CONTIGUOUS
flag, which may cause VRAM fragmentation that prevents subsequent
allocations of larger objects, like fair VF LMEM provisioning.
To avoid such failures, round down fair VF LMEM provisioning size
to next power of two size, to compensate what xe_ttm_vram_mgr is
doing to achieve contiguous allocations.
Fixes: ac6598aed1 ("drm/xe/pf: Add support to configure SR-IOV VFs")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240711192320.1198-2-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 4c3fe5eae4)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
As per recommendation in the workarounds:
WA_22019338487
There is an issue with accessing Stolen memory pages due a
hardware limitation. Limit the usage of stolen memory for
fbdev for LNL+. Don't use BIOS FB from stolen on LNL+ and
assign the same from system memory.
v2: Corrected the WA Number, limited WA to LNL and
Adopted XE_WA framework as suggested by Lucas and Matt.
v3: Introduced the waxxx_display to implement display side
of WA changes on Lunarlake. Used xe_root_mmio_gt and
avoid the for loop (Suggested by Lucas)
v4: Fixed some nits (Luca)
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240717082252.3875909-1-uma.shankar@intel.com
Xe2+ has unified compression (exactly one compression mode/format),
where compression is now controlled via PAT at PTE level.
This simplifies KMD operations, as it can now decompress freely
without concern for the buffer's original compression format—unlike DG2,
which had multiple compression formats and thus required copying the
raw CCS state during VRAM eviction. In addition mixed VRAM and system
memory buffers were not supported with compression enabled.
On Xe2 dGPU compression is still only supported with VRAM, however we
can now support compression with VRAM and system memory buffers,
with GPU access being seamless underneath. So long as when doing
VRAM -> system memory the KMD uses compressed -> uncompressed,
to decompress it. This also allows CPU access to such buffers,
assuming that userspace first decompress the corresponding
pages being accessed.
If the pages are already in system memory then KMD would have already
decompressed them. When restoring such buffers with sysmem -> VRAM
the KMD can't easily know which pages were originally compressed,
so we always use uncompressed -> uncompressed here.
With this it also means we can drop all the raw CCS handling on such
platforms (including needing to allocate extra CCS storage).
In order to support this we now need to have two different identity
mappings for compressed and uncompressed VRAM.
In this patch, we set up the additional identity map for the VRAM with
compressed pat_index. We then select the appropriate mapping during
migration/clear. During eviction (vram->sysmem), we use the mapping
from compressed -> uncompressed. During restore (sysmem->vram), we need
the mapping from uncompressed -> uncompressed.
Therefore, we need to have two different mappings for compressed and
uncompressed vram. We set up an additional identity map for the vram
with compressed pat_index.
We then select the appropriate mapping during migration/clear.
v2: Formatting nits, Updated code to match recent changes in
xe_migrate_prepare_vm(). (Matt)
v3: Move identity map loop to a helper function. (Matt Brost)
v4: Split helper function in different patch, and
add asserts and nits. (Matt Brost)
v5: Convert the 2 bool arguments of pte_update_size to flags
argument (Matt Brost)
v6: Formatting nits (Matt Brost)
Signed-off-by: Akshata Jahagirdar <akshata.jahagirdar@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b00db5c7267e54260cb6183ba24b15c1e6ae52a3.1721250309.git.akshata.jahagirdar@intel.com
Wedge the entire device, not just GT which may have triggered the wedge.
To implement this, cleanup the layering so xe_device_declare_wedged()
calls into the lower layers (GT) to ensure entire device is wedged.
While we are here, also signal any pending GT TLB invalidations upon
wedging device.
Lastly, short circuit reset wait if device is wedged.
v2:
- Short circuit reset wait if device is wedged (Local testing)
Fixes: 8ed9aaae39 ("drm/xe: Force wedged state and block GT reset upon any GPU hang")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240716063902.1390130-1-matthew.brost@intel.com
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
Due to the current design of the BO and VRAM manager, any object
with XE_BO_FLAG_PINNED flag, which the PF driver uses during VF
LMEM provisionining, is created with the TTM_PL_FLAG_CONTIGUOUS
flag, which may cause VRAM fragmentation that prevents subsequent
allocations of larger objects, like fair VF LMEM provisioning.
To avoid such failures, round down fair VF LMEM provisioning size
to next power of two size, to compensate what xe_ttm_vram_mgr is
doing to achieve contiguous allocations.
Fixes: ac6598aed1 ("drm/xe/pf: Add support to configure SR-IOV VFs")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240711192320.1198-2-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
The test case logic is implemented by the functions compiled as
part of the core Xe driver module and then exported to build and
register the test suite in the live test module.
But we don't need to export individual test case functions, we may
just export the entire test suite. And we don't need to register
this test suite in a separate file, it can be done in the main
file of the live test module.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240708111210.1154-5-michal.wajdeczko@intel.com
