When imported dma-bufs are destroyed, TTM is not fully
individualizing the dma-resv, but it *is* copying the fences that
need to be waited for before declaring idle. So in the case where
the bo->resv != bo->_resv we can still drop the preempt-fences, but
make sure we do that on bo->_resv which contains the fence-pointer
copy.
In the case where the copying fails, bo->_resv will typically not
contain any fences pointers at all, so there will be nothing to
drop. In that case, TTM would have ensured all fences that would
have been copied are signaled, including any remaining preempt
fences.
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Fixes: fa0af721bd ("drm/ttm: test private resv obj on release/destroy")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.16+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Tested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251217093441.5073-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 425fe550fb)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
A 10ms timeslice for long-running workloads is far too long and causes
significant jitter in benchmarks when the system is shared. Adjust the
value to 5ms for preempt-fencing VMs, as the resume step there is quite
costly as memory is moved around, and set it to zero for pagefault VMs,
since switching back to pagefault mode after dma-fence mode is
relatively fast.
Also change min_run_period_ms to 'unsiged int' type rather than 's64' as
only positive values make sense.
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/20251212182847.1683222-2-matthew.brost@intel.com
(cherry picked from commit 33a5abd9a6)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
The exec and vm_bind ioctl allow userspace to specify an arbitrary
num_syncs value. Without bounds checking, a very large num_syncs
can force an excessively large allocation, leading to kernel warnings
from the page allocator as below.
Introduce DRM_XE_MAX_SYNCS (set to 1024) and reject any request
exceeding this limit.
"
------------[ cut here ]------------
WARNING: CPU: 0 PID: 1217 at mm/page_alloc.c:5124 __alloc_frozen_pages_noprof+0x2f8/0x2180 mm/page_alloc.c:5124
...
Call Trace:
<TASK>
alloc_pages_mpol+0xe4/0x330 mm/mempolicy.c:2416
___kmalloc_large_node+0xd8/0x110 mm/slub.c:4317
__kmalloc_large_node_noprof+0x18/0xe0 mm/slub.c:4348
__do_kmalloc_node mm/slub.c:4364 [inline]
__kmalloc_noprof+0x3d4/0x4b0 mm/slub.c:4388
kmalloc_noprof include/linux/slab.h:909 [inline]
kmalloc_array_noprof include/linux/slab.h:948 [inline]
xe_exec_ioctl+0xa47/0x1e70 drivers/gpu/drm/xe/xe_exec.c:158
drm_ioctl_kernel+0x1f1/0x3e0 drivers/gpu/drm/drm_ioctl.c:797
drm_ioctl+0x5e7/0xc50 drivers/gpu/drm/drm_ioctl.c:894
xe_drm_ioctl+0x10b/0x170 drivers/gpu/drm/xe/xe_device.c:224
vfs_ioctl fs/ioctl.c:51 [inline]
__do_sys_ioctl fs/ioctl.c:598 [inline]
__se_sys_ioctl fs/ioctl.c:584 [inline]
__x64_sys_ioctl+0x18b/0x210 fs/ioctl.c:584
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xbb/0x380 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f
...
"
v2: Add "Reported-by" and Cc stable kernels.
v3: Change XE_MAX_SYNCS from 64 to 1024. (Matt & Ashutosh)
v4: s/XE_MAX_SYNCS/DRM_XE_MAX_SYNCS/ (Matt)
v5: Do the check at the top of the exec func. (Matt)
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Reported-by: Koen Koning <koen.koning@intel.com>
Reported-by: Peter Senna Tschudin <peter.senna@linux.intel.com>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/6450
Cc: <stable@vger.kernel.org> # v6.12+
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: Carl Zhang <carl.zhang@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Ivan Briano <ivan.briano@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251205234715.2476561-5-shuicheng.lin@intel.com
(cherry picked from commit b07bac9bd7)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Pass character "0" rather than NULL terminator to properly format
queue restoration SMI events. Currently, the NULL terminator precedes
the newline character that is intended to delineate separate events
in the SMI event buffer, which can break userspace parsers.
Signed-off-by: Brian Kocoloski <brian.kocoloski@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6e7143e5e6)
User-configured SCLK(GPU core clock)frequencies were not persisting
across S0ix suspend/resume cycles on smu v14 hardware.
The issue occurred because of the code resetting clock frequency
to zero during resume.
This patch addresses the problem by:
- Preserving user-configured values in driver and sets the
clock frequency across resume
- Preserved settings are sent to the hardware during resume
Signed-off-by: mythilam <mythilam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 20ba98326f)
During GT reset recovery in do_gt_restart(), xe_uc_start() was called
before xe_reg_sr_apply_mmio() restored engine-specific registers. This
created a race window where the scheduler could run jobs before hardware
state was fully restored.
This caused failures in eudebug tests (xe_exec_sip_eudebug@breakpoint-
waitsip-*) where TD_CTL register (containing TD_CTL_GLOBAL_DEBUG_ENABLE)
wasn't restored before jobs started executing. Breakpoints would fail to
trigger SIP entry because the debug enable bit wasn't set yet.
Fix by moving xe_uc_start() after all MMIO register restoration,
including engine registers and CCS mode configuration, ensuring all
hardware state is fully restored before any jobs can be scheduled.
Fixes: dd08ebf6c3 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Jan Maslak <jan.maslak@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251210145618.169625-2-jan.maslak@intel.com
(cherry picked from commit 825aed0328)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
MEI GSC interrupt comes from i915 or xe driver. It has top half and
bottom half. Top half is called from i915/xe interrupt handler. It
should be in irq disabled context.
With RT kernel(PREEMPT_RT enabled), by default IRQ handler is in
threaded IRQ. MEI GSC top half might be in threaded IRQ context.
generic_handle_irq_safe API could be called from either IRQ or
process context, it disables local IRQ then calls MEI GSC interrupt
top half.
This change fixes B580 GPU boot issue with RT enabled.
Fixes: e02cea83d3 ("drm/xe/gsc: add Battlemage support")
Tested-by: Baoli Zhang <baoli.zhang@intel.com>
Signed-off-by: Junxiao Chang <junxiao.chang@intel.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20251107033152.834960-1-junxiao.chang@intel.com
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
(cherry picked from commit 3efadf0287)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
If wait for ring space started just before migration, it can delay
the recovery process, by waiting without bailout path for up to 2
seconds.
Two second wait for recovery is not acceptable, and if the ring was
completely filled even without the migration temporarily stopping
execution, then such a wait will result in up to a thousand new jobs
(assuming constant flow) being added while the wait is happening.
While this will not cause data corruption, it will lead to warning
messages getting logged due to reset being scheduled on a GT under
recovery. Also several seconds of unresponsiveness, as the backlog
of jobs gets progressively executed.
Add a bailout condition, to make sure the recovery starts without
much delay. The recovery is expected to finish in about 100 ms when
under moderate stress, so the condition verification period needs to be
below that - settling at 64 ms.
The theoretical max time which the recovery can take depends on how
many requests can be emitted to engine rings and be pending execution.
While stress testing, it was possible to reach 10k pending requests
on rings when a platform with two GTs was used. This resulted in max
recovery time of 5 seconds. But in real life situations, it is very
unlikely that the amount of pending requests will ever exceed 100,
and for that the recovery time will be around 50 ms - well within our
claimed limit of 100ms.
Fixes: a4dae94aad ("drm/xe/vf: Wakeup in GuC backend on VF post migration recovery")
Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patch.msgid.link/20251204200820.2206168-1-tomasz.lis@intel.com
(cherry picked from commit a00e305fba)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
The Xe driver fails to build when CONFIG_DRM_XE_GPUSVM is disabled
but CONFIG_DRM_GPUSVM is turned on, due to the clash of two commits:
In file included from drivers/gpu/drm/xe/xe_vm_madvise.c:8:
drivers/gpu/drm/xe/xe_svm.h: In function 'xe_svm_init':
include/linux/stddef.h:8:14: error: passing argument 5 of 'drm_gpusvm_init' makes integer from pointer without a cast [-Wint-conversion]
drivers/gpu/drm/xe/xe_svm.h:217:38: note: in expansion of macro 'NULL'
217 | NULL, NULL, 0, 0, 0, NULL, NULL, 0);
| ^~~~
In file included from drivers/gpu/drm/xe/xe_bo_types.h:11,
from drivers/gpu/drm/xe/xe_bo.h:11,
from drivers/gpu/drm/xe/xe_vm_madvise.c:11:
include/drm/drm_gpusvm.h:254:35: note: expected 'long unsigned int' but argument is of type 'void *'
254 | unsigned long mm_start, unsigned long mm_range,
| ~~~~~~~~~~~~~~^~~~~~~~
In file included from drivers/gpu/drm/xe/xe_vm_madvise.c:14:
drivers/gpu/drm/xe/xe_svm.h:216:16: error: too many arguments to function 'drm_gpusvm_init'; expected 10, have 11
216 | return drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM (simple)", &vm->xe->drm,
| ^~~~~~~~~~~~~~~
217 | NULL, NULL, 0, 0, 0, NULL, NULL, 0);
| ~
include/drm/drm_gpusvm.h:251:5: note: declared here
Adapt the caller to the new argument list by removing the extraneous
NULL argument.
Fixes: 9e97874148 ("drm/xe/userptr: replace xe_hmm with gpusvm")
Fixes: 10aa5c8060 ("drm/gpusvm, drm/xe: Fix userptr to not allow device private pages")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/20251204094704.1030933-1-arnd@kernel.org
(cherry picked from commit 29bce9c8b4)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Pull in rc1 to include all changes since the merge window closed,
and grab all fixes and changes from drm/drm-next.
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Pull more drm fixes from Dave Airlie:
"These are the enqueued fixes that ended up in our fixes branch,
nouveau mostly, along with some small fixes in other places.
plane:
- Handle IS_ERR vs NULL in drm_plane_create_hotspot_properties()
ttm:
- fix devcoredump for evicted bos
panel:
- Fix stack usage warning in novatek-nt35560
nouveau:
- alloc fwsec sb at boot to avoid s/r problems
- fix strcpy usage
- fix i2c encoder crash
bridge:
- Ignore spurious PLL_UNLOCK bit in ti-sn65dsi83
mgag200:
- Fix bigendian handling in mgag200
tilcdc:
- Fix probe failure in tilcdc"
* tag 'drm-fixes-2025-12-13' of https://gitlab.freedesktop.org/drm/kernel:
drm/mgag200: Fix big-endian support
drm/tilcdc: Fix removal actions in case of failed probe
drm/ttm: Avoid NULL pointer deref for evicted BOs
drm: nouveau: Replace sprintf() with sysfs_emit()
drm/nouveau: fix circular dep oops from vendored i2c encoder
drm/nouveau: refactor deprecated strcpy
drm/plane: Fix IS_ERR() vs NULL check in drm_plane_create_hotspot_properties()
drm/bridge: ti-sn65dsi83: ignore PLL_UNLOCK errors
drm/nouveau/gsp: Allocate fwsec-sb at boot
drm/panel: novatek-nt35560: avoid on-stack device structure
Pull drm fixes from Dave Airlie:
"This is the weekly fixes for what is in next tree, mostly amdgpu and
some i915, panthor and a core revert.
core:
- revert dumb bo 8 byte alignment
amdgpu:
- SI fix
- DC reduce stack usage
- HDMI fixes
- VCN 4.0.5 fix
- DP MST fix
- DC memory allocation fix
amdkfd:
- SVM fix
- Trap handler fix
- VGPR fixes for GC 11.5
i915:
- Fix format string truncation warning
- FIx runtime PM reference during fbdev BO creation
panthor:
- fix UAF
renesas:
- fix sync flag handling"
* tag 'drm-next-2025-12-13' of https://gitlab.freedesktop.org/drm/kernel:
Revert "drm/amd/display: Fix pbn to kbps Conversion"
drm/amd: Fix unbind/rebind for VCN 4.0.5
drm/i915: Fix format string truncation warning
drm/i915/fbdev: Hold runtime PM ref during fbdev BO creation
drm/amd/display: Improve HDMI info retrieval
drm/amdkfd: bump minimum vgpr size for gfx1151
drm/amd/display: shrink struct members
drm/amdkfd: Export the cwsr_size and ctl_stack_size to userspace
drm/amd/display: Refactor dml_core_mode_support to reduce stack frame
drm/amdgpu: don't attach the tlb fence for SI
drm/amd/display: Use GFP_ATOMIC in dc_create_plane_state()
drm/amdkfd: Trap handler support for expert scheduling mode
drm/amdkfd: Use huge page size to check split svm range alignment
drm/rcar-du: dsi: Handle both DRM_MODE_FLAG_N.SYNC and !DRM_MODE_FLAG_P.SYNC
drm/gem-shmem: revert the 8-byte alignment constraint
drm/gem-dma: revert the 8-byte alignment constraint
drm/panthor: Prevent potential UAF in group creation
drm-misc-fixes for v6.19-rc1:
- Fix stack usage warning in novatek-nt35560.
- Fix s/r, i2c issues in nouveau and update string handling.
- Ignore spurious PLL_UNLOCK bit in ti-sn65dsi83.
- Handle IS_ERR vs NULL in drm_plane_create_hotspot_properties().
- Fix devcoredump crash on reading evicted bo's.
- Fix bigendian handling in mgag200.
- Fix probe failure in tilcdc.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/6c371dc1-08bf-4a34-895c-9ef348b6061b@linux.intel.com
Fedora/CentOS/RHEL CI is reporting intermittent failures while running
the KUnit tests present in drm_hdmi_state_helper_test.c [1].
While the specific test causing the failure change between runs, all of
them are caused by drm_kunit_helper_enable_crtc_connector() returning
-EDEADLK. The error trace always follow this structure:
# <test name>: ASSERTION FAILED at
# drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c:<line>
Expected ret == 0, but
ret == -35 (0xffffffffffffffdd)
As documented, if the drm_kunit_helper_enable_crtc_connector() function
returns -EDEADLK (-35), the entire atomic sequence must be restarted.
Handle this error code for all function calls.
Closes: https://datawarehouse.cki-project.org/issue/4039 [1]
Fixes: 6a5c0ad7e0 ("drm/tests: hdmi_state_helpers: Switch to new helper")
Reviewed-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Link: https://patch.msgid.link/20251104102258.10026-1-jose.exposito89@gmail.com
Unbinding amdgpu has no problems, but binding it again leads to an
error of sysfs file already existing. This is because it wasn't
actually cleaned up on unbind. Add the missing cleanup step.
Fixes: 547aad32ed ("drm/amdgpu: add VCN4 ip block support")
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d717e62e9b)
Cc: stable@vger.kernel.org
GCC notices that the 16-byte uabi_name field could theoretically be too
small for the formatted string if the instance number exceeds 100.
So grow the field to 20 bytes.
drivers/gpu/drm/i915/intel_memory_region.c: In function ‘intel_memory_region_create’:
drivers/gpu/drm/i915/intel_memory_region.c:273:61: error: ‘%u’ directive output may be truncated writing between 1 and 5 bytes into a region of size between 3 and 11 [-Werror=format-truncation=]
273 | snprintf(mem->uabi_name, sizeof(mem->uabi_name), "%s%u",
| ^~
drivers/gpu/drm/i915/intel_memory_region.c:273:58: note: directive argument in the range [0, 65535]
273 | snprintf(mem->uabi_name, sizeof(mem->uabi_name), "%s%u",
| ^~~~~~
drivers/gpu/drm/i915/intel_memory_region.c:273:9: note: ‘snprintf’ output between 7 and 19 bytes into a destination of size 16
273 | snprintf(mem->uabi_name, sizeof(mem->uabi_name), "%s%u",
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
274 | intel_memory_type_str(type), instance);
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Fixes: 3b38d35157 ("drm/i915: Add stable memory region names")
Cc: <stable@vger.kernel.org> # v6.8+
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20251205113500.684286-2-ardb@kernel.org
(cherry picked from commit 18476087f1)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
The drm_kms_helper_poll_fini() and drm_atomic_helper_shutdown() helpers
should only be called when the device has been successfully registered.
Currently, these functions are called unconditionally in tilcdc_fini(),
which causes warnings during probe deferral scenarios.
[ 7.972317] WARNING: CPU: 0 PID: 23 at drivers/gpu/drm/drm_atomic_state_helper.c:175 drm_atomic_helper_crtc_duplicate_state+0x60/0x68
...
[ 8.005820] drm_atomic_helper_crtc_duplicate_state from drm_atomic_get_crtc_state+0x68/0x108
[ 8.005858] drm_atomic_get_crtc_state from drm_atomic_helper_disable_all+0x90/0x1c8
[ 8.005885] drm_atomic_helper_disable_all from drm_atomic_helper_shutdown+0x90/0x144
[ 8.005911] drm_atomic_helper_shutdown from tilcdc_fini+0x68/0xf8 [tilcdc]
[ 8.005957] tilcdc_fini [tilcdc] from tilcdc_pdev_probe+0xb0/0x6d4 [tilcdc]
Fix this by rewriting the failed probe cleanup path using the standard
goto error handling pattern, which ensures that cleanup functions are
only called on successfully initialized resources. Additionally, remove
the now-unnecessary is_registered flag.
Cc: stable@vger.kernel.org
Fixes: 3c4babae3c ("drm: Call drm_atomic_helper_shutdown() at shutdown/remove time for misc drivers")
Signed-off-by: Kory Maincent (TI.com) <kory.maincent@bootlin.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patch.msgid.link/20251125090546.137193-1-kory.maincent@bootlin.com
