- 28 Mar, 2024 4 commits
-
-
Thomas Hellström authored
Rebinding might allocate page-table bos, causing evictions. To support blocking locking during these evictions, perform the rebinding in the drm_exec locking loop. Also Reserve fence slots where actually needed rather than trying to predict how many fence slots will be needed over a complete wound-wait transaction. v2: - Remove a leftover call to xe_vm_rebind() (Matt Brost) - Add a helper function xe_vm_validate_rebind() (Matt Brost) v3: - Add comments and squash with previous patch (Matt Brost) Fixes: 24f947d5 ("drm/xe: Use DRM GPUVM helpers for external- and evicted objects") Fixes: 29f424eb ("drm/xe/exec: move fence reservation") Cc: Matthew Auld <matthew.auld@intel.com> Signed-off-by:
Thomas Hellström <thomas.hellstrom@linux.intel.com> Reviewed-by:
Matthew Brost <matthew.brost@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240327091136.3271-5-thomas.hellstrom@linux.intel.com
-
Thomas Hellström authored
They can actually complete out-of-order, so allocate a unique fence context for each fence. Fixes: 5387e865 ("drm/xe: Add TLB invalidation fence after rebinds issued from execs") Cc: Matthew Brost <matthew.brost@intel.com> Cc: <stable@vger.kernel.org> # v6.8+ Signed-off-by:
-
Thomas Hellström authored
Instead of handling the vm's rebind fence separately, which is error prone if they are not strictly ordered, attach rebind fences as kernel fences to the vm's resv. Fixes: dd08ebf6 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Matthew Brost <matthew.brost@intel.com> Cc: <stable@vger.kernel.org> # v6.8+ Signed-off-by:
-
Thomas Hellström authored
For each rebind we insert a GuC TLB invalidation and add a corresponding unordered TLB invalidation fence. This might add a huge number of TLB invalidation fences to wait for so rather than doing that, defer the TLB invalidation to the next ring ops for each affected exec queue. Since the TLB is invalidated on exec_queue switch, we need to invalidate once for each affected exec_queue. v2: - Simplify if-statements around the tlb_flush_seqno. (Matthew Brost) - Add some comments and asserts. Fixes: 5387e865 ("drm/xe: Add TLB invalidation fence after rebinds issued from execs") Cc: Matthew Brost <matthew.brost@intel.com> Cc: <stable@vger.kernel.org> # v6.8+ Signed-off-by:
-
- 27 Mar, 2024 6 commits
-
-
Michal Wajdeczko authored
We are ready to replace private guc_ids management code with separate GuC ID Manager that can be shared with upcoming SR-IOV PF provisioning code. Cc: Matthew Brost <matthew.brost@intel.com> Signed-off-by:
Michal Wajdeczko <michal.wajdeczko@intel.com> Reviewed-by:
-
Michal Wajdeczko authored
Before we switch-over submission code to use new GuC context ID Manager, lets add some kunit tests to make sure that ID manager works as expected. Signed-off-by:
-
Michal Wajdeczko authored
While we are already managing GuC IDs directly in GuC submission code, using bitmap() for MLRC and ida() for SLRC, this code can't be easily extended to meet additional requirements for SR-IOV use cases, like limited number of IDs available on VFs, or ID range reservation for provisioning VFs by the PF. Add a separate component for managing GuC IDs, that will replace existing ID management. Start with bitmap() based implementation that could be optimized later based on perf data. Cc: Matthew Brost <matthew.brost@intel.com> Signed-off-by:
-
Michal Wajdeczko authored
This macro represents GuC firmware capability and shall be defined in the firmware ABI header. Move it to xe_guc_fwif.h file. Cc: Matthew Brost <matthew.brost@intel.com> Reviewed-by:
-
Michal Wajdeczko authored
Use include guard macro name that follows naming used by the other GuC ABI files. Signed-off-by:
Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240213214908.1481-1-michal.wajdeczko@intel.com
-
Michal Wajdeczko authored
It's better to keep all hardware GGTT definitions separated from the driver code. It also helps to avoid duplicated definitions. Signed-off-by:
Matt Roper <matthew.d.roper@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240326131042.319-1-michal.wajdeczko@intel.com
-
- 26 Mar, 2024 4 commits
-
-
Nirmoy Das authored
Refactor xe_sync_entry_signal so it doesn't have to modify xe_sched_job struct instead create a new helper function to set user fence values for a job. v2: Move the sync type check to xe_sched_job_init_user_fence(Lucas) Cc: Lucas De Marchi <lucas.demarchi@intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Cc: Matthew Brost <matthew.brost@intel.com> Cc: Michal Wajdeczko <michal.wajdeczko@intel.com> Signed-off-by:
Nirmoy Das <nirmoy.das@intel.com> Reviewed-by:
Lucas De Marchi <lucas.demarchi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240321161142.4954-1-nirmoy.das@intel.comSigned-off-by:
-
Vinay Belgaumkar authored
SLPC shutdown is called in reset and suspend paths. In the reset path, it is possible that the H2G call gets lost as GuC is in the process of being reset. There is no value in stopping SLPC when it will happen anyways. In the suspend path, we disable communication with GuC, so there is no need to explicitly shutdown SLPC. v2: Rebase Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by:
Vinay Belgaumkar <vinay.belgaumkar@intel.com> Signed-off-by:
Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240325235602.1155486-1-vinay.belgaumkar@intel.com
-
Ravi Kumar Vodapalli authored
New PCI IDs are added in Bspec for DG2 platform, add them in driver Bspec: 44477 Signed-off-by:
Ravi Kumar Vodapalli <ravi.kumar.vodapalli@intel.com> Reviewed-by:
-
Niranjana Vishwanathapura authored
Use FIELD_PREP for setting lrc descriptor fields instead of shifting values to fields. v2: Use ULL macro variants v3: Do not use FIELD_PREP for 1-bit values Signed-off-by:
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> Reviewed-by:
-
- 22 Mar, 2024 9 commits
-
-
Lucas De Marchi authored
xe_device.h implements these helpers, just use them. Reviewed-by:
Ashutosh Dixit <ashutosh.dixit@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240321213818.72311-1-lucas.demarchi@intel.comSigned-off-by:
-
Lucas De Marchi authored
mips declares an END macro in its headers so it can't be used without namespace in a driver like xe. Instead of coming up with a longer name, just remove the macro and replace its use with 0 since it's still clear what that means: set_offsets() was already using that implicitly when checking the data variable. Reported-by:
Guenter Roeck <linux@roeck-us.net> Closes: http://kisskb.ellerman.id.au/kisskb/buildresult/15143996/Tested-by:
Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240322145037.196548-1-lucas.demarchi@intel.comSigned-off-by:
-
Daniele Ceraolo Spurio authored
The initialization via drmm_mutex_init can fail, so we need to check the return code and escalate the failure. The mutex initialization has been moved after all the other init steps that can't fail, so we're always guaranteed to have those done and don't have to check in the cleanup code. Signed-off-by:
-
Vinay Belgaumkar authored
Return failures from pc_adjust_freq_bounds. Signed-off-by:
-
José Roberto de Souza authored
This is a left over of commit f1a9abc0 ("drm/xe/uapi: Remove support for persistent exec_queues"). Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by:
Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Signed-off-by:
José Roberto de Souza <jose.souza@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240307135229.41973-3-jose.souza@intel.com
-
José Roberto de Souza authored
My testing machine has only 8GB of RAM and while running piglit tests I can reach the OOM cache in xe_vm_snapshot_capture() snap allocaiton sometimes. So to differentiate the OOM from race between capture and UMDs unbinbind VMs here I'm adding a '[0].error: -12' to devcoredump. v2: - fix returned errno values Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by:
-
José Roberto de Souza authored
This makes VM error consistent with [x].length and [x].data. Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by:
-
Jani Nikula authored
modeset_restore_state has been unused since commit 6af0ffc0 ("drm/i915/display: move restore state and ctx under display sub-struct"). member global_obj_list has been unused since commit e2925e19 ("drm/i915/display: move global_obj_list under display sub-struct"). hti_state has been unused since commit 62749912 ("drm/i915/display: move hti under display sub-struct"). snps_phy_failed_calibration has been unused since commit 3a7e2d58 ("drm/i915: move snps_phy_failed_calibration to display sub-struct under snps"). Reviewed-by:
-
Matthew Auld authored
The user provided gt_id should always be less than the XE_MAX_GT_PER_TILE. Fixes: 7793d00d ("drm/xe: Correlate engine and cpu timestamps with better accuracy") Signed-off-by:
Matthew Auld <matthew.auld@intel.com> Cc: Nirmoy Das <nirmoy.das@intel.com> Cc: <stable@vger.kernel.org> # v6.8+ Reviewed-by:
Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240321110629.334701-2-matthew.auld@intel.com
-
- 21 Mar, 2024 4 commits
-
-
Matthew Brost authored
Extra debug is useful when working on VM issues. Signed-off-by:
-
Himal Prasad Ghimiray authored
Use USEC_PER_MSEC rather than the hard coded value of 1000. Static analyzer Reported "casting either timeout_ms or 1000U to type u64" to avoid overflow-before-widen. Using USEC_PER_MSEC seems better and will help with static analyzer report cleanup. Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by:
-
Matthew Auld authored
The q->width should always be exactly one here for migration queue/vm. The width will anyway be overridden later since we need to emit two jumps for special migration jobs. Enforce that here to ensure caller is not doing something strange. While here also convert to the helper to determine if the queue is migration based. Signed-off-by:
-
Matthew Auld authored
The queue width will determine the number of batch buffer emitted into the ring. In the case of xe_bb_create_job() we pass exactly one batch address, therefore add an assert for the width to make sure we don't go out of bounds. While here also convert to the helper to determine if the queue is migration based. Signed-off-by:
-
- 20 Mar, 2024 12 commits
-
-
Daniele Ceraolo Spurio authored
The GGTT is currently a 32 bit address space, but the HW and GuC support 48b addresses in GGTT-related operations, both to keep the interface/HW paths common between PPGTT and GGTT and to allow for future increase of the GGTT size. This leaves us having to program a 64b field with a 32b offset, which currently we're in some cases doing this by using an upper_32_bits() call on a 32b variable, which doesn't make any sense. To do this cleanly we have 2 options: 1 - Set the upper 32 bits directly to zero. 2 - Use 64b variables for the offset and keep programming the whole thing, so we're ready if we ever have bigger offsets. This patch goes with option #2 and switches the related variables to u64. v2: don't change the log ctl flag variable (John) Signed-off-by:John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240319195101.2784480-1-daniele.ceraolospurio@intel.com
-
Daniele Ceraolo Spurio authored
A force_wake_get failure means that the HW might not be awake for the access we're doing; this can lead to an immediate error or it can be a more subtle problem (e.g. a register read might return an incorrect value that is still valid, leading the driver to make a wrong choice instead of flagging an error). We avoid an error from the force_wake function because callers might handle or tolerate the error, but this only works if all callers are checking the error code. The majority already do, but a few are not. These are mainly falling into 3 categories, which are each handled differently: 1) error capture: in this case we want to continue the capture, but we log an info message in dmesg to notify the user that the capture might have incorrect data. 2) ioctl: in this case we return a -EIO error to userspace 3) unabortable actions: these are scenarios where we can't simply abort and retry and so it's better to just try it anyway because there is a chance the HW is awake even with the failure. In this case we throw a warning so we know there was a forcewake problem if something fails down the line. v2: use gt_WARN_ON where appropriate Signed-off-by:
Tejas Upadhyay <tejas.upadhyay@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240318154924.3453513-1-daniele.ceraolospurio@intel.com
-
Radhakrishna Sripada authored
Disable clockgating for TDL SVHS fub. v2: Extend the Wa to 1274(MattR) Bspec: 46045 Reviewed-by:
Radhakrishna Sripada <radhakrishna.sripada@intel.com> Reviewed-by:
-
Tejas Upadhyay authored
Remove continue statement which does not have real effect as no actions are to be taken post continue. Signed-off-by:
-
Luca Coelho authored
Some of the backported intel_uncore_read*() functions used the wrong types. Change the function declarations accordingly. Reviewed-by:
Gustavo Sousa <gustavo.sousa@intel.com> Signed-off-by:
Luca Coelho <luciano.coelho@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240314065221.1181158-1-luciano.coelho@intel.comSigned-off-by:
-
Maarten Lankhorst authored
Considering the caller of the GGTT functions should keep the backing storage alive before the function completes, it's not necessary to invalidate with the GGTT lock held. This just adds latency for every user of the GGTT. Signed-off-by:
-
Matthew Brost authored
Add XE_BO_GGTT_INVALIDATE flag which indicates the GGTT should be invalidated when a BO is added / removed from the GGTT. This is typically set when a BO is used by the GuC as the GuC has GGTT TLBs. Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Signed-off-by:
-
Matthew Brost authored
Only buffers mapped in the GGTT used by the GuC require an invalidation. Display buffers do not require an invalidation. Delete the invalidatio from display code and make invalidation a static function in xe_ggtt.c. Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Signed-off-by:
-
Nirmoy Das authored
Add an explicit check to ensure that the mgr is not NULL. Cc: Matthew Auld <matthew.auld@intel.com> Signed-off-by:
-
Niranjana Vishwanathapura authored
Use xe_exec_queue_user_extension_fn type for exec_queue_user_extension_funcs.` Signed-off-by:
-
Niranjana Vishwanathapura authored
Ensure exec queue freeing happens at one place, that is in __xe_exec_queue_free(). It releases q->vm reference also. Set q->vm before handling extensions as they can potentially reference it. Signed-off-by:
-
Niranjana Vishwanathapura authored
Abstract out the core part of sched_done and deregister_done handlers to separate functions to decouple them from any protocol error handling part and make them more readable. Signed-off-by:
-
- 19 Mar, 2024 1 commit
-
-
Daniele Ceraolo Spurio authored
Supporting older GuC versions comes with baggage, both on the coding side (due to interfaces only being available from a certain version onwards) and on the testing side (due to having to make sure the driver works as expected with older GuCs). Since all of our Xe platform are still under force probe, we haven't committed to support any specific GuC version and we therefore don't need to support the older once, which means that we can force a bottom limit to what GuC we accept. This allows us to remove any conditional statements based on older GuC versions and also to approach newer additions knowing that we'll never attempt to load something older than our minimum requirement. As an initial value, the minimum expected version is set to 70.19, which is the version currently in the firmware table, but the expectation is that this will be bumbed every time we update the table, until we remove the force probe. Signed-off-by:
-
