- 21 Dec, 2023 40 commits
-
-
Matt Roper authored
Xe2 uses the same steering control register and steering semaphore register as MTL. As with recent platforms, group/instance 0,0 is sufficient to target a non-terminated instance for most classes of MCR registers; the only types of ranges that need to consider platform fusing to find a non-terminated instance are SLICE/DSS ranges and a new SQIDI_PSMI type of range. Note that the range of valid bits in XE2_NODE_ENABLE_MASK may be reduced for some Xe2 SKUs. However the lowest bits are always valid and only the lowest instance is obtained via __ffs(), so there's no need to complicate the masking with extra platform/subplatform checks. Also note that Wa_14017387313 suggests skipping MCR lock acquisition around GAM and GAMWKR registers to prevent MCR register accesses in an interrupt handler from deadlocking when the steering semaphore is already held outside the interrupt context. At this time Xe never issues MCR accesses from within an interrupt handler so the workaround is not currently needed. v2: - [0x008700-0x0087FF] range to extend up to 0x887F (Matt Attwood) - [0x00EF00-0x00F4FF] -> [0x00F000, 0xFFFF] to follow latest bspec version (Bala) Bspec: 71185 Signed-off-by:Matt Roper <matthew.d.roper@intel.com> Signed-off-by:
Lucas De Marchi <lucas.demarchi@intel.com> Reviewed-by:
Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com> Reviewed-by:
Matt Atwood <matthew.s.atwood@intel.com> Signed-off-by:
Rodrigo Vivi <rodrigo.vivi@intel.com>
-
Matt Roper authored
Xe2 platforms have three DSS fuse registers for both geometry and compute. Bspec: 67171, 67537, 67401, 67536 Signed-off-by:
-
Matt Roper authored
The render and compute context are significantly smaller on Xe2 than on previous platforms. Registers: - Render: 3008 dwords -> 12032 bytes -> round to 3 pages - Compute: 1424 dwords -> 5696 bytes -> round to 2 pages We also allocate one additional page for the HWSP, so the total allocation sizes for render and compute are 4 and 3 pages respectively. Bspec: 65182, 56578, 55793 Signed-off-by:
-
Matt Roper authored
The choice of Y-major tiling format (either the legacy "TileY" or the newer "Tile4") is based on graphics IP version (12.50 and beyond have Tile4, earlier platforms have TileY). The tracking in xe was originally added to allow re-using display from i915. However as of i915 commit 4ebf43d0 ("drm/i915: Eliminate has_4tile feature flag"), the display code determines TileY vs Tile4 itself, so this can be removed from xe. Reviewed-by:
-
Daniele Ceraolo Spurio authored
On MTL (and only on MTL) the GSCCS defaults with idle messaging disabled. This means that, once awoken, the GSCCS will never signal its idleness to the GT. To allow the GT to enter the proper low-power state, we need therefore to turn idle messaging on. As part of this, we also need to set a proper hysteresis value for the engine. v2: use MEDIA_VERSION() and CLR() for the RTP rule and action, add reg bit define in descending order (Matt) Bspec: 71496 Signed-off-by:
Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com> Cc: Matt Roper <matthew.d.roper@intel.com> Reviewed-by:
-
Daniele Ceraolo Spurio authored
The kernel is the only expected user of the GSCCS, so we don't want to expose it to userspace. Signed-off-by:
-
Daniele Ceraolo Spurio authored
The ID for the GSC forcewake domain already exists, but we're missing the register definitions and the domain intialization, so add that in. v2: move reg definition to be in address order (Matt) Signed-off-by:
-
Daniele Ceraolo Spurio authored
Like the BCS, the GSCCS doesn't have any special HW that needs handling when emitting commands, so we can re-use the same emit_job code. To make it clear that this is now a shared low-level function, it has been renamed to use the "simple" postfix, instead of "copy", to indicate that it applies to all engines that don't need any additional engine-specific handling. Signed-off-by:
-
Daniele Ceraolo Spurio authored
The GSCCS has its own enable and mask registers. The interrupt identity for the GSCCS shows OTHER_CLASS instance 6. Bspec: 54029, 54030 Signed-off-by:
-
Daniele Ceraolo Spurio authored
The first step in introducing the GSCCS is to add all the basic defs for it (name, mmio base, class/instance, lrc size etc). Bspec: 60149, 60421, 63752 Signed-off-by:
-
Daniele Ceraolo Spurio authored
The queue name assignment is identical in both GuC and execlists backends, so we can move it to a common function. This will make adding a new entry in the next patch slightly cleaner. Signed-off-by:
-
Niranjana Vishwanathapura authored
Allow preemption timeout to be specified as a config option. v2: Change unit to microseconds (Tejas) v3: Remove get_default_preempt_timeout() Reviewed-by:
Tejas Upadhyay <tejas.upadhyay@intel.com> Signed-off-by:
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> Signed-off-by:
-
Niranjana Vishwanathapura authored
Shortens the too long code lines. Reviewed-by:
-
Shekhar Chauhan authored
Since this is specific to DirectX, we don't need it on Linux. Signed-off-by:
Shekhar Chauhan <shekhar.chauhan@intel.com> Reviewed-by:
-
Oak Zeng authored
Print both device physical address range and CPU io range of vram. Also print vram's actual size, usable size excluding stolen memory, and CPU io accessible size. V1: - Add back small BAR device info (Matt) Signed-off-by:
Oak Zeng <oak.zeng@intel.com> Reviewed-by:
Michael J. Ruhl <michael.j.ruhl@intel.com> Reviewed-by:
Matthew Brost <matthew.brost@intel.com> Signed-off-by:
-
Oak Zeng authored
Make a xe_mem_region structure which will be used in the coming patches. The new structure is used in both xe device level (xe->mem.vram) and xe_tile level (tile->vram). Make the definition of xe_mem_region.dpa_base to be the DPA base of this memory region and change codes according to this new definition. v1: - rename xe_mem_region.base to dpa_base per conversation with Mike Ruhl Signed-off-by: -
Matthew Brost authored
Usually we call __guc_exec_queue_fini_async via a worker as the exec_queue fini can be done from within the GPU scheduler which creates a circular dependency without a worker. Kernel exec_queues are fini'd at driver unload (not from within the GPU scheduler) so it is safe to directly call __guc_exec_queue_fini_async. Suggested-by:
Oded Gabbay <ogabbay@kernel.org> Signed-off-by:
-
Matthew Auld authored
If we are closing a vm, mark each vma as XE_VMA_DESTROYED and skip touching the rebind_list if this is seen on the eviction path. That way we can safely drop the vm dma-resv lock on the close path without needing to worry about racing with the eviction path trying to add stuff to the rebind_list which can corrupt our contended list, since the destroy and rebind links are the same list entry underneath. References: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/514Signed-off-by:
Matthew Auld <matthew.auld@intel.com> Cc: Matthew Brost <matthew.brost@intel.com> Reviewed-by:
-
Matthew Auld authored
Rather check if the engine is still registered before proceeding with deregister steps. Also the engine being marked as disabled doesn't mean the engine has been disabled or deregistered from GuC pov, and here we are signalling fences so we need to be sure GuC is not still using this context. v2: - Drop the read_stopped() for this path. Since we are signalling fences on error here, best play it safe and wait for the GT reset to mark the engine as disabled, rather than it just being queued. v3 (Matt Brost): - Keep the read_stopped() on the wait event, since there is no need to wait for an already scheduled GT reset. If it is set we can then just bail without signalling anything. Signed-off-by:
-
Anshuman Gupta authored
Do not register vram_d3cold_threshold device sysfs universally for each gfx device, only register sysfs and set the threshold value for d3cold capable devices. Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by:
Anshuman Gupta <anshuman.gupta@intel.com> Reviewed-by:
-
Matt Roper authored
The workaround database tells us to set this bit, even though the bspec indicates the bit doesn't exist on these platforms. Since this is a write-only register, we also can't read back its value to verify whether it's actually working or not. For now we'll trust that the workaround database knows what it's talking about; if not, the hardware will just ignore the attempt to write to a non-existent bit and it shouldn't cause any problems. Reviewed-by:
-
Matthew Auld authored
This appears to be easily user triggerable so warning is perhaps too much. Rather just make it debug print. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/534Signed-off-by:
-
Oak Zeng authored
To workaround a HW bug on DG2, driver is required to map the whole ppgtt virtual address space before GPU workload submission. Thus set the XE_VM_FLAG_SCRATCH_PAGE flag during vm create so the whole address space is mapped to point to scratch page. v1: - Move the workaround implementation from xe_vm_create to xe_vm_create_ioctl - Brian - Reorder error checking in xe_vm_create_ioctl - Jose - Implement WA only for DG2-G10 and DG2-G12 Signed-off-by:Brian Welty <brian.welty@intel.com> Reviewed-by:
José Roberto de Souza <jose.souza@intel.com> Signed-off-by:
-
Lucas De Marchi authored
BSpec changed with regard the DevIDs for ARL-S. Update the define accordingly. Bspec: 55420 Reviewed-by:
-
Matthew Brost authored
When a rebind is skipped, we must set the max pte size of the newly created vma to value of the old vma as we do not pte walk for the new vma. Without this future rebinds may be incorrectly skipped due to the wrong max pte size. Null binds are more likely to expose this bug as larger ptes are more frequently used compared to normal bindings. Reviewed-by:
Paulo Zanoni <paulo.r.zanoni@intel.com> Fixes: 8f33b4f0 ("drm/xe: Avoid doing rebinds") Reference: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23045Signed-off-by:
-
Matthew Auld authored
It seems that various things can trigger the lr cleanup worker, including CAT error, engine reset and destroying the actual engine, so seems plausible to end up triggering the worker more than once in some cases. If that does happen we can race with an ongoing engine deregister before it has completed, thus triggering it again and also changing the state back into pending_disable. Checking if the engine has been marked as destroyed looks like it should prevent this. Signed-off-by:
-
Lucas De Marchi authored
If the forcewake failed, put xe_device_mem_access. Reviewed-by:
-
Lucas De Marchi authored
Make sure to always call xe_device_mem_access_put(), even on error. Reviewed-by:
-
Tejas Upadhyay authored
Add sysfs entries for the min, max, and defaults for each of engine scheduler controls for every hardware engine class. Non-elevated user IOCTLs to set these controls must be within the min-max ranges of the sysfs entries, elevated user can set these controls to any value. However, introduced compile time CONFIG min-max values which restricts elevated user to be in compile time min-max range if at all sysfs min/max are violated. Sysfs entries examples are, DUT# cat /sys/class/drm/cardX/device/tileN/gtN/engines/ccs/.defaults/ job_timeout_max job_timeout_ms preempt_timeout_min timeslice_duration_max timeslice_duration_us job_timeout_min preempt_timeout_max preempt_timeout_us timeslice_duration_min DUT# cat /sys/class/drm/card1/device/tileN/gtN/engines/ccs/ .defaults/ job_timeout_min preempt_timeout_max preempt_timeout_us timeslice_duration_min job_timeout_max job_timeout_ms preempt_timeout_min timeslice_duration_max timeslice_duration_us V12: - Rebase V11: - Make engine_get_prop_minmax and enforce_sched_limit static - Matt - use enum in place of string in engine_get_prop_minmax - Matt - no need to use enforce_sched_limit or no need to filter min/max per user type in sysfs - Matt V10: - Add kernel doc for non-static func - Make helper to get min/max for range validation - Matt - Filter min/max per user type V9 : - Rebase to use s/xe_engine/xe_hw_engine/ - Matt V8 : - fix enforce_sched_limit and avoid code duplication - Niranjana - Make sure min < max - Niranjana V7 : - Rebase to replace hw engine with eclass interface - return EINVAL in place of EPERM - Use some APIs to avoid code duplication V6 : - Rebase changes to reflect per engine class props interface - MattB - Use #if ENABLED - MattB - Remove MAX_SCHED_TIMEOUT check as range validation is enough V5 : - Rebase to resolve conflicts - CI V4 : - Rebase - Update commit to reflect tile addition - Use XE_HW macro directly as they are already filtered for CONFIG checks - Niranjana - Add CONFIG for enable/disable min/max limitation on elevated user. Default is enable - Matt/Joonas V3 : - Resolve CI hooks warning for kernel-doc V2 : - Restric min/max setting to #define default min/max for elevated user - Himal - Remove unrelated changes from patch - Niranjana Reviewed-by: -
Tejas Upadhyay authored
The preemption request and timeout is used for higher priority context or kill hung context and reset hardware engine. The preempt timeout can be adjusted per-engine class using, /sys/class/drm/cardX/device/tileN/gtN/engines/ccs/preempt_timeout_us and can be disabled by setting it to 0. V7: - Rebase V6: - Rebase to use s/xe_engine/xe_hw_engine/ - Matt V5: - Remove timeout validation, not relevant - Niranjana V4: - Rebase to replace hw engine with eclass interface V3: - Rebase to per class engine props interface V2: - Rebase - Update commit message to add tile Reviewed-by:
-
Tejas Upadhyay authored
Timeslices between multiple context is supported via guc scheduling. Add sysfs entry to provide user defined timeslice duration to guc scheduling. The timeslice duration can be adjusted per-engine class using, /sys/class/drm/cardX/device/tileN/gtN/engines/ccs/timeslice_duration_us V8: - Rebase V7: - Rebase to use s/xe_engine/xe_hw_engine/ - Matt V6: - Remove duration validation, not relevant - Niranjana V5: - Rebase to replace hw engine with eclass interface V4: - Rebase to per class engine props interface V3: - Rebase - Update commit messge to add tile V2: - Rebase Reviewed-by:
-
Tejas Upadhyay authored
The time after which a job is removed from the scheduler. Add sysfs entry to provide user defined job timeout to scheduler. The job timeout can be adjusted per-engine class using, /sys/class/drm/cardX/device/tileN/gtN/engines/ccs/job_timeout_ms V8: - Rebase V7: - Rebase to use s/xe_engine/xe_hw_engine/ - Matt V6: - Remove timeout validation, not relevant - Niranjana - Rebase to use common error path V5: - Rebase to use engine class interface instead of hw engine V4: - Rebase to per class engine props interface V3: - Rebase - Update commit message to reflect tile update V2: - Use sysfs_create_files as part of this patch Reviewed-by:
-
Tejas Upadhyay authored
For each HW engine under GT we are adding defaults sysfs entry to list all engine scheduler properties and its default values. So that it will be easier for user to fetch default values of these properties anytime to go back to default. For example, DUT# cat /sys/class/drm/card1/device/tileN/gtN/engines/bcs/.defaults/ job_timeout_ms preempt_timeout_us timeslice_duration_us where, @job_timeout_ms: The time after which a job is removed from the scheduler. @preempt_timeout_us: How long to wait (in microseconds) for a preemption event to occur when submitting a new context. @timeslice_duration_us: Each context is scheduled for execution for the timeslice duration, before switching to the next context. V12: - Add missing drmm_add_action_or_reset and remove sysfs files V11: - Rebase V10: - Remove xe_gt.h inclusion from .h - Matt V9 : - Remove jiffies for job_timeout_ms - Matt V8 : - replace xe_engine with xe_hw_engine - Matt V7 : - Push all errors to one error path at every places - Niranjana - Describe struct member to resolve kernel doc err - CI hooks V6 : - Use engine class interface instead of hw engine in sysfs for better interfacing readability - Niranjana V5 : - Scheduling props should apply per class engine not per hardware engine - Matt - Do not record value of job_timeout_ms if changed based on dma_fence - Matt V4 : - Resolve merge conflicts - CI V3 : - Rearrange code in its own file - Rebase - Update commit message to reflect tile addition V2 : - Use sysfs_create_files in this patch - Niranjana - Handle prototype error for xe_add_engine_defaults - CI hooks - Remove unused member sysfs_hwe - Niranjana Reviewed-by: -
Tejas Upadhyay authored
Add engines sysfs directory under its GT and create sub directory for all engine class (note its not per instance) present on GT. For example, DUT# cat /sys/class/drm/cardX/device/tileN/gtN/engines/ bcs/ ccs/ V9 : - Add missing drmm_add_action_or_reset V8 : - Rebase V7 : - Remove xe_gt.h from .h and include in .c - Matt V6 : - Add kernel doc and arrange file in make file by alphabet - Matt V5 : - replace xe_engine with xe_hw_engine - Matt V4 : - Rebase to resolve conflicts - CI V3 : - Move code in its own file - Rename API name V2 : - Correct class mask logic - Himal - Remove extra parenthesis Reviewed-by:
-
Francois Dugast authored
Engine was inappropriately used to refer to execution queues and it also created some confusion with hardware engines. Where it applies the exec_queue variable name is changed to q and comments are also updated. Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/162Signed-off-by:
Francois Dugast <francois.dugast@intel.com> Reviewed-by:
-
Francois Dugast authored
This is a preparation commit for a larger renaming of engine to exec queue. Signed-off-by:
-
Maarten Lankhorst authored
ttm_bo_init_reserved() calls the destroy() callback if it fails. Because of this, __xe_bo_create_locked is required to be responsible for freeing the bo even when it's passed in as argument. Additionally, if the placement check fails, the bo was kept alive. Fix it too. Reported-by:
Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by:
-
Matthew Brost authored
The header variable is unused, remove it. Reviewed-by:
-
Francois Dugast authored
Replace calls to XE_BUG_ON() with calls XE_WARN_ON() which in turn calls WARN() instead of BUG(). BUG() crashes the kernel and should only be used when it is absolutely unavoidable in case of catastrophic and unrecoverable failures, which is not the case here. Signed-off-by:
-
Francois Dugast authored
Remove XE_EXTRA_DEBUG for cleanup as it is not used. Signed-off-by:
-
