kernel/linux.git/drivers/accel/ivpu, branch v6.19.11

accel/ivpu: Add disable clock relinquish workaround for NVL-A0

2026-04-02T11:25:39+00:00

commit e8ab57b56402697a9bef50b71aecc613f0d61846 upstream. Turn on disable clock relinquish workaround for Nova Lake A0. Without this workaround NPU may not power off correctly after inference, leading to unexpected system behavior. Fixes: 550f4dd2cedd ("accel/ivpu: Add support for Nova Lake's NPU") Cc: # v6.19+ Reviewed-by: Lizhi.hou Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260323095029.64613-1-karol.wachowski@linux.intel.com Signed-off-by: Greg Kroah-Hartman

accel/ivpu: Fix warning due to undefined CONFIG_PROC_FS

2025-11-12T08:34:18+00:00

Change #if to #ifdef CONFIG_PROC_FS to fix warning reported by test robot: drivers/accel/ivpu/ivpu_drv.c:458:5: warning: "CONFIG_PROC_FS" is not defined, evaluates to 0 [-Wundef] Fixes: 63cc028484ab ("accel/ivpu: Add fdinfo support for memory statistics") Reviewed-by: Maciej Falkowski Reviewed-by: Andrzej.Kacprowski@linux.intel.com Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251112071911.1136934-1-karol.wachowski@linux.intel.com

accel/ivpu: Count only resident buffers in memory utilization

2025-11-12T06:58:44+00:00

Do not count buffer objects that have no backing pages, including imported buffers where pages are set by VM faults triggered by userspace or pinned by other drivers. Instead, return information about actual memory used by the NPU. Counting imported buffers results in incorrect calculations when the same pages are counted multiple times, giving overly high results. Fixes: 7bfc9fa99580 ("accel/ivpu: Expose NPU memory utilization info in sysfs") Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251106101052.1050348-3-karol.wachowski@linux.intel.com

accel/ivpu: Add fdinfo support for memory statistics

2025-11-12T06:58:44+00:00

Implement DRM fdinfo interface to expose memory usage statistics for NPU device file descriptors. Exclude unpinned and imported buffers from resident memory calculations to provide accurate memory usage reporting. Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251106101052.1050348-2-karol.wachowski@linux.intel.com

accel/ivpu: Improve debug and warning messages

2025-11-05T07:35:33+00:00

Add IOCTL debug bit for logging user provided parameter validation errors. Refactor several warning and error messages to better reflect fault reason. User generated faults should not flood kernel messages with warnings or errors, so change those to ivpu_dbg(). Add additional debug logs for parameter validation in IOCTLs. Check size provided by in metric streamer start and return -EINVAL together with a debug message print. Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251104132418.970784-1-karol.wachowski@linux.intel.com

accel/ivpu: Wait for CDYN de-assertion during power down sequence

2025-10-30T15:58:20+00:00

During power down, pending DVFS operations may still be in progress when the NPU reset is asserted after CDYN=0 is set. Since the READY bit may already be deasserted at this point, checking only the READY bit is insufficient to ensure all transactions have completed. Add an explicit check for CDYN de-assertion after the READY bit check to guarantee no outstanding transactions remain before proceeding. Fixes: 550f4dd2cedd ("accel/ivpu: Add support for Nova Lake's NPU") Reviewed-by: Maciej Falkowski Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251030091700.293341-1-karol.wachowski@linux.intel.com

accel/ivpu: Disallow setting sched mode OS starting from NPU6

2025-10-30T07:58:21+00:00

OS scheduling mode gets deprecated starting from NPU6 onward. Print warning and fallback to HW scheduling mode if OS mode is explicitly selected with sched_mode parameter. Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251029201554.257708-1-karol.wachowski@linux.intel.com

accel/ivpu: Add support for userptr buffer objects

2025-10-30T07:52:51+00:00

Introduce a new ioctl `drm_ivpu_bo_create_from_userptr` that allows users to create GEM buffer objects from user pointers to memory regions. The user pointer must be page-aligned and the memory region must remain valid for the buffer object's lifetime. Userptr buffers enable direct use of mmapped files (e.g. inference weights) in NPU workloads without copying data to NPU buffer objects. This reduces memory usage and provides better flexibility for NPU applications. Signed-off-by: Jacek Lawrynowicz Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251029091752.203198-1-karol.wachowski@linux.intel.com

accel/ivpu: Fix race condition when unbinding BOs

2025-10-30T07:48:00+00:00

Fix 'Memory manager not clean during takedown' warning that occurs when ivpu_gem_bo_free() removes the BO from the BOs list before it gets unmapped. Then file_priv_unbind() triggers a warning in drm_mm_takedown() during context teardown. Protect the unmapping sequence with bo_list_lock to ensure the BO is always fully unmapped when removed from the list. This ensures the BO is either fully unmapped at context teardown time or present on the list and unmapped by file_priv_unbind(). Fixes: 48aea7f2a2ef ("accel/ivpu: Fix locking in ivpu_bo_remove_all_bos_from_context()") Signed-off-by: Tomasz Rusinowicz Reviewed-by: Jeff Hugo Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251029071451.184243-1-karol.wachowski@linux.intel.com

accel/ivpu: replace use of system_wq with system_percpu_wq

2025-10-30T07:40:40+00:00

Currently if a user enqueue a work item using schedule_delayed_work() the used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to schedule_work() that is using system_wq and queue_work(), that makes use again of WORK_CPU_UNBOUND. This lack of consistency cannot be addressed without refactoring the API. system_wq should be the per-cpu workqueue, yet in this name nothing makes that clear, so replace system_wq with system_percpu_wq. The old wq (system_wq) will be kept for a few release cycles. Suggested-by: Tejun Heo Signed-off-by: Marco Crivellari Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20251029165642.364488-3-marco.crivellari@suse.com