linux-toradex.git/drivers/accel, branch v7.0-rc7 Linux kernel for Apalis and Colibri modules accel/qaic: Handle DBC deactivation if the owner went away 2026-03-27T16:48:30+00:00 Youssef Samir youssef.abdulrahman@oss.qualcomm.com 2026-02-05T12:34:14+00:00 2feec5ae5df785658924ab6bd91280dc3926507c When a DBC is released, the device sends a QAIC_TRANS_DEACTIVATE_FROM_DEV transaction to the host over the QAIC_CONTROL MHI channel. QAIC handles this by calling decode_deactivate() to release the resources allocated for that DBC. Since that handling is done in the qaic_manage_ioctl() context, if the user goes away before receiving and handling the deactivation, the host will be out-of-sync with the DBCs available for use, and the DBC resources will not be freed unless the device is removed. If another user loads and requests to activate a network, then the device assigns the same DBC to that network, QAIC will "indefinitely" wait for dbc->in_use = false, leading the user process to hang. As a solution to this, handle QAIC_TRANS_DEACTIVATE_FROM_DEV transactions that are received after the user has gone away. Fixes: 129776ac2e38 ("accel/qaic: Add control path") Signed-off-by: Youssef Samir <youssef.abdulrahman@oss.qualcomm.com> Reviewed-by: Lizhi Hou <lizhi.hou@amd.com> Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> Link: https://patch.msgid.link/20260205123415.3870898-1-youssef.abdulrahman@oss.qualcomm.com 
When a DBC is released, the device sends a QAIC_TRANS_DEACTIVATE_FROM_DEV
transaction to the host over the QAIC_CONTROL MHI channel. QAIC handles
this by calling decode_deactivate() to release the resources allocated for
that DBC. Since that handling is done in the qaic_manage_ioctl() context,
if the user goes away before receiving and handling the deactivation, the
host will be out-of-sync with the DBCs available for use, and the DBC
resources will not be freed unless the device is removed. If another user
loads and requests to activate a network, then the device assigns the same
DBC to that network, QAIC will "indefinitely" wait for dbc->in_use = false,
leading the user process to hang.

As a solution to this, handle QAIC_TRANS_DEACTIVATE_FROM_DEV transactions
that are received after the user has gone away.

Fixes: 129776ac2e38 ("accel/qaic: Add control path")
Signed-off-by: Youssef Samir <youssef.abdulrahman@oss.qualcomm.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com>
Link: https://patch.msgid.link/20260205123415.3870898-1-youssef.abdulrahman@oss.qualcomm.com
accel/ivpu: Add disable clock relinquish workaround for NVL-A0 2026-03-24T08:29:28+00:00 Karol Wachowski karol.wachowski@linux.intel.com 2026-03-23T09:50:29+00:00 e8ab57b56402697a9bef50b71aecc613f0d61846 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: <stable@vger.kernel.org> # v6.19+ Reviewed-by: Lizhi.hou <lizhi.hou@amd.com> Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com> Link: https://patch.msgid.link/20260323095029.64613-1-karol.wachowski@linux.intel.com 
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: <stable@vger.kernel.org> # v6.19+

Reviewed-by: Lizhi.hou <lizhi.hou@amd.com>
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Link: https://patch.msgid.link/20260323095029.64613-1-karol.wachowski@linux.intel.com
accel/amdxdna: Fix runtime suspend deadlock when there is pending job 2026-03-10T18:46:40+00:00 Lizhi Hou lizhi.hou@amd.com 2026-03-10T18:00:58+00:00 6b13cb8f48a42ddf6dd98865b673a82e37ff238b The runtime suspend callback drains the running job workqueue before suspending the device. If a job is still executing and calls pm_runtime_resume_and_get(), it can deadlock with the runtime suspend path. Fix this by moving pm_runtime_resume_and_get() from the job execution routine to the job submission routine, ensuring the device is resumed before the job is queued and avoiding the deadlock during runtime suspend. Fixes: 063db451832b ("accel/amdxdna: Enhance runtime power management") Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com> Link: https://patch.msgid.link/20260310180058.336348-1-lizhi.hou@amd.com 
The runtime suspend callback drains the running job workqueue before
suspending the device. If a job is still executing and calls
pm_runtime_resume_and_get(), it can deadlock with the runtime suspend
path.

Fix this by moving pm_runtime_resume_and_get() from the job execution
routine to the job submission routine, ensuring the device is resumed
before the job is queued and avoiding the deadlock during runtime
suspend.

Fixes: 063db451832b ("accel/amdxdna: Enhance runtime power management")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260310180058.336348-1-lizhi.hou@amd.com
accel/ivpu: Remove boot params address setting via MMIO register 2026-03-10T12:34:31+00:00 Andrzej Kacprowski andrzej.kacprowski@linux.intel.com 2026-03-05T14:22:26+00:00 59bdbabccaa470ed94aae7d94a1229c7b0ff4681 The NPU 60XX uses the default boot params location specified in the firmware image header, consistent with earlier generations. Remove the unnecessary MMIO register write, freeing the AON register for future use. Fixes: 44e4c88951fa ("accel/ivpu: Implement warm boot flow for NPU6 and unify boot handling") Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com> Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com> Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com> Link: https://patch.msgid.link/20260305142226.194995-1-andrzej.kacprowski@linux.intel.com (cherry picked from commit 81e62e7bf8b9309bf0febdf00940818f98bc23d8) Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de> 
The NPU 60XX uses the default boot params location specified
in the firmware image header, consistent with earlier generations.
Remove the unnecessary MMIO register write, freeing the AON register
for future use.

Fixes: 44e4c88951fa ("accel/ivpu: Implement warm boot flow for NPU6 and unify boot handling")
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Link: https://patch.msgid.link/20260305142226.194995-1-andrzej.kacprowski@linux.intel.com
(cherry picked from commit 81e62e7bf8b9309bf0febdf00940818f98bc23d8)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
accel: ethosu: Handle possible underflow in IFM size calculations 2026-03-05T21:21:17+00:00 Rob Herring (Arm) robh@kernel.org 2026-02-18T22:21:57+00:00 021f1b77f70d62351bba67b050b8d784641d817f If the command stream has larger padding sizes than the IFM and OFM diminsions, then the calculations will underflow to a negative value. The result is a very large region bounds which is caught on submit, but it's better to catch it earlier. Current mesa ethosu driver has a signedness bug which resulted in padding of 127 (the max) and triggers this issue. Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org> Link: https://patch.msgid.link/20260218-ethos-fixes-v1-3-be3fa3ea9a30@kernel.org Signed-off-by: Rob Herring (Arm) <robh@kernel.org> 
If the command stream has larger padding sizes than the IFM and OFM
diminsions, then the calculations will underflow to a negative value.
The result is a very large region bounds which is caught on submit, but
it's better to catch it earlier.

Current mesa ethosu driver has a signedness bug which resulted in
padding of 127 (the max) and triggers this issue.

Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-3-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
accel: ethosu: Fix NPU_OP_ELEMENTWISE validation with scalar 2026-03-05T21:21:17+00:00 Rob Herring (Arm) robh@kernel.org 2026-02-18T22:21:56+00:00 838ae99f9a77a5724ee6d4e7b7b1eb079147f888 The NPU_OP_ELEMENTWISE instruction uses a scalar value for IFM2 if the IFM2_BROADCAST "scalar" mode is set. It is a bit (7) on the u65 and part of a field (bits 3:0) on the u85. The driver was hardcoded to the u85. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org> Link: https://patch.msgid.link/20260218-ethos-fixes-v1-2-be3fa3ea9a30@kernel.org Signed-off-by: Rob Herring (Arm) <robh@kernel.org> 
The NPU_OP_ELEMENTWISE instruction uses a scalar value for IFM2 if the
IFM2_BROADCAST "scalar" mode is set. It is a bit (7) on the u65 and
part of a field (bits 3:0) on the u85. The driver was hardcoded to the
u85.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-2-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
accel: ethosu: Fix job submit error clean-up refcount underflows 2026-03-05T21:21:17+00:00 Rob Herring (Arm) robh@kernel.org 2026-02-18T22:21:55+00:00 150bceb3e0a4a30950279d91ea0e8cc69a736742 If the job submit fails before adding the job to the scheduler queue such as when the GEM buffer bounds checks fail, then doing a ethosu_job_put() results in a pm_runtime_put_autosuspend() without the corresponding pm_runtime_resume_and_get(). The dma_fence_put()'s are also unnecessary, but seem to be harmless. Split the ethosu_job_cleanup() function into 2 parts for the before and after the job is queued. Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver") Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org> Link: https://patch.msgid.link/20260218-ethos-fixes-v1-1-be3fa3ea9a30@kernel.org Signed-off-by: Rob Herring (Arm) <robh@kernel.org> 
If the job submit fails before adding the job to the scheduler queue
such as when the GEM buffer bounds checks fail, then doing a
ethosu_job_put() results in a pm_runtime_put_autosuspend() without the
corresponding pm_runtime_resume_and_get(). The dma_fence_put()'s are
also unnecessary, but seem to be harmless.

Split the ethosu_job_cleanup() function into 2 parts for the before
and after the job is queued.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Reviewed-and-Tested-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://patch.msgid.link/20260218-ethos-fixes-v1-1-be3fa3ea9a30@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
accel/amdxdna: Split mailbox channel create function 2026-03-05T17:24:33+00:00 Lizhi Hou lizhi.hou@amd.com 2026-03-05T06:20:41+00:00 d5b8b0347fa8470b751a506fb801797e271d7548 The management channel used for firmware control command submission is currently created after the firmware is started. If channel creation fails (for example, due to memory allocation failure or workqueue creation interruption), the firmware remains in a pending state and is unable to receive any control commands. To avoid leaving the firmware in this inconsistent state, split xdna_mailbox_create_channel() into two separate functions so that resource allocation can be completed before interacting with the hardware. xdna_mailbox_alloc_channel() Allocates memory and initializes the workqueue. This can be called earlier, before interacting with the hardware. xdna_mailbox_start_channel() Performs the hardware interaction required to start the channel. Rename xdna_mailbox_destroy_channel() to xdna_mailbox_free_channel(). Ensure that xdna_mailbox_stop_channel() and xdna_mailbox_free_channel() properly unwind the corresponding start and allocation steps, respectively. Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox") Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com> Link: https://patch.msgid.link/20260305062041.3954024-1-lizhi.hou@amd.com 
The management channel used for firmware control command submission is
currently created after the firmware is started. If channel creation
fails (for example, due to memory allocation failure or workqueue
creation interruption), the firmware remains in a pending state and is
unable to receive any control commands.

To avoid leaving the firmware in this inconsistent state, split
xdna_mailbox_create_channel() into two separate functions so that
resource allocation can be completed before interacting with the
hardware.
  xdna_mailbox_alloc_channel()
    Allocates memory and initializes the workqueue. This can be called
    earlier, before interacting with the hardware.
  xdna_mailbox_start_channel()
    Performs the hardware interaction required to start the channel.

Rename xdna_mailbox_destroy_channel() to xdna_mailbox_free_channel().
Ensure that xdna_mailbox_stop_channel() and xdna_mailbox_free_channel()
properly unwind the corresponding start and allocation steps, respectively.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260305062041.3954024-1-lizhi.hou@amd.com
accel/amdxdna: Fix major version check on NPU1 platform 2026-03-04T20:05:02+00:00 Lizhi Hou lizhi.hou@amd.com 2026-03-04T19:50:12+00:00 f82859c84a9862e242c904e72fb0625fef9b24e7 Add the missing major number in npu1_fw_feature_table. Without the major version specified, the firmware feature check fails, preventing new firmware commands from being enabled on the NPU1 platform. With the correct major version populated, the driver properly detects firmware support and enables the new command. Fixes: f1eac46fe5f7 ("accel/amdxdna: Update firmware version check for latest firmware") Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com> Link: https://patch.msgid.link/20260304195012.3616908-1-lizhi.hou@amd.com 
Add the missing major number in npu1_fw_feature_table.

Without the major version specified, the firmware feature check fails,
preventing new firmware commands from being enabled on the NPU1
platform.

With the correct major version populated, the driver properly detects
firmware support and enables the new command.

Fixes: f1eac46fe5f7 ("accel/amdxdna: Update firmware version check for latest firmware")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260304195012.3616908-1-lizhi.hou@amd.com
accel/amdxdna: Fix NULL pointer dereference of mgmt_chann 2026-03-02T17:43:22+00:00 Lizhi Hou lizhi.hou@amd.com 2026-02-26T21:38:57+00:00 6270ee26e1edd862ea17e3eba148ca8fb2c99dc9 mgmt_chann may be set to NULL if the firmware returns an unexpected error in aie2_send_mgmt_msg_wait(). This can later lead to a NULL pointer dereference in aie2_hw_stop(). Fix this by introducing a dedicated helper to destroy mgmt_chann and by adding proper NULL checks before accessing it. Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox") Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com> Link: https://patch.msgid.link/20260226213857.3068474-1-lizhi.hou@amd.com 
mgmt_chann may be set to NULL if the firmware returns an unexpected
error in aie2_send_mgmt_msg_wait(). This can later lead to a NULL
pointer dereference in aie2_hw_stop().

Fix this by introducing a dedicated helper to destroy mgmt_chann
and by adding proper NULL checks before accessing it.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260226213857.3068474-1-lizhi.hou@amd.com