On Tue, May 12, 2026 at 4:54 AM Boris Brezillon
<[email protected]> wrote:
>
> Rather than assuming an interrupt is always expected for request
> acks, temporarily enable the relevant interrupts when the polling-wait
> failed. This should hopefully reduce the number of interrupts the CPU
> has to process.
>
> Signed-off-by: Boris Brezillon <[email protected]>
WIth minor comments below, Reviewed-by: Chia-I Wu <[email protected]>
> ---
> drivers/gpu/drm/panthor/panthor_fw.c | 34
> +++++++++++++++++++--------------
> drivers/gpu/drm/panthor/panthor_sched.c | 5 +++--
> 2 files changed, 23 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_fw.c
> b/drivers/gpu/drm/panthor/panthor_fw.c
> index 8239a6951569..f5e0ceca4130 100644
> --- a/drivers/gpu/drm/panthor/panthor_fw.c
> +++ b/drivers/gpu/drm/panthor/panthor_fw.c
> @@ -1039,16 +1039,10 @@ static void panthor_fw_init_global_iface(struct
> panthor_device *ptdev)
> glb_iface->input->progress_timer = PROGRESS_TIMEOUT_CYCLES >>
> PROGRESS_TIMEOUT_SCALE_SHIFT;
> glb_iface->input->idle_timer = panthor_fw_conv_timeout(ptdev,
> IDLE_HYSTERESIS_US);
>
> - /* Enable interrupts we care about. */
> - glb_iface->input->ack_irq_mask = GLB_CFG_ALLOC_EN |
> - GLB_PING |
> - GLB_CFG_PROGRESS_TIMER |
> - GLB_CFG_POWEROFF_TIMER |
> - GLB_IDLE_EN |
> - GLB_IDLE;
> -
> - if (panthor_fw_has_glb_state(ptdev))
> - glb_iface->input->ack_irq_mask |= GLB_STATE_MASK;
> + /* Enable interrupts for asynchronous events that are not
> + * triggered by request acks.
> + */
> + glb_iface->input->ack_irq_mask = GLB_IDLE;
We should static_assert or & with GLB_EVT_MASK. Same for CSG and CS.
>
> panthor_fw_update_reqs(glb_iface, req, GLB_IDLE_EN | GLB_COUNTER_EN,
> GLB_IDLE_EN | GLB_COUNTER_EN);
> @@ -1318,8 +1312,8 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
> * Return: 0 on success, -ETIMEDOUT otherwise.
> */
> static int panthor_fw_wait_acks(const u32 *req_ptr, const u32 *ack_ptr,
> - wait_queue_head_t *wq,
> - u32 req_mask, u32 *acked,
> + u32 *ack_irq_mask_ptr, spinlock_t *lock,
> + wait_queue_head_t *wq, u32 req_mask, u32
> *acked,
> u32 timeout_ms)
> {
> u32 ack, req = READ_ONCE(*req_ptr) & req_mask;
> @@ -1334,8 +1328,16 @@ static int panthor_fw_wait_acks(const u32 *req_ptr,
> const u32 *ack_ptr,
> if (!ret)
> return 0;
>
> - if (wait_event_timeout(*wq, (READ_ONCE(*ack_ptr) & req_mask) == req,
> - msecs_to_jiffies(timeout_ms)))
> + scoped_guard(spinlock_irqsave, lock)
> + *ack_irq_mask_ptr |= req_mask;
> +
> + ret = wait_event_timeout(*wq, (READ_ONCE(*ack_ptr) & req_mask) == req,
> + msecs_to_jiffies(timeout_ms));
> +
> + scoped_guard(spinlock_irqsave, lock)
> + *ack_irq_mask_ptr &= ~req_mask;
We should add a comment saying that this is safe because
{GLB,CSG,CS}_REQ_MASK and {GLB,CSG,CS}_EVT_MASK are disjoint, and thus
req_mask and ack_irq_mask are disjoint.
> +
> + if (ret)
> return 0;
>
> /* Check one last time, in case we were not woken up for some reason.
> */
> @@ -1369,6 +1371,8 @@ int panthor_fw_glb_wait_acks(struct panthor_device
> *ptdev,
>
> return panthor_fw_wait_acks(&glb_iface->input->req,
> &glb_iface->output->ack,
> + &glb_iface->input->ack_irq_mask,
> + &glb_iface->lock,
> &ptdev->fw->req_waitqueue,
> req_mask, acked, timeout_ms);
> }
> @@ -1395,6 +1399,8 @@ int panthor_fw_csg_wait_acks(struct panthor_device
> *ptdev, u32 csg_slot,
>
> ret = panthor_fw_wait_acks(&csg_iface->input->req,
> &csg_iface->output->ack,
> + &csg_iface->input->ack_irq_mask,
> + &csg_iface->lock,
> &ptdev->fw->req_waitqueue,
> req_mask, acked, timeout_ms);
>
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c
> b/drivers/gpu/drm/panthor/panthor_sched.c
> index 6c5ba747ae45..a9124bcc7de6 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -1110,7 +1110,7 @@ cs_slot_prog_locked(struct panthor_device *ptdev, u32
> csg_id, u32 cs_id)
> cs_iface->input->ringbuf_output = queue->iface.output_fw_va;
> cs_iface->input->config = CS_CONFIG_PRIORITY(queue->priority) |
> CS_CONFIG_DOORBELL(queue->doorbell_id);
> - cs_iface->input->ack_irq_mask = ~0;
> + cs_iface->input->ack_irq_mask = CS_FATAL | CS_FAULT | CS_TILER_OOM;
> panthor_fw_update_reqs(cs_iface, req,
> CS_IDLE_SYNC_WAIT |
> CS_IDLE_EMPTY |
> @@ -1378,7 +1378,8 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32
> csg_id, u32 priority)
> csg_iface->input->protm_suspend_buf = 0;
> }
>
> - csg_iface->input->ack_irq_mask = ~0;
> + csg_iface->input->ack_irq_mask = CSG_SYNC_UPDATE | CSG_IDLE |
> + CSG_PROGRESS_TIMER_EVENT;
> panthor_fw_toggle_reqs(csg_iface, doorbell_req, doorbell_ack,
> queue_mask);
> return 0;
> }
>
> --
> 2.54.0
>
On Tue, May 12, 2026 at 4:54 AM Boris Brezillon
<[email protected]> wrote:
>
> Rather than assuming an interrupt is always expected for request
> acks, temporarily enable the relevant interrupts when the polling-wait
> failed. This should hopefully reduce the number of interrupts the CPU
> has to process.
>
> Signed-off-by: Boris Brezillon <[email protected]>
> ---
> drivers/gpu/drm/panthor/panthor_fw.c | 34
> +++++++++++++++++++--------------
> drivers/gpu/drm/panthor/panthor_sched.c | 5 +++--
> 2 files changed, 23 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_fw.c
> b/drivers/gpu/drm/panthor/panthor_fw.c
> index 8239a6951569..f5e0ceca4130 100644
> --- a/drivers/gpu/drm/panthor/panthor_fw.c
> +++ b/drivers/gpu/drm/panthor/panthor_fw.c
> @@ -1039,16 +1039,10 @@ static void panthor_fw_init_global_iface(struct
> panthor_device *ptdev)
> glb_iface->input->progress_timer = PROGRESS_TIMEOUT_CYCLES >>
> PROGRESS_TIMEOUT_SCALE_SHIFT;
> glb_iface->input->idle_timer = panthor_fw_conv_timeout(ptdev,
> IDLE_HYSTERESIS_US);
>
> - /* Enable interrupts we care about. */
> - glb_iface->input->ack_irq_mask = GLB_CFG_ALLOC_EN |
> - GLB_PING |
> - GLB_CFG_PROGRESS_TIMER |
> - GLB_CFG_POWEROFF_TIMER |
> - GLB_IDLE_EN |
> - GLB_IDLE;
> -
> - if (panthor_fw_has_glb_state(ptdev))
> - glb_iface->input->ack_irq_mask |= GLB_STATE_MASK;
> + /* Enable interrupts for asynchronous events that are not
> + * triggered by request acks.
> + */
> + glb_iface->input->ack_irq_mask = GLB_IDLE;
>
> panthor_fw_update_reqs(glb_iface, req, GLB_IDLE_EN | GLB_COUNTER_EN,
> GLB_IDLE_EN | GLB_COUNTER_EN);
> @@ -1318,8 +1312,8 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
> * Return: 0 on success, -ETIMEDOUT otherwise.
> */
> static int panthor_fw_wait_acks(const u32 *req_ptr, const u32 *ack_ptr,
> - wait_queue_head_t *wq,
> - u32 req_mask, u32 *acked,
> + u32 *ack_irq_mask_ptr, spinlock_t *lock,
> + wait_queue_head_t *wq, u32 req_mask, u32
> *acked,
> u32 timeout_ms)
> {
> u32 ack, req = READ_ONCE(*req_ptr) & req_mask;
> @@ -1334,8 +1328,16 @@ static int panthor_fw_wait_acks(const u32 *req_ptr,
> const u32 *ack_ptr,
> if (!ret)
> return 0;
>
> - if (wait_event_timeout(*wq, (READ_ONCE(*ack_ptr) & req_mask) == req,
> - msecs_to_jiffies(timeout_ms)))
> + scoped_guard(spinlock_irqsave, lock)
> + *ack_irq_mask_ptr |= req_mask;
> +
> + ret = wait_event_timeout(*wq, (READ_ONCE(*ack_ptr) & req_mask) == req,
> + msecs_to_jiffies(timeout_ms));
> +
> + scoped_guard(spinlock_irqsave, lock)
> + *ack_irq_mask_ptr &= ~req_mask;
> +
> + if (ret)
> return 0;
>
> /* Check one last time, in case we were not woken up for some reason.
> */
> @@ -1369,6 +1371,8 @@ int panthor_fw_glb_wait_acks(struct panthor_device
> *ptdev,
>
> return panthor_fw_wait_acks(&glb_iface->input->req,
> &glb_iface->output->ack,
> + &glb_iface->input->ack_irq_mask,
> + &glb_iface->lock,
> &ptdev->fw->req_waitqueue,
> req_mask, acked, timeout_ms);
> }
> @@ -1395,6 +1399,8 @@ int panthor_fw_csg_wait_acks(struct panthor_device
> *ptdev, u32 csg_slot,
>
> ret = panthor_fw_wait_acks(&csg_iface->input->req,
> &csg_iface->output->ack,
> + &csg_iface->input->ack_irq_mask,
> + &csg_iface->lock,
> &ptdev->fw->req_waitqueue,
> req_mask, acked, timeout_ms);
>
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c
> b/drivers/gpu/drm/panthor/panthor_sched.c
> index 6c5ba747ae45..a9124bcc7de6 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -1110,7 +1110,7 @@ cs_slot_prog_locked(struct panthor_device *ptdev, u32
> csg_id, u32 cs_id)
> cs_iface->input->ringbuf_output = queue->iface.output_fw_va;
> cs_iface->input->config = CS_CONFIG_PRIORITY(queue->priority) |
> CS_CONFIG_DOORBELL(queue->doorbell_id);
> - cs_iface->input->ack_irq_mask = ~0;
> + cs_iface->input->ack_irq_mask = CS_FATAL | CS_FAULT | CS_TILER_OOM;
> panthor_fw_update_reqs(cs_iface, req,
> CS_IDLE_SYNC_WAIT |
> CS_IDLE_EMPTY |
> @@ -1378,7 +1378,8 @@ csg_slot_prog_locked(struct panthor_device *ptdev, u32
> csg_id, u32 priority)
> csg_iface->input->protm_suspend_buf = 0;
> }
>
> - csg_iface->input->ack_irq_mask = ~0;
> + csg_iface->input->ack_irq_mask = CSG_SYNC_UPDATE | CSG_IDLE |
> + CSG_PROGRESS_TIMER_EVENT;
> panthor_fw_toggle_reqs(csg_iface, doorbell_req, doorbell_ack,
> queue_mask);
> return 0;
> }
>
> --
> 2.54.0
>
