[RFC PATCH v4 5/9] accel: rocket: Keep the IOMMU domain attached across jobs

[MidG971 <midgy971@gmail.com>]

From: Midgy BALON <midgy971@gmail.com>

rocket attached the job's IOMMU domain in rocket_job_run() and
detached it again on every completion and reset. Each attach/detach
toggles the rk_iommu stall/force-reset/paging handshake, and on
RK3568 the NPU MMU is idle between jobs, so that handshake times out
and logs a burst of "stall/paging request timed out" errors for
every job.

Attach the per-context domain once and keep it: track the attached
domain in the core, swap it only when a job from a different context
runs, and detach it at core teardown. A reference on the attached
domain is held so it outlives the job that first attached it and is
released on swap/teardown.

Because a hardware reset (on job timeout) wipes the IOMMU page-table
base register, drop the attached domain after rocket_core_reset() so
the next job re-attaches and reprograms it. Also tear down the
scheduler before detaching the IOMMU in rocket_core_fini(), so an
in-flight job can no longer reach the domain being detached.

Signed-off-by: Midgy BALON <midgy971@gmail.com>
---
 drivers/accel/rocket/rocket_core.c | 14 +++++++++++-
 drivers/accel/rocket/rocket_core.h |  3 +++
 drivers/accel/rocket/rocket_job.c  | 35 +++++++++++++++++++++++++-----
 3 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/accel/rocket/rocket_core.c b/drivers/accel/rocket/rocket_core.c
index 779e951596a15..6c128f585cff4 100644
--- a/drivers/accel/rocket/rocket_core.c
+++ b/drivers/accel/rocket/rocket_core.c
@@ -13,6 +13,7 @@
 #include <linux/reset.h>
 
 #include "rocket_core.h"
+#include "rocket_drv.h"
 #include "rocket_job.h"
 
 int rocket_core_init(struct rocket_core *core)
@@ -112,9 +113,20 @@ void rocket_core_fini(struct rocket_core *core)
 {
 	pm_runtime_dont_use_autosuspend(core->dev);
 	pm_runtime_disable(core->dev);
+
+	/*
+	 * Stop the scheduler before tearing down the IOMMU so an in-flight
+	 * job can no longer touch the (about to be detached) domain.
+	 */
+	rocket_job_fini(core);
+
+	if (core->attached_domain) {
+		iommu_detach_group(NULL, core->iommu_group);
+		rocket_iommu_domain_put(core->attached_domain);
+		core->attached_domain = NULL;
+	}
 	iommu_group_put(core->iommu_group);
 	core->iommu_group = NULL;
-	rocket_job_fini(core);
 }
 
 void rocket_core_reset(struct rocket_core *core)
diff --git a/drivers/accel/rocket/rocket_core.h b/drivers/accel/rocket/rocket_core.h
index 5a145ba8c5a92..78791ecb32e75 100644
--- a/drivers/accel/rocket/rocket_core.h
+++ b/drivers/accel/rocket/rocket_core.h
@@ -42,6 +42,8 @@ struct rocket_soc_data {
 #define rocket_core_writel(core, reg, value) \
 	writel(value, (core)->core_iomem + (REG_CORE_##reg) - REG_CORE_S_STATUS)
 
+struct rocket_iommu_domain;
+
 struct rocket_core {
 	struct device *dev;
 	struct rocket_device *rdev;
@@ -56,6 +58,7 @@ struct rocket_core {
 	struct reset_control_bulk_data resets[2];
 
 	struct iommu_group *iommu_group;
+	struct rocket_iommu_domain *attached_domain;
 
 	struct mutex job_lock;
 	struct rocket_job *in_flight_job;
diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c
index e25234261536b..368b2ebead1b3 100644
--- a/drivers/accel/rocket/rocket_job.c
+++ b/drivers/accel/rocket/rocket_job.c
@@ -9,6 +9,7 @@
 #include <drm/rocket_accel.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
+#include <linux/kref.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
@@ -314,9 +315,26 @@ static struct dma_fence *rocket_job_run(struct drm_sched_job *sched_job)
 	if (ret < 0)
 		return fence;
 
-	ret = iommu_attach_group(job->domain->domain, core->iommu_group);
-	if (ret < 0)
-		return fence;
+	/*
+	 * Attach the job's IOMMU domain only when it differs from the one
+	 * already attached. Re-attaching per job toggles the rk_iommu
+	 * stall/reset handshake on an idle NPU MMU, which is slow and
+	 * noisy; keep the domain attached across jobs instead.
+	 */
+	if (core->attached_domain != job->domain) {
+		if (core->attached_domain) {
+			iommu_detach_group(NULL, core->iommu_group);
+			rocket_iommu_domain_put(core->attached_domain);
+			core->attached_domain = NULL;
+		}
+
+		ret = iommu_attach_group(job->domain->domain, core->iommu_group);
+		if (ret < 0)
+			return fence;
+
+		kref_get(&job->domain->kref);
+		core->attached_domain = job->domain;
+	}
 
 	scoped_guard(mutex, &core->job_lock) {
 		core->in_flight_job = job;
@@ -340,7 +358,6 @@ static void rocket_job_handle_irq(struct rocket_core *core)
 				return;
 			}
 
-			iommu_detach_group(NULL, iommu_group_get(core->dev));
 			dma_fence_signal(core->in_flight_job->done_fence);
 			pm_runtime_put_autosuspend(core->dev);
 			core->in_flight_job = NULL;
@@ -376,7 +393,15 @@ rocket_reset(struct rocket_core *core, struct drm_sched_job *bad)
 	 */
 	rocket_core_reset(core);
 
-	iommu_detach_group(NULL, core->iommu_group);
+	/*
+	 * The reset wipes the IOMMU page-table base, so drop the attached
+	 * domain to force the next job to re-attach and reprogram it.
+	 */
+	if (core->attached_domain) {
+		iommu_detach_group(NULL, core->iommu_group);
+		rocket_iommu_domain_put(core->attached_domain);
+		core->attached_domain = NULL;
+	}
 
 	/* NPU has been reset, we can clear the reset pending bit. */
 	atomic_set(&core->reset.pending, 0);
-- 
2.39.5


_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip