accel/ivpu: Add Intel VPU MMU support

VPU Memory Management Unit is based on ARM MMU-600.
It allows the creation of multiple virtual address spaces for
the device and map noncontinuous host memory (there is no dedicated
memory on the VPU).

Address space is implemented as a struct ivpu_mmu_context, it has an ID,
drm_mm allocator for VPU addresses and struct ivpu_mmu_pgtable that
holds actual 3-level, 4KB page table.
Context with ID 0 (global context) is created upon driver initialization
and it's mainly used for mapping memory required to execute
the firmware.
Contexts with non-zero IDs are user contexts allocated each time
the devices is open()-ed and they map command buffers and other
workload-related memory.
Workloads executing in a given contexts have access only
to the memory mapped in this context.

This patch is has two main files:
  - ivpu_mmu_context.c handles MMU page tables and memory mapping
  - ivpu_mmu.c implements a driver that programs the MMU device

Co-developed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Co-developed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117092723.60441-3-jacek.lawrynowicz@linux.intel.com

1 files changed, 81 insertions, 2 deletions

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 1134fb0028ad..69ca7dae8b57 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -15,6 +15,8 @@
 
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
+#include "ivpu_mmu.h"
+#include "ivpu_mmu_context.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
@@ -37,23 +39,38 @@ MODULE_PARM_DESC(pll_max_ratio, "Maximum PLL ratio used to set VPU frequency");
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv)
 {
+	struct ivpu_device *vdev = file_priv->vdev;
+
 	kref_get(&file_priv->ref);
+
+	ivpu_dbg(vdev, KREF, "file_priv get: ctx %u refcount %u\n",
+		 file_priv->ctx.id, kref_read(&file_priv->ref));
+
 	return file_priv;
 }
 
 static void file_priv_release(struct kref *ref)
 {
 	struct ivpu_file_priv *file_priv = container_of(ref, struct ivpu_file_priv, ref);
+	struct ivpu_device *vdev = file_priv->vdev;
 
+	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
+
+	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+	WARN_ON(xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	kfree(file_priv);
 }
 
 void ivpu_file_priv_put(struct ivpu_file_priv **link)
 {
 	struct ivpu_file_priv *file_priv = *link;
+	struct ivpu_device *vdev = file_priv->vdev;
 
 	WARN_ON(!file_priv);
 
+	ivpu_dbg(vdev, KREF, "file_priv put: ctx %u refcount %u\n",
+		 file_priv->ctx.id, kref_read(&file_priv->ref));
+
 	*link = NULL;
 	kref_put(&file_priv->ref, file_priv_release);
 }
@@ -88,6 +105,9 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
 		args->value = file_priv->priority;
 		break;
+	case DRM_IVPU_PARAM_CONTEXT_ID:
+		args->value = file_priv->ctx.id;
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -120,22 +140,59 @@ static int ivpu_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_file_priv *file_priv;
+	u32 ctx_id;
+	void *old;
+	int ret;
+
+	ret = xa_alloc_irq(&vdev->context_xa, &ctx_id, NULL, vdev->context_xa_limit, GFP_KERNEL);
+	if (ret) {
+		ivpu_err(vdev, "Failed to allocate context id: %d\n", ret);
+		return ret;
+	}
 
 	file_priv = kzalloc(sizeof(*file_priv), GFP_KERNEL);
-	if (!file_priv)
-		return -ENOMEM;
+	if (!file_priv) {
+		ret = -ENOMEM;
+		goto err_xa_erase;
+	}
 
 	file_priv->vdev = vdev;
 	file_priv->priority = DRM_IVPU_CONTEXT_PRIORITY_NORMAL;
 	kref_init(&file_priv->ref);
 
+	ret = ivpu_mmu_user_context_init(vdev, &file_priv->ctx, ctx_id);
+	if (ret)
+		goto err_free_file_priv;
+
+	old = xa_store_irq(&vdev->context_xa, ctx_id, file_priv, GFP_KERNEL);
+	if (xa_is_err(old)) {
+		ret = xa_err(old);
+		ivpu_err(vdev, "Failed to store context %u: %d\n", ctx_id, ret);
+		goto err_ctx_fini;
+	}
+
+	ivpu_dbg(vdev, FILE, "file_priv create: ctx %u process %s pid %d\n",
+		 ctx_id, current->comm, task_pid_nr(current));
+
 	file->driver_priv = file_priv;
 	return 0;
+
+err_ctx_fini:
+	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
+err_free_file_priv:
+	kfree(file_priv);
+err_xa_erase:
+	xa_erase_irq(&vdev->context_xa, ctx_id);
+	return ret;
 }
 
 static void ivpu_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = to_ivpu_device(dev);
+
+	ivpu_dbg(vdev, FILE, "file_priv close: ctx %u process %s pid %d\n",
+		 file_priv->ctx.id, current->comm, task_pid_nr(current));
 
 	ivpu_file_priv_put(&file_priv);
 }
@@ -150,6 +207,7 @@ int ivpu_shutdown(struct ivpu_device *vdev)
 	int ret;
 
 	ivpu_hw_irq_disable(vdev);
+	ivpu_mmu_disable(vdev);
 
 	ret = ivpu_hw_power_down(vdev);
 	if (ret)
@@ -251,6 +309,10 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (!vdev->hw)
 		return -ENOMEM;
 
+	vdev->mmu = drmm_kzalloc(&vdev->drm, sizeof(*vdev->mmu), GFP_KERNEL);
+	if (!vdev->mmu)
+		return -ENOMEM;
+
 	vdev->hw->ops = &ivpu_hw_mtl_ops;
 	vdev->platform = IVPU_PLATFORM_INVALID;
 	vdev->context_xa_limit.min = IVPU_GLOBAL_CONTEXT_MMU_SSID + 1;
@@ -283,8 +345,24 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 		goto err_xa_destroy;
 	}
 
+	ret = ivpu_mmu_global_context_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize global MMU context: %d\n", ret);
+		goto err_power_down;
+	}
+
+	ret = ivpu_mmu_init(vdev);
+	if (ret) {
+		ivpu_err(vdev, "Failed to initialize MMU device: %d\n", ret);
+		goto err_mmu_gctx_fini;
+	}
+
 	return 0;
 
+err_mmu_gctx_fini:
+	ivpu_mmu_global_context_fini(vdev);
+err_power_down:
+	ivpu_hw_power_down(vdev);
 err_xa_destroy:
 	xa_destroy(&vdev->context_xa);
 	return ret;
@@ -293,6 +371,7 @@ err_xa_destroy:
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_shutdown(vdev);
+	ivpu_mmu_global_context_fini(vdev);
 
 	drm_WARN_ON(&vdev->drm, !xa_empty(&vdev->context_xa));
 	xa_destroy(&vdev->context_xa);