[RESEND PATCH v2 4/5] drm/msm: add DRM_MSM_GEM_SYNC_CACHE for non-coherent cache maintenance

[Jonathan Marek <jonathan@marek.ca>]

This makes it possible to use the non-coherent cached MSM_BO_CACHED mode,
which otherwise doesn't provide any method for cleaning/invalidating the
cache to sync with the device.

Signed-off-by: Jonathan Marek <jonathan@marek.ca>
---
 drivers/gpu/drm/msm/msm_drv.c | 21 +++++++++++++++++++++
 drivers/gpu/drm/msm/msm_drv.h |  2 ++
 drivers/gpu/drm/msm/msm_gem.c | 23 +++++++++++++++++++++++
 include/uapi/drm/msm_drm.h    | 20 ++++++++++++++++++++
 4 files changed, 66 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index bae48afca82e..3f17acdf6594 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -959,6 +959,26 @@ static int msm_ioctl_submitqueue_close(struct drm_device *dev, void *data,
 	return msm_submitqueue_remove(file->driver_priv, id);
 }
 
+static int msm_ioctl_gem_sync_cache(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct drm_msm_gem_sync_cache *args = data;
+	struct drm_gem_object *obj;
+
+	if (args->flags & ~MSM_GEM_SYNC_CACHE_FLAGS)
+		return -EINVAL;
+
+	obj = drm_gem_object_lookup(file, args->handle);
+	if (!obj)
+		return -ENOENT;
+
+	msm_gem_sync_cache(obj, args->flags, args->offset, args->end);
+
+	drm_gem_object_put(obj);
+
+	return 0;
+}
+
 static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_GET_PARAM,    msm_ioctl_get_param,    DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_GEM_NEW,      msm_ioctl_gem_new,      DRM_RENDER_ALLOW),
@@ -971,6 +991,7 @@ static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_NEW,   msm_ioctl_submitqueue_new,   DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_CLOSE, msm_ioctl_submitqueue_close, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_QUERY, msm_ioctl_submitqueue_query, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(MSM_GEM_SYNC_CACHE,    msm_ioctl_gem_sync_cache,    DRM_RENDER_ALLOW),
 };
 
 static const struct vm_operations_struct vm_ops = {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 22ebecb28349..f170f843010e 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -318,6 +318,8 @@ void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu);
 void msm_gem_active_put(struct drm_gem_object *obj);
 int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout);
 int msm_gem_cpu_fini(struct drm_gem_object *obj);
+void msm_gem_sync_cache(struct drm_gem_object *obj, uint32_t flags,
+		size_t range_start, size_t range_end);
 void msm_gem_free_object(struct drm_gem_object *obj);
 int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file,
 		uint32_t size, uint32_t flags, uint32_t *handle, char *name);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 3d8254b5de16..039738696f9a 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -797,6 +797,29 @@ int msm_gem_cpu_fini(struct drm_gem_object *obj)
 	return 0;
 }
 
+void msm_gem_sync_cache(struct drm_gem_object *obj, uint32_t flags,
+		size_t range_start, size_t range_end)
+{
+	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct device *dev = msm_obj->base.dev->dev;
+
+	/* exit early if get_pages() hasn't been called yet */
+	if (!msm_obj->pages)
+		return;
+
+	/* TODO: sync only the specified range */
+
+	if (flags & MSM_GEM_SYNC_FOR_DEVICE) {
+		dma_sync_sg_for_device(dev, msm_obj->sgt->sgl,
+				msm_obj->sgt->nents, DMA_TO_DEVICE);
+	}
+
+	if (flags & MSM_GEM_SYNC_FOR_CPU) {
+		dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl,
+				msm_obj->sgt->nents, DMA_FROM_DEVICE);
+	}
+}
+
 #ifdef CONFIG_DEBUG_FS
 static void describe_fence(struct dma_fence *fence, const char *type,
 		struct seq_file *m)
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index 474497e8743a..c8288f328528 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -319,6 +319,24 @@ struct drm_msm_submitqueue_query {
 	__u32 pad;
 };
 
+/*
+ * Host cache maintenance (relevant for MSM_BO_CACHED)
+ * driver may both clean/invalidate (flush) for clean
+ */
+
+#define MSM_GEM_SYNC_FOR_DEVICE		0x1
+#define MSM_GEM_SYNC_FOR_CPU		0x2
+
+#define MSM_GEM_SYNC_CACHE_FLAGS	(MSM_GEM_SYNC_FOR_DEVICE | \
+					 MSM_GEM_SYNC_FOR_CPU)
+
+struct drm_msm_gem_sync_cache {
+	__u32 handle;
+	__u32 flags;
+	__u64 offset;
+	__u64 end;      /* offset + size */
+};
+
 #define DRM_MSM_GET_PARAM              0x00
 /* placeholder:
 #define DRM_MSM_SET_PARAM              0x01
@@ -336,6 +354,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_MSM_SUBMITQUEUE_NEW        0x0A
 #define DRM_MSM_SUBMITQUEUE_CLOSE      0x0B
 #define DRM_MSM_SUBMITQUEUE_QUERY      0x0C
+#define DRM_MSM_GEM_SYNC_CACHE         0x0D
 
 #define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
 #define DRM_IOCTL_MSM_GEM_NEW          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new)
@@ -348,6 +367,7 @@ struct drm_msm_submitqueue_query {
 #define DRM_IOCTL_MSM_SUBMITQUEUE_NEW    DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
 #define DRM_IOCTL_MSM_SUBMITQUEUE_QUERY  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_QUERY, struct drm_msm_submitqueue_query)
+#define DRM_IOCTL_MSM_GEM_SYNC_CACHE     DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_SYNC_CACHE, struct drm_msm_gem_sync_cache)
 
 #if defined(__cplusplus)
 }
-- 
2.26.1