[PATCH 2/2] drm/msm: don't tear down shared VM mappings on handle close

On targets (like A530 / MSM8996) without per-process pgtables
msm_gpu_create_private_vm() uses the global VM, so all DRM files share
one GPU address space.  msm_gem_close() unmaps the object from ctx->vm,
which on those targets pulls the buffer out from under every other file
that still has it open, and frees the iova for immediate reuse.

A dma-buf imported into a second file hits this as soon as the exporter
closes its handle: the importer's texture keeps sampling the old
address, which the next allocation has taken over.  On a530 this is
every ext_image_dma_buf_import sampling test, reading back all zeros.

The VMA teardown a shared VM needs is the one already used for kms->vm
-- defer it to the @vma_ref drop, when the last handle and dma_buf
reference are gone.  That restores the pre-drm_gpuvm lifetime without
reintroducing the reference loop, since a BO with a live vma_ref is held
by userspace anyway.

Fixes: 111fdd2198e6 ("drm/msm: drm_gpuvm conversion")
Assisted-by: LLM
Signed-off-by: Dmitry Baryshkov <[email protected]>
---
 drivers/gpu/drm/msm/msm_gem.c | 13 ++++++++++++-
 drivers/gpu/drm/msm/msm_gpu.c |  4 +++-
 drivers/gpu/drm/msm/msm_gpu.h |  3 +++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f90afffe3442..e73cf49c360e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -63,6 +63,7 @@ static void put_iova_spaces(struct drm_gem_object *obj, struct drm_gpuvm *vm,
 
 static void msm_gem_close(struct drm_gem_object *obj, struct drm_file *file)
 {
+	struct msm_drm_private *priv = obj->dev->dev_private;
 	struct msm_context *ctx = file->driver_priv;
 
 	update_ctx_mem(file, -obj->size);
@@ -84,6 +85,10 @@ static void msm_gem_close(struct drm_gem_object *obj, struct drm_file *file)
 	if (msm_context_is_vmbind(ctx))
 		return;
 
+	/* A global VM's VMAs are torn down by the @vma_ref drop above */
+	if (priv->gpu && ctx->vm == priv->gpu->vm)
+		return;
+
 	/*
 	 * TODO we might need to kick this to a queue to avoid blocking
 	 * in CLOSE ioctl
@@ -95,7 +100,7 @@ static void msm_gem_close(struct drm_gem_object *obj, struct drm_file *file)
 }
 
 /*
- * Get/put for kms->vm VMA
+ * Get/put for VMAs in VMs shared between contexts: kms->vm, gpu->vm
  */
 
 void msm_gem_vma_get(struct drm_gem_object *obj)
@@ -110,6 +115,12 @@ void msm_gem_vma_put(struct drm_gem_object *obj)
 	if (atomic_dec_return(&to_msm_bo(obj)->vma_ref))
 		return;
 
+	if (priv->gpu && priv->gpu->vm_shared) {
+		dma_resv_wait_timeout(obj->resv, DMA_RESV_USAGE_BOOKKEEP, false,
+				      MAX_SCHEDULE_TIMEOUT);
+		put_iova_spaces(obj, priv->gpu->vm, true, "vma_put");
+	}
+
 	if (!priv->kms)
 		return;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0c2c35636251..31d84e2b123a 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -879,8 +879,10 @@ msm_gpu_create_private_vm(struct msm_gpu *gpu, struct task_struct *task,
 			to_msm_vm(vm)->pid = get_pid(task_pid(task));
 	}
 
-	if (IS_ERR_OR_NULL(vm) && kernel_managed)
+	if (IS_ERR_OR_NULL(vm) && kernel_managed) {
 		vm = drm_gpuvm_get(gpu->vm);
+		gpu->vm_shared = true;
+	}
 
 	return vm;
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index d27d54bdb7a7..7722776e9129 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -223,6 +223,9 @@ struct msm_gpu {
 
 	struct drm_gpuvm *vm;
 
+	/** @vm_shared: Has @vm been handed out as a context VM? */
+	bool vm_shared;
+
 	/* Power Control: */
 	struct regulator *gpu_reg, *gpu_cx;
 	struct clk_bulk_data *grp_clks;

-- 
2.47.3