drm/amdgpu: hold a runtime PM reference for P2P dma-buf attachments

amdgpu_dma_buf_map() adds VRAM to the allowed domains for a peer2peer
attachment.  GTT is only a fallback placement when VRAM is preferred, so
ttm_bo_validate() migrates the buffer from GTT into VRAM.  While the
exporting device is runtime suspended its SDMA rings are down and the
move fails:

  amdgpu: Move buffer fallback to memcpy unavailable

An importer on a second GPU reaches this holding no runtime PM
reference on the exporter, e.g. a compositor on the APU submitting a
frame that references a buffer exported by an idle dGPU:

  amdgpu_cs_ioctl -> amdgpu_cs_parser_bos -> amdgpu_cs_bo_validate
    -> ttm_bo_validate -> amdgpu_bo_move -> dma_buf_map_attachment
      -> amdgpu_dma_buf_map -> ttm_bo_validate -> amdgpu_bo_move

Pinning a dma-buf into VRAM has the same requirement, which
commit 030631e97b20 ("drm/amdgpu: revert "take runtime pm reference
when we attach a buffer" v2") called out as the one case that would
need the reference back.

Take it in attach and drop it in detach.  pm_runtime_get_if_active()
never resumes the device, so it cannot deadlock against the reservation
taken during resume, which is why the old pm_runtime_get_sync() had to
go.  If the device is not active, clear peer2peer instead: the buffer
then stays in GTT, which remains accessible while the GPU is powered
down.  If runtime PM is disabled, take a plain reference so the put in
detach stays balanced.

Fixes: 030631e97b20 ("drm/amdgpu: revert "take runtime pm reference when we attach a buffer" v2")
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Mike Lothian <mike@fireburn.co.uk>
Assisted-by: Claude:Opus-5 [Claude Code]
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 062ff15e30a48d14fb7d7558eba84f8dc97197f0)
Cc: stable@vger.kernel.org

1 files changed, 42 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index b33c300e26e2..9adf3eed8822 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -43,6 +43,7 @@
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
+#include <linux/pm_runtime.h>
 
 static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops;
 
@@ -100,15 +101,54 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
+	/*
+	 * Only allow P2P while the exporter is active, and keep it active
+	 * until detach.  With runtime PM disabled take a plain reference so
+	 * the put in detach stays balanced.
+	 */
+	if (attach->peer2peer) {
+		struct device *dev = adev_to_drm(adev)->dev;
+		int ret = pm_runtime_get_if_active(dev);
+
+		if (!ret)
+			attach->peer2peer = false;
+		else if (ret < 0)
+			pm_runtime_get_noresume(dev);
+	}
+
 	r = dma_resv_lock(bo->tbo.base.resv, NULL);
 	if (r)
-		return r;
+		goto err_pm_put;
 
 	amdgpu_vm_bo_update_shared(bo);
 
 	dma_resv_unlock(bo->tbo.base.resv);
 
 	return 0;
+
+err_pm_put:
+	if (attach->peer2peer)
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+	return r;
+}
+
+/**
+ * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
+ *
+ * @dmabuf: DMA-buf where we remove the attachment from
+ * @attach: the attachment to remove
+ *
+ * Drop the runtime PM reference taken in amdgpu_dma_buf_attach().
+ */
+static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
+				  struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (attach->peer2peer)
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 }
 
 /**
@@ -350,6 +390,7 @@ static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.attach = amdgpu_dma_buf_attach,
+	.detach = amdgpu_dma_buf_detach,
 	.pin = amdgpu_dma_buf_pin,
 	.unpin = amdgpu_dma_buf_unpin,
 	.map_dma_buf = amdgpu_dma_buf_map,