[PATCH v2 1/2] media: iris: Fix iova allocation from restrict region

The VPU issues DMA through several SMMU streams, and the hardware does
not give every stream the same addressable range. The non-pixel stream
cannot address the low 600MB of IOVA space, while the pixel stream can
address the full range:
    +-----------------------------------------------------------+
    | non-pixel stream addressable range (600 MB - 3.5 GB)      |
    | 0x25800000 - 0xe0000000                                   |
    +-----------------------------------------------------------+
    | pixel stream addressable range (0 - 3.5 GB)               |
    | 0x00000000 - 0xe0000000                                   |
    +-----------------------------------------------------------+

A single "iommus" property on the video-codec node puts every stream
in one IOMMU domain sharing one IOVA space, so nothing stops a
non-pixel buffer from landing below 600MB. Once an allocation lands
below that boundary the hardware faults, which shows up as unhandled
SMMU page faults and spontaneous reboots.
https://gitlab.freedesktop.org/drm/msm/-/work_items/100

Fix this by reserving the 0-600MB range, below the boundary the
non-pixel stream cannot address, using dma_iova_try_alloc() so the
IOMMU-DMA core never hands that range out to a real DMA mapping. This
reserves only IOVA space, it does not allocate any physical memory.

Since sub-nodes for non-pixel, pixel, and secure streams do not exist
yet and only a single device is available, the restriction is applied
to both non-pixel and pixel stream IDs.

Fixes: d7378f84e94e ("media: iris: introduce iris core state management with shared queues")
Cc: [email protected]
Reviewed-by: Vikash Garodia <[email protected]>
Reviewed-by: Dmitry Baryshkov <[email protected]>
Signed-off-by: Vishnu Reddy <[email protected]>
---
 drivers/media/platform/qcom/iris/iris_core.h  |  6 +++
 drivers/media/platform/qcom/iris/iris_probe.c | 62 ++++++++++++++++++++++++++-
 2 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/iris/iris_core.h b/drivers/media/platform/qcom/iris/iris_core.h
index 24da60448cf2..3e4cf652bf39 100644
--- a/drivers/media/platform/qcom/iris/iris_core.h
+++ b/drivers/media/platform/qcom/iris/iris_core.h
@@ -7,6 +7,7 @@
 #define __IRIS_CORE_H__
 
 #include <linux/types.h>
+#include <linux/dma-mapping.h>
 #include <linux/pm_domain.h>
 #include <media/v4l2-device.h>
 
@@ -25,6 +26,9 @@ struct icc_info {
 #define IRIS_FW_VERSION_LENGTH		128
 #define IFACEQ_CORE_PKT_SIZE		(1024 * 4)
 
+#define IRIS_NP_RESERVE_IOVA_START	0x0
+#define IRIS_NP_RESERVE_IOVA_SIZE	0x25800000
+
 enum domain_type {
 	ENCODER	= BIT(0),
 	DECODER	= BIT(1),
@@ -77,6 +81,7 @@ struct qcom_ubwc_cfg_data;
  * @instances: a list_head of all instances
  * @inst_fw_caps_dec: an array of supported instance capabilities by decoder
  * @inst_fw_caps_enc: an array of supported instance capabilities by encoder
+ * @iova_state: a pointer to an array of dma_iova_state entries reserved for restricted IOVA region
  */
 
 struct iris_core {
@@ -123,6 +128,7 @@ struct iris_core {
 	/* encoder and decoder have overlapping caps, so two different arrays are required */
 	struct platform_inst_fw_cap		inst_fw_caps_dec[INST_FW_CAP_MAX];
 	struct platform_inst_fw_cap		inst_fw_caps_enc[INST_FW_CAP_MAX];
+	struct dma_iova_state			*iova_state;
 };
 
 int iris_core_init(struct iris_core *core);
diff --git a/drivers/media/platform/qcom/iris/iris_probe.c b/drivers/media/platform/qcom/iris/iris_probe.c
index e4acf4a74f94..6581a969fe3f 100644
--- a/drivers/media/platform/qcom/iris/iris_probe.c
+++ b/drivers/media/platform/qcom/iris/iris_probe.c
@@ -150,6 +150,57 @@ static int iris_init_resources(struct iris_core *core)
 	return iris_init_resets(core);
 }
 
+static void iris_unreserve_iova_region(struct device *dev, struct dma_iova_state *iova_state)
+{
+	unsigned int i;
+
+	for (i = 0; dma_iova_size(&iova_state[i]); i++)
+		dma_iova_free(dev, &iova_state[i]);
+}
+
+static int iris_reserve_iova_region(struct device *dev, struct dma_iova_state **iova_state,
+				    unsigned long start, unsigned long size)
+{
+	unsigned long dma_limit = dev->bus_dma_limit;
+	unsigned long end, rem, chunk;
+	struct dma_iova_state *state;
+	unsigned int count = 0;
+	int ret = -ENOMEM;
+
+	state = devm_kcalloc(dev, BITS_PER_TYPE(dma_addr_t) + 1, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return ret;
+
+	end = start + size;
+	rem = end - max(start, PAGE_SIZE);
+	dev->bus_dma_limit = end - 1;
+
+	while (rem) {
+		chunk = min(end & -end, (u64)1 << (fls64(rem) - 1));
+
+		if (!dma_iova_try_alloc(dev, &state[count], 0, chunk))
+			goto err_free_iova;
+
+		if (state[count].addr != end - chunk || state[count].__size != chunk)
+			goto err_free_iova;
+
+		rem -= chunk;
+		end -= chunk;
+		count++;
+	}
+
+	*iova_state = state;
+	dev->bus_dma_limit = dma_limit;
+
+	return 0;
+
+err_free_iova:
+	iris_unreserve_iova_region(dev, state);
+	dev->bus_dma_limit = dma_limit;
+
+	return ret;
+}
+
 static int iris_register_video_device(struct iris_core *core, enum domain_type type)
 {
 	struct video_device *vdev;
@@ -207,6 +258,8 @@ static void iris_remove(struct platform_device *pdev)
 
 	v4l2_device_unregister(&core->v4l2_dev);
 
+	iris_unreserve_iova_region(core->dev, core->iova_state);
+
 	mutex_destroy(&core->lock);
 }
 
@@ -269,10 +322,15 @@ static int iris_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = v4l2_device_register(dev, &core->v4l2_dev);
+	ret = iris_reserve_iova_region(dev, &core->iova_state, IRIS_NP_RESERVE_IOVA_START,
+				       IRIS_NP_RESERVE_IOVA_SIZE);
 	if (ret)
 		return ret;
 
+	ret = v4l2_device_register(dev, &core->v4l2_dev);
+	if (ret)
+		goto err_unresv_iova_region;
+
 	ret = iris_register_video_device(core, DECODER);
 	if (ret)
 		goto err_v4l2_unreg;
@@ -306,6 +364,8 @@ static int iris_probe(struct platform_device *pdev)
 	video_unregister_device(core->vdev_dec);
 err_v4l2_unreg:
 	v4l2_device_unregister(&core->v4l2_dev);
+err_unresv_iova_region:
+	iris_unreserve_iova_region(dev, core->iova_state);
 
 	return ret;
 }

-- 
2.34.1