staging: mmal-vchiq: Use vc-sm-cma to support zero copy

With the vc-sm-cma driver we can support zero copy of buffers between
the kernel and VPU. Add this support to mmal-vchiq.

Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>

vc-sm-cma: fixed kbuild problem

error logs:
  drivers/staging/vc04_services/vc-sm-cma/Kconfig:1:error: recursive dependency detected!
  drivers/staging/vc04_services/vc-sm-cma/Kconfig:1:      symbol BCM_VC_SM_CMA is selected by BCM2835_VCHIQ_MMAL
  drivers/staging/vc04_services/vchiq-mmal/Kconfig:1:     symbol BCM2835_VCHIQ_MMAL depends on BCM2835_VCHIQ
  drivers/staging/vc04_services/Kconfig:14:       symbol BCM2835_VCHIQ is selected by BCM_VC_SM_CMA
  For a resolution refer to Documentation/kbuild/kconfig-language.rst
  subsection "Kconfig recursive dependency limitations"

Tested-by: make ARCH=arm64 bcm2711_defconfig
Test platform: fedora 33
Branch: rpi-5.10.y

drivers/staging/vc04_services/vchiq-mmal/Kconfig

@@ -1,6 +1,7 @@
 config BCM2835_VCHIQ_MMAL
 	tristate "BCM2835 MMAL VCHIQ service"
-	depends on BCM2835_VCHIQ
+	select BCM2835_VCHIQ
+	select BCM_VC_SM_CMA
 	help
 	  Enables the MMAL API over VCHIQ interface as used for the
 	  majority of the multimedia services on VideoCore.

drivers/staging/vc04_services/vchiq-mmal/mmal-common.h

@@ -50,6 +50,10 @@ struct mmal_buffer {
 
 	struct mmal_msg_context *msg_context;
 
+	struct dma_buf *dma_buf;/* Exported dmabuf fd from videobuf2 */
+	void *vcsm_handle;	/* VCSM handle having imported the dmabuf */
+	u32 vc_handle;		/* VC handle to that dmabuf */
+
 	u32 cmd;		/* MMAL command. 0=data. */
 	unsigned long length;
 	u32 mmal_flags;

drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c

@@ -28,9 +28,12 @@
 #include "../include/linux/raspberrypi/vchiq.h"
 #include "../interface/vchiq_arm/vchiq_arm.h"
 #include "mmal-common.h"
+#include "mmal-parameters.h"
 #include "mmal-vchiq.h"
 #include "mmal-msg.h"
 
+#include "../vc-sm-cma/vc_sm_knl.h"
+
 /*
  * maximum number of components supported.
  * This matches the maximum permitted by default on the VPU
@@ -417,8 +420,13 @@ buffer_from_host(struct vchiq_mmal_instance *instance,
 
 	/* buffer header */
 	m.u.buffer_from_host.buffer_header.cmd = 0;
-	m.u.buffer_from_host.buffer_header.data =
-		(u32)(unsigned long)buf->buffer;
+	if (port->zero_copy) {
+		m.u.buffer_from_host.buffer_header.data = buf->vc_handle;
+	} else {
+		m.u.buffer_from_host.buffer_header.data =
+			(u32)(unsigned long)buf->buffer;
+	}
+
 	m.u.buffer_from_host.buffer_header.alloc_size = buf->buffer_size;
 	if (port->type == MMAL_PORT_TYPE_OUTPUT) {
 		m.u.buffer_from_host.buffer_header.length = 0;
@@ -584,6 +592,22 @@ static void buffer_to_host_cb(struct vchiq_mmal_instance *instance,
 
 		msg_context->u.bulk.status = msg->h.status;
 
+	} else if (msg->u.buffer_from_host.is_zero_copy) {
+		/*
+		 * Zero copy buffer, so nothing to do.
+		 * Copy buffer info and make callback.
+		 */
+		msg_context->u.bulk.buffer_used =
+				msg->u.buffer_from_host.buffer_header.length;
+		msg_context->u.bulk.mmal_flags =
+				msg->u.buffer_from_host.buffer_header.flags;
+		msg_context->u.bulk.dts =
+				msg->u.buffer_from_host.buffer_header.dts;
+		msg_context->u.bulk.pts =
+				msg->u.buffer_from_host.buffer_header.pts;
+		msg_context->u.bulk.cmd =
+				msg->u.buffer_from_host.buffer_header.cmd;
+
 	} else if (msg->u.buffer_from_host.buffer_header.length == 0) {
 		/* empty buffer */
 		if (msg->u.buffer_from_host.buffer_header.flags &
@@ -1530,6 +1554,9 @@ int vchiq_mmal_port_parameter_set(struct vchiq_mmal_instance *instance,
 
 	mutex_unlock(&instance->vchiq_mutex);
 
+	if (parameter == MMAL_PARAMETER_ZERO_COPY && !ret)
+		port->zero_copy = !!(*(bool *)value);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vchiq_mmal_port_parameter_set);
@@ -1698,6 +1725,31 @@ int vchiq_mmal_submit_buffer(struct vchiq_mmal_instance *instance,
 	unsigned long flags = 0;
 	int ret;
 
+	/*
+	 * We really want to do this in mmal_vchi_buffer_init but can't as
+	 * videobuf2 won't let us have the dmabuf there.
+	 */
+	if (port->zero_copy && buffer->dma_buf && !buffer->vcsm_handle) {
+		pr_debug("%s: import dmabuf %p\n", __func__, buffer->dma_buf);
+		ret = vc_sm_cma_import_dmabuf(buffer->dma_buf,
+					      &buffer->vcsm_handle);
+		if (ret) {
+			pr_err("%s: vc_sm_import_dmabuf_fd failed, ret %d\n",
+			       __func__, ret);
+			return ret;
+		}
+
+		buffer->vc_handle = vc_sm_cma_int_handle(buffer->vcsm_handle);
+		if (!buffer->vc_handle) {
+			pr_err("%s: vc_sm_int_handle failed %d\n",
+			       __func__, ret);
+			vc_sm_cma_free(buffer->vcsm_handle);
+			return ret;
+		}
+		pr_debug("%s: import dmabuf %p - got vc handle %08X\n",
+			 __func__, buffer->dma_buf, buffer->vc_handle);
+	}
+
 	ret = buffer_from_host(instance, port, buffer);
 	if (ret == -EINVAL) {
 		/* Port is disabled. Queue for when it is enabled. */
@@ -1731,6 +1783,16 @@ int mmal_vchi_buffer_cleanup(struct mmal_buffer *buf)
 		release_msg_context(msg_context);
 	buf->msg_context = NULL;
 
+	if (buf->vcsm_handle) {
+		int ret;
+
+		pr_debug("%s: vc_sm_cma_free on handle %p\n", __func__,
+			 buf->vcsm_handle);
+		ret = vc_sm_cma_free(buf->vcsm_handle);
+		if (ret)
+			pr_err("%s: vcsm_free failed, ret %d\n", __func__, ret);
+		buf->vcsm_handle = 0;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mmal_vchi_buffer_cleanup);

drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.h

@@ -49,6 +49,7 @@ typedef void (*vchiq_mmal_buffer_cb)(struct vchiq_mmal_instance  *instance,
 
 struct vchiq_mmal_port {
 	bool enabled;
+	u32 zero_copy:1;
 	u32 handle;
 	u32 type; /* port type, cached to use on port info set */
 	u32 index; /* port index, cached to use on port info set */