Commit b301f8de authored by Dmitry Osipenko's avatar Dmitry Osipenko Committed by Mauro Carvalho Chehab
Browse files

media: staging: media: tegra-vde: Add IOMMU support 



All Tegra's could provide memory isolation for the video decoder
hardware using IOMMU, it is also required for Tegra30+ in order
to handle sparse dmabuf's which GPU exports in a default kernel
configuration.

Signed-off-by: default avatarDmitry Osipenko <digetx@gmail.com>
Signed-off-by: default avatarHans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: default avatarMauro Carvalho Chehab <mchehab+samsung@kernel.org>
parent 6bc5a4a1

drivers/staging/media/tegra-vde/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -3,6 +3,7 @@ config TEGRA_VDE 
	tristate "NVIDIA Tegra Video Decoder Engine driver"

	depends on ARCH_TEGRA || COMPILE_TEST

	select DMA_SHARED_BUFFER

	select IOMMU_IOVA if IOMMU_SUPPORT

	select SRAM

	help

	    Say Y here to enable support for the NVIDIA Tegra video decoder

drivers/staging/media/tegra-vde/Makefile

+1 −0
Original line number Diff line number Diff line 
# SPDX-License-Identifier: GPL-2.0

tegra-vde-y := vde.o iommu.o

obj-$(CONFIG_TEGRA_VDE)	+= tegra-vde.o

drivers/staging/media/tegra-vde/iommu.c

0 → 100644
+159 −0
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0+

/*

 * NVIDIA Tegra Video decoder driver

 *

 * Copyright (C) 2016-2019 GRATE-DRIVER project

 */



#include <linux/iommu.h>

#include <linux/iova.h>

#include <linux/kernel.h>

#include <linux/platform_device.h>



#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)

#include <asm/dma-iommu.h>

#endif



#include "vde.h"



int tegra_vde_iommu_map(struct tegra_vde *vde,

			struct sg_table *sgt,

			struct iova **iovap,

			dma_addr_t *addrp,

			size_t size)

{

	struct iova *iova;

	unsigned long shift;

	unsigned long end;

	dma_addr_t addr;



	end = vde->domain->geometry.aperture_end;

	size = iova_align(&vde->iova, size);

	shift = iova_shift(&vde->iova);



	iova = alloc_iova(&vde->iova, size >> shift, end >> shift, true);

	if (!iova)

		return -ENOMEM;



	addr = iova_dma_addr(&vde->iova, iova);



	size = iommu_map_sg(vde->domain, addr, sgt->sgl, sgt->nents,

			    IOMMU_READ | IOMMU_WRITE);

	if (!size) {

		__free_iova(&vde->iova, iova);

		return -ENXIO;

	}



	*iovap = iova;

	*addrp = addr;



	return 0;

}



void tegra_vde_iommu_unmap(struct tegra_vde *vde, struct iova *iova)

{

	unsigned long shift = iova_shift(&vde->iova);

	unsigned long size = iova_size(iova) << shift;

	dma_addr_t addr = iova_dma_addr(&vde->iova, iova);



	iommu_unmap(vde->domain, addr, size);

	__free_iova(&vde->iova, iova);

}



int tegra_vde_iommu_init(struct tegra_vde *vde)

{

	struct device *dev = vde->miscdev.parent;

	struct iova *iova;

	unsigned long order;

	unsigned long shift;

	int err;



	vde->group = iommu_group_get(dev);

	if (!vde->group)

		return 0;



#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)

	if (dev->archdata.mapping) {

		struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);



		arm_iommu_detach_device(dev);

		arm_iommu_release_mapping(mapping);

	}

#endif

	vde->domain = iommu_domain_alloc(&platform_bus_type);

	if (!vde->domain) {

		err = -ENOMEM;

		goto put_group;

	}



	err = iova_cache_get();

	if (err)

		goto free_domain;



	order = __ffs(vde->domain->pgsize_bitmap);

	init_iova_domain(&vde->iova, 1UL << order, 0);



	err = iommu_attach_group(vde->domain, vde->group);

	if (err)

		goto put_iova;



	/*

	 * We're using some static addresses that are not accessible by VDE

	 * to trap invalid memory accesses.

	 */

	shift = iova_shift(&vde->iova);

	iova = reserve_iova(&vde->iova, 0x60000000 >> shift,

			    0x70000000 >> shift);

	if (!iova) {

		err = -ENOMEM;

		goto detach_group;

	}



	vde->iova_resv_static_addresses = iova;



	/*

	 * BSEV's end-address wraps around due to integer overflow during

	 * of hardware context preparation if IOVA is allocated at the end

	 * of address space and VDE can't handle that. Hence simply reserve

	 * the last page to avoid the problem.

	 */

	iova = reserve_iova(&vde->iova, 0xffffffff >> shift,

			    (0xffffffff >> shift) + 1);

	if (!iova) {

		err = -ENOMEM;

		goto unreserve_iova;

	}



	vde->iova_resv_last_page = iova;



	return 0;



unreserve_iova:

	__free_iova(&vde->iova, vde->iova_resv_static_addresses);

detach_group:

	iommu_detach_group(vde->domain, vde->group);

put_iova:

	put_iova_domain(&vde->iova);

	iova_cache_put();

free_domain:

	iommu_domain_free(vde->domain);

put_group:

	iommu_group_put(vde->group);



	return err;

}



void tegra_vde_iommu_deinit(struct tegra_vde *vde)

{

	if (vde->domain) {

		__free_iova(&vde->iova, vde->iova_resv_last_page);

		__free_iova(&vde->iova, vde->iova_resv_static_addresses);

		iommu_detach_group(vde->domain, vde->group);

		put_iova_domain(&vde->iova);

		iova_cache_put();

		iommu_domain_free(vde->domain);

		iommu_group_put(vde->group);



		vde->domain = NULL;

	}

}

drivers/staging/media/tegra-vde/trace.h

+2 −0
Original line number Diff line number Diff line
@@ -8,6 +8,8 @@ 


#include <linux/tracepoint.h>



#include "vde.h"



DECLARE_EVENT_CLASS(register_access,

	TP_PROTO(struct tegra_vde *vde, void __iomem *base,

		 u32 offset, u32 value),

drivers/staging/media/tegra-vde/tegra-vde.c→drivers/staging/media/tegra-vde/vde.c

+95 −93
Original line number Diff line number Diff line
@@ -22,6 +22,10 @@ 
#include <soc/tegra/pmc.h>



#include "uapi.h"

#include "vde.h"



#define CREATE_TRACE_POINTS

#include "trace.h"



#define ICMDQUE_WR		0x00

#define CMDQUE_CONTROL		0x08
@@ -33,6 +37,10 @@ 
#define BSE_DMA_BUSY		BIT(23)



struct video_frame {

	struct iova *y_iova;

	struct iova *cb_iova;

	struct iova *cr_iova;

	struct iova *aux_iova;

	struct dma_buf_attachment *y_dmabuf_attachment;

	struct dma_buf_attachment *cb_dmabuf_attachment;

	struct dma_buf_attachment *cr_dmabuf_attachment;
@@ -49,63 +57,6 @@ struct video_frame { 
	u32 flags;

};



struct tegra_vde {

	void __iomem *sxe;

	void __iomem *bsev;

	void __iomem *mbe;

	void __iomem *ppe;

	void __iomem *mce;

	void __iomem *tfe;

	void __iomem *ppb;

	void __iomem *vdma;

	void __iomem *frameid;

	struct mutex lock;

	struct miscdevice miscdev;

	struct reset_control *rst;

	struct reset_control *rst_mc;

	struct gen_pool *iram_pool;

	struct completion decode_completion;

	struct clk *clk;

	dma_addr_t iram_lists_addr;

	u32 *iram;

};



static __maybe_unused char const *

tegra_vde_reg_base_name(struct tegra_vde *vde, void __iomem *base)

{

	if (vde->sxe == base)

		return "SXE";



	if (vde->bsev == base)

		return "BSEV";



	if (vde->mbe == base)

		return "MBE";



	if (vde->ppe == base)

		return "PPE";



	if (vde->mce == base)

		return "MCE";



	if (vde->tfe == base)

		return "TFE";



	if (vde->ppb == base)

		return "PPB";



	if (vde->vdma == base)

		return "VDMA";



	if (vde->frameid == base)

		return "FRAMEID";



	return "???";

}



#define CREATE_TRACE_POINTS

#include "trace.h"



static void tegra_vde_writel(struct tegra_vde *vde,

			     u32 value, void __iomem *base, u32 offset)

{
@@ -543,28 +494,35 @@ static void tegra_vde_decode_frame(struct tegra_vde *vde, 
			 vde->sxe, 0x00);

}



static void tegra_vde_detach_and_put_dmabuf(struct dma_buf_attachment *a,

static void tegra_vde_detach_and_put_dmabuf(struct tegra_vde *vde,

					    enum dma_data_direction dma_dir,

					    struct dma_buf_attachment *a,

					    struct sg_table *sgt,

					    enum dma_data_direction dma_dir)

					    struct iova *iova)

{

	struct dma_buf *dmabuf = a->dmabuf;



	if (vde->domain)

		tegra_vde_iommu_unmap(vde, iova);



	dma_buf_unmap_attachment(a, sgt, dma_dir);

	dma_buf_detach(dmabuf, a);

	dma_buf_put(dmabuf);

}



static int tegra_vde_attach_dmabuf(struct device *dev,

static int tegra_vde_attach_dmabuf(struct tegra_vde *vde,

				   int fd,

				   unsigned long offset,

				   size_t min_size,

				   size_t align_size,

				   struct dma_buf_attachment **a,

				   dma_addr_t *addr,

				   dma_addr_t *addrp,

				   struct sg_table **s,

				   struct iova **iovap,

				   size_t *size,

				   enum dma_data_direction dma_dir)

{

	struct device *dev = vde->miscdev.parent;

	struct dma_buf_attachment *attachment;

	struct dma_buf *dmabuf;

	struct sg_table *sgt;
@@ -602,13 +560,23 @@ static int tegra_vde_attach_dmabuf(struct device *dev, 
		goto err_detach;

	}



	if (sgt->nents != 1) {

		dev_err(dev, "Sparse DMA region is unsupported\n");

	if (!vde->domain && sgt->nents > 1) {

		dev_err(dev, "Sparse DMA region is unsupported, please enable IOMMU\n");

		err = -EINVAL;

		goto err_unmap;

	}



	*addr = sg_dma_address(sgt->sgl) + offset;

	if (vde->domain) {

		err = tegra_vde_iommu_map(vde, sgt, iovap, addrp, dmabuf->size);

		if (err) {

			dev_err(dev, "IOMMU mapping failed: %d\n", err);

			goto err_unmap;

		}

	} else {

		*addrp = sg_dma_address(sgt->sgl);

	}



	*addrp = *addrp + offset;

	*a = attachment;

	*s = sgt;
@@ -627,7 +595,7 @@ err_put: 
	return err;

}



static int tegra_vde_attach_dmabufs_to_frame(struct device *dev,

static int tegra_vde_attach_dmabufs_to_frame(struct tegra_vde *vde,

					     struct video_frame *frame,

					     struct tegra_vde_h264_frame *src,

					     enum dma_data_direction dma_dir,
@@ -636,29 +604,32 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, 
{

	int err;



	err = tegra_vde_attach_dmabuf(dev, src->y_fd,

	err = tegra_vde_attach_dmabuf(vde, src->y_fd,

				      src->y_offset, lsize, SZ_256,

				      &frame->y_dmabuf_attachment,

				      &frame->y_addr,

				      &frame->y_sgt,

				      &frame->y_iova,

				      NULL, dma_dir);

	if (err)

		return err;



	err = tegra_vde_attach_dmabuf(dev, src->cb_fd,

	err = tegra_vde_attach_dmabuf(vde, src->cb_fd,

				      src->cb_offset, csize, SZ_256,

				      &frame->cb_dmabuf_attachment,

				      &frame->cb_addr,

				      &frame->cb_sgt,

				      &frame->cb_iova,

				      NULL, dma_dir);

	if (err)

		goto err_release_y;



	err = tegra_vde_attach_dmabuf(dev, src->cr_fd,

	err = tegra_vde_attach_dmabuf(vde, src->cr_fd,

				      src->cr_offset, csize, SZ_256,

				      &frame->cr_dmabuf_attachment,

				      &frame->cr_addr,

				      &frame->cr_sgt,

				      &frame->cr_iova,

				      NULL, dma_dir);

	if (err)

		goto err_release_cb;
@@ -668,11 +639,12 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, 
		return 0;

	}



	err = tegra_vde_attach_dmabuf(dev, src->aux_fd,

	err = tegra_vde_attach_dmabuf(vde, src->aux_fd,

				      src->aux_offset, csize, SZ_256,

				      &frame->aux_dmabuf_attachment,

				      &frame->aux_addr,

				      &frame->aux_sgt,

				      &frame->aux_iova,

				      NULL, dma_dir);

	if (err)

		goto err_release_cr;
@@ -680,34 +652,49 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, 
	return 0;



err_release_cr:

	tegra_vde_detach_and_put_dmabuf(frame->cr_dmabuf_attachment,

					frame->cr_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->cr_dmabuf_attachment,

					frame->cr_sgt,

					frame->cr_iova);

err_release_cb:

	tegra_vde_detach_and_put_dmabuf(frame->cb_dmabuf_attachment,

					frame->cb_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->cb_dmabuf_attachment,

					frame->cb_sgt,

					frame->cb_iova);

err_release_y:

	tegra_vde_detach_and_put_dmabuf(frame->y_dmabuf_attachment,

					frame->y_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->y_dmabuf_attachment,

					frame->y_sgt,

					frame->y_iova);



	return err;

}



static void tegra_vde_release_frame_dmabufs(struct video_frame *frame,

static void tegra_vde_release_frame_dmabufs(struct tegra_vde *vde,

					    struct video_frame *frame,

					    enum dma_data_direction dma_dir,

					    bool baseline_profile)

{

	if (!baseline_profile)

		tegra_vde_detach_and_put_dmabuf(frame->aux_dmabuf_attachment,

						frame->aux_sgt, dma_dir);

		tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

						frame->aux_dmabuf_attachment,

						frame->aux_sgt,

						frame->aux_iova);



	tegra_vde_detach_and_put_dmabuf(frame->cr_dmabuf_attachment,

					frame->cr_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->cr_dmabuf_attachment,

					frame->cr_sgt,

					frame->cr_iova);



	tegra_vde_detach_and_put_dmabuf(frame->cb_dmabuf_attachment,

					frame->cb_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->cb_dmabuf_attachment,

					frame->cb_sgt,

					frame->cb_iova);



	tegra_vde_detach_and_put_dmabuf(frame->y_dmabuf_attachment,

					frame->y_sgt, dma_dir);

	tegra_vde_detach_and_put_dmabuf(vde, dma_dir,

					frame->y_dmabuf_attachment,

					frame->y_sgt,

					frame->y_iova);

}



static int tegra_vde_validate_frame(struct device *dev,
@@ -800,6 +787,7 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, 
	struct video_frame *dpb_frames;

	struct dma_buf_attachment *bitstream_data_dmabuf_attachment;

	struct sg_table *bitstream_sgt;

	struct iova *bitstream_iova;

	enum dma_data_direction dma_dir;

	dma_addr_t bitstream_data_addr;

	dma_addr_t bsev_ptr;
@@ -819,12 +807,13 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, 
	if (ret)

		return ret;



	ret = tegra_vde_attach_dmabuf(dev, ctx.bitstream_data_fd,

	ret = tegra_vde_attach_dmabuf(vde, ctx.bitstream_data_fd,

				      ctx.bitstream_data_offset,

				      SZ_16K, SZ_16K,

				      &bitstream_data_dmabuf_attachment,

				      &bitstream_data_addr,

				      &bitstream_sgt,

				      &bitstream_iova,

				      &bitstream_data_size,

				      DMA_TO_DEVICE);

	if (ret)
@@ -866,7 +855,7 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, 


		dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;



		ret = tegra_vde_attach_dmabufs_to_frame(dev, &dpb_frames[i],

		ret = tegra_vde_attach_dmabufs_to_frame(vde, &dpb_frames[i],

							&frames[i], dma_dir,

							ctx.baseline_profile,

							lsize, csize);
@@ -954,7 +943,7 @@ release_dpb_frames: 
	while (i--) {

		dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;



		tegra_vde_release_frame_dmabufs(&dpb_frames[i], dma_dir,

		tegra_vde_release_frame_dmabufs(vde, &dpb_frames[i], dma_dir,

						ctx.baseline_profile);

	}
@@ -965,8 +954,10 @@ free_frames: 
	kfree(frames);



release_bitstream_dmabuf:

	tegra_vde_detach_and_put_dmabuf(bitstream_data_dmabuf_attachment,

					bitstream_sgt, DMA_TO_DEVICE);

	tegra_vde_detach_and_put_dmabuf(vde, DMA_TO_DEVICE,

					bitstream_data_dmabuf_attachment,

					bitstream_sgt,

					bitstream_iova);



	return ret;

}
@@ -1176,10 +1167,16 @@ static int tegra_vde_probe(struct platform_device *pdev) 
	vde->miscdev.fops = &tegra_vde_fops;

	vde->miscdev.parent = dev;



	err = tegra_vde_iommu_init(vde);

	if (err) {

		dev_err(dev, "Failed to initialize IOMMU: %d\n", err);

		goto err_gen_free;

	}



	err = misc_register(&vde->miscdev);

	if (err) {

		dev_err(dev, "Failed to register misc device: %d\n", err);

		goto err_gen_free;

		goto err_deinit_iommu;

	}



	pm_runtime_enable(dev);
@@ -1197,6 +1194,9 @@ static int tegra_vde_probe(struct platform_device *pdev) 
err_misc_unreg:

	misc_deregister(&vde->miscdev);



err_deinit_iommu:

	tegra_vde_iommu_deinit(vde);



err_gen_free:

	gen_pool_free(vde->iram_pool, (unsigned long)vde->iram,

		      gen_pool_size(vde->iram_pool));
@@ -1221,6 +1221,8 @@ static int tegra_vde_remove(struct platform_device *pdev) 


	misc_deregister(&vde->miscdev);



	tegra_vde_iommu_deinit(vde);



	gen_pool_free(vde->iram_pool, (unsigned long)vde->iram,

		      gen_pool_size(vde->iram_pool));

CRA Git | Maintained and supported by SUSTech CRA and CCSE