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: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>

drivers/staging/media/tegra-vde/Kconfig

@@ -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

 # 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

+// 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

@@ -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/vde.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * NVIDIA Tegra Video decoder driver
+ *
+ * Copyright (C) 2016-2019 GRATE-DRIVER project
+ */
+
+#ifndef TEGRA_VDE_H
+#define TEGRA_VDE_H
+
+#include <linux/completion.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/iova.h>
+
+struct clk;
+struct gen_pool;
+struct iommu_group;
+struct iommu_domain;
+struct reset_control;
+
+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;
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+	struct iova_domain iova;
+	struct iova *iova_resv_static_addresses;
+	struct iova *iova_resv_last_page;
+	dma_addr_t iram_lists_addr;
+	u32 *iram;
+};
+
+int tegra_vde_iommu_init(struct tegra_vde *vde);
+void tegra_vde_iommu_deinit(struct tegra_vde *vde);
+int tegra_vde_iommu_map(struct tegra_vde *vde,
+			struct sg_table *sgt,
+			struct iova **iovap,
+			dma_addr_t *addrp,
+			size_t size);
+void tegra_vde_iommu_unmap(struct tegra_vde *vde, struct iova *iova);
+
+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 "???";
+}
+
+#endif /* TEGRA_VDE_H */