Adding upstream version 6.6.15.upstream/6.6.15

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

15 files changed, 4274 insertions, 0 deletions

diff --git a/drivers/gpu/drm/v3d/Kconfig b/drivers/gpu/drm/v3d/Kconfig
new file mode 100644
index 0000000000..ce62c5908e
--- /dev/null
+++ b/drivers/gpu/drm/v3d/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config DRM_V3D
+	tristate "Broadcom V3D 3.x and newer"
+	depends on ARCH_BCM || ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	depends on DRM
+	depends on COMMON_CLK
+	depends on MMU
+	select DRM_SCHED
+	select DRM_GEM_SHMEM_HELPER
+	help
+	  Choose this option if you have a system that has a Broadcom
+	  V3D 3.x or newer GPUs. SoCs supported include the BCM2711,
+	  BCM7268 and BCM7278.
diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile
new file mode 100644
index 0000000000..e8b3141370
--- /dev/null
+++ b/drivers/gpu/drm/v3d/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Please keep these build lists sorted!
+
+# core driver code
+v3d-y := \
+	v3d_bo.o \
+	v3d_drv.o \
+	v3d_fence.o \
+	v3d_gem.o \
+	v3d_irq.o \
+	v3d_mmu.o \
+	v3d_perfmon.o \
+	v3d_trace_points.o \
+	v3d_sched.o
+
+v3d-$(CONFIG_DEBUG_FS) += v3d_debugfs.o
+
+obj-$(CONFIG_DRM_V3D)  += v3d.o
+
+CFLAGS_v3d_trace_points.o := -I$(src)
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
new file mode 100644
index 0000000000..8b3229a37c
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+/**
+ * DOC: V3D GEM BO management support
+ *
+ * Compared to VC4 (V3D 2.x), V3D 3.3 introduces an MMU between the
+ * GPU and the bus, allowing us to use shmem objects for our storage
+ * instead of CMA.
+ *
+ * Physically contiguous objects may still be imported to V3D, but the
+ * driver doesn't allocate physically contiguous objects on its own.
+ * Display engines requiring physically contiguous allocations should
+ * look into Mesa's "renderonly" support (as used by the Mesa pl111
+ * driver) for an example of how to integrate with V3D.
+ *
+ * Long term, we should support evicting pages from the MMU when under
+ * memory pressure (thus the v3d_bo_get_pages() refcounting), but
+ * that's not a high priority since our systems tend to not have swap.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/pfn_t.h>
+
+#include "v3d_drv.h"
+#include "uapi/drm/v3d_drm.h"
+
+/* Called DRM core on the last userspace/kernel unreference of the
+ * BO.
+ */
+void v3d_free_object(struct drm_gem_object *obj)
+{
+	struct v3d_dev *v3d = to_v3d_dev(obj->dev);
+	struct v3d_bo *bo = to_v3d_bo(obj);
+
+	v3d_mmu_remove_ptes(bo);
+
+	mutex_lock(&v3d->bo_lock);
+	v3d->bo_stats.num_allocated--;
+	v3d->bo_stats.pages_allocated -= obj->size >> PAGE_SHIFT;
+	mutex_unlock(&v3d->bo_lock);
+
+	spin_lock(&v3d->mm_lock);
+	drm_mm_remove_node(&bo->node);
+	spin_unlock(&v3d->mm_lock);
+
+	/* GPU execution may have dirtied any pages in the BO. */
+	bo->base.pages_mark_dirty_on_put = true;
+
+	drm_gem_shmem_free(&bo->base);
+}
+
+static const struct drm_gem_object_funcs v3d_gem_funcs = {
+	.free = v3d_free_object,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
+	.vm_ops = &drm_gem_shmem_vm_ops,
+};
+
+/* gem_create_object function for allocating a BO struct and doing
+ * early setup.
+ */
+struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size)
+{
+	struct v3d_bo *bo;
+	struct drm_gem_object *obj;
+
+	if (size == 0)
+		return ERR_PTR(-EINVAL);
+
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (!bo)
+		return ERR_PTR(-ENOMEM);
+	obj = &bo->base.base;
+
+	obj->funcs = &v3d_gem_funcs;
+	bo->base.map_wc = true;
+	INIT_LIST_HEAD(&bo->unref_head);
+
+	return &bo->base.base;
+}
+
+static int
+v3d_bo_create_finish(struct drm_gem_object *obj)
+{
+	struct v3d_dev *v3d = to_v3d_dev(obj->dev);
+	struct v3d_bo *bo = to_v3d_bo(obj);
+	struct sg_table *sgt;
+	int ret;
+
+	/* So far we pin the BO in the MMU for its lifetime, so use
+	 * shmem's helper for getting a lifetime sgt.
+	 */
+	sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+	if (IS_ERR(sgt))
+		return PTR_ERR(sgt);
+
+	spin_lock(&v3d->mm_lock);
+	/* Allocate the object's space in the GPU's page tables.
+	 * Inserting PTEs will happen later, but the offset is for the
+	 * lifetime of the BO.
+	 */
+	ret = drm_mm_insert_node_generic(&v3d->mm, &bo->node,
+					 obj->size >> PAGE_SHIFT,
+					 GMP_GRANULARITY >> PAGE_SHIFT, 0, 0);
+	spin_unlock(&v3d->mm_lock);
+	if (ret)
+		return ret;
+
+	/* Track stats for /debug/dri/n/bo_stats. */
+	mutex_lock(&v3d->bo_lock);
+	v3d->bo_stats.num_allocated++;
+	v3d->bo_stats.pages_allocated += obj->size >> PAGE_SHIFT;
+	mutex_unlock(&v3d->bo_lock);
+
+	v3d_mmu_insert_ptes(bo);
+
+	return 0;
+}
+
+struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
+			     size_t unaligned_size)
+{
+	struct drm_gem_shmem_object *shmem_obj;
+	struct v3d_bo *bo;
+	int ret;
+
+	shmem_obj = drm_gem_shmem_create(dev, unaligned_size);
+	if (IS_ERR(shmem_obj))
+		return ERR_CAST(shmem_obj);
+	bo = to_v3d_bo(&shmem_obj->base);
+
+	ret = v3d_bo_create_finish(&shmem_obj->base);
+	if (ret)
+		goto free_obj;
+
+	return bo;
+
+free_obj:
+	drm_gem_shmem_free(shmem_obj);
+	return ERR_PTR(ret);
+}
+
+struct drm_gem_object *
+v3d_prime_import_sg_table(struct drm_device *dev,
+			  struct dma_buf_attachment *attach,
+			  struct sg_table *sgt)
+{
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_shmem_prime_import_sg_table(dev, attach, sgt);
+	if (IS_ERR(obj))
+		return obj;
+
+	ret = v3d_bo_create_finish(obj);
+	if (ret) {
+		drm_gem_shmem_free(&to_v3d_bo(obj)->base);
+		return ERR_PTR(ret);
+	}
+
+	return obj;
+}
+
+int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
+{
+	struct drm_v3d_create_bo *args = data;
+	struct v3d_bo *bo = NULL;
+	int ret;
+
+	if (args->flags != 0) {
+		DRM_INFO("unknown create_bo flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	bo = v3d_bo_create(dev, file_priv, PAGE_ALIGN(args->size));
+	if (IS_ERR(bo))
+		return PTR_ERR(bo);
+
+	args->offset = bo->node.start << PAGE_SHIFT;
+
+	ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle);
+	drm_gem_object_put(&bo->base.base);
+
+	return ret;
+}
+
+int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_v3d_mmap_bo *args = data;
+	struct drm_gem_object *gem_obj;
+
+	if (args->flags != 0) {
+		DRM_INFO("unknown mmap_bo flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
+	if (!gem_obj) {
+		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
+		return -ENOENT;
+	}
+
+	args->offset = drm_vma_node_offset_addr(&gem_obj->vma_node);
+	drm_gem_object_put(gem_obj);
+
+	return 0;
+}
+
+int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv)
+{
+	struct drm_v3d_get_bo_offset *args = data;
+	struct drm_gem_object *gem_obj;
+	struct v3d_bo *bo;
+
+	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
+	if (!gem_obj) {
+		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
+		return -ENOENT;
+	}
+	bo = to_v3d_bo(gem_obj);
+
+	args->offset = bo->node.start << PAGE_SHIFT;
+
+	drm_gem_object_put(gem_obj);
+	return 0;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_debugfs.c b/drivers/gpu/drm/v3d/v3d_debugfs.c
new file mode 100644
index 0000000000..330669f51f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_debugfs.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+#include <linux/circ_buf.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string_helpers.h>
+
+#include <drm/drm_debugfs.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define REGDEF(reg) { reg, #reg }
+struct v3d_reg_def {
+	u32 reg;
+	const char *name;
+};
+
+static const struct v3d_reg_def v3d_hub_reg_defs[] = {
+	REGDEF(V3D_HUB_AXICFG),
+	REGDEF(V3D_HUB_UIFCFG),
+	REGDEF(V3D_HUB_IDENT0),
+	REGDEF(V3D_HUB_IDENT1),
+	REGDEF(V3D_HUB_IDENT2),
+	REGDEF(V3D_HUB_IDENT3),
+	REGDEF(V3D_HUB_INT_STS),
+	REGDEF(V3D_HUB_INT_MSK_STS),
+
+	REGDEF(V3D_MMU_CTL),
+	REGDEF(V3D_MMU_VIO_ADDR),
+	REGDEF(V3D_MMU_VIO_ID),
+	REGDEF(V3D_MMU_DEBUG_INFO),
+};
+
+static const struct v3d_reg_def v3d_gca_reg_defs[] = {
+	REGDEF(V3D_GCA_SAFE_SHUTDOWN),
+	REGDEF(V3D_GCA_SAFE_SHUTDOWN_ACK),
+};
+
+static const struct v3d_reg_def v3d_core_reg_defs[] = {
+	REGDEF(V3D_CTL_IDENT0),
+	REGDEF(V3D_CTL_IDENT1),
+	REGDEF(V3D_CTL_IDENT2),
+	REGDEF(V3D_CTL_MISCCFG),
+	REGDEF(V3D_CTL_INT_STS),
+	REGDEF(V3D_CTL_INT_MSK_STS),
+	REGDEF(V3D_CLE_CT0CS),
+	REGDEF(V3D_CLE_CT0CA),
+	REGDEF(V3D_CLE_CT0EA),
+	REGDEF(V3D_CLE_CT1CS),
+	REGDEF(V3D_CLE_CT1CA),
+	REGDEF(V3D_CLE_CT1EA),
+
+	REGDEF(V3D_PTB_BPCA),
+	REGDEF(V3D_PTB_BPCS),
+
+	REGDEF(V3D_GMP_STATUS),
+	REGDEF(V3D_GMP_CFG),
+	REGDEF(V3D_GMP_VIO_ADDR),
+
+	REGDEF(V3D_ERR_FDBGO),
+	REGDEF(V3D_ERR_FDBGB),
+	REGDEF(V3D_ERR_FDBGS),
+	REGDEF(V3D_ERR_STAT),
+};
+
+static const struct v3d_reg_def v3d_csd_reg_defs[] = {
+	REGDEF(V3D_CSD_STATUS),
+	REGDEF(V3D_CSD_CURRENT_CFG0),
+	REGDEF(V3D_CSD_CURRENT_CFG1),
+	REGDEF(V3D_CSD_CURRENT_CFG2),
+	REGDEF(V3D_CSD_CURRENT_CFG3),
+	REGDEF(V3D_CSD_CURRENT_CFG4),
+	REGDEF(V3D_CSD_CURRENT_CFG5),
+	REGDEF(V3D_CSD_CURRENT_CFG6),
+};
+
+static int v3d_v3d_debugfs_regs(struct seq_file *m, void *unused)
+{
+	struct drm_debugfs_entry *entry = m->private;
+	struct drm_device *dev = entry->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	int i, core;
+
+	for (i = 0; i < ARRAY_SIZE(v3d_hub_reg_defs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   v3d_hub_reg_defs[i].name, v3d_hub_reg_defs[i].reg,
+			   V3D_READ(v3d_hub_reg_defs[i].reg));
+	}
+
+	if (v3d->ver < 41) {
+		for (i = 0; i < ARRAY_SIZE(v3d_gca_reg_defs); i++) {
+			seq_printf(m, "%s (0x%04x): 0x%08x\n",
+				   v3d_gca_reg_defs[i].name,
+				   v3d_gca_reg_defs[i].reg,
+				   V3D_GCA_READ(v3d_gca_reg_defs[i].reg));
+		}
+	}
+
+	for (core = 0; core < v3d->cores; core++) {
+		for (i = 0; i < ARRAY_SIZE(v3d_core_reg_defs); i++) {
+			seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
+				   core,
+				   v3d_core_reg_defs[i].name,
+				   v3d_core_reg_defs[i].reg,
+				   V3D_CORE_READ(core,
+						 v3d_core_reg_defs[i].reg));
+		}
+
+		if (v3d_has_csd(v3d)) {
+			for (i = 0; i < ARRAY_SIZE(v3d_csd_reg_defs); i++) {
+				seq_printf(m, "core %d %s (0x%04x): 0x%08x\n",
+					   core,
+					   v3d_csd_reg_defs[i].name,
+					   v3d_csd_reg_defs[i].reg,
+					   V3D_CORE_READ(core,
+							 v3d_csd_reg_defs[i].reg));
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int v3d_v3d_debugfs_ident(struct seq_file *m, void *unused)
+{
+	struct drm_debugfs_entry *entry = m->private;
+	struct drm_device *dev = entry->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	u32 ident0, ident1, ident2, ident3, cores;
+	int core;
+
+	ident0 = V3D_READ(V3D_HUB_IDENT0);
+	ident1 = V3D_READ(V3D_HUB_IDENT1);
+	ident2 = V3D_READ(V3D_HUB_IDENT2);
+	ident3 = V3D_READ(V3D_HUB_IDENT3);
+	cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
+
+	seq_printf(m, "Revision:   %d.%d.%d.%d\n",
+		   V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER),
+		   V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV),
+		   V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPREV),
+		   V3D_GET_FIELD(ident3, V3D_HUB_IDENT3_IPIDX));
+	seq_printf(m, "MMU:        %s\n",
+		   str_yes_no(ident2 & V3D_HUB_IDENT2_WITH_MMU));
+	seq_printf(m, "TFU:        %s\n",
+		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_TFU));
+	seq_printf(m, "TSY:        %s\n",
+		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_TSY));
+	seq_printf(m, "MSO:        %s\n",
+		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_MSO));
+	seq_printf(m, "L3C:        %s (%dkb)\n",
+		   str_yes_no(ident1 & V3D_HUB_IDENT1_WITH_L3C),
+		   V3D_GET_FIELD(ident2, V3D_HUB_IDENT2_L3C_NKB));
+
+	for (core = 0; core < cores; core++) {
+		u32 misccfg;
+		u32 nslc, ntmu, qups;
+
+		ident0 = V3D_CORE_READ(core, V3D_CTL_IDENT0);
+		ident1 = V3D_CORE_READ(core, V3D_CTL_IDENT1);
+		ident2 = V3D_CORE_READ(core, V3D_CTL_IDENT2);
+		misccfg = V3D_CORE_READ(core, V3D_CTL_MISCCFG);
+
+		nslc = V3D_GET_FIELD(ident1, V3D_IDENT1_NSLC);
+		ntmu = V3D_GET_FIELD(ident1, V3D_IDENT1_NTMU);
+		qups = V3D_GET_FIELD(ident1, V3D_IDENT1_QUPS);
+
+		seq_printf(m, "Core %d:\n", core);
+		seq_printf(m, "  Revision:     %d.%d\n",
+			   V3D_GET_FIELD(ident0, V3D_IDENT0_VER),
+			   V3D_GET_FIELD(ident1, V3D_IDENT1_REV));
+		seq_printf(m, "  Slices:       %d\n", nslc);
+		seq_printf(m, "  TMUs:         %d\n", nslc * ntmu);
+		seq_printf(m, "  QPUs:         %d\n", nslc * qups);
+		seq_printf(m, "  Semaphores:   %d\n",
+			   V3D_GET_FIELD(ident1, V3D_IDENT1_NSEM));
+		seq_printf(m, "  BCG int:      %d\n",
+			   (ident2 & V3D_IDENT2_BCG_INT) != 0);
+		seq_printf(m, "  Override TMU: %d\n",
+			   (misccfg & V3D_MISCCFG_OVRTMUOUT) != 0);
+	}
+
+	return 0;
+}
+
+static int v3d_debugfs_bo_stats(struct seq_file *m, void *unused)
+{
+	struct drm_debugfs_entry *entry = m->private;
+	struct drm_device *dev = entry->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+
+	mutex_lock(&v3d->bo_lock);
+	seq_printf(m, "allocated bos:          %d\n",
+		   v3d->bo_stats.num_allocated);
+	seq_printf(m, "allocated bo size (kb): %ld\n",
+		   (long)v3d->bo_stats.pages_allocated << (PAGE_SHIFT - 10));
+	mutex_unlock(&v3d->bo_lock);
+
+	return 0;
+}
+
+static int v3d_measure_clock(struct seq_file *m, void *unused)
+{
+	struct drm_debugfs_entry *entry = m->private;
+	struct drm_device *dev = entry->dev;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	uint32_t cycles;
+	int core = 0;
+	int measure_ms = 1000;
+
+	if (v3d->ver >= 40) {
+		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_SRC_0_3,
+			       V3D_SET_FIELD(V3D_PCTR_CYCLE_COUNT,
+					     V3D_PCTR_S0));
+		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_CLR, 1);
+		V3D_CORE_WRITE(core, V3D_V4_PCTR_0_EN, 1);
+	} else {
+		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_PCTRS0,
+			       V3D_PCTR_CYCLE_COUNT);
+		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_CLR, 1);
+		V3D_CORE_WRITE(core, V3D_V3_PCTR_0_EN,
+			       V3D_V3_PCTR_0_EN_ENABLE |
+			       1);
+	}
+	msleep(measure_ms);
+	cycles = V3D_CORE_READ(core, V3D_PCTR_0_PCTR0);
+
+	seq_printf(m, "cycles: %d (%d.%d Mhz)\n",
+		   cycles,
+		   cycles / (measure_ms * 1000),
+		   (cycles / (measure_ms * 100)) % 10);
+
+	return 0;
+}
+
+static const struct drm_debugfs_info v3d_debugfs_list[] = {
+	{"v3d_ident", v3d_v3d_debugfs_ident, 0},
+	{"v3d_regs", v3d_v3d_debugfs_regs, 0},
+	{"measure_clock", v3d_measure_clock, 0},
+	{"bo_stats", v3d_debugfs_bo_stats, 0},
+};
+
+void
+v3d_debugfs_init(struct drm_minor *minor)
+{
+	drm_debugfs_add_files(minor->dev, v3d_debugfs_list, ARRAY_SIZE(v3d_debugfs_list));
+}
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
new file mode 100644
index 0000000000..ffbbe9d527
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D Graphics Driver
+ *
+ * This driver supports the Broadcom V3D 3.3 and 4.1 OpenGL ES GPUs.
+ * For V3D 2.x support, see the VC4 driver.
+ *
+ * The V3D GPU includes a tiled render (composed of a bin and render
+ * pipelines), the TFU (texture formatting unit), and the CSD (compute
+ * shader dispatch).
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_managed.h>
+#include <uapi/drm/v3d_drm.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define DRIVER_NAME "v3d"
+#define DRIVER_DESC "Broadcom V3D graphics"
+#define DRIVER_DATE "20180419"
+#define DRIVER_MAJOR 1
+#define DRIVER_MINOR 0
+#define DRIVER_PATCHLEVEL 0
+
+static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct drm_v3d_get_param *args = data;
+	static const u32 reg_map[] = {
+		[DRM_V3D_PARAM_V3D_UIFCFG] = V3D_HUB_UIFCFG,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT1] = V3D_HUB_IDENT1,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT2] = V3D_HUB_IDENT2,
+		[DRM_V3D_PARAM_V3D_HUB_IDENT3] = V3D_HUB_IDENT3,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT0] = V3D_CTL_IDENT0,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT1] = V3D_CTL_IDENT1,
+		[DRM_V3D_PARAM_V3D_CORE0_IDENT2] = V3D_CTL_IDENT2,
+	};
+
+	if (args->pad != 0)
+		return -EINVAL;
+
+	/* Note that DRM_V3D_PARAM_V3D_CORE0_IDENT0 is 0, so we need
+	 * to explicitly allow it in the "the register in our
+	 * parameter map" check.
+	 */
+	if (args->param < ARRAY_SIZE(reg_map) &&
+	    (reg_map[args->param] ||
+	     args->param == DRM_V3D_PARAM_V3D_CORE0_IDENT0)) {
+		u32 offset = reg_map[args->param];
+
+		if (args->value != 0)
+			return -EINVAL;
+
+		if (args->param >= DRM_V3D_PARAM_V3D_CORE0_IDENT0 &&
+		    args->param <= DRM_V3D_PARAM_V3D_CORE0_IDENT2) {
+			args->value = V3D_CORE_READ(0, offset);
+		} else {
+			args->value = V3D_READ(offset);
+		}
+		return 0;
+	}
+
+	switch (args->param) {
+	case DRM_V3D_PARAM_SUPPORTS_TFU:
+		args->value = 1;
+		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_CSD:
+		args->value = v3d_has_csd(v3d);
+		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH:
+		args->value = 1;
+		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_PERFMON:
+		args->value = (v3d->ver >= 40);
+		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT:
+		args->value = 1;
+		return 0;
+	default:
+		DRM_DEBUG("Unknown parameter %d\n", args->param);
+		return -EINVAL;
+	}
+}
+
+static int
+v3d_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv;
+	struct drm_gpu_scheduler *sched;
+	int i;
+
+	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
+	if (!v3d_priv)
+		return -ENOMEM;
+
+	v3d_priv->v3d = v3d;
+
+	for (i = 0; i < V3D_MAX_QUEUES; i++) {
+		sched = &v3d->queue[i].sched;
+		drm_sched_entity_init(&v3d_priv->sched_entity[i],
+				      DRM_SCHED_PRIORITY_NORMAL, &sched,
+				      1, NULL);
+	}
+
+	v3d_perfmon_open_file(v3d_priv);
+	file->driver_priv = v3d_priv;
+
+	return 0;
+}
+
+static void
+v3d_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct v3d_file_priv *v3d_priv = file->driver_priv;
+	enum v3d_queue q;
+
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
+		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
+
+	v3d_perfmon_close_file(v3d_priv);
+	kfree(v3d_priv);
+}
+
+DEFINE_DRM_GEM_FOPS(v3d_drm_fops);
+
+/* DRM_AUTH is required on SUBMIT_CL for now, while we don't have GMP
+ * protection between clients.  Note that render nodes would be
+ * able to submit CLs that could access BOs from clients authenticated
+ * with the master node.  The TFU doesn't use the GMP, so it would
+ * need to stay DRM_AUTH until we do buffer size/offset validation.
+ */
+static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CL, v3d_submit_cl_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_WAIT_BO, v3d_wait_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_CREATE_BO, v3d_create_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_MMAP_BO, v3d_mmap_bo_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_GET_PARAM, v3d_get_param_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_GET_BO_OFFSET, v3d_get_bo_offset_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_TFU, v3d_submit_tfu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CSD, v3d_submit_csd_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_CREATE, v3d_perfmon_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_DESTROY, v3d_perfmon_destroy_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
+};
+
+static const struct drm_driver v3d_drm_driver = {
+	.driver_features = (DRIVER_GEM |
+			    DRIVER_RENDER |
+			    DRIVER_SYNCOBJ),
+
+	.open = v3d_open,
+	.postclose = v3d_postclose,
+
+#if defined(CONFIG_DEBUG_FS)
+	.debugfs_init = v3d_debugfs_init,
+#endif
+
+	.gem_create_object = v3d_create_object,
+	.gem_prime_import_sg_table = v3d_prime_import_sg_table,
+
+	.ioctls = v3d_drm_ioctls,
+	.num_ioctls = ARRAY_SIZE(v3d_drm_ioctls),
+	.fops = &v3d_drm_fops,
+
+	.name = DRIVER_NAME,
+	.desc = DRIVER_DESC,
+	.date = DRIVER_DATE,
+	.major = DRIVER_MAJOR,
+	.minor = DRIVER_MINOR,
+	.patchlevel = DRIVER_PATCHLEVEL,
+};
+
+static const struct of_device_id v3d_of_match[] = {
+	{ .compatible = "brcm,2711-v3d" },
+	{ .compatible = "brcm,7268-v3d" },
+	{ .compatible = "brcm,7278-v3d" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, v3d_of_match);
+
+static int
+map_regs(struct v3d_dev *v3d, void __iomem **regs, const char *name)
+{
+	*regs = devm_platform_ioremap_resource_byname(v3d_to_pdev(v3d), name);
+	return PTR_ERR_OR_ZERO(*regs);
+}
+
+static int v3d_platform_drm_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct drm_device *drm;
+	struct v3d_dev *v3d;
+	int ret;
+	u32 mmu_debug;
+	u32 ident1;
+	u64 mask;
+
+	v3d = devm_drm_dev_alloc(dev, &v3d_drm_driver, struct v3d_dev, drm);
+	if (IS_ERR(v3d))
+		return PTR_ERR(v3d);
+
+	drm = &v3d->drm;
+
+	platform_set_drvdata(pdev, drm);
+
+	ret = map_regs(v3d, &v3d->hub_regs, "hub");
+	if (ret)
+		return ret;
+
+	ret = map_regs(v3d, &v3d->core_regs[0], "core0");
+	if (ret)
+		return ret;
+
+	mmu_debug = V3D_READ(V3D_MMU_DEBUG_INFO);
+	mask = DMA_BIT_MASK(30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_PA_WIDTH));
+	ret = dma_set_mask_and_coherent(dev, mask);
+	if (ret)
+		return ret;
+
+	v3d->va_width = 30 + V3D_GET_FIELD(mmu_debug, V3D_MMU_VA_WIDTH);
+
+	ident1 = V3D_READ(V3D_HUB_IDENT1);
+	v3d->ver = (V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_TVER) * 10 +
+		    V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_REV));
+	v3d->cores = V3D_GET_FIELD(ident1, V3D_HUB_IDENT1_NCORES);
+	WARN_ON(v3d->cores > 1); /* multicore not yet implemented */
+
+	v3d->reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(v3d->reset)) {
+		ret = PTR_ERR(v3d->reset);
+
+		if (ret == -EPROBE_DEFER)
+			return ret;
+
+		v3d->reset = NULL;
+		ret = map_regs(v3d, &v3d->bridge_regs, "bridge");
+		if (ret) {
+			dev_err(dev,
+				"Failed to get reset control or bridge regs\n");
+			return ret;
+		}
+	}
+
+	if (v3d->ver < 41) {
+		ret = map_regs(v3d, &v3d->gca_regs, "gca");
+		if (ret)
+			return ret;
+	}
+
+	v3d->mmu_scratch = dma_alloc_wc(dev, 4096, &v3d->mmu_scratch_paddr,
+					GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!v3d->mmu_scratch) {
+		dev_err(dev, "Failed to allocate MMU scratch page\n");
+		return -ENOMEM;
+	}
+
+	ret = v3d_gem_init(drm);
+	if (ret)
+		goto dma_free;
+
+	ret = v3d_irq_init(v3d);
+	if (ret)
+		goto gem_destroy;
+
+	ret = drm_dev_register(drm, 0);
+	if (ret)
+		goto irq_disable;
+
+	return 0;
+
+irq_disable:
+	v3d_irq_disable(v3d);
+gem_destroy:
+	v3d_gem_destroy(drm);
+dma_free:
+	dma_free_wc(dev, 4096, v3d->mmu_scratch, v3d->mmu_scratch_paddr);
+	return ret;
+}
+
+static void v3d_platform_drm_remove(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+
+	drm_dev_unregister(drm);
+
+	v3d_gem_destroy(drm);
+
+	dma_free_wc(v3d->drm.dev, 4096, v3d->mmu_scratch,
+		    v3d->mmu_scratch_paddr);
+}
+
+static struct platform_driver v3d_platform_driver = {
+	.probe		= v3d_platform_drm_probe,
+	.remove_new	= v3d_platform_drm_remove,
+	.driver		= {
+		.name	= "v3d",
+		.of_match_table = v3d_of_match,
+	},
+};
+
+module_platform_driver(v3d_platform_driver);
+
+MODULE_ALIAS("platform:v3d-drm");
+MODULE_DESCRIPTION("Broadcom V3D DRM Driver");
+MODULE_AUTHOR("Eric Anholt <eric@anholt.net>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
new file mode 100644
index 0000000000..7f664a4b2a
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+#include <linux/delay.h>
+#include <linux/mutex.h>
+#include <linux/spinlock_types.h>
+#include <linux/workqueue.h>
+
+#include <drm/drm_encoder.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/gpu_scheduler.h>
+
+#include "uapi/drm/v3d_drm.h"
+
+struct clk;
+struct platform_device;
+struct reset_control;
+
+#define GMP_GRANULARITY (128 * 1024)
+
+#define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1)
+
+struct v3d_queue_state {
+	struct drm_gpu_scheduler sched;
+
+	u64 fence_context;
+	u64 emit_seqno;
+};
+
+/* Performance monitor object. The perform lifetime is controlled by userspace
+ * using perfmon related ioctls. A perfmon can be attached to a submit_cl
+ * request, and when this is the case, HW perf counters will be activated just
+ * before the submit_cl is submitted to the GPU and disabled when the job is
+ * done. This way, only events related to a specific job will be counted.
+ */
+struct v3d_perfmon {
+	/* Tracks the number of users of the perfmon, when this counter reaches
+	 * zero the perfmon is destroyed.
+	 */
+	refcount_t refcnt;
+
+	/* Protects perfmon stop, as it can be invoked from multiple places. */
+	struct mutex lock;
+
+	/* Number of counters activated in this perfmon instance
+	 * (should be less than DRM_V3D_MAX_PERF_COUNTERS).
+	 */
+	u8 ncounters;
+
+	/* Events counted by the HW perf counters. */
+	u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+
+	/* Storage for counter values. Counters are incremented by the
+	 * HW perf counter values every time the perfmon is attached
+	 * to a GPU job.  This way, perfmon users don't have to
+	 * retrieve the results after each job if they want to track
+	 * events covering several submissions.  Note that counter
+	 * values can't be reset, but you can fake a reset by
+	 * destroying the perfmon and creating a new one.
+	 */
+	u64 values[];
+};
+
+struct v3d_dev {
+	struct drm_device drm;
+
+	/* Short representation (e.g. 33, 41) of the V3D tech version
+	 * and revision.
+	 */
+	int ver;
+	bool single_irq_line;
+
+	void __iomem *hub_regs;
+	void __iomem *core_regs[3];
+	void __iomem *bridge_regs;
+	void __iomem *gca_regs;
+	struct clk *clk;
+	struct reset_control *reset;
+
+	/* Virtual and DMA addresses of the single shared page table. */
+	volatile u32 *pt;
+	dma_addr_t pt_paddr;
+
+	/* Virtual and DMA addresses of the MMU's scratch page.  When
+	 * a read or write is invalid in the MMU, it will be
+	 * redirected here.
+	 */
+	void *mmu_scratch;
+	dma_addr_t mmu_scratch_paddr;
+	/* virtual address bits from V3D to the MMU. */
+	int va_width;
+
+	/* Number of V3D cores. */
+	u32 cores;
+
+	/* Allocator managing the address space.  All units are in
+	 * number of pages.
+	 */
+	struct drm_mm mm;
+	spinlock_t mm_lock;
+
+	struct work_struct overflow_mem_work;
+
+	struct v3d_bin_job *bin_job;
+	struct v3d_render_job *render_job;
+	struct v3d_tfu_job *tfu_job;
+	struct v3d_csd_job *csd_job;
+
+	struct v3d_queue_state queue[V3D_MAX_QUEUES];
+
+	/* Spinlock used to synchronize the overflow memory
+	 * management against bin job submission.
+	 */
+	spinlock_t job_lock;
+
+	/* Used to track the active perfmon if any. */
+	struct v3d_perfmon *active_perfmon;
+
+	/* Protects bo_stats */
+	struct mutex bo_lock;
+
+	/* Lock taken when resetting the GPU, to keep multiple
+	 * processes from trying to park the scheduler threads and
+	 * reset at once.
+	 */
+	struct mutex reset_lock;
+
+	/* Lock taken when creating and pushing the GPU scheduler
+	 * jobs, to keep the sched-fence seqnos in order.
+	 */
+	struct mutex sched_lock;
+
+	/* Lock taken during a cache clean and when initiating an L2
+	 * flush, to keep L2 flushes from interfering with the
+	 * synchronous L2 cleans.
+	 */
+	struct mutex cache_clean_lock;
+
+	struct {
+		u32 num_allocated;
+		u32 pages_allocated;
+	} bo_stats;
+};
+
+static inline struct v3d_dev *
+to_v3d_dev(struct drm_device *dev)
+{
+	return container_of(dev, struct v3d_dev, drm);
+}
+
+static inline bool
+v3d_has_csd(struct v3d_dev *v3d)
+{
+	return v3d->ver >= 41;
+}
+
+#define v3d_to_pdev(v3d) to_platform_device((v3d)->drm.dev)
+
+/* The per-fd struct, which tracks the MMU mappings. */
+struct v3d_file_priv {
+	struct v3d_dev *v3d;
+
+	struct {
+		struct idr idr;
+		struct mutex lock;
+	} perfmon;
+
+	struct drm_sched_entity sched_entity[V3D_MAX_QUEUES];
+};
+
+struct v3d_bo {
+	struct drm_gem_shmem_object base;
+
+	struct drm_mm_node node;
+
+	/* List entry for the BO's position in
+	 * v3d_render_job->unref_list
+	 */
+	struct list_head unref_head;
+};
+
+static inline struct v3d_bo *
+to_v3d_bo(struct drm_gem_object *bo)
+{
+	return (struct v3d_bo *)bo;
+}
+
+struct v3d_fence {
+	struct dma_fence base;
+	struct drm_device *dev;
+	/* v3d seqno for signaled() test */
+	u64 seqno;
+	enum v3d_queue queue;
+};
+
+static inline struct v3d_fence *
+to_v3d_fence(struct dma_fence *fence)
+{
+	return (struct v3d_fence *)fence;
+}
+
+#define V3D_READ(offset) readl(v3d->hub_regs + offset)
+#define V3D_WRITE(offset, val) writel(val, v3d->hub_regs + offset)
+
+#define V3D_BRIDGE_READ(offset) readl(v3d->bridge_regs + offset)
+#define V3D_BRIDGE_WRITE(offset, val) writel(val, v3d->bridge_regs + offset)
+
+#define V3D_GCA_READ(offset) readl(v3d->gca_regs + offset)
+#define V3D_GCA_WRITE(offset, val) writel(val, v3d->gca_regs + offset)
+
+#define V3D_CORE_READ(core, offset) readl(v3d->core_regs[core] + offset)
+#define V3D_CORE_WRITE(core, offset, val) writel(val, v3d->core_regs[core] + offset)
+
+struct v3d_job {
+	struct drm_sched_job base;
+
+	struct kref refcount;
+
+	struct v3d_dev *v3d;
+
+	/* This is the array of BOs that were looked up at the start
+	 * of submission.
+	 */
+	struct drm_gem_object **bo;
+	u32 bo_count;
+
+	/* v3d fence to be signaled by IRQ handler when the job is complete. */
+	struct dma_fence *irq_fence;
+
+	/* scheduler fence for when the job is considered complete and
+	 * the BO reservations can be released.
+	 */
+	struct dma_fence *done_fence;
+
+	/* Pointer to a performance monitor object if the user requested it,
+	 * NULL otherwise.
+	 */
+	struct v3d_perfmon *perfmon;
+
+	/* Callback for the freeing of the job on refcount going to 0. */
+	void (*free)(struct kref *ref);
+};
+
+struct v3d_bin_job {
+	struct v3d_job base;
+
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
+
+	u32 timedout_ctca, timedout_ctra;
+
+	/* Corresponding render job, for attaching our overflow memory. */
+	struct v3d_render_job *render;
+
+	/* Submitted tile memory allocation start/size, tile state. */
+	u32 qma, qms, qts;
+};
+
+struct v3d_render_job {
+	struct v3d_job base;
+
+	/* GPU virtual addresses of the start/end of the CL job. */
+	u32 start, end;
+
+	u32 timedout_ctca, timedout_ctra;
+
+	/* List of overflow BOs used in the job that need to be
+	 * released once the job is complete.
+	 */
+	struct list_head unref_list;
+};
+
+struct v3d_tfu_job {
+	struct v3d_job base;
+
+	struct drm_v3d_submit_tfu args;
+};
+
+struct v3d_csd_job {
+	struct v3d_job base;
+
+	u32 timedout_batches;
+
+	struct drm_v3d_submit_csd args;
+};
+
+struct v3d_submit_outsync {
+	struct drm_syncobj *syncobj;
+};
+
+struct v3d_submit_ext {
+	u32 flags;
+	u32 wait_stage;
+
+	u32 in_sync_count;
+	u64 in_syncs;
+
+	u32 out_sync_count;
+	struct v3d_submit_outsync *out_syncs;
+};
+
+/**
+ * __wait_for - magic wait macro
+ *
+ * Macro to help avoid open coding check/wait/timeout patterns. Note that it's
+ * important that we check the condition again after having timed out, since the
+ * timeout could be due to preemption or similar and we've never had a chance to
+ * check the condition before the timeout.
+ */
+#define __wait_for(OP, COND, US, Wmin, Wmax) ({ \
+	const ktime_t end__ = ktime_add_ns(ktime_get_raw(), 1000ll * (US)); \
+	long wait__ = (Wmin); /* recommended min for usleep is 10 us */	\
+	int ret__;							\
+	might_sleep();							\
+	for (;;) {							\
+		const bool expired__ = ktime_after(ktime_get_raw(), end__); \
+		OP;							\
+		/* Guarantee COND check prior to timeout */		\
+		barrier();						\
+		if (COND) {						\
+			ret__ = 0;					\
+			break;						\
+		}							\
+		if (expired__) {					\
+			ret__ = -ETIMEDOUT;				\
+			break;						\
+		}							\
+		usleep_range(wait__, wait__ * 2);			\
+		if (wait__ < (Wmax))					\
+			wait__ <<= 1;					\
+	}								\
+	ret__;								\
+})
+
+#define _wait_for(COND, US, Wmin, Wmax)	__wait_for(, (COND), (US), (Wmin), \
+						   (Wmax))
+#define wait_for(COND, MS)		_wait_for((COND), (MS) * 1000, 10, 1000)
+
+static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
+{
+	/* nsecs_to_jiffies64() does not guard against overflow */
+	if ((NSEC_PER_SEC % HZ) != 0 &&
+	    div_u64(n, NSEC_PER_SEC) >= MAX_JIFFY_OFFSET / HZ)
+		return MAX_JIFFY_OFFSET;
+
+	return min_t(u64, MAX_JIFFY_OFFSET, nsecs_to_jiffies64(n) + 1);
+}
+
+/* v3d_bo.c */
+struct drm_gem_object *v3d_create_object(struct drm_device *dev, size_t size);
+void v3d_free_object(struct drm_gem_object *gem_obj);
+struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv,
+			     size_t size);
+int v3d_create_bo_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv);
+struct drm_gem_object *v3d_prime_import_sg_table(struct drm_device *dev,
+						 struct dma_buf_attachment *attach,
+						 struct sg_table *sgt);
+
+/* v3d_debugfs.c */
+void v3d_debugfs_init(struct drm_minor *minor);
+
+/* v3d_fence.c */
+extern const struct dma_fence_ops v3d_fence_ops;
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue);
+
+/* v3d_gem.c */
+int v3d_gem_init(struct drm_device *dev);
+void v3d_gem_destroy(struct drm_device *dev);
+int v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+int v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+int v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv);
+void v3d_job_cleanup(struct v3d_job *job);
+void v3d_job_put(struct v3d_job *job);
+void v3d_reset(struct v3d_dev *v3d);
+void v3d_invalidate_caches(struct v3d_dev *v3d);
+void v3d_clean_caches(struct v3d_dev *v3d);
+
+/* v3d_irq.c */
+int v3d_irq_init(struct v3d_dev *v3d);
+void v3d_irq_enable(struct v3d_dev *v3d);
+void v3d_irq_disable(struct v3d_dev *v3d);
+void v3d_irq_reset(struct v3d_dev *v3d);
+
+/* v3d_mmu.c */
+int v3d_mmu_get_offset(struct drm_file *file_priv, struct v3d_bo *bo,
+		       u32 *offset);
+int v3d_mmu_set_page_table(struct v3d_dev *v3d);
+void v3d_mmu_insert_ptes(struct v3d_bo *bo);
+void v3d_mmu_remove_ptes(struct v3d_bo *bo);
+
+/* v3d_sched.c */
+int v3d_sched_init(struct v3d_dev *v3d);
+void v3d_sched_fini(struct v3d_dev *v3d);
+
+/* v3d_perfmon.c */
+void v3d_perfmon_get(struct v3d_perfmon *perfmon);
+void v3d_perfmon_put(struct v3d_perfmon *perfmon);
+void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon);
+void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
+		      bool capture);
+struct v3d_perfmon *v3d_perfmon_find(struct v3d_file_priv *v3d_priv, int id);
+void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv);
+void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv);
+int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv);
+int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
new file mode 100644
index 0000000000..89840ed212
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+#include "v3d_drv.h"
+
+struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue)
+{
+	struct v3d_fence *fence;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return ERR_PTR(-ENOMEM);
+
+	fence->dev = &v3d->drm;
+	fence->queue = queue;
+	fence->seqno = ++v3d->queue[queue].emit_seqno;
+	dma_fence_init(&fence->base, &v3d_fence_ops, &v3d->job_lock,
+		       v3d->queue[queue].fence_context, fence->seqno);
+
+	return &fence->base;
+}
+
+static const char *v3d_fence_get_driver_name(struct dma_fence *fence)
+{
+	return "v3d";
+}
+
+static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct v3d_fence *f = to_v3d_fence(fence);
+
+	switch (f->queue) {
+	case V3D_BIN:
+		return "v3d-bin";
+	case V3D_RENDER:
+		return "v3d-render";
+	case V3D_TFU:
+		return "v3d-tfu";
+	case V3D_CSD:
+		return "v3d-csd";
+	default:
+		return NULL;
+	}
+}
+
+const struct dma_fence_ops v3d_fence_ops = {
+	.get_driver_name = v3d_fence_get_driver_name,
+	.get_timeline_name = v3d_fence_get_timeline_name,
+};
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
new file mode 100644
index 0000000000..2e94ce788c
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -0,0 +1,1080 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
+
+#include <drm/drm_managed.h>
+#include <drm/drm_syncobj.h>
+#include <uapi/drm/v3d_drm.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+#include "v3d_trace.h"
+
+static void
+v3d_init_core(struct v3d_dev *v3d, int core)
+{
+	/* Set OVRTMUOUT, which means that the texture sampler uniform
+	 * configuration's tmu output type field is used, instead of
+	 * using the hardware default behavior based on the texture
+	 * type.  If you want the default behavior, you can still put
+	 * "2" in the indirect texture state's output_type field.
+	 */
+	if (v3d->ver < 40)
+		V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT);
+
+	/* Whenever we flush the L2T cache, we always want to flush
+	 * the whole thing.
+	 */
+	V3D_CORE_WRITE(core, V3D_CTL_L2TFLSTA, 0);
+	V3D_CORE_WRITE(core, V3D_CTL_L2TFLEND, ~0);
+}
+
+/* Sets invariant state for the HW. */
+static void
+v3d_init_hw_state(struct v3d_dev *v3d)
+{
+	v3d_init_core(v3d, 0);
+}
+
+static void
+v3d_idle_axi(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_GMP_CFG, V3D_GMP_CFG_STOP_REQ);
+
+	if (wait_for((V3D_CORE_READ(core, V3D_GMP_STATUS) &
+		      (V3D_GMP_STATUS_RD_COUNT_MASK |
+		       V3D_GMP_STATUS_WR_COUNT_MASK |
+		       V3D_GMP_STATUS_CFG_BUSY)) == 0, 100)) {
+		DRM_ERROR("Failed to wait for safe GMP shutdown\n");
+	}
+}
+
+static void
+v3d_idle_gca(struct v3d_dev *v3d)
+{
+	if (v3d->ver >= 41)
+		return;
+
+	V3D_GCA_WRITE(V3D_GCA_SAFE_SHUTDOWN, V3D_GCA_SAFE_SHUTDOWN_EN);
+
+	if (wait_for((V3D_GCA_READ(V3D_GCA_SAFE_SHUTDOWN_ACK) &
+		      V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED) ==
+		     V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED, 100)) {
+		DRM_ERROR("Failed to wait for safe GCA shutdown\n");
+	}
+}
+
+static void
+v3d_reset_by_bridge(struct v3d_dev *v3d)
+{
+	int version = V3D_BRIDGE_READ(V3D_TOP_GR_BRIDGE_REVISION);
+
+	if (V3D_GET_FIELD(version, V3D_TOP_GR_BRIDGE_MAJOR) == 2) {
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_0,
+				 V3D_TOP_GR_BRIDGE_SW_INIT_0_V3D_CLK_108_SW_INIT);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_0, 0);
+
+		/* GFXH-1383: The SW_INIT may cause a stray write to address 0
+		 * of the unit, so reset it to its power-on value here.
+		 */
+		V3D_WRITE(V3D_HUB_AXICFG, V3D_HUB_AXICFG_MAX_LEN_MASK);
+	} else {
+		WARN_ON_ONCE(V3D_GET_FIELD(version,
+					   V3D_TOP_GR_BRIDGE_MAJOR) != 7);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1,
+				 V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT);
+		V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1, 0);
+	}
+}
+
+static void
+v3d_reset_v3d(struct v3d_dev *v3d)
+{
+	if (v3d->reset)
+		reset_control_reset(v3d->reset);
+	else
+		v3d_reset_by_bridge(v3d);
+
+	v3d_init_hw_state(v3d);
+}
+
+void
+v3d_reset(struct v3d_dev *v3d)
+{
+	struct drm_device *dev = &v3d->drm;
+
+	DRM_DEV_ERROR(dev->dev, "Resetting GPU for hang.\n");
+	DRM_DEV_ERROR(dev->dev, "V3D_ERR_STAT: 0x%08x\n",
+		      V3D_CORE_READ(0, V3D_ERR_STAT));
+	trace_v3d_reset_begin(dev);
+
+	/* XXX: only needed for safe powerdown, not reset. */
+	if (false)
+		v3d_idle_axi(v3d, 0);
+
+	v3d_idle_gca(v3d);
+	v3d_reset_v3d(v3d);
+
+	v3d_mmu_set_page_table(v3d);
+	v3d_irq_reset(v3d);
+
+	v3d_perfmon_stop(v3d, v3d->active_perfmon, false);
+
+	trace_v3d_reset_end(dev);
+}
+
+static void
+v3d_flush_l3(struct v3d_dev *v3d)
+{
+	if (v3d->ver < 41) {
+		u32 gca_ctrl = V3D_GCA_READ(V3D_GCA_CACHE_CTRL);
+
+		V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
+			      gca_ctrl | V3D_GCA_CACHE_CTRL_FLUSH);
+
+		if (v3d->ver < 33) {
+			V3D_GCA_WRITE(V3D_GCA_CACHE_CTRL,
+				      gca_ctrl & ~V3D_GCA_CACHE_CTRL_FLUSH);
+		}
+	}
+}
+
+/* Invalidates the (read-only) L2C cache.  This was the L2 cache for
+ * uniforms and instructions on V3D 3.2.
+ */
+static void
+v3d_invalidate_l2c(struct v3d_dev *v3d, int core)
+{
+	if (v3d->ver > 32)
+		return;
+
+	V3D_CORE_WRITE(core, V3D_CTL_L2CACTL,
+		       V3D_L2CACTL_L2CCLR |
+		       V3D_L2CACTL_L2CENA);
+}
+
+/* Invalidates texture L2 cachelines */
+static void
+v3d_flush_l2t(struct v3d_dev *v3d, int core)
+{
+	/* While there is a busy bit (V3D_L2TCACTL_L2TFLS), we don't
+	 * need to wait for completion before dispatching the job --
+	 * L2T accesses will be stalled until the flush has completed.
+	 * However, we do need to make sure we don't try to trigger a
+	 * new flush while the L2_CLEAN queue is trying to
+	 * synchronously clean after a job.
+	 */
+	mutex_lock(&v3d->cache_clean_lock);
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
+		       V3D_L2TCACTL_L2TFLS |
+		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_FLUSH, V3D_L2TCACTL_FLM));
+	mutex_unlock(&v3d->cache_clean_lock);
+}
+
+/* Cleans texture L1 and L2 cachelines (writing back dirty data).
+ *
+ * For cleaning, which happens from the CACHE_CLEAN queue after CSD has
+ * executed, we need to make sure that the clean is done before
+ * signaling job completion.  So, we synchronously wait before
+ * returning, and we make sure that L2 invalidates don't happen in the
+ * meantime to confuse our are-we-done checks.
+ */
+void
+v3d_clean_caches(struct v3d_dev *v3d)
+{
+	struct drm_device *dev = &v3d->drm;
+	int core = 0;
+
+	trace_v3d_cache_clean_begin(dev);
+
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_TMUWCF), 100)) {
+		DRM_ERROR("Timeout waiting for TMU write combiner flush\n");
+	}
+
+	mutex_lock(&v3d->cache_clean_lock);
+	V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
+		       V3D_L2TCACTL_L2TFLS |
+		       V3D_SET_FIELD(V3D_L2TCACTL_FLM_CLEAN, V3D_L2TCACTL_FLM));
+
+	if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+		       V3D_L2TCACTL_L2TFLS), 100)) {
+		DRM_ERROR("Timeout waiting for L2T clean\n");
+	}
+
+	mutex_unlock(&v3d->cache_clean_lock);
+
+	trace_v3d_cache_clean_end(dev);
+}
+
+/* Invalidates the slice caches.  These are read-only caches. */
+static void
+v3d_invalidate_slices(struct v3d_dev *v3d, int core)
+{
+	V3D_CORE_WRITE(core, V3D_CTL_SLCACTL,
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_TVCCS) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_TDCCS) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_UCC) |
+		       V3D_SET_FIELD(0xf, V3D_SLCACTL_ICC));
+}
+
+void
+v3d_invalidate_caches(struct v3d_dev *v3d)
+{
+	/* Invalidate the caches from the outside in.  That way if
+	 * another CL's concurrent use of nearby memory were to pull
+	 * an invalidated cacheline back in, we wouldn't leave stale
+	 * data in the inner cache.
+	 */
+	v3d_flush_l3(v3d);
+	v3d_invalidate_l2c(v3d, 0);
+	v3d_flush_l2t(v3d, 0);
+	v3d_invalidate_slices(v3d, 0);
+}
+
+/* Takes the reservation lock on all the BOs being referenced, so that
+ * at queue submit time we can update the reservations.
+ *
+ * We don't lock the RCL the tile alloc/state BOs, or overflow memory
+ * (all of which are on exec->unref_list).  They're entirely private
+ * to v3d, so we don't attach dma-buf fences to them.
+ */
+static int
+v3d_lock_bo_reservations(struct v3d_job *job,
+			 struct ww_acquire_ctx *acquire_ctx)
+{
+	int i, ret;
+
+	ret = drm_gem_lock_reservations(job->bo, job->bo_count, acquire_ctx);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < job->bo_count; i++) {
+		ret = dma_resv_reserve_fences(job->bo[i]->resv, 1);
+		if (ret)
+			goto fail;
+
+		ret = drm_sched_job_add_implicit_dependencies(&job->base,
+							      job->bo[i], true);
+		if (ret)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
+	return ret;
+}
+
+/**
+ * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects
+ * referenced by the job.
+ * @dev: DRM device
+ * @file_priv: DRM file for this fd
+ * @job: V3D job being set up
+ * @bo_handles: GEM handles
+ * @bo_count: Number of GEM handles passed in
+ *
+ * The command validator needs to reference BOs by their index within
+ * the submitted job's BO list.  This does the validation of the job's
+ * BO list and reference counting for the lifetime of the job.
+ *
+ * Note that this function doesn't need to unreference the BOs on
+ * failure, because that will happen at v3d_exec_cleanup() time.
+ */
+static int
+v3d_lookup_bos(struct drm_device *dev,
+	       struct drm_file *file_priv,
+	       struct v3d_job *job,
+	       u64 bo_handles,
+	       u32 bo_count)
+{
+	job->bo_count = bo_count;
+
+	if (!job->bo_count) {
+		/* See comment on bo_index for why we have to check
+		 * this.
+		 */
+		DRM_DEBUG("Rendering requires BOs\n");
+		return -EINVAL;
+	}
+
+	return drm_gem_objects_lookup(file_priv,
+				      (void __user *)(uintptr_t)bo_handles,
+				      job->bo_count, &job->bo);
+}
+
+static void
+v3d_job_free(struct kref *ref)
+{
+	struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+	int i;
+
+	if (job->bo) {
+		for (i = 0; i < job->bo_count; i++)
+			drm_gem_object_put(job->bo[i]);
+		kvfree(job->bo);
+	}
+
+	dma_fence_put(job->irq_fence);
+	dma_fence_put(job->done_fence);
+
+	if (job->perfmon)
+		v3d_perfmon_put(job->perfmon);
+
+	kfree(job);
+}
+
+static void
+v3d_render_job_free(struct kref *ref)
+{
+	struct v3d_render_job *job = container_of(ref, struct v3d_render_job,
+						  base.refcount);
+	struct v3d_bo *bo, *save;
+
+	list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) {
+		drm_gem_object_put(&bo->base.base);
+	}
+
+	v3d_job_free(ref);
+}
+
+void v3d_job_cleanup(struct v3d_job *job)
+{
+	if (!job)
+		return;
+
+	drm_sched_job_cleanup(&job->base);
+	v3d_job_put(job);
+}
+
+void v3d_job_put(struct v3d_job *job)
+{
+	kref_put(&job->refcount, job->free);
+}
+
+int
+v3d_wait_bo_ioctl(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv)
+{
+	int ret;
+	struct drm_v3d_wait_bo *args = data;
+	ktime_t start = ktime_get();
+	u64 delta_ns;
+	unsigned long timeout_jiffies =
+		nsecs_to_jiffies_timeout(args->timeout_ns);
+
+	if (args->pad != 0)
+		return -EINVAL;
+
+	ret = drm_gem_dma_resv_wait(file_priv, args->handle,
+				    true, timeout_jiffies);
+
+	/* Decrement the user's timeout, in case we got interrupted
+	 * such that the ioctl will be restarted.
+	 */
+	delta_ns = ktime_to_ns(ktime_sub(ktime_get(), start));
+	if (delta_ns < args->timeout_ns)
+		args->timeout_ns -= delta_ns;
+	else
+		args->timeout_ns = 0;
+
+	/* Asked to wait beyond the jiffie/scheduler precision? */
+	if (ret == -ETIME && args->timeout_ns)
+		ret = -EAGAIN;
+
+	return ret;
+}
+
+static int
+v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
+	     void **container, size_t size, void (*free)(struct kref *ref),
+	     u32 in_sync, struct v3d_submit_ext *se, enum v3d_queue queue)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct v3d_job *job;
+	bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC);
+	int ret, i;
+
+	*container = kcalloc(1, size, GFP_KERNEL);
+	if (!*container) {
+		DRM_ERROR("Cannot allocate memory for v3d job.");
+		return -ENOMEM;
+	}
+
+	job = *container;
+	job->v3d = v3d;
+	job->free = free;
+
+	ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
+				 v3d_priv);
+	if (ret)
+		goto fail;
+
+	if (has_multisync) {
+		if (se->in_sync_count && se->wait_stage == queue) {
+			struct drm_v3d_sem __user *handle = u64_to_user_ptr(se->in_syncs);
+
+			for (i = 0; i < se->in_sync_count; i++) {
+				struct drm_v3d_sem in;
+
+				if (copy_from_user(&in, handle++, sizeof(in))) {
+					ret = -EFAULT;
+					DRM_DEBUG("Failed to copy wait dep handle.\n");
+					goto fail_deps;
+				}
+				ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in.handle, 0);
+
+				// TODO: Investigate why this was filtered out for the IOCTL.
+				if (ret && ret != -ENOENT)
+					goto fail_deps;
+			}
+		}
+	} else {
+		ret = drm_sched_job_add_syncobj_dependency(&job->base, file_priv, in_sync, 0);
+
+		// TODO: Investigate why this was filtered out for the IOCTL.
+		if (ret && ret != -ENOENT)
+			goto fail_deps;
+	}
+
+	kref_init(&job->refcount);
+
+	return 0;
+
+fail_deps:
+	drm_sched_job_cleanup(&job->base);
+fail:
+	kfree(*container);
+	*container = NULL;
+
+	return ret;
+}
+
+static void
+v3d_push_job(struct v3d_job *job)
+{
+	drm_sched_job_arm(&job->base);
+
+	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+	/* put by scheduler job completion */
+	kref_get(&job->refcount);
+
+	drm_sched_entity_push_job(&job->base);
+}
+
+static void
+v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
+					 struct v3d_job *job,
+					 struct ww_acquire_ctx *acquire_ctx,
+					 u32 out_sync,
+					 struct v3d_submit_ext *se,
+					 struct dma_fence *done_fence)
+{
+	struct drm_syncobj *sync_out;
+	bool has_multisync = se && (se->flags & DRM_V3D_EXT_ID_MULTI_SYNC);
+	int i;
+
+	for (i = 0; i < job->bo_count; i++) {
+		/* XXX: Use shared fences for read-only objects. */
+		dma_resv_add_fence(job->bo[i]->resv, job->done_fence,
+				   DMA_RESV_USAGE_WRITE);
+	}
+
+	drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
+
+	/* Update the return sync object for the job */
+	/* If it only supports a single signal semaphore*/
+	if (!has_multisync) {
+		sync_out = drm_syncobj_find(file_priv, out_sync);
+		if (sync_out) {
+			drm_syncobj_replace_fence(sync_out, done_fence);
+			drm_syncobj_put(sync_out);
+		}
+		return;
+	}
+
+	/* If multiple semaphores extension is supported */
+	if (se->out_sync_count) {
+		for (i = 0; i < se->out_sync_count; i++) {
+			drm_syncobj_replace_fence(se->out_syncs[i].syncobj,
+						  done_fence);
+			drm_syncobj_put(se->out_syncs[i].syncobj);
+		}
+		kvfree(se->out_syncs);
+	}
+}
+
+static void
+v3d_put_multisync_post_deps(struct v3d_submit_ext *se)
+{
+	unsigned int i;
+
+	if (!(se && se->out_sync_count))
+		return;
+
+	for (i = 0; i < se->out_sync_count; i++)
+		drm_syncobj_put(se->out_syncs[i].syncobj);
+	kvfree(se->out_syncs);
+}
+
+static int
+v3d_get_multisync_post_deps(struct drm_file *file_priv,
+			    struct v3d_submit_ext *se,
+			    u32 count, u64 handles)
+{
+	struct drm_v3d_sem __user *post_deps;
+	int i, ret;
+
+	if (!count)
+		return 0;
+
+	se->out_syncs = (struct v3d_submit_outsync *)
+			kvmalloc_array(count,
+				       sizeof(struct v3d_submit_outsync),
+				       GFP_KERNEL);
+	if (!se->out_syncs)
+		return -ENOMEM;
+
+	post_deps = u64_to_user_ptr(handles);
+
+	for (i = 0; i < count; i++) {
+		struct drm_v3d_sem out;
+
+		if (copy_from_user(&out, post_deps++, sizeof(out))) {
+			ret = -EFAULT;
+			DRM_DEBUG("Failed to copy post dep handles\n");
+			goto fail;
+		}
+
+		se->out_syncs[i].syncobj = drm_syncobj_find(file_priv,
+							    out.handle);
+		if (!se->out_syncs[i].syncobj) {
+			ret = -EINVAL;
+			goto fail;
+		}
+	}
+	se->out_sync_count = count;
+
+	return 0;
+
+fail:
+	for (i--; i >= 0; i--)
+		drm_syncobj_put(se->out_syncs[i].syncobj);
+	kvfree(se->out_syncs);
+
+	return ret;
+}
+
+/* Get data for multiple binary semaphores synchronization. Parse syncobj
+ * to be signaled when job completes (out_sync).
+ */
+static int
+v3d_get_multisync_submit_deps(struct drm_file *file_priv,
+			      struct drm_v3d_extension __user *ext,
+			      void *data)
+{
+	struct drm_v3d_multi_sync multisync;
+	struct v3d_submit_ext *se = data;
+	int ret;
+
+	if (copy_from_user(&multisync, ext, sizeof(multisync)))
+		return -EFAULT;
+
+	if (multisync.pad)
+		return -EINVAL;
+
+	ret = v3d_get_multisync_post_deps(file_priv, data, multisync.out_sync_count,
+					  multisync.out_syncs);
+	if (ret)
+		return ret;
+
+	se->in_sync_count = multisync.in_sync_count;
+	se->in_syncs = multisync.in_syncs;
+	se->flags |= DRM_V3D_EXT_ID_MULTI_SYNC;
+	se->wait_stage = multisync.wait_stage;
+
+	return 0;
+}
+
+/* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data
+ * according to the extension id (name).
+ */
+static int
+v3d_get_extensions(struct drm_file *file_priv,
+		   u64 ext_handles,
+		   void *data)
+{
+	struct drm_v3d_extension __user *user_ext;
+	int ret;
+
+	user_ext = u64_to_user_ptr(ext_handles);
+	while (user_ext) {
+		struct drm_v3d_extension ext;
+
+		if (copy_from_user(&ext, user_ext, sizeof(ext))) {
+			DRM_DEBUG("Failed to copy submit extension\n");
+			return -EFAULT;
+		}
+
+		switch (ext.id) {
+		case DRM_V3D_EXT_ID_MULTI_SYNC:
+			ret = v3d_get_multisync_submit_deps(file_priv, user_ext, data);
+			if (ret)
+				return ret;
+			break;
+		default:
+			DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id);
+			return -EINVAL;
+		}
+
+		user_ext = u64_to_user_ptr(ext.next);
+	}
+
+	return 0;
+}
+
+/**
+ * v3d_submit_cl_ioctl() - Submits a job (frame) to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * This is the main entrypoint for userspace to submit a 3D frame to
+ * the GPU.  Userspace provides the binner command list (if
+ * applicable), and the kernel sets up the render command list to draw
+ * to the framebuffer described in the ioctl, using the command lists
+ * that the 3D engine's binner will produce.
+ */
+int
+v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_submit_cl *args = data;
+	struct v3d_submit_ext se = {0};
+	struct v3d_bin_job *bin = NULL;
+	struct v3d_render_job *render = NULL;
+	struct v3d_job *clean_job = NULL;
+	struct v3d_job *last_job;
+	struct ww_acquire_ctx acquire_ctx;
+	int ret = 0;
+
+	trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
+
+	if (args->pad)
+		return -EINVAL;
+
+	if (args->flags &&
+	    args->flags & ~(DRM_V3D_SUBMIT_CL_FLUSH_CACHE |
+			    DRM_V3D_SUBMIT_EXTENSION)) {
+		DRM_INFO("invalid flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	if (args->flags & DRM_V3D_SUBMIT_EXTENSION) {
+		ret = v3d_get_extensions(file_priv, args->extensions, &se);
+		if (ret) {
+			DRM_DEBUG("Failed to get extensions.\n");
+			return ret;
+		}
+	}
+
+	ret = v3d_job_init(v3d, file_priv, (void *)&render, sizeof(*render),
+			   v3d_render_job_free, args->in_sync_rcl, &se, V3D_RENDER);
+	if (ret)
+		goto fail;
+
+	render->start = args->rcl_start;
+	render->end = args->rcl_end;
+	INIT_LIST_HEAD(&render->unref_list);
+
+	if (args->bcl_start != args->bcl_end) {
+		ret = v3d_job_init(v3d, file_priv, (void *)&bin, sizeof(*bin),
+				   v3d_job_free, args->in_sync_bcl, &se, V3D_BIN);
+		if (ret)
+			goto fail;
+
+		bin->start = args->bcl_start;
+		bin->end = args->bcl_end;
+		bin->qma = args->qma;
+		bin->qms = args->qms;
+		bin->qts = args->qts;
+		bin->render = render;
+	}
+
+	if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) {
+		ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job),
+				   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
+		if (ret)
+			goto fail;
+
+		last_job = clean_job;
+	} else {
+		last_job = &render->base;
+	}
+
+	ret = v3d_lookup_bos(dev, file_priv, last_job,
+			     args->bo_handles, args->bo_handle_count);
+	if (ret)
+		goto fail;
+
+	ret = v3d_lock_bo_reservations(last_job, &acquire_ctx);
+	if (ret)
+		goto fail;
+
+	if (args->perfmon_id) {
+		render->base.perfmon = v3d_perfmon_find(v3d_priv,
+							args->perfmon_id);
+
+		if (!render->base.perfmon) {
+			ret = -ENOENT;
+			goto fail_perfmon;
+		}
+	}
+
+	mutex_lock(&v3d->sched_lock);
+	if (bin) {
+		bin->base.perfmon = render->base.perfmon;
+		v3d_perfmon_get(bin->base.perfmon);
+		v3d_push_job(&bin->base);
+
+		ret = drm_sched_job_add_dependency(&render->base.base,
+						   dma_fence_get(bin->base.done_fence));
+		if (ret)
+			goto fail_unreserve;
+	}
+
+	v3d_push_job(&render->base);
+
+	if (clean_job) {
+		struct dma_fence *render_fence =
+			dma_fence_get(render->base.done_fence);
+		ret = drm_sched_job_add_dependency(&clean_job->base,
+						   render_fence);
+		if (ret)
+			goto fail_unreserve;
+		clean_job->perfmon = render->base.perfmon;
+		v3d_perfmon_get(clean_job->perfmon);
+		v3d_push_job(clean_job);
+	}
+
+	mutex_unlock(&v3d->sched_lock);
+
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 last_job,
+						 &acquire_ctx,
+						 args->out_sync,
+						 &se,
+						 last_job->done_fence);
+
+	if (bin)
+		v3d_job_put(&bin->base);
+	v3d_job_put(&render->base);
+	if (clean_job)
+		v3d_job_put(clean_job);
+
+	return 0;
+
+fail_unreserve:
+	mutex_unlock(&v3d->sched_lock);
+fail_perfmon:
+	drm_gem_unlock_reservations(last_job->bo,
+				    last_job->bo_count, &acquire_ctx);
+fail:
+	v3d_job_cleanup((void *)bin);
+	v3d_job_cleanup((void *)render);
+	v3d_job_cleanup(clean_job);
+	v3d_put_multisync_post_deps(&se);
+
+	return ret;
+}
+
+/**
+ * v3d_submit_tfu_ioctl() - Submits a TFU (texture formatting) job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace provides the register setup for the TFU, which we don't
+ * need to validate since the TFU is behind the MMU.
+ */
+int
+v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct drm_v3d_submit_tfu *args = data;
+	struct v3d_submit_ext se = {0};
+	struct v3d_tfu_job *job = NULL;
+	struct ww_acquire_ctx acquire_ctx;
+	int ret = 0;
+
+	trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia);
+
+	if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) {
+		DRM_DEBUG("invalid flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	if (args->flags & DRM_V3D_SUBMIT_EXTENSION) {
+		ret = v3d_get_extensions(file_priv, args->extensions, &se);
+		if (ret) {
+			DRM_DEBUG("Failed to get extensions.\n");
+			return ret;
+		}
+	}
+
+	ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job),
+			   v3d_job_free, args->in_sync, &se, V3D_TFU);
+	if (ret)
+		goto fail;
+
+	job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
+			       sizeof(*job->base.bo), GFP_KERNEL);
+	if (!job->base.bo) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	job->args = *args;
+
+	for (job->base.bo_count = 0;
+	     job->base.bo_count < ARRAY_SIZE(args->bo_handles);
+	     job->base.bo_count++) {
+		struct drm_gem_object *bo;
+
+		if (!args->bo_handles[job->base.bo_count])
+			break;
+
+		bo = drm_gem_object_lookup(file_priv, args->bo_handles[job->base.bo_count]);
+		if (!bo) {
+			DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
+				  job->base.bo_count,
+				  args->bo_handles[job->base.bo_count]);
+			ret = -ENOENT;
+			goto fail;
+		}
+		job->base.bo[job->base.bo_count] = bo;
+	}
+
+	ret = v3d_lock_bo_reservations(&job->base, &acquire_ctx);
+	if (ret)
+		goto fail;
+
+	mutex_lock(&v3d->sched_lock);
+	v3d_push_job(&job->base);
+	mutex_unlock(&v3d->sched_lock);
+
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 &job->base, &acquire_ctx,
+						 args->out_sync,
+						 &se,
+						 job->base.done_fence);
+
+	v3d_job_put(&job->base);
+
+	return 0;
+
+fail:
+	v3d_job_cleanup((void *)job);
+	v3d_put_multisync_post_deps(&se);
+
+	return ret;
+}
+
+/**
+ * v3d_submit_csd_ioctl() - Submits a CSD (texture formatting) job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace provides the register setup for the CSD, which we don't
+ * need to validate since the CSD is behind the MMU.
+ */
+int
+v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_submit_csd *args = data;
+	struct v3d_submit_ext se = {0};
+	struct v3d_csd_job *job = NULL;
+	struct v3d_job *clean_job = NULL;
+	struct ww_acquire_ctx acquire_ctx;
+	int ret;
+
+	trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]);
+
+	if (args->pad)
+		return -EINVAL;
+
+	if (!v3d_has_csd(v3d)) {
+		DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n");
+		return -EINVAL;
+	}
+
+	if (args->flags && !(args->flags & DRM_V3D_SUBMIT_EXTENSION)) {
+		DRM_INFO("invalid flags: %d\n", args->flags);
+		return -EINVAL;
+	}
+
+	if (args->flags & DRM_V3D_SUBMIT_EXTENSION) {
+		ret = v3d_get_extensions(file_priv, args->extensions, &se);
+		if (ret) {
+			DRM_DEBUG("Failed to get extensions.\n");
+			return ret;
+		}
+	}
+
+	ret = v3d_job_init(v3d, file_priv, (void *)&job, sizeof(*job),
+			   v3d_job_free, args->in_sync, &se, V3D_CSD);
+	if (ret)
+		goto fail;
+
+	ret = v3d_job_init(v3d, file_priv, (void *)&clean_job, sizeof(*clean_job),
+			   v3d_job_free, 0, NULL, V3D_CACHE_CLEAN);
+	if (ret)
+		goto fail;
+
+	job->args = *args;
+
+	ret = v3d_lookup_bos(dev, file_priv, clean_job,
+			     args->bo_handles, args->bo_handle_count);
+	if (ret)
+		goto fail;
+
+	ret = v3d_lock_bo_reservations(clean_job, &acquire_ctx);
+	if (ret)
+		goto fail;
+
+	if (args->perfmon_id) {
+		job->base.perfmon = v3d_perfmon_find(v3d_priv,
+						     args->perfmon_id);
+		if (!job->base.perfmon) {
+			ret = -ENOENT;
+			goto fail_perfmon;
+		}
+	}
+
+	mutex_lock(&v3d->sched_lock);
+	v3d_push_job(&job->base);
+
+	ret = drm_sched_job_add_dependency(&clean_job->base,
+					   dma_fence_get(job->base.done_fence));
+	if (ret)
+		goto fail_unreserve;
+
+	v3d_push_job(clean_job);
+	mutex_unlock(&v3d->sched_lock);
+
+	v3d_attach_fences_and_unlock_reservation(file_priv,
+						 clean_job,
+						 &acquire_ctx,
+						 args->out_sync,
+						 &se,
+						 clean_job->done_fence);
+
+	v3d_job_put(&job->base);
+	v3d_job_put(clean_job);
+
+	return 0;
+
+fail_unreserve:
+	mutex_unlock(&v3d->sched_lock);
+fail_perfmon:
+	drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count,
+				    &acquire_ctx);
+fail:
+	v3d_job_cleanup((void *)job);
+	v3d_job_cleanup(clean_job);
+	v3d_put_multisync_post_deps(&se);
+
+	return ret;
+}
+
+int
+v3d_gem_init(struct drm_device *dev)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	u32 pt_size = 4096 * 1024;
+	int ret, i;
+
+	for (i = 0; i < V3D_MAX_QUEUES; i++)
+		v3d->queue[i].fence_context = dma_fence_context_alloc(1);
+
+	spin_lock_init(&v3d->mm_lock);
+	spin_lock_init(&v3d->job_lock);
+	ret = drmm_mutex_init(dev, &v3d->bo_lock);
+	if (ret)
+		return ret;
+	ret = drmm_mutex_init(dev, &v3d->reset_lock);
+	if (ret)
+		return ret;
+	ret = drmm_mutex_init(dev, &v3d->sched_lock);
+	if (ret)
+		return ret;
+	ret = drmm_mutex_init(dev, &v3d->cache_clean_lock);
+	if (ret)
+		return ret;
+
+	/* Note: We don't allocate address 0.  Various bits of HW
+	 * treat 0 as special, such as the occlusion query counters
+	 * where 0 means "disabled".
+	 */
+	drm_mm_init(&v3d->mm, 1, pt_size / sizeof(u32) - 1);
+
+	v3d->pt = dma_alloc_wc(v3d->drm.dev, pt_size,
+			       &v3d->pt_paddr,
+			       GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!v3d->pt) {
+		drm_mm_takedown(&v3d->mm);
+		dev_err(v3d->drm.dev,
+			"Failed to allocate page tables. Please ensure you have DMA enabled.\n");
+		return -ENOMEM;
+	}
+
+	v3d_init_hw_state(v3d);
+	v3d_mmu_set_page_table(v3d);
+
+	ret = v3d_sched_init(v3d);
+	if (ret) {
+		drm_mm_takedown(&v3d->mm);
+		dma_free_coherent(v3d->drm.dev, 4096 * 1024, (void *)v3d->pt,
+				  v3d->pt_paddr);
+	}
+
+	return 0;
+}
+
+void
+v3d_gem_destroy(struct drm_device *dev)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+
+	v3d_sched_fini(v3d);
+
+	/* Waiting for jobs to finish would need to be done before
+	 * unregistering V3D.
+	 */
+	WARN_ON(v3d->bin_job);
+	WARN_ON(v3d->render_job);
+
+	drm_mm_takedown(&v3d->mm);
+
+	dma_free_coherent(v3d->drm.dev, 4096 * 1024, (void *)v3d->pt,
+			  v3d->pt_paddr);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
new file mode 100644
index 0000000000..e714d5318f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2014-2018 Broadcom */
+
+/**
+ * DOC: Interrupt management for the V3D engine
+ *
+ * When we take a bin, render, TFU done, or CSD done interrupt, we
+ * need to signal the fence for that job so that the scheduler can
+ * queue up the next one and unblock any waiters.
+ *
+ * When we take the binner out of memory interrupt, we need to
+ * allocate some new memory and pass it to the binner so that the
+ * current job can make progress.
+ */
+
+#include <linux/platform_device.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+#include "v3d_trace.h"
+
+#define V3D_CORE_IRQS ((u32)(V3D_INT_OUTOMEM |	\
+			     V3D_INT_FLDONE |	\
+			     V3D_INT_FRDONE |	\
+			     V3D_INT_CSDDONE |	\
+			     V3D_INT_GMPV))
+
+#define V3D_HUB_IRQS ((u32)(V3D_HUB_INT_MMU_WRV |	\
+			    V3D_HUB_INT_MMU_PTI |	\
+			    V3D_HUB_INT_MMU_CAP |	\
+			    V3D_HUB_INT_TFUC))
+
+static irqreturn_t
+v3d_hub_irq(int irq, void *arg);
+
+static void
+v3d_overflow_mem_work(struct work_struct *work)
+{
+	struct v3d_dev *v3d =
+		container_of(work, struct v3d_dev, overflow_mem_work);
+	struct drm_device *dev = &v3d->drm;
+	struct v3d_bo *bo = v3d_bo_create(dev, NULL /* XXX: GMP */, 256 * 1024);
+	struct drm_gem_object *obj;
+	unsigned long irqflags;
+
+	if (IS_ERR(bo)) {
+		DRM_ERROR("Couldn't allocate binner overflow mem\n");
+		return;
+	}
+	obj = &bo->base.base;
+
+	/* We lost a race, and our work task came in after the bin job
+	 * completed and exited.  This can happen because the HW
+	 * signals OOM before it's fully OOM, so the binner might just
+	 * barely complete.
+	 *
+	 * If we lose the race and our work task comes in after a new
+	 * bin job got scheduled, that's fine.  We'll just give them
+	 * some binner pool anyway.
+	 */
+	spin_lock_irqsave(&v3d->job_lock, irqflags);
+	if (!v3d->bin_job) {
+		spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+		goto out;
+	}
+
+	drm_gem_object_get(obj);
+	list_add_tail(&bo->unref_head, &v3d->bin_job->render->unref_list);
+	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+
+	V3D_CORE_WRITE(0, V3D_PTB_BPOA, bo->node.start << PAGE_SHIFT);
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, obj->size);
+
+out:
+	drm_gem_object_put(obj);
+}
+
+static irqreturn_t
+v3d_irq(int irq, void *arg)
+{
+	struct v3d_dev *v3d = arg;
+	u32 intsts;
+	irqreturn_t status = IRQ_NONE;
+
+	intsts = V3D_CORE_READ(0, V3D_CTL_INT_STS);
+
+	/* Acknowledge the interrupts we're handling here. */
+	V3D_CORE_WRITE(0, V3D_CTL_INT_CLR, intsts);
+
+	if (intsts & V3D_INT_OUTOMEM) {
+		/* Note that the OOM status is edge signaled, so the
+		 * interrupt won't happen again until the we actually
+		 * add more memory.  Also, as of V3D 4.1, FLDONE won't
+		 * be reported until any OOM state has been cleared.
+		 */
+		schedule_work(&v3d->overflow_mem_work);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & V3D_INT_FLDONE) {
+		struct v3d_fence *fence =
+			to_v3d_fence(v3d->bin_job->base.irq_fence);
+
+		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
+		dma_fence_signal(&fence->base);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & V3D_INT_FRDONE) {
+		struct v3d_fence *fence =
+			to_v3d_fence(v3d->render_job->base.irq_fence);
+
+		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
+		dma_fence_signal(&fence->base);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & V3D_INT_CSDDONE) {
+		struct v3d_fence *fence =
+			to_v3d_fence(v3d->csd_job->base.irq_fence);
+
+		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
+		dma_fence_signal(&fence->base);
+		status = IRQ_HANDLED;
+	}
+
+	/* We shouldn't be triggering these if we have GMP in
+	 * always-allowed mode.
+	 */
+	if (intsts & V3D_INT_GMPV)
+		dev_err(v3d->drm.dev, "GMP violation\n");
+
+	/* V3D 4.2 wires the hub and core IRQs together, so if we &
+	 * didn't see the common one then check hub for MMU IRQs.
+	 */
+	if (v3d->single_irq_line && status == IRQ_NONE)
+		return v3d_hub_irq(irq, arg);
+
+	return status;
+}
+
+static irqreturn_t
+v3d_hub_irq(int irq, void *arg)
+{
+	struct v3d_dev *v3d = arg;
+	u32 intsts;
+	irqreturn_t status = IRQ_NONE;
+
+	intsts = V3D_READ(V3D_HUB_INT_STS);
+
+	/* Acknowledge the interrupts we're handling here. */
+	V3D_WRITE(V3D_HUB_INT_CLR, intsts);
+
+	if (intsts & V3D_HUB_INT_TFUC) {
+		struct v3d_fence *fence =
+			to_v3d_fence(v3d->tfu_job->base.irq_fence);
+
+		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
+		dma_fence_signal(&fence->base);
+		status = IRQ_HANDLED;
+	}
+
+	if (intsts & (V3D_HUB_INT_MMU_WRV |
+		      V3D_HUB_INT_MMU_PTI |
+		      V3D_HUB_INT_MMU_CAP)) {
+		u32 axi_id = V3D_READ(V3D_MMU_VIO_ID);
+		u64 vio_addr = ((u64)V3D_READ(V3D_MMU_VIO_ADDR) <<
+				(v3d->va_width - 32));
+		static const char *const v3d41_axi_ids[] = {
+			"L2T",
+			"PTB",
+			"PSE",
+			"TLB",
+			"CLE",
+			"TFU",
+			"MMU",
+			"GMP",
+		};
+		const char *client = "?";
+
+		V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL));
+
+		if (v3d->ver >= 41) {
+			axi_id = axi_id >> 5;
+			if (axi_id < ARRAY_SIZE(v3d41_axi_ids))
+				client = v3d41_axi_ids[axi_id];
+		}
+
+		dev_err(v3d->drm.dev, "MMU error from client %s (%d) at 0x%llx%s%s%s\n",
+			client, axi_id, (long long)vio_addr,
+			((intsts & V3D_HUB_INT_MMU_WRV) ?
+			 ", write violation" : ""),
+			((intsts & V3D_HUB_INT_MMU_PTI) ?
+			 ", pte invalid" : ""),
+			((intsts & V3D_HUB_INT_MMU_CAP) ?
+			 ", cap exceeded" : ""));
+		status = IRQ_HANDLED;
+	}
+
+	return status;
+}
+
+int
+v3d_irq_init(struct v3d_dev *v3d)
+{
+	int irq1, ret, core;
+
+	INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work);
+
+	/* Clear any pending interrupts someone might have left around
+	 * for us.
+	 */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+
+	irq1 = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
+	if (irq1 == -EPROBE_DEFER)
+		return irq1;
+	if (irq1 > 0) {
+		ret = devm_request_irq(v3d->drm.dev, irq1,
+				       v3d_irq, IRQF_SHARED,
+				       "v3d_core0", v3d);
+		if (ret)
+			goto fail;
+		ret = devm_request_irq(v3d->drm.dev,
+				       platform_get_irq(v3d_to_pdev(v3d), 0),
+				       v3d_hub_irq, IRQF_SHARED,
+				       "v3d_hub", v3d);
+		if (ret)
+			goto fail;
+	} else {
+		v3d->single_irq_line = true;
+
+		ret = devm_request_irq(v3d->drm.dev,
+				       platform_get_irq(v3d_to_pdev(v3d), 0),
+				       v3d_irq, IRQF_SHARED,
+				       "v3d", v3d);
+		if (ret)
+			goto fail;
+	}
+
+	v3d_irq_enable(v3d);
+	return 0;
+
+fail:
+	if (ret != -EPROBE_DEFER)
+		dev_err(v3d->drm.dev, "IRQ setup failed: %d\n", ret);
+	return ret;
+}
+
+void
+v3d_irq_enable(struct v3d_dev *v3d)
+{
+	int core;
+
+	/* Enable our set of interrupts, masking out any others. */
+	for (core = 0; core < v3d->cores; core++) {
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~V3D_CORE_IRQS);
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_CLR, V3D_CORE_IRQS);
+	}
+
+	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~V3D_HUB_IRQS);
+	V3D_WRITE(V3D_HUB_INT_MSK_CLR, V3D_HUB_IRQS);
+}
+
+void
+v3d_irq_disable(struct v3d_dev *v3d)
+{
+	int core;
+
+	/* Disable all interrupts. */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~0);
+	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~0);
+
+	/* Clear any pending interrupts we might have left. */
+	for (core = 0; core < v3d->cores; core++)
+		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS);
+	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS);
+
+	cancel_work_sync(&v3d->overflow_mem_work);
+}
+
+/** Reinitializes interrupt registers when a GPU reset is performed. */
+void v3d_irq_reset(struct v3d_dev *v3d)
+{
+	v3d_irq_enable(v3d);
+}
diff --git a/drivers/gpu/drm/v3d/v3d_mmu.c b/drivers/gpu/drm/v3d/v3d_mmu.c
new file mode 100644
index 0000000000..5a45353290
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_mmu.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D MMU
+ *
+ * The V3D 3.x hardware (compared to VC4) now includes an MMU.  It has
+ * a single level of page tables for the V3D's 4GB address space to
+ * map to AXI bus addresses, thus it could need up to 4MB of
+ * physically contiguous memory to store the PTEs.
+ *
+ * Because the 4MB of contiguous memory for page tables is precious,
+ * and switching between them is expensive, we load all BOs into the
+ * same 4GB address space.
+ *
+ * To protect clients from each other, we should use the GMP to
+ * quickly mask out (at 128kb granularity) what pages are available to
+ * each client.  This is not yet implemented.
+ */
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define V3D_MMU_PAGE_SHIFT 12
+
+/* Note: All PTEs for the 1MB superpage must be filled with the
+ * superpage bit set.
+ */
+#define V3D_PTE_SUPERPAGE BIT(31)
+#define V3D_PTE_WRITEABLE BIT(29)
+#define V3D_PTE_VALID BIT(28)
+
+static int v3d_mmu_flush_all(struct v3d_dev *v3d)
+{
+	int ret;
+
+	/* Make sure that another flush isn't already running when we
+	 * start this one.
+	 */
+	ret = wait_for(!(V3D_READ(V3D_MMU_CTL) &
+			 V3D_MMU_CTL_TLB_CLEARING), 100);
+	if (ret)
+		dev_err(v3d->drm.dev, "TLB clear wait idle pre-wait failed\n");
+
+	V3D_WRITE(V3D_MMU_CTL, V3D_READ(V3D_MMU_CTL) |
+		  V3D_MMU_CTL_TLB_CLEAR);
+
+	V3D_WRITE(V3D_MMUC_CONTROL,
+		  V3D_MMUC_CONTROL_FLUSH |
+		  V3D_MMUC_CONTROL_ENABLE);
+
+	ret = wait_for(!(V3D_READ(V3D_MMU_CTL) &
+			 V3D_MMU_CTL_TLB_CLEARING), 100);
+	if (ret) {
+		dev_err(v3d->drm.dev, "TLB clear wait idle failed\n");
+		return ret;
+	}
+
+	ret = wait_for(!(V3D_READ(V3D_MMUC_CONTROL) &
+			 V3D_MMUC_CONTROL_FLUSHING), 100);
+	if (ret)
+		dev_err(v3d->drm.dev, "MMUC flush wait idle failed\n");
+
+	return ret;
+}
+
+int v3d_mmu_set_page_table(struct v3d_dev *v3d)
+{
+	V3D_WRITE(V3D_MMU_PT_PA_BASE, v3d->pt_paddr >> V3D_MMU_PAGE_SHIFT);
+	V3D_WRITE(V3D_MMU_CTL,
+		  V3D_MMU_CTL_ENABLE |
+		  V3D_MMU_CTL_PT_INVALID_ENABLE |
+		  V3D_MMU_CTL_PT_INVALID_ABORT |
+		  V3D_MMU_CTL_PT_INVALID_INT |
+		  V3D_MMU_CTL_WRITE_VIOLATION_ABORT |
+		  V3D_MMU_CTL_WRITE_VIOLATION_INT |
+		  V3D_MMU_CTL_CAP_EXCEEDED_ABORT |
+		  V3D_MMU_CTL_CAP_EXCEEDED_INT);
+	V3D_WRITE(V3D_MMU_ILLEGAL_ADDR,
+		  (v3d->mmu_scratch_paddr >> V3D_MMU_PAGE_SHIFT) |
+		  V3D_MMU_ILLEGAL_ADDR_ENABLE);
+	V3D_WRITE(V3D_MMUC_CONTROL, V3D_MMUC_CONTROL_ENABLE);
+
+	return v3d_mmu_flush_all(v3d);
+}
+
+void v3d_mmu_insert_ptes(struct v3d_bo *bo)
+{
+	struct drm_gem_shmem_object *shmem_obj = &bo->base;
+	struct v3d_dev *v3d = to_v3d_dev(shmem_obj->base.dev);
+	u32 page = bo->node.start;
+	u32 page_prot = V3D_PTE_WRITEABLE | V3D_PTE_VALID;
+	struct sg_dma_page_iter dma_iter;
+
+	for_each_sgtable_dma_page(shmem_obj->sgt, &dma_iter, 0) {
+		dma_addr_t dma_addr = sg_page_iter_dma_address(&dma_iter);
+		u32 page_address = dma_addr >> V3D_MMU_PAGE_SHIFT;
+		u32 pte = page_prot | page_address;
+		u32 i;
+
+		BUG_ON(page_address + (PAGE_SIZE >> V3D_MMU_PAGE_SHIFT) >=
+		       BIT(24));
+		for (i = 0; i < PAGE_SIZE >> V3D_MMU_PAGE_SHIFT; i++)
+			v3d->pt[page++] = pte + i;
+	}
+
+	WARN_ON_ONCE(page - bo->node.start !=
+		     shmem_obj->base.size >> V3D_MMU_PAGE_SHIFT);
+
+	if (v3d_mmu_flush_all(v3d))
+		dev_err(v3d->drm.dev, "MMU flush timeout\n");
+}
+
+void v3d_mmu_remove_ptes(struct v3d_bo *bo)
+{
+	struct v3d_dev *v3d = to_v3d_dev(bo->base.base.dev);
+	u32 npages = bo->base.base.size >> V3D_MMU_PAGE_SHIFT;
+	u32 page;
+
+	for (page = bo->node.start; page < bo->node.start + npages; page++)
+		v3d->pt[page] = 0;
+
+	if (v3d_mmu_flush_all(v3d))
+		dev_err(v3d->drm.dev, "MMU flush timeout\n");
+}
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
new file mode 100644
index 0000000000..e1be7368b8
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Raspberry Pi
+ */
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+
+#define V3D_PERFMONID_MIN	1
+#define V3D_PERFMONID_MAX	U32_MAX
+
+void v3d_perfmon_get(struct v3d_perfmon *perfmon)
+{
+	if (perfmon)
+		refcount_inc(&perfmon->refcnt);
+}
+
+void v3d_perfmon_put(struct v3d_perfmon *perfmon)
+{
+	if (perfmon && refcount_dec_and_test(&perfmon->refcnt)) {
+		mutex_destroy(&perfmon->lock);
+		kfree(perfmon);
+	}
+}
+
+void v3d_perfmon_start(struct v3d_dev *v3d, struct v3d_perfmon *perfmon)
+{
+	unsigned int i;
+	u32 mask;
+	u8 ncounters;
+
+	if (WARN_ON_ONCE(!perfmon || v3d->active_perfmon))
+		return;
+
+	ncounters = perfmon->ncounters;
+	mask = GENMASK(ncounters - 1, 0);
+
+	for (i = 0; i < ncounters; i++) {
+		u32 source = i / 4;
+		u32 channel = V3D_SET_FIELD(perfmon->counters[i], V3D_PCTR_S0);
+
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S1);
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S2);
+		i++;
+		channel |= V3D_SET_FIELD(i < ncounters ? perfmon->counters[i] : 0,
+					 V3D_PCTR_S3);
+		V3D_CORE_WRITE(0, V3D_V4_PCTR_0_SRC_X(source), channel);
+	}
+
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_CLR, mask);
+	V3D_CORE_WRITE(0, V3D_PCTR_0_OVERFLOW, mask);
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_EN, mask);
+
+	v3d->active_perfmon = perfmon;
+}
+
+void v3d_perfmon_stop(struct v3d_dev *v3d, struct v3d_perfmon *perfmon,
+		      bool capture)
+{
+	unsigned int i;
+
+	if (!perfmon || !v3d->active_perfmon)
+		return;
+
+	mutex_lock(&perfmon->lock);
+	if (perfmon != v3d->active_perfmon) {
+		mutex_unlock(&perfmon->lock);
+		return;
+	}
+
+	if (capture)
+		for (i = 0; i < perfmon->ncounters; i++)
+			perfmon->values[i] += V3D_CORE_READ(0, V3D_PCTR_0_PCTRX(i));
+
+	V3D_CORE_WRITE(0, V3D_V4_PCTR_0_EN, 0);
+
+	v3d->active_perfmon = NULL;
+	mutex_unlock(&perfmon->lock);
+}
+
+struct v3d_perfmon *v3d_perfmon_find(struct v3d_file_priv *v3d_priv, int id)
+{
+	struct v3d_perfmon *perfmon;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_find(&v3d_priv->perfmon.idr, id);
+	v3d_perfmon_get(perfmon);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	return perfmon;
+}
+
+void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv)
+{
+	mutex_init(&v3d_priv->perfmon.lock);
+	idr_init_base(&v3d_priv->perfmon.idr, 1);
+}
+
+static int v3d_perfmon_idr_del(int id, void *elem, void *data)
+{
+	struct v3d_perfmon *perfmon = elem;
+
+	v3d_perfmon_put(perfmon);
+
+	return 0;
+}
+
+void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv)
+{
+	mutex_lock(&v3d_priv->perfmon.lock);
+	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, NULL);
+	idr_destroy(&v3d_priv->perfmon.idr);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+	mutex_destroy(&v3d_priv->perfmon.lock);
+}
+
+int v3d_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_create *req = data;
+	struct v3d_perfmon *perfmon;
+	unsigned int i;
+	int ret;
+
+	/* Number of monitored counters cannot exceed HW limits. */
+	if (req->ncounters > DRM_V3D_MAX_PERF_COUNTERS ||
+	    !req->ncounters)
+		return -EINVAL;
+
+	/* Make sure all counters are valid. */
+	for (i = 0; i < req->ncounters; i++) {
+		if (req->counters[i] >= V3D_PERFCNT_NUM)
+			return -EINVAL;
+	}
+
+	perfmon = kzalloc(struct_size(perfmon, values, req->ncounters),
+			  GFP_KERNEL);
+	if (!perfmon)
+		return -ENOMEM;
+
+	for (i = 0; i < req->ncounters; i++)
+		perfmon->counters[i] = req->counters[i];
+
+	perfmon->ncounters = req->ncounters;
+
+	refcount_set(&perfmon->refcnt, 1);
+	mutex_init(&perfmon->lock);
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	ret = idr_alloc(&v3d_priv->perfmon.idr, perfmon, V3D_PERFMONID_MIN,
+			V3D_PERFMONID_MAX, GFP_KERNEL);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (ret < 0) {
+		mutex_destroy(&perfmon->lock);
+		kfree(perfmon);
+		return ret;
+	}
+
+	req->id = ret;
+
+	return 0;
+}
+
+int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_destroy *req = data;
+	struct v3d_perfmon *perfmon;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_remove(&v3d_priv->perfmon.idr, req->id);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	v3d_perfmon_put(perfmon);
+
+	return 0;
+}
+
+int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_get_values *req = data;
+	struct v3d_perfmon *perfmon;
+	int ret = 0;
+
+	if (req->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&v3d_priv->perfmon.lock);
+	perfmon = idr_find(&v3d_priv->perfmon.idr, req->id);
+	v3d_perfmon_get(perfmon);
+	mutex_unlock(&v3d_priv->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	v3d_perfmon_stop(v3d, perfmon, true);
+
+	if (copy_to_user(u64_to_user_ptr(req->values_ptr), perfmon->values,
+			 perfmon->ncounters * sizeof(u64)))
+		ret = -EFAULT;
+
+	v3d_perfmon_put(perfmon);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
new file mode 100644
index 0000000000..3663e0d6bf
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -0,0 +1,499 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2017-2018 Broadcom */
+
+#ifndef V3D_REGS_H
+#define V3D_REGS_H
+
+#include <linux/bitops.h>
+
+#define V3D_MASK(high, low) ((u32)GENMASK(high, low))
+/* Using the GNU statement expression extension */
+#define V3D_SET_FIELD(value, field)					\
+	({								\
+		u32 fieldval = (value) << field##_SHIFT;		\
+		WARN_ON((fieldval & ~field##_MASK) != 0);		\
+		fieldval & field##_MASK;				\
+	 })
+
+#define V3D_GET_FIELD(word, field) (((word) & field##_MASK) >>		\
+				    field##_SHIFT)
+
+/* Hub registers for shared hardware between V3D cores. */
+
+#define V3D_HUB_AXICFG                                 0x00000
+# define V3D_HUB_AXICFG_MAX_LEN_MASK                   V3D_MASK(3, 0)
+# define V3D_HUB_AXICFG_MAX_LEN_SHIFT                  0
+#define V3D_HUB_UIFCFG                                 0x00004
+#define V3D_HUB_IDENT0                                 0x00008
+
+#define V3D_HUB_IDENT1                                 0x0000c
+# define V3D_HUB_IDENT1_WITH_MSO                       BIT(19)
+# define V3D_HUB_IDENT1_WITH_TSY                       BIT(18)
+# define V3D_HUB_IDENT1_WITH_TFU                       BIT(17)
+# define V3D_HUB_IDENT1_WITH_L3C                       BIT(16)
+# define V3D_HUB_IDENT1_NHOSTS_MASK                    V3D_MASK(15, 12)
+# define V3D_HUB_IDENT1_NHOSTS_SHIFT                   12
+# define V3D_HUB_IDENT1_NCORES_MASK                    V3D_MASK(11, 8)
+# define V3D_HUB_IDENT1_NCORES_SHIFT                   8
+# define V3D_HUB_IDENT1_REV_MASK                       V3D_MASK(7, 4)
+# define V3D_HUB_IDENT1_REV_SHIFT                      4
+# define V3D_HUB_IDENT1_TVER_MASK                      V3D_MASK(3, 0)
+# define V3D_HUB_IDENT1_TVER_SHIFT                     0
+
+#define V3D_HUB_IDENT2                                 0x00010
+# define V3D_HUB_IDENT2_WITH_MMU                       BIT(8)
+# define V3D_HUB_IDENT2_L3C_NKB_MASK                   V3D_MASK(7, 0)
+# define V3D_HUB_IDENT2_L3C_NKB_SHIFT                  0
+
+#define V3D_HUB_IDENT3                                 0x00014
+# define V3D_HUB_IDENT3_IPREV_MASK                     V3D_MASK(15, 8)
+# define V3D_HUB_IDENT3_IPREV_SHIFT                    8
+# define V3D_HUB_IDENT3_IPIDX_MASK                     V3D_MASK(7, 0)
+# define V3D_HUB_IDENT3_IPIDX_SHIFT                    0
+
+#define V3D_HUB_INT_STS                                0x00050
+#define V3D_HUB_INT_SET                                0x00054
+#define V3D_HUB_INT_CLR                                0x00058
+#define V3D_HUB_INT_MSK_STS                            0x0005c
+#define V3D_HUB_INT_MSK_SET                            0x00060
+#define V3D_HUB_INT_MSK_CLR                            0x00064
+# define V3D_HUB_INT_MMU_WRV                           BIT(5)
+# define V3D_HUB_INT_MMU_PTI                           BIT(4)
+# define V3D_HUB_INT_MMU_CAP                           BIT(3)
+# define V3D_HUB_INT_MSO                               BIT(2)
+# define V3D_HUB_INT_TFUC                              BIT(1)
+# define V3D_HUB_INT_TFUF                              BIT(0)
+
+#define V3D_GCA_CACHE_CTRL                             0x0000c
+# define V3D_GCA_CACHE_CTRL_FLUSH                      BIT(0)
+
+#define V3D_GCA_SAFE_SHUTDOWN                          0x000b0
+# define V3D_GCA_SAFE_SHUTDOWN_EN                      BIT(0)
+
+#define V3D_GCA_SAFE_SHUTDOWN_ACK                      0x000b4
+# define V3D_GCA_SAFE_SHUTDOWN_ACK_ACKED               3
+
+# define V3D_TOP_GR_BRIDGE_REVISION                    0x00000
+# define V3D_TOP_GR_BRIDGE_MAJOR_MASK                  V3D_MASK(15, 8)
+# define V3D_TOP_GR_BRIDGE_MAJOR_SHIFT                 8
+# define V3D_TOP_GR_BRIDGE_MINOR_MASK                  V3D_MASK(7, 0)
+# define V3D_TOP_GR_BRIDGE_MINOR_SHIFT                 0
+
+/* 7268 reset reg */
+# define V3D_TOP_GR_BRIDGE_SW_INIT_0                   0x00008
+# define V3D_TOP_GR_BRIDGE_SW_INIT_0_V3D_CLK_108_SW_INIT BIT(0)
+/* 7278 reset reg */
+# define V3D_TOP_GR_BRIDGE_SW_INIT_1                   0x0000c
+# define V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT BIT(0)
+
+#define V3D_TFU_CS                                     0x00400
+/* Stops current job, empties input fifo. */
+# define V3D_TFU_CS_TFURST                             BIT(31)
+# define V3D_TFU_CS_CVTCT_MASK                         V3D_MASK(23, 16)
+# define V3D_TFU_CS_CVTCT_SHIFT                        16
+# define V3D_TFU_CS_NFREE_MASK                         V3D_MASK(13, 8)
+# define V3D_TFU_CS_NFREE_SHIFT                        8
+# define V3D_TFU_CS_BUSY                               BIT(0)
+
+#define V3D_TFU_SU                                     0x00404
+/* Interrupt when FINTTHR input slots are free (0 = disabled) */
+# define V3D_TFU_SU_FINTTHR_MASK                       V3D_MASK(13, 8)
+# define V3D_TFU_SU_FINTTHR_SHIFT                      8
+/* Skips resetting the CRC at the start of CRC generation. */
+# define V3D_TFU_SU_CRCCHAIN                           BIT(4)
+/* skips writes, computes CRC of the image.  miplevels must be 0. */
+# define V3D_TFU_SU_CRC                                BIT(3)
+# define V3D_TFU_SU_THROTTLE_MASK                      V3D_MASK(1, 0)
+# define V3D_TFU_SU_THROTTLE_SHIFT                     0
+
+#define V3D_TFU_ICFG                                   0x00408
+/* Interrupt when the conversion is complete. */
+# define V3D_TFU_ICFG_IOC                              BIT(0)
+
+/* Input Image Address */
+#define V3D_TFU_IIA                                    0x0040c
+/* Input Chroma Address */
+#define V3D_TFU_ICA                                    0x00410
+/* Input Image Stride */
+#define V3D_TFU_IIS                                    0x00414
+/* Input Image U-Plane Address */
+#define V3D_TFU_IUA                                    0x00418
+/* Output Image Address */
+#define V3D_TFU_IOA                                    0x0041c
+/* Image Output Size */
+#define V3D_TFU_IOS                                    0x00420
+/* TFU YUV Coefficient 0 */
+#define V3D_TFU_COEF0                                  0x00424
+/* Use these regs instead of the defaults. */
+# define V3D_TFU_COEF0_USECOEF                         BIT(31)
+/* TFU YUV Coefficient 1 */
+#define V3D_TFU_COEF1                                  0x00428
+/* TFU YUV Coefficient 2 */
+#define V3D_TFU_COEF2                                  0x0042c
+/* TFU YUV Coefficient 3 */
+#define V3D_TFU_COEF3                                  0x00430
+
+#define V3D_TFU_CRC                                    0x00434
+
+/* Per-MMU registers. */
+
+#define V3D_MMUC_CONTROL                               0x01000
+# define V3D_MMUC_CONTROL_CLEAR                        BIT(3)
+# define V3D_MMUC_CONTROL_FLUSHING                     BIT(2)
+# define V3D_MMUC_CONTROL_FLUSH                        BIT(1)
+# define V3D_MMUC_CONTROL_ENABLE                       BIT(0)
+
+#define V3D_MMU_CTL                                    0x01200
+# define V3D_MMU_CTL_CAP_EXCEEDED                      BIT(27)
+# define V3D_MMU_CTL_CAP_EXCEEDED_ABORT                BIT(26)
+# define V3D_MMU_CTL_CAP_EXCEEDED_INT                  BIT(25)
+# define V3D_MMU_CTL_CAP_EXCEEDED_EXCEPTION            BIT(24)
+# define V3D_MMU_CTL_PT_INVALID                        BIT(20)
+# define V3D_MMU_CTL_PT_INVALID_ABORT                  BIT(19)
+# define V3D_MMU_CTL_PT_INVALID_INT                    BIT(18)
+# define V3D_MMU_CTL_PT_INVALID_EXCEPTION              BIT(17)
+# define V3D_MMU_CTL_PT_INVALID_ENABLE                 BIT(16)
+# define V3D_MMU_CTL_WRITE_VIOLATION                   BIT(12)
+# define V3D_MMU_CTL_WRITE_VIOLATION_ABORT             BIT(11)
+# define V3D_MMU_CTL_WRITE_VIOLATION_INT               BIT(10)
+# define V3D_MMU_CTL_WRITE_VIOLATION_EXCEPTION         BIT(9)
+# define V3D_MMU_CTL_TLB_CLEARING                      BIT(7)
+# define V3D_MMU_CTL_TLB_STATS_CLEAR                   BIT(3)
+# define V3D_MMU_CTL_TLB_CLEAR                         BIT(2)
+# define V3D_MMU_CTL_TLB_STATS_ENABLE                  BIT(1)
+# define V3D_MMU_CTL_ENABLE                            BIT(0)
+
+#define V3D_MMU_PT_PA_BASE                             0x01204
+#define V3D_MMU_HIT                                    0x01208
+#define V3D_MMU_MISSES                                 0x0120c
+#define V3D_MMU_STALLS                                 0x01210
+
+#define V3D_MMU_ADDR_CAP                               0x01214
+# define V3D_MMU_ADDR_CAP_ENABLE                       BIT(31)
+# define V3D_MMU_ADDR_CAP_MPAGE_MASK                   V3D_MASK(11, 0)
+# define V3D_MMU_ADDR_CAP_MPAGE_SHIFT                  0
+
+#define V3D_MMU_SHOOT_DOWN                             0x01218
+# define V3D_MMU_SHOOT_DOWN_SHOOTING                   BIT(29)
+# define V3D_MMU_SHOOT_DOWN_SHOOT                      BIT(28)
+# define V3D_MMU_SHOOT_DOWN_PAGE_MASK                  V3D_MASK(27, 0)
+# define V3D_MMU_SHOOT_DOWN_PAGE_SHIFT                 0
+
+#define V3D_MMU_BYPASS_START                           0x0121c
+#define V3D_MMU_BYPASS_END                             0x01220
+
+/* AXI ID of the access that faulted */
+#define V3D_MMU_VIO_ID                                 0x0122c
+
+/* Address for illegal PTEs to return */
+#define V3D_MMU_ILLEGAL_ADDR                           0x01230
+# define V3D_MMU_ILLEGAL_ADDR_ENABLE                   BIT(31)
+
+/* Address that faulted */
+#define V3D_MMU_VIO_ADDR                               0x01234
+
+#define V3D_MMU_DEBUG_INFO                             0x01238
+# define V3D_MMU_PA_WIDTH_MASK                         V3D_MASK(11, 8)
+# define V3D_MMU_PA_WIDTH_SHIFT                        8
+# define V3D_MMU_VA_WIDTH_MASK                         V3D_MASK(7, 4)
+# define V3D_MMU_VA_WIDTH_SHIFT                        4
+# define V3D_MMU_VERSION_MASK                          V3D_MASK(3, 0)
+# define V3D_MMU_VERSION_SHIFT                         0
+
+/* Per-V3D-core registers */
+
+#define V3D_CTL_IDENT0                                 0x00000
+# define V3D_IDENT0_VER_MASK                           V3D_MASK(31, 24)
+# define V3D_IDENT0_VER_SHIFT                          24
+
+#define V3D_CTL_IDENT1                                 0x00004
+/* Multiples of 1kb */
+# define V3D_IDENT1_VPM_SIZE_MASK                      V3D_MASK(31, 28)
+# define V3D_IDENT1_VPM_SIZE_SHIFT                     28
+# define V3D_IDENT1_NSEM_MASK                          V3D_MASK(23, 16)
+# define V3D_IDENT1_NSEM_SHIFT                         16
+# define V3D_IDENT1_NTMU_MASK                          V3D_MASK(15, 12)
+# define V3D_IDENT1_NTMU_SHIFT                         12
+# define V3D_IDENT1_QUPS_MASK                          V3D_MASK(11, 8)
+# define V3D_IDENT1_QUPS_SHIFT                         8
+# define V3D_IDENT1_NSLC_MASK                          V3D_MASK(7, 4)
+# define V3D_IDENT1_NSLC_SHIFT                         4
+# define V3D_IDENT1_REV_MASK                           V3D_MASK(3, 0)
+# define V3D_IDENT1_REV_SHIFT                          0
+
+#define V3D_CTL_IDENT2                                 0x00008
+# define V3D_IDENT2_BCG_INT                            BIT(28)
+
+#define V3D_CTL_MISCCFG                                0x00018
+# define V3D_CTL_MISCCFG_QRMAXCNT_MASK                 V3D_MASK(3, 1)
+# define V3D_CTL_MISCCFG_QRMAXCNT_SHIFT                1
+# define V3D_MISCCFG_OVRTMUOUT                         BIT(0)
+
+#define V3D_CTL_L2CACTL                                0x00020
+# define V3D_L2CACTL_L2CCLR                            BIT(2)
+# define V3D_L2CACTL_L2CDIS                            BIT(1)
+# define V3D_L2CACTL_L2CENA                            BIT(0)
+
+#define V3D_CTL_SLCACTL                                0x00024
+# define V3D_SLCACTL_TVCCS_MASK                        V3D_MASK(27, 24)
+# define V3D_SLCACTL_TVCCS_SHIFT                       24
+# define V3D_SLCACTL_TDCCS_MASK                        V3D_MASK(19, 16)
+# define V3D_SLCACTL_TDCCS_SHIFT                       16
+# define V3D_SLCACTL_UCC_MASK                          V3D_MASK(11, 8)
+# define V3D_SLCACTL_UCC_SHIFT                         8
+# define V3D_SLCACTL_ICC_MASK                          V3D_MASK(3, 0)
+# define V3D_SLCACTL_ICC_SHIFT                         0
+
+#define V3D_CTL_L2TCACTL                               0x00030
+# define V3D_L2TCACTL_TMUWCF                           BIT(8)
+# define V3D_L2TCACTL_L2T_NO_WM                        BIT(4)
+/* Invalidates cache lines. */
+# define V3D_L2TCACTL_FLM_FLUSH                        0
+/* Removes cachelines without writing dirty lines back. */
+# define V3D_L2TCACTL_FLM_CLEAR                        1
+/* Writes out dirty cachelines and marks them clean, but doesn't invalidate. */
+# define V3D_L2TCACTL_FLM_CLEAN                        2
+# define V3D_L2TCACTL_FLM_MASK                         V3D_MASK(2, 1)
+# define V3D_L2TCACTL_FLM_SHIFT                        1
+# define V3D_L2TCACTL_L2TFLS                           BIT(0)
+#define V3D_CTL_L2TFLSTA                               0x00034
+#define V3D_CTL_L2TFLEND                               0x00038
+
+#define V3D_CTL_INT_STS                                0x00050
+#define V3D_CTL_INT_SET                                0x00054
+#define V3D_CTL_INT_CLR                                0x00058
+#define V3D_CTL_INT_MSK_STS                            0x0005c
+#define V3D_CTL_INT_MSK_SET                            0x00060
+#define V3D_CTL_INT_MSK_CLR                            0x00064
+# define V3D_INT_QPU_MASK                              V3D_MASK(27, 16)
+# define V3D_INT_QPU_SHIFT                             16
+# define V3D_INT_CSDDONE                               BIT(7)
+# define V3D_INT_PCTR                                  BIT(6)
+# define V3D_INT_GMPV                                  BIT(5)
+# define V3D_INT_TRFB                                  BIT(4)
+# define V3D_INT_SPILLUSE                              BIT(3)
+# define V3D_INT_OUTOMEM                               BIT(2)
+# define V3D_INT_FLDONE                                BIT(1)
+# define V3D_INT_FRDONE                                BIT(0)
+
+#define V3D_CLE_CT0CS                                  0x00100
+#define V3D_CLE_CT1CS                                  0x00104
+#define V3D_CLE_CTNCS(n) (V3D_CLE_CT0CS + 4 * n)
+#define V3D_CLE_CT0EA                                  0x00108
+#define V3D_CLE_CT1EA                                  0x0010c
+#define V3D_CLE_CTNEA(n) (V3D_CLE_CT0EA + 4 * n)
+#define V3D_CLE_CT0CA                                  0x00110
+#define V3D_CLE_CT1CA                                  0x00114
+#define V3D_CLE_CTNCA(n) (V3D_CLE_CT0CA + 4 * n)
+#define V3D_CLE_CT0RA                                  0x00118
+#define V3D_CLE_CT1RA                                  0x0011c
+#define V3D_CLE_CTNRA(n) (V3D_CLE_CT0RA + 4 * n)
+#define V3D_CLE_CT0LC                                  0x00120
+#define V3D_CLE_CT1LC                                  0x00124
+#define V3D_CLE_CT0PC                                  0x00128
+#define V3D_CLE_CT1PC                                  0x0012c
+#define V3D_CLE_PCS                                    0x00130
+#define V3D_CLE_BFC                                    0x00134
+#define V3D_CLE_RFC                                    0x00138
+#define V3D_CLE_TFBC                                   0x0013c
+#define V3D_CLE_TFIT                                   0x00140
+#define V3D_CLE_CT1CFG                                 0x00144
+#define V3D_CLE_CT1TILECT                              0x00148
+#define V3D_CLE_CT1TSKIP                               0x0014c
+#define V3D_CLE_CT1PTCT                                0x00150
+#define V3D_CLE_CT0SYNC                                0x00154
+#define V3D_CLE_CT1SYNC                                0x00158
+#define V3D_CLE_CT0QTS                                 0x0015c
+# define V3D_CLE_CT0QTS_ENABLE                         BIT(1)
+#define V3D_CLE_CT0QBA                                 0x00160
+#define V3D_CLE_CT1QBA                                 0x00164
+#define V3D_CLE_CTNQBA(n) (V3D_CLE_CT0QBA + 4 * n)
+#define V3D_CLE_CT0QEA                                 0x00168
+#define V3D_CLE_CT1QEA                                 0x0016c
+#define V3D_CLE_CTNQEA(n) (V3D_CLE_CT0QEA + 4 * n)
+#define V3D_CLE_CT0QMA                                 0x00170
+#define V3D_CLE_CT0QMS                                 0x00174
+#define V3D_CLE_CT1QCFG                                0x00178
+/* If set without ETPROC, entirely skip tiles with no primitives. */
+# define V3D_CLE_QCFG_ETFILT                           BIT(7)
+/* If set with ETFILT, just write the clear color to tiles with no
+ * primitives.
+ */
+# define V3D_CLE_QCFG_ETPROC                           BIT(6)
+# define V3D_CLE_QCFG_ETSFLUSH                         BIT(1)
+# define V3D_CLE_QCFG_MCDIS                            BIT(0)
+
+#define V3D_PTB_BPCA                                   0x00300
+#define V3D_PTB_BPCS                                   0x00304
+#define V3D_PTB_BPOA                                   0x00308
+#define V3D_PTB_BPOS                                   0x0030c
+
+#define V3D_PTB_BXCF                                   0x00310
+# define V3D_PTB_BXCF_RWORDERDISA                      BIT(1)
+# define V3D_PTB_BXCF_CLIPDISA                         BIT(0)
+
+#define V3D_V3_PCTR_0_EN                               0x00674
+#define V3D_V3_PCTR_0_EN_ENABLE                        BIT(31)
+#define V3D_V4_PCTR_0_EN                               0x00650
+/* When a bit is set, resets the counter to 0. */
+#define V3D_V3_PCTR_0_CLR                              0x00670
+#define V3D_V4_PCTR_0_CLR                              0x00654
+#define V3D_PCTR_0_OVERFLOW                            0x00658
+
+#define V3D_V3_PCTR_0_PCTRS0                           0x00684
+#define V3D_V3_PCTR_0_PCTRS15                          0x00660
+#define V3D_V3_PCTR_0_PCTRSX(x)                        (V3D_V3_PCTR_0_PCTRS0 + \
+							4 * (x))
+/* Each src reg muxes four counters each. */
+#define V3D_V4_PCTR_0_SRC_0_3                          0x00660
+#define V3D_V4_PCTR_0_SRC_28_31                        0x0067c
+#define V3D_V4_PCTR_0_SRC_X(x)                         (V3D_V4_PCTR_0_SRC_0_3 + \
+							4 * (x))
+# define V3D_PCTR_S0_MASK                              V3D_MASK(6, 0)
+# define V3D_PCTR_S0_SHIFT                             0
+# define V3D_PCTR_S1_MASK                              V3D_MASK(14, 8)
+# define V3D_PCTR_S1_SHIFT                             8
+# define V3D_PCTR_S2_MASK                              V3D_MASK(22, 16)
+# define V3D_PCTR_S2_SHIFT                             16
+# define V3D_PCTR_S3_MASK                              V3D_MASK(30, 24)
+# define V3D_PCTR_S3_SHIFT                             24
+# define V3D_PCTR_CYCLE_COUNT                          32
+
+/* Output values of the counters. */
+#define V3D_PCTR_0_PCTR0                               0x00680
+#define V3D_PCTR_0_PCTR31                              0x006fc
+#define V3D_PCTR_0_PCTRX(x)                            (V3D_PCTR_0_PCTR0 + \
+							4 * (x))
+#define V3D_GMP_STATUS                                 0x00800
+# define V3D_GMP_STATUS_GMPRST                         BIT(31)
+# define V3D_GMP_STATUS_WR_COUNT_MASK                  V3D_MASK(30, 24)
+# define V3D_GMP_STATUS_WR_COUNT_SHIFT                 24
+# define V3D_GMP_STATUS_RD_COUNT_MASK                  V3D_MASK(22, 16)
+# define V3D_GMP_STATUS_RD_COUNT_SHIFT                 16
+# define V3D_GMP_STATUS_WR_ACTIVE                      BIT(5)
+# define V3D_GMP_STATUS_RD_ACTIVE                      BIT(4)
+# define V3D_GMP_STATUS_CFG_BUSY                       BIT(3)
+# define V3D_GMP_STATUS_CNTOVF                         BIT(2)
+# define V3D_GMP_STATUS_INVPROT                        BIT(1)
+# define V3D_GMP_STATUS_VIO                            BIT(0)
+
+#define V3D_GMP_CFG                                    0x00804
+# define V3D_GMP_CFG_LBURSTEN                          BIT(3)
+# define V3D_GMP_CFG_PGCRSEN                           BIT()
+# define V3D_GMP_CFG_STOP_REQ                          BIT(1)
+# define V3D_GMP_CFG_PROT_ENABLE                       BIT(0)
+
+#define V3D_GMP_VIO_ADDR                               0x00808
+#define V3D_GMP_VIO_TYPE                               0x0080c
+#define V3D_GMP_TABLE_ADDR                             0x00810
+#define V3D_GMP_CLEAR_LOAD                             0x00814
+#define V3D_GMP_PRESERVE_LOAD                          0x00818
+#define V3D_GMP_VALID_LINES                            0x00820
+
+#define V3D_CSD_STATUS                                 0x00900
+# define V3D_CSD_STATUS_NUM_COMPLETED_MASK             V3D_MASK(11, 4)
+# define V3D_CSD_STATUS_NUM_COMPLETED_SHIFT            4
+# define V3D_CSD_STATUS_NUM_ACTIVE_MASK                V3D_MASK(3, 2)
+# define V3D_CSD_STATUS_NUM_ACTIVE_SHIFT               2
+# define V3D_CSD_STATUS_HAVE_CURRENT_DISPATCH          BIT(1)
+# define V3D_CSD_STATUS_HAVE_QUEUED_DISPATCH           BIT(0)
+
+#define V3D_CSD_QUEUED_CFG0                            0x00904
+# define V3D_CSD_QUEUED_CFG0_NUM_WGS_X_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG0_NUM_WGS_X_SHIFT           16
+# define V3D_CSD_QUEUED_CFG0_WG_X_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG0_WG_X_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG1                            0x00908
+# define V3D_CSD_QUEUED_CFG1_NUM_WGS_Y_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG1_NUM_WGS_Y_SHIFT           16
+# define V3D_CSD_QUEUED_CFG1_WG_Y_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG1_WG_Y_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG2                            0x0090c
+# define V3D_CSD_QUEUED_CFG2_NUM_WGS_Z_MASK            V3D_MASK(31, 16)
+# define V3D_CSD_QUEUED_CFG2_NUM_WGS_Z_SHIFT           16
+# define V3D_CSD_QUEUED_CFG2_WG_Z_OFFSET_MASK          V3D_MASK(15, 0)
+# define V3D_CSD_QUEUED_CFG2_WG_Z_OFFSET_SHIFT         0
+
+#define V3D_CSD_QUEUED_CFG3                            0x00910
+# define V3D_CSD_QUEUED_CFG3_OVERLAP_WITH_PREV         BIT(26)
+# define V3D_CSD_QUEUED_CFG3_MAX_SG_ID_MASK            V3D_MASK(25, 20)
+# define V3D_CSD_QUEUED_CFG3_MAX_SG_ID_SHIFT           20
+# define V3D_CSD_QUEUED_CFG3_BATCHES_PER_SG_M1_MASK    V3D_MASK(19, 12)
+# define V3D_CSD_QUEUED_CFG3_BATCHES_PER_SG_M1_SHIFT   12
+# define V3D_CSD_QUEUED_CFG3_WGS_PER_SG_MASK           V3D_MASK(11, 8)
+# define V3D_CSD_QUEUED_CFG3_WGS_PER_SG_SHIFT          8
+# define V3D_CSD_QUEUED_CFG3_WG_SIZE_MASK              V3D_MASK(7, 0)
+# define V3D_CSD_QUEUED_CFG3_WG_SIZE_SHIFT             0
+
+/* Number of batches, minus 1 */
+#define V3D_CSD_QUEUED_CFG4                            0x00914
+
+/* Shader address, pnan, singleseg, threading, like a shader record. */
+#define V3D_CSD_QUEUED_CFG5                            0x00918
+
+/* Uniforms address (4 byte aligned) */
+#define V3D_CSD_QUEUED_CFG6                            0x0091c
+
+#define V3D_CSD_CURRENT_CFG0                          0x00920
+#define V3D_CSD_CURRENT_CFG1                          0x00924
+#define V3D_CSD_CURRENT_CFG2                          0x00928
+#define V3D_CSD_CURRENT_CFG3                          0x0092c
+#define V3D_CSD_CURRENT_CFG4                          0x00930
+#define V3D_CSD_CURRENT_CFG5                          0x00934
+#define V3D_CSD_CURRENT_CFG6                          0x00938
+
+#define V3D_CSD_CURRENT_ID0                            0x0093c
+# define V3D_CSD_CURRENT_ID0_WG_X_MASK                 V3D_MASK(31, 16)
+# define V3D_CSD_CURRENT_ID0_WG_X_SHIFT                16
+# define V3D_CSD_CURRENT_ID0_WG_IN_SG_MASK             V3D_MASK(11, 8)
+# define V3D_CSD_CURRENT_ID0_WG_IN_SG_SHIFT            8
+# define V3D_CSD_CURRENT_ID0_L_IDX_MASK                V3D_MASK(7, 0)
+# define V3D_CSD_CURRENT_ID0_L_IDX_SHIFT               0
+
+#define V3D_CSD_CURRENT_ID1                            0x00940
+# define V3D_CSD_CURRENT_ID0_WG_Z_MASK                 V3D_MASK(31, 16)
+# define V3D_CSD_CURRENT_ID0_WG_Z_SHIFT                16
+# define V3D_CSD_CURRENT_ID0_WG_Y_MASK                 V3D_MASK(15, 0)
+# define V3D_CSD_CURRENT_ID0_WG_Y_SHIFT                0
+
+#define V3D_ERR_FDBGO                                  0x00f04
+#define V3D_ERR_FDBGB                                  0x00f08
+#define V3D_ERR_FDBGR                                  0x00f0c
+
+#define V3D_ERR_FDBGS                                  0x00f10
+# define V3D_ERR_FDBGS_INTERPZ_IP_STALL                BIT(17)
+# define V3D_ERR_FDBGS_DEPTHO_FIFO_IP_STALL            BIT(16)
+# define V3D_ERR_FDBGS_XYNRM_IP_STALL                  BIT(14)
+# define V3D_ERR_FDBGS_EZREQ_FIFO_OP_VALID             BIT(13)
+# define V3D_ERR_FDBGS_QXYF_FIFO_OP_VALID              BIT(12)
+# define V3D_ERR_FDBGS_QXYF_FIFO_OP_LAST               BIT(11)
+# define V3D_ERR_FDBGS_EZTEST_ANYQVALID                BIT(7)
+# define V3D_ERR_FDBGS_EZTEST_PASS                     BIT(6)
+# define V3D_ERR_FDBGS_EZTEST_QREADY                   BIT(5)
+# define V3D_ERR_FDBGS_EZTEST_VLF_OKNOVALID            BIT(4)
+# define V3D_ERR_FDBGS_EZTEST_QSTALL                   BIT(3)
+# define V3D_ERR_FDBGS_EZTEST_IP_VLFSTALL              BIT(2)
+# define V3D_ERR_FDBGS_EZTEST_IP_PRSTALL               BIT(1)
+# define V3D_ERR_FDBGS_EZTEST_IP_QSTALL                BIT(0)
+
+#define V3D_ERR_STAT                                   0x00f20
+# define V3D_ERR_L2CARE                                BIT(15)
+# define V3D_ERR_VCMBE                                 BIT(14)
+# define V3D_ERR_VCMRE                                 BIT(13)
+# define V3D_ERR_VCDI                                  BIT(12)
+# define V3D_ERR_VCDE                                  BIT(11)
+# define V3D_ERR_VDWE                                  BIT(10)
+# define V3D_ERR_VPMEAS                                BIT(9)
+# define V3D_ERR_VPMEFNA                               BIT(8)
+# define V3D_ERR_VPMEWNA                               BIT(7)
+# define V3D_ERR_VPMERNA                               BIT(6)
+# define V3D_ERR_VPMERR                                BIT(5)
+# define V3D_ERR_VPMEWR                                BIT(4)
+# define V3D_ERR_VPAERRGL                              BIT(3)
+# define V3D_ERR_VPAEBRGL                              BIT(2)
+# define V3D_ERR_VPAERGS                               BIT(1)
+# define V3D_ERR_VPAEABB                               BIT(0)
+
+#endif /* V3D_REGS_H */
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
new file mode 100644
index 0000000000..06238e6d7f
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Broadcom */
+
+/**
+ * DOC: Broadcom V3D scheduling
+ *
+ * The shared DRM GPU scheduler is used to coordinate submitting jobs
+ * to the hardware.  Each DRM fd (roughly a client process) gets its
+ * own scheduler entity, which will process jobs in order.  The GPU
+ * scheduler will round-robin between clients to submit the next job.
+ *
+ * For simplicity, and in order to keep latency low for interactive
+ * jobs when bulk background jobs are queued up, we submit a new job
+ * to the HW only when it has completed the last one, instead of
+ * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use
+ * drm_sched_job_add_dependency() to manage the dependency between bin and
+ * render, instead of having the clients submit jobs using the HW's
+ * semaphores to interlock between them.
+ */
+
+#include <linux/kthread.h>
+
+#include "v3d_drv.h"
+#include "v3d_regs.h"
+#include "v3d_trace.h"
+
+static struct v3d_job *
+to_v3d_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_job, base);
+}
+
+static struct v3d_bin_job *
+to_bin_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_bin_job, base.base);
+}
+
+static struct v3d_render_job *
+to_render_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_render_job, base.base);
+}
+
+static struct v3d_tfu_job *
+to_tfu_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_tfu_job, base.base);
+}
+
+static struct v3d_csd_job *
+to_csd_job(struct drm_sched_job *sched_job)
+{
+	return container_of(sched_job, struct v3d_csd_job, base.base);
+}
+
+static void
+v3d_sched_job_free(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+
+	v3d_job_cleanup(job);
+}
+
+static void
+v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
+{
+	if (job->perfmon != v3d->active_perfmon)
+		v3d_perfmon_stop(v3d, v3d->active_perfmon, true);
+
+	if (job->perfmon && v3d->active_perfmon != job->perfmon)
+		v3d_perfmon_start(v3d, job->perfmon);
+}
+
+static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+	unsigned long irqflags;
+
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
+	/* Lock required around bin_job update vs
+	 * v3d_overflow_mem_work().
+	 */
+	spin_lock_irqsave(&v3d->job_lock, irqflags);
+	v3d->bin_job = job;
+	/* Clear out the overflow allocation, so we don't
+	 * reuse the overflow attached to a previous job.
+	 */
+	V3D_CORE_WRITE(0, V3D_PTB_BPOS, 0);
+	spin_unlock_irqrestore(&v3d->job_lock, irqflags);
+
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_BIN);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	v3d_switch_perfmon(v3d, &job->base);
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	if (job->qma) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMA, job->qma);
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QMS, job->qms);
+	}
+	if (job->qts) {
+		V3D_CORE_WRITE(0, V3D_CLE_CT0QTS,
+			       V3D_CLE_CT0QTS_ENABLE |
+			       job->qts);
+	}
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT0QEA, job->end);
+
+	return fence;
+}
+
+static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+
+	if (unlikely(job->base.base.s_fence->finished.error))
+		return NULL;
+
+	v3d->render_job = job;
+
+	/* Can we avoid this flush?  We need to be careful of
+	 * scheduling, though -- imagine job0 rendering to texture and
+	 * job1 reading, and them being executed as bin0, bin1,
+	 * render0, render1, so that render1's flush at bin time
+	 * wasn't enough.
+	 */
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_RENDER);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
+			    job->start, job->end);
+
+	v3d_switch_perfmon(v3d, &job->base);
+
+	/* XXX: Set the QCFG */
+
+	/* Set the current and end address of the control list.
+	 * Writing the end register is what starts the job.
+	 */
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QBA, job->start);
+	V3D_CORE_WRITE(0, V3D_CLE_CT1QEA, job->end);
+
+	return fence;
+}
+
+static struct dma_fence *
+v3d_tfu_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_tfu_job *job = to_tfu_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+
+	fence = v3d_fence_create(v3d, V3D_TFU);
+	if (IS_ERR(fence))
+		return NULL;
+
+	v3d->tfu_job = job;
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
+
+	V3D_WRITE(V3D_TFU_IIA, job->args.iia);
+	V3D_WRITE(V3D_TFU_IIS, job->args.iis);
+	V3D_WRITE(V3D_TFU_ICA, job->args.ica);
+	V3D_WRITE(V3D_TFU_IUA, job->args.iua);
+	V3D_WRITE(V3D_TFU_IOA, job->args.ioa);
+	V3D_WRITE(V3D_TFU_IOS, job->args.ios);
+	V3D_WRITE(V3D_TFU_COEF0, job->args.coef[0]);
+	if (job->args.coef[0] & V3D_TFU_COEF0_USECOEF) {
+		V3D_WRITE(V3D_TFU_COEF1, job->args.coef[1]);
+		V3D_WRITE(V3D_TFU_COEF2, job->args.coef[2]);
+		V3D_WRITE(V3D_TFU_COEF3, job->args.coef[3]);
+	}
+	/* ICFG kicks off the job. */
+	V3D_WRITE(V3D_TFU_ICFG, job->args.icfg | V3D_TFU_ICFG_IOC);
+
+	return fence;
+}
+
+static struct dma_fence *
+v3d_csd_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_csd_job *job = to_csd_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	struct drm_device *dev = &v3d->drm;
+	struct dma_fence *fence;
+	int i;
+
+	v3d->csd_job = job;
+
+	v3d_invalidate_caches(v3d);
+
+	fence = v3d_fence_create(v3d, V3D_CSD);
+	if (IS_ERR(fence))
+		return NULL;
+
+	if (job->base.irq_fence)
+		dma_fence_put(job->base.irq_fence);
+	job->base.irq_fence = dma_fence_get(fence);
+
+	trace_v3d_submit_csd(dev, to_v3d_fence(fence)->seqno);
+
+	v3d_switch_perfmon(v3d, &job->base);
+
+	for (i = 1; i <= 6; i++)
+		V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0 + 4 * i, job->args.cfg[i]);
+	/* CFG0 write kicks off the job. */
+	V3D_CORE_WRITE(0, V3D_CSD_QUEUED_CFG0, job->args.cfg[0]);
+
+	return fence;
+}
+
+static struct dma_fence *
+v3d_cache_clean_job_run(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_dev *v3d = job->v3d;
+
+	v3d_clean_caches(v3d);
+
+	return NULL;
+}
+
+static enum drm_gpu_sched_stat
+v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
+{
+	enum v3d_queue q;
+
+	mutex_lock(&v3d->reset_lock);
+
+	/* block scheduler */
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
+		drm_sched_stop(&v3d->queue[q].sched, sched_job);
+
+	if (sched_job)
+		drm_sched_increase_karma(sched_job);
+
+	/* get the GPU back into the init state */
+	v3d_reset(v3d);
+
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
+		drm_sched_resubmit_jobs(&v3d->queue[q].sched);
+
+	/* Unblock schedulers and restart their jobs. */
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		drm_sched_start(&v3d->queue[q].sched, true);
+	}
+
+	mutex_unlock(&v3d->reset_lock);
+
+	return DRM_GPU_SCHED_STAT_NOMINAL;
+}
+
+/* If the current address or return address have changed, then the GPU
+ * has probably made progress and we should delay the reset.  This
+ * could fail if the GPU got in an infinite loop in the CL, but that
+ * is pretty unlikely outside of an i-g-t testcase.
+ */
+static enum drm_gpu_sched_stat
+v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q,
+		    u32 *timedout_ctca, u32 *timedout_ctra)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+	struct v3d_dev *v3d = job->v3d;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q));
+
+	if (*timedout_ctca != ctca || *timedout_ctra != ctra) {
+		*timedout_ctca = ctca;
+		*timedout_ctra = ctra;
+		return DRM_GPU_SCHED_STAT_NOMINAL;
+	}
+
+	return v3d_gpu_reset_for_timeout(v3d, sched_job);
+}
+
+static enum drm_gpu_sched_stat
+v3d_bin_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_bin_job *job = to_bin_job(sched_job);
+
+	return v3d_cl_job_timedout(sched_job, V3D_BIN,
+				   &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static enum drm_gpu_sched_stat
+v3d_render_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_render_job *job = to_render_job(sched_job);
+
+	return v3d_cl_job_timedout(sched_job, V3D_RENDER,
+				   &job->timedout_ctca, &job->timedout_ctra);
+}
+
+static enum drm_gpu_sched_stat
+v3d_generic_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_job *job = to_v3d_job(sched_job);
+
+	return v3d_gpu_reset_for_timeout(job->v3d, sched_job);
+}
+
+static enum drm_gpu_sched_stat
+v3d_csd_job_timedout(struct drm_sched_job *sched_job)
+{
+	struct v3d_csd_job *job = to_csd_job(sched_job);
+	struct v3d_dev *v3d = job->base.v3d;
+	u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4);
+
+	/* If we've made progress, skip reset and let the timer get
+	 * rearmed.
+	 */
+	if (job->timedout_batches != batches) {
+		job->timedout_batches = batches;
+		return DRM_GPU_SCHED_STAT_NOMINAL;
+	}
+
+	return v3d_gpu_reset_for_timeout(v3d, sched_job);
+}
+
+static const struct drm_sched_backend_ops v3d_bin_sched_ops = {
+	.run_job = v3d_bin_job_run,
+	.timedout_job = v3d_bin_job_timedout,
+	.free_job = v3d_sched_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_render_sched_ops = {
+	.run_job = v3d_render_job_run,
+	.timedout_job = v3d_render_job_timedout,
+	.free_job = v3d_sched_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_tfu_sched_ops = {
+	.run_job = v3d_tfu_job_run,
+	.timedout_job = v3d_generic_job_timedout,
+	.free_job = v3d_sched_job_free,
+};
+
+static const struct drm_sched_backend_ops v3d_csd_sched_ops = {
+	.run_job = v3d_csd_job_run,
+	.timedout_job = v3d_csd_job_timedout,
+	.free_job = v3d_sched_job_free
+};
+
+static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {
+	.run_job = v3d_cache_clean_job_run,
+	.timedout_job = v3d_generic_job_timedout,
+	.free_job = v3d_sched_job_free
+};
+
+int
+v3d_sched_init(struct v3d_dev *v3d)
+{
+	int hw_jobs_limit = 1;
+	int job_hang_limit = 0;
+	int hang_limit_ms = 500;
+	int ret;
+
+	ret = drm_sched_init(&v3d->queue[V3D_BIN].sched,
+			     &v3d_bin_sched_ops,
+			     hw_jobs_limit, job_hang_limit,
+			     msecs_to_jiffies(hang_limit_ms), NULL,
+			     NULL, "v3d_bin", v3d->drm.dev);
+	if (ret)
+		return ret;
+
+	ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched,
+			     &v3d_render_sched_ops,
+			     hw_jobs_limit, job_hang_limit,
+			     msecs_to_jiffies(hang_limit_ms), NULL,
+			     NULL, "v3d_render", v3d->drm.dev);
+	if (ret)
+		goto fail;
+
+	ret = drm_sched_init(&v3d->queue[V3D_TFU].sched,
+			     &v3d_tfu_sched_ops,
+			     hw_jobs_limit, job_hang_limit,
+			     msecs_to_jiffies(hang_limit_ms), NULL,
+			     NULL, "v3d_tfu", v3d->drm.dev);
+	if (ret)
+		goto fail;
+
+	if (v3d_has_csd(v3d)) {
+		ret = drm_sched_init(&v3d->queue[V3D_CSD].sched,
+				     &v3d_csd_sched_ops,
+				     hw_jobs_limit, job_hang_limit,
+				     msecs_to_jiffies(hang_limit_ms), NULL,
+				     NULL, "v3d_csd", v3d->drm.dev);
+		if (ret)
+			goto fail;
+
+		ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched,
+				     &v3d_cache_clean_sched_ops,
+				     hw_jobs_limit, job_hang_limit,
+				     msecs_to_jiffies(hang_limit_ms), NULL,
+				     NULL, "v3d_cache_clean", v3d->drm.dev);
+		if (ret)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	v3d_sched_fini(v3d);
+	return ret;
+}
+
+void
+v3d_sched_fini(struct v3d_dev *v3d)
+{
+	enum v3d_queue q;
+
+	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+		if (v3d->queue[q].sched.ready)
+			drm_sched_fini(&v3d->queue[q].sched);
+	}
+}
diff --git a/drivers/gpu/drm/v3d/v3d_trace.h b/drivers/gpu/drm/v3d/v3d_trace.h
new file mode 100644
index 0000000000..7aa8dc356e
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_trace.h
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015-2018 Broadcom */
+
+#if !defined(_V3D_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _V3D_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM v3d
+#define TRACE_INCLUDE_FILE v3d_trace
+
+TRACE_EVENT(v3d_submit_cl_ioctl,
+	    TP_PROTO(struct drm_device *dev, u32 ct1qba, u32 ct1qea),
+	    TP_ARGS(dev, ct1qba, ct1qea),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, ct1qba)
+			     __field(u32, ct1qea)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->ct1qba = ct1qba;
+			   __entry->ct1qea = ct1qea;
+			   ),
+
+	    TP_printk("dev=%u, RCL 0x%08x..0x%08x",
+		      __entry->dev,
+		      __entry->ct1qba,
+		      __entry->ct1qea)
+);
+
+TRACE_EVENT(v3d_submit_cl,
+	    TP_PROTO(struct drm_device *dev, bool is_render,
+		     uint64_t seqno,
+		     u32 ctnqba, u32 ctnqea),
+	    TP_ARGS(dev, is_render, seqno, ctnqba, ctnqea),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(bool, is_render)
+			     __field(u64, seqno)
+			     __field(u32, ctnqba)
+			     __field(u32, ctnqea)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->is_render = is_render;
+			   __entry->seqno = seqno;
+			   __entry->ctnqba = ctnqba;
+			   __entry->ctnqea = ctnqea;
+			   ),
+
+	    TP_printk("dev=%u, %s, seqno=%llu, 0x%08x..0x%08x",
+		      __entry->dev,
+		      __entry->is_render ? "RCL" : "BCL",
+		      __entry->seqno,
+		      __entry->ctnqba,
+		      __entry->ctnqea)
+);
+
+TRACE_EVENT(v3d_bcl_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_rcl_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_tfu_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_csd_irq,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_submit_tfu_ioctl,
+	    TP_PROTO(struct drm_device *dev, u32 iia),
+	    TP_ARGS(dev, iia),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, iia)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->iia = iia;
+			   ),
+
+	    TP_printk("dev=%u, IIA 0x%08x",
+		      __entry->dev,
+		      __entry->iia)
+);
+
+TRACE_EVENT(v3d_submit_tfu,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_submit_csd_ioctl,
+	    TP_PROTO(struct drm_device *dev, u32 cfg5, u32 cfg6),
+	    TP_ARGS(dev, cfg5, cfg6),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u32, cfg5)
+			     __field(u32, cfg6)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->cfg5 = cfg5;
+			   __entry->cfg6 = cfg6;
+			   ),
+
+	    TP_printk("dev=%u, CFG5 0x%08x, CFG6 0x%08x",
+		      __entry->dev,
+		      __entry->cfg5,
+		      __entry->cfg6)
+);
+
+TRACE_EVENT(v3d_submit_csd,
+	    TP_PROTO(struct drm_device *dev,
+		     uint64_t seqno),
+	    TP_ARGS(dev, seqno),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     __field(u64, seqno)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   __entry->seqno = seqno;
+			   ),
+
+	    TP_printk("dev=%u, seqno=%llu",
+		      __entry->dev,
+		      __entry->seqno)
+);
+
+TRACE_EVENT(v3d_cache_clean_begin,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+TRACE_EVENT(v3d_cache_clean_end,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+TRACE_EVENT(v3d_reset_begin,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+TRACE_EVENT(v3d_reset_end,
+	    TP_PROTO(struct drm_device *dev),
+	    TP_ARGS(dev),
+
+	    TP_STRUCT__entry(
+			     __field(u32, dev)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->dev = dev->primary->index;
+			   ),
+
+	    TP_printk("dev=%u",
+		      __entry->dev)
+);
+
+#endif /* _V3D_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/v3d/v3d_trace_points.c b/drivers/gpu/drm/v3d/v3d_trace_points.c
new file mode 100644
index 0000000000..482922d7c7
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_trace_points.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2015 Broadcom */
+
+#include "v3d_drv.h"
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "v3d_trace.h"
+#endif