drm/lima: driver for ARM Mali4xx GPUs

- Mali 4xx GPUs have two kinds of processors GP and PP. GP is for
  OpenGL vertex shader processing and PP is for fragment shader
  processing. Each processor has its own MMU so prcessors work in
  virtual address space.
- There's only one GP but multiple PP (max 4 for mali 400 and 8
  for mali 450) in the same mali 4xx GPU. All PPs are grouped
  togather to handle a single fragment shader task divided by
  FB output tiled pixels. Mali 400 user space driver is
  responsible for assign target tiled pixels to each PP, but mali
  450 has a HW module called DLBU to dynamically balance each
  PP's load.
- User space driver allocate buffer object and map into GPU
  virtual address space, upload command stream and draw data with
  CPU mmap of the buffer object, then submit task to GP/PP with
  a register frame indicating where is the command stream and misc
  settings.
- There's no command stream validation/relocation due to each user
  process has its own GPU virtual address space. GP/PP's MMU switch
  virtual address space before running two tasks from different
  user process. Error or evil user space code just get MMU fault
  or GP/PP error IRQ, then the HW/SW will be recovered.
- Use GEM+shmem for MM. Currently just alloc and pin memory when
  gem object creation. GPU vm map of the buffer is also done in
  the alloc stage in kernel space. We may delay the memory
  allocation and real GPU vm map to command submission stage in the
  furture as improvement.
- Use drm_sched for GPU task schedule. Each OpenGL context should
  have a lima context object in the kernel to distinguish tasks
  from different user. drm_sched gets task from each lima context
  in a fair way.

mesa driver can be found here before upstreamed:
https://gitlab.freedesktop.org/lima/mesa

v8:
- add comments for in_sync
- fix ctx free miss mutex unlock

v7:
- remove lima_fence_ops with default value
- move fence slab create to device probe
- check pad ioctl args to be zero
- add comments for user/kernel interface

v6:
- fix comments by checkpatch.pl

v5:
- export gp/pp version to userspace
- rebase on drm-misc-next

v4:
- use get param interface to get info
- separate context create/free ioctl
- remove unused max sched task param
- update copyright time
- use xarray instead of idr
- stop using drmP.h

v3:
- fix comments from kbuild robot
- restrict supported arch to tested ones

v2:
- fix syscall argument check
- fix job finish fence leak since kernel 5.0
- use drm syncobj to replace native fence
- move buffer object GPU va map into kernel
- reserve syscall argument space for future info
- remove kernel gem modifier
- switch TTM back to GEM+shmem MM
- use time based io poll
- use whole register name
- adopt gem reservation obj integration
- use drm_timeout_abs_to_jiffies

Cc: Eric Anholt <eric@anholt.net>
Cc: Rob Herring <robh@kernel.org>
Cc: Christian König <ckoenig.leichtzumerken@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Alex Deucher <alexdeucher@gmail.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Dave Airlie <airlied@gmail.com>
Signed-off-by: Andreas Baierl <ichgeh@imkreisrum.de>
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Marek Vasut <marex@denx.de>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Simon Shields <simon@lineageos.org>
Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Rob Herring <robh@kerrnel.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/291200/

36 files changed, 4248 insertions, 0 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 5e1bc630b885..98e9ac8498c0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -337,6 +337,8 @@ source "drivers/gpu/drm/xen/Kconfig"
 
 source "drivers/gpu/drm/vboxvideo/Kconfig"
 
+source "drivers/gpu/drm/lima/Kconfig"
+
 # Keep legacy drivers last
 
 menuconfig DRM_LEGACY
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index e630eccb951c..6c7e8d162b4e 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -111,3 +111,4 @@ obj-$(CONFIG_DRM_PL111) += pl111/
 obj-$(CONFIG_DRM_TVE200) += tve200/
 obj-$(CONFIG_DRM_XEN) += xen/
 obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/
+obj-$(CONFIG_DRM_LIMA)  += lima/
diff --git a/drivers/gpu/drm/lima/Kconfig b/drivers/gpu/drm/lima/Kconfig
new file mode 100644
index 000000000000..f11314448093
--- /dev/null
+++ b/drivers/gpu/drm/lima/Kconfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0 OR MIT
+# Copyright 2017-2019 Qiang Yu <yuq825@gmail.com>
+
+config DRM_LIMA
+       tristate "LIMA (DRM support for ARM Mali 400/450 GPU)"
+       depends on DRM
+       depends on ARM || ARM64 || COMPILE_TEST
+       select DRM_SCHED
+       help
+         DRM driver for ARM Mali 400/450 GPUs.
diff --git a/drivers/gpu/drm/lima/Makefile b/drivers/gpu/drm/lima/Makefile
new file mode 100644
index 000000000000..38cc70281ba5
--- /dev/null
+++ b/drivers/gpu/drm/lima/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0 OR MIT
+# Copyright 2017-2019 Qiang Yu <yuq825@gmail.com>
+
+lima-y := \
+	lima_drv.o \
+	lima_device.o \
+	lima_pmu.o \
+	lima_l2_cache.o \
+	lima_mmu.o \
+	lima_gp.o \
+	lima_pp.o \
+	lima_gem.o \
+	lima_vm.o \
+	lima_sched.o \
+	lima_ctx.o \
+	lima_gem_prime.o \
+	lima_dlbu.o \
+	lima_bcast.o \
+	lima_object.o
+
+obj-$(CONFIG_DRM_LIMA) += lima.o
diff --git a/drivers/gpu/drm/lima/lima_bcast.c b/drivers/gpu/drm/lima/lima_bcast.c
new file mode 100644
index 000000000000..288398027bfa
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_bcast.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/io.h>
+#include <linux/device.h>
+
+#include "lima_device.h"
+#include "lima_bcast.h"
+#include "lima_regs.h"
+
+#define bcast_write(reg, data) writel(data, ip->iomem + reg)
+#define bcast_read(reg) readl(ip->iomem + reg)
+
+void lima_bcast_enable(struct lima_device *dev, int num_pp)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+	struct lima_ip *ip = dev->ip + lima_ip_bcast;
+	int i, mask = bcast_read(LIMA_BCAST_BROADCAST_MASK) & 0xffff0000;
+
+	for (i = 0; i < num_pp; i++) {
+		struct lima_ip *pp = pipe->processor[i];
+
+		mask |= 1 << (pp->id - lima_ip_pp0);
+	}
+
+	bcast_write(LIMA_BCAST_BROADCAST_MASK, mask);
+}
+
+int lima_bcast_init(struct lima_ip *ip)
+{
+	int i, mask = 0;
+
+	for (i = lima_ip_pp0; i <= lima_ip_pp7; i++) {
+		if (ip->dev->ip[i].present)
+			mask |= 1 << (i - lima_ip_pp0);
+	}
+
+	bcast_write(LIMA_BCAST_BROADCAST_MASK, mask << 16);
+	bcast_write(LIMA_BCAST_INTERRUPT_MASK, mask);
+	return 0;
+}
+
+void lima_bcast_fini(struct lima_ip *ip)
+{
+
+}
+
diff --git a/drivers/gpu/drm/lima/lima_bcast.h b/drivers/gpu/drm/lima/lima_bcast.h
new file mode 100644
index 000000000000..c47e58563d0a
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_bcast.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_BCAST_H__
+#define __LIMA_BCAST_H__
+
+struct lima_ip;
+
+int lima_bcast_init(struct lima_ip *ip);
+void lima_bcast_fini(struct lima_ip *ip);
+
+void lima_bcast_enable(struct lima_device *dev, int num_pp);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_ctx.c b/drivers/gpu/drm/lima/lima_ctx.c
new file mode 100644
index 000000000000..c8d12f7c6894
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_ctx.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/slab.h>
+
+#include "lima_device.h"
+#include "lima_ctx.h"
+
+int lima_ctx_create(struct lima_device *dev, struct lima_ctx_mgr *mgr, u32 *id)
+{
+	struct lima_ctx *ctx;
+	int i, err;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	ctx->dev = dev;
+	kref_init(&ctx->refcnt);
+
+	for (i = 0; i < lima_pipe_num; i++) {
+		err = lima_sched_context_init(dev->pipe + i, ctx->context + i, &ctx->guilty);
+		if (err)
+			goto err_out0;
+	}
+
+	err = xa_alloc(&mgr->handles, id, UINT_MAX, ctx, GFP_KERNEL);
+	if (err < 0)
+		goto err_out0;
+
+	return 0;
+
+err_out0:
+	for (i--; i >= 0; i--)
+		lima_sched_context_fini(dev->pipe + i, ctx->context + i);
+	kfree(ctx);
+	return err;
+}
+
+static void lima_ctx_do_release(struct kref *ref)
+{
+	struct lima_ctx *ctx = container_of(ref, struct lima_ctx, refcnt);
+	int i;
+
+	for (i = 0; i < lima_pipe_num; i++)
+		lima_sched_context_fini(ctx->dev->pipe + i, ctx->context + i);
+	kfree(ctx);
+}
+
+int lima_ctx_free(struct lima_ctx_mgr *mgr, u32 id)
+{
+	struct lima_ctx *ctx;
+	int ret = 0;
+
+	mutex_lock(&mgr->lock);
+	ctx = xa_erase(&mgr->handles, id);
+	if (ctx)
+		kref_put(&ctx->refcnt, lima_ctx_do_release);
+	else
+		ret = -EINVAL;
+	mutex_unlock(&mgr->lock);
+	return ret;
+}
+
+struct lima_ctx *lima_ctx_get(struct lima_ctx_mgr *mgr, u32 id)
+{
+	struct lima_ctx *ctx;
+
+	mutex_lock(&mgr->lock);
+	ctx = xa_load(&mgr->handles, id);
+	if (ctx)
+		kref_get(&ctx->refcnt);
+	mutex_unlock(&mgr->lock);
+	return ctx;
+}
+
+void lima_ctx_put(struct lima_ctx *ctx)
+{
+	kref_put(&ctx->refcnt, lima_ctx_do_release);
+}
+
+void lima_ctx_mgr_init(struct lima_ctx_mgr *mgr)
+{
+	mutex_init(&mgr->lock);
+	xa_init_flags(&mgr->handles, XA_FLAGS_ALLOC);
+}
+
+void lima_ctx_mgr_fini(struct lima_ctx_mgr *mgr)
+{
+	struct lima_ctx *ctx;
+	unsigned long id;
+
+	xa_for_each(&mgr->handles, id, ctx) {
+		kref_put(&ctx->refcnt, lima_ctx_do_release);
+	}
+
+	xa_destroy(&mgr->handles);
+	mutex_destroy(&mgr->lock);
+}
diff --git a/drivers/gpu/drm/lima/lima_ctx.h b/drivers/gpu/drm/lima/lima_ctx.h
new file mode 100644
index 000000000000..6154e5c9bfe4
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_ctx.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_CTX_H__
+#define __LIMA_CTX_H__
+
+#include <linux/xarray.h>
+
+#include "lima_device.h"
+
+struct lima_ctx {
+	struct kref refcnt;
+	struct lima_device *dev;
+	struct lima_sched_context context[lima_pipe_num];
+	atomic_t guilty;
+};
+
+struct lima_ctx_mgr {
+	struct mutex lock;
+	struct xarray handles;
+};
+
+int lima_ctx_create(struct lima_device *dev, struct lima_ctx_mgr *mgr, u32 *id);
+int lima_ctx_free(struct lima_ctx_mgr *mgr, u32 id);
+struct lima_ctx *lima_ctx_get(struct lima_ctx_mgr *mgr, u32 id);
+void lima_ctx_put(struct lima_ctx *ctx);
+void lima_ctx_mgr_init(struct lima_ctx_mgr *mgr);
+void lima_ctx_mgr_fini(struct lima_ctx_mgr *mgr);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c
new file mode 100644
index 000000000000..570d0e93f9a9
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_device.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/regulator/consumer.h>
+#include <linux/reset.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+
+#include "lima_device.h"
+#include "lima_gp.h"
+#include "lima_pp.h"
+#include "lima_mmu.h"
+#include "lima_pmu.h"
+#include "lima_l2_cache.h"
+#include "lima_dlbu.h"
+#include "lima_bcast.h"
+#include "lima_vm.h"
+
+struct lima_ip_desc {
+	char *name;
+	char *irq_name;
+	bool must_have[lima_gpu_num];
+	int offset[lima_gpu_num];
+
+	int (*init)(struct lima_ip *ip);
+	void (*fini)(struct lima_ip *ip);
+};
+
+#define LIMA_IP_DESC(ipname, mst0, mst1, off0, off1, func, irq) \
+	[lima_ip_##ipname] = { \
+		.name = #ipname, \
+		.irq_name = irq, \
+		.must_have = { \
+			[lima_gpu_mali400] = mst0, \
+			[lima_gpu_mali450] = mst1, \
+		}, \
+		.offset = { \
+			[lima_gpu_mali400] = off0, \
+			[lima_gpu_mali450] = off1, \
+		}, \
+		.init = lima_##func##_init, \
+		.fini = lima_##func##_fini, \
+	}
+
+static struct lima_ip_desc lima_ip_desc[lima_ip_num] = {
+	LIMA_IP_DESC(pmu,         false, false, 0x02000, 0x02000, pmu,      "pmu"),
+	LIMA_IP_DESC(l2_cache0,   true,  true,  0x01000, 0x10000, l2_cache, NULL),
+	LIMA_IP_DESC(l2_cache1,   false, true,  -1,      0x01000, l2_cache, NULL),
+	LIMA_IP_DESC(l2_cache2,   false, false, -1,      0x11000, l2_cache, NULL),
+	LIMA_IP_DESC(gp,          true,  true,  0x00000, 0x00000, gp,       "gp"),
+	LIMA_IP_DESC(pp0,         true,  true,  0x08000, 0x08000, pp,       "pp0"),
+	LIMA_IP_DESC(pp1,         false, false, 0x0A000, 0x0A000, pp,       "pp1"),
+	LIMA_IP_DESC(pp2,         false, false, 0x0C000, 0x0C000, pp,       "pp2"),
+	LIMA_IP_DESC(pp3,         false, false, 0x0E000, 0x0E000, pp,       "pp3"),
+	LIMA_IP_DESC(pp4,         false, false, -1,      0x28000, pp,       "pp4"),
+	LIMA_IP_DESC(pp5,         false, false, -1,      0x2A000, pp,       "pp5"),
+	LIMA_IP_DESC(pp6,         false, false, -1,      0x2C000, pp,       "pp6"),
+	LIMA_IP_DESC(pp7,         false, false, -1,      0x2E000, pp,       "pp7"),
+	LIMA_IP_DESC(gpmmu,       true,  true,  0x03000, 0x03000, mmu,      "gpmmu"),
+	LIMA_IP_DESC(ppmmu0,      true,  true,  0x04000, 0x04000, mmu,      "ppmmu0"),
+	LIMA_IP_DESC(ppmmu1,      false, false, 0x05000, 0x05000, mmu,      "ppmmu1"),
+	LIMA_IP_DESC(ppmmu2,      false, false, 0x06000, 0x06000, mmu,      "ppmmu2"),
+	LIMA_IP_DESC(ppmmu3,      false, false, 0x07000, 0x07000, mmu,      "ppmmu3"),
+	LIMA_IP_DESC(ppmmu4,      false, false, -1,      0x1C000, mmu,      "ppmmu4"),
+	LIMA_IP_DESC(ppmmu5,      false, false, -1,      0x1D000, mmu,      "ppmmu5"),
+	LIMA_IP_DESC(ppmmu6,      false, false, -1,      0x1E000, mmu,      "ppmmu6"),
+	LIMA_IP_DESC(ppmmu7,      false, false, -1,      0x1F000, mmu,      "ppmmu7"),
+	LIMA_IP_DESC(dlbu,        false, true,  -1,      0x14000, dlbu,     NULL),
+	LIMA_IP_DESC(bcast,       false, true,  -1,      0x13000, bcast,    NULL),
+	LIMA_IP_DESC(pp_bcast,    false, true,  -1,      0x16000, pp_bcast, "pp"),
+	LIMA_IP_DESC(ppmmu_bcast, false, true,  -1,      0x15000, mmu,      NULL),
+};
+
+const char *lima_ip_name(struct lima_ip *ip)
+{
+	return lima_ip_desc[ip->id].name;
+}
+
+static int lima_clk_init(struct lima_device *dev)
+{
+	int err;
+	unsigned long bus_rate, gpu_rate;
+
+	dev->clk_bus = devm_clk_get(dev->dev, "bus");
+	if (IS_ERR(dev->clk_bus)) {
+		dev_err(dev->dev, "get bus clk failed %ld\n", PTR_ERR(dev->clk_bus));
+		return PTR_ERR(dev->clk_bus);
+	}
+
+	dev->clk_gpu = devm_clk_get(dev->dev, "core");
+	if (IS_ERR(dev->clk_gpu)) {
+		dev_err(dev->dev, "get core clk failed %ld\n", PTR_ERR(dev->clk_gpu));
+		return PTR_ERR(dev->clk_gpu);
+	}
+
+	bus_rate = clk_get_rate(dev->clk_bus);
+	dev_info(dev->dev, "bus rate = %lu\n", bus_rate);
+
+	gpu_rate = clk_get_rate(dev->clk_gpu);
+	dev_info(dev->dev, "mod rate = %lu", gpu_rate);
+
+	err = clk_prepare_enable(dev->clk_bus);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(dev->clk_gpu);
+	if (err)
+		goto error_out0;
+
+	dev->reset = devm_reset_control_get_optional(dev->dev, NULL);
+	if (IS_ERR(dev->reset)) {
+		err = PTR_ERR(dev->reset);
+		goto error_out1;
+	} else if (dev->reset != NULL) {
+		err = reset_control_deassert(dev->reset);
+		if (err)
+			goto error_out1;
+	}
+
+	return 0;
+
+error_out1:
+	clk_disable_unprepare(dev->clk_gpu);
+error_out0:
+	clk_disable_unprepare(dev->clk_bus);
+	return err;
+}
+
+static void lima_clk_fini(struct lima_device *dev)
+{
+	if (dev->reset != NULL)
+		reset_control_assert(dev->reset);
+	clk_disable_unprepare(dev->clk_gpu);
+	clk_disable_unprepare(dev->clk_bus);
+}
+
+static int lima_regulator_init(struct lima_device *dev)
+{
+	int ret;
+
+	dev->regulator = devm_regulator_get_optional(dev->dev, "mali");
+	if (IS_ERR(dev->regulator)) {
+		ret = PTR_ERR(dev->regulator);
+		dev->regulator = NULL;
+		if (ret == -ENODEV)
+			return 0;
+		dev_err(dev->dev, "failed to get regulator: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_enable(dev->regulator);
+	if (ret < 0) {
+		dev_err(dev->dev, "failed to enable regulator: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void lima_regulator_fini(struct lima_device *dev)
+{
+	if (dev->regulator)
+		regulator_disable(dev->regulator);
+}
+
+static int lima_init_ip(struct lima_device *dev, int index)
+{
+	struct lima_ip_desc *desc = lima_ip_desc + index;
+	struct lima_ip *ip = dev->ip + index;
+	int offset = desc->offset[dev->id];
+	bool must = desc->must_have[dev->id];
+	int err;
+
+	if (offset < 0)
+		return 0;
+
+	ip->dev = dev;
+	ip->id = index;
+	ip->iomem = dev->iomem + offset;
+	if (desc->irq_name) {
+		err = platform_get_irq_byname(dev->pdev, desc->irq_name);
+		if (err < 0)
+			goto out;
+		ip->irq = err;
+	}
+
+	err = desc->init(ip);
+	if (!err) {
+		ip->present = true;
+		return 0;
+	}
+
+out:
+	return must ? err : 0;
+}
+
+static void lima_fini_ip(struct lima_device *ldev, int index)
+{
+	struct lima_ip_desc *desc = lima_ip_desc + index;
+	struct lima_ip *ip = ldev->ip + index;
+
+	if (ip->present)
+		desc->fini(ip);
+}
+
+static int lima_init_gp_pipe(struct lima_device *dev)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
+	int err;
+
+	err = lima_sched_pipe_init(pipe, "gp");
+	if (err)
+		return err;
+
+	pipe->l2_cache[pipe->num_l2_cache++] = dev->ip + lima_ip_l2_cache0;
+	pipe->mmu[pipe->num_mmu++] = dev->ip + lima_ip_gpmmu;
+	pipe->processor[pipe->num_processor++] = dev->ip + lima_ip_gp;
+
+	err = lima_gp_pipe_init(dev);
+	if (err) {
+		lima_sched_pipe_fini(pipe);
+		return err;
+	}
+
+	return 0;
+}
+
+static void lima_fini_gp_pipe(struct lima_device *dev)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
+
+	lima_gp_pipe_fini(dev);
+	lima_sched_pipe_fini(pipe);
+}
+
+static int lima_init_pp_pipe(struct lima_device *dev)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+	int err, i;
+
+	err = lima_sched_pipe_init(pipe, "pp");
+	if (err)
+		return err;
+
+	for (i = 0; i < LIMA_SCHED_PIPE_MAX_PROCESSOR; i++) {
+		struct lima_ip *pp = dev->ip + lima_ip_pp0 + i;
+		struct lima_ip *ppmmu = dev->ip + lima_ip_ppmmu0 + i;
+		struct lima_ip *l2_cache;
+
+		if (dev->id == lima_gpu_mali400)
+			l2_cache = dev->ip + lima_ip_l2_cache0;
+		else
+			l2_cache = dev->ip + lima_ip_l2_cache1 + (i >> 2);
+
+		if (pp->present && ppmmu->present && l2_cache->present) {
+			pipe->mmu[pipe->num_mmu++] = ppmmu;
+			pipe->processor[pipe->num_processor++] = pp;
+			if (!pipe->l2_cache[i >> 2])
+				pipe->l2_cache[pipe->num_l2_cache++] = l2_cache;
+		}
+	}
+
+	if (dev->ip[lima_ip_bcast].present) {
+		pipe->bcast_processor = dev->ip + lima_ip_pp_bcast;
+		pipe->bcast_mmu = dev->ip + lima_ip_ppmmu_bcast;
+	}
+
+	err = lima_pp_pipe_init(dev);
+	if (err) {
+		lima_sched_pipe_fini(pipe);
+		return err;
+	}
+
+	return 0;
+}
+
+static void lima_fini_pp_pipe(struct lima_device *dev)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+
+	lima_pp_pipe_fini(dev);
+	lima_sched_pipe_fini(pipe);
+}
+
+int lima_device_init(struct lima_device *ldev)
+{
+	int err, i;
+	struct resource *res;
+
+	dma_set_coherent_mask(ldev->dev, DMA_BIT_MASK(32));
+
+	err = lima_clk_init(ldev);
+	if (err) {
+		dev_err(ldev->dev, "clk init fail %d\n", err);
+		return err;
+	}
+
+	err = lima_regulator_init(ldev);
+	if (err) {
+		dev_err(ldev->dev, "regulator init fail %d\n", err);
+		goto err_out0;
+	}
+
+	ldev->empty_vm = lima_vm_create(ldev);
+	if (!ldev->empty_vm) {
+		err = -ENOMEM;
+		goto err_out1;
+	}
+
+	ldev->va_start = 0;
+	if (ldev->id == lima_gpu_mali450) {
+		ldev->va_end = LIMA_VA_RESERVE_START;
+		ldev->dlbu_cpu = dma_alloc_wc(
+			ldev->dev, LIMA_PAGE_SIZE,
+			&ldev->dlbu_dma, GFP_KERNEL);
+		if (!ldev->dlbu_cpu) {
+			err = -ENOMEM;
+			goto err_out2;
+		}
+	} else
+		ldev->va_end = LIMA_VA_RESERVE_END;
+
+	res = platform_get_resource(ldev->pdev, IORESOURCE_MEM, 0);
+	ldev->iomem = devm_ioremap_resource(ldev->dev, res);
+	if (IS_ERR(ldev->iomem)) {
+		dev_err(ldev->dev, "fail to ioremap iomem\n");
+		err = PTR_ERR(ldev->iomem);
+		goto err_out3;
+	}
+
+	for (i = 0; i < lima_ip_num; i++) {
+		err = lima_init_ip(ldev, i);
+		if (err)
+			goto err_out4;
+	}
+
+	err = lima_init_gp_pipe(ldev);
+	if (err)
+		goto err_out4;
+
+	err = lima_init_pp_pipe(ldev);
+	if (err)
+		goto err_out5;
+
+	return 0;
+
+err_out5:
+	lima_fini_gp_pipe(ldev);
+err_out4:
+	while (--i >= 0)
+		lima_fini_ip(ldev, i);
+err_out3:
+	if (ldev->dlbu_cpu)
+		dma_free_wc(ldev->dev, LIMA_PAGE_SIZE,
+			    ldev->dlbu_cpu, ldev->dlbu_dma);
+err_out2:
+	lima_vm_put(ldev->empty_vm);
+err_out1:
+	lima_regulator_fini(ldev);
+err_out0:
+	lima_clk_fini(ldev);
+	return err;
+}
+
+void lima_device_fini(struct lima_device *ldev)
+{
+	int i;
+
+	lima_fini_pp_pipe(ldev);
+	lima_fini_gp_pipe(ldev);
+
+	for (i = lima_ip_num - 1; i >= 0; i--)
+		lima_fini_ip(ldev, i);
+
+	if (ldev->dlbu_cpu)
+		dma_free_wc(ldev->dev, LIMA_PAGE_SIZE,
+			    ldev->dlbu_cpu, ldev->dlbu_dma);
+
+	lima_vm_put(ldev->empty_vm);
+
+	lima_regulator_fini(ldev);
+
+	lima_clk_fini(ldev);
+}
diff --git a/drivers/gpu/drm/lima/lima_device.h b/drivers/gpu/drm/lima/lima_device.h
new file mode 100644
index 000000000000..31158d86271c
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_device.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_DEVICE_H__
+#define __LIMA_DEVICE_H__
+
+#include <drm/drm_device.h>
+#include <linux/delay.h>
+
+#include "lima_sched.h"
+
+enum lima_gpu_id {
+	lima_gpu_mali400 = 0,
+	lima_gpu_mali450,
+	lima_gpu_num,
+};
+
+enum lima_ip_id {
+	lima_ip_pmu,
+	lima_ip_gpmmu,
+	lima_ip_ppmmu0,
+	lima_ip_ppmmu1,
+	lima_ip_ppmmu2,
+	lima_ip_ppmmu3,
+	lima_ip_ppmmu4,
+	lima_ip_ppmmu5,
+	lima_ip_ppmmu6,
+	lima_ip_ppmmu7,
+	lima_ip_gp,
+	lima_ip_pp0,
+	lima_ip_pp1,
+	lima_ip_pp2,
+	lima_ip_pp3,
+	lima_ip_pp4,
+	lima_ip_pp5,
+	lima_ip_pp6,
+	lima_ip_pp7,
+	lima_ip_l2_cache0,
+	lima_ip_l2_cache1,
+	lima_ip_l2_cache2,
+	lima_ip_dlbu,
+	lima_ip_bcast,
+	lima_ip_pp_bcast,
+	lima_ip_ppmmu_bcast,
+	lima_ip_num,
+};
+
+struct lima_device;
+
+struct lima_ip {
+	struct lima_device *dev;
+	enum lima_ip_id id;
+	bool present;
+
+	void __iomem *iomem;
+	int irq;
+
+	union {
+		/* gp/pp */
+		bool async_reset;
+		/* l2 cache */
+		spinlock_t lock;
+	} data;
+};
+
+enum lima_pipe_id {
+	lima_pipe_gp,
+	lima_pipe_pp,
+	lima_pipe_num,
+};
+
+struct lima_device {
+	struct device *dev;
+	struct drm_device *ddev;
+	struct platform_device *pdev;
+
+	enum lima_gpu_id id;
+	u32 gp_version;
+	u32 pp_version;
+	int num_pp;
+
+	void __iomem *iomem;
+	struct clk *clk_bus;
+	struct clk *clk_gpu;
+	struct reset_control *reset;
+	struct regulator *regulator;
+
+	struct lima_ip ip[lima_ip_num];
+	struct lima_sched_pipe pipe[lima_pipe_num];
+
+	struct lima_vm *empty_vm;
+	uint64_t va_start;
+	uint64_t va_end;
+
+	u32 *dlbu_cpu;
+	dma_addr_t dlbu_dma;
+};
+
+static inline struct lima_device *
+to_lima_dev(struct drm_device *dev)
+{
+	return dev->dev_private;
+}
+
+int lima_device_init(struct lima_device *ldev);
+void lima_device_fini(struct lima_device *ldev);
+
+const char *lima_ip_name(struct lima_ip *ip);
+
+typedef int (*lima_poll_func_t)(struct lima_ip *);
+
+static inline int lima_poll_timeout(struct lima_ip *ip, lima_poll_func_t func,
+				    int sleep_us, int timeout_us)
+{
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us);
+
+	might_sleep_if(sleep_us);
+	while (1) {
+		if (func(ip))
+			return 0;
+
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0)
+			return -ETIMEDOUT;
+
+		if (sleep_us)
+			usleep_range((sleep_us >> 2) + 1, sleep_us);
+	}
+	return 0;
+}
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_dlbu.c b/drivers/gpu/drm/lima/lima_dlbu.c
new file mode 100644
index 000000000000..8399ceffb94b
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_dlbu.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/io.h>
+#include <linux/device.h>
+
+#include "lima_device.h"
+#include "lima_dlbu.h"
+#include "lima_vm.h"
+#include "lima_regs.h"
+
+#define dlbu_write(reg, data) writel(data, ip->iomem + reg)
+#define dlbu_read(reg) readl(ip->iomem + reg)
+
+void lima_dlbu_enable(struct lima_device *dev, int num_pp)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+	struct lima_ip *ip = dev->ip + lima_ip_dlbu;
+	int i, mask = 0;
+
+	for (i = 0; i < num_pp; i++) {
+		struct lima_ip *pp = pipe->processor[i];
+
+		mask |= 1 << (pp->id - lima_ip_pp0);
+	}
+
+	dlbu_write(LIMA_DLBU_PP_ENABLE_MASK, mask);
+}
+
+void lima_dlbu_disable(struct lima_device *dev)
+{
+	struct lima_ip *ip = dev->ip + lima_ip_dlbu;
+
+	dlbu_write(LIMA_DLBU_PP_ENABLE_MASK, 0);
+}
+
+void lima_dlbu_set_reg(struct lima_ip *ip, u32 *reg)
+{
+	dlbu_write(LIMA_DLBU_TLLIST_VBASEADDR, reg[0]);