Adding upstream version 5.10.209.upstream/5.10.209

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

34 files changed, 5101 insertions, 0 deletions

diff --git a/drivers/gpu/drm/lima/Kconfig b/drivers/gpu/drm/lima/Kconfig
new file mode 100644
index 000000000..fa1d4f5df
--- /dev/null
+++ b/drivers/gpu/drm/lima/Kconfig
@@ -0,0 +1,16 @@
+# 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
+       depends on MMU
+       depends on COMMON_CLK
+       depends on OF
+       select DRM_SCHED
+       select DRM_GEM_SHMEM_HELPER
+       select PM_DEVFREQ
+       select DEVFREQ_GOV_SIMPLE_ONDEMAND
+       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 000000000..ca2097b8e
--- /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_dlbu.o \
+	lima_bcast.o \
+	lima_trace.o \
+	lima_devfreq.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 000000000..fbc43f243
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_bcast.c
@@ -0,0 +1,62 @@
+// 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);
+}
+
+static int lima_bcast_hw_init(struct lima_ip *ip)
+{
+	bcast_write(LIMA_BCAST_BROADCAST_MASK, ip->data.mask << 16);
+	bcast_write(LIMA_BCAST_INTERRUPT_MASK, ip->data.mask);
+	return 0;
+}
+
+int lima_bcast_resume(struct lima_ip *ip)
+{
+	return lima_bcast_hw_init(ip);
+}
+
+void lima_bcast_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_bcast_init(struct lima_ip *ip)
+{
+	int i;
+
+	for (i = lima_ip_pp0; i <= lima_ip_pp7; i++) {
+		if (ip->dev->ip[i].present)
+			ip->data.mask |= 1 << (i - lima_ip_pp0);
+	}
+
+	return lima_bcast_hw_init(ip);
+}
+
+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 000000000..465ee587b
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_bcast.h
@@ -0,0 +1,16 @@
+/* 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_resume(struct lima_ip *ip);
+void lima_bcast_suspend(struct lima_ip *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 000000000..891d5cd50
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_ctx.c
@@ -0,0 +1,101 @@
+// 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, ctx, xa_limit_32b, GFP_KERNEL);
+	if (err < 0)
+		goto err_out0;
+
+	ctx->pid = task_pid_nr(current);
+	get_task_comm(ctx->pname, current);
+
+	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 000000000..74e2be090
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_ctx.h
@@ -0,0 +1,35 @@
+/* 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 <linux/sched.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;
+
+	/* debug info */
+	char pname[TASK_COMM_LEN];
+	pid_t pid;
+};
+
+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_devfreq.c b/drivers/gpu/drm/lima/lima_devfreq.c
new file mode 100644
index 000000000..bbe028177
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_devfreq.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+ *
+ * Based on panfrost_devfreq.c:
+ *   Copyright 2019 Collabora ltd.
+ */
+#include <linux/clk.h>
+#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/property.h>
+
+#include "lima_device.h"
+#include "lima_devfreq.h"
+
+static void lima_devfreq_update_utilization(struct lima_devfreq *devfreq)
+{
+	ktime_t now, last;
+
+	now = ktime_get();
+	last = devfreq->time_last_update;
+
+	if (devfreq->busy_count > 0)
+		devfreq->busy_time += ktime_sub(now, last);
+	else
+		devfreq->idle_time += ktime_sub(now, last);
+
+	devfreq->time_last_update = now;
+}
+
+static int lima_devfreq_target(struct device *dev, unsigned long *freq,
+			       u32 flags)
+{
+	struct dev_pm_opp *opp;
+	int err;
+
+	opp = devfreq_recommended_opp(dev, freq, flags);
+	if (IS_ERR(opp))
+		return PTR_ERR(opp);
+	dev_pm_opp_put(opp);
+
+	err = dev_pm_opp_set_rate(dev, *freq);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void lima_devfreq_reset(struct lima_devfreq *devfreq)
+{
+	devfreq->busy_time = 0;
+	devfreq->idle_time = 0;
+	devfreq->time_last_update = ktime_get();
+}
+
+static int lima_devfreq_get_dev_status(struct device *dev,
+				       struct devfreq_dev_status *status)
+{
+	struct lima_device *ldev = dev_get_drvdata(dev);
+	struct lima_devfreq *devfreq = &ldev->devfreq;
+	unsigned long irqflags;
+
+	status->current_frequency = clk_get_rate(ldev->clk_gpu);
+
+	spin_lock_irqsave(&devfreq->lock, irqflags);
+
+	lima_devfreq_update_utilization(devfreq);
+
+	status->total_time = ktime_to_ns(ktime_add(devfreq->busy_time,
+						   devfreq->idle_time));
+	status->busy_time = ktime_to_ns(devfreq->busy_time);
+
+	lima_devfreq_reset(devfreq);
+
+	spin_unlock_irqrestore(&devfreq->lock, irqflags);
+
+	dev_dbg(ldev->dev, "busy %lu total %lu %lu %% freq %lu MHz\n",
+		status->busy_time, status->total_time,
+		status->busy_time / (status->total_time / 100),
+		status->current_frequency / 1000 / 1000);
+
+	return 0;
+}
+
+static struct devfreq_dev_profile lima_devfreq_profile = {
+	.polling_ms = 50, /* ~3 frames */
+	.target = lima_devfreq_target,
+	.get_dev_status = lima_devfreq_get_dev_status,
+};
+
+void lima_devfreq_fini(struct lima_device *ldev)
+{
+	struct lima_devfreq *devfreq = &ldev->devfreq;
+
+	if (devfreq->cooling) {
+		devfreq_cooling_unregister(devfreq->cooling);
+		devfreq->cooling = NULL;
+	}
+
+	if (devfreq->devfreq) {
+		devm_devfreq_remove_device(ldev->dev, devfreq->devfreq);
+		devfreq->devfreq = NULL;
+	}
+
+	if (devfreq->opp_of_table_added) {
+		dev_pm_opp_of_remove_table(ldev->dev);
+		devfreq->opp_of_table_added = false;
+	}
+
+	if (devfreq->regulators_opp_table) {
+		dev_pm_opp_put_regulators(devfreq->regulators_opp_table);
+		devfreq->regulators_opp_table = NULL;
+	}
+
+	if (devfreq->clkname_opp_table) {
+		dev_pm_opp_put_clkname(devfreq->clkname_opp_table);
+		devfreq->clkname_opp_table = NULL;
+	}
+}
+
+int lima_devfreq_init(struct lima_device *ldev)
+{
+	struct thermal_cooling_device *cooling;
+	struct device *dev = ldev->dev;
+	struct opp_table *opp_table;
+	struct devfreq *devfreq;
+	struct lima_devfreq *ldevfreq = &ldev->devfreq;
+	struct dev_pm_opp *opp;
+	unsigned long cur_freq;
+	int ret;
+
+	if (!device_property_present(dev, "operating-points-v2"))
+		/* Optional, continue without devfreq */
+		return 0;
+
+	spin_lock_init(&ldevfreq->lock);
+
+	opp_table = dev_pm_opp_set_clkname(dev, "core");
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+		goto err_fini;
+	}
+
+	ldevfreq->clkname_opp_table = opp_table;
+
+	opp_table = dev_pm_opp_set_regulators(dev,
+					      (const char *[]){ "mali" },
+					      1);
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+
+		/* Continue if the optional regulator is missing */
+		if (ret != -ENODEV)
+			goto err_fini;
+	} else {
+		ldevfreq->regulators_opp_table = opp_table;
+	}
+
+	ret = dev_pm_opp_of_add_table(dev);
+	if (ret)
+		goto err_fini;
+	ldevfreq->opp_of_table_added = true;
+
+	lima_devfreq_reset(ldevfreq);
+
+	cur_freq = clk_get_rate(ldev->clk_gpu);
+
+	opp = devfreq_recommended_opp(dev, &cur_freq, 0);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_fini;
+	}
+
+	lima_devfreq_profile.initial_freq = cur_freq;
+	dev_pm_opp_put(opp);
+
+	devfreq = devm_devfreq_add_device(dev, &lima_devfreq_profile,
+					  DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
+	if (IS_ERR(devfreq)) {
+		dev_err(dev, "Couldn't initialize GPU devfreq\n");
+		ret = PTR_ERR(devfreq);
+		goto err_fini;
+	}
+
+	ldevfreq->devfreq = devfreq;
+
+	cooling = of_devfreq_cooling_register(dev->of_node, devfreq);
+	if (IS_ERR(cooling))
+		dev_info(dev, "Failed to register cooling device\n");
+	else
+		ldevfreq->cooling = cooling;
+
+	return 0;
+
+err_fini:
+	lima_devfreq_fini(ldev);
+	return ret;
+}
+
+void lima_devfreq_record_busy(struct lima_devfreq *devfreq)
+{
+	unsigned long irqflags;
+
+	if (!devfreq->devfreq)
+		return;
+
+	spin_lock_irqsave(&devfreq->lock, irqflags);
+
+	lima_devfreq_update_utilization(devfreq);
+
+	devfreq->busy_count++;
+
+	spin_unlock_irqrestore(&devfreq->lock, irqflags);
+}
+
+void lima_devfreq_record_idle(struct lima_devfreq *devfreq)
+{
+	unsigned long irqflags;
+
+	if (!devfreq->devfreq)
+		return;
+
+	spin_lock_irqsave(&devfreq->lock, irqflags);
+
+	lima_devfreq_update_utilization(devfreq);
+
+	WARN_ON(--devfreq->busy_count < 0);
+
+	spin_unlock_irqrestore(&devfreq->lock, irqflags);
+}
+
+int lima_devfreq_resume(struct lima_devfreq *devfreq)
+{
+	unsigned long irqflags;
+
+	if (!devfreq->devfreq)
+		return 0;
+
+	spin_lock_irqsave(&devfreq->lock, irqflags);
+
+	lima_devfreq_reset(devfreq);
+
+	spin_unlock_irqrestore(&devfreq->lock, irqflags);
+
+	return devfreq_resume_device(devfreq->devfreq);
+}
+
+int lima_devfreq_suspend(struct lima_devfreq *devfreq)
+{
+	if (!devfreq->devfreq)
+		return 0;
+
+	return devfreq_suspend_device(devfreq->devfreq);
+}
diff --git a/drivers/gpu/drm/lima/lima_devfreq.h b/drivers/gpu/drm/lima/lima_devfreq.h
new file mode 100644
index 000000000..5eed2975a
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_devfreq.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2020 Martin Blumenstingl <martin.blumenstingl@googlemail.com> */
+
+#ifndef __LIMA_DEVFREQ_H__
+#define __LIMA_DEVFREQ_H__
+
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+
+struct devfreq;
+struct opp_table;
+struct thermal_cooling_device;
+
+struct lima_device;
+
+struct lima_devfreq {
+	struct devfreq *devfreq;
+	struct opp_table *clkname_opp_table;
+	struct opp_table *regulators_opp_table;
+	struct thermal_cooling_device *cooling;
+	bool opp_of_table_added;
+
+	ktime_t busy_time;
+	ktime_t idle_time;
+	ktime_t time_last_update;
+	int busy_count;
+	/*
+	 * Protect busy_time, idle_time, time_last_update and busy_count
+	 * because these can be updated concurrently, for example by the GP
+	 * and PP interrupts.
+	 */
+	spinlock_t lock;
+};
+
+int lima_devfreq_init(struct lima_device *ldev);
+void lima_devfreq_fini(struct lima_device *ldev);
+
+void lima_devfreq_record_busy(struct lima_devfreq *devfreq);
+void lima_devfreq_record_idle(struct lima_devfreq *devfreq);
+
+int lima_devfreq_resume(struct lima_devfreq *devfreq);
+int lima_devfreq_suspend(struct lima_devfreq *devfreq);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c
new file mode 100644
index 000000000..36c990589
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_device.c
@@ -0,0 +1,534 @@
+// 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);
+	int (*resume)(struct lima_ip *ip);
+	void (*suspend)(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, \
+		.resume = lima_##func##_resume, \
+		.suspend = lima_##func##_suspend, \
+	}
+
+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_enable(struct lima_device *dev)
+{
+	int err;
+
+	err = clk_prepare_enable(dev->clk_bus);
+	if (err)
+		return err;
+
+	err = clk_prepare_enable(dev->clk_gpu);
+	if (err)
+		goto error_out0;
+
+	if (dev->reset) {
+		err = reset_control_deassert(dev->reset);
+		if (err) {
+			dev_err(dev->dev,
+				"reset controller deassert failed %d\n", 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_disable(struct lima_device *dev)
+{
+	if (dev->reset)
+		reset_control_assert(dev->reset);
+	clk_disable_unprepare(dev->clk_gpu);
+	clk_disable_unprepare(dev->clk_bus);
+}
+
+static int lima_clk_init(struct lima_device *dev)
+{
+	int err;
+
+	dev->clk_bus = devm_clk_get(dev->dev, "bus");
+	if (IS_ERR(dev->clk_bus)) {
+		err = PTR_ERR(dev->clk_bus);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev->dev, "get bus clk failed %d\n", err);
+		dev->clk_bus = NULL;
+		return err;
+	}
+
+	dev->clk_gpu = devm_clk_get(dev->dev, "core");
+	if (IS_ERR(dev->clk_gpu)) {
+		err = PTR_ERR(dev->clk_gpu);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev->dev, "get core clk failed %d\n", err);
+		dev->clk_gpu = NULL;
+		return err;
+	}
+
+	dev->reset = devm_reset_control_array_get_optional_shared(dev->dev);
+	if (IS_ERR(dev->reset)) {
+		err = PTR_ERR(dev->reset);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev->dev, "get reset controller failed %d\n",
+				err);
+		dev->reset = NULL;
+		return err;
+	}
+
+	return lima_clk_enable(dev);
+}
+
+static void lima_clk_fini(struct lima_device *dev)
+{
+	lima_clk_disable(dev);
+}
+
+static int lima_regulator_enable(struct lima_device *dev)
+{
+	int ret;
+
+	if (!dev->regulator)
+		return 0;
+
+	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_disable(struct lima_device *dev)
+{
+	if (dev->regulator)
+		regulator_disable(dev->regulator);
+}
+
+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;
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev->dev, "failed to get regulator: %d\n", ret);
+		return ret;
+	}
+
+	return lima_regulator_enable(dev);
+}
+
+static void lima_regulator_fini(struct lima_device *dev)
+{
+	lima_regulator_disable(dev);
+}
+
+static int lima_init_ip(struct lima_device *dev, int index)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct lima_ip_desc *desc = lima_ip_desc + index;
+	struct lima_ip *ip = dev->ip + index;
+	const char *irq_name = desc->irq_name;
+	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 (irq_name) {
+		err = must ? platform_get_irq_byname(pdev, irq_name) :
+			     platform_get_irq_byname_optional(pdev, 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_resume_ip(struct lima_device *ldev, int index)
+{
+	struct lima_ip_desc *desc = lima_ip_desc + index;
+	struct lima_ip *ip = ldev->ip + index;
+	int ret = 0;
+
+	if (ip->present)
+		ret = desc->resume(ip);
+
+	return ret;
+}
+
+static void lima_suspend_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->suspend(ip);
+}
+
+static int lima_init_gp_pipe(struct lima_device *dev)
+{
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
+	int err;
+
+	pipe->ldev = dev;
+
+	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;
+
+	pipe->ldev = dev;
+
+	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)
+{
+	struct platform_device *pdev = to_platform_device(ldev->dev);
+	int err, i;
+
+	dma_set_coherent_mask(ldev->dev, DMA_BIT_MASK(32));
+	dma_set_max_seg_size(ldev->dev, UINT_MAX);
+
+	err = lima_clk_init(ldev);
+	if (err)
+		return err;
+
+	err = lima_regulator_init(ldev);
+	if (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 | __GFP_NOWARN);
+		if (!ldev->dlbu_cpu) {
+			err = -ENOMEM;
+			goto err_out2;
+		}
+	} else
+		ldev->va_end = LIMA_VA_RESERVE_END;
+
+	ldev->iomem = devm_platform_ioremap_resource(pdev, 0);
+	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;
+
+	ldev->dump.magic = LIMA_DUMP_MAGIC;
+	ldev->dump.version_major = LIMA_DUMP_MAJOR;
+	ldev->dump.version_minor = LIMA_DUMP_MINOR;
+	INIT_LIST_HEAD(&ldev->error_task_list);
+	mutex_init(&ldev->error_task_list_lock);
+
+	dev_info(ldev->dev, "bus rate = %lu\n", clk_get_rate(ldev->clk_bus));
+	dev_info(ldev->dev, "mod rate = %lu", clk_get_rate(ldev->clk_gpu));
+
+	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;
+	struct lima_sched_error_task *et, *tmp;
+
+	list_for_each_entry_safe(et, tmp, &ldev->error_task_list, list) {
+		list_del(&et->list);
+		kvfree(et);
+	}
+	mutex_destroy(&ldev->error_task_list_lock);
+
+	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);
+}
+
+int lima_device_resume(struct device *dev)
+{
+	struct lima_device *ldev = dev_get_drvdata(dev);
+	int i, err;
+
+	err = lima_clk_enable(ldev);
+	if (err) {
+		dev_err(dev, "resume clk fail %d\n", err);
+		return err;
+	}
+
+	err = lima_regulator_enable(ldev);
+	if (err) {
+		dev_err(dev, "resume regulator fail %d\n", err);
+		goto err_out0;
+	}
+
+	for (i = 0; i < lima_ip_num; i++) {
+		err = lima_resume_ip(ldev, i);
+		if (err) {
+			dev_err(dev, "resume ip %d fail\n", i);
+			goto err_out1;
+		}
+	}
+
+	err = lima_devfreq_resume(&ldev->devfreq);
+	if (err) {
+		dev_err(dev, "devfreq resume fail\n");
+		goto err_out1;
+	}
+
+	return 0;
+
+err_out1:
+	while (--i >= 0)
+		lima_suspend_ip(ldev, i);
+	lima_regulator_disable(ldev);
+err_out0:
+	lima_clk_disable(ldev);
+	return err;
+}
+
+int lima_device_suspend(struct device *dev)
+{
+	struct lima_device *ldev = dev_get_drvdata(dev);
+	int i, err;
+
+	/* check any task running */
+	for (i = 0; i < lima_pipe_num; i++) {
+		if (atomic_read(&ldev->pipe[i].base.hw_rq_count))
+			return -EBUSY;
+	}
+
+	err = lima_devfreq_suspend(&ldev->devfreq);
+	if (err) {
+		dev_err(dev, "devfreq suspend fail\n");
+		return err;
+	}
+
+	for (i = lima_ip_num - 1; i >= 0; i--)
+		lima_suspend_ip(ldev, i);
+
+	lima_regulator_disable(ldev);
+
+	lima_clk_disable(ldev);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/lima/lima_device.h b/drivers/gpu/drm/lima/lima_device.h
new file mode 100644
index 000000000..41b9d7b4b
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_device.h
@@ -0,0 +1,146 @@
+/* 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 <linux/list.h>
+#include <linux/mutex.h>
+
+#include "lima_sched.h"
+#include "lima_dump.h"
+#include "lima_devfreq.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;
+		/* pmu/bcast */
+		u32 mask;
+	} data;
+};
+
+enum lima_pipe_id {
+	lima_pipe_gp,
+	lima_pipe_pp,
+	lima_pipe_num,
+};
+
+struct lima_device {
+	struct device *dev;
+	struct drm_device *ddev;
+
+	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;
+
+	struct lima_devfreq devfreq;
+
+	/* debug info */
+	struct lima_dump_head dump;
+	struct list_head error_task_list;
+	struct mutex error_task_list_lock;
+};
+
+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;
+}
+
+int lima_device_suspend(struct device *dev);
+int lima_device_resume(struct device *dev);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_dlbu.c b/drivers/gpu/drm/lima/lima_dlbu.c
new file mode 100644
index 000000000..c1d5ea35d
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_dlbu.c
@@ -0,0 +1,73 @@
+// 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]);
+	dlbu_write(LIMA_DLBU_FB_DIM, reg[1]);
+	dlbu_write(LIMA_DLBU_TLLIST_CONF, reg[2]);
+	dlbu_write(LIMA_DLBU_START_TILE_POS, reg[3]);
+}
+
+static int lima_dlbu_hw_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+
+	dlbu_write(LIMA_DLBU_MASTER_TLLIST_PHYS_ADDR, dev->dlbu_dma | 1);
+	dlbu_write(LIMA_DLBU_MASTER_TLLIST_VADDR, LIMA_VA_RESERVE_DLBU);
+
+	return 0;
+}
+
+int lima_dlbu_resume(struct lima_ip *ip)
+{
+	return lima_dlbu_hw_init(ip);
+}
+
+void lima_dlbu_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_dlbu_init(struct lima_ip *ip)
+{
+	return lima_dlbu_hw_init(ip);
+}
+
+void lima_dlbu_fini(struct lima_ip *ip)
+{
+
+}
diff --git a/drivers/gpu/drm/lima/lima_dlbu.h b/drivers/gpu/drm/lima/lima_dlbu.h
new file mode 100644
index 000000000..be71daaae
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_dlbu.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_DLBU_H__
+#define __LIMA_DLBU_H__
+
+struct lima_ip;
+struct lima_device;
+
+void lima_dlbu_enable(struct lima_device *dev, int num_pp);
+void lima_dlbu_disable(struct lima_device *dev);
+
+void lima_dlbu_set_reg(struct lima_ip *ip, u32 *reg);
+
+int lima_dlbu_resume(struct lima_ip *ip);
+void lima_dlbu_suspend(struct lima_ip *ip);
+int lima_dlbu_init(struct lima_ip *ip);
+void lima_dlbu_fini(struct lima_ip *ip);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c
new file mode 100644
index 000000000..65dc0dc2c
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_drv.c
@@ -0,0 +1,491 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <drm/drm_ioctl.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_prime.h>
+#include <drm/lima_drm.h>
+
+#include "lima_device.h"
+#include "lima_drv.h"
+#include "lima_gem.h"
+#include "lima_vm.h"
+
+int lima_sched_timeout_ms;
+uint lima_heap_init_nr_pages = 8;
+uint lima_max_error_tasks;
+uint lima_job_hang_limit;
+
+MODULE_PARM_DESC(sched_timeout_ms, "task run timeout in ms");
+module_param_named(sched_timeout_ms, lima_sched_timeout_ms, int, 0444);
+
+MODULE_PARM_DESC(heap_init_nr_pages, "heap buffer init number of pages");
+module_param_named(heap_init_nr_pages, lima_heap_init_nr_pages, uint, 0444);
+
+MODULE_PARM_DESC(max_error_tasks, "max number of error tasks to save");
+module_param_named(max_error_tasks, lima_max_error_tasks, uint, 0644);
+
+MODULE_PARM_DESC(job_hang_limit, "number of times to allow a job to hang before dropping it (default 0)");
+module_param_named(job_hang_limit, lima_job_hang_limit, uint, 0444);
+
+static int lima_ioctl_get_param(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_get_param *args = data;
+	struct lima_device *ldev = to_lima_dev(dev);
+
+	if (args->pad)
+		return -EINVAL;
+
+	switch (args->param) {
+	case DRM_LIMA_PARAM_GPU_ID:
+		switch (ldev->id) {
+		case lima_gpu_mali400:
+			args->value = DRM_LIMA_PARAM_GPU_ID_MALI400;
+			break;
+		case lima_gpu_mali450:
+			args->value = DRM_LIMA_PARAM_GPU_ID_MALI450;
+			break;
+		default:
+			args->value = DRM_LIMA_PARAM_GPU_ID_UNKNOWN;
+			break;
+		}
+		break;
+
+	case DRM_LIMA_PARAM_NUM_PP:
+		args->value = ldev->pipe[lima_pipe_pp].num_processor;
+		break;
+
+	case DRM_LIMA_PARAM_GP_VERSION:
+		args->value = ldev->gp_version;
+		break;
+
+	case DRM_LIMA_PARAM_PP_VERSION:
+		args->value = ldev->pp_version;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int lima_ioctl_gem_create(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_gem_create *args = data;
+
+	if (args->pad)
+		return -EINVAL;
+
+	if (args->flags & ~(LIMA_BO_FLAG_HEAP))
+		return -EINVAL;
+
+	if (args->size == 0)
+		return -EINVAL;
+
+	return lima_gem_create_handle(dev, file, args->size, args->flags, &args->handle);
+}
+
+static int lima_ioctl_gem_info(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_gem_info *args = data;
+
+	return lima_gem_get_info(file, args->handle, &args->va, &args->offset);
+}
+
+static int lima_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_gem_submit *args = data;
+	struct lima_device *ldev = to_lima_dev(dev);
+	struct lima_drm_priv *priv = file->driver_priv;
+	struct drm_lima_gem_submit_bo *bos;
+	struct lima_sched_pipe *pipe;
+	struct lima_sched_task *task;
+	struct lima_ctx *ctx;
+	struct lima_submit submit = {0};
+	size_t size;
+	int err = 0;
+
+	if (args->pipe >= lima_pipe_num || args->nr_bos == 0)
+		return -EINVAL;
+
+	if (args->flags & ~(LIMA_SUBMIT_FLAG_EXPLICIT_FENCE))
+		return -EINVAL;
+
+	pipe = ldev->pipe + args->pipe;
+	if (args->frame_size != pipe->frame_size)
+		return -EINVAL;
+
+	bos = kvcalloc(args->nr_bos, sizeof(*submit.bos) + sizeof(*submit.lbos), GFP_KERNEL);
+	if (!bos)
+		return -ENOMEM;
+
+	size = args->nr_bos * sizeof(*submit.bos);
+	if (copy_from_user(bos, u64_to_user_ptr(args->bos), size)) {
+		err = -EFAULT;
+		goto out0;
+	}
+
+	task = kmem_cache_zalloc(pipe->task_slab, GFP_KERNEL);
+	if (!task) {
+		err = -ENOMEM;
+		goto out0;
+	}
+
+	task->frame = task + 1;
+	if (copy_from_user(task->frame, u64_to_user_ptr(args->frame), args->frame_size)) {
+		err = -EFAULT;
+		goto out1;
+	}
+
+	err = pipe->task_validate(pipe, task);
+	if (err)
+		goto out1;
+
+	ctx = lima_ctx_get(&priv->ctx_mgr, args->ctx);
+	if (!ctx) {
+		err = -ENOENT;
+		goto out1;
+	}
+
+	submit.pipe = args->pipe;
+	submit.bos = bos;
+	submit.lbos = (void *)bos + size;
+	submit.nr_bos = args->nr_bos;
+	submit.task = task;
+	submit.ctx = ctx;
+	submit.flags = args->flags;
+	submit.in_sync[0] = args->in_sync[0];
+	submit.in_sync[1] = args->in_sync[1];
+	submit.out_sync = args->out_sync;
+
+	err = lima_gem_submit(file, &submit);
+
+	lima_ctx_put(ctx);
+out1:
+	if (err)
+		kmem_cache_free(pipe->task_slab, task);
+out0:
+	kvfree(bos);
+	return err;
+}
+
+static int lima_ioctl_gem_wait(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_gem_wait *args = data;
+
+	if (args->op & ~(LIMA_GEM_WAIT_READ|LIMA_GEM_WAIT_WRITE))
+		return -EINVAL;
+
+	return lima_gem_wait(file, args->handle, args->op, args->timeout_ns);
+}
+
+static int lima_ioctl_ctx_create(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_ctx_create *args = data;
+	struct lima_drm_priv *priv = file->driver_priv;
+	struct lima_device *ldev = to_lima_dev(dev);
+
+	if (args->_pad)
+		return -EINVAL;
+
+	return lima_ctx_create(ldev, &priv->ctx_mgr, &args->id);
+}
+
+static int lima_ioctl_ctx_free(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_lima_ctx_create *args = data;
+	struct lima_drm_priv *priv = file->driver_priv;
+
+	if (args->_pad)
+		return -EINVAL;
+
+	return lima_ctx_free(&priv->ctx_mgr, args->id);
+}
+
+static int lima_drm_driver_open(struct drm_device *dev, struct drm_file *file)
+{
+	int err;
+	struct lima_drm_priv *priv;
+	struct lima_device *ldev = to_lima_dev(dev);
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->vm = lima_vm_create(ldev);
+	if (!priv->vm) {
+		err = -ENOMEM;
+		goto err_out0;
+	}
+
+	lima_ctx_mgr_init(&priv->ctx_mgr);
+
+	file->driver_priv = priv;
+	return 0;
+
+err_out0:
+	kfree(priv);
+	return err;
+}
+
+static void lima_drm_driver_postclose(struct drm_device *dev, struct drm_file *file)
+{
+	struct lima_drm_priv *priv = file->driver_priv;
+
+	lima_ctx_mgr_fini(&priv->ctx_mgr);
+	lima_vm_put(priv->vm);
+	kfree(priv);
+}
+
+static const struct drm_ioctl_desc lima_drm_driver_ioctls[] = {
+	DRM_IOCTL_DEF_DRV(LIMA_GET_PARAM, lima_ioctl_get_param, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_GEM_CREATE, lima_ioctl_gem_create, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_GEM_INFO, lima_ioctl_gem_info, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_GEM_SUBMIT, lima_ioctl_gem_submit, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_GEM_WAIT, lima_ioctl_gem_wait, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_CTX_CREATE, lima_ioctl_ctx_create, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(LIMA_CTX_FREE, lima_ioctl_ctx_free, DRM_RENDER_ALLOW),
+};
+
+DEFINE_DRM_GEM_FOPS(lima_drm_driver_fops);
+
+/**
+ * Changelog:
+ *
+ * - 1.1.0 - add heap buffer support
+ */
+
+static struct drm_driver lima_drm_driver = {
+	.driver_features    = DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ,
+	.open               = lima_drm_driver_open,
+	.postclose          = lima_drm_driver_postclose,
+	.ioctls             = lima_drm_driver_ioctls,
+	.num_ioctls         = ARRAY_SIZE(lima_drm_driver_ioctls),
+	.fops               = &lima_drm_driver_fops,
+	.name               = "lima",
+	.desc               = "lima DRM",
+	.date               = "20191231",
+	.major              = 1,
+	.minor              = 1,
+	.patchlevel         = 0,
+
+	.gem_create_object  = lima_gem_create_object,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
+	.gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table,
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.gem_prime_mmap = drm_gem_prime_mmap,
+};
+
+struct lima_block_reader {
+	void *dst;
+	size_t base;
+	size_t count;
+	size_t off;
+	ssize_t read;
+};
+
+static bool lima_read_block(struct lima_block_reader *reader,
+			    void *src, size_t src_size)
+{
+	size_t max_off = reader->base + src_size;
+
+	if (reader->off < max_off) {
+		size_t size = min_t(size_t, max_off - reader->off,
+				    reader->count);
+
+		memcpy(reader->dst, src + (reader->off - reader->base), size);
+
+		reader->dst += size;
+		reader->off += size;
+		reader->read += size;
+		reader->count -= size;
+	}
+
+	reader->base = max_off;
+
+	return !!reader->count;
+}
+
+static ssize_t lima_error_state_read(struct file *filp, struct kobject *kobj,
+				     struct bin_attribute *attr, char *buf,
+				     loff_t off, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct lima_device *ldev = dev_get_drvdata(dev);
+	struct lima_sched_error_task *et;
+	struct lima_block_reader reader = {
+		.dst = buf,
+		.count = count,
+		.off = off,
+	};
+
+	mutex_lock(&ldev->error_task_list_lock);
+
+	if (lima_read_block(&reader, &ldev->dump, sizeof(ldev->dump))) {
+		list_for_each_entry(et, &ldev->error_task_list, list) {
+			if (!lima_read_block(&reader, et->data, et->size))
+				break;
+		}
+	}
+
+	mutex_unlock(&ldev->error_task_list_lock);
+	return reader.read;
+}
+
+static ssize_t lima_error_state_write(struct file *file, struct kobject *kobj,
+				      struct bin_attribute *attr, char *buf,
+				      loff_t off, size_t count)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct lima_device *ldev = dev_get_drvdata(dev);
+	struct lima_sched_error_task *et, *tmp;
+
+	mutex_lock(&ldev->error_task_list_lock);
+
+	list_for_each_entry_safe(et, tmp, &ldev->error_task_list, list) {
+		list_del(&et->list);
+		kvfree(et);
+	}
+
+	ldev->dump.size = 0;
+	ldev->dump.num_tasks = 0;
+
+	mutex_unlock(&ldev->error_task_list_lock);
+
+	return count;
+}
+
+static const struct bin_attribute lima_error_state_attr = {
+	.attr.name = "error",
+	.attr.mode = 0600,
+	.size = 0,
+	.read = lima_error_state_read,
+	.write = lima_error_state_write,
+};
+
+static int lima_pdev_probe(struct platform_device *pdev)
+{
+	struct lima_device *ldev;
+	struct drm_device *ddev;
+	int err;
+
+	err = lima_sched_slab_init();
+	if (err)
+		return err;
+
+	ldev = devm_kzalloc(&pdev->dev, sizeof(*ldev), GFP_KERNEL);
+	if (!ldev) {
+		err = -ENOMEM;
+		goto err_out0;
+	}
+
+	ldev->dev = &pdev->dev;
+	ldev->id = (enum lima_gpu_id)of_device_get_match_data(&pdev->dev);
+
+	platform_set_drvdata(pdev, ldev);
+
+	/* Allocate and initialize the DRM device. */
+	ddev = drm_dev_alloc(&lima_drm_driver, &pdev->dev);
+	if (IS_ERR(ddev)) {
+		err = PTR_ERR(ddev);
+		goto err_out0;
+	}
+
+	ddev->dev_private = ldev;
+	ldev->ddev = ddev;
+
+	err = lima_device_init(ldev);
+	if (err)
+		goto err_out1;
+
+	err = lima_devfreq_init(ldev);
+	if (err) {
+		dev_err(&pdev->dev, "Fatal error during devfreq init\n");
+		goto err_out2;
+	}
+
+	pm_runtime_set_active(ldev->dev);
+	pm_runtime_mark_last_busy(ldev->dev);
+	pm_runtime_set_autosuspend_delay(ldev->dev, 200);
+	pm_runtime_use_autosuspend(ldev->dev);
+	pm_runtime_enable(ldev->dev);
+
+	/*
+	 * Register the DRM device with the core and the connectors with
+	 * sysfs.
+	 */
+	err = drm_dev_register(ddev, 0);
+	if (err < 0)
+		goto err_out3;
+
+	if (sysfs_create_bin_file(&ldev->dev->kobj, &lima_error_state_attr))
+		dev_warn(ldev->dev, "fail to create error state sysfs\n");
+
+	return 0;
+
+err_out3:
+	pm_runtime_disable(ldev->dev);
+	lima_devfreq_fini(ldev);
+err_out2:
+	lima_device_fini(ldev);
+err_out1:
+	drm_dev_put(ddev);
+err_out0:
+	lima_sched_slab_fini();
+	return err;
+}
+
+static int lima_pdev_remove(struct platform_device *pdev)
+{
+	struct lima_device *ldev = platform_get_drvdata(pdev);
+	struct drm_device *ddev = ldev->ddev;
+
+	sysfs_remove_bin_file(&ldev->dev->kobj, &lima_error_state_attr);
+
+	drm_dev_unregister(ddev);
+
+	/* stop autosuspend to make sure device is in active state */
+	pm_runtime_set_autosuspend_delay(ldev->dev, -1);
+	pm_runtime_disable(ldev->dev);
+
+	lima_devfreq_fini(ldev);
+	lima_device_fini(ldev);
+
+	drm_dev_put(ddev);
+	lima_sched_slab_fini();
+	return 0;
+}
+
+static const struct of_device_id dt_match[] = {
+	{ .compatible = "arm,mali-400", .data = (void *)lima_gpu_mali400 },
+	{ .compatible = "arm,mali-450", .data = (void *)lima_gpu_mali450 },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dt_match);
+
+static const struct dev_pm_ops lima_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(lima_device_suspend, lima_device_resume, NULL)
+};
+
+static struct platform_driver lima_platform_driver = {
+	.probe      = lima_pdev_probe,
+	.remove     = lima_pdev_remove,
+	.driver     = {
+		.name   = "lima",
+		.pm	= &lima_pm_ops,
+		.of_match_table = dt_match,
+	},
+};
+
+module_platform_driver(lima_platform_driver);
+
+MODULE_AUTHOR("Lima Project Developers");
+MODULE_DESCRIPTION("Lima DRM Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/lima/lima_drv.h b/drivers/gpu/drm/lima/lima_drv.h
new file mode 100644
index 000000000..c738d2885
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_drv.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_DRV_H__
+#define __LIMA_DRV_H__
+
+#include <drm/drm_file.h>
+
+#include "lima_ctx.h"
+
+extern int lima_sched_timeout_ms;
+extern uint lima_heap_init_nr_pages;
+extern uint lima_max_error_tasks;
+extern uint lima_job_hang_limit;
+
+struct lima_vm;
+struct lima_bo;
+struct lima_sched_task;
+
+struct drm_lima_gem_submit_bo;
+
+struct lima_drm_priv {
+	struct lima_vm *vm;
+	struct lima_ctx_mgr ctx_mgr;
+};
+
+struct lima_submit {
+	struct lima_ctx *ctx;
+	int pipe;
+	u32 flags;
+
+	struct drm_lima_gem_submit_bo *bos;
+	struct lima_bo **lbos;
+	u32 nr_bos;
+
+	u32 in_sync[2];
+	u32 out_sync;
+
+	struct lima_sched_task *task;
+};
+
+static inline struct lima_drm_priv *
+to_lima_drm_priv(struct drm_file *file)
+{
+	return file->driver_priv;
+}
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_dump.h b/drivers/gpu/drm/lima/lima_dump.h
new file mode 100644
index 000000000..ca243d99c
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_dump.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2020 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_DUMP_H__
+#define __LIMA_DUMP_H__
+
+#include <linux/types.h>
+
+/**
+ * dump file format for all the information to start a lima task
+ *
+ * top level format
+ * | magic code "LIMA" | format version | num tasks | data size |
+ * | reserved | reserved | reserved | reserved |
+ * | task 1 ID | task 1 size | num chunks | reserved | task 1 data |
+ * | task 2 ID | task 2 size | num chunks | reserved | task 2 data |
+ * ...
+ *
+ * task data format
+ * | chunk 1 ID | chunk 1 size | reserved | reserved | chunk 1 data |
+ * | chunk 2 ID | chunk 2 size | reserved | reserved | chunk 2 data |
+ * ...
+ *
+ */
+
+#define LIMA_DUMP_MAJOR 1
+#define LIMA_DUMP_MINOR 0
+
+#define LIMA_DUMP_MAGIC 0x414d494c
+
+struct lima_dump_head {
+	__u32 magic;
+	__u16 version_major;
+	__u16 version_minor;
+	__u32 num_tasks;
+	__u32 size;
+	__u32 reserved[4];
+};
+
+#define LIMA_DUMP_TASK_GP   0
+#define LIMA_DUMP_TASK_PP   1
+#define LIMA_DUMP_TASK_NUM  2
+
+struct lima_dump_task {
+	__u32 id;
+	__u32 size;
+	__u32 num_chunks;
+	__u32 reserved;
+};
+
+#define LIMA_DUMP_CHUNK_FRAME         0
+#define LIMA_DUMP_CHUNK_BUFFER        1
+#define LIMA_DUMP_CHUNK_PROCESS_NAME  2
+#define LIMA_DUMP_CHUNK_PROCESS_ID    3
+#define LIMA_DUMP_CHUNK_NUM           4
+
+struct lima_dump_chunk {
+	__u32 id;
+	__u32 size;
+	__u32 reserved[2];
+};
+
+struct lima_dump_chunk_buffer {
+	__u32 id;
+	__u32 size;
+	__u32 va;
+	__u32 reserved;
+};
+
+struct lima_dump_chunk_pid {
+	__u32 id;
+	__u32 size;
+	__u32 pid;
+	__u32 reserved;
+};
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c
new file mode 100644
index 000000000..11223fe34
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_gem.c
@@ -0,0 +1,419 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/mm.h>
+#include <linux/sync_file.h>
+#include <linux/pagemap.h>
+#include <linux/shmem_fs.h>
+#include <linux/dma-mapping.h>
+
+#include <drm/drm_file.h>
+#include <drm/drm_syncobj.h>
+#include <drm/drm_utils.h>
+
+#include <drm/lima_drm.h>
+
+#include "lima_drv.h"
+#include "lima_gem.h"
+#include "lima_vm.h"
+
+int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm)
+{
+	struct page **pages;
+	struct address_space *mapping = bo->base.base.filp->f_mapping;
+	struct device *dev = bo->base.base.dev->dev;
+	size_t old_size = bo->heap_size;
+	size_t new_size = bo->heap_size ? bo->heap_size * 2 :
+		(lima_heap_init_nr_pages << PAGE_SHIFT);
+	struct sg_table sgt;
+	int i, ret;
+
+	if (bo->heap_size >= bo->base.base.size)
+		return -ENOSPC;
+
+	new_size = min(new_size, bo->base.base.size);
+
+	mutex_lock(&bo->base.pages_lock);
+
+	if (bo->base.pages) {
+		pages = bo->base.pages;
+	} else {
+		pages = kvmalloc_array(bo->base.base.size >> PAGE_SHIFT,
+				       sizeof(*pages), GFP_KERNEL | __GFP_ZERO);
+		if (!pages) {
+			mutex_unlock(&bo->base.pages_lock);
+			return -ENOMEM;
+		}
+
+		bo->base.pages = pages;
+		bo->base.pages_use_count = 1;
+
+		mapping_set_unevictable(mapping);
+	}
+
+	for (i = old_size >> PAGE_SHIFT; i < new_size >> PAGE_SHIFT; i++) {
+		struct page *page = shmem_read_mapping_page(mapping, i);
+
+		if (IS_ERR(page)) {
+			mutex_unlock(&bo->base.pages_lock);
+			return PTR_ERR(page);
+		}
+		pages[i] = page;
+	}
+
+	mutex_unlock(&bo->base.pages_lock);
+
+	ret = sg_alloc_table_from_pages(&sgt, pages, i, 0,
+					new_size, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	if (bo->base.sgt) {
+		dma_unmap_sgtable(dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0);
+		sg_free_table(bo->base.sgt);
+	} else {
+		bo->base.sgt = kmalloc(sizeof(*bo->base.sgt), GFP_KERNEL);
+		if (!bo->base.sgt) {
+			sg_free_table(&sgt);
+			return -ENOMEM;
+		}
+	}
+
+	ret = dma_map_sgtable(dev, &sgt, DMA_BIDIRECTIONAL, 0);
+	if (ret) {
+		sg_free_table(&sgt);
+		kfree(bo->base.sgt);
+		bo->base.sgt = NULL;
+		return ret;
+	}
+
+	*bo->base.sgt = sgt;
+
+	if (vm) {
+		ret = lima_vm_map_bo(vm, bo, old_size >> PAGE_SHIFT);
+		if (ret)
+			return ret;
+	}
+
+	bo->heap_size = new_size;
+	return 0;
+}
+
+int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file,
+			   u32 size, u32 flags, u32 *handle)
+{
+	int err;
+	gfp_t mask;
+	struct drm_gem_shmem_object *shmem;
+	struct drm_gem_object *obj;
+	struct lima_bo *bo;
+	bool is_heap = flags & LIMA_BO_FLAG_HEAP;
+
+	shmem = drm_gem_shmem_create(dev, size);
+	if (IS_ERR(shmem))
+		return PTR_ERR(shmem);
+
+	obj = &shmem->base;
+
+	/* Mali Utgard GPU can only support 32bit address space */
+	mask = mapping_gfp_mask(obj->filp->f_mapping);
+	mask &= ~__GFP_HIGHMEM;
+	mask |= __GFP_DMA32;
+	mapping_set_gfp_mask(obj->filp->f_mapping, mask);
+
+	if (is_heap) {
+		bo = to_lima_bo(obj);
+		err = lima_heap_alloc(bo, NULL);
+		if (err)
+			goto out;
+	} else {
+		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(obj);
+
+		if (IS_ERR(sgt)) {
+			err = PTR_ERR(sgt);
+			goto out;
+		}
+	}
+
+	err = drm_gem_handle_create(file, obj, handle);
+
+out:
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_put(obj);
+
+	return err;
+}
+
+static void lima_gem_free_object(struct drm_gem_object *obj)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+
+	if (!list_empty(&bo->va))
+		dev_err(obj->dev->dev, "lima gem free bo still has va\n");
+
+	drm_gem_shmem_free_object(obj);
+}
+
+static int lima_gem_object_open(struct drm_gem_object *obj, struct drm_file *file)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+	struct lima_drm_priv *priv = to_lima_drm_priv(file);
+	struct lima_vm *vm = priv->vm;
+
+	return lima_vm_bo_add(vm, bo, true);
+}
+
+static void lima_gem_object_close(struct drm_gem_object *obj, struct drm_file *file)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+	struct lima_drm_priv *priv = to_lima_drm_priv(file);
+	struct lima_vm *vm = priv->vm;
+
+	lima_vm_bo_del(vm, bo);
+}
+
+static int lima_gem_pin(struct drm_gem_object *obj)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+
+	if (bo->heap_size)
+		return -EINVAL;
+
+	return drm_gem_shmem_pin(obj);
+}
+
+static void *lima_gem_vmap(struct drm_gem_object *obj)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+
+	if (bo->heap_size)
+		return ERR_PTR(-EINVAL);
+
+	return drm_gem_shmem_vmap(obj);
+}
+
+static int lima_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct lima_bo *bo = to_lima_bo(obj);
+
+	if (bo->heap_size)
+		return -EINVAL;
+
+	return drm_gem_shmem_mmap(obj, vma);
+}
+
+static const struct drm_gem_object_funcs lima_gem_funcs = {
+	.free = lima_gem_free_object,
+	.open = lima_gem_object_open,
+	.close = lima_gem_object_close,
+	.print_info = drm_gem_shmem_print_info,
+	.pin = lima_gem_pin,
+	.unpin = drm_gem_shmem_unpin,
+	.get_sg_table = drm_gem_shmem_get_sg_table,
+	.vmap = lima_gem_vmap,
+	.vunmap = drm_gem_shmem_vunmap,
+	.mmap = lima_gem_mmap,
+};
+
+struct drm_gem_object *lima_gem_create_object(struct drm_device *dev, size_t size)
+{
+	struct lima_bo *bo;
+
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (!bo)
+		return NULL;
+
+	mutex_init(&bo->lock);
+	INIT_LIST_HEAD(&bo->va);
+
+	bo->base.base.funcs = &lima_gem_funcs;
+
+	return &bo->base.base;
+}
+
+int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset)
+{
+	struct drm_gem_object *obj;
+	struct lima_bo *bo;
+	struct lima_drm_priv *priv = to_lima_drm_priv(file);
+	struct lima_vm *vm = priv->vm;
+
+	obj = drm_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	bo = to_lima_bo(obj);
+
+	*va = lima_vm_get_va(vm, bo);
+
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
+
+	drm_gem_object_put(obj);
+	return 0;
+}
+
+static int lima_gem_sync_bo(struct lima_sched_task *task, struct lima_bo *bo,
+			    bool write, bool explicit)
+{
+	int err = 0;
+
+	if (!write) {
+		err = dma_resv_reserve_shared(lima_bo_resv(bo), 1);
+		if (err)
+			return err;
+	}
+
+	/* explicit sync use user passed dep fence */
+	if (explicit)
+		return 0;
+
+	return drm_gem_fence_array_add_implicit(&task->deps, &bo->base.base, write);
+}
+
+static int lima_gem_add_deps(struct drm_file *file, struct lima_submit *submit)
+{
+	int i, err;
+
+	for (i = 0; i < ARRAY_SIZE(submit->in_sync); i++) {
+		struct dma_fence *fence = NULL;
+
+		if (!submit->in_sync[i])
+			continue;
+
+		err = drm_syncobj_find_fence(file, submit->in_sync[i],
+					     0, 0, &fence);
+		if (err)
+			return err;
+
+		err = drm_gem_fence_array_add(&submit->task->deps, fence);
+		if (err) {
+			dma_fence_put(fence);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int lima_gem_submit(struct drm_file *file, struct lima_submit *submit)
+{
+	int i, err = 0;
+	struct ww_acquire_ctx ctx;
+	struct lima_drm_priv *priv = to_lima_drm_priv(file);
+	struct lima_vm *vm = priv->vm;
+	struct drm_syncobj *out_sync = NULL;
+	struct dma_fence *fence;
+	struct lima_bo **bos = submit->lbos;
+
+	if (submit->out_sync) {
+		out_sync = drm_syncobj_find(file, submit->out_sync);
+		if (!out_sync)
+			return -ENOENT;
+	}
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		struct drm_gem_object *obj;
+		struct lima_bo *bo;
+
+		obj = drm_gem_object_lookup(file, submit->bos[i].handle);
+		if (!obj) {
+			err = -ENOENT;
+			goto err_out0;
+		}
+
+		bo = to_lima_bo(obj);
+
+		/* increase refcnt of gpu va map to prevent unmapped when executing,
+		 * will be decreased when task done
+		 */
+		err = lima_vm_bo_add(vm, bo, false);
+		if (err) {
+			drm_gem_object_put(obj);
+			goto err_out0;
+		}
+
+		bos[i] = bo;
+	}
+
+	err = drm_gem_lock_reservations((struct drm_gem_object **)bos,
+					submit->nr_bos, &ctx);
+	if (err)
+		goto err_out0;
+
+	err = lima_sched_task_init(
+		submit->task, submit->ctx->context + submit->pipe,
+		bos, submit->nr_bos, vm);
+	if (err)
+		goto err_out1;
+
+	err = lima_gem_add_deps(file, submit);
+	if (err)
+		goto err_out2;
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		err = lima_gem_sync_bo(
+			submit->task, bos[i],
+			submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE,
+			submit->flags & LIMA_SUBMIT_FLAG_EXPLICIT_FENCE);
+		if (err)
+			goto err_out2;
+	}
+
+	fence = lima_sched_context_queue_task(
+		submit->ctx->context + submit->pipe, submit->task);
+
+	for (i = 0; i < submit->nr_bos; i++) {
+		if (submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE)
+			dma_resv_add_excl_fence(lima_bo_resv(bos[i]), fence);
+		else
+			dma_resv_add_shared_fence(lima_bo_resv(bos[i]), fence);
+	}
+
+	drm_gem_unlock_reservations((struct drm_gem_object **)bos,
+				    submit->nr_bos, &ctx);
+
+	for (i = 0; i < submit->nr_bos; i++)
+		drm_gem_object_put(&bos[i]->base.base);
+
+	if (out_sync) {
+		drm_syncobj_replace_fence(out_sync, fence);
+		drm_syncobj_put(out_sync);
+	}
+
+	dma_fence_put(fence);
+
+	return 0;
+
+err_out2:
+	lima_sched_task_fini(submit->task);
+err_out1:
+	drm_gem_unlock_reservations((struct drm_gem_object **)bos,
+				    submit->nr_bos, &ctx);
+err_out0:
+	for (i = 0; i < submit->nr_bos; i++) {
+		if (!bos[i])
+			break;
+		lima_vm_bo_del(vm, bos[i]);
+		drm_gem_object_put(&bos[i]->base.base);
+	}
+	if (out_sync)
+		drm_syncobj_put(out_sync);
+	return err;
+}
+
+int lima_gem_wait(struct drm_file *file, u32 handle, u32 op, s64 timeout_ns)
+{
+	bool write = op & LIMA_GEM_WAIT_WRITE;
+	long ret, timeout;
+
+	if (!op)
+		return 0;
+
+	timeout = drm_timeout_abs_to_jiffies(timeout_ns);
+
+	ret = drm_gem_dma_resv_wait(file, handle, write, timeout);
+	if (ret == -ETIME)
+		ret = timeout ? -ETIMEDOUT : -EBUSY;
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/lima/lima_gem.h b/drivers/gpu/drm/lima/lima_gem.h
new file mode 100644
index 000000000..ccea06142
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_gem.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_GEM_H__
+#define __LIMA_GEM_H__
+
+#include <drm/drm_gem_shmem_helper.h>
+
+struct lima_submit;
+struct lima_vm;
+
+struct lima_bo {
+	struct drm_gem_shmem_object base;
+
+	struct mutex lock;
+	struct list_head va;
+
+	size_t heap_size;
+};
+
+static inline struct lima_bo *
+to_lima_bo(struct drm_gem_object *obj)
+{
+	return container_of(to_drm_gem_shmem_obj(obj), struct lima_bo, base);
+}
+
+static inline size_t lima_bo_size(struct lima_bo *bo)
+{
+	return bo->base.base.size;
+}
+
+static inline struct dma_resv *lima_bo_resv(struct lima_bo *bo)
+{
+	return bo->base.base.resv;
+}
+
+int lima_heap_alloc(struct lima_bo *bo, struct lima_vm *vm);
+struct drm_gem_object *lima_gem_create_object(struct drm_device *dev, size_t size);
+int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file,
+			   u32 size, u32 flags, u32 *handle);
+int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset);
+int lima_gem_submit(struct drm_file *file, struct lima_submit *submit);
+int lima_gem_wait(struct drm_file *file, u32 handle, u32 op, s64 timeout_ns);
+
+void lima_set_vma_flags(struct vm_area_struct *vma);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_gp.c b/drivers/gpu/drm/lima/lima_gp.c
new file mode 100644
index 000000000..8dd501b7a
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_gp.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+
+#include <drm/lima_drm.h>
+
+#include "lima_device.h"
+#include "lima_gp.h"
+#include "lima_regs.h"
+#include "lima_gem.h"
+#include "lima_vm.h"
+
+#define gp_write(reg, data) writel(data, ip->iomem + reg)
+#define gp_read(reg) readl(ip->iomem + reg)
+
+static irqreturn_t lima_gp_irq_handler(int irq, void *data)
+{
+	struct lima_ip *ip = data;
+	struct lima_device *dev = ip->dev;
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
+	struct lima_sched_task *task = pipe->current_task;
+	u32 state = gp_read(LIMA_GP_INT_STAT);
+	u32 status = gp_read(LIMA_GP_STATUS);
+	bool done = false;
+
+	/* for shared irq case */
+	if (!state)
+		return IRQ_NONE;
+
+	if (state & LIMA_GP_IRQ_MASK_ERROR) {
+		if ((state & LIMA_GP_IRQ_MASK_ERROR) ==
+		    LIMA_GP_IRQ_PLBU_OUT_OF_MEM) {
+			dev_dbg(dev->dev, "gp out of heap irq status=%x\n",
+				status);
+		} else {
+			dev_err(dev->dev, "gp error irq state=%x status=%x\n",
+				state, status);
+			if (task)
+				task->recoverable = false;
+		}
+
+		/* mask all interrupts before hard reset */
+		gp_write(LIMA_GP_INT_MASK, 0);
+
+		pipe->error = true;
+		done = true;
+	} else {
+		bool valid = state & (LIMA_GP_IRQ_VS_END_CMD_LST |
+				      LIMA_GP_IRQ_PLBU_END_CMD_LST);
+		bool active = status & (LIMA_GP_STATUS_VS_ACTIVE |
+					LIMA_GP_STATUS_PLBU_ACTIVE);
+		done = valid && !active;
+		pipe->error = false;
+	}
+
+	gp_write(LIMA_GP_INT_CLEAR, state);
+
+	if (done)
+		lima_sched_pipe_task_done(pipe);
+
+	return IRQ_HANDLED;
+}
+
+static void lima_gp_soft_reset_async(struct lima_ip *ip)
+{
+	if (ip->data.async_reset)
+		return;
+
+	gp_write(LIMA_GP_INT_MASK, 0);
+	gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_RESET_COMPLETED);
+	gp_write(LIMA_GP_CMD, LIMA_GP_CMD_SOFT_RESET);
+	ip->data.async_reset = true;
+}
+
+static int lima_gp_soft_reset_async_wait(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+	u32 v;
+
+	if (!ip->data.async_reset)
+		return 0;
+
+	err = readl_poll_timeout(ip->iomem + LIMA_GP_INT_RAWSTAT, v,
+				 v & LIMA_GP_IRQ_RESET_COMPLETED,
+				 0, 100);
+	if (err) {
+		dev_err(dev->dev, "gp soft reset time out\n");
+		return err;
+	}
+
+	gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL);
+	gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED);
+
+	ip->data.async_reset = false;
+	return 0;
+}
+
+static int lima_gp_task_validate(struct lima_sched_pipe *pipe,
+				 struct lima_sched_task *task)
+{
+	struct drm_lima_gp_frame *frame = task->frame;
+	u32 *f = frame->frame;
+	(void)pipe;
+
+	if (f[LIMA_GP_VSCL_START_ADDR >> 2] >
+	    f[LIMA_GP_VSCL_END_ADDR >> 2] ||
+	    f[LIMA_GP_PLBUCL_START_ADDR >> 2] >
+	    f[LIMA_GP_PLBUCL_END_ADDR >> 2] ||
+	    f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2] >
+	    f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2])
+		return -EINVAL;
+
+	if (f[LIMA_GP_VSCL_START_ADDR >> 2] ==
+	    f[LIMA_GP_VSCL_END_ADDR >> 2] &&
+	    f[LIMA_GP_PLBUCL_START_ADDR >> 2] ==
+	    f[LIMA_GP_PLBUCL_END_ADDR >> 2])
+		return -EINVAL;
+
+	return 0;
+}
+
+static void lima_gp_task_run(struct lima_sched_pipe *pipe,
+			     struct lima_sched_task *task)
+{
+	struct lima_ip *ip = pipe->processor[0];
+	struct drm_lima_gp_frame *frame = task->frame;
+	u32 *f = frame->frame;
+	u32 cmd = 0;
+	int i;
+
+	/* update real heap buffer size for GP */
+	for (i = 0; i < task->num_bos; i++) {
+		struct lima_bo *bo = task->bos[i];
+
+		if (bo->heap_size &&
+		    lima_vm_get_va(task->vm, bo) ==
+		    f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2]) {
+			f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2] =
+				f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2] +
+				bo->heap_size;
+			task->recoverable = true;
+			task->heap = bo;
+			break;
+		}
+	}
+
+	if (f[LIMA_GP_VSCL_START_ADDR >> 2] !=
+	    f[LIMA_GP_VSCL_END_ADDR >> 2])
+		cmd |= LIMA_GP_CMD_START_VS;
+	if (f[LIMA_GP_PLBUCL_START_ADDR >> 2] !=
+	    f[LIMA_GP_PLBUCL_END_ADDR >> 2])
+		cmd |= LIMA_GP_CMD_START_PLBU;
+
+	/* before any hw ops, wait last success task async soft reset */
+	lima_gp_soft_reset_async_wait(ip);
+
+	for (i = 0; i < LIMA_GP_FRAME_REG_NUM; i++)
+		writel(f[i], ip->iomem + LIMA_GP_VSCL_START_ADDR + i * 4);
+
+	gp_write(LIMA_GP_CMD, LIMA_GP_CMD_UPDATE_PLBU_ALLOC);
+	gp_write(LIMA_GP_CMD, cmd);
+}
+
+static int lima_gp_hard_reset_poll(struct lima_ip *ip)
+{
+	gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC01A0000);
+	return gp_read(LIMA_GP_PERF_CNT_0_LIMIT) == 0xC01A0000;
+}
+
+static int lima_gp_hard_reset(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int ret;
+
+	gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC0FFE000);
+	gp_write(LIMA_GP_INT_MASK, 0);
+	gp_write(LIMA_GP_CMD, LIMA_GP_CMD_RESET);
+	ret = lima_poll_timeout(ip, lima_gp_hard_reset_poll, 10, 100);
+	if (ret) {
+		dev_err(dev->dev, "gp hard reset timeout\n");
+		return ret;
+	}
+
+	gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0);
+	gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL);
+	gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED);
+	return 0;
+}
+
+static void lima_gp_task_fini(struct lima_sched_pipe *pipe)
+{
+	lima_gp_soft_reset_async(pipe->processor[0]);
+}
+
+static void lima_gp_task_error(struct lima_sched_pipe *pipe)
+{
+	struct lima_ip *ip = pipe->processor[0];
+
+	dev_err(ip->dev->dev, "gp task error int_state=%x status=%x\n",
+		gp_read(LIMA_GP_INT_STAT), gp_read(LIMA_GP_STATUS));
+
+	lima_gp_hard_reset(ip);
+}
+
+static void lima_gp_task_mmu_error(struct lima_sched_pipe *pipe)
+{
+	lima_sched_pipe_task_done(pipe);
+}
+
+static int lima_gp_task_recover(struct lima_sched_pipe *pipe)
+{
+	struct lima_ip *ip = pipe->processor[0];
+	struct lima_sched_task *task = pipe->current_task;
+	struct drm_lima_gp_frame *frame = task->frame;
+	u32 *f = frame->frame;
+	size_t fail_size =
+		f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2] -
+		f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2];
+
+	if (fail_size == task->heap->heap_size) {
+		int ret;
+
+		ret = lima_heap_alloc(task->heap, task->vm);
+		if (ret < 0)
+			return ret;
+	}
+
+	gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED);
+	/* Resume from where we stopped, i.e. new start is old end */
+	gp_write(LIMA_GP_PLBU_ALLOC_START_ADDR,
+		 f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2]);
+	f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2] =
+		f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2] + task->heap->heap_size;
+	gp_write(LIMA_GP_PLBU_ALLOC_END_ADDR,
+		 f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2]);
+	gp_write(LIMA_GP_CMD, LIMA_GP_CMD_UPDATE_PLBU_ALLOC);
+	return 0;
+}
+
+static void lima_gp_print_version(struct lima_ip *ip)
+{
+	u32 version, major, minor;
+	char *name;
+
+	version = gp_read(LIMA_GP_VERSION);
+	major = (version >> 8) & 0xFF;
+	minor = version & 0xFF;
+	switch (version >> 16) {
+	case 0xA07:
+	    name = "mali200";
+		break;
+	case 0xC07:
+		name = "mali300";
+		break;
+	case 0xB07:
+		name = "mali400";
+		break;
+	case 0xD07:
+		name = "mali450";
+		break;
+	default:
+		name = "unknown";
+		break;
+	}
+	dev_info(ip->dev->dev, "%s - %s version major %d minor %d\n",
+		 lima_ip_name(ip), name, major, minor);
+}
+
+static struct kmem_cache *lima_gp_task_slab;
+static int lima_gp_task_slab_refcnt;
+
+static int lima_gp_hw_init(struct lima_ip *ip)
+{
+	ip->data.async_reset = false;
+	lima_gp_soft_reset_async(ip);
+	return lima_gp_soft_reset_async_wait(ip);
+}
+
+int lima_gp_resume(struct lima_ip *ip)
+{
+	return lima_gp_hw_init(ip);
+}
+
+void lima_gp_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_gp_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+
+	lima_gp_print_version(ip);
+
+	err = lima_gp_hw_init(ip);
+	if (err)
+		return err;
+
+	err = devm_request_irq(dev->dev, ip->irq, lima_gp_irq_handler,
+			       IRQF_SHARED, lima_ip_name(ip), ip);
+	if (err) {
+		dev_err(dev->dev, "gp %s fail to request irq\n",
+			lima_ip_name(ip));
+		return err;
+	}
+
+	dev->gp_version = gp_read(LIMA_GP_VERSION);
+
+	return 0;
+}
+
+void lima_gp_fini(struct lima_ip *ip)
+{
+
+}
+
+int lima_gp_pipe_init(struct lima_device *dev)
+{
+	int frame_size = sizeof(struct drm_lima_gp_frame);
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp;
+
+	if (!lima_gp_task_slab) {
+		lima_gp_task_slab = kmem_cache_create_usercopy(
+			"lima_gp_task", sizeof(struct lima_sched_task) + frame_size,
+			0, SLAB_HWCACHE_ALIGN, sizeof(struct lima_sched_task),
+			frame_size, NULL);
+		if (!lima_gp_task_slab)
+			return -ENOMEM;
+	}
+	lima_gp_task_slab_refcnt++;
+
+	pipe->frame_size = frame_size;
+	pipe->task_slab = lima_gp_task_slab;
+
+	pipe->task_validate = lima_gp_task_validate;
+	pipe->task_run = lima_gp_task_run;
+	pipe->task_fini = lima_gp_task_fini;
+	pipe->task_error = lima_gp_task_error;
+	pipe->task_mmu_error = lima_gp_task_mmu_error;
+	pipe->task_recover = lima_gp_task_recover;
+
+	return 0;
+}
+
+void lima_gp_pipe_fini(struct lima_device *dev)
+{
+	if (!--lima_gp_task_slab_refcnt) {
+		kmem_cache_destroy(lima_gp_task_slab);
+		lima_gp_task_slab = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/lima/lima_gp.h b/drivers/gpu/drm/lima/lima_gp.h
new file mode 100644
index 000000000..02ec9af78
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_gp.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_GP_H__
+#define __LIMA_GP_H__
+
+struct lima_ip;
+struct lima_device;
+
+int lima_gp_resume(struct lima_ip *ip);
+void lima_gp_suspend(struct lima_ip *ip);
+int lima_gp_init(struct lima_ip *ip);
+void lima_gp_fini(struct lima_ip *ip);
+
+int lima_gp_pipe_init(struct lima_device *dev);
+void lima_gp_pipe_fini(struct lima_device *dev);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_l2_cache.c b/drivers/gpu/drm/lima/lima_l2_cache.c
new file mode 100644
index 000000000..c4080a029
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_l2_cache.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/iopoll.h>
+#include <linux/device.h>
+
+#include "lima_device.h"
+#include "lima_l2_cache.h"
+#include "lima_regs.h"
+
+#define l2_cache_write(reg, data) writel(data, ip->iomem + reg)
+#define l2_cache_read(reg) readl(ip->iomem + reg)
+
+static int lima_l2_cache_wait_idle(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+	u32 v;
+
+	err = readl_poll_timeout(ip->iomem + LIMA_L2_CACHE_STATUS, v,
+				 !(v & LIMA_L2_CACHE_STATUS_COMMAND_BUSY),
+				 0, 1000);
+	if (err) {
+		dev_err(dev->dev, "l2 cache wait command timeout\n");
+		return err;
+	}
+	return 0;
+}
+
+int lima_l2_cache_flush(struct lima_ip *ip)
+{
+	int ret;
+
+	spin_lock(&ip->data.lock);
+	l2_cache_write(LIMA_L2_CACHE_COMMAND, LIMA_L2_CACHE_COMMAND_CLEAR_ALL);
+	ret = lima_l2_cache_wait_idle(ip);
+	spin_unlock(&ip->data.lock);
+	return ret;
+}
+
+static int lima_l2_cache_hw_init(struct lima_ip *ip)
+{
+	int err;
+
+	err = lima_l2_cache_flush(ip);
+	if (err)
+		return err;
+
+	l2_cache_write(LIMA_L2_CACHE_ENABLE,
+		       LIMA_L2_CACHE_ENABLE_ACCESS |
+		       LIMA_L2_CACHE_ENABLE_READ_ALLOCATE);
+	l2_cache_write(LIMA_L2_CACHE_MAX_READS, 0x1c);
+
+	return 0;
+}
+
+int lima_l2_cache_resume(struct lima_ip *ip)
+{
+	return lima_l2_cache_hw_init(ip);
+}
+
+void lima_l2_cache_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_l2_cache_init(struct lima_ip *ip)
+{
+	int i;
+	u32 size;
+	struct lima_device *dev = ip->dev;
+
+	/* l2_cache2 only exists when one of PP4-7 present */
+	if (ip->id == lima_ip_l2_cache2) {
+		for (i = lima_ip_pp4; i <= lima_ip_pp7; i++) {
+			if (dev->ip[i].present)
+				break;
+		}
+		if (i > lima_ip_pp7)
+			return -ENODEV;
+	}
+
+	spin_lock_init(&ip->data.lock);
+
+	size = l2_cache_read(LIMA_L2_CACHE_SIZE);
+	dev_info(dev->dev, "l2 cache %uK, %u-way, %ubyte cache line, %ubit external bus\n",
+		 1 << (((size >> 16) & 0xff) - 10),
+		 1 << ((size >> 8) & 0xff),
+		 1 << (size & 0xff),
+		 1 << ((size >> 24) & 0xff));
+
+	return lima_l2_cache_hw_init(ip);
+}
+
+void lima_l2_cache_fini(struct lima_ip *ip)
+{
+
+}
diff --git a/drivers/gpu/drm/lima/lima_l2_cache.h b/drivers/gpu/drm/lima/lima_l2_cache.h
new file mode 100644
index 000000000..1aeeefd53
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_l2_cache.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_L2_CACHE_H__
+#define __LIMA_L2_CACHE_H__
+
+struct lima_ip;
+
+int lima_l2_cache_resume(struct lima_ip *ip);
+void lima_l2_cache_suspend(struct lima_ip *ip);
+int lima_l2_cache_init(struct lima_ip *ip);
+void lima_l2_cache_fini(struct lima_ip *ip);
+
+int lima_l2_cache_flush(struct lima_ip *ip);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_mmu.c b/drivers/gpu/drm/lima/lima_mmu.c
new file mode 100644
index 000000000..a1ae6c252
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_mmu.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/device.h>
+
+#include "lima_device.h"
+#include "lima_mmu.h"
+#include "lima_vm.h"
+#include "lima_regs.h"
+
+#define mmu_write(reg, data) writel(data, ip->iomem + reg)
+#define mmu_read(reg) readl(ip->iomem + reg)
+
+#define lima_mmu_send_command(cmd, addr, val, cond)	     \
+({							     \
+	int __ret;					     \
+							     \
+	mmu_write(LIMA_MMU_COMMAND, cmd);		     \
+	__ret = readl_poll_timeout(ip->iomem + (addr), val,  \
+				  cond, 0, 100);	     \
+	if (__ret)					     \
+		dev_err(dev->dev,			     \
+			"mmu command %x timeout\n", cmd);    \
+	__ret;						     \
+})
+
+static irqreturn_t lima_mmu_irq_handler(int irq, void *data)
+{
+	struct lima_ip *ip = data;
+	struct lima_device *dev = ip->dev;
+	u32 status = mmu_read(LIMA_MMU_INT_STATUS);
+	struct lima_sched_pipe *pipe;
+
+	/* for shared irq case */
+	if (!status)
+		return IRQ_NONE;
+
+	if (status & LIMA_MMU_INT_PAGE_FAULT) {
+		u32 fault = mmu_read(LIMA_MMU_PAGE_FAULT_ADDR);
+
+		dev_err(dev->dev, "mmu page fault at 0x%x from bus id %d of type %s on %s\n",
+			fault, LIMA_MMU_STATUS_BUS_ID(status),
+			status & LIMA_MMU_STATUS_PAGE_FAULT_IS_WRITE ? "write" : "read",
+			lima_ip_name(ip));
+	}
+
+	if (status & LIMA_MMU_INT_READ_BUS_ERROR)
+		dev_err(dev->dev, "mmu %s irq bus error\n", lima_ip_name(ip));
+
+	/* mask all interrupts before resume */
+	mmu_write(LIMA_MMU_INT_MASK, 0);
+	mmu_write(LIMA_MMU_INT_CLEAR, status);
+
+	pipe = dev->pipe + (ip->id == lima_ip_gpmmu ? lima_pipe_gp : lima_pipe_pp);
+	lima_sched_pipe_mmu_error(pipe);
+
+	return IRQ_HANDLED;
+}
+
+static int lima_mmu_hw_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+	u32 v;
+
+	mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_HARD_RESET);
+	err = lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET,
+				    LIMA_MMU_DTE_ADDR, v, v == 0);
+	if (err)
+		return err;
+
+	mmu_write(LIMA_MMU_INT_MASK,
+		  LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR);
+	mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma);
+	return lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING,
+				     LIMA_MMU_STATUS, v,
+				     v & LIMA_MMU_STATUS_PAGING_ENABLED);
+}
+
+int lima_mmu_resume(struct lima_ip *ip)
+{
+	if (ip->id == lima_ip_ppmmu_bcast)
+		return 0;
+
+	return lima_mmu_hw_init(ip);
+}
+
+void lima_mmu_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_mmu_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+
+	if (ip->id == lima_ip_ppmmu_bcast)
+		return 0;
+
+	mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE);
+	if (mmu_read(LIMA_MMU_DTE_ADDR) != 0xCAFEB000) {
+		dev_err(dev->dev, "mmu %s dte write test fail\n", lima_ip_name(ip));
+		return -EIO;
+	}
+
+	err = devm_request_irq(dev->dev, ip->irq, lima_mmu_irq_handler,
+			       IRQF_SHARED, lima_ip_name(ip), ip);
+	if (err) {
+		dev_err(dev->dev, "mmu %s fail to request irq\n", lima_ip_name(ip));
+		return err;
+	}
+
+	return lima_mmu_hw_init(ip);
+}
+
+void lima_mmu_fini(struct lima_ip *ip)
+{
+
+}
+
+void lima_mmu_flush_tlb(struct lima_ip *ip)
+{
+	mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_ZAP_CACHE);
+}
+
+void lima_mmu_switch_vm(struct lima_ip *ip, struct lima_vm *vm)
+{
+	struct lima_device *dev = ip->dev;
+	u32 v;
+
+	lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_STALL,
+			      LIMA_MMU_STATUS, v,
+			      v & LIMA_MMU_STATUS_STALL_ACTIVE);
+
+	mmu_write(LIMA_MMU_DTE_ADDR, vm->pd.dma);
+
+	/* flush the TLB */
+	mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_ZAP_CACHE);
+
+	lima_mmu_send_command(LIMA_MMU_COMMAND_DISABLE_STALL,
+			      LIMA_MMU_STATUS, v,
+			      !(v & LIMA_MMU_STATUS_STALL_ACTIVE));
+}
+
+void lima_mmu_page_fault_resume(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	u32 status = mmu_read(LIMA_MMU_STATUS);
+	u32 v;
+
+	if (status & LIMA_MMU_STATUS_PAGE_FAULT_ACTIVE) {
+		dev_info(dev->dev, "mmu resume\n");
+
+		mmu_write(LIMA_MMU_INT_MASK, 0);
+		mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE);
+		lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET,
+				      LIMA_MMU_DTE_ADDR, v, v == 0);
+		mmu_write(LIMA_MMU_INT_MASK, LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR);
+		mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma);
+		lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING,
+				      LIMA_MMU_STATUS, v,
+				      v & LIMA_MMU_STATUS_PAGING_ENABLED);
+	}
+}
diff --git a/drivers/gpu/drm/lima/lima_mmu.h b/drivers/gpu/drm/lima/lima_mmu.h
new file mode 100644
index 000000000..f0c97ac75
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_mmu.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_MMU_H__
+#define __LIMA_MMU_H__
+
+struct lima_ip;
+struct lima_vm;
+
+int lima_mmu_resume(struct lima_ip *ip);
+void lima_mmu_suspend(struct lima_ip *ip);
+int lima_mmu_init(struct lima_ip *ip);
+void lima_mmu_fini(struct lima_ip *ip);
+
+void lima_mmu_flush_tlb(struct lima_ip *ip);
+void lima_mmu_switch_vm(struct lima_ip *ip, struct lima_vm *vm);
+void lima_mmu_page_fault_resume(struct lima_ip *ip);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_pmu.c b/drivers/gpu/drm/lima/lima_pmu.c
new file mode 100644
index 000000000..e397e1146
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_pmu.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/iopoll.h>
+#include <linux/device.h>
+
+#include "lima_device.h"
+#include "lima_pmu.h"
+#include "lima_regs.h"
+
+#define pmu_write(reg, data) writel(data, ip->iomem + reg)
+#define pmu_read(reg) readl(ip->iomem + reg)
+
+static int lima_pmu_wait_cmd(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+	u32 v;
+
+	err = readl_poll_timeout(ip->iomem + LIMA_PMU_INT_RAWSTAT,
+				 v, v & LIMA_PMU_INT_CMD_MASK,
+				 100, 100000);
+	if (err) {
+		dev_err(dev->dev, "timeout wait pmu cmd\n");
+		return err;
+	}
+
+	pmu_write(LIMA_PMU_INT_CLEAR, LIMA_PMU_INT_CMD_MASK);
+	return 0;
+}
+
+static u32 lima_pmu_get_ip_mask(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	u32 ret = 0;
+	int i;
+
+	ret |= LIMA_PMU_POWER_GP0_MASK;
+
+	if (dev->id == lima_gpu_mali400) {
+		ret |= LIMA_PMU_POWER_L2_MASK;
+		for (i = 0; i < 4; i++) {
+			if (dev->ip[lima_ip_pp0 + i].present)
+				ret |= LIMA_PMU_POWER_PP_MASK(i);
+		}
+	} else {
+		if (dev->ip[lima_ip_pp0].present)
+			ret |= LIMA450_PMU_POWER_PP0_MASK;
+		for (i = lima_ip_pp1; i <= lima_ip_pp3; i++) {
+			if (dev->ip[i].present) {
+				ret |= LIMA450_PMU_POWER_PP13_MASK;
+				break;
+			}
+		}
+		for (i = lima_ip_pp4; i <= lima_ip_pp7; i++) {
+			if (dev->ip[i].present) {
+				ret |= LIMA450_PMU_POWER_PP47_MASK;
+				break;
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int lima_pmu_hw_init(struct lima_ip *ip)
+{
+	int err;
+	u32 stat;
+
+	pmu_write(LIMA_PMU_INT_MASK, 0);
+
+	/* If this value is too low, when in high GPU clk freq,
+	 * GPU will be in unstable state.
+	 */
+	pmu_write(LIMA_PMU_SW_DELAY, 0xffff);
+
+	/* status reg 1=off 0=on */
+	stat = pmu_read(LIMA_PMU_STATUS);
+
+	/* power up all ip */
+	if (stat) {
+		pmu_write(LIMA_PMU_POWER_UP, stat);
+		err = lima_pmu_wait_cmd(ip);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static void lima_pmu_hw_fini(struct lima_ip *ip)
+{
+	u32 stat;
+
+	if (!ip->data.mask)
+		ip->data.mask = lima_pmu_get_ip_mask(ip);
+
+	stat = ~pmu_read(LIMA_PMU_STATUS) & ip->data.mask;
+	if (stat) {
+		pmu_write(LIMA_PMU_POWER_DOWN, stat);
+
+		/* Don't wait for interrupt on Mali400 if all domains are
+		 * powered off because the HW won't generate an interrupt
+		 * in this case.
+		 */
+		if (ip->dev->id == lima_gpu_mali400)
+			pmu_write(LIMA_PMU_INT_CLEAR, LIMA_PMU_INT_CMD_MASK);
+		else
+			lima_pmu_wait_cmd(ip);
+	}
+}
+
+int lima_pmu_resume(struct lima_ip *ip)
+{
+	return lima_pmu_hw_init(ip);
+}
+
+void lima_pmu_suspend(struct lima_ip *ip)
+{
+	lima_pmu_hw_fini(ip);
+}
+
+int lima_pmu_init(struct lima_ip *ip)
+{
+	return lima_pmu_hw_init(ip);
+}
+
+void lima_pmu_fini(struct lima_ip *ip)
+{
+	lima_pmu_hw_fini(ip);
+}
diff --git a/drivers/gpu/drm/lima/lima_pmu.h b/drivers/gpu/drm/lima/lima_pmu.h
new file mode 100644
index 000000000..652dc7af3
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_pmu.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_PMU_H__
+#define __LIMA_PMU_H__
+
+struct lima_ip;
+
+int lima_pmu_resume(struct lima_ip *ip);
+void lima_pmu_suspend(struct lima_ip *ip);
+int lima_pmu_init(struct lima_ip *ip);
+void lima_pmu_fini(struct lima_ip *ip);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c
new file mode 100644
index 000000000..a5c95bed0
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_pp.c
@@ -0,0 +1,460 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+
+#include <drm/lima_drm.h>
+
+#include "lima_device.h"
+#include "lima_pp.h"
+#include "lima_dlbu.h"
+#include "lima_bcast.h"
+#include "lima_vm.h"
+#include "lima_regs.h"
+
+#define pp_write(reg, data) writel(data, ip->iomem + reg)
+#define pp_read(reg) readl(ip->iomem + reg)
+
+static void lima_pp_handle_irq(struct lima_ip *ip, u32 state)
+{
+	struct lima_device *dev = ip->dev;
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+
+	if (state & LIMA_PP_IRQ_MASK_ERROR) {
+		u32 status = pp_read(LIMA_PP_STATUS);
+
+		dev_err(dev->dev, "pp error irq state=%x status=%x\n",
+			state, status);
+
+		pipe->error = true;
+
+		/* mask all interrupts before hard reset */
+		pp_write(LIMA_PP_INT_MASK, 0);
+	}
+
+	pp_write(LIMA_PP_INT_CLEAR, state);
+}
+
+static irqreturn_t lima_pp_irq_handler(int irq, void *data)
+{
+	struct lima_ip *ip = data;
+	struct lima_device *dev = ip->dev;
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+	u32 state = pp_read(LIMA_PP_INT_STATUS);
+
+	/* for shared irq case */
+	if (!state)
+		return IRQ_NONE;
+
+	lima_pp_handle_irq(ip, state);
+
+	if (atomic_dec_and_test(&pipe->task))
+		lima_sched_pipe_task_done(pipe);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t lima_pp_bcast_irq_handler(int irq, void *data)
+{
+	int i;
+	irqreturn_t ret = IRQ_NONE;
+	struct lima_ip *pp_bcast = data;
+	struct lima_device *dev = pp_bcast->dev;
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+	struct drm_lima_m450_pp_frame *frame;
+
+	/* for shared irq case */
+	if (!pipe->current_task)
+		return IRQ_NONE;
+
+	frame = pipe->current_task->frame;
+
+	for (i = 0; i < frame->num_pp; i++) {
+		struct lima_ip *ip = pipe->processor[i];
+		u32 status, state;
+
+		if (pipe->done & (1 << i))
+			continue;
+
+		/* status read first in case int state change in the middle
+		 * which may miss the interrupt handling
+		 */
+		status = pp_read(LIMA_PP_STATUS);
+		state = pp_read(LIMA_PP_INT_STATUS);
+
+		if (state) {
+			lima_pp_handle_irq(ip, state);
+			ret = IRQ_HANDLED;
+		} else {
+			if (status & LIMA_PP_STATUS_RENDERING_ACTIVE)
+				continue;
+		}
+
+		pipe->done |= (1 << i);
+		if (atomic_dec_and_test(&pipe->task))
+			lima_sched_pipe_task_done(pipe);
+	}
+
+	return ret;
+}
+
+static void lima_pp_soft_reset_async(struct lima_ip *ip)
+{
+	if (ip->data.async_reset)
+		return;
+
+	pp_write(LIMA_PP_INT_MASK, 0);
+	pp_write(LIMA_PP_INT_RAWSTAT, LIMA_PP_IRQ_MASK_ALL);
+	pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_SOFT_RESET);
+	ip->data.async_reset = true;
+}
+
+static int lima_pp_soft_reset_poll(struct lima_ip *ip)
+{
+	return !(pp_read(LIMA_PP_STATUS) & LIMA_PP_STATUS_RENDERING_ACTIVE) &&
+		pp_read(LIMA_PP_INT_RAWSTAT) == LIMA_PP_IRQ_RESET_COMPLETED;
+}
+
+static int lima_pp_soft_reset_async_wait_one(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int ret;
+
+	ret = lima_poll_timeout(ip, lima_pp_soft_reset_poll, 0, 100);
+	if (ret) {
+		dev_err(dev->dev, "pp %s reset time out\n", lima_ip_name(ip));
+		return ret;
+	}
+
+	pp_write(LIMA_PP_INT_CLEAR, LIMA_PP_IRQ_MASK_ALL);
+	pp_write(LIMA_PP_INT_MASK, LIMA_PP_IRQ_MASK_USED);
+	return 0;
+}
+
+static int lima_pp_soft_reset_async_wait(struct lima_ip *ip)
+{
+	int i, err = 0;
+
+	if (!ip->data.async_reset)
+		return 0;
+
+	if (ip->id == lima_ip_pp_bcast) {
+		struct lima_device *dev = ip->dev;
+		struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+		struct drm_lima_m450_pp_frame *frame = pipe->current_task->frame;
+
+		for (i = 0; i < frame->num_pp; i++)
+			err |= lima_pp_soft_reset_async_wait_one(pipe->processor[i]);
+	} else
+		err = lima_pp_soft_reset_async_wait_one(ip);
+
+	ip->data.async_reset = false;
+	return err;
+}
+
+static void lima_pp_write_frame(struct lima_ip *ip, u32 *frame, u32 *wb)
+{
+	int i, j, n = 0;
+
+	for (i = 0; i < LIMA_PP_FRAME_REG_NUM; i++)
+		writel(frame[i], ip->iomem + LIMA_PP_FRAME + i * 4);
+
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < LIMA_PP_WB_REG_NUM; j++)
+			writel(wb[n++], ip->iomem + LIMA_PP_WB(i) + j * 4);
+	}
+}
+
+static int lima_pp_hard_reset_poll(struct lima_ip *ip)
+{
+	pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0xC01A0000);
+	return pp_read(LIMA_PP_PERF_CNT_0_LIMIT) == 0xC01A0000;
+}
+
+static int lima_pp_hard_reset(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int ret;
+
+	pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0xC0FFE000);
+	pp_write(LIMA_PP_INT_MASK, 0);
+	pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_FORCE_RESET);
+	ret = lima_poll_timeout(ip, lima_pp_hard_reset_poll, 10, 100);
+	if (ret) {
+		dev_err(dev->dev, "pp hard reset timeout\n");
+		return ret;
+	}
+
+	pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0);
+	pp_write(LIMA_PP_INT_CLEAR, LIMA_PP_IRQ_MASK_ALL);
+	pp_write(LIMA_PP_INT_MASK, LIMA_PP_IRQ_MASK_USED);
+	return 0;
+}
+
+static void lima_pp_print_version(struct lima_ip *ip)
+{
+	u32 version, major, minor;
+	char *name;
+
+	version = pp_read(LIMA_PP_VERSION);
+	major = (version >> 8) & 0xFF;
+	minor = version & 0xFF;
+	switch (version >> 16) {
+	case 0xC807:
+	    name = "mali200";
+		break;
+	case 0xCE07:
+		name = "mali300";
+		break;
+	case 0xCD07:
+		name = "mali400";
+		break;
+	case 0xCF07:
+		name = "mali450";
+		break;
+	default:
+		name = "unknown";
+		break;
+	}
+	dev_info(ip->dev->dev, "%s - %s version major %d minor %d\n",
+		 lima_ip_name(ip), name, major, minor);
+}
+
+static int lima_pp_hw_init(struct lima_ip *ip)
+{
+	ip->data.async_reset = false;
+	lima_pp_soft_reset_async(ip);
+	return lima_pp_soft_reset_async_wait(ip);
+}
+
+int lima_pp_resume(struct lima_ip *ip)
+{
+	return lima_pp_hw_init(ip);
+}
+
+void lima_pp_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_pp_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+
+	lima_pp_print_version(ip);
+
+	err = lima_pp_hw_init(ip);
+	if (err)
+		return err;
+
+	err = devm_request_irq(dev->dev, ip->irq, lima_pp_irq_handler,
+			       IRQF_SHARED, lima_ip_name(ip), ip);
+	if (err) {
+		dev_err(dev->dev, "pp %s fail to request irq\n",
+			lima_ip_name(ip));
+		return err;
+	}
+
+	dev->pp_version = pp_read(LIMA_PP_VERSION);
+
+	return 0;
+}
+
+void lima_pp_fini(struct lima_ip *ip)
+{
+
+}
+
+int lima_pp_bcast_resume(struct lima_ip *ip)
+{
+	/* PP has been reset by individual PP resume */
+	ip->data.async_reset = false;
+	return 0;
+}
+
+void lima_pp_bcast_suspend(struct lima_ip *ip)
+{
+
+}
+
+int lima_pp_bcast_init(struct lima_ip *ip)
+{
+	struct lima_device *dev = ip->dev;
+	int err;
+
+	err = devm_request_irq(dev->dev, ip->irq, lima_pp_bcast_irq_handler,
+			       IRQF_SHARED, lima_ip_name(ip), ip);
+	if (err) {
+		dev_err(dev->dev, "pp %s fail to request irq\n",
+			lima_ip_name(ip));
+		return err;
+	}
+
+	return 0;
+}
+
+void lima_pp_bcast_fini(struct lima_ip *ip)
+{
+
+}
+
+static int lima_pp_task_validate(struct lima_sched_pipe *pipe,
+				 struct lima_sched_task *task)
+{
+	u32 num_pp;
+
+	if (pipe->bcast_processor) {
+		struct drm_lima_m450_pp_frame *f = task->frame;
+
+		num_pp = f->num_pp;
+
+		if (f->_pad)
+			return -EINVAL;
+	} else {
+		struct drm_lima_m400_pp_frame *f = task->frame;
+
+		num_pp = f->num_pp;
+	}
+
+	if (num_pp == 0 || num_pp > pipe->num_processor)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void lima_pp_task_run(struct lima_sched_pipe *pipe,
+			     struct lima_sched_task *task)
+{
+	if (pipe->bcast_processor) {
+		struct drm_lima_m450_pp_frame *frame = task->frame;
+		struct lima_device *dev = pipe->bcast_processor->dev;
+		struct lima_ip *ip = pipe->bcast_processor;
+		int i;
+
+		pipe->done = 0;
+		atomic_set(&pipe->task, frame->num_pp);
+
+		if (frame->use_dlbu) {
+			lima_dlbu_enable(dev, frame->num_pp);
+
+			frame->frame[LIMA_PP_FRAME >> 2] = LIMA_VA_RESERVE_DLBU;
+			lima_dlbu_set_reg(dev->ip + lima_ip_dlbu, frame->dlbu_regs);
+		} else
+			lima_dlbu_disable(dev);
+
+		lima_bcast_enable(dev, frame->num_pp);
+
+		lima_pp_soft_reset_async_wait(ip);
+
+		lima_pp_write_frame(ip, frame->frame, frame->wb);
+
+		for (i = 0; i < frame->num_pp; i++) {
+			struct lima_ip *ip = pipe->processor[i];
+
+			pp_write(LIMA_PP_STACK, frame->fragment_stack_address[i]);
+			if (!frame->use_dlbu)
+				pp_write(LIMA_PP_FRAME, frame->plbu_array_address[i]);
+		}
+
+		pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_START_RENDERING);
+	} else {
+		struct drm_lima_m400_pp_frame *frame = task->frame;
+		int i;
+
+		atomic_set(&pipe->task, frame->num_pp);
+
+		for (i = 0; i < frame->num_pp; i++) {
+			struct lima_ip *ip = pipe->processor[i];
+
+			frame->frame[LIMA_PP_FRAME >> 2] =
+				frame->plbu_array_address[i];
+			frame->frame[LIMA_PP_STACK >> 2] =
+				frame->fragment_stack_address[i];
+
+			lima_pp_soft_reset_async_wait(ip);
+
+			lima_pp_write_frame(ip, frame->frame, frame->wb);
+
+			pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_START_RENDERING);
+		}
+	}
+}
+
+static void lima_pp_task_fini(struct lima_sched_pipe *pipe)
+{
+	if (pipe->bcast_processor)
+		lima_pp_soft_reset_async(pipe->bcast_processor);
+	else {
+		int i;
+
+		for (i = 0; i < pipe->num_processor; i++)
+			lima_pp_soft_reset_async(pipe->processor[i]);
+	}
+}
+
+static void lima_pp_task_error(struct lima_sched_pipe *pipe)
+{
+	int i;
+
+	for (i = 0; i < pipe->num_processor; i++) {
+		struct lima_ip *ip = pipe->processor[i];
+
+		dev_err(ip->dev->dev, "pp task error %d int_state=%x status=%x\n",
+			i, pp_read(LIMA_PP_INT_STATUS), pp_read(LIMA_PP_STATUS));
+
+		lima_pp_hard_reset(ip);
+	}
+}
+
+static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe)
+{
+	if (atomic_dec_and_test(&pipe->task))
+		lima_sched_pipe_task_done(pipe);
+}
+
+static struct kmem_cache *lima_pp_task_slab;
+static int lima_pp_task_slab_refcnt;
+
+int lima_pp_pipe_init(struct lima_device *dev)
+{
+	int frame_size;
+	struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp;
+
+	if (dev->id == lima_gpu_mali400)
+		frame_size = sizeof(struct drm_lima_m400_pp_frame);
+	else
+		frame_size = sizeof(struct drm_lima_m450_pp_frame);
+
+	if (!lima_pp_task_slab) {
+		lima_pp_task_slab = kmem_cache_create_usercopy(
+			"lima_pp_task", sizeof(struct lima_sched_task) + frame_size,
+			0, SLAB_HWCACHE_ALIGN, sizeof(struct lima_sched_task),
+			frame_size, NULL);
+		if (!lima_pp_task_slab)
+			return -ENOMEM;
+	}
+	lima_pp_task_slab_refcnt++;
+
+	pipe->frame_size = frame_size;
+	pipe->task_slab = lima_pp_task_slab;
+
+	pipe->task_validate = lima_pp_task_validate;
+	pipe->task_run = lima_pp_task_run;
+	pipe->task_fini = lima_pp_task_fini;
+	pipe->task_error = lima_pp_task_error;
+	pipe->task_mmu_error = lima_pp_task_mmu_error;
+
+	return 0;
+}
+
+void lima_pp_pipe_fini(struct lima_device *dev)
+{
+	if (!--lima_pp_task_slab_refcnt) {
+		kmem_cache_destroy(lima_pp_task_slab);
+		lima_pp_task_slab = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/lima/lima_pp.h b/drivers/gpu/drm/lima/lima_pp.h
new file mode 100644
index 000000000..16ec96de1
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_pp.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_PP_H__
+#define __LIMA_PP_H__
+
+struct lima_ip;
+struct lima_device;
+
+int lima_pp_resume(struct lima_ip *ip);
+void lima_pp_suspend(struct lima_ip *ip);
+int lima_pp_init(struct lima_ip *ip);
+void lima_pp_fini(struct lima_ip *ip);
+
+int lima_pp_bcast_resume(struct lima_ip *ip);
+void lima_pp_bcast_suspend(struct lima_ip *ip);
+int lima_pp_bcast_init(struct lima_ip *ip);
+void lima_pp_bcast_fini(struct lima_ip *ip);
+
+int lima_pp_pipe_init(struct lima_device *dev);
+void lima_pp_pipe_fini(struct lima_device *dev);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_regs.h b/drivers/gpu/drm/lima/lima_regs.h
new file mode 100644
index 000000000..0124c90e0
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_regs.h
@@ -0,0 +1,299 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2010-2017 ARM Limited. All rights reserved.
+ * Copyright 2017-2019 Qiang Yu <yuq825@gmail.com>
+ */
+
+#ifndef __LIMA_REGS_H__
+#define __LIMA_REGS_H__
+
+/* This file's register definition is collected from the
+ * official ARM Mali Utgard GPU kernel driver source code
+ */
+
+/* PMU regs */
+#define LIMA_PMU_POWER_UP                  0x00
+#define LIMA_PMU_POWER_DOWN                0x04
+#define   LIMA_PMU_POWER_GP0_MASK          BIT(0)
+#define   LIMA_PMU_POWER_L2_MASK           BIT(1)
+#define   LIMA_PMU_POWER_PP_MASK(i)        BIT(2 + i)
+
+/*
+ * On Mali450 each block automatically starts up its corresponding L2
+ * and the PPs are not fully independent controllable.
+ * Instead PP0, PP1-3 and PP4-7 can be turned on or off.
+ */
+#define   LIMA450_PMU_POWER_PP0_MASK       BIT(1)
+#define   LIMA450_PMU_POWER_PP13_MASK      BIT(2)
+#define   LIMA450_PMU_POWER_PP47_MASK      BIT(3)
+
+#define LIMA_PMU_STATUS                    0x08
+#define LIMA_PMU_INT_MASK                  0x0C
+#define LIMA_PMU_INT_RAWSTAT               0x10
+#define LIMA_PMU_INT_CLEAR                 0x18
+#define   LIMA_PMU_INT_CMD_MASK            BIT(0)
+#define LIMA_PMU_SW_DELAY                  0x1C
+
+/* L2 cache regs */
+#define LIMA_L2_CACHE_SIZE                   0x0004
+#define LIMA_L2_CACHE_STATUS                 0x0008
+#define   LIMA_L2_CACHE_STATUS_COMMAND_BUSY  BIT(0)
+#define   LIMA_L2_CACHE_STATUS_DATA_BUSY     BIT(1)
+#define LIMA_L2_CACHE_COMMAND                0x0010
+#define   LIMA_L2_CACHE_COMMAND_CLEAR_ALL    BIT(0)
+#define LIMA_L2_CACHE_CLEAR_PAGE             0x0014
+#define LIMA_L2_CACHE_MAX_READS              0x0018
+#define LIMA_L2_CACHE_ENABLE                 0x001C
+#define   LIMA_L2_CACHE_ENABLE_ACCESS        BIT(0)
+#define   LIMA_L2_CACHE_ENABLE_READ_ALLOCATE BIT(1)
+#define LIMA_L2_CACHE_PERFCNT_SRC0           0x0020
+#define LIMA_L2_CACHE_PERFCNT_VAL0           0x0024
+#define LIMA_L2_CACHE_PERFCNT_SRC1           0x0028
+#define LIMA_L2_CACHE_ERFCNT_VAL1            0x002C
+
+/* GP regs */
+#define LIMA_GP_VSCL_START_ADDR                0x00
+#define LIMA_GP_VSCL_END_ADDR                  0x04
+#define LIMA_GP_PLBUCL_START_ADDR              0x08
+#define LIMA_GP_PLBUCL_END_ADDR                0x0c
+#define LIMA_GP_PLBU_ALLOC_START_ADDR          0x10
+#define LIMA_GP_PLBU_ALLOC_END_ADDR            0x14
+#define LIMA_GP_CMD                            0x20
+#define   LIMA_GP_CMD_START_VS                 BIT(0)
+#define   LIMA_GP_CMD_START_PLBU               BIT(1)
+#define   LIMA_GP_CMD_UPDATE_PLBU_ALLOC        BIT(4)
+#define   LIMA_GP_CMD_RESET                    BIT(5)
+#define   LIMA_GP_CMD_FORCE_HANG               BIT(6)
+#define   LIMA_GP_CMD_STOP_BUS                 BIT(9)
+#define   LIMA_GP_CMD_SOFT_RESET               BIT(10)
+#define LIMA_GP_INT_RAWSTAT                    0x24
+#define LIMA_GP_INT_CLEAR                      0x28
+#define LIMA_GP_INT_MASK                       0x2C
+#define LIMA_GP_INT_STAT                       0x30
+#define   LIMA_GP_IRQ_VS_END_CMD_LST           BIT(0)
+#define   LIMA_GP_IRQ_PLBU_END_CMD_LST         BIT(1)
+#define   LIMA_GP_IRQ_PLBU_OUT_OF_MEM          BIT(2)
+#define   LIMA_GP_IRQ_VS_SEM_IRQ               BIT(3)
+#define   LIMA_GP_IRQ_PLBU_SEM_IRQ             BIT(4)
+#define   LIMA_GP_IRQ_HANG                     BIT(5)
+#define   LIMA_GP_IRQ_FORCE_HANG               BIT(6)
+#define   LIMA_GP_IRQ_PERF_CNT_0_LIMIT         BIT(7)
+#define   LIMA_GP_IRQ_PERF_CNT_1_LIMIT         BIT(8)
+#define   LIMA_GP_IRQ_WRITE_BOUND_ERR          BIT(9)
+#define   LIMA_GP_IRQ_SYNC_ERROR               BIT(10)
+#define   LIMA_GP_IRQ_AXI_BUS_ERROR            BIT(11)
+#define   LIMA_GP_IRQ_AXI_BUS_STOPPED          BIT(12)
+#define   LIMA_GP_IRQ_VS_INVALID_CMD           BIT(13)
+#define   LIMA_GP_IRQ_PLB_INVALID_CMD          BIT(14)
+#define   LIMA_GP_IRQ_RESET_COMPLETED          BIT(19)
+#define   LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW      BIT(20)
+#define   LIMA_GP_IRQ_SEMAPHORE_OVERFLOW       BIT(21)
+#define   LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS  BIT(22)
+#define LIMA_GP_WRITE_BOUND_LOW                0x34
+#define LIMA_GP_PERF_CNT_0_ENABLE              0x3C
+#define LIMA_GP_PERF_CNT_1_ENABLE              0x40
+#define LIMA_GP_PERF_CNT_0_SRC                 0x44
+#define LIMA_GP_PERF_CNT_1_SRC                 0x48
+#define LIMA_GP_PERF_CNT_0_VALUE               0x4C
+#define LIMA_GP_PERF_CNT_1_VALUE               0x50
+#define LIMA_GP_PERF_CNT_0_LIMIT               0x54
+#define LIMA_GP_STATUS                         0x68
+#define   LIMA_GP_STATUS_VS_ACTIVE             BIT(1)
+#define   LIMA_GP_STATUS_BUS_STOPPED           BIT(2)
+#define   LIMA_GP_STATUS_PLBU_ACTIVE           BIT(3)
+#define   LIMA_GP_STATUS_BUS_ERROR             BIT(6)
+#define   LIMA_GP_STATUS_WRITE_BOUND_ERR       BIT(8)
+#define LIMA_GP_VERSION                        0x6C
+#define LIMA_GP_VSCL_START_ADDR_READ           0x80
+#define LIMA_GP_PLBCL_START_ADDR_READ          0x84
+#define LIMA_GP_CONTR_AXI_BUS_ERROR_STAT       0x94
+
+#define LIMA_GP_IRQ_MASK_ALL		   \
+	(				   \
+	 LIMA_GP_IRQ_VS_END_CMD_LST      | \
+	 LIMA_GP_IRQ_PLBU_END_CMD_LST    | \
+	 LIMA_GP_IRQ_PLBU_OUT_OF_MEM     | \
+	 LIMA_GP_IRQ_VS_SEM_IRQ          | \
+	 LIMA_GP_IRQ_PLBU_SEM_IRQ        | \
+	 LIMA_GP_IRQ_HANG                | \
+	 LIMA_GP_IRQ_FORCE_HANG          | \
+	 LIMA_GP_IRQ_PERF_CNT_0_LIMIT    | \
+	 LIMA_GP_IRQ_PERF_CNT_1_LIMIT    | \
+	 LIMA_GP_IRQ_WRITE_BOUND_ERR     | \
+	 LIMA_GP_IRQ_SYNC_ERROR          | \
+	 LIMA_GP_IRQ_AXI_BUS_ERROR       | \
+	 LIMA_GP_IRQ_AXI_BUS_STOPPED     | \
+	 LIMA_GP_IRQ_VS_INVALID_CMD      | \
+	 LIMA_GP_IRQ_PLB_INVALID_CMD     | \
+	 LIMA_GP_IRQ_RESET_COMPLETED     | \
+	 LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW | \
+	 LIMA_GP_IRQ_SEMAPHORE_OVERFLOW  | \
+	 LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS)
+
+#define LIMA_GP_IRQ_MASK_ERROR             \
+	(                                  \
+	 LIMA_GP_IRQ_PLBU_OUT_OF_MEM     | \
+	 LIMA_GP_IRQ_FORCE_HANG          | \
+	 LIMA_GP_IRQ_WRITE_BOUND_ERR     | \
+	 LIMA_GP_IRQ_SYNC_ERROR          | \
+	 LIMA_GP_IRQ_AXI_BUS_ERROR       | \
+	 LIMA_GP_IRQ_VS_INVALID_CMD      | \
+	 LIMA_GP_IRQ_PLB_INVALID_CMD     | \
+	 LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW | \
+	 LIMA_GP_IRQ_SEMAPHORE_OVERFLOW  | \
+	 LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS)
+
+#define LIMA_GP_IRQ_MASK_USED		   \
+	(				   \
+	 LIMA_GP_IRQ_VS_END_CMD_LST      | \
+	 LIMA_GP_IRQ_PLBU_END_CMD_LST    | \
+	 LIMA_GP_IRQ_MASK_ERROR)
+
+/* PP regs */
+#define LIMA_PP_FRAME                        0x0000
+#define LIMA_PP_RSW			     0x0004
+#define LIMA_PP_STACK			     0x0030
+#define LIMA_PP_STACK_SIZE		     0x0034
+#define LIMA_PP_ORIGIN_OFFSET_X	             0x0040
+#define LIMA_PP_WB(i)                        (0x0100 * (i + 1))
+#define   LIMA_PP_WB_SOURCE_SELECT           0x0000
+#define	  LIMA_PP_WB_SOURCE_ADDR             0x0004
+
+#define LIMA_PP_VERSION                      0x1000
+#define LIMA_PP_CURRENT_REND_LIST_ADDR       0x1004
+#define LIMA_PP_STATUS                       0x1008
+#define   LIMA_PP_STATUS_RENDERING_ACTIVE    BIT(0)
+#define   LIMA_PP_STATUS_BUS_STOPPED         BIT(4)
+#define LIMA_PP_CTRL                         0x100c
+#define   LIMA_PP_CTRL_STOP_BUS              BIT(0)
+#define   LIMA_PP_CTRL_FLUSH_CACHES          BIT(3)
+#define   LIMA_PP_CTRL_FORCE_RESET           BIT(5)
+#define   LIMA_PP_CTRL_START_RENDERING       BIT(6)
+#define   LIMA_PP_CTRL_SOFT_RESET            BIT(7)
+#define LIMA_PP_INT_RAWSTAT                  0x1020
+#define LIMA_PP_INT_CLEAR                    0x1024
+#define LIMA_PP_INT_MASK                     0x1028
+#define LIMA_PP_INT_STATUS                   0x102c
+#define   LIMA_PP_IRQ_END_OF_FRAME           BIT(0)
+#define   LIMA_PP_IRQ_END_OF_TILE            BIT(1)
+#define   LIMA_PP_IRQ_HANG                   BIT(2)
+#define   LIMA_PP_IRQ_FORCE_HANG             BIT(3)
+#define   LIMA_PP_IRQ_BUS_ERROR              BIT(4)
+#define   LIMA_PP_IRQ_BUS_STOP               BIT(5)
+#define   LIMA_PP_IRQ_CNT_0_LIMIT            BIT(6)
+#define   LIMA_PP_IRQ_CNT_1_LIMIT            BIT(7)
+#define   LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR   BIT(8)
+#define   LIMA_PP_IRQ_INVALID_PLIST_COMMAND  BIT(9)
+#define   LIMA_PP_IRQ_CALL_STACK_UNDERFLOW   BIT(10)
+#define   LIMA_PP_IRQ_CALL_STACK_OVERFLOW    BIT(11)
+#define   LIMA_PP_IRQ_RESET_COMPLETED        BIT(12)
+#define LIMA_PP_WRITE_BOUNDARY_LOW           0x1044
+#define LIMA_PP_BUS_ERROR_STATUS             0x1050
+#define LIMA_PP_PERF_CNT_0_ENABLE            0x1080
+#define LIMA_PP_PERF_CNT_0_SRC               0x1084
+#define LIMA_PP_PERF_CNT_0_LIMIT             0x1088
+#define LIMA_PP_PERF_CNT_0_VALUE             0x108c
+#define LIMA_PP_PERF_CNT_1_ENABLE            0x10a0
+#define LIMA_PP_PERF_CNT_1_SRC               0x10a4
+#define LIMA_PP_PERF_CNT_1_LIMIT             0x10a8
+#define LIMA_PP_PERF_CNT_1_VALUE             0x10ac
+#define LIMA_PP_PERFMON_CONTR                0x10b0
+#define LIMA_PP_PERFMON_BASE                 0x10b4
+
+#define LIMA_PP_IRQ_MASK_ALL                 \
+	(                                    \
+	 LIMA_PP_IRQ_END_OF_FRAME          | \
+	 LIMA_PP_IRQ_END_OF_TILE           | \
+	 LIMA_PP_IRQ_HANG                  | \
+	 LIMA_PP_IRQ_FORCE_HANG            | \
+	 LIMA_PP_IRQ_BUS_ERROR             | \
+	 LIMA_PP_IRQ_BUS_STOP              | \
+	 LIMA_PP_IRQ_CNT_0_LIMIT           | \
+	 LIMA_PP_IRQ_CNT_1_LIMIT           | \
+	 LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR  | \
+	 LIMA_PP_IRQ_INVALID_PLIST_COMMAND | \
+	 LIMA_PP_IRQ_CALL_STACK_UNDERFLOW  | \
+	 LIMA_PP_IRQ_CALL_STACK_OVERFLOW   | \
+	 LIMA_PP_IRQ_RESET_COMPLETED)
+
+#define LIMA_PP_IRQ_MASK_ERROR               \
+	(                                    \
+	 LIMA_PP_IRQ_FORCE_HANG            | \
+	 LIMA_PP_IRQ_BUS_ERROR             | \
+	 LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR  | \
+	 LIMA_PP_IRQ_INVALID_PLIST_COMMAND | \
+	 LIMA_PP_IRQ_CALL_STACK_UNDERFLOW  | \
+	 LIMA_PP_IRQ_CALL_STACK_OVERFLOW)
+
+#define LIMA_PP_IRQ_MASK_USED                \
+	(                                    \
+	 LIMA_PP_IRQ_END_OF_FRAME          | \
+	 LIMA_PP_IRQ_MASK_ERROR)
+
+/* MMU regs */
+#define LIMA_MMU_DTE_ADDR                     0x0000
+#define LIMA_MMU_STATUS                       0x0004
+#define   LIMA_MMU_STATUS_PAGING_ENABLED      BIT(0)
+#define   LIMA_MMU_STATUS_PAGE_FAULT_ACTIVE   BIT(1)
+#define   LIMA_MMU_STATUS_STALL_ACTIVE        BIT(2)
+#define   LIMA_MMU_STATUS_IDLE                BIT(3)
+#define   LIMA_MMU_STATUS_REPLAY_BUFFER_EMPTY BIT(4)
+#define   LIMA_MMU_STATUS_PAGE_FAULT_IS_WRITE BIT(5)
+#define   LIMA_MMU_STATUS_BUS_ID(x)           ((x >> 6) & 0x1F)
+#define   LIMA_MMU_STATUS_STALL_NOT_ACTIVE    BIT(31)
+#define LIMA_MMU_COMMAND                      0x0008
+#define   LIMA_MMU_COMMAND_ENABLE_PAGING      0x00
+#define   LIMA_MMU_COMMAND_DISABLE_PAGING     0x01
+#define   LIMA_MMU_COMMAND_ENABLE_STALL       0x02
+#define   LIMA_MMU_COMMAND_DISABLE_STALL      0x03
+#define   LIMA_MMU_COMMAND_ZAP_CACHE          0x04
+#define   LIMA_MMU_COMMAND_PAGE_FAULT_DONE    0x05
+#define   LIMA_MMU_COMMAND_HARD_RESET         0x06
+#define LIMA_MMU_PAGE_FAULT_ADDR              0x000C
+#define LIMA_MMU_ZAP_ONE_LINE                 0x0010
+#define LIMA_MMU_INT_RAWSTAT                  0x0014
+#define LIMA_MMU_INT_CLEAR                    0x0018
+#define LIMA_MMU_INT_MASK                     0x001C
+#define   LIMA_MMU_INT_PAGE_FAULT             BIT(0)
+#define   LIMA_MMU_INT_READ_BUS_ERROR         BIT(1)
+#define LIMA_MMU_INT_STATUS                   0x0020
+
+#define LIMA_VM_FLAG_PRESENT          BIT(0)
+#define LIMA_VM_FLAG_READ_PERMISSION  BIT(1)
+#define LIMA_VM_FLAG_WRITE_PERMISSION BIT(2)
+#define LIMA_VM_FLAG_OVERRIDE_CACHE   BIT(3)
+#define LIMA_VM_FLAG_WRITE_CACHEABLE  BIT(4)
+#define LIMA_VM_FLAG_WRITE_ALLOCATE   BIT(5)
+#define LIMA_VM_FLAG_WRITE_BUFFERABLE BIT(6)
+#define LIMA_VM_FLAG_READ_CACHEABLE   BIT(7)
+#define LIMA_VM_FLAG_READ_ALLOCATE    BIT(8)
+#define LIMA_VM_FLAG_MASK             0x1FF
+
+#define LIMA_VM_FLAGS_CACHE (			 \
+		LIMA_VM_FLAG_PRESENT |		 \
+		LIMA_VM_FLAG_READ_PERMISSION |	 \
+		LIMA_VM_FLAG_WRITE_PERMISSION |	 \
+		LIMA_VM_FLAG_OVERRIDE_CACHE |	 \
+		LIMA_VM_FLAG_WRITE_CACHEABLE |	 \
+		LIMA_VM_FLAG_WRITE_BUFFERABLE |	 \
+		LIMA_VM_FLAG_READ_CACHEABLE |	 \
+		LIMA_VM_FLAG_READ_ALLOCATE)
+
+#define LIMA_VM_FLAGS_UNCACHE (			\
+		LIMA_VM_FLAG_PRESENT |		\
+		LIMA_VM_FLAG_READ_PERMISSION |	\
+		LIMA_VM_FLAG_WRITE_PERMISSION)
+
+/* DLBU regs */
+#define LIMA_DLBU_MASTER_TLLIST_PHYS_ADDR  0x0000
+#define	LIMA_DLBU_MASTER_TLLIST_VADDR      0x0004
+#define	LIMA_DLBU_TLLIST_VBASEADDR         0x0008
+#define	LIMA_DLBU_FB_DIM                   0x000C
+#define	LIMA_DLBU_TLLIST_CONF              0x0010
+#define	LIMA_DLBU_START_TILE_POS           0x0014
+#define	LIMA_DLBU_PP_ENABLE_MASK           0x0018
+
+/* BCAST regs */
+#define LIMA_BCAST_BROADCAST_MASK    0x0
+#define LIMA_BCAST_INTERRUPT_MASK    0x4
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
new file mode 100644
index 000000000..f6e7a88a5
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -0,0 +1,532 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/pm_runtime.h>
+
+#include "lima_devfreq.h"
+#include "lima_drv.h"
+#include "lima_sched.h"
+#include "lima_vm.h"
+#include "lima_mmu.h"
+#include "lima_l2_cache.h"
+#include "lima_gem.h"
+#include "lima_trace.h"
+
+struct lima_fence {
+	struct dma_fence base;
+	struct lima_sched_pipe *pipe;
+};
+
+static struct kmem_cache *lima_fence_slab;
+static int lima_fence_slab_refcnt;
+
+int lima_sched_slab_init(void)
+{
+	if (!lima_fence_slab) {
+		lima_fence_slab = kmem_cache_create(
+			"lima_fence", sizeof(struct lima_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!lima_fence_slab)
+			return -ENOMEM;
+	}
+
+	lima_fence_slab_refcnt++;
+	return 0;
+}
+
+void lima_sched_slab_fini(void)
+{
+	if (!--lima_fence_slab_refcnt) {
+		kmem_cache_destroy(lima_fence_slab);
+		lima_fence_slab = NULL;
+	}
+}
+
+static inline struct lima_fence *to_lima_fence(struct dma_fence *fence)
+{
+	return container_of(fence, struct lima_fence, base);
+}
+
+static const char *lima_fence_get_driver_name(struct dma_fence *fence)
+{
+	return "lima";
+}
+
+static const char *lima_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct lima_fence *f = to_lima_fence(fence);
+
+	return f->pipe->base.name;
+}
+
+static void lima_fence_release_rcu(struct rcu_head *rcu)
+{
+	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
+	struct lima_fence *fence = to_lima_fence(f);
+
+	kmem_cache_free(lima_fence_slab, fence);
+}
+
+static void lima_fence_release(struct dma_fence *fence)
+{
+	struct lima_fence *f = to_lima_fence(fence);
+
+	call_rcu(&f->base.rcu, lima_fence_release_rcu);
+}
+
+static const struct dma_fence_ops lima_fence_ops = {
+	.get_driver_name = lima_fence_get_driver_name,
+	.get_timeline_name = lima_fence_get_timeline_name,
+	.release = lima_fence_release,
+};
+
+static struct lima_fence *lima_fence_create(struct lima_sched_pipe *pipe)
+{
+	struct lima_fence *fence;
+
+	fence = kmem_cache_zalloc(lima_fence_slab, GFP_KERNEL);
+	if (!fence)
+		return NULL;
+
+	fence->pipe = pipe;
+	dma_fence_init(&fence->base, &lima_fence_ops, &pipe->fence_lock,
+		       pipe->fence_context, ++pipe->fence_seqno);
+
+	return fence;
+}
+
+static inline struct lima_sched_task *to_lima_task(struct drm_sched_job *job)
+{
+	return container_of(job, struct lima_sched_task, base);
+}
+
+static inline struct lima_sched_pipe *to_lima_pipe(struct drm_gpu_scheduler *sched)
+{
+	return container_of(sched, struct lima_sched_pipe, base);
+}
+
+int lima_sched_task_init(struct lima_sched_task *task,
+			 struct lima_sched_context *context,
+			 struct lima_bo **bos, int num_bos,
+			 struct lima_vm *vm)
+{
+	int err, i;
+
+	task->bos = kmemdup(bos, sizeof(*bos) * num_bos, GFP_KERNEL);
+	if (!task->bos)
+		return -ENOMEM;
+
+	for (i = 0; i < num_bos; i++)
+		drm_gem_object_get(&bos[i]->base.base);
+
+	err = drm_sched_job_init(&task->base, &context->base, vm);
+	if (err) {
+		kfree(task->bos);
+		return err;
+	}
+
+	task->num_bos = num_bos;
+	task->vm = lima_vm_get(vm);
+
+	xa_init_flags(&task->deps, XA_FLAGS_ALLOC);
+
+	return 0;
+}
+
+void lima_sched_task_fini(struct lima_sched_task *task)
+{
+	struct dma_fence *fence;
+	unsigned long index;
+	int i;
+
+	drm_sched_job_cleanup(&task->base);
+
+	xa_for_each(&task->deps, index, fence) {
+		dma_fence_put(fence);
+	}
+	xa_destroy(&task->deps);
+
+	if (task->bos) {
+		for (i = 0; i < task->num_bos; i++)
+			drm_gem_object_put(&task->bos[i]->base.base);
+		kfree(task->bos);
+	}
+
+	lima_vm_put(task->vm);
+}
+
+int lima_sched_context_init(struct lima_sched_pipe *pipe,
+			    struct lima_sched_context *context,
+			    atomic_t *guilty)
+{
+	struct drm_gpu_scheduler *sched = &pipe->base;
+
+	return drm_sched_entity_init(&context->base, DRM_SCHED_PRIORITY_NORMAL,
+				     &sched, 1, guilty);
+}
+
+void lima_sched_context_fini(struct lima_sched_pipe *pipe,
+			     struct lima_sched_context *context)
+{
+	drm_sched_entity_fini(&context->base);
+}
+
+struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context,
+						struct lima_sched_task *task)
+{
+	struct dma_fence *fence = dma_fence_get(&task->base.s_fence->finished);
+
+	trace_lima_task_submit(task);
+	drm_sched_entity_push_job(&task->base, &context->base);
+	return fence;
+}
+
+static struct dma_fence *lima_sched_dependency(struct drm_sched_job *job,
+					       struct drm_sched_entity *entity)
+{
+	struct lima_sched_task *task = to_lima_task(job);
+
+	if (!xa_empty(&task->deps))
+		return xa_erase(&task->deps, task->last_dep++);
+
+	return NULL;
+}
+
+static int lima_pm_busy(struct lima_device *ldev)
+{
+	int ret;
+
+	/* resume GPU if it has been suspended by runtime PM */
+	ret = pm_runtime_resume_and_get(ldev->dev);
+	if (ret < 0)
+		return ret;
+
+	lima_devfreq_record_busy(&ldev->devfreq);
+	return 0;
+}
+
+static void lima_pm_idle(struct lima_device *ldev)
+{
+	lima_devfreq_record_idle(&ldev->devfreq);
+
+	/* GPU can do auto runtime suspend */
+	pm_runtime_mark_last_busy(ldev->dev);
+	pm_runtime_put_autosuspend(ldev->dev);
+}
+
+static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job)
+{
+	struct lima_sched_task *task = to_lima_task(job);
+	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
+	struct lima_device *ldev = pipe->ldev;
+	struct lima_fence *fence;
+	struct dma_fence *ret;
+	int i, err;
+
+	/* after GPU reset */
+	if (job->s_fence->finished.error < 0)
+		return NULL;
+
+	fence = lima_fence_create(pipe);
+	if (!fence)
+		return NULL;
+
+	err = lima_pm_busy(ldev);
+	if (err < 0) {
+		dma_fence_put(&fence->base);
+		return NULL;
+	}
+
+	task->fence = &fence->base;
+
+	/* for caller usage of the fence, otherwise irq handler
+	 * may consume the fence before caller use it
+	 */
+	ret = dma_fence_get(task->fence);
+
+	pipe->current_task = task;
+
+	/* this is needed for MMU to work correctly, otherwise GP/PP
+	 * will hang or page fault for unknown reason after running for
+	 * a while.
+	 *
+	 * Need to investigate:
+	 * 1. is it related to TLB
+	 * 2. how much performance will be affected by L2 cache flush
+	 * 3. can we reduce the calling of this function because all
+	 *    GP/PP use the same L2 cache on mali400
+	 *
+	 * TODO:
+	 * 1. move this to task fini to save some wait time?
+	 * 2. when GP/PP use different l2 cache, need PP wait GP l2
+	 *    cache flush?
+	 */
+	for (i = 0; i < pipe->num_l2_cache; i++)
+		lima_l2_cache_flush(pipe->l2_cache[i]);
+
+	lima_vm_put(pipe->current_vm);
+	pipe->current_vm = lima_vm_get(task->vm);
+
+	if (pipe->bcast_mmu)
+		lima_mmu_switch_vm(pipe->bcast_mmu, pipe->current_vm);
+	else {
+		for (i = 0; i < pipe->num_mmu; i++)
+			lima_mmu_switch_vm(pipe->mmu[i], pipe->current_vm);
+	}
+
+	trace_lima_task_run(task);
+
+	pipe->error = false;
+	pipe->task_run(pipe, task);
+
+	return task->fence;
+}
+
+static void lima_sched_build_error_task_list(struct lima_sched_task *task)
+{
+	struct lima_sched_error_task *et;
+	struct lima_sched_pipe *pipe = to_lima_pipe(task->base.sched);
+	struct lima_ip *ip = pipe->processor[0];
+	int pipe_id = ip->id == lima_ip_gp ? lima_pipe_gp : lima_pipe_pp;
+	struct lima_device *dev = ip->dev;
+	struct lima_sched_context *sched_ctx =
+		container_of(task->base.entity,
+			     struct lima_sched_context, base);
+	struct lima_ctx *ctx =
+		container_of(sched_ctx, struct lima_ctx, context[pipe_id]);
+	struct lima_dump_task *dt;
+	struct lima_dump_chunk *chunk;
+	struct lima_dump_chunk_pid *pid_chunk;
+	struct lima_dump_chunk_buffer *buffer_chunk;
+	u32 size, task_size, mem_size;
+	int i;
+
+	mutex_lock(&dev->error_task_list_lock);
+
+	if (dev->dump.num_tasks >= lima_max_error_tasks) {
+		dev_info(dev->dev, "fail to save task state from %s pid %d: "
+			 "error task list is full\n", ctx->pname, ctx->pid);
+		goto out;
+	}
+
+	/* frame chunk */
+	size = sizeof(struct lima_dump_chunk) + pipe->frame_size;
+	/* process name chunk */
+	size += sizeof(struct lima_dump_chunk) + sizeof(ctx->pname);
+	/* pid chunk */
+	size += sizeof(struct lima_dump_chunk);
+	/* buffer chunks */
+	for (i = 0; i < task->num_bos; i++) {
+		struct lima_bo *bo = task->bos[i];
+
+		size += sizeof(struct lima_dump_chunk);
+		size += bo->heap_size ? bo->heap_size : lima_bo_size(bo);
+	}
+
+	task_size = size + sizeof(struct lima_dump_task);
+	mem_size = task_size + sizeof(*et);
+	et = kvmalloc(mem_size, GFP_KERNEL);
+	if (!et) {
+		dev_err(dev->dev, "fail to alloc task dump buffer of size %x\n",
+			mem_size);
+		goto out;
+	}
+
+	et->data = et + 1;
+	et->size = task_size;
+
+	dt = et->data;
+	memset(dt, 0, sizeof(*dt));
+	dt->id = pipe_id;
+	dt->size = size;
+
+	chunk = (struct lima_dump_chunk *)(dt + 1);
+	memset(chunk, 0, sizeof(*chunk));
+	chunk->id = LIMA_DUMP_CHUNK_FRAME;
+	chunk->size = pipe->frame_size;
+	memcpy(chunk + 1, task->frame, pipe->frame_size);
+	dt->num_chunks++;
+
+	chunk = (void *)(chunk + 1) + chunk->size;
+	memset(chunk, 0, sizeof(*chunk));
+	chunk->id = LIMA_DUMP_CHUNK_PROCESS_NAME;
+	chunk->size = sizeof(ctx->pname);
+	memcpy(chunk + 1, ctx->pname, sizeof(ctx->pname));
+	dt->num_chunks++;
+
+	pid_chunk = (void *)(chunk + 1) + chunk->size;
+	memset(pid_chunk, 0, sizeof(*pid_chunk));
+	pid_chunk->id = LIMA_DUMP_CHUNK_PROCESS_ID;
+	pid_chunk->pid = ctx->pid;
+	dt->num_chunks++;
+
+	buffer_chunk = (void *)(pid_chunk + 1) + pid_chunk->size;
+	for (i = 0; i < task->num_bos; i++) {
+		struct lima_bo *bo = task->bos[i];
+		void *data;
+
+		memset(buffer_chunk, 0, sizeof(*buffer_chunk));
+		buffer_chunk->id = LIMA_DUMP_CHUNK_BUFFER;
+		buffer_chunk->va = lima_vm_get_va(task->vm, bo);
+
+		if (bo->heap_size) {
+			buffer_chunk->size = bo->heap_size;
+
+			data = vmap(bo->base.pages, bo->heap_size >> PAGE_SHIFT,
+				    VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+			if (!data) {
+				kvfree(et);
+				goto out;
+			}
+
+			memcpy(buffer_chunk + 1, data, buffer_chunk->size);
+
+			vunmap(data);
+		} else {
+			buffer_chunk->size = lima_bo_size(bo);
+
+			data = drm_gem_shmem_vmap(&bo->base.base);
+			if (IS_ERR_OR_NULL(data)) {
+				kvfree(et);
+				goto out;
+			}
+
+			memcpy(buffer_chunk + 1, data, buffer_chunk->size);
+
+			drm_gem_shmem_vunmap(&bo->base.base, data);
+		}
+
+		buffer_chunk = (void *)(buffer_chunk + 1) + buffer_chunk->size;
+		dt->num_chunks++;
+	}
+
+	list_add(&et->list, &dev->error_task_list);
+	dev->dump.size += et->size;
+	dev->dump.num_tasks++;
+
+	dev_info(dev->dev, "save error task state success\n");
+
+out:
+	mutex_unlock(&dev->error_task_list_lock);
+}
+
+static void lima_sched_timedout_job(struct drm_sched_job *job)
+{
+	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
+	struct lima_sched_task *task = to_lima_task(job);
+	struct lima_device *ldev = pipe->ldev;
+
+	if (!pipe->error)
+		DRM_ERROR("lima job timeout\n");
+
+	drm_sched_stop(&pipe->base, &task->base);
+
+	drm_sched_increase_karma(&task->base);
+
+	lima_sched_build_error_task_list(task);
+
+	pipe->task_error(pipe);
+
+	if (pipe->bcast_mmu)
+		lima_mmu_page_fault_resume(pipe->bcast_mmu);
+	else {
+		int i;
+
+		for (i = 0; i < pipe->num_mmu; i++)
+			lima_mmu_page_fault_resume(pipe->mmu[i]);
+	}
+
+	lima_vm_put(pipe->current_vm);
+	pipe->current_vm = NULL;
+	pipe->current_task = NULL;
+
+	lima_pm_idle(ldev);
+
+	drm_sched_resubmit_jobs(&pipe->base);
+	drm_sched_start(&pipe->base, true);
+}
+
+static void lima_sched_free_job(struct drm_sched_job *job)
+{
+	struct lima_sched_task *task = to_lima_task(job);
+	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
+	struct lima_vm *vm = task->vm;
+	struct lima_bo **bos = task->bos;
+	int i;
+
+	dma_fence_put(task->fence);
+
+	for (i = 0; i < task->num_bos; i++)
+		lima_vm_bo_del(vm, bos[i]);
+
+	lima_sched_task_fini(task);
+	kmem_cache_free(pipe->task_slab, task);
+}
+
+static const struct drm_sched_backend_ops lima_sched_ops = {
+	.dependency = lima_sched_dependency,
+	.run_job = lima_sched_run_job,
+	.timedout_job = lima_sched_timedout_job,
+	.free_job = lima_sched_free_job,
+};
+
+static void lima_sched_recover_work(struct work_struct *work)
+{
+	struct lima_sched_pipe *pipe =
+		container_of(work, struct lima_sched_pipe, recover_work);
+	int i;
+
+	for (i = 0; i < pipe->num_l2_cache; i++)
+		lima_l2_cache_flush(pipe->l2_cache[i]);
+
+	if (pipe->bcast_mmu) {
+		lima_mmu_flush_tlb(pipe->bcast_mmu);
+	} else {
+		for (i = 0; i < pipe->num_mmu; i++)
+			lima_mmu_flush_tlb(pipe->mmu[i]);
+	}
+
+	if (pipe->task_recover(pipe))
+		drm_sched_fault(&pipe->base);
+}
+
+int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
+{
+	unsigned int timeout = lima_sched_timeout_ms > 0 ?
+			       lima_sched_timeout_ms : 500;
+
+	pipe->fence_context = dma_fence_context_alloc(1);
+	spin_lock_init(&pipe->fence_lock);
+
+	INIT_WORK(&pipe->recover_work, lima_sched_recover_work);
+
+	return drm_sched_init(&pipe->base, &lima_sched_ops, 1,
+			      lima_job_hang_limit, msecs_to_jiffies(timeout),
+			      name);
+}
+
+void lima_sched_pipe_fini(struct lima_sched_pipe *pipe)
+{
+	drm_sched_fini(&pipe->base);
+}
+
+void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe)
+{
+	struct lima_sched_task *task = pipe->current_task;
+	struct lima_device *ldev = pipe->ldev;
+
+	if (pipe->error) {
+		if (task && task->recoverable)
+			schedule_work(&pipe->recover_work);
+		else
+			drm_sched_fault(&pipe->base);
+	} else {
+		pipe->task_fini(pipe);
+		dma_fence_signal(task->fence);
+
+		lima_pm_idle(ldev);
+	}
+}
diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h
new file mode 100644
index 000000000..90f03c48e
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_sched.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_SCHED_H__
+#define __LIMA_SCHED_H__
+
+#include <drm/gpu_scheduler.h>
+#include <linux/list.h>
+#include <linux/xarray.h>
+
+struct lima_device;
+struct lima_vm;
+
+struct lima_sched_error_task {
+	struct list_head list;
+	void *data;
+	u32 size;
+};
+
+struct lima_sched_task {
+	struct drm_sched_job base;
+
+	struct lima_vm *vm;
+	void *frame;
+
+	struct xarray deps;
+	unsigned long last_dep;
+
+	struct lima_bo **bos;
+	int num_bos;
+
+	bool recoverable;
+	struct lima_bo *heap;
+
+	/* pipe fence */
+	struct dma_fence *fence;
+};
+
+struct lima_sched_context {
+	struct drm_sched_entity base;
+};
+
+#define LIMA_SCHED_PIPE_MAX_MMU       8
+#define LIMA_SCHED_PIPE_MAX_L2_CACHE  2
+#define LIMA_SCHED_PIPE_MAX_PROCESSOR 8
+
+struct lima_ip;
+
+struct lima_sched_pipe {
+	struct drm_gpu_scheduler base;
+
+	u64 fence_context;
+	u32 fence_seqno;
+	spinlock_t fence_lock;
+
+	struct lima_device *ldev;
+
+	struct lima_sched_task *current_task;
+	struct lima_vm *current_vm;
+
+	struct lima_ip *mmu[LIMA_SCHED_PIPE_MAX_MMU];
+	int num_mmu;
+
+	struct lima_ip *l2_cache[LIMA_SCHED_PIPE_MAX_L2_CACHE];
+	int num_l2_cache;
+
+	struct lima_ip *processor[LIMA_SCHED_PIPE_MAX_PROCESSOR];
+	int num_processor;
+
+	struct lima_ip *bcast_processor;
+	struct lima_ip *bcast_mmu;
+
+	u32 done;
+	bool error;
+	atomic_t task;
+
+	int frame_size;
+	struct kmem_cache *task_slab;
+
+	int (*task_validate)(struct lima_sched_pipe *pipe, struct lima_sched_task *task);
+	void (*task_run)(struct lima_sched_pipe *pipe, struct lima_sched_task *task);
+	void (*task_fini)(struct lima_sched_pipe *pipe);
+	void (*task_error)(struct lima_sched_pipe *pipe);
+	void (*task_mmu_error)(struct lima_sched_pipe *pipe);
+	int (*task_recover)(struct lima_sched_pipe *pipe);
+
+	struct work_struct recover_work;
+};
+
+int lima_sched_task_init(struct lima_sched_task *task,
+			 struct lima_sched_context *context,
+			 struct lima_bo **bos, int num_bos,
+			 struct lima_vm *vm);
+void lima_sched_task_fini(struct lima_sched_task *task);
+
+int lima_sched_context_init(struct lima_sched_pipe *pipe,
+			    struct lima_sched_context *context,
+			    atomic_t *guilty);
+void lima_sched_context_fini(struct lima_sched_pipe *pipe,
+			     struct lima_sched_context *context);
+struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context,
+						struct lima_sched_task *task);
+
+int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name);
+void lima_sched_pipe_fini(struct lima_sched_pipe *pipe);
+void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe);
+
+static inline void lima_sched_pipe_mmu_error(struct lima_sched_pipe *pipe)
+{
+	pipe->error = true;
+	pipe->task_mmu_error(pipe);
+}
+
+int lima_sched_slab_init(void);
+void lima_sched_slab_fini(void);
+
+#endif
diff --git a/drivers/gpu/drm/lima/lima_trace.c b/drivers/gpu/drm/lima/lima_trace.c
new file mode 100644
index 000000000..ea1c7289b
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_trace.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2020 Qiang Yu <yuq825@gmail.com> */
+
+#include "lima_sched.h"
+
+#define CREATE_TRACE_POINTS
+#include "lima_trace.h"
diff --git a/drivers/gpu/drm/lima/lima_trace.h b/drivers/gpu/drm/lima/lima_trace.h
new file mode 100644
index 000000000..3a430e93d
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_trace.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2020 Qiang Yu <yuq825@gmail.com> */
+
+#if !defined(_LIMA_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _LIMA_TRACE_H_
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lima
+#define TRACE_INCLUDE_FILE lima_trace
+
+DECLARE_EVENT_CLASS(lima_task,
+	TP_PROTO(struct lima_sched_task *task),
+	TP_ARGS(task),
+	TP_STRUCT__entry(
+		__field(uint64_t, task_id)
+		__field(unsigned int, context)
+		__field(unsigned int, seqno)
+		__string(pipe, task->base.sched->name)
+		),
+
+	TP_fast_assign(
+		__entry->task_id = task->base.id;
+		__entry->context = task->base.s_fence->finished.context;
+		__entry->seqno = task->base.s_fence->finished.seqno;
+		__assign_str(pipe, task->base.sched->name)
+		),
+
+	TP_printk("task=%llu, context=%u seqno=%u pipe=%s",
+		  __entry->task_id, __entry->context, __entry->seqno,
+		  __get_str(pipe))
+);
+
+DEFINE_EVENT(lima_task, lima_task_submit,
+	     TP_PROTO(struct lima_sched_task *task),
+	     TP_ARGS(task)
+);
+
+DEFINE_EVENT(lima_task, lima_task_run,
+	     TP_PROTO(struct lima_sched_task *task),
+	     TP_ARGS(task)
+);
+
+#endif
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/lima
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/lima/lima_vm.c b/drivers/gpu/drm/lima/lima_vm.c
new file mode 100644
index 000000000..2b2739adc
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_vm.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+
+#include "lima_device.h"
+#include "lima_vm.h"
+#include "lima_gem.h"
+#include "lima_regs.h"
+
+struct lima_bo_va {
+	struct list_head list;
+	unsigned int ref_count;
+
+	struct drm_mm_node node;
+
+	struct lima_vm *vm;
+};
+
+#define LIMA_VM_PD_SHIFT 22
+#define LIMA_VM_PT_SHIFT 12
+#define LIMA_VM_PB_SHIFT (LIMA_VM_PD_SHIFT + LIMA_VM_NUM_PT_PER_BT_SHIFT)
+#define LIMA_VM_BT_SHIFT LIMA_VM_PT_SHIFT
+
+#define LIMA_VM_PT_MASK ((1 << LIMA_VM_PD_SHIFT) - 1)
+#define LIMA_VM_BT_MASK ((1 << LIMA_VM_PB_SHIFT) - 1)
+
+#define LIMA_PDE(va) (va >> LIMA_VM_PD_SHIFT)
+#define LIMA_PTE(va) ((va & LIMA_VM_PT_MASK) >> LIMA_VM_PT_SHIFT)
+#define LIMA_PBE(va) (va >> LIMA_VM_PB_SHIFT)
+#define LIMA_BTE(va) ((va & LIMA_VM_BT_MASK) >> LIMA_VM_BT_SHIFT)
+
+
+static void lima_vm_unmap_range(struct lima_vm *vm, u32 start, u32 end)
+{
+	u32 addr;
+
+	for (addr = start; addr <= end; addr += LIMA_PAGE_SIZE) {
+		u32 pbe = LIMA_PBE(addr);
+		u32 bte = LIMA_BTE(addr);
+
+		vm->bts[pbe].cpu[bte] = 0;
+	}
+}
+
+static int lima_vm_map_page(struct lima_vm *vm, dma_addr_t pa, u32 va)
+{
+	u32 pbe = LIMA_PBE(va);
+	u32 bte = LIMA_BTE(va);
+
+	if (!vm->bts[pbe].cpu) {
+		dma_addr_t pts;
+		u32 *pd;
+		int j;
+
+		vm->bts[pbe].cpu = dma_alloc_wc(
+			vm->dev->dev, LIMA_PAGE_SIZE << LIMA_VM_NUM_PT_PER_BT_SHIFT,
+			&vm->bts[pbe].dma, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+		if (!vm->bts[pbe].cpu)
+			return -ENOMEM;
+
+		pts = vm->bts[pbe].dma;
+		pd = vm->pd.cpu + (pbe << LIMA_VM_NUM_PT_PER_BT_SHIFT);
+		for (j = 0; j < LIMA_VM_NUM_PT_PER_BT; j++) {
+			pd[j] = pts | LIMA_VM_FLAG_PRESENT;
+			pts += LIMA_PAGE_SIZE;
+		}
+	}
+
+	vm->bts[pbe].cpu[bte] = pa | LIMA_VM_FLAGS_CACHE;
+
+	return 0;
+}
+
+static struct lima_bo_va *
+lima_vm_bo_find(struct lima_vm *vm, struct lima_bo *bo)
+{
+	struct lima_bo_va *bo_va, *ret = NULL;
+
+	list_for_each_entry(bo_va, &bo->va, list) {
+		if (bo_va->vm == vm) {
+			ret = bo_va;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create)
+{
+	struct lima_bo_va *bo_va;
+	struct sg_dma_page_iter sg_iter;
+	int offset = 0, err;
+
+	mutex_lock(&bo->lock);
+
+	bo_va = lima_vm_bo_find(vm, bo);
+	if (bo_va) {
+		bo_va->ref_count++;
+		mutex_unlock(&bo->lock);
+		return 0;
+	}
+
+	/* should not create new bo_va if not asked by caller */
+	if (!create) {
+		mutex_unlock(&bo->lock);
+		return -ENOENT;
+	}
+
+	bo_va = kzalloc(sizeof(*bo_va), GFP_KERNEL);
+	if (!bo_va) {
+		err = -ENOMEM;
+		goto err_out0;
+	}
+
+	bo_va->vm = vm;
+	bo_va->ref_count = 1;
+
+	mutex_lock(&vm->lock);
+
+	err = drm_mm_insert_node(&vm->mm, &bo_va->node, lima_bo_size(bo));
+	if (err)
+		goto err_out1;
+
+	for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, 0) {
+		err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
+				       bo_va->node.start + offset);
+		if (err)
+			goto err_out2;
+
+		offset += PAGE_SIZE;
+	}
+
+	mutex_unlock(&vm->lock);
+
+	list_add_tail(&bo_va->list, &bo->va);
+
+	mutex_unlock(&bo->lock);
+	return 0;
+
+err_out2:
+	if (offset)
+		lima_vm_unmap_range(vm, bo_va->node.start, bo_va->node.start + offset - 1);
+	drm_mm_remove_node(&bo_va->node);
+err_out1:
+	mutex_unlock(&vm->lock);
+	kfree(bo_va);
+err_out0:
+	mutex_unlock(&bo->lock);
+	return err;
+}
+
+void lima_vm_bo_del(struct lima_vm *vm, struct lima_bo *bo)
+{
+	struct lima_bo_va *bo_va;
+	u32 size;
+
+	mutex_lock(&bo->lock);
+
+	bo_va = lima_vm_bo_find(vm, bo);
+	if (--bo_va->ref_count > 0) {
+		mutex_unlock(&bo->lock);
+		return;
+	}
+
+	mutex_lock(&vm->lock);
+
+	size = bo->heap_size ? bo->heap_size : bo_va->node.size;
+	lima_vm_unmap_range(vm, bo_va->node.start,
+			    bo_va->node.start + size - 1);
+
+	drm_mm_remove_node(&bo_va->node);
+
+	mutex_unlock(&vm->lock);
+
+	list_del(&bo_va->list);
+
+	mutex_unlock(&bo->lock);
+
+	kfree(bo_va);
+}
+
+u32 lima_vm_get_va(struct lima_vm *vm, struct lima_bo *bo)
+{
+	struct lima_bo_va *bo_va;
+	u32 ret;
+
+	mutex_lock(&bo->lock);
+
+	bo_va = lima_vm_bo_find(vm, bo);
+	ret = bo_va->node.start;
+
+	mutex_unlock(&bo->lock);
+
+	return ret;
+}
+
+struct lima_vm *lima_vm_create(struct lima_device *dev)
+{
+	struct lima_vm *vm;
+
+	vm = kzalloc(sizeof(*vm), GFP_KERNEL);
+	if (!vm)
+		return NULL;
+
+	vm->dev = dev;
+	mutex_init(&vm->lock);
+	kref_init(&vm->refcount);
+
+	vm->pd.cpu = dma_alloc_wc(dev->dev, LIMA_PAGE_SIZE, &vm->pd.dma,
+				  GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
+	if (!vm->pd.cpu)
+		goto err_out0;
+
+	if (dev->dlbu_cpu) {
+		int err = lima_vm_map_page(
+			vm, dev->dlbu_dma, LIMA_VA_RESERVE_DLBU);
+		if (err)
+			goto err_out1;
+	}
+
+	drm_mm_init(&vm->mm, dev->va_start, dev->va_end - dev->va_start);
+
+	return vm;
+
+err_out1:
+	dma_free_wc(dev->dev, LIMA_PAGE_SIZE, vm->pd.cpu, vm->pd.dma);
+err_out0:
+	kfree(vm);
+	return NULL;
+}
+
+void lima_vm_release(struct kref *kref)
+{
+	struct lima_vm *vm = container_of(kref, struct lima_vm, refcount);
+	int i;
+
+	drm_mm_takedown(&vm->mm);
+
+	for (i = 0; i < LIMA_VM_NUM_BT; i++) {
+		if (vm->bts[i].cpu)
+			dma_free_wc(vm->dev->dev, LIMA_PAGE_SIZE << LIMA_VM_NUM_PT_PER_BT_SHIFT,
+				    vm->bts[i].cpu, vm->bts[i].dma);
+	}
+
+	if (vm->pd.cpu)
+		dma_free_wc(vm->dev->dev, LIMA_PAGE_SIZE, vm->pd.cpu, vm->pd.dma);
+
+	kfree(vm);
+}
+
+void lima_vm_print(struct lima_vm *vm)
+{
+	int i, j, k;
+	u32 *pd, *pt;
+
+	if (!vm->pd.cpu)
+		return;
+
+	pd = vm->pd.cpu;
+	for (i = 0; i < LIMA_VM_NUM_BT; i++) {
+		if (!vm->bts[i].cpu)
+			continue;
+
+		pt = vm->bts[i].cpu;
+		for (j = 0; j < LIMA_VM_NUM_PT_PER_BT; j++) {
+			int idx = (i << LIMA_VM_NUM_PT_PER_BT_SHIFT) + j;
+
+			printk(KERN_INFO "lima vm pd %03x:%08x\n", idx, pd[idx]);
+
+			for (k = 0; k < LIMA_PAGE_ENT_NUM; k++) {
+				u32 pte = *pt++;
+
+				if (pte)
+					printk(KERN_INFO "  pt %03x:%08x\n", k, pte);
+			}
+		}
+	}
+}
+
+int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff)
+{
+	struct lima_bo_va *bo_va;
+	struct sg_dma_page_iter sg_iter;
+	int offset = 0, err;
+	u32 base;
+
+	mutex_lock(&bo->lock);
+
+	bo_va = lima_vm_bo_find(vm, bo);
+	if (!bo_va) {
+		err = -ENOENT;
+		goto err_out0;
+	}
+
+	mutex_lock(&vm->lock);
+
+	base = bo_va->node.start + (pageoff << PAGE_SHIFT);
+	for_each_sgtable_dma_page(bo->base.sgt, &sg_iter, pageoff) {
+		err = lima_vm_map_page(vm, sg_page_iter_dma_address(&sg_iter),
+				       base + offset);
+		if (err)
+			goto err_out1;
+
+		offset += PAGE_SIZE;
+	}
+
+	mutex_unlock(&vm->lock);
+
+	mutex_unlock(&bo->lock);
+	return 0;
+
+err_out1:
+	if (offset)
+		lima_vm_unmap_range(vm, base, base + offset - 1);
+	mutex_unlock(&vm->lock);
+err_out0:
+	mutex_unlock(&bo->lock);
+	return err;
+}
diff --git a/drivers/gpu/drm/lima/lima_vm.h b/drivers/gpu/drm/lima/lima_vm.h
new file mode 100644
index 000000000..3a7c74822
--- /dev/null
+++ b/drivers/gpu/drm/lima/lima_vm.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_VM_H__
+#define __LIMA_VM_H__
+
+#include <drm/drm_mm.h>
+#include <linux/kref.h>
+
+#define LIMA_PAGE_SIZE    4096
+#define LIMA_PAGE_MASK    (LIMA_PAGE_SIZE - 1)
+#define LIMA_PAGE_ENT_NUM (LIMA_PAGE_SIZE / sizeof(u32))
+
+#define LIMA_VM_NUM_PT_PER_BT_SHIFT 3
+#define LIMA_VM_NUM_PT_PER_BT (1 << LIMA_VM_NUM_PT_PER_BT_SHIFT)
+#define LIMA_VM_NUM_BT (LIMA_PAGE_ENT_NUM >> LIMA_VM_NUM_PT_PER_BT_SHIFT)
+
+#define LIMA_VA_RESERVE_START  0x0FFF00000ULL
+#define LIMA_VA_RESERVE_DLBU   LIMA_VA_RESERVE_START
+#define LIMA_VA_RESERVE_END    0x100000000ULL
+
+struct lima_device;
+
+struct lima_vm_page {
+	u32 *cpu;
+	dma_addr_t dma;
+};
+
+struct lima_vm {
+	struct mutex lock;
+	struct kref refcount;
+
+	struct drm_mm mm;
+
+	struct lima_device *dev;
+
+	struct lima_vm_page pd;
+	struct lima_vm_page bts[LIMA_VM_NUM_BT];
+};
+
+int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create);
+void lima_vm_bo_del(struct lima_vm *vm, struct lima_bo *bo);
+
+u32 lima_vm_get_va(struct lima_vm *vm, struct lima_bo *bo);
+
+struct lima_vm *lima_vm_create(struct lima_device *dev);
+void lima_vm_release(struct kref *kref);
+
+static inline struct lima_vm *lima_vm_get(struct lima_vm *vm)
+{
+	kref_get(&vm->refcount);
+	return vm;
+}
+
+static inline void lima_vm_put(struct lima_vm *vm)
+{
+	if (vm)
+		kref_put(&vm->refcount, lima_vm_release);
+}
+
+void lima_vm_print(struct lima_vm *vm);
+int lima_vm_map_bo(struct lima_vm *vm, struct lima_bo *bo, int pageoff);
+
+#endif