123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574// SPDX-License-Identifier: GPL-2.0
//
// Copyright (c) 2018 MediaTek Inc.

#include <linux/bitops.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/iopoll.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/mailbox_controller.h>
#include <linux/mailbox/mtk-cmdq-mailbox.h>
#include <linux/of_device.h>

#define CMDQ_OP_CODE_MASK		(0xff << CMDQ_OP_CODE_SHIFT)
#define CMDQ_IRQ_MASK			0xffff
#define CMDQ_NUM_CMD(t)			(t->cmd_buf_size / CMDQ_INST_SIZE)

#define CMDQ_CURR_IRQ_STATUS		0x10
#define CMDQ_THR_SLOT_CYCLES		0x30
#define CMDQ_THR_BASE			0x100
#define CMDQ_THR_SIZE			0x80
#define CMDQ_THR_WARM_RESET		0x00
#define CMDQ_THR_ENABLE_TASK		0x04
#define CMDQ_THR_SUSPEND_TASK		0x08
#define CMDQ_THR_CURR_STATUS		0x0c
#define CMDQ_THR_IRQ_STATUS		0x10
#define CMDQ_THR_IRQ_ENABLE		0x14
#define CMDQ_THR_CURR_ADDR		0x20
#define CMDQ_THR_END_ADDR		0x24
#define CMDQ_THR_WAIT_TOKEN		0x30
#define CMDQ_THR_PRIORITY		0x40

#define CMDQ_THR_ACTIVE_SLOT_CYCLES	0x3200
#define CMDQ_THR_ENABLED		0x1
#define CMDQ_THR_DISABLED		0x0
#define CMDQ_THR_SUSPEND		0x1
#define CMDQ_THR_RESUME			0x0
#define CMDQ_THR_STATUS_SUSPENDED	BIT(1)
#define CMDQ_THR_DO_WARM_RESET		BIT(0)
#define CMDQ_THR_IRQ_DONE		0x1
#define CMDQ_THR_IRQ_ERROR		0x12
#define CMDQ_THR_IRQ_EN			(CMDQ_THR_IRQ_ERROR | CMDQ_THR_IRQ_DONE)
#define CMDQ_THR_IS_WAITING		BIT(31)

#define CMDQ_JUMP_BY_OFFSET		0x10000000
#define CMDQ_JUMP_BY_PA			0x10000001

struct cmdq_thread {
	struct mbox_chan	*chan;
	void __iomem		*base;
	struct list_head	task_busy_list;
	u32			priority;
	bool			atomic_exec;
};

struct cmdq_task {
	struct cmdq		*cmdq;
	struct list_head	list_entry;
	dma_addr_t		pa_base;
	struct cmdq_thread	*thread;
	struct cmdq_pkt		*pkt; /* the packet sent from mailbox client */
};

struct cmdq {
	struct mbox_controller	mbox;
	void __iomem		*base;
	u32			irq;
	u32			thread_nr;
	struct cmdq_thread	*thread;
	struct clk		*clock;
	bool			suspended;
};

static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
{
	u32 status;

	writel(CMDQ_THR_SUSPEND, thread->base + CMDQ_THR_SUSPEND_TASK);

	/* If already disabled, treat as suspended successful. */
	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
		return 0;

	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_STATUS,
			status, status & CMDQ_THR_STATUS_SUSPENDED, 0, 10)) {
		dev_err(cmdq->mbox.dev, "suspend GCE thread 0x%x failed\n",
			(u32)(thread->base - cmdq->base));
		return -EFAULT;
	}

	return 0;
}

static void cmdq_thread_resume(struct cmdq_thread *thread)
{
	writel(CMDQ_THR_RESUME, thread->base + CMDQ_THR_SUSPEND_TASK);
}

static void cmdq_init(struct cmdq *cmdq)
{
	WARN_ON(clk_enable(cmdq->clock) < 0);
	writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES);
	clk_disable(cmdq->clock);
}

static int cmdq_thread_reset(struct cmdq *cmdq, struct cmdq_thread *thread)
{
	u32 warm_reset;

	writel(CMDQ_THR_DO_WARM_RESET, thread->base + CMDQ_THR_WARM_RESET);
	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_WARM_RESET,
			warm_reset, !(warm_reset & CMDQ_THR_DO_WARM_RESET),
			0, 10)) {
		dev_err(cmdq->mbox.dev, "reset GCE thread 0x%x failed\n",
			(u32)(thread->base - cmdq->base));
		return -EFAULT;
	}

	return 0;
}

static void cmdq_thread_disable(struct cmdq *cmdq, struct cmdq_thread *thread)
{
	cmdq_thread_reset(cmdq, thread);
	writel(CMDQ_THR_DISABLED, thread->base + CMDQ_THR_ENABLE_TASK);
}

/* notify GCE to re-fetch commands by setting GCE thread PC */
static void cmdq_thread_invalidate_fetched_data(struct cmdq_thread *thread)
{
	writel(readl(thread->base + CMDQ_THR_CURR_ADDR),
	       thread->base + CMDQ_THR_CURR_ADDR);
}

static void cmdq_task_insert_into_thread(struct cmdq_task *task)
{
	struct device *dev = task->cmdq->mbox.dev;
	struct cmdq_thread *thread = task->thread;
	struct cmdq_task *prev_task = list_last_entry(
			&thread->task_busy_list, typeof(*task), list_entry);
	u64 *prev_task_base = prev_task->pkt->va_base;

	/* let previous task jump to this task */
	dma_sync_single_for_cpu(dev, prev_task->pa_base,
				prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);
	prev_task_base[CMDQ_NUM_CMD(prev_task->pkt) - 1] =
		(u64)CMDQ_JUMP_BY_PA << 32 | task->pa_base;
	dma_sync_single_for_device(dev, prev_task->pa_base,
				   prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);

	cmdq_thread_invalidate_fetched_data(thread);
}

static bool cmdq_command_is_wfe(u64 cmd)
{
	u64 wfe_option = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
	u64 wfe_op = (u64)(CMDQ_CODE_WFE << CMDQ_OP_CODE_SHIFT) << 32;
	u64 wfe_mask = (u64)CMDQ_OP_CODE_MASK << 32 | 0xffffffff;

	return ((cmd & wfe_mask) == (wfe_op | wfe_option));
}

/* we assume tasks in the same display GCE thread are waiting the same event. */
static void cmdq_task_remove_wfe(struct cmdq_task *task)
{
	struct device *dev = task->cmdq->mbox.dev;
	u64 *base = task->pkt->va_base;
	int i;

	dma_sync_single_for_cpu(dev, task->pa_base, task->pkt->cmd_buf_size,
				DMA_TO_DEVICE);
	for (i = 0; i < CMDQ_NUM_CMD(task->pkt); i++)
		if (cmdq_command_is_wfe(base[i]))
			base[i] = (u64)CMDQ_JUMP_BY_OFFSET << 32 |
				  CMDQ_JUMP_PASS;
	dma_sync_single_for_device(dev, task->pa_base, task->pkt->cmd_buf_size,
				   DMA_TO_DEVICE);
}

static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread)
{
	return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING;
}

static void cmdq_thread_wait_end(struct cmdq_thread *thread,
				 unsigned long end_pa)
{
	struct device *dev = thread->chan->mbox->dev;
	unsigned long curr_pa;

	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_ADDR,
			curr_pa, curr_pa == end_pa, 1, 20))
		dev_err(dev, "GCE thread cannot run to end.\n");
}

static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta)
{
	struct cmdq_task_cb *cb = &task->pkt->async_cb;
	struct cmdq_cb_data data;

	WARN_ON(cb->cb == (cmdq_async_flush_cb)NULL);
	data.sta = sta;
	data.data = cb->data;
	cb->cb(data);

	list_del(&task->list_entry);
}

static void cmdq_task_handle_error(struct cmdq_task *task)
{
	struct cmdq_thread *thread = task->thread;
	struct cmdq_task *next_task;

	dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task);
	WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0);
	next_task = list_first_entry_or_null(&thread->task_busy_list,
			struct cmdq_task, list_entry);
	if (next_task)
		writel(next_task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
	cmdq_thread_resume(thread);
}

static void cmdq_thread_irq_handler(struct cmdq *cmdq,
				    struct cmdq_thread *thread)
{
	struct cmdq_task *task, *tmp, *curr_task = NULL;
	u32 curr_pa, irq_flag, task_end_pa;
	bool err;

	irq_flag = readl(thread->base + CMDQ_THR_IRQ_STATUS);
	writel(~irq_flag, thread->base + CMDQ_THR_IRQ_STATUS);

	/*
	 * When ISR call this function, another CPU core could run
	 * "release task" right before we acquire the spin lock, and thus
	 * reset / disable this GCE thread, so we need to check the enable
	 * bit of this GCE thread.
	 */
	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
		return;

	if (irq_flag & CMDQ_THR_IRQ_ERROR)
		err = true;
	else if (irq_flag & CMDQ_THR_IRQ_DONE)
		err = false;
	else
		return;

	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);

	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
				 list_entry) {
		task_end_pa = task->pa_base + task->pkt->cmd_buf_size;
		if (curr_pa >= task->pa_base && curr_pa < task_end_pa)
			curr_task = task;

		if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) {
			cmdq_task_exec_done(task, CMDQ_CB_NORMAL);
			kfree(task);
		} else if (err) {
			cmdq_task_exec_done(task, CMDQ_CB_ERROR);
			cmdq_task_handle_error(curr_task);
			kfree(task);
		}

		if (curr_task)
			break;
	}

	if (list_empty(&thread->task_busy_list)) {
		cmdq_thread_disable(cmdq, thread);
		clk_disable(cmdq->clock);
	}
}

static irqreturn_t cmdq_irq_handler(int irq, void *dev)
{
	struct cmdq *cmdq = dev;
	unsigned long irq_status, flags = 0L;
	int bit;

	irq_status = readl(cmdq->base + CMDQ_CURR_IRQ_STATUS) & CMDQ_IRQ_MASK;
	if (!(irq_status ^ CMDQ_IRQ_MASK))
		return IRQ_NONE;

	for_each_clear_bit(bit, &irq_status, fls(CMDQ_IRQ_MASK)) {
		struct cmdq_thread *thread = &cmdq->thread[bit];

		spin_lock_irqsave(&thread->chan->lock, flags);
		cmdq_thread_irq_handler(cmdq, thread);
		spin_unlock_irqrestore(&thread->chan->lock, flags);
	}

	return IRQ_HANDLED;
}

static int cmdq_suspend(struct device *dev)
{
	struct cmdq *cmdq = dev_get_drvdata(dev);
	struct cmdq_thread *thread;
	int i;
	bool task_running = false;

	cmdq->suspended = true;

	for (i = 0; i < cmdq->thread_nr; i++) {
		thread = &cmdq->thread[i];
		if (!list_empty(&thread->task_busy_list)) {
			task_running = true;
			break;
		}
	}

	if (task_running)
		dev_warn(dev, "exist running task(s) in suspend\n");

	clk_unprepare(cmdq->clock);

	return 0;
}

static int cmdq_resume(struct device *dev)
{
	struct cmdq *cmdq = dev_get_drvdata(dev);

	WARN_ON(clk_prepare(cmdq->clock) < 0);
	cmdq->suspended = false;
	return 0;
}

static int cmdq_remove(struct platform_device *pdev)
{
	struct cmdq *cmdq = platform_get_drvdata(pdev);

	mbox_controller_unregister(&cmdq->mbox);
	clk_unprepare(cmdq->clock);

	if (cmdq->mbox.chans)
		devm_kfree(&pdev->dev, cmdq->mbox.chans);

	if (cmdq->thread)
		devm_kfree(&pdev->dev, cmdq->thread);

	devm_kfree(&pdev->dev, cmdq);

	return 0;
}

static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
{
	struct cmdq_pkt *pkt = (struct cmdq_pkt *)data;
	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
	struct cmdq_task *task;
	unsigned long curr_pa, end_pa;

	/* Client should not flush new tasks if suspended. */
	WARN_ON(cmdq->suspended);

	task = kzalloc(sizeof(*task), GFP_ATOMIC);
	if (!task)
		return -ENOMEM;

	task->cmdq = cmdq;
	INIT_LIST_HEAD(&task->list_entry);
	task->pa_base = pkt->pa_base;
	task->thread = thread;
	task->pkt = pkt;

	if (list_empty(&thread->task_busy_list)) {
		WARN_ON(clk_enable(cmdq->clock) < 0);
		WARN_ON(cmdq_thread_reset(cmdq, thread) < 0);

		writel(task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
		writel(task->pa_base + pkt->cmd_buf_size,
		       thread->base + CMDQ_THR_END_ADDR);
		writel(thread->priority, thread->base + CMDQ_THR_PRIORITY);
		writel(CMDQ_THR_IRQ_EN, thread->base + CMDQ_THR_IRQ_ENABLE);
		writel(CMDQ_THR_ENABLED, thread->base + CMDQ_THR_ENABLE_TASK);
	} else {
		WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
		end_pa = readl(thread->base + CMDQ_THR_END_ADDR);

		/*
		 * Atomic execution should remove the following wfe, i.e. only
		 * wait event at first task, and prevent to pause when running.
		 */
		if (thread->atomic_exec) {
			/* GCE is executing if command is not WFE */
			if (!cmdq_thread_is_in_wfe(thread)) {
				cmdq_thread_resume(thread);
				cmdq_thread_wait_end(thread, end_pa);
				WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
				/* set to this task directly */
				writel(task->pa_base,
				       thread->base + CMDQ_THR_CURR_ADDR);
			} else {
				cmdq_task_insert_into_thread(task);
				cmdq_task_remove_wfe(task);
				smp_mb(); /* modify jump before enable thread */
			}
		} else {
			/* check boundary */
			if (curr_pa == end_pa - CMDQ_INST_SIZE ||
			    curr_pa == end_pa) {
				/* set to this task directly */
				writel(task->pa_base,
				       thread->base + CMDQ_THR_CURR_ADDR);
			} else {
				cmdq_task_insert_into_thread(task);
				smp_mb(); /* modify jump before enable thread */
			}
		}
		writel(task->pa_base + pkt->cmd_buf_size,
		       thread->base + CMDQ_THR_END_ADDR);
		cmdq_thread_resume(thread);
	}
	list_move_tail(&task->list_entry, &thread->task_busy_list);

	return 0;
}

static int cmdq_mbox_startup(struct mbox_chan *chan)
{
	return 0;
}

static void cmdq_mbox_shutdown(struct mbox_chan *chan)
{
}

static const struct mbox_chan_ops cmdq_mbox_chan_ops = {
	.send_data = cmdq_mbox_send_data,
	.startup = cmdq_mbox_startup,
	.shutdown = cmdq_mbox_shutdown,
};

static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
		const struct of_phandle_args *sp)
{
	int ind = sp->args[0];
	struct cmdq_thread *thread;

	if (ind >= mbox->num_chans)
		return ERR_PTR(-EINVAL);

	thread = (struct cmdq_thread *)mbox->chans[ind].con_priv;
	thread->priority = sp->args[1];
	thread->atomic_exec = (sp->args[2] != 0);
	thread->chan = &mbox->chans[ind];

	return &mbox->chans[ind];
}

static int cmdq_probe(struct platform_device *pdev)
{
	struct device *dev = &pdev->dev;
	struct resource *res;
	struct cmdq *cmdq;
	int err, i;

	cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL);
	if (!cmdq)
		return -ENOMEM;

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	cmdq->base = devm_ioremap_resource(dev, res);
	if (IS_ERR(cmdq->base)) {
		dev_err(dev, "failed to ioremap gce\n");
		return PTR_ERR(cmdq->base);
	}

	cmdq->irq = platform_get_irq(pdev, 0);
	if (!cmdq->irq) {
		dev_err(dev, "failed to get irq\n");
		return -EINVAL;
	}
	err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED,
			       "mtk_cmdq", cmdq);
	if (err < 0) {
		dev_err(dev, "failed to register ISR (%d)\n", err);
		return err;
	}

	dev_dbg(dev, "cmdq device: addr:0x%p, va:0x%p, irq:%d\n",
		dev, cmdq->base, cmdq->irq);

	cmdq->clock = devm_clk_get(dev, "gce");
	if (IS_ERR(cmdq->clock)) {
		dev_err(dev, "failed to get gce clk\n");
		return PTR_ERR(cmdq->clock);
	}

	cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev);
	cmdq->mbox.dev = dev;
	cmdq->mbox.chans = devm_kcalloc(dev, cmdq->thread_nr,
					sizeof(*cmdq->mbox.chans), GFP_KERNEL);
	if (!cmdq->mbox.chans)
		return -ENOMEM;

	cmdq->mbox.num_chans = cmdq->thread_nr;
	cmdq->mbox.ops = &cmdq_mbox_chan_ops;
	cmdq->mbox.of_xlate = cmdq_xlate;

	/* make use of TXDONE_BY_ACK */
	cmdq->mbox.txdone_irq = false;
	cmdq->mbox.txdone_poll = false;

	cmdq->thread = devm_kcalloc(dev, cmdq->thread_nr,
					sizeof(*cmdq->thread), GFP_KERNEL);
	if (!cmdq->thread)
		return -ENOMEM;

	for (i = 0; i < cmdq->thread_nr; i++) {
		cmdq->thread[i].base = cmdq->base + CMDQ_THR_BASE +
				CMDQ_THR_SIZE * i;
		INIT_LIST_HEAD(&cmdq->thread[i].task_busy_list);
		cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i];
	}

	err = mbox_controller_register(&cmdq->mbox);
	if (err < 0) {
		dev_err(dev, "failed to register mailbox: %d\n", err);
		return err;
	}

	platform_set_drvdata(pdev, cmdq);
	WARN_ON(clk_prepare(cmdq->clock) < 0);

	cmdq_init(cmdq);

	return 0;
}

static const struct dev_pm_ops cmdq_pm_ops = {
	.suspend = cmdq_suspend,
	.resume = cmdq_resume,
};

static const struct of_device_id cmdq_of_ids[] = {
	{.compatible = "mediatek,mt8173-gce", .data = (void *)16},
	{}
};

static struct platform_driver cmdq_drv = {
	.probe = cmdq_probe,
	.remove = cmdq_remove,
	.driver = {
		.name = "mtk_cmdq",
		.pm = &cmdq_pm_ops,
		.of_match_table = cmdq_of_ids,
	}
};

static int __init cmdq_drv_init(void)
{
	return platform_driver_register(&cmdq_drv);
}

static void __exit cmdq_drv_exit(void)
{
	platform_driver_unregister(&cmdq_drv);
}

subsys_initcall(cmdq_drv_init);
module_exit(cmdq_drv_exit);

MODULE_LICENSE("GPL v2"