1 files changed, 232 insertions, 111 deletions

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 9a6ce9f5a7db..9465f9081515 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -19,6 +19,7 @@
 
 #define CMDQ_OP_CODE_MASK		(0xff << CMDQ_OP_CODE_SHIFT)
 #define CMDQ_NUM_CMD(t)			(t->cmd_buf_size / CMDQ_INST_SIZE)
+#define CMDQ_GCE_NUM_MAX		(2)
 
 #define CMDQ_CURR_IRQ_STATUS		0x10
 #define CMDQ_SYNC_TOKEN_UPDATE		0x68
@@ -36,6 +37,8 @@
 #define CMDQ_THR_WAIT_TOKEN		0x30
 #define CMDQ_THR_PRIORITY		0x40
 
+#define GCE_GCTL_VALUE			0x48
+
 #define CMDQ_THR_ACTIVE_SLOT_CYCLES	0x3200
 #define CMDQ_THR_ENABLED		0x1
 #define CMDQ_THR_DISABLED		0x0
@@ -56,7 +59,6 @@ struct cmdq_thread {
 	void __iomem		*base;
 	struct list_head	task_busy_list;
 	u32			priority;
-	bool			atomic_exec;
 };
 
 struct cmdq_task {
@@ -70,14 +72,32 @@ struct cmdq_task {
 struct cmdq {
 	struct mbox_controller	mbox;
 	void __iomem		*base;
-	u32			irq;
+	int			irq;
 	u32			thread_nr;
 	u32			irq_mask;
 	struct cmdq_thread	*thread;
-	struct clk		*clock;
+	struct clk_bulk_data	clocks[CMDQ_GCE_NUM_MAX];
 	bool			suspended;
+	u8			shift_pa;
+	bool			control_by_sw;
+	u32			gce_num;
+};
+
+struct gce_plat {
+	u32 thread_nr;
+	u8 shift;
+	bool control_by_sw;
+	u32 gce_num;
 };
 
+u8 cmdq_get_shift_pa(struct mbox_chan *chan)
+{
+	struct cmdq *cmdq = container_of(chan->mbox, struct cmdq, mbox);
+
+	return cmdq->shift_pa;
+}
+EXPORT_SYMBOL(cmdq_get_shift_pa);
+
 static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
 {
 	u32 status;
@@ -107,11 +127,13 @@ static void cmdq_init(struct cmdq *cmdq)
 {
 	int i;
 
-	WARN_ON(clk_enable(cmdq->clock) < 0);
+	WARN_ON(clk_bulk_enable(cmdq->gce_num, cmdq->clocks));
+	if (cmdq->control_by_sw)
+		writel(0x7, cmdq->base + GCE_GCTL_VALUE);
 	writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES);
 	for (i = 0; i <= CMDQ_MAX_EVENT; i++)
 		writel(i, cmdq->base + CMDQ_SYNC_TOKEN_UPDATE);
-	clk_disable(cmdq->clock);
+	clk_bulk_disable(cmdq->gce_num, cmdq->clocks);
 }
 
 static int cmdq_thread_reset(struct cmdq *cmdq, struct cmdq_thread *thread)
@@ -155,64 +177,26 @@ static void cmdq_task_insert_into_thread(struct cmdq_task *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;
+		(u64)CMDQ_JUMP_BY_PA << 32 |
+		(task->pa_base >> task->cmdq->shift_pa);
 	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)
+static void cmdq_task_exec_done(struct cmdq_task *task, int 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);
+	data.pkt = task->pkt;
+	mbox_chan_received_data(task->thread->chan, &data);
 
 	list_del(&task->list_entry);
 }
@@ -221,13 +205,15 @@ static void cmdq_task_handle_error(struct cmdq_task *task)
 {
 	struct cmdq_thread *thread = task->thread;
 	struct cmdq_task *next_task;
+	struct cmdq *cmdq = task->cmdq;
 
-	dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task);
-	WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0);
+	dev_err(cmdq->mbox.dev, "task 0x%p error\n", task);
+	WARN_ON(cmdq_thread_suspend(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);
+		writel(next_task->pa_base >> cmdq->shift_pa,
+		       thread->base + CMDQ_THR_CURR_ADDR);
 	cmdq_thread_resume(thread);
 }
 
@@ -257,7 +243,7 @@ static void cmdq_thread_irq_handler(struct cmdq *cmdq,
 	else
 		return;
 
-	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR) << cmdq->shift_pa;
 
 	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
 				 list_entry) {
@@ -266,10 +252,10 @@ static void cmdq_thread_irq_handler(struct cmdq *cmdq,
 			curr_task = task;
 
 		if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) {
-			cmdq_task_exec_done(task, CMDQ_CB_NORMAL);
+			cmdq_task_exec_done(task, 0);
 			kfree(task);
 		} else if (err) {
-			cmdq_task_exec_done(task, CMDQ_CB_ERROR);
+			cmdq_task_exec_done(task, -ENOEXEC);
 			cmdq_task_handle_error(curr_task);
 			kfree(task);
 		}
@@ -280,7 +266,7 @@ static void cmdq_thread_irq_handler(struct cmdq *cmdq,
 
 	if (list_empty(&thread->task_busy_list)) {
 		cmdq_thread_disable(cmdq, thread);
-		clk_disable(cmdq->clock);
+		clk_bulk_disable(cmdq->gce_num, cmdq->clocks);
 	}
 }
 
@@ -325,7 +311,7 @@ static int cmdq_suspend(struct device *dev)
 	if (task_running)
 		dev_warn(dev, "exist running task(s) in suspend\n");
 
-	clk_unprepare(cmdq->clock);
+	clk_bulk_unprepare(cmdq->gce_num, cmdq->clocks);
 
 	return 0;
 }
@@ -334,7 +320,7 @@ static int cmdq_resume(struct device *dev)
 {
 	struct cmdq *cmdq = dev_get_drvdata(dev);
 
-	WARN_ON(clk_prepare(cmdq->clock) < 0);
+	WARN_ON(clk_bulk_prepare(cmdq->gce_num, cmdq->clocks));
 	cmdq->suspended = false;
 	return 0;
 }
@@ -343,8 +329,7 @@ static int cmdq_remove(struct platform_device *pdev)
 {
 	struct cmdq *cmdq = platform_get_drvdata(pdev);
 
-	clk_unprepare(cmdq->clock);
-
+	clk_bulk_unprepare(cmdq->gce_num, cmdq->clocks);
 	return 0;
 }
 
@@ -370,51 +355,41 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
 	task->pkt = pkt;
 
 	if (list_empty(&thread->task_busy_list)) {
-		WARN_ON(clk_enable(cmdq->clock) < 0);
+		WARN_ON(clk_bulk_enable(cmdq->gce_num, cmdq->clocks));
+
+		/*
+		 * The thread reset will clear thread related register to 0,
+		 * including pc, end, priority, irq, suspend and enable. Thus
+		 * set CMDQ_THR_ENABLED to CMDQ_THR_ENABLE_TASK will enable
+		 * thread and make it running.
+		 */
 		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,
+		writel(task->pa_base >> cmdq->shift_pa,
+		       thread->base + CMDQ_THR_CURR_ADDR);
+		writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->shift_pa,
 		       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 */
-			}
+		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR) <<
+			cmdq->shift_pa;
+		end_pa = readl(thread->base + CMDQ_THR_END_ADDR) <<
+			cmdq->shift_pa;
+		/* check boundary */
+		if (curr_pa == end_pa - CMDQ_INST_SIZE ||
+		    curr_pa == end_pa) {
+			/* set to this task directly */
+			writel(task->pa_base >> cmdq->shift_pa,
+			       thread->base + CMDQ_THR_CURR_ADDR);
 		} 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 */
-			}
+			cmdq_task_insert_into_thread(task);
+			smp_mb(); /* modify jump before enable thread */
 		}
-		writel(task->pa_base + pkt->cmd_buf_size,
+		writel((task->pa_base + pkt->cmd_buf_size) >> cmdq->shift_pa,
 		       thread->base + CMDQ_THR_END_ADDR);
 		cmdq_thread_resume(thread);
 	}
@@ -430,12 +405,93 @@ static int cmdq_mbox_startup(struct mbox_chan *chan)
 
 static void cmdq_mbox_shutdown(struct mbox_chan *chan)
 {
+	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
+	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
+	struct cmdq_task *task, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&thread->chan->lock, flags);
+	if (list_empty(&thread->task_busy_list))
+		goto done;
+
+	WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+
+	/* make sure executed tasks have success callback */
+	cmdq_thread_irq_handler(cmdq, thread);
+	if (list_empty(&thread->task_busy_list))
+		goto done;
+
+	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
+				 list_entry) {
+		cmdq_task_exec_done(task, -ECONNABORTED);
+		kfree(task);
+	}
+
+	cmdq_thread_disable(cmdq, thread);
+	clk_bulk_disable(cmdq->gce_num, cmdq->clocks);
+
+done:
+	/*
+	 * The thread->task_busy_list empty means thread already disable. The
+	 * cmdq_mbox_send_data() always reset thread which clear disable and
+	 * suspend statue when first pkt send to channel, so there is no need
+	 * to do any operation here, only unlock and leave.
+	 */
+	spin_unlock_irqrestore(&thread->chan->lock, flags);
+}
+
+static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout)
+{
+	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
+	struct cmdq_cb_data data;
+	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
+	struct cmdq_task *task, *tmp;
+	unsigned long flags;
+	u32 enable;
+
+	spin_lock_irqsave(&thread->chan->lock, flags);
+	if (list_empty(&thread->task_busy_list))
+		goto out;
+
+	WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+	if (!cmdq_thread_is_in_wfe(thread))
+		goto wait;
+
+	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
+				 list_entry) {
+		data.sta = -ECONNABORTED;
+		data.pkt = task->pkt;
+		mbox_chan_received_data(task->thread->chan, &data);
+		list_del(&task->list_entry);
+		kfree(task);
+	}
+
+	cmdq_thread_resume(thread);
+	cmdq_thread_disable(cmdq, thread);
+	clk_bulk_disable(cmdq->gce_num, cmdq->clocks);
+
+out:
+	spin_unlock_irqrestore(&thread->chan->lock, flags);
+	return 0;
+
+wait:
+	cmdq_thread_resume(thread);
+	spin_unlock_irqrestore(&thread->chan->lock, flags);
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_ENABLE_TASK,
+				      enable, enable == 0, 1, timeout)) {
+		dev_err(cmdq->mbox.dev, "Fail to wait GCE thread 0x%x done\n",
+			(u32)(thread->base - cmdq->base));
+
+		return -EFAULT;
+	}
+	return 0;
 }
 
 static const struct mbox_chan_ops cmdq_mbox_chan_ops = {
 	.send_data = cmdq_mbox_send_data,
 	.startup = cmdq_mbox_startup,
 	.shutdown = cmdq_mbox_shutdown,
+	.flush = cmdq_mbox_flush,
 };
 
 static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
@@ -449,7 +505,6 @@ static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
 
 	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];
@@ -458,28 +513,37 @@ static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
 static int cmdq_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
 	struct cmdq *cmdq;
 	int err, i;
+	struct gce_plat *plat_data;
+	struct device_node *phandle = dev->of_node;
+	struct device_node *node;
+	int alias_id = 0;
+	static const char * const clk_name = "gce";
+	static const char * const clk_names[] = { "gce0", "gce1" };
 
 	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");
+	cmdq->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(cmdq->base))
 		return PTR_ERR(cmdq->base);
-	}
 
 	cmdq->irq = platform_get_irq(pdev, 0);
-	if (!cmdq->irq) {
-		dev_err(dev, "failed to get irq\n");
+	if (cmdq->irq < 0)
+		return cmdq->irq;
+
+	plat_data = (struct gce_plat *)of_device_get_match_data(dev);
+	if (!plat_data) {
+		dev_err(dev, "failed to get match data\n");
 		return -EINVAL;
 	}
 
-	cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev);
+	cmdq->thread_nr = plat_data->thread_nr;
+	cmdq->shift_pa = plat_data->shift;
+	cmdq->control_by_sw = plat_data->control_by_sw;
+	cmdq->gce_num = plat_data->gce_num;
 	cmdq->irq_mask = GENMASK(cmdq->thread_nr - 1, 0);
 	err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED,
 			       "mtk_cmdq", cmdq);
@@ -491,10 +555,28 @@ static int cmdq_probe(struct platform_device *pdev)
 	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);
+	if (cmdq->gce_num > 1) {
+		for_each_child_of_node(phandle->parent, node) {
+			alias_id = of_alias_get_id(node, clk_name);
+			if (alias_id >= 0 && alias_id < cmdq->gce_num) {
+				cmdq->clocks[alias_id].id = clk_names[alias_id];
+				cmdq->clocks[alias_id].clk = of_clk_get(node, 0);
+				if (IS_ERR(cmdq->clocks[alias_id].clk)) {
+					of_node_put(node);
+					return dev_err_probe(dev,
+							     PTR_ERR(cmdq->clocks[alias_id].clk),
+							     "failed to get gce clk: %d\n",
+							     alias_id);
+				}
+			}
+		}
+	} else {
+		cmdq->clocks[alias_id].id = clk_name;
+		cmdq->clocks[alias_id].clk = devm_clk_get(&pdev->dev, clk_name);
+		if (IS_ERR(cmdq->clocks[alias_id].clk)) {
+			return dev_err_probe(dev, PTR_ERR(cmdq->clocks[alias_id].clk),
+					     "failed to get gce clk\n");
+		}
 	}
 
 	cmdq->mbox.dev = dev;
@@ -530,7 +612,8 @@ static int cmdq_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, cmdq);
-	WARN_ON(clk_prepare(cmdq->clock) < 0);
+
+	WARN_ON(clk_bulk_prepare(cmdq->gce_num, cmdq->clocks));
 
 	cmdq_init(cmdq);
 
@@ -542,9 +625,47 @@ static const struct dev_pm_ops cmdq_pm_ops = {
 	.resume = cmdq_resume,
 };
 
+static const struct gce_plat gce_plat_v2 = {
+	.thread_nr = 16,
+	.shift = 0,
+	.control_by_sw = false,
+	.gce_num = 1
+};
+
+static const struct gce_plat gce_plat_v3 = {
+	.thread_nr = 24,
+	.shift = 0,
+	.control_by_sw = false,
+	.gce_num = 1
+};
+
+static const struct gce_plat gce_plat_v4 = {
+	.thread_nr = 24,
+	.shift = 3,
+	.control_by_sw = false,
+	.gce_num = 1
+};
+
+static const struct gce_plat gce_plat_v5 = {
+	.thread_nr = 24,
+	.shift = 3,
+	.control_by_sw = true,
+	.gce_num = 1
+};
+
+static const struct gce_plat gce_plat_v6 = {
+	.thread_nr = 24,
+	.shift = 3,
+	.control_by_sw = true,
+	.gce_num = 2
+};
+
 static const struct of_device_id cmdq_of_ids[] = {
-	{.compatible = "mediatek,mt8173-gce", .data = (void *)16},
-	{.compatible = "mediatek,mt8183-gce", .data = (void *)24},
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)&gce_plat_v2},
+	{.compatible = "mediatek,mt8183-gce", .data = (void *)&gce_plat_v3},
+	{.compatible = "mediatek,mt6779-gce", .data = (void *)&gce_plat_v4},
+	{.compatible = "mediatek,mt8192-gce", .data = (void *)&gce_plat_v5},
+	{.compatible = "mediatek,mt8195-gce", .data = (void *)&gce_plat_v6},
 	{}
 };