ARM: 8202/1: dmaengine: pl330: Add runtime Power Management support v12

This patch adds runtime PM support to pl330 DMA engine driver.

The runtime power management for pl330 DMA driver allows gating of AMBA
clock (PDMA) in FSYS clock domain, when the device is not processing any
requests. This is necessary to enter low power modes on Exynos SoCs
(e.g. LPA on Exynos4x12 or W-AFTR on Exynos3250).

Runtime PM resuming of the device may happen in atomic context (during
call device_issue_pending()) so pm_runtime_irq_safe() is used. This will
lead only to disabling/enabling of the clock but this is sufficient for
gating the clock and for reducing energy usage.

Driver uses runtime PM callbacks from amba/bus.c driver only.

Suggested-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 4839bfa..39ea8d4 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -27,6 +27,7 @@
 #include <linux/of.h>
 #include <linux/of_dma.h>
 #include <linux/err.h>
+#include <linux/pm_runtime.h>
 
 #include "dmaengine.h"
 #define PL330_MAX_CHAN		8
@@ -265,6 +266,9 @@
 
 #define NR_DEFAULT_DESC	16
 
+/* Delay for runtime PM autosuspend, ms */
+#define PL330_AUTOSUSPEND_DELAY 20
+
 /* Populated by the PL330 core driver for DMA API driver's info */
 struct pl330_config {
 	u32	periph_id;
@@ -1958,6 +1962,7 @@
 	struct dma_pl330_chan *pch = (struct dma_pl330_chan *)data;
 	struct dma_pl330_desc *desc, *_dt;
 	unsigned long flags;
+	bool power_down = false;
 
 	spin_lock_irqsave(&pch->lock, flags);
 
@@ -1972,10 +1977,17 @@
 	/* Try to submit a req imm. next to the last completed cookie */
 	fill_queue(pch);
 
-	/* Make sure the PL330 Channel thread is active */
-	spin_lock(&pch->thread->dmac->lock);
-	_start(pch->thread);
-	spin_unlock(&pch->thread->dmac->lock);
+	if (list_empty(&pch->work_list)) {
+		spin_lock(&pch->thread->dmac->lock);
+		_stop(pch->thread);
+		spin_unlock(&pch->thread->dmac->lock);
+		power_down = true;
+	} else {
+		/* Make sure the PL330 Channel thread is active */
+		spin_lock(&pch->thread->dmac->lock);
+		_start(pch->thread);
+		spin_unlock(&pch->thread->dmac->lock);
+	}
 
 	while (!list_empty(&pch->completed_list)) {
 		dma_async_tx_callback callback;
@@ -1990,6 +2002,12 @@
 		if (pch->cyclic) {
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
+			if (power_down) {
+				spin_lock(&pch->thread->dmac->lock);
+				_start(pch->thread);
+				spin_unlock(&pch->thread->dmac->lock);
+				power_down = false;
+			}
 		} else {
 			desc->status = FREE;
 			list_move_tail(&desc->node, &pch->dmac->desc_pool);
@@ -2004,6 +2022,12 @@
 		}
 	}
 	spin_unlock_irqrestore(&pch->lock, flags);
+
+	/* If work list empty, power down */
+	if (power_down) {
+		pm_runtime_mark_last_busy(pch->dmac->ddma.dev);
+		pm_runtime_put_autosuspend(pch->dmac->ddma.dev);
+	}
 }
 
 bool pl330_filter(struct dma_chan *chan, void *param)
@@ -2073,6 +2097,7 @@
 
 	switch (cmd) {
 	case DMA_TERMINATE_ALL:
+		pm_runtime_get_sync(pl330->ddma.dev);
 		spin_lock_irqsave(&pch->lock, flags);
 
 		spin_lock(&pl330->lock);
@@ -2099,10 +2124,15 @@
 			dma_cookie_complete(&desc->txd);
 		}
 
+		if (!list_empty(&pch->work_list))
+			pm_runtime_put(pl330->ddma.dev);
+
 		list_splice_tail_init(&pch->submitted_list, &pl330->desc_pool);
 		list_splice_tail_init(&pch->work_list, &pl330->desc_pool);
 		list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 		spin_unlock_irqrestore(&pch->lock, flags);
+		pm_runtime_mark_last_busy(pl330->ddma.dev);
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 		break;
 	case DMA_SLAVE_CONFIG:
 		slave_config = (struct dma_slave_config *)arg;
@@ -2138,6 +2168,7 @@
 
 	tasklet_kill(&pch->task);
 
+	pm_runtime_get_sync(pch->dmac->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
 
 	pl330_release_channel(pch->thread);
@@ -2147,6 +2178,8 @@
 		list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool);
 
 	spin_unlock_irqrestore(&pch->lock, flags);
+	pm_runtime_mark_last_busy(pch->dmac->ddma.dev);
+	pm_runtime_put_autosuspend(pch->dmac->ddma.dev);
 }
 
 static enum dma_status
@@ -2162,6 +2195,15 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&pch->lock, flags);
+	if (list_empty(&pch->work_list)) {
+		/*
+		 * Warn on nothing pending. Empty submitted_list may
+		 * break our pm_runtime usage counter as it is
+		 * updated on work_list emptiness status.
+		 */
+		WARN_ON(list_empty(&pch->submitted_list));
+		pm_runtime_get_sync(pch->dmac->ddma.dev);
+	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);
 	spin_unlock_irqrestore(&pch->lock, flags);
 
@@ -2738,6 +2780,12 @@
 		pcfg->data_buf_dep, pcfg->data_bus_width / 8, pcfg->num_chan,
 		pcfg->num_peri, pcfg->num_events);
 
+	pm_runtime_irq_safe(&adev->dev);
+	pm_runtime_use_autosuspend(&adev->dev);
+	pm_runtime_set_autosuspend_delay(&adev->dev, PL330_AUTOSUSPEND_DELAY);
+	pm_runtime_mark_last_busy(&adev->dev);
+	pm_runtime_put_autosuspend(&adev->dev);
+
 	return 0;
 probe_err3:
 	/* Idle the DMAC */
@@ -2764,6 +2812,8 @@
 	struct pl330_dmac *pl330 = amba_get_drvdata(adev);
 	struct dma_pl330_chan *pch, *_p;
 
+	pm_runtime_get_noresume(pl330->ddma.dev);
+
 	if (adev->dev.of_node)
 		of_dma_controller_free(adev->dev.of_node);