Merge tag 'dmaengine-fix-4.10-rc4' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine fixes from Vinod Koul:
 "The fixes this time around are spread over drivers, pretty normal
  update:

   - PCI ID for SKL ioatdma, workaround for SKX and
     ioat_alloc_chan_resources sleepy allocation fix

   - dw kconfig typo fix

   - null pointer deref for stm32

   - MAINTAINERS Update for at_hdmac

   - pl330 runtime pm fixes

   - omap-dma port window fix

   - rcar-dmac unmap slave resource fix"

* tag 'dmaengine-fix-4.10-rc4' of git://git.infradead.org/users/vkoul/slave-dma:
  dmaengine: rcar-dmac: unmap slave resource when channel is freed
  dmaengine: omap-dma: Fix the port_window support
  dmaengine: iota: ioat_alloc_chan_resources should not perform sleeping allocations.
  dmaengine: pl330: Fix runtime PM support for terminated transfers
  MAINTAINERS: dmaengine: Update + Hand over the at_hdmac driver to Ludovic
  dmaengine: omap-dma: Fix dynamic lch_map allocation
  dmaengine: ti-dma-crossbar: Add some 'of_node_put()' in error path.
  dmaengine: stm32-dma: Fix null pointer dereference in stm32_dma_tx_status
  dmaengine: stm32-dma: Set correct args number for DMA request from DT
  dmaengine: dw: fix typo in Kconfig
  dmaengine: ioatdma: workaround SKX ioatdma version
  dmaengine: ioatdma: Add Skylake PCI Dev ID

MAINTAINERS

@@ -2193,14 +2193,6 @@ L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/atmel
 
-ATMEL DMA DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
-F:	drivers/dma/at_hdmac.c
-F:	drivers/dma/at_hdmac_regs.h
-F:	include/linux/platform_data/dma-atmel.h
-
 ATMEL XDMA DRIVER
 M:	Ludovic Desroches <ludovic.desroches@atmel.com>
 L:	linux-arm-kernel@lists.infradead.org
@@ -8178,6 +8170,15 @@ S:	Maintained
 F:	drivers/tty/serial/atmel_serial.c
 F:	include/linux/atmel_serial.h
 
+MICROCHIP / ATMEL DMA DRIVER
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	dmaengine@vger.kernel.org
+S:	Supported
+F:	drivers/dma/at_hdmac.c
+F:	drivers/dma/at_hdmac_regs.h
+F:	include/linux/platform_data/dma-atmel.h
+
 MICROCHIP / ATMEL ISC DRIVER
 M:	Songjun Wu <songjun.wu@microchip.com>
 L:	linux-media@vger.kernel.org

drivers/dma/dw/Kconfig

@@ -24,5 +24,5 @@ config DW_DMAC_PCI
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller on the
-	  platfroms that enumerate it as a PCI device. For example,
+	  platforms that enumerate it as a PCI device. For example,
 	  Intel Medfield has integrated this GPDMA controller.

drivers/dma/ioat/hw.h

@@ -64,6 +64,8 @@
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX8	0x6f2e
 #define PCI_DEVICE_ID_INTEL_IOAT_BDX9	0x6f2f
 
+#define PCI_DEVICE_ID_INTEL_IOAT_SKX	0x2021
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */

drivers/dma/ioat/init.c

@@ -106,6 +106,8 @@ static struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX8) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDX9) },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_SKX) },
+
 	/* I/OAT v3.3 platforms */
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD0) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BWD1) },
@@ -243,10 +245,15 @@ static bool is_bdx_ioat(struct pci_dev *pdev)
 	}
 }
 
+static inline bool is_skx_ioat(struct pci_dev *pdev)
+{
+	return (pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SKX) ? true : false;
+}
+
 static bool is_xeon_cb32(struct pci_dev *pdev)
 {
 	return is_jf_ioat(pdev) || is_snb_ioat(pdev) || is_ivb_ioat(pdev) ||
-		is_hsw_ioat(pdev) || is_bdx_ioat(pdev);
+		is_hsw_ioat(pdev) || is_bdx_ioat(pdev) || is_skx_ioat(pdev);
 }
 
 bool is_bwd_ioat(struct pci_dev *pdev)
@@ -693,7 +700,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
 	ioat_chan->completion =
 		dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool,
-				GFP_KERNEL, &ioat_chan->completion_dma);
+				GFP_NOWAIT, &ioat_chan->completion_dma);
 	if (!ioat_chan->completion)
 		return -ENOMEM;
 
@@ -703,7 +710,7 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
 	order = IOAT_MAX_ORDER;
-	ring = ioat_alloc_ring(c, order, GFP_KERNEL);
+	ring = ioat_alloc_ring(c, order, GFP_NOWAIT);
 	if (!ring)
 		return -ENOMEM;
 
@@ -1357,6 +1364,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
 	if (device->version >= IOAT_VER_3_0) {
+		if (is_skx_ioat(pdev))
+			device->version = IOAT_VER_3_2;
 		err = ioat3_dma_probe(device, ioat_dca_enabled);
 
 		if (device->version >= IOAT_VER_3_3)

drivers/dma/omap-dma.c

@@ -938,21 +938,14 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		d->ccr |= CCR_DST_AMODE_POSTINC;
 		if (port_window) {
 			d->ccr |= CCR_SRC_AMODE_DBLIDX;
-			d->ei = 1;
-			/*
-			 * One frame covers the port_window and by  configure
-			 * the source frame index to be -1 * (port_window - 1)
-			 * we instruct the sDMA that after a frame is processed
-			 * it should move back to the start of the window.
-			 */
-			d->fi = -(port_window_bytes - 1);
 
 			if (port_window_bytes >= 64)
-				d->csdp = CSDP_SRC_BURST_64 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_64;
 			else if (port_window_bytes >= 32)
-				d->csdp = CSDP_SRC_BURST_32 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_32;
 			else if (port_window_bytes >= 16)
-				d->csdp = CSDP_SRC_BURST_16 | CSDP_SRC_PACKED;
+				d->csdp |= CSDP_SRC_BURST_16;
+
 		} else {
 			d->ccr |= CCR_SRC_AMODE_CONSTANT;
 		}
@@ -962,13 +955,21 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		d->ccr |= CCR_SRC_AMODE_POSTINC;
 		if (port_window) {
 			d->ccr |= CCR_DST_AMODE_DBLIDX;
+			d->ei = 1;
+			/*
+			 * One frame covers the port_window and by  configure
+			 * the source frame index to be -1 * (port_window - 1)
+			 * we instruct the sDMA that after a frame is processed
+			 * it should move back to the start of the window.
+			 */
+			d->fi = -(port_window_bytes - 1);
 
 			if (port_window_bytes >= 64)
-				d->csdp = CSDP_DST_BURST_64 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_64;
 			else if (port_window_bytes >= 32)
-				d->csdp = CSDP_DST_BURST_32 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_32;
 			else if (port_window_bytes >= 16)
-				d->csdp = CSDP_DST_BURST_16 | CSDP_DST_PACKED;
+				d->csdp |= CSDP_DST_BURST_16;
 		} else {
 			d->ccr |= CCR_DST_AMODE_CONSTANT;
 		}
@@ -1017,7 +1018,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_slave_sg(
 		osg->addr = sg_dma_address(sgent);
 		osg->en = en;
 		osg->fn = sg_dma_len(sgent) / frame_bytes;
-		if (port_window && dir == DMA_MEM_TO_DEV) {
+		if (port_window && dir == DMA_DEV_TO_MEM) {
 			osg->ei = 1;
 			/*
 			 * One frame covers the port_window and by  configure
@@ -1452,6 +1453,7 @@ static int omap_dma_probe(struct platform_device *pdev)
 	struct omap_dmadev *od;
 	struct resource *res;
 	int rc, i, irq;
+	u32 lch_count;
 
 	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
 	if (!od)
@@ -1494,20 +1496,31 @@ static int omap_dma_probe(struct platform_device *pdev)
 	spin_lock_init(&od->lock);
 	spin_lock_init(&od->irq_lock);
 
-	if (!pdev->dev.of_node) {
-		od->dma_requests = od->plat->dma_attr->lch_count;
-		if (unlikely(!od->dma_requests))
+	/* Number of DMA requests */
 	od->dma_requests = OMAP_SDMA_REQUESTS;
-	} else if (of_property_read_u32(pdev->dev.of_node, "dma-requests",
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-requests",
 						      &od->dma_requests)) {
 		dev_info(&pdev->dev,
 			 "Missing dma-requests property, using %u.\n",
 			 OMAP_SDMA_REQUESTS);
-		od->dma_requests = OMAP_SDMA_REQUESTS;
 	}
 
-	od->lch_map = devm_kcalloc(&pdev->dev, od->dma_requests,
-				   sizeof(*od->lch_map), GFP_KERNEL);
+	/* Number of available logical channels */
+	if (!pdev->dev.of_node) {
+		lch_count = od->plat->dma_attr->lch_count;
+		if (unlikely(!lch_count))
+			lch_count = OMAP_SDMA_CHANNELS;
+	} else if (of_property_read_u32(pdev->dev.of_node, "dma-channels",
+					&lch_count)) {
+		dev_info(&pdev->dev,
+			 "Missing dma-channels property, using %u.\n",
+			 OMAP_SDMA_CHANNELS);
+		lch_count = OMAP_SDMA_CHANNELS;
+	}
+
+	od->lch_map = devm_kcalloc(&pdev->dev, lch_count, sizeof(*od->lch_map),
+				   GFP_KERNEL);
 	if (!od->lch_map)
 		return -ENOMEM;
 

drivers/dma/pl330.c

@@ -448,6 +448,9 @@ struct dma_pl330_chan {
 
 	/* for cyclic capability */
 	bool cyclic;
+
+	/* for runtime pm tracking */
+	bool active;
 };
 
 struct pl330_dmac {
@@ -2033,6 +2036,7 @@ static void pl330_tasklet(unsigned long data)
 		_stop(pch->thread);
 		spin_unlock(&pch->thread->dmac->lock);
 		power_down = true;
+		pch->active = false;
 	} else {
 		/* Make sure the PL330 Channel thread is active */
 		spin_lock(&pch->thread->dmac->lock);
@@ -2052,6 +2056,7 @@ static void pl330_tasklet(unsigned long data)
 			desc->status = PREP;
 			list_move_tail(&desc->node, &pch->work_list);
 			if (power_down) {
+				pch->active = true;
 				spin_lock(&pch->thread->dmac->lock);
 				_start(pch->thread);
 				spin_unlock(&pch->thread->dmac->lock);
@@ -2166,6 +2171,7 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
 	LIST_HEAD(list);
+	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);
 	spin_lock_irqsave(&pch->lock, flags);
@@ -2176,6 +2182,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	pch->thread->req[0].desc = NULL;
 	pch->thread->req[1].desc = NULL;
 	pch->thread->req_running = -1;
+	power_down = pch->active;
+	pch->active = false;
 
 	/* Mark all desc done */
 	list_for_each_entry(desc, &pch->submitted_list, node) {
@@ -2193,6 +2201,8 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	list_splice_tail_init(&pch->completed_list, &pl330->desc_pool);
 	spin_unlock_irqrestore(&pch->lock, flags);
 	pm_runtime_mark_last_busy(pl330->ddma.dev);
+	if (power_down)
+		pm_runtime_put_autosuspend(pl330->ddma.dev);
 	pm_runtime_put_autosuspend(pl330->ddma.dev);
 
 	return 0;
@@ -2357,6 +2367,7 @@ static void pl330_issue_pending(struct dma_chan *chan)
 		 * updated on work_list emptiness status.
 		 */
 		WARN_ON(list_empty(&pch->submitted_list));
+		pch->active = true;
 		pm_runtime_get_sync(pch->dmac->ddma.dev);
 	}
 	list_splice_tail_init(&pch->submitted_list, &pch->work_list);

drivers/dma/sh/rcar-dmac.c

@@ -986,6 +986,7 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
+	struct rcar_dmac_chan_map *map = &rchan->map;
 	struct rcar_dmac_desc_page *page, *_page;
 	struct rcar_dmac_desc *desc;
 	LIST_HEAD(list);
@@ -1019,6 +1020,13 @@ static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
 		free_page((unsigned long)page);
 	}
 
+	/* Remove slave mapping if present. */
+	if (map->slave.xfer_size) {
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+		map->slave.xfer_size = 0;
+	}
+
 	pm_runtime_put(chan->device->dev);
 }
 

drivers/dma/stm32-dma.c

@@ -880,7 +880,7 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
 	struct virt_dma_desc *vdesc;
 	enum dma_status status;
 	unsigned long flags;
-	u32 residue;
+	u32 residue = 0;
 
 	status = dma_cookie_status(c, cookie, state);
 	if ((status == DMA_COMPLETE) || (!state))
@@ -888,16 +888,12 @@ static enum dma_status stm32_dma_tx_status(struct dma_chan *c,
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 	vdesc = vchan_find_desc(&chan->vchan, cookie);
-	if (cookie == chan->desc->vdesc.tx.cookie) {
+	if (chan->desc && cookie == chan->desc->vdesc.tx.cookie)
 		residue = stm32_dma_desc_residue(chan, chan->desc,
 						 chan->next_sg);
-	} else if (vdesc) {
+	else if (vdesc)
 		residue = stm32_dma_desc_residue(chan,
 						 to_stm32_dma_desc(vdesc), 0);
-	} else {
-		residue = 0;
-	}
-
 	dma_set_residue(state, residue);
 
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);
@@ -972,21 +968,18 @@ static struct dma_chan *stm32_dma_of_xlate(struct of_phandle_args *dma_spec,
 	struct stm32_dma_chan *chan;
 	struct dma_chan *c;
 
-	if (dma_spec->args_count < 3)
+	if (dma_spec->args_count < 4)
 		return NULL;
 
 	cfg.channel_id = dma_spec->args[0];
 	cfg.request_line = dma_spec->args[1];
 	cfg.stream_config = dma_spec->args[2];
-	cfg.threshold = 0;
+	cfg.threshold = dma_spec->args[3];
 
 	if ((cfg.channel_id >= STM32_DMA_MAX_CHANNELS) || (cfg.request_line >=
 				STM32_DMA_MAX_REQUEST_ID))
 		return NULL;
 
-	if (dma_spec->args_count > 3)
-		cfg.threshold = dma_spec->args[3];
-
 	chan = &dmadev->chan[cfg.channel_id];
 
 	c = dma_get_slave_channel(&chan->vchan.chan);

drivers/dma/ti-dma-crossbar.c

@@ -149,6 +149,7 @@ static int ti_am335x_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_am335x_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}
 
@@ -339,6 +340,7 @@ static int ti_dra7_xbar_probe(struct platform_device *pdev)
 	match = of_match_node(ti_dra7_master_match, dma_node);
 	if (!match) {
 		dev_err(&pdev->dev, "DMA master is not supported\n");
+		of_node_put(dma_node);
 		return -EINVAL;
 	}