6 files changed, 315 insertions, 181 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 6ee23592700a..ef138731c0ea 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -109,7 +109,7 @@ config FSL_DMA
 
 config MPC512X_DMA
 	tristate "Freescale MPC512x built-in DMA engine support"
-	depends on PPC_MPC512x
+	depends on PPC_MPC512x || PPC_MPC831x
 	select DMA_ENGINE
 	---help---
 	  Enable support for the Freescale MPC512x built-in DMA engine.
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index d0602dd5d1b2..d5a5d4d9c19b 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -273,50 +273,6 @@ struct sdma_channel {
 #define MXC_SDMA_MIN_PRIORITY 1
 #define MXC_SDMA_MAX_PRIORITY 7
 
-/**
- * struct sdma_script_start_addrs - SDMA script start pointers
- *
- * start addresses of the different functions in the physical
- * address space of the SDMA engine.
- */
-struct sdma_script_start_addrs {
-	u32 ap_2_ap_addr;
-	u32 ap_2_bp_addr;
-	u32 ap_2_ap_fixed_addr;
-	u32 bp_2_ap_addr;
-	u32 loopback_on_dsp_side_addr;
-	u32 mcu_interrupt_only_addr;
-	u32 firi_2_per_addr;
-	u32 firi_2_mcu_addr;
-	u32 per_2_firi_addr;
-	u32 mcu_2_firi_addr;
-	u32 uart_2_per_addr;
-	u32 uart_2_mcu_addr;
-	u32 per_2_app_addr;
-	u32 mcu_2_app_addr;
-	u32 per_2_per_addr;
-	u32 uartsh_2_per_addr;
-	u32 uartsh_2_mcu_addr;
-	u32 per_2_shp_addr;
-	u32 mcu_2_shp_addr;
-	u32 ata_2_mcu_addr;
-	u32 mcu_2_ata_addr;
-	u32 app_2_per_addr;
-	u32 app_2_mcu_addr;
-	u32 shp_2_per_addr;
-	u32 shp_2_mcu_addr;
-	u32 mshc_2_mcu_addr;
-	u32 mcu_2_mshc_addr;
-	u32 spdif_2_mcu_addr;
-	u32 mcu_2_spdif_addr;
-	u32 asrc_2_mcu_addr;
-	u32 ext_mem_2_ipu_addr;
-	u32 descrambler_addr;
-	u32 dptc_dvfs_addr;
-	u32 utra_addr;
-	u32 ram_code_start_addr;
-};
-
 #define SDMA_FIRMWARE_MAGIC 0x414d4453
 
 /**
@@ -1127,8 +1083,74 @@ static void sdma_issue_pending(struct dma_chan *chan)
 	 */
 }
 
-static int __init sdma_init(struct sdma_engine *sdma,
-		void *ram_code, int ram_code_size)
+#define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1	34
+
+static void sdma_add_scripts(struct sdma_engine *sdma,
+		const struct sdma_script_start_addrs *addr)
+{
+	s32 *addr_arr = (u32 *)addr;
+	s32 *saddr_arr = (u32 *)sdma->script_addrs;
+	int i;
+
+	for (i = 0; i < SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; i++)
+		if (addr_arr[i] > 0)
+			saddr_arr[i] = addr_arr[i];
+}
+
+static int __init sdma_get_firmware(struct sdma_engine *sdma,
+		const char *cpu_name, int to_version)
+{
+	const struct firmware *fw;
+	char *fwname;
+	const struct sdma_firmware_header *header;
+	int ret;
+	const struct sdma_script_start_addrs *addr;
+	unsigned short *ram_code;
+
+	fwname = kasprintf(GFP_KERNEL, "sdma-%s-to%d.bin", cpu_name, to_version);
+	if (!fwname)
+		return -ENOMEM;
+
+	ret = request_firmware(&fw, fwname, sdma->dev);
+	if (ret) {
+		kfree(fwname);
+		return ret;
+	}
+	kfree(fwname);
+
+	if (fw->size < sizeof(*header))
+		goto err_firmware;
+
+	header = (struct sdma_firmware_header *)fw->data;
+
+	if (header->magic != SDMA_FIRMWARE_MAGIC)
+		goto err_firmware;
+	if (header->ram_code_start + header->ram_code_size > fw->size)
+		goto err_firmware;
+
+	addr = (void *)header + header->script_addrs_start;
+	ram_code = (void *)header + header->ram_code_start;
+
+	clk_enable(sdma->clk);
+	/* download the RAM image for SDMA */
+	sdma_load_script(sdma, ram_code,
+			header->ram_code_size,
+			sdma->script_addrs->ram_code_start_addr);
+	clk_disable(sdma->clk);
+
+	sdma_add_scripts(sdma, addr);
+
+	dev_info(sdma->dev, "loaded firmware %d.%d\n",
+			header->version_major,
+			header->version_minor);
+
+err_firmware:
+	release_firmware(fw);
+
+	return ret;
+}
+
+static int __init sdma_init(struct sdma_engine *sdma)
 {
 	int i, ret;
 	dma_addr_t ccb_phys;
@@ -1192,11 +1214,6 @@ static int __init sdma_init(struct sdma_engine *sdma,
 
 	__raw_writel(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
-	/* download the RAM image for SDMA */
-	sdma_load_script(sdma, ram_code,
-			ram_code_size,
-			sdma->script_addrs->ram_code_start_addr);
-
 	/* Set bits of CONFIG register with given context switching mode */
 	__raw_writel(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
 
@@ -1216,14 +1233,9 @@ err_dma_alloc:
 static int __init sdma_probe(struct platform_device *pdev)
 {
 	int ret;
-	const struct firmware *fw;
-	const struct sdma_firmware_header *header;
-	const struct sdma_script_start_addrs *addr;
 	int irq;
-	unsigned short *ram_code;
 	struct resource *iores;
 	struct sdma_platform_data *pdata = pdev->dev.platform_data;
-	char *fwname;
 	int i;
 	dma_cap_mask_t mask;
 	struct sdma_engine *sdma;
@@ -1262,38 +1274,9 @@ static int __init sdma_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_request_irq;
 
-	fwname = kasprintf(GFP_KERNEL, "sdma-%s-to%d.bin",
-			pdata->cpu_name, pdata->to_version);
-	if (!fwname) {
-		ret = -ENOMEM;
-		goto err_cputype;
-	}
-
-	ret = request_firmware(&fw, fwname, &pdev->dev);
-	if (ret) {
-		dev_err(&pdev->dev, "request firmware \"%s\" failed with %d\n",
-				fwname, ret);
-		kfree(fwname);
-		goto err_cputype;
-	}
-	kfree(fwname);
-
-	if (fw->size < sizeof(*header))
-		goto err_firmware;
-
-	header = (struct sdma_firmware_header *)fw->data;
-
-	if (header->magic != SDMA_FIRMWARE_MAGIC)
-		goto err_firmware;
-	if (header->ram_code_start + header->ram_code_size > fw->size)
-		goto err_firmware;
-
-	addr = (void *)header + header->script_addrs_start;
-	ram_code = (void *)header + header->ram_code_start;
-	sdma->script_addrs = kmalloc(sizeof(*addr), GFP_KERNEL);
+	sdma->script_addrs = kzalloc(sizeof(*sdma->script_addrs), GFP_KERNEL);
 	if (!sdma->script_addrs)
-		goto err_firmware;
-	memcpy(sdma->script_addrs, addr, sizeof(*addr));
+		goto err_alloc;
 
 	sdma->version = pdata->sdma_version;
 
@@ -1316,10 +1299,15 @@ static int __init sdma_probe(struct platform_device *pdev)
 		list_add_tail(&sdmac->chan.device_node, &sdma->dma_device.channels);
 	}
 
-	ret = sdma_init(sdma, ram_code, header->ram_code_size);
+	ret = sdma_init(sdma);
 	if (ret)
 		goto err_init;
 
+	if (pdata->script_addrs)
+		sdma_add_scripts(sdma, pdata->script_addrs);
+
+	sdma_get_firmware(sdma, pdata->cpu_name, pdata->to_version);
+
 	sdma->dma_device.dev = &pdev->dev;
 
 	sdma->dma_device.device_alloc_chan_resources = sdma_alloc_chan_resources;
@@ -1336,10 +1324,6 @@ static int __init sdma_probe(struct platform_device *pdev)
 		goto err_init;
 	}
 
-	dev_info(&pdev->dev, "initialized (firmware %d.%d)\n",
-			header->version_major,
-			header->version_minor);
-
 	/* request channel 0. This is an internal control channel
 	 * to the SDMA engine and not available to clients.
 	 */
@@ -1347,15 +1331,13 @@ static int __init sdma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SLAVE, mask);
 	dma_request_channel(mask, NULL, NULL);
 
-	release_firmware(fw);
+	dev_info(sdma->dev, "initialized\n");
 
 	return 0;
 
 err_init:
 	kfree(sdma->script_addrs);
-err_firmware:
-	release_firmware(fw);
-err_cputype:
+err_alloc:
 	free_irq(irq, sdma);
 err_request_irq:
 	iounmap(sdma->regs);
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 4e9cbf300594..59c270192ccc 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -1,6 +1,7 @@
 /*
  * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008.
  * Copyright (C) Semihalf 2009
+ * Copyright (C) Ilya Yanok, Emcraft Systems 2010
  *
  * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description
  * (defines, structures and comments) was taken from MPC5121 DMA driver
@@ -70,6 +71,8 @@
 #define MPC_DMA_DMAES_SBE	(1 << 1)
 #define MPC_DMA_DMAES_DBE	(1 << 0)
 
+#define MPC_DMA_DMAGPOR_SNOOP_ENABLE	(1 << 6)
+
 #define MPC_DMA_TSIZE_1		0x00
 #define MPC_DMA_TSIZE_2		0x01
 #define MPC_DMA_TSIZE_4		0x02
@@ -104,7 +107,10 @@ struct __attribute__ ((__packed__)) mpc_dma_regs {
 	/* 0x30 */
 	u32 dmahrsh;		/* DMA hw request status high(ch63~32) */
 	u32 dmahrsl;		/* DMA hardware request status low(ch31~0) */
-	u32 dmaihsa;		/* DMA interrupt high select AXE(ch63~32) */
+	union {
+		u32 dmaihsa;	/* DMA interrupt high select AXE(ch63~32) */
+		u32 dmagpor;	/* (General purpose register on MPC8308) */
+	};
 	u32 dmailsa;		/* DMA interrupt low select AXE(ch31~0) */
 	/* 0x40 ~ 0xff */
 	u32 reserve0[48];	/* Reserved */
@@ -195,7 +201,9 @@ struct mpc_dma {
 	struct mpc_dma_regs __iomem	*regs;
 	struct mpc_dma_tcd __iomem	*tcd;
 	int				irq;
+	int				irq2;
 	uint				error_status;
+	int				is_mpc8308;
 
 	/* Lock for error_status field in this structure */
 	spinlock_t			error_status_lock;
@@ -252,11 +260,13 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan)
 		prev = mdesc;
 	}
 
-	prev->tcd->start = 0;
 	prev->tcd->int_maj = 1;
 
 	/* Send first descriptor in chain into hardware */
 	memcpy_toio(&mdma->tcd[cid], first->tcd, sizeof(struct mpc_dma_tcd));
+
+	if (first != prev)
+		mdma->tcd[cid].e_sg = 1;
 	out_8(&mdma->regs->dmassrt, cid);
 }
 
@@ -274,6 +284,9 @@ static void mpc_dma_irq_process(struct mpc_dma *mdma, u32 is, u32 es, int off)
 
 		spin_lock(&mchan->lock);
 
+		out_8(&mdma->regs->dmacint, ch + off);
+		out_8(&mdma->regs->dmacerr, ch + off);
+
 		/* Check error status */
 		if (es & (1 << ch))
 			list_for_each_entry(mdesc, &mchan->active, node)
@@ -302,36 +315,68 @@ static irqreturn_t mpc_dma_irq(int irq, void *data)
 	spin_unlock(&mdma->error_status_lock);
 
 	/* Handle interrupt on each channel */
-	mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth),
+	if (mdma->dma.chancnt > 32) {
+		mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth),
 					in_be32(&mdma->regs->dmaerrh), 32);
+	}
 	mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmaintl),
 					in_be32(&mdma->regs->dmaerrl), 0);
 
-	/* Ack interrupt on all channels */
-	out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
-
 	/* Schedule tasklet */
 	tasklet_schedule(&mdma->tasklet);
 
 	return IRQ_HANDLED;
 }
 
-/* DMA Tasklet */
-static void mpc_dma_tasklet(unsigned long data)
+/* proccess completed descriptors */
+static void mpc_dma_process_completed(struct mpc_dma *mdma)
 {
-	struct mpc_dma *mdma = (void *)data;
 	dma_cookie_t last_cookie = 0;
 	struct mpc_dma_chan *mchan;
 	struct mpc_dma_desc *mdesc;
 	struct dma_async_tx_descriptor *desc;
 	unsigned long flags;
 	LIST_HEAD(list);
-	uint es;
 	int i;
 
+	for (i = 0; i < mdma->dma.chancnt; i++) {
+		mchan = &mdma->channels[i];
+
+		/* Get all completed descriptors */
+		spin_lock_irqsave(&mchan->lock, flags);
+		if (!list_empty(&mchan->completed))
+			list_splice_tail_init(&mchan->completed, &list);
+		spin_unlock_irqrestore(&mchan->lock, flags);
+
+		if (list_empty(&list))
+			continue;
+
+		/* Execute callbacks and run dependencies */
+		list_for_each_entry(mdesc, &list, node) {
+			desc = &mdesc->desc;
+
+			if (desc->callback)
+				desc->callback(desc->callback_param);
+
+			last_cookie = desc->cookie;
+			dma_run_dependencies(desc);
+		}
+
+		/* Free descriptors */
+		spin_lock_irqsave(&mchan->lock, flags);
+		list_splice_tail_init(&list, &mchan->free);
+		mchan->completed_cookie = last_cookie;
+		spin_unlock_irqrestore(&mchan->lock, flags);
+	}
+}
+
+/* DMA Tasklet */
+static void mpc_dma_tasklet(unsigned long data)
+{
+	struct mpc_dma *mdma = (void *)data;
+	unsigned long flags;
+	uint es;
+
 	spin_lock_irqsave(&mdma->error_status_lock, flags);
 	es = mdma->error_status;
 	mdma->error_status = 0;
@@ -370,35 +415,7 @@ static void mpc_dma_tasklet(unsigned long data)
 			dev_err(mdma->dma.dev, "- Destination Bus Error\n");
 	}
 
-	for (i = 0; i < mdma->dma.chancnt; i++) {
-		mchan = &mdma->channels[i];
-
-		/* Get all completed descriptors */
-		spin_lock_irqsave(&mchan->lock, flags);
-		if (!list_empty(&mchan->completed))
-			list_splice_tail_init(&mchan->completed, &list);
-		spin_unlock_irqrestore(&mchan->lock, flags);
-
-		if (list_empty(&list))
-			continue;
-
-		/* Execute callbacks and run dependencies */
-		list_for_each_entry(mdesc, &list, node) {
-			desc = &mdesc->desc;
-
-			if (desc->callback)
-				desc->callback(desc->callback_param);
-
-			last_cookie = desc->cookie;
-			dma_run_dependencies(desc);
-		}
-
-		/* Free descriptors */
-		spin_lock_irqsave(&mchan->lock, flags);
-		list_splice_tail_init(&list, &mchan->free);
-		mchan->completed_cookie = last_cookie;
-		spin_unlock_irqrestore(&mchan->lock, flags);
-	}
+	mpc_dma_process_completed(mdma);
 }
 
 /* Submit descriptor to hardware */
@@ -563,6 +580,7 @@ static struct dma_async_tx_descriptor *
 mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 					size_t len, unsigned long flags)
 {
+	struct mpc_dma *mdma = dma_chan_to_mpc_dma(chan);
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
 	struct mpc_dma_desc *mdesc = NULL;
 	struct mpc_dma_tcd *tcd;
@@ -577,8 +595,11 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 	}
 	spin_unlock_irqrestore(&mchan->lock, iflags);
 
-	if (!mdesc)
+	if (!mdesc) {
+		/* try to free completed descriptors */
+		mpc_dma_process_completed(mdma);
 		return NULL;
+	}
 
 	mdesc->error = 0;
 	tcd = mdesc->tcd;
@@ -591,7 +612,8 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 		tcd->dsize = MPC_DMA_TSIZE_32;
 		tcd->soff = 32;
 		tcd->doff = 32;
-	} else if (IS_ALIGNED(src | dst | len, 16)) {
+	} else if (!mdma->is_mpc8308 && IS_ALIGNED(src | dst | len, 16)) {
+		/* MPC8308 doesn't support 16 byte transfers */
 		tcd->ssize = MPC_DMA_TSIZE_16;
 		tcd->dsize = MPC_DMA_TSIZE_16;
 		tcd->soff = 16;
@@ -651,6 +673,15 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 		return -EINVAL;
 	}
 
+	if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) {
+		mdma->is_mpc8308 = 1;
+		mdma->irq2 = irq_of_parse_and_map(dn, 1);
+		if (mdma->irq2 == NO_IRQ) {
+			dev_err(dev, "Error mapping IRQ!\n");
+			return -EINVAL;
+		}
+	}
+
 	retval = of_address_to_resource(dn, 0, &res);
 	if (retval) {
 		dev_err(dev, "Error parsing memory region!\n");
@@ -681,11 +712,23 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 		return -EINVAL;
 	}
 
+	if (mdma->is_mpc8308) {
+		retval = devm_request_irq(dev, mdma->irq2, &mpc_dma_irq, 0,
+				DRV_NAME, mdma);
+		if (retval) {
+			dev_err(dev, "Error requesting IRQ2!\n");
+			return -EINVAL;
+		}
+	}
+
 	spin_lock_init(&mdma->error_status_lock);
 
 	dma = &mdma->dma;
 	dma->dev = dev;
-	dma->chancnt = MPC_DMA_CHANNELS;
+	if (!mdma->is_mpc8308)
+		dma->chancnt = MPC_DMA_CHANNELS;
+	else
+		dma->chancnt = 16; /* MPC8308 DMA has only 16 channels */
 	dma->device_alloc_chan_resources = mpc_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = mpc_dma_free_chan_resources;
 	dma->device_issue_pending = mpc_dma_issue_pending;
@@ -721,26 +764,40 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 	 * - Round-robin group arbitration,
 	 * - Round-robin channel arbitration.
 	 */
-	out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
-				MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
-
-	/* Disable hardware DMA requests */
-	out_be32(&mdma->regs->dmaerqh, 0);
-	out_be32(&mdma->regs->dmaerql, 0);
-
-	/* Disable error interrupts */
-	out_be32(&mdma->regs->dmaeeih, 0);
-	out_be32(&mdma->regs->dmaeeil, 0);
-
-	/* Clear interrupts status */
-	out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
-
-	/* Route interrupts to IPIC */
-	out_be32(&mdma->regs->dmaihsa, 0);
-	out_be32(&mdma->regs->dmailsa, 0);
+	if (!mdma->is_mpc8308) {
+		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
+					MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
+
+		/* Disable hardware DMA requests */
+		out_be32(&mdma->regs->dmaerqh, 0);
+		out_be32(&mdma->regs->dmaerql, 0);
+
+		/* Disable error interrupts */
+		out_be32(&mdma->regs->dmaeeih, 0);
+		out_be32(&mdma->regs->dmaeeil, 0);
+
+		/* Clear interrupts status */
+		out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
+
+		/* Route interrupts to IPIC */
+		out_be32(&mdma->regs->dmaihsa, 0);
+		out_be32(&mdma->regs->dmailsa, 0);
+	} else {
+		/* MPC8308 has 16 channels and lacks some registers */
+		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA);
+
+		/* enable snooping */
+		out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE);
+		/* Disable error interrupts */
+		out_be32(&mdma->regs->dmaeeil, 0);
+
+		/* Clear interrupts status */
+		out_be32(&mdma->regs->dmaintl, 0xFFFF);
+		out_be32(&mdma->regs->dmaerrl, 0xFFFF);
+	}
 
 	/* Register DMA engine */
 	dev_set_drvdata(dev, mdma);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 411d5bf50fc4..a25f5f61e0e0 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -449,7 +449,7 @@ mv_xor_slot_cleanup(struct mv_xor_chan *mv_chan)
 static void mv_xor_tasklet(unsigned long data)
 {
 	struct mv_xor_chan *chan = (struct mv_xor_chan *) data;
-	__mv_xor_slot_cleanup(chan);
+	mv_xor_slot_cleanup(chan);
 }
 
 static struct mv_xor_desc_slot *
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 85ffd5e38c50..28720d3103c4 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -27,7 +27,10 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/sh_dma.h>
-
+#include <linux/notifier.h>
+#include <linux/kdebug.h>
+#include <linux/spinlock.h>
+#include <linux/rculist.h>
 #include "shdma.h"
 
 /* DMA descriptor control */
@@ -43,6 +46,13 @@ enum sh_dmae_desc_status {
 /* Default MEMCPY transfer size = 2^2 = 4 bytes */
 #define LOG2_DEFAULT_XFER_SIZE	2
 
+/*
+ * Used for write-side mutual exclusion for the global device list,
+ * read-side synchronization by way of RCU.
+ */
+static DEFINE_SPINLOCK(sh_dmae_lock);
+static LIST_HEAD(sh_dmae_devices);
+
 /* A bitmask with bits enough for enum sh_dmae_slave_chan_id */
 static unsigned long sh_dmae_slave_used[BITS_TO_LONGS(SH_DMA_SLAVE_NUMBER)];
 
@@ -817,10 +827,9 @@ static irqreturn_t sh_dmae_interrupt(int irq, void *data)
 	return ret;
 }
 
-#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
-static irqreturn_t sh_dmae_err(int irq, void *data)
+static unsigned int sh_dmae_reset(struct sh_dmae_device *shdev)
 {
-	struct sh_dmae_device *shdev = (struct sh_dmae_device *)data;
+	unsigned int handled = 0;
 	int i;
 
 	/* halt the dma controller */
@@ -829,25 +838,35 @@ static irqreturn_t sh_dmae_err(int irq, void *data)
 	/* We cannot detect, which channel caused the error, have to reset all */
 	for (i = 0; i < SH_DMAC_MAX_CHANNELS; i++) {
 		struct sh_dmae_chan *sh_chan = shdev->chan[i];
-		if (sh_chan) {
-			struct sh_desc *desc;
-			/* Stop the channel */
-			dmae_halt(sh_chan);
-			/* Complete all  */
-			list_for_each_entry(desc, &sh_chan->ld_queue, node) {
-				struct dma_async_tx_descriptor *tx = &desc->async_tx;
-				desc->mark = DESC_IDLE;
-				if (tx->callback)
-					tx->callback(tx->callback_param);
-			}
-			list_splice_init(&sh_chan->ld_queue, &sh_chan->ld_free);
+		struct sh_desc *desc;
+
+		if (!sh_chan)
+			continue;
+
+		/* Stop the channel */
+		dmae_halt(sh_chan);
+
+		/* Complete all  */
+		list_for_each_entry(desc, &sh_chan->ld_queue, node) {
+			struct dma_async_tx_descriptor *tx = &desc->async_tx;
+			desc->mark = DESC_IDLE;
+			if (tx->callback)
+				tx->callback(tx->callback_param);
 		}
+
+		list_splice_init(&sh_chan->ld_queue, &sh_chan->ld_free);
+		handled++;
 	}
+
 	sh_dmae_rst(shdev);
 
-	return IRQ_HANDLED;
+	return !!handled;
+}
+
+static irqreturn_t sh_dmae_err(int irq, void *data)
+{
+	return IRQ_RETVAL(sh_dmae_reset(data));
 }
-#endif
 
 static void dmae_do_tasklet(unsigned long data)
 {
@@ -876,6 +895,60 @@ static void dmae_do_tasklet(unsigned long data)
 	sh_dmae_chan_ld_cleanup(sh_chan, false);
 }
 
+static bool sh_dmae_nmi_notify(struct sh_dmae_device *shdev)
+{
+	unsigned int handled;
+
+	/* Fast path out if NMIF is not asserted for this controller */
+	if ((dmaor_read(shdev) & DMAOR_NMIF) == 0)
+		return false;
+
+	handled = sh_dmae_reset(shdev);
+	if (handled)
+		return true;
+
+	return false;
+}
+
+static int sh_dmae_nmi_handler(struct notifier_block *self,
+			       unsigned long cmd, void *data)
+{
+	struct sh_dmae_device *shdev;
+	int ret = NOTIFY_DONE;
+	bool triggered;
+
+	/*
+	 * Only concern ourselves with NMI events.
+	 *
+	 * Normally we would check the die chain value, but as this needs
+	 * to be architecture independent, check for NMI context instead.
+	 */
+	if (!in_nmi())
+		return NOTIFY_DONE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(shdev, &sh_dmae_devices, node) {
+		/*
+		 * Only stop if one of the controllers has NMIF asserted,
+		 * we do not want to interfere with regular address error
+		 * handling or NMI events that don't concern the DMACs.
+		 */
+		triggered = sh_dmae_nmi_notify(shdev);
+		if (triggered == true)
+			ret = NOTIFY_OK;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static struct notifier_block sh_dmae_nmi_notifier __read_mostly = {
+	.notifier_call	= sh_dmae_nmi_handler,
+
+	/* Run before NMI debug handler and KGDB */
+	.priority	= 1,
+};
+
 static int __devinit sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
 					int irq, unsigned long flags)
 {
@@ -967,6 +1040,7 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 	struct sh_dmae_pdata *pdata = pdev->dev.platform_data;
 	unsigned long irqflags = IRQF_DISABLED,
 		chan_flag[SH_DMAC_MAX_CHANNELS] = {};
+	unsigned long flags;
 	int errirq, chan_irq[SH_DMAC_MAX_CHANNELS];
 	int err, i, irq_cnt = 0, irqres = 0;
 	struct sh_dmae_device *shdev;
@@ -1032,6 +1106,10 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
+	spin_lock_irqsave(&sh_dmae_lock, flags);
+	list_add_tail_rcu(&shdev->node, &sh_dmae_devices);
+	spin_unlock_irqrestore(&sh_dmae_lock, flags);
+
 	/* reset dma controller */
 	err = sh_dmae_rst(shdev);
 	if (err)
@@ -1135,6 +1213,10 @@ eirqres:
 eirq_err:
 #endif
 rst_err:
+	spin_lock_irqsave(&sh_dmae_lock, flags);
+	list_del_rcu(&shdev->node);
+	spin_unlock_irqrestore(&sh_dmae_lock, flags);
+
 	pm_runtime_put(&pdev->dev);
 	if (dmars)
 		iounmap(shdev->dmars);
@@ -1155,6 +1237,7 @@ static int __exit sh_dmae_remove(struct platform_device *pdev)
 {
 	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
 	struct resource *res;
+	unsigned long flags;
 	int errirq = platform_get_irq(pdev, 0);
 
 	dma_async_device_unregister(&shdev->common);
@@ -1162,6 +1245,10 @@ static int __exit sh_dmae_remove(struct platform_device *pdev)
 	if (errirq > 0)
 		free_irq(errirq, shdev);
 
+	spin_lock_irqsave(&sh_dmae_lock, flags);
+	list_del_rcu(&shdev->node);
+	spin_unlock_irqrestore(&sh_dmae_lock, flags);
+
 	/* channel data remove */
 	sh_dmae_chan_remove(shdev);
 
@@ -1200,6 +1287,11 @@ static struct platform_driver sh_dmae_driver = {
 
 static int __init sh_dmae_init(void)
 {
+	/* Wire up NMI handling */
+	int err = register_die_notifier(&sh_dmae_nmi_notifier);
+	if (err)
+		return err;
+
 	return platform_driver_probe(&sh_dmae_driver, sh_dmae_probe);
 }
 module_init(sh_dmae_init);
@@ -1207,6 +1299,8 @@ module_init(sh_dmae_init);
 static void __exit sh_dmae_exit(void)
 {
 	platform_driver_unregister(&sh_dmae_driver);
+
+	unregister_die_notifier(&sh_dmae_nmi_notifier);
 }
 module_exit(sh_dmae_exit);
 
diff --git a/drivers/dma/shdma.h b/drivers/dma/shdma.h
index 4021275a0a43..52e4fb173805 100644
--- a/drivers/dma/shdma.h
+++ b/drivers/dma/shdma.h
@@ -43,6 +43,7 @@ struct sh_dmae_device {
 	struct dma_device common;
 	struct sh_dmae_chan *chan[SH_DMAC_MAX_CHANNELS];
 	struct sh_dmae_pdata *pdata;
+	struct list_head node;
 	u32 __iomem *chan_reg;
 	u16 __iomem *dmars;
 };