Merge branch 'topic/st_fdma' into for-linus

7 files changed, 1534 insertions, 9 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 4595f5009244..b4cb5cb7775c 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -435,6 +435,20 @@ config STE_DMA40
 	help
 	  Support for ST-Ericsson DMA40 controller
 
+config ST_FDMA
+	tristate "ST FDMA dmaengine support"
+	depends on ARCH_STI
+	depends on REMOTEPROC
+	select ST_SLIM_REMOTEPROC
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for ST FDMA controller.
+	  It supports 16 independent DMA channels, accepts up to 32 DMA requests
+
+	  Say Y here if you have such a chipset.
+	  If unsure, say N.
+
 config STM32_DMA
 	bool "STMicroelectronics STM32 DMA support"
 	depends on ARCH_STM32 || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index e4dc9cac7ee8..a4fa3360e609 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -67,6 +67,7 @@ obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-crossbar.o
 obj-$(CONFIG_TI_EDMA) += edma.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx296702_dma.o
+obj-$(CONFIG_ST_FDMA) += st_fdma.o
 
 obj-y += qcom/
 obj-y += xilinx/
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
new file mode 100644
index 000000000000..bfb79bd0c6de
--- /dev/null
+++ b/drivers/dma/st_fdma.c
@@ -0,0 +1,889 @@
+/*
+ * DMA driver for STMicroelectronics STi FDMA controller
+ *
+ * Copyright (C) 2014 STMicroelectronics
+ *
+ * Author: Ludovic Barre <Ludovic.barre@st.com>
+ *	   Peter Griffin <peter.griffin@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/remoteproc.h>
+
+#include "st_fdma.h"
+
+static inline struct st_fdma_chan *to_st_fdma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct st_fdma_chan, vchan.chan);
+}
+
+static struct st_fdma_desc *to_st_fdma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct st_fdma_desc, vdesc);
+}
+
+static int st_fdma_dreq_get(struct st_fdma_chan *fchan)
+{
+	struct st_fdma_dev *fdev = fchan->fdev;
+	u32 req_line_cfg = fchan->cfg.req_line;
+	u32 dreq_line;
+	int try = 0;
+
+	/*
+	 * dreq_mask is shared for n channels of fdma, so all accesses must be
+	 * atomic. if the dreq_mask is changed between ffz and set_bit,
+	 * we retry
+	 */
+	do {
+		if (fdev->dreq_mask == ~0L) {
+			dev_err(fdev->dev, "No req lines available\n");
+			return -EINVAL;
+		}
+
+		if (try || req_line_cfg >= ST_FDMA_NR_DREQS) {
+			dev_err(fdev->dev, "Invalid or used req line\n");
+			return -EINVAL;
+		} else {
+			dreq_line = req_line_cfg;
+		}
+
+		try++;
+	} while (test_and_set_bit(dreq_line, &fdev->dreq_mask));
+
+	dev_dbg(fdev->dev, "get dreq_line:%d mask:%#lx\n",
+		dreq_line, fdev->dreq_mask);
+
+	return dreq_line;
+}
+
+static void st_fdma_dreq_put(struct st_fdma_chan *fchan)
+{
+	struct st_fdma_dev *fdev = fchan->fdev;
+
+	dev_dbg(fdev->dev, "put dreq_line:%#x\n", fchan->dreq_line);
+	clear_bit(fchan->dreq_line, &fdev->dreq_mask);
+}
+
+static void st_fdma_xfer_desc(struct st_fdma_chan *fchan)
+{
+	struct virt_dma_desc *vdesc;
+	unsigned long nbytes, ch_cmd, cmd;
+
+	vdesc = vchan_next_desc(&fchan->vchan);
+	if (!vdesc)
+		return;
+
+	fchan->fdesc = to_st_fdma_desc(vdesc);
+	nbytes = fchan->fdesc->node[0].desc->nbytes;
+	cmd = FDMA_CMD_START(fchan->vchan.chan.chan_id);
+	ch_cmd = fchan->fdesc->node[0].pdesc | FDMA_CH_CMD_STA_START;
+
+	/* start the channel for the descriptor */
+	fnode_write(fchan, nbytes, FDMA_CNTN_OFST);
+	fchan_write(fchan, ch_cmd, FDMA_CH_CMD_OFST);
+	writel(cmd,
+		fchan->fdev->slim_rproc->peri + FDMA_CMD_SET_OFST);
+
+	dev_dbg(fchan->fdev->dev, "start chan:%d\n", fchan->vchan.chan.chan_id);
+}
+
+static void st_fdma_ch_sta_update(struct st_fdma_chan *fchan,
+				  unsigned long int_sta)
+{
+	unsigned long ch_sta, ch_err;
+	int ch_id = fchan->vchan.chan.chan_id;
+	struct st_fdma_dev *fdev = fchan->fdev;
+
+	ch_sta = fchan_read(fchan, FDMA_CH_CMD_OFST);
+	ch_err = ch_sta & FDMA_CH_CMD_ERR_MASK;
+	ch_sta &= FDMA_CH_CMD_STA_MASK;
+
+	if (int_sta & FDMA_INT_STA_ERR) {
+		dev_warn(fdev->dev, "chan:%d, error:%ld\n", ch_id, ch_err);
+		fchan->status = DMA_ERROR;
+		return;
+	}
+
+	switch (ch_sta) {
+	case FDMA_CH_CMD_STA_PAUSED:
+		fchan->status = DMA_PAUSED;
+		break;
+
+	case FDMA_CH_CMD_STA_RUNNING:
+		fchan->status = DMA_IN_PROGRESS;
+		break;
+	}
+}
+
+static irqreturn_t st_fdma_irq_handler(int irq, void *dev_id)
+{
+	struct st_fdma_dev *fdev = dev_id;
+	irqreturn_t ret = IRQ_NONE;
+	struct st_fdma_chan *fchan = &fdev->chans[0];
+	unsigned long int_sta, clr;
+
+	int_sta = fdma_read(fdev, FDMA_INT_STA_OFST);
+	clr = int_sta;
+
+	for (; int_sta != 0 ; int_sta >>= 2, fchan++) {
+		if (!(int_sta & (FDMA_INT_STA_CH | FDMA_INT_STA_ERR)))
+			continue;
+
+		spin_lock(&fchan->vchan.lock);
+		st_fdma_ch_sta_update(fchan, int_sta);
+
+		if (fchan->fdesc) {
+			if (!fchan->fdesc->iscyclic) {
+				list_del(&fchan->fdesc->vdesc.node);
+				vchan_cookie_complete(&fchan->fdesc->vdesc);
+				fchan->fdesc = NULL;
+				fchan->status = DMA_COMPLETE;
+			} else {
+				vchan_cyclic_callback(&fchan->fdesc->vdesc);
+			}
+
+			/* Start the next descriptor (if available) */
+			if (!fchan->fdesc)
+				st_fdma_xfer_desc(fchan);
+		}
+
+		spin_unlock(&fchan->vchan.lock);
+		ret = IRQ_HANDLED;
+	}
+
+	fdma_write(fdev, clr, FDMA_INT_CLR_OFST);
+
+	return ret;
+}
+
+static struct dma_chan *st_fdma_of_xlate(struct of_phandle_args *dma_spec,
+					 struct of_dma *ofdma)
+{
+	struct st_fdma_dev *fdev = ofdma->of_dma_data;
+	struct dma_chan *chan;
+	struct st_fdma_chan *fchan;
+	int ret;
+
+	if (dma_spec->args_count < 1)
+		return ERR_PTR(-EINVAL);
+
+	if (fdev->dma_device.dev->of_node != dma_spec->np)
+		return ERR_PTR(-EINVAL);
+
+	ret = rproc_boot(fdev->slim_rproc->rproc);
+	if (ret == -ENOENT)
+		return ERR_PTR(-EPROBE_DEFER);
+	else if (ret)
+		return ERR_PTR(ret);
+
+	chan = dma_get_any_slave_channel(&fdev->dma_device);
+	if (!chan)
+		goto err_chan;
+
+	fchan = to_st_fdma_chan(chan);
+
+	fchan->cfg.of_node = dma_spec->np;
+	fchan->cfg.req_line = dma_spec->args[0];
+	fchan->cfg.req_ctrl = 0;
+	fchan->cfg.type = ST_FDMA_TYPE_FREE_RUN;
+
+	if (dma_spec->args_count > 1)
+		fchan->cfg.req_ctrl = dma_spec->args[1]
+			& FDMA_REQ_CTRL_CFG_MASK;
+
+	if (dma_spec->args_count > 2)
+		fchan->cfg.type = dma_spec->args[2];
+
+	if (fchan->cfg.type == ST_FDMA_TYPE_FREE_RUN) {
+		fchan->dreq_line = 0;
+	} else {
+		fchan->dreq_line = st_fdma_dreq_get(fchan);
+		if (IS_ERR_VALUE(fchan->dreq_line)) {
+			chan = ERR_PTR(fchan->dreq_line);
+			goto err_chan;
+		}
+	}
+
+	dev_dbg(fdev->dev, "xlate req_line:%d type:%d req_ctrl:%#lx\n",
+		fchan->cfg.req_line, fchan->cfg.type, fchan->cfg.req_ctrl);
+
+	return chan;
+
+err_chan:
+	rproc_shutdown(fdev->slim_rproc->rproc);
+	return chan;
+
+}
+
+static void st_fdma_free_desc(struct virt_dma_desc *vdesc)
+{
+	struct st_fdma_desc *fdesc;
+	int i;
+
+	fdesc = to_st_fdma_desc(vdesc);
+	for (i = 0; i < fdesc->n_nodes; i++)
+		dma_pool_free(fdesc->fchan->node_pool, fdesc->node[i].desc,
+			      fdesc->node[i].pdesc);
+	kfree(fdesc);
+}
+
+static struct st_fdma_desc *st_fdma_alloc_desc(struct st_fdma_chan *fchan,
+					       int sg_len)
+{
+	struct st_fdma_desc *fdesc;
+	int i;
+
+	fdesc = kzalloc(sizeof(*fdesc) +
+			sizeof(struct st_fdma_sw_node) * sg_len, GFP_NOWAIT);
+	if (!fdesc)
+		return NULL;
+
+	fdesc->fchan = fchan;
+	fdesc->n_nodes = sg_len;
+	for (i = 0; i < sg_len; i++) {
+		fdesc->node[i].desc = dma_pool_alloc(fchan->node_pool,
+				GFP_NOWAIT, &fdesc->node[i].pdesc);
+		if (!fdesc->node[i].desc)
+			goto err;
+	}
+	return fdesc;
+
+err:
+	while (--i >= 0)
+		dma_pool_free(fchan->node_pool, fdesc->node[i].desc,
+			      fdesc->node[i].pdesc);
+	kfree(fdesc);
+	return NULL;
+}
+
+static int st_fdma_alloc_chan_res(struct dma_chan *chan)
+{
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+
+	/* Create the dma pool for descriptor allocation */
+	fchan->node_pool = dma_pool_create(dev_name(&chan->dev->device),
+					    fchan->fdev->dev,
+					    sizeof(struct st_fdma_hw_node),
+					    __alignof__(struct st_fdma_hw_node),
+					    0);
+
+	if (!fchan->node_pool) {
+		dev_err(fchan->fdev->dev, "unable to allocate desc pool\n");
+		return -ENOMEM;
+	}
+
+	dev_dbg(fchan->fdev->dev, "alloc ch_id:%d type:%d\n",
+		fchan->vchan.chan.chan_id, fchan->cfg.type);
+
+	return 0;
+}
+
+static void st_fdma_free_chan_res(struct dma_chan *chan)
+{
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	struct rproc *rproc = fchan->fdev->slim_rproc->rproc;
+	unsigned long flags;
+
+	LIST_HEAD(head);
+
+	dev_dbg(fchan->fdev->dev, "%s: freeing chan:%d\n",
+		__func__, fchan->vchan.chan.chan_id);
+
+	if (fchan->cfg.type != ST_FDMA_TYPE_FREE_RUN)
+		st_fdma_dreq_put(fchan);
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+	fchan->fdesc = NULL;
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+
+	dma_pool_destroy(fchan->node_pool);
+	fchan->node_pool = NULL;
+	memset(&fchan->cfg, 0, sizeof(struct st_fdma_cfg));
+
+	rproc_shutdown(rproc);
+}
+
+static struct dma_async_tx_descriptor *st_fdma_prep_dma_memcpy(
+	struct dma_chan *chan,	dma_addr_t dst, dma_addr_t src,
+	size_t len, unsigned long flags)
+{
+	struct st_fdma_chan *fchan;
+	struct st_fdma_desc *fdesc;
+	struct st_fdma_hw_node *hw_node;
+
+	if (!len)
+		return NULL;
+
+	fchan = to_st_fdma_chan(chan);
+
+	/* We only require a single descriptor */
+	fdesc = st_fdma_alloc_desc(fchan, 1);
+	if (!fdesc) {
+		dev_err(fchan->fdev->dev, "no memory for desc\n");
+		return NULL;
+	}
+
+	hw_node = fdesc->node[0].desc;
+	hw_node->next = 0;
+	hw_node->control = FDMA_NODE_CTRL_REQ_MAP_FREE_RUN;
+	hw_node->control |= FDMA_NODE_CTRL_SRC_INCR;
+	hw_node->control |= FDMA_NODE_CTRL_DST_INCR;
+	hw_node->control |= FDMA_NODE_CTRL_INT_EON;
+	hw_node->nbytes = len;
+	hw_node->saddr = src;
+	hw_node->daddr = dst;
+	hw_node->generic.length = len;
+	hw_node->generic.sstride = 0;
+	hw_node->generic.dstride = 0;
+
+	return vchan_tx_prep(&fchan->vchan, &fdesc->vdesc, flags);
+}
+
+static int config_reqctrl(struct st_fdma_chan *fchan,
+			  enum dma_transfer_direction direction)
+{
+	u32 maxburst = 0, addr = 0;
+	enum dma_slave_buswidth width;
+	int ch_id = fchan->vchan.chan.chan_id;
+	struct st_fdma_dev *fdev = fchan->fdev;
+
+	switch (direction) {
+
+	case DMA_DEV_TO_MEM:
+		fchan->cfg.req_ctrl &= ~FDMA_REQ_CTRL_WNR;
+		maxburst = fchan->scfg.src_maxburst;
+		width = fchan->scfg.src_addr_width;
+		addr = fchan->scfg.src_addr;
+		break;
+
+	case DMA_MEM_TO_DEV:
+		fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_WNR;
+		maxburst = fchan->scfg.dst_maxburst;
+		width = fchan->scfg.dst_addr_width;
+		addr = fchan->scfg.dst_addr;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	fchan->cfg.req_ctrl &= ~FDMA_REQ_CTRL_OPCODE_MASK;
+
+	switch (width) {
+
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_OPCODE_LD_ST1;
+		break;
+
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_OPCODE_LD_ST2;
+		break;
+
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_OPCODE_LD_ST4;
+		break;
+
+	case DMA_SLAVE_BUSWIDTH_8_BYTES:
+		fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_OPCODE_LD_ST8;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	fchan->cfg.req_ctrl &= ~FDMA_REQ_CTRL_NUM_OPS_MASK;
+	fchan->cfg.req_ctrl |= FDMA_REQ_CTRL_NUM_OPS(maxburst-1);
+	dreq_write(fchan, fchan->cfg.req_ctrl, FDMA_REQ_CTRL_OFST);
+
+	fchan->cfg.dev_addr = addr;
+	fchan->cfg.dir = direction;
+
+	dev_dbg(fdev->dev, "chan:%d config_reqctrl:%#x req_ctrl:%#lx\n",
+		ch_id, addr, fchan->cfg.req_ctrl);
+
+	return 0;
+}
+
+static void fill_hw_node(struct st_fdma_hw_node *hw_node,
+			struct st_fdma_chan *fchan,
+			enum dma_transfer_direction direction)
+{
+	if (direction == DMA_MEM_TO_DEV) {
+		hw_node->control |= FDMA_NODE_CTRL_SRC_INCR;
+		hw_node->control |= FDMA_NODE_CTRL_DST_STATIC;
+		hw_node->daddr = fchan->cfg.dev_addr;
+	} else {
+		hw_node->control |= FDMA_NODE_CTRL_SRC_STATIC;
+		hw_node->control |= FDMA_NODE_CTRL_DST_INCR;
+		hw_node->saddr = fchan->cfg.dev_addr;
+	}
+
+	hw_node->generic.sstride = 0;
+	hw_node->generic.dstride = 0;
+}
+
+static inline struct st_fdma_chan *st_fdma_prep_common(struct dma_chan *chan,
+		size_t len, enum dma_transfer_direction direction)
+{
+	struct st_fdma_chan *fchan;
+
+	if (!chan || !len)
+		return NULL;
+
+	fchan = to_st_fdma_chan(chan);
+
+	if (!is_slave_direction(direction)) {
+		dev_err(fchan->fdev->dev, "bad direction?\n");
+		return NULL;
+	}
+
+	return fchan;
+}
+
+static struct dma_async_tx_descriptor *st_fdma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t buf_addr, size_t len,
+		size_t period_len, enum dma_transfer_direction direction,
+		unsigned long flags)
+{
+	struct st_fdma_chan *fchan;
+	struct st_fdma_desc *fdesc;
+	int sg_len, i;
+
+	fchan = st_fdma_prep_common(chan, len, direction);
+	if (!fchan)
+		return NULL;
+
+	if (!period_len)
+		return NULL;
+
+	if (config_reqctrl(fchan, direction)) {
+		dev_err(fchan->fdev->dev, "bad width or direction\n");
+		return NULL;
+	}
+
+	/* the buffer length must be a multiple of period_len */
+	if (len % period_len != 0) {
+		dev_err(fchan->fdev->dev, "len is not multiple of period\n");
+		return NULL;
+	}
+
+	sg_len = len / period_len;
+	fdesc = st_fdma_alloc_desc(fchan, sg_len);
+	if (!fdesc) {
+		dev_err(fchan->fdev->dev, "no memory for desc\n");
+		return NULL;
+	}
+
+	fdesc->iscyclic = true;
+
+	for (i = 0; i < sg_len; i++) {
+		struct st_fdma_hw_node *hw_node = fdesc->node[i].desc;
+
+		hw_node->next = fdesc->node[(i + 1) % sg_len].pdesc;
+
+		hw_node->control =
+			FDMA_NODE_CTRL_REQ_MAP_DREQ(fchan->dreq_line);
+		hw_node->control |= FDMA_NODE_CTRL_INT_EON;
+
+		fill_hw_node(hw_node, fchan, direction);
+
+		if (direction == DMA_MEM_TO_DEV)
+			hw_node->saddr = buf_addr + (i * period_len);
+		else
+			hw_node->daddr = buf_addr + (i * period_len);
+
+		hw_node->nbytes = period_len;
+		hw_node->generic.length = period_len;
+	}
+
+	return vchan_tx_prep(&fchan->vchan, &fdesc->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *st_fdma_prep_slave_sg(
+		struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct st_fdma_chan *fchan;
+	struct st_fdma_desc *fdesc;
+	struct st_fdma_hw_node *hw_node;
+	struct scatterlist *sg;
+	int i;
+
+	fchan = st_fdma_prep_common(chan, sg_len, direction);
+	if (!fchan)
+		return NULL;
+
+	if (!sgl)
+		return NULL;
+
+	fdesc = st_fdma_alloc_desc(fchan, sg_len);
+	if (!fdesc) {
+		dev_err(fchan->fdev->dev, "no memory for desc\n");
+		return NULL;
+	}
+
+	fdesc->iscyclic = false;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		hw_node = fdesc->node[i].desc;
+
+		hw_node->next = fdesc->node[(i + 1) % sg_len].pdesc;
+		hw_node->control = FDMA_NODE_CTRL_REQ_MAP_DREQ(fchan->dreq_line);
+
+		fill_hw_node(hw_node, fchan, direction);
+
+		if (direction == DMA_MEM_TO_DEV)
+			hw_node->saddr = sg_dma_address(sg);
+		else
+			hw_node->daddr = sg_dma_address(sg);
+
+		hw_node->nbytes = sg_dma_len(sg);
+		hw_node->generic.length = sg_dma_len(sg);
+	}
+
+	/* interrupt at end of last node */
+	hw_node->control |= FDMA_NODE_CTRL_INT_EON;
+
+	return vchan_tx_prep(&fchan->vchan, &fdesc->vdesc, flags);
+}
+
+static size_t st_fdma_desc_residue(struct st_fdma_chan *fchan,
+				   struct virt_dma_desc *vdesc,
+				   bool in_progress)
+{
+	struct st_fdma_desc *fdesc = fchan->fdesc;
+	size_t residue = 0;
+	dma_addr_t cur_addr = 0;
+	int i;
+
+	if (in_progress) {
+		cur_addr = fchan_read(fchan, FDMA_CH_CMD_OFST);
+		cur_addr &= FDMA_CH_CMD_DATA_MASK;
+	}
+
+	for (i = fchan->fdesc->n_nodes - 1 ; i >= 0; i--) {
+		if (cur_addr == fdesc->node[i].pdesc) {
+			residue += fnode_read(fchan, FDMA_CNTN_OFST);
+			break;
+		}
+		residue += fdesc->node[i].desc->nbytes;
+	}
+
+	return residue;
+}
+
+static enum dma_status st_fdma_tx_status(struct dma_chan *chan,
+					 dma_cookie_t cookie,
+					 struct dma_tx_state *txstate)
+{
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+	vd = vchan_find_desc(&fchan->vchan, cookie);
+	if (fchan->fdesc && cookie == fchan->fdesc->vdesc.tx.cookie)
+		txstate->residue = st_fdma_desc_residue(fchan, vd, true);
+	else if (vd)
+		txstate->residue = st_fdma_desc_residue(fchan, vd, false);
+	else
+		txstate->residue = 0;
+
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+
+	return ret;
+}
+
+static void st_fdma_issue_pending(struct dma_chan *chan)
+{
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+
+	if (vchan_issue_pending(&fchan->vchan) && !fchan->fdesc)
+		st_fdma_xfer_desc(fchan);
+
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+}
+
+static int st_fdma_pause(struct dma_chan *chan)
+{
+	unsigned long flags;
+	LIST_HEAD(head);
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	int ch_id = fchan->vchan.chan.chan_id;
+	unsigned long cmd = FDMA_CMD_PAUSE(ch_id);
+
+	dev_dbg(fchan->fdev->dev, "pause chan:%d\n", ch_id);
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+	if (fchan->fdesc)
+		fdma_write(fchan->fdev, cmd, FDMA_CMD_SET_OFST);
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+
+	return 0;
+}
+
+static int st_fdma_resume(struct dma_chan *chan)
+{
+	unsigned long flags;
+	unsigned long val;
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	int ch_id = fchan->vchan.chan.chan_id;
+
+	dev_dbg(fchan->fdev->dev, "resume chan:%d\n", ch_id);
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+	if (fchan->fdesc) {
+		val = fchan_read(fchan, FDMA_CH_CMD_OFST);
+		val &= FDMA_CH_CMD_DATA_MASK;
+		fchan_write(fchan, val, FDMA_CH_CMD_OFST);
+	}
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+
+	return 0;
+}
+
+static int st_fdma_terminate_all(struct dma_chan *chan)
+{
+	unsigned long flags;
+	LIST_HEAD(head);
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+	int ch_id = fchan->vchan.chan.chan_id;
+	unsigned long cmd = FDMA_CMD_PAUSE(ch_id);
+
+	dev_dbg(fchan->fdev->dev, "terminate chan:%d\n", ch_id);
+
+	spin_lock_irqsave(&fchan->vchan.lock, flags);
+	fdma_write(fchan->fdev, cmd, FDMA_CMD_SET_OFST);
+	fchan->fdesc = NULL;
+	vchan_get_all_descriptors(&fchan->vchan, &head);
+	spin_unlock_irqrestore(&fchan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&fchan->vchan, &head);
+
+	return 0;
+}
+
+static int st_fdma_slave_config(struct dma_chan *chan,
+				struct dma_slave_config *slave_cfg)
+{
+	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
+
+	memcpy(&fchan->scfg, slave_cfg, sizeof(fchan->scfg));
+	return 0;
+}
+
+static const struct st_fdma_driverdata fdma_mpe31_stih407_11 = {
+	.name = "STiH407",
+	.id = 0,
+};
+
+static const struct st_fdma_driverdata fdma_mpe31_stih407_12 = {
+	.name = "STiH407",
+	.id = 1,
+};
+
+static const struct st_fdma_driverdata fdma_mpe31_stih407_13 = {
+	.name = "STiH407",
+	.id = 2,
+};
+
+static const struct of_device_id st_fdma_match[] = {
+	{ .compatible = "st,stih407-fdma-mpe31-11"
+	  , .data = &fdma_mpe31_stih407_11 },
+	{ .compatible = "st,stih407-fdma-mpe31-12"
+	  , .data = &fdma_mpe31_stih407_12 },
+	{ .compatible = "st,stih407-fdma-mpe31-13"
+	  , .data = &fdma_mpe31_stih407_13 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, st_fdma_match);
+
+static int st_fdma_parse_dt(struct platform_device *pdev,
+			const struct st_fdma_driverdata *drvdata,
+			struct st_fdma_dev *fdev)
+{
+	snprintf(fdev->fw_name, FW_NAME_SIZE, "fdma_%s_%d.elf",
+		drvdata->name, drvdata->id);
+
+	return of_property_read_u32(pdev->dev.of_node, "dma-channels",
+				    &fdev->nr_channels);
+}
+#define FDMA_DMA_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
+
+static void st_fdma_free(struct st_fdma_dev *fdev)
+{
+	struct st_fdma_chan *fchan;
+	int i;
+
+	for (i = 0; i < fdev->nr_channels; i++) {
+		fchan = &fdev->chans[i];
+		list_del(&fchan->vchan.chan.device_node);
+		tasklet_kill(&fchan->vchan.task);
+	}
+}
+
+static int st_fdma_probe(struct platform_device *pdev)
+{
+	struct st_fdma_dev *fdev;
+	const struct of_device_id *match;
+	struct device_node *np = pdev->dev.of_node;
+	const struct st_fdma_driverdata *drvdata;
+	int ret, i;
+
+	match = of_match_device((st_fdma_match), &pdev->dev);
+	if (!match || !match->data) {
+		dev_err(&pdev->dev, "No device match found\n");
+		return -ENODEV;
+	}
+
+	drvdata = match->data;
+
+	fdev = devm_kzalloc(&pdev->dev, sizeof(*fdev), GFP_KERNEL);
+	if (!fdev)
+		return -ENOMEM;
+
+	ret = st_fdma_parse_dt(pdev, drvdata, fdev);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to find platform data\n");
+		goto err;
+	}
+
+	fdev->chans = devm_kcalloc(&pdev->dev, fdev->nr_channels,
+				   sizeof(struct st_fdma_chan), GFP_KERNEL);
+	if (!fdev->chans)
+		return -ENOMEM;
+
+	fdev->dev = &pdev->dev;
+	fdev->drvdata = drvdata;
+	platform_set_drvdata(pdev, fdev);
+
+	fdev->irq = platform_get_irq(pdev, 0);
+	if (fdev->irq < 0) {
+		dev_err(&pdev->dev, "Failed to get irq resource\n");
+		return -EINVAL;
+	}
+
+	ret = devm_request_irq(&pdev->dev, fdev->irq, st_fdma_irq_handler, 0,
+			       dev_name(&pdev->dev), fdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request irq (%d)\n", ret);
+		goto err;
+	}
+
+	fdev->slim_rproc = st_slim_rproc_alloc(pdev, fdev->fw_name);
+	if (IS_ERR(fdev->slim_rproc)) {
+		ret = PTR_ERR(fdev->slim_rproc);
+		dev_err(&pdev->dev, "slim_rproc_alloc failed (%d)\n", ret);
+		goto err;
+	}
+
+	/* Initialise list of FDMA channels */
+	INIT_LIST_HEAD(&fdev->dma_device.channels);
+	for (i = 0; i < fdev->nr_channels; i++) {
+		struct st_fdma_chan *fchan = &fdev->chans[i];
+
+		fchan->fdev = fdev;
+		fchan->vchan.desc_free = st_fdma_free_desc;
+		vchan_init(&fchan->vchan, &fdev->dma_device);
+	}
+
+	/* Initialise the FDMA dreq (reserve 0 & 31 for FDMA use) */
+	fdev->dreq_mask = BIT(0) | BIT(31);
+
+	dma_cap_set(DMA_SLAVE, fdev->dma_device.cap_mask);
+	dma_cap_set(DMA_CYCLIC, fdev->dma_device.cap_mask);
+	dma_cap_set(DMA_MEMCPY, fdev->dma_device.cap_mask);
+
+	fdev->dma_device.dev = &pdev->dev;
+	fdev->dma_device.device_alloc_chan_resources = st_fdma_alloc_chan_res;
+	fdev->dma_device.device_free_chan_resources = st_fdma_free_chan_res;
+	fdev->dma_device.device_prep_dma_cyclic	= st_fdma_prep_dma_cyclic;
+	fdev->dma_device.device_prep_slave_sg = st_fdma_prep_slave_sg;
+	fdev->dma_device.device_prep_dma_memcpy = st_fdma_prep_dma_memcpy;
+	fdev->dma_device.device_tx_status = st_fdma_tx_status;
+	fdev->dma_device.device_issue_pending = st_fdma_issue_pending;
+	fdev->dma_device.device_terminate_all = st_fdma_terminate_all;
+	fdev->dma_device.device_config = st_fdma_slave_config;
+	fdev->dma_device.device_pause = st_fdma_pause;
+	fdev->dma_device.device_resume = st_fdma_resume;
+
+	fdev->dma_device.src_addr_widths = FDMA_DMA_BUSWIDTHS;
+	fdev->dma_device.dst_addr_widths = FDMA_DMA_BUSWIDTHS;
+	fdev->dma_device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	fdev->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	ret = dma_async_device_register(&fdev->dma_device);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed to register DMA device (%d)\n", ret);
+		goto err_rproc;
+	}
+
+	ret = of_dma_controller_register(np, st_fdma_of_xlate, fdev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Failed to register controller (%d)\n", ret);
+		goto err_dma_dev;
+	}
+
+	dev_info(&pdev->dev, "ST FDMA engine driver, irq:%d\n", fdev->irq);
+
+	return 0;
+
+err_dma_dev:
+	dma_async_device_unregister(&fdev->dma_device);
+err_rproc:
+	st_fdma_free(fdev);
+	st_slim_rproc_put(fdev->slim_rproc);
+err:
+	return ret;
+}
+
+static int st_fdma_remove(struct platform_device *pdev)
+{
+	struct st_fdma_dev *fdev = platform_get_drvdata(pdev);
+
+	devm_free_irq(&pdev->dev, fdev->irq, fdev);
+	st_slim_rproc_put(fdev->slim_rproc);
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&fdev->dma_device);
+
+	return 0;
+}
+
+static struct platform_driver st_fdma_platform_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = st_fdma_match,
+	},
+	.probe = st_fdma_probe,
+	.remove = st_fdma_remove,
+};
+module_platform_driver(st_fdma_platform_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("STMicroelectronics FDMA engine driver");
+MODULE_AUTHOR("Ludovic.barre <Ludovic.barre@st.com>");
+MODULE_AUTHOR("Peter Griffin <peter.griffin@linaro.org>");
+MODULE_ALIAS("platform: " DRIVER_NAME);
diff --git a/drivers/dma/st_fdma.h b/drivers/dma/st_fdma.h
new file mode 100644
index 000000000000..c58e00d4ab37
--- /dev/null
+++ b/drivers/dma/st_fdma.h
@@ -0,0 +1,249 @@
+/*
+ * DMA driver header for STMicroelectronics STi FDMA controller
+ *
+ * Copyright (C) 2014 STMicroelectronics
+ *
+ * Author: Ludovic Barre <Ludovic.barre@st.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#ifndef __DMA_ST_FDMA_H
+#define __DMA_ST_FDMA_H
+
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/io.h>
+#include <linux/remoteproc/st_slim_rproc.h>
+#include "virt-dma.h"
+
+#define ST_FDMA_NR_DREQS 32
+#define FW_NAME_SIZE 30
+#define DRIVER_NAME "st-fdma"
+
+/**
+ * struct st_fdma_generic_node - Free running/paced generic node
+ *
+ * @length: Length in bytes of a line in a 2D mem to mem
+ * @sstride: Stride, in bytes, between source lines in a 2D data move
+ * @dstride: Stride, in bytes, between destination lines in a 2D data move
+ */
+struct st_fdma_generic_node {
+	u32 length;
+	u32 sstride;
+	u32 dstride;
+};
+
+/**
+ * struct st_fdma_hw_node - Node structure used by fdma hw
+ *
+ * @next: Pointer to next node
+ * @control: Transfer Control Parameters
+ * @nbytes: Number of Bytes to read
+ * @saddr: Source address
+ * @daddr: Destination address
+ *
+ * @generic: generic node for free running/paced transfert type
+ * 2 others transfert type are possible, but not yet implemented
+ *
+ * The NODE structures must be aligned to a 32 byte boundary
+ */
+struct st_fdma_hw_node {
+	u32 next;
+	u32 control;
+	u32 nbytes;
+	u32 saddr;
+	u32 daddr;
+	union {
+		struct st_fdma_generic_node generic;
+	};
+} __aligned(32);
+
+/*
+ * node control parameters
+ */
+#define FDMA_NODE_CTRL_REQ_MAP_MASK	GENMASK(4, 0)
+#define FDMA_NODE_CTRL_REQ_MAP_FREE_RUN	0x0
+#define FDMA_NODE_CTRL_REQ_MAP_DREQ(n)	((n)&FDMA_NODE_CTRL_REQ_MAP_MASK)
+#define FDMA_NODE_CTRL_REQ_MAP_EXT		FDMA_NODE_CTRL_REQ_MAP_MASK
+#define FDMA_NODE_CTRL_SRC_MASK		GENMASK(6, 5)
+#define FDMA_NODE_CTRL_SRC_STATIC	BIT(5)
+#define FDMA_NODE_CTRL_SRC_INCR		BIT(6)
+#define FDMA_NODE_CTRL_DST_MASK		GENMASK(8, 7)
+#define FDMA_NODE_CTRL_DST_STATIC	BIT(7)
+#define FDMA_NODE_CTRL_DST_INCR		BIT(8)
+#define FDMA_NODE_CTRL_SECURE		BIT(15)
+#define FDMA_NODE_CTRL_PAUSE_EON	BIT(30)
+#define FDMA_NODE_CTRL_INT_EON		BIT(31)
+
+/**
+ * struct st_fdma_sw_node - descriptor structure for link list
+ *
+ * @pdesc: Physical address of desc
+ * @node: link used for putting this into a channel queue
+ */
+struct st_fdma_sw_node {
+	dma_addr_t pdesc;
+	struct st_fdma_hw_node *desc;
+};
+
+#define NAME_SZ 10
+
+struct st_fdma_driverdata {
+	u32 id;
+	char name[NAME_SZ];
+};
+
+struct st_fdma_desc {
+	struct virt_dma_desc vdesc;
+	struct st_fdma_chan *fchan;
+	bool iscyclic;
+	unsigned int n_nodes;
+	struct st_fdma_sw_node node[];
+};
+
+enum st_fdma_type {
+	ST_FDMA_TYPE_FREE_RUN,
+	ST_FDMA_TYPE_PACED,
+};
+
+struct st_fdma_cfg {
+	struct device_node *of_node;
+	enum st_fdma_type type;
+	dma_addr_t dev_addr;
+	enum dma_transfer_direction dir;
+	int req_line; /* request line */
+	long req_ctrl; /* Request control */
+};
+
+struct st_fdma_chan {
+	struct st_fdma_dev *fdev;
+	struct dma_pool *node_pool;
+	struct dma_slave_config scfg;
+	struct st_fdma_cfg cfg;
+
+	int dreq_line;
+
+	struct virt_dma_chan vchan;
+	struct st_fdma_desc *fdesc;
+	enum dma_status	status;
+};
+
+struct st_fdma_dev {
+	struct device *dev;
+	const struct st_fdma_driverdata *drvdata;
+	struct dma_device dma_device;
+
+	struct st_slim_rproc *slim_rproc;
+
+	int irq;
+
+	struct st_fdma_chan *chans;
+
+	spinlock_t dreq_lock;
+	unsigned long dreq_mask;
+
+	u32 nr_channels;
+	char fw_name[FW_NAME_SIZE];
+};
+
+/* Peripheral Registers*/
+
+#define FDMA_CMD_STA_OFST	0xFC0
+#define FDMA_CMD_SET_OFST	0xFC4
+#define FDMA_CMD_CLR_OFST	0xFC8
+#define FDMA_CMD_MASK_OFST	0xFCC
+#define FDMA_CMD_START(ch)		(0x1 << (ch << 1))
+#define FDMA_CMD_PAUSE(ch)		(0x2 << (ch << 1))
+#define FDMA_CMD_FLUSH(ch)		(0x3 << (ch << 1))
+
+#define FDMA_INT_STA_OFST	0xFD0
+#define FDMA_INT_STA_CH			0x1
+#define FDMA_INT_STA_ERR		0x2
+
+#define FDMA_INT_SET_OFST	0xFD4
+#define FDMA_INT_CLR_OFST	0xFD8
+#define FDMA_INT_MASK_OFST	0xFDC
+
+#define fdma_read(fdev, name) \
+	readl((fdev)->slim_rproc->peri + name)
+
+#define fdma_write(fdev, val, name) \
+	writel((val), (fdev)->slim_rproc->peri + name)
+
+/* fchan interface (dmem) */
+#define FDMA_CH_CMD_OFST	0x200
+#define FDMA_CH_CMD_STA_MASK		GENMASK(1, 0)
+#define FDMA_CH_CMD_STA_IDLE		(0x0)
+#define FDMA_CH_CMD_STA_START		(0x1)
+#define FDMA_CH_CMD_STA_RUNNING		(0x2)
+#define FDMA_CH_CMD_STA_PAUSED		(0x3)
+#define FDMA_CH_CMD_ERR_MASK		GENMASK(4, 2)
+#define FDMA_CH_CMD_ERR_INT		(0x0 << 2)
+#define FDMA_CH_CMD_ERR_NAND		(0x1 << 2)
+#define FDMA_CH_CMD_ERR_MCHI		(0x2 << 2)
+#define FDMA_CH_CMD_DATA_MASK		GENMASK(31, 5)
+#define fchan_read(fchan, name) \
+	readl((fchan)->fdev->slim_rproc->mem[ST_SLIM_DMEM].cpu_addr \
+			+ (fchan)->vchan.chan.chan_id * 0x4 \
+			+ name)
+
+#define fchan_write(fchan, val, name) \
+	writel((val), (fchan)->fdev->slim_rproc->mem[ST_SLIM_DMEM].cpu_addr \
+			+ (fchan)->vchan.chan.chan_id * 0x4 \
+			+ name)
+
+/* req interface */
+#define FDMA_REQ_CTRL_OFST	0x240
+#define dreq_write(fchan, val, name) \
+	writel((val), (fchan)->fdev->slim_rproc->mem[ST_SLIM_DMEM].cpu_addr \
+			+ fchan->dreq_line * 0x04 \
+			+ name)
+/* node interface */
+#define FDMA_NODE_SZ 128
+#define FDMA_PTRN_OFST		0x800
+#define FDMA_CNTN_OFST		0x808
+#define FDMA_SADDRN_OFST	0x80c
+#define FDMA_DADDRN_OFST	0x810
+#define fnode_read(fchan, name) \
+	readl((fchan)->fdev->slim_rproc->mem[ST_SLIM_DMEM].cpu_addr \
+			+ (fchan)->vchan.chan.chan_id * FDMA_NODE_SZ \
+			+ name)
+
+#define fnode_write(fchan, val, name) \
+	writel((val), (fchan)->fdev->slim_rproc->mem[ST_SLIM_DMEM].cpu_addr \
+			+ (fchan)->vchan.chan.chan_id * FDMA_NODE_SZ \
+			+ name)
+
+/*
+ * request control bits
+ */
+#define FDMA_REQ_CTRL_NUM_OPS_MASK	GENMASK(31, 24)
+#define FDMA_REQ_CTRL_NUM_OPS(n)	(FDMA_REQ_CTRL_NUM_OPS_MASK & \
+					((n) << 24))
+#define FDMA_REQ_CTRL_INITIATOR_MASK	BIT(22)
+#define FDMA_REQ_CTRL_INIT0		(0x0 << 22)
+#define FDMA_REQ_CTRL_INIT1		(0x1 << 22)
+#define FDMA_REQ_CTRL_INC_ADDR_ON	BIT(21)
+#define FDMA_REQ_CTRL_DATA_SWAP_ON	BIT(17)
+#define FDMA_REQ_CTRL_WNR		BIT(14)
+#define FDMA_REQ_CTRL_OPCODE_MASK	GENMASK(7, 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST1	(0x0 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST2	(0x1 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST4	(0x2 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST8	(0x3 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST16	(0x4 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST32	(0x5 << 4)
+#define FDMA_REQ_CTRL_OPCODE_LD_ST64	(0x6 << 4)
+#define FDMA_REQ_CTRL_HOLDOFF_MASK	GENMASK(2, 0)
+#define FDMA_REQ_CTRL_HOLDOFF(n)	((n) & FDMA_REQ_CTRL_HOLDOFF_MASK)
+
+/* bits used by client to configure request control */
+#define FDMA_REQ_CTRL_CFG_MASK (FDMA_REQ_CTRL_HOLDOFF_MASK | \
+				FDMA_REQ_CTRL_DATA_SWAP_ON | \
+				FDMA_REQ_CTRL_INC_ADDR_ON | \
+				FDMA_REQ_CTRL_INITIATOR_MASK)
+
+#endif	/* __DMA_ST_FDMA_H */
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index f396bfef5d42..14d5d2d43a38 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -1,20 +1,21 @@
 menu "Remoteproc drivers"
 
-# REMOTEPROC gets selected by whoever wants it
 config REMOTEPROC
-	tristate
+	tristate "Support for Remote Processor subsystem"
 	depends on HAS_DMA
 	select CRC32
 	select FW_LOADER
 	select VIRTIO
 	select VIRTUALIZATION
 
+if REMOTEPROC
+
 config OMAP_REMOTEPROC
 	tristate "OMAP remoteproc support"
 	depends on HAS_DMA
 	depends on ARCH_OMAP4 || SOC_OMAP5
 	depends on OMAP_IOMMU
-	select REMOTEPROC
+	depends on REMOTEPROC
 	select MAILBOX
 	select OMAP2PLUS_MBOX
 	select RPMSG_VIRTIO
@@ -34,7 +35,7 @@ config OMAP_REMOTEPROC
 config STE_MODEM_RPROC
 	tristate "STE-Modem remoteproc support"
 	depends on HAS_DMA
-	select REMOTEPROC
+	depends on REMOTEPROC
 	default n
 	help
 	  Say y or m here to support STE-Modem shared memory driver.
@@ -44,7 +45,7 @@ config STE_MODEM_RPROC
 config WKUP_M3_RPROC
 	tristate "AMx3xx Wakeup M3 remoteproc support"
 	depends on SOC_AM33XX || SOC_AM43XX
-	select REMOTEPROC
+	depends on REMOTEPROC
 	help
 	  Say y here to support Wakeup M3 remote processor on TI AM33xx
 	  and AM43xx family of SoCs.
@@ -57,8 +58,8 @@ config WKUP_M3_RPROC
 config DA8XX_REMOTEPROC
 	tristate "DA8xx/OMAP-L13x remoteproc support"
 	depends on ARCH_DAVINCI_DA8XX
+	depends on REMOTEPROC
 	select CMA if MMU
-	select REMOTEPROC
 	select RPMSG_VIRTIO
 	help
 	  Say y here to support DA8xx/OMAP-L13x remote processors via the
@@ -84,9 +85,9 @@ config QCOM_Q6V5_PIL
 	tristate "Qualcomm Hexagon V5 Peripherial Image Loader"
 	depends on OF && ARCH_QCOM
 	depends on QCOM_SMEM
+	depends on REMOTEPROC
 	select MFD_SYSCON
 	select QCOM_MDT_LOADER
-	select REMOTEPROC
 	help
 	  Say y here to support the Qualcomm Peripherial Image Loader for the
 	  Hexagon V5 based remote processors.
@@ -99,10 +100,10 @@ config QCOM_WCNSS_PIL
 	tristate "Qualcomm WCNSS Peripheral Image Loader"
 	depends on OF && ARCH_QCOM
 	depends on QCOM_SMEM
+	depends on REMOTEPROC
 	select QCOM_MDT_LOADER
 	select QCOM_SCM
 	select QCOM_WCNSS_IRIS
-	select REMOTEPROC
 	help
 	  Say y here to support the Peripheral Image Loader for the Qualcomm
 	  Wireless Connectivity Subsystem.
@@ -110,10 +111,16 @@ config QCOM_WCNSS_PIL
 config ST_REMOTEPROC
 	tristate "ST remoteproc support"
 	depends on ARCH_STI
-	select REMOTEPROC
+	depends on REMOTEPROC
 	help
 	  Say y here to support ST's adjunct processors via the remote
 	  processor framework.
 	  This can be either built-in or a loadable module.
 
+config ST_SLIM_REMOTEPROC
+	tristate
+	depends on REMOTEPROC
+
+endif # REMOTEPROC
+
 endmenu
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 6dfb62ed643f..924f0cb25470 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -16,3 +16,4 @@ obj-$(CONFIG_QCOM_Q6V5_PIL)		+= qcom_q6v5_pil.o
 obj-$(CONFIG_QCOM_WCNSS_IRIS)		+= qcom_wcnss_iris.o
 obj-$(CONFIG_QCOM_WCNSS_PIL)		+= qcom_wcnss.o
 obj-$(CONFIG_ST_REMOTEPROC)		+= st_remoteproc.o
+obj-$(CONFIG_ST_SLIM_REMOTEPROC)	+= st_slim_rproc.o
diff --git a/drivers/remoteproc/st_slim_rproc.c b/drivers/remoteproc/st_slim_rproc.c
new file mode 100644
index 000000000000..1484e9717946
--- /dev/null
+++ b/drivers/remoteproc/st_slim_rproc.c
@@ -0,0 +1,364 @@
+/*
+ * SLIM core rproc driver
+ *
+ * Copyright (C) 2016 STMicroelectronics
+ *
+ * Author: Peter Griffin <peter.griffin@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/remoteproc/st_slim_rproc.h>
+#include "remoteproc_internal.h"
+
+/* SLIM core registers */
+#define SLIM_ID_OFST		0x0
+#define SLIM_VER_OFST		0x4
+
+#define SLIM_EN_OFST		0x8
+#define SLIM_EN_RUN			BIT(0)
+
+#define SLIM_CLK_GATE_OFST	0xC
+#define SLIM_CLK_GATE_DIS		BIT(0)
+#define SLIM_CLK_GATE_RESET		BIT(2)
+
+#define SLIM_SLIM_PC_OFST	0x20
+
+/* DMEM registers */
+#define SLIM_REV_ID_OFST	0x0
+#define SLIM_REV_ID_MIN_MASK		GENMASK(15, 8)
+#define SLIM_REV_ID_MIN(id)		((id & SLIM_REV_ID_MIN_MASK) >> 8)
+#define SLIM_REV_ID_MAJ_MASK		GENMASK(23, 16)
+#define SLIM_REV_ID_MAJ(id)		((id & SLIM_REV_ID_MAJ_MASK) >> 16)
+
+
+/* peripherals registers */
+#define SLIM_STBUS_SYNC_OFST	0xF88
+#define SLIM_STBUS_SYNC_DIS		BIT(0)
+
+#define SLIM_INT_SET_OFST	0xFD4
+#define SLIM_INT_CLR_OFST	0xFD8
+#define SLIM_INT_MASK_OFST	0xFDC
+
+#define SLIM_CMD_CLR_OFST	0xFC8
+#define SLIM_CMD_MASK_OFST	0xFCC
+
+static const char *mem_names[ST_SLIM_MEM_MAX] = {
+	[ST_SLIM_DMEM]	= "dmem",
+	[ST_SLIM_IMEM]	= "imem",
+};
+
+static int slim_clk_get(struct st_slim_rproc *slim_rproc, struct device *dev)
+{
+	int clk, err;
+
+	for (clk = 0; clk < ST_SLIM_MAX_CLK; clk++) {
+		slim_rproc->clks[clk] = of_clk_get(dev->of_node, clk);
+		if (IS_ERR(slim_rproc->clks[clk])) {
+			err = PTR_ERR(slim_rproc->clks[clk]);
+			if (err == -EPROBE_DEFER)
+				goto err_put_clks;
+			slim_rproc->clks[clk] = NULL;
+			break;
+		}
+	}
+
+	return 0;
+
+err_put_clks:
+	while (--clk >= 0)
+		clk_put(slim_rproc->clks[clk]);
+
+	return err;
+}
+
+static void slim_clk_disable(struct st_slim_rproc *slim_rproc)
+{
+	int clk;
+
+	for (clk = 0; clk < ST_SLIM_MAX_CLK && slim_rproc->clks[clk]; clk++)
+		clk_disable_unprepare(slim_rproc->clks[clk]);
+}
+
+static int slim_clk_enable(struct st_slim_rproc *slim_rproc)
+{
+	int clk, ret;
+
+	for (clk = 0; clk < ST_SLIM_MAX_CLK && slim_rproc->clks[clk]; clk++) {
+		ret = clk_prepare_enable(slim_rproc->clks[clk]);
+		if (ret)
+			goto err_disable_clks;
+	}
+
+	return 0;
+
+err_disable_clks:
+	while (--clk >= 0)
+		clk_disable_unprepare(slim_rproc->clks[clk]);
+
+	return ret;
+}
+
+/*
+ * Remoteproc slim specific device handlers
+ */
+static int slim_rproc_start(struct rproc *rproc)
+{
+	struct device *dev = &rproc->dev;
+	struct st_slim_rproc *slim_rproc = rproc->priv;
+	unsigned long hw_id, hw_ver, fw_rev;
+	u32 val;
+
+	/* disable CPU pipeline clock & reset CPU pipeline */
+	val = SLIM_CLK_GATE_DIS | SLIM_CLK_GATE_RESET;
+	writel(val, slim_rproc->slimcore + SLIM_CLK_GATE_OFST);
+
+	/* disable SLIM core STBus sync */
+	writel(SLIM_STBUS_SYNC_DIS, slim_rproc->peri + SLIM_STBUS_SYNC_OFST);
+
+	/* enable cpu pipeline clock */
+	writel(!SLIM_CLK_GATE_DIS,
+		slim_rproc->slimcore + SLIM_CLK_GATE_OFST);
+
+	/* clear int & cmd mailbox */
+	writel(~0U, slim_rproc->peri + SLIM_INT_CLR_OFST);
+	writel(~0U, slim_rproc->peri + SLIM_CMD_CLR_OFST);
+
+	/* enable all channels cmd & int */
+	writel(~0U, slim_rproc->peri + SLIM_INT_MASK_OFST);
+	writel(~0U, slim_rproc->peri + SLIM_CMD_MASK_OFST);
+
+	/* enable cpu */
+	writel(SLIM_EN_RUN, slim_rproc->slimcore + SLIM_EN_OFST);
+
+	hw_id = readl_relaxed(slim_rproc->slimcore + SLIM_ID_OFST);
+	hw_ver = readl_relaxed(slim_rproc->slimcore + SLIM_VER_OFST);
+
+	fw_rev = readl(slim_rproc->mem[ST_SLIM_DMEM].cpu_addr +
+			SLIM_REV_ID_OFST);
+
+	dev_info(dev, "fw rev:%ld.%ld on SLIM %ld.%ld\n",
+		 SLIM_REV_ID_MAJ(fw_rev), SLIM_REV_ID_MIN(fw_rev),
+		 hw_id, hw_ver);
+
+	return 0;
+}
+
+static int slim_rproc_stop(struct rproc *rproc)
+{
+	struct st_slim_rproc *slim_rproc = rproc->priv;
+	u32 val;
+
+	/* mask all (cmd & int) channels */
+	writel(0UL, slim_rproc->peri + SLIM_INT_MASK_OFST);
+	writel(0UL, slim_rproc->peri + SLIM_CMD_MASK_OFST);
+
+	/* disable cpu pipeline clock */
+	writel(SLIM_CLK_GATE_DIS, slim_rproc->slimcore + SLIM_CLK_GATE_OFST);
+
+	writel(!SLIM_EN_RUN, slim_rproc->slimcore + SLIM_EN_OFST);
+
+	val = readl(slim_rproc->slimcore + SLIM_EN_OFST);
+	if (val & SLIM_EN_RUN)
+		dev_warn(&rproc->dev, "Failed to disable SLIM");
+
+	dev_dbg(&rproc->dev, "slim stopped\n");
+
+	return 0;
+}
+
+static void *slim_rproc_da_to_va(struct rproc *rproc, u64 da, int len)
+{
+	struct st_slim_rproc *slim_rproc = rproc->priv;
+	void *va = NULL;
+	int i;
+
+	for (i = 0; i < ST_SLIM_MEM_MAX; i++) {
+		if (da != slim_rproc->mem[i].bus_addr)
+			continue;
+
+		if (len <= slim_rproc->mem[i].size) {
+			/* __force to make sparse happy with type conversion */
+			va = (__force void *)slim_rproc->mem[i].cpu_addr;
+			break;
+		}
+	}
+
+	dev_dbg(&rproc->dev, "da = 0x%llx len = 0x%x va = 0x%p\n", da, len, va);
+
+	return va;
+}
+
+static struct rproc_ops slim_rproc_ops = {
+	.start		= slim_rproc_start,
+	.stop		= slim_rproc_stop,
+	.da_to_va       = slim_rproc_da_to_va,
+};
+
+/*
+ * Firmware handler operations: sanity, boot address, load ...
+ */
+
+static struct resource_table empty_rsc_tbl = {
+	.ver = 1,
+	.num = 0,
+};
+
+static struct resource_table *slim_rproc_find_rsc_table(struct rproc *rproc,
+					       const struct firmware *fw,
+					       int *tablesz)
+{
+	*tablesz = sizeof(empty_rsc_tbl);
+	return &empty_rsc_tbl;
+}
+
+static struct rproc_fw_ops slim_rproc_fw_ops = {
+	.find_rsc_table = slim_rproc_find_rsc_table,
+};
+
+/**
+ * st_slim_rproc_alloc() - allocate and initialise slim rproc
+ * @pdev: Pointer to the platform_device struct
+ * @fw_name: Name of firmware for rproc to use
+ *
+ * Function for allocating and initialising a slim rproc for use by
+ * device drivers whose IP is based around the SLIM core. It
+ * obtains and enables any clocks required by the SLIM core and also
+ * ioremaps the various IO.
+ *
+ * Returns st_slim_rproc pointer or PTR_ERR() on error.
+ */
+
+struct st_slim_rproc *st_slim_rproc_alloc(struct platform_device *pdev,
+				char *fw_name)
+{
+	struct device *dev = &pdev->dev;
+	struct st_slim_rproc *slim_rproc;
+	struct device_node *np = dev->of_node;
+	struct rproc *rproc;
+	struct resource *res;
+	int err, i;
+	const struct rproc_fw_ops *elf_ops;
+
+	if (!fw_name)
+		return ERR_PTR(-EINVAL);
+
+	if (!of_device_is_compatible(np, "st,slim-rproc"))
+		return ERR_PTR(-EINVAL);
+
+	rproc = rproc_alloc(dev, np->name, &slim_rproc_ops,
+			fw_name, sizeof(*slim_rproc));
+	if (!rproc)
+		return ERR_PTR(-ENOMEM);
+
+	rproc->has_iommu = false;
+
+	slim_rproc = rproc->priv;
+	slim_rproc->rproc = rproc;
+
+	elf_ops = rproc->fw_ops;
+	/* Use some generic elf ops */
+	slim_rproc_fw_ops.load = elf_ops->load;
+	slim_rproc_fw_ops.sanity_check = elf_ops->sanity_check;
+
+	rproc->fw_ops = &slim_rproc_fw_ops;
+
+	/* get imem and dmem */
+	for (i = 0; i < ARRAY_SIZE(mem_names); i++) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						mem_names[i]);
+
+		slim_rproc->mem[i].cpu_addr = devm_ioremap_resource(dev, res);
+		if (IS_ERR(slim_rproc->mem[i].cpu_addr)) {
+			dev_err(&pdev->dev, "devm_ioremap_resource failed\n");
+			err = PTR_ERR(slim_rproc->mem[i].cpu_addr);
+			goto err;
+		}
+		slim_rproc->mem[i].bus_addr = res->start;
+		slim_rproc->mem[i].size = resource_size(res);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "slimcore");
+	slim_rproc->slimcore = devm_ioremap_resource(dev, res);
+	if (IS_ERR(slim_rproc->slimcore)) {
+		dev_err(&pdev->dev, "failed to ioremap slimcore IO\n");
+		err = PTR_ERR(slim_rproc->slimcore);
+		goto err;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "peripherals");
+	slim_rproc->peri = devm_ioremap_resource(dev, res);
+	if (IS_ERR(slim_rproc->peri)) {
+		dev_err(&pdev->dev, "failed to ioremap peripherals IO\n");
+		err = PTR_ERR(slim_rproc->peri);
+		goto err;
+	}
+
+	err = slim_clk_get(slim_rproc, dev);
+	if (err)
+		goto err;
+
+	err = slim_clk_enable(slim_rproc);
+	if (err) {
+		dev_err(dev, "Failed to enable clocks\n");
+		goto err_clk_put;
+	}
+
+	/* Register as a remoteproc device */
+	err = rproc_add(rproc);
+	if (err) {
+		dev_err(dev, "registration of slim remoteproc failed\n");
+		goto err_clk_dis;
+	}
+
+	return slim_rproc;
+
+err_clk_dis:
+	slim_clk_disable(slim_rproc);
+err_clk_put:
+	for (i = 0; i < ST_SLIM_MAX_CLK && slim_rproc->clks[i]; i++)
+		clk_put(slim_rproc->clks[i]);
+err:
+	rproc_put(rproc);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(st_slim_rproc_alloc);
+
+/**
+  * st_slim_rproc_put() - put slim rproc resources
+  * @slim_rproc: Pointer to the st_slim_rproc struct
+  *
+  * Function for calling respective _put() functions on slim_rproc resources.
+  *
+  */
+void st_slim_rproc_put(struct st_slim_rproc *slim_rproc)
+{
+	int clk;
+
+	if (!slim_rproc)
+		return;
+
+	slim_clk_disable(slim_rproc);
+
+	for (clk = 0; clk < ST_SLIM_MAX_CLK && slim_rproc->clks[clk]; clk++)
+		clk_put(slim_rproc->clks[clk]);
+
+	rproc_del(slim_rproc->rproc);
+	rproc_put(slim_rproc->rproc);
+}
+EXPORT_SYMBOL(st_slim_rproc_put);
+
+MODULE_AUTHOR("Peter Griffin <peter.griffin@linaro.org>");
+MODULE_DESCRIPTION("STMicroelectronics SLIM core rproc driver");
+MODULE_LICENSE("GPL v2");