Merge tag 'dmaengine-fix-4.3-rc4' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine fixes from Vinod Koul:
 "This contains fixes spread throughout the drivers, and also fixes one
  more instance of privatecnt in dmaengine.

  Driver fixes summary:
   - bunch of pxa_dma fixes for reuse of descriptor issue, residue and
     no-requestor
   - odd fixes in xgene, idma, sun4i and zxdma
   - at_xdmac fixes for cleaning descriptor and block addr mode"

* tag 'dmaengine-fix-4.3-rc4' of git://git.infradead.org/users/vkoul/slave-dma:
  dmaengine: pxa_dma: fix residue corner case
  dmaengine: pxa_dma: fix the no-requestor case
  dmaengine: zxdma: Fix off-by-one for testing valid pchan request
  dmaengine: at_xdmac: clean used descriptor
  dmaengine: at_xdmac: change block increment addressing mode
  dmaengine: dw: properly read DWC_PARAMS register
  dmaengine: xgene-dma: Fix overwritting DMA tx ring
  dmaengine: fix balance of privatecnt
  dmaengine: sun4i: fix unsafe list iteration
  dmaengine: idma64: improve residue estimation
  dmaengine: xgene-dma: fix handling xgene_dma_get_ring_size result
  dmaengine: pxa_dma: fix initial list move

8 files changed, 77 insertions, 53 deletions

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index a165b4bfd330..dd24375b76dd 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -455,6 +455,15 @@ static struct at_xdmac_desc *at_xdmac_alloc_desc(struct dma_chan *chan,
 	return desc;
 }
 
+void at_xdmac_init_used_desc(struct at_xdmac_desc *desc)
+{
+	memset(&desc->lld, 0, sizeof(desc->lld));
+	INIT_LIST_HEAD(&desc->descs_list);
+	desc->direction = DMA_TRANS_NONE;
+	desc->xfer_size = 0;
+	desc->active_xfer = false;
+}
+
 /* Call must be protected by lock. */
 static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
 {
@@ -466,7 +475,7 @@ static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
 		desc = list_first_entry(&atchan->free_descs_list,
 					struct at_xdmac_desc, desc_node);
 		list_del(&desc->desc_node);
-		desc->active_xfer = false;
+		at_xdmac_init_used_desc(desc);
 	}
 
 	return desc;
@@ -875,14 +884,14 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 
 	if (xt->src_inc) {
 		if (xt->src_sgl)
-			chan_cc |=  AT_XDMAC_CC_SAM_UBS_DS_AM;
+			chan_cc |=  AT_XDMAC_CC_SAM_UBS_AM;
 		else
 			chan_cc |=  AT_XDMAC_CC_SAM_INCREMENTED_AM;
 	}
 
 	if (xt->dst_inc) {
 		if (xt->dst_sgl)
-			chan_cc |=  AT_XDMAC_CC_DAM_UBS_DS_AM;
+			chan_cc |=  AT_XDMAC_CC_DAM_UBS_AM;
 		else
 			chan_cc |=  AT_XDMAC_CC_DAM_INCREMENTED_AM;
 	}
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 3ff284c8e3d5..09479d4be4db 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -554,10 +554,18 @@ struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
 	mutex_lock(&dma_list_mutex);
 
 	if (chan->client_count == 0) {
+		struct dma_device *device = chan->device;
+
+		dma_cap_set(DMA_PRIVATE, device->cap_mask);
+		device->privatecnt++;
 		err = dma_chan_get(chan);
-		if (err)
+		if (err) {
 			pr_debug("%s: failed to get %s: (%d)\n",
 				__func__, dma_chan_name(chan), err);
+			chan = NULL;
+			if (--device->privatecnt == 0)
+				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
+		}
 	} else
 		chan = NULL;
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index cf1c87fa1edd..bedce038c6e2 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1591,7 +1591,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
-		int			r = nr_channels - i - 1;
 
 		dwc->chan.device = &dw->dma;
 		dma_cookie_init(&dwc->chan);
@@ -1603,7 +1602,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = r;
+			dwc->priority = nr_channels - i - 1;
 		else
 			dwc->priority = i;
 
@@ -1622,6 +1621,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 		/* Hardware configuration */
 		if (autocfg) {
 			unsigned int dwc_params;
+			unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
 			void __iomem *addr = chip->regs + r * sizeof(u32);
 
 			dwc_params = dma_read_byaddr(addr, DWC_PARAMS);
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 18c14e1f1414..48d6d9e94f67 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -355,23 +355,23 @@ static size_t idma64_active_desc_size(struct idma64_chan *idma64c)
 	struct idma64_desc *desc = idma64c->desc;
 	struct idma64_hw_desc *hw;
 	size_t bytes = desc->length;
-	u64 llp;
-	u32 ctlhi;
+	u64 llp = channel_readq(idma64c, LLP);
+	u32 ctlhi = channel_readl(idma64c, CTL_HI);
 	unsigned int i = 0;
 
-	llp = channel_readq(idma64c, LLP);
 	do {
 		hw = &desc->hw[i];
-	} while ((hw->llp != llp) && (++i < desc->ndesc));
+		if (hw->llp == llp)
+			break;
+		bytes -= hw->len;
+	} while (++i < desc->ndesc);
 
 	if (!i)
 		return bytes;
 
-	do {
-		bytes -= desc->hw[--i].len;
-	} while (i);
+	/* The current chunk is not fully transfered yet */
+	bytes += desc->hw[--i].len;
 
-	ctlhi = channel_readl(idma64c, CTL_HI);
 	return bytes - IDMA64C_CTLH_BLOCK_TS(ctlhi);
 }
 
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 5cb61ce01036..fc4156afa070 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -473,8 +473,10 @@ static void pxad_free_phy(struct pxad_chan *chan)
 		return;
 
 	/* clear the channel mapping in DRCMR */
-	reg = pxad_drcmr(chan->drcmr);
-	writel_relaxed(0, chan->phy->base + reg);
+	if (chan->drcmr <= DRCMR_CHLNUM) {
+		reg = pxad_drcmr(chan->drcmr);
+		writel_relaxed(0, chan->phy->base + reg);
+	}
 
 	spin_lock_irqsave(&pdev->phy_lock, flags);
 	for (i = 0; i < 32; i++)
@@ -516,8 +518,10 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned)
 		"%s(); phy=%p(%d) misaligned=%d\n", __func__,
 		phy, phy->idx, misaligned);
 
-	reg = pxad_drcmr(phy->vchan->drcmr);
-	writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+	if (phy->vchan->drcmr <= DRCMR_CHLNUM) {
+		reg = pxad_drcmr(phy->vchan->drcmr);
+		writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
+	}
 
 	dalgn = phy_readl_relaxed(phy, DALGN);
 	if (misaligned)
@@ -887,6 +891,7 @@ pxad_tx_prep(struct virt_dma_chan *vc, struct virt_dma_desc *vd,
 	struct dma_async_tx_descriptor *tx;
 	struct pxad_chan *chan = container_of(vc, struct pxad_chan, vc);
 
+	INIT_LIST_HEAD(&vd->node);
 	tx = vchan_tx_prep(vc, vd, tx_flags);
 	tx->tx_submit = pxad_tx_submit;
 	dev_dbg(&chan->vc.chan.dev->device,
@@ -910,14 +915,18 @@ static void pxad_get_config(struct pxad_chan *chan,
 		width = chan->cfg.src_addr_width;
 		dev_addr = chan->cfg.src_addr;
 		*dev_src = dev_addr;
-		*dcmd |= PXA_DCMD_INCTRGADDR | PXA_DCMD_FLOWSRC;
+		*dcmd |= PXA_DCMD_INCTRGADDR;
+		if (chan->drcmr <= DRCMR_CHLNUM)
+			*dcmd |= PXA_DCMD_FLOWSRC;
 	}
 	if (dir == DMA_MEM_TO_DEV) {
 		maxburst = chan->cfg.dst_maxburst;
 		width = chan->cfg.dst_addr_width;
 		dev_addr = chan->cfg.dst_addr;
 		*dev_dst = dev_addr;
-		*dcmd |= PXA_DCMD_INCSRCADDR | PXA_DCMD_FLOWTRG;
+		*dcmd |= PXA_DCMD_INCSRCADDR;
+		if (chan->drcmr <= DRCMR_CHLNUM)
+			*dcmd |= PXA_DCMD_FLOWTRG;
 	}
 	if (dir == DMA_MEM_TO_MEM)
 		*dcmd |= PXA_DCMD_BURST32 | PXA_DCMD_INCTRGADDR |
@@ -1177,6 +1186,16 @@ static unsigned int pxad_residue(struct pxad_chan *chan,
 	else
 		curr = phy_readl_relaxed(chan->phy, DTADR);
 
+	/*
+	 * curr has to be actually read before checking descriptor
+	 * completion, so that a curr inside a status updater
+	 * descriptor implies the following test returns true, and
+	 * preventing reordering of curr load and the test.
+	 */
+	rmb();
+	if (is_desc_completed(vd))
+		goto out;
+
 	for (i = 0; i < sw_desc->nb_desc - 1; i++) {
 		hw_desc = sw_desc->hw_desc[i];
 		if (sw_desc->hw_desc[0]->dcmd & PXA_DCMD_INCSRCADDR)
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index a1a500d96ff2..1661d518224a 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -599,13 +599,13 @@ get_next_cyclic_promise(struct sun4i_dma_contract *contract)
 static void sun4i_dma_free_contract(struct virt_dma_desc *vd)
 {
 	struct sun4i_dma_contract *contract = to_sun4i_dma_contract(vd);
-	struct sun4i_dma_promise *promise;
+	struct sun4i_dma_promise *promise, *tmp;
 
 	/* Free all the demands and completed demands */
-	list_for_each_entry(promise, &contract->demands, list)
+	list_for_each_entry_safe(promise, tmp, &contract->demands, list)
 		kfree(promise);
 
-	list_for_each_entry(promise, &contract->completed_demands, list)
+	list_for_each_entry_safe(promise, tmp, &contract->completed_demands, list)
 		kfree(promise);
 
 	kfree(contract);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index b23e8d52d126..8d57b1b12e41 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -59,7 +59,6 @@
 #define XGENE_DMA_RING_MEM_RAM_SHUTDOWN		0xD070
 #define XGENE_DMA_RING_BLK_MEM_RDY		0xD074
 #define XGENE_DMA_RING_BLK_MEM_RDY_VAL		0xFFFFFFFF
-#define XGENE_DMA_RING_DESC_CNT(v)		(((v) & 0x0001FFFE) >> 1)
 #define XGENE_DMA_RING_ID_GET(owner, num)	(((owner) << 6) | (num))
 #define XGENE_DMA_RING_DST_ID(v)		((1 << 10) | (v))
 #define XGENE_DMA_RING_CMD_OFFSET		0x2C
@@ -379,14 +378,6 @@ static u8 xgene_dma_encode_xor_flyby(u32 src_cnt)
 	return flyby_type[src_cnt];
 }
 
-static u32 xgene_dma_ring_desc_cnt(struct xgene_dma_ring *ring)
-{
-	u32 __iomem *cmd_base = ring->cmd_base;
-	u32 ring_state = ioread32(&cmd_base[1]);
-
-	return XGENE_DMA_RING_DESC_CNT(ring_state);
-}
-
 static void xgene_dma_set_src_buffer(__le64 *ext8, size_t *len,
 				     dma_addr_t *paddr)
 {
@@ -659,15 +650,12 @@ static void xgene_dma_clean_running_descriptor(struct xgene_dma_chan *chan,
 	dma_pool_free(chan->desc_pool, desc, desc->tx.phys);
 }
 
-static int xgene_chan_xfer_request(struct xgene_dma_ring *ring,
-				   struct xgene_dma_desc_sw *desc_sw)
+static void xgene_chan_xfer_request(struct xgene_dma_chan *chan,
+				    struct xgene_dma_desc_sw *desc_sw)
 {
+	struct xgene_dma_ring *ring = &chan->tx_ring;
 	struct xgene_dma_desc_hw *desc_hw;
 
-	/* Check if can push more descriptor to hw for execution */
-	if (xgene_dma_ring_desc_cnt(ring) > (ring->slots - 2))
-		return -EBUSY;
-
 	/* Get hw descriptor from DMA tx ring */
 	desc_hw = &ring->desc_hw[ring->head];
 
@@ -694,11 +682,13 @@ static int xgene_chan_xfer_request(struct xgene_dma_ring *ring,
 		memcpy(desc_hw, &desc_sw->desc2, sizeof(*desc_hw));
 	}
 
+	/* Increment the pending transaction count */
+	chan->pending += ((desc_sw->flags &
+			  XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
+
 	/* Notify the hw that we have descriptor ready for execution */
 	iowrite32((desc_sw->flags & XGENE_DMA_FLAG_64B_DESC) ?
 		  2 : 1, ring->cmd);
-
-	return 0;
 }
 
 /**
@@ -710,7 +700,6 @@ static int xgene_chan_xfer_request(struct xgene_dma_ring *ring,
 static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan)
 {
 	struct xgene_dma_desc_sw *desc_sw, *_desc_sw;
-	int ret;
 
 	/*
 	 * If the list of pending descriptors is empty, then we
@@ -735,18 +724,13 @@ static void xgene_chan_xfer_ld_pending(struct xgene_dma_chan *chan)
 		if (chan->pending >= chan->max_outstanding)
 			return;
 
-		ret = xgene_chan_xfer_request(&chan->tx_ring, desc_sw);
-		if (ret)
-			return;
+		xgene_chan_xfer_request(chan, desc_sw);
 
 		/*
 		 * Delete this element from ld pending queue and append it to
 		 * ld running queue
 		 */
 		list_move_tail(&desc_sw->node, &chan->ld_running);
-
-		/* Increment the pending transaction count */
-		chan->pending++;
 	}
 }
 
@@ -821,7 +805,8 @@ static void xgene_dma_cleanup_descriptors(struct xgene_dma_chan *chan)
 		 * Decrement the pending transaction count
 		 * as we have processed one
 		 */
-		chan->pending--;
+		chan->pending -= ((desc_sw->flags &
+				  XGENE_DMA_FLAG_64B_DESC) ? 2 : 1);
 
 		/*
 		 * Delete this node from ld running queue and append it to
@@ -1421,15 +1406,18 @@ static int xgene_dma_create_ring_one(struct xgene_dma_chan *chan,
 				     struct xgene_dma_ring *ring,
 				     enum xgene_dma_ring_cfgsize cfgsize)
 {
+	int ret;
+
 	/* Setup DMA ring descriptor variables */
 	ring->pdma = chan->pdma;
 	ring->cfgsize = cfgsize;
 	ring->num = chan->pdma->ring_num++;
 	ring->id = XGENE_DMA_RING_ID_GET(ring->owner, ring->buf_num);
 
-	ring->size = xgene_dma_get_ring_size(chan, cfgsize);
-	if (ring->size <= 0)
-		return ring->size;
+	ret = xgene_dma_get_ring_size(chan, cfgsize);
+	if (ret <= 0)
+		return ret;
+	ring->size = ret;
 
 	/* Allocate memory for DMA ring descriptor */
 	ring->desc_vaddr = dma_zalloc_coherent(chan->dev, ring->size,
@@ -1482,7 +1470,7 @@ static int xgene_dma_create_chan_rings(struct xgene_dma_chan *chan)
 		 tx_ring->id, tx_ring->num, tx_ring->desc_vaddr);
 
 	/* Set the max outstanding request possible to this channel */
-	chan->max_outstanding = rx_ring->slots;
+	chan->max_outstanding = tx_ring->slots;
 
 	return ret;
 }
diff --git a/drivers/dma/zx296702_dma.c b/drivers/dma/zx296702_dma.c
index 39915a6b7986..c017fcd8e07c 100644
--- a/drivers/dma/zx296702_dma.c
+++ b/drivers/dma/zx296702_dma.c
@@ -739,7 +739,7 @@ static struct dma_chan *zx_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
 	struct dma_chan *chan;
 	struct zx_dma_chan *c;
 
-	if (request > d->dma_requests)
+	if (request >= d->dma_requests)
 		return NULL;
 
 	chan = dma_get_any_slave_channel(&d->slave);