Merge tag 'dmaengine-fix-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine fixes from Vinod Koul:
 "Driver fixes for:

   - stm32 dma residue calculation and chaining

   - stm32 mdma for setting inflight bytes, residue calculation and
     resume abort

   - channel request, channel enable and dma error in fsl_edma

   - runtime pm imbalance in ste_dma40 driver

   - deadlock fix in mediatek driver"

* tag 'dmaengine-fix-6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine:
  dmaengine: fsl-edma: fix all channels requested when call fsl_edma3_xlate()
  dmaengine: stm32-dma: fix residue in case of MDMA chaining
  dmaengine: stm32-dma: fix stm32_dma_prep_slave_sg in case of MDMA chaining
  dmaengine: stm32-mdma: set in_flight_bytes in case CRQA flag is set
  dmaengine: stm32-mdma: use Link Address Register to compute residue
  dmaengine: stm32-mdma: abort resume if no ongoing transfer
  dmaengine: ste_dma40: Fix PM disable depth imbalance in d40_probe
  dmaengine: mediatek: Fix deadlock caused by synchronize_irq()
  dmaengine: idxd: use spin_lock_irqsave before wait_event_lock_irq
  dmaengine: fsl-edma: fix edma4 channel enable failure on second attempt
  dt-bindings: dmaengine: zynqmp_dma: add xlnx,bus-width required property
  dmaengine: fsl-dma: fix DMA error when enabling sg if 'DONE' bit is set

9 files changed, 79 insertions, 24 deletions

diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml
index 23ada8f87526..769ce23aaac2 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml
+++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml
@@ -13,6 +13,8 @@ description: |
 
 maintainers:
   - Michael Tretter <m.tretter@pengutronix.de>
+  - Harini Katakam <harini.katakam@amd.com>
+  - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
 
 allOf:
   - $ref: ../dma-controller.yaml#
@@ -65,6 +67,7 @@ required:
   - interrupts
   - clocks
   - clock-names
+  - xlnx,bus-width
 
 additionalProperties: false
 
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index a0f5741abcc4..6a3abe5b1790 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -92,8 +92,14 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
 
 	edma_writel_chreg(fsl_chan, val, ch_sbr);
 
-	if (flags & FSL_EDMA_DRV_HAS_CHMUX)
-		edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux);
+	if (flags & FSL_EDMA_DRV_HAS_CHMUX) {
+		/*
+		 * ch_mux: With the exception of 0, attempts to write a value
+		 * already in use will be forced to 0.
+		 */
+		if (!edma_readl_chreg(fsl_chan, ch_mux))
+			edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux);
+	}
 
 	val = edma_readl_chreg(fsl_chan, ch_csr);
 	val |= EDMA_V3_CH_CSR_ERQ;
@@ -448,12 +454,25 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 
 	edma_write_tcdreg(fsl_chan, tcd->dlast_sga, dlast_sga);
 
+	csr = le16_to_cpu(tcd->csr);
+
 	if (fsl_chan->is_sw) {
-		csr = le16_to_cpu(tcd->csr);
 		csr |= EDMA_TCD_CSR_START;
 		tcd->csr = cpu_to_le16(csr);
 	}
 
+	/*
+	 * Must clear CHn_CSR[DONE] bit before enable TCDn_CSR[ESG] at EDMAv3
+	 * eDMAv4 have not such requirement.
+	 * Change MLINK need clear CHn_CSR[DONE] for both eDMAv3 and eDMAv4.
+	 */
+	if (((fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_CLEAR_DONE_E_SG) &&
+		(csr & EDMA_TCD_CSR_E_SG)) ||
+	    ((fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_CLEAR_DONE_E_LINK) &&
+		(csr & EDMA_TCD_CSR_E_LINK)))
+		edma_writel_chreg(fsl_chan, edma_readl_chreg(fsl_chan, ch_csr), ch_csr);
+
+
 	edma_write_tcdreg(fsl_chan, tcd->csr, csr);
 }
 
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 3cc0cc8fc2d0..40d50cc3d75a 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -183,11 +183,23 @@ struct fsl_edma_desc {
 #define FSL_EDMA_DRV_BUS_8BYTE		BIT(10)
 #define FSL_EDMA_DRV_DEV_TO_DEV		BIT(11)
 #define FSL_EDMA_DRV_ALIGN_64BYTE	BIT(12)
+/* Need clean CHn_CSR DONE before enable TCD's ESG */
+#define FSL_EDMA_DRV_CLEAR_DONE_E_SG	BIT(13)
+/* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */
+#define FSL_EDMA_DRV_CLEAR_DONE_E_LINK	BIT(14)
 
 #define FSL_EDMA_DRV_EDMA3	(FSL_EDMA_DRV_SPLIT_REG |	\
 				 FSL_EDMA_DRV_BUS_8BYTE |	\
 				 FSL_EDMA_DRV_DEV_TO_DEV |	\
-				 FSL_EDMA_DRV_ALIGN_64BYTE)
+				 FSL_EDMA_DRV_ALIGN_64BYTE |	\
+				 FSL_EDMA_DRV_CLEAR_DONE_E_SG |	\
+				 FSL_EDMA_DRV_CLEAR_DONE_E_LINK)
+
+#define FSL_EDMA_DRV_EDMA4	(FSL_EDMA_DRV_SPLIT_REG |	\
+				 FSL_EDMA_DRV_BUS_8BYTE |	\
+				 FSL_EDMA_DRV_DEV_TO_DEV |	\
+				 FSL_EDMA_DRV_ALIGN_64BYTE |	\
+				 FSL_EDMA_DRV_CLEAR_DONE_E_LINK)
 
 struct fsl_edma_drvdata {
 	u32			dmamuxs; /* only used before v3 */
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 63d48d046f04..8c4ed7012e23 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -154,18 +154,20 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		fsl_chan = to_fsl_edma_chan(chan);
 		i = fsl_chan - fsl_edma->chans;
 
-		chan = dma_get_slave_channel(chan);
-		chan->device->privatecnt++;
 		fsl_chan->priority = dma_spec->args[1];
 		fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX;
 		fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
 		fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
 
 		if (!b_chmux && i == dma_spec->args[0]) {
+			chan = dma_get_slave_channel(chan);
+			chan->device->privatecnt++;
 			mutex_unlock(&fsl_edma->fsl_edma_mutex);
 			return chan;
 		} else if (b_chmux && !fsl_chan->srcid) {
 			/* if controller support channel mux, choose a free channel */
+			chan = dma_get_slave_channel(chan);
+			chan->device->privatecnt++;
 			fsl_chan->srcid = dma_spec->args[0];
 			mutex_unlock(&fsl_edma->fsl_edma_mutex);
 			return chan;
@@ -355,7 +357,7 @@ static struct fsl_edma_drvdata imx93_data3 = {
 };
 
 static struct fsl_edma_drvdata imx93_data4 = {
-	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3,
+	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
 	.setup_irq = fsl_edma3_irq_init,
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 22d6f4e455b7..8f754f922217 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -477,6 +477,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	union idxd_command_reg cmd;
 	DECLARE_COMPLETION_ONSTACK(done);
 	u32 stat;
+	unsigned long flags;
 
 	if (idxd_device_is_halted(idxd)) {
 		dev_warn(&idxd->pdev->dev, "Device is HALTED!\n");
@@ -490,7 +491,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	cmd.operand = operand;
 	cmd.int_req = 1;
 
-	spin_lock(&idxd->cmd_lock);
+	spin_lock_irqsave(&idxd->cmd_lock, flags);
 	wait_event_lock_irq(idxd->cmd_waitq,
 			    !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags),
 			    idxd->cmd_lock);
@@ -507,7 +508,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand,
 	 * After command submitted, release lock and go to sleep until
 	 * the command completes via interrupt.
 	 */
-	spin_unlock(&idxd->cmd_lock);
+	spin_unlock_irqrestore(&idxd->cmd_lock, flags);
 	wait_for_completion(&done);
 	stat = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET);
 	spin_lock(&idxd->cmd_lock);
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index c51dc017b48a..06d12ac39144 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -450,9 +450,8 @@ static int mtk_uart_apdma_device_pause(struct dma_chan *chan)
 	mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B);
 	mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B);
 
-	synchronize_irq(c->irq);
-
 	spin_unlock_irqrestore(&c->vc.lock, flags);
+	synchronize_irq(c->irq);
 
 	return 0;
 }
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 89e82508c133..002833fb1fa0 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3668,6 +3668,7 @@ static int __init d40_probe(struct platform_device *pdev)
 		regulator_disable(base->lcpa_regulator);
 		regulator_put(base->lcpa_regulator);
 	}
+	pm_runtime_disable(base->dev);
 
  report_failure:
 	d40_err(dev, "probe failed\n");
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 5c36811aa134..0b30151fb45c 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -1113,8 +1113,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg(
 		chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL;
 
 	/* Activate Double Buffer Mode if DMA triggers STM32 MDMA and more than 1 sg */
-	if (chan->trig_mdma && sg_len > 1)
+	if (chan->trig_mdma && sg_len > 1) {
 		chan->chan_reg.dma_scr |= STM32_DMA_SCR_DBM;
+		chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_CT;
+	}
 
 	for_each_sg(sgl, sg, sg_len, i) {
 		ret = stm32_dma_set_xfer_param(chan, direction, &buswidth,
@@ -1387,11 +1389,12 @@ static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
 
 	residue = stm32_dma_get_remaining_bytes(chan);
 
-	if (chan->desc->cyclic && !stm32_dma_is_current_sg(chan)) {
+	if ((chan->desc->cyclic || chan->trig_mdma) && !stm32_dma_is_current_sg(chan)) {
 		n_sg++;
 		if (n_sg == chan->desc->num_sgs)
 			n_sg = 0;
-		residue = sg_req->len;
+		if (!chan->trig_mdma)
+			residue = sg_req->len;
 	}
 
 	/*
@@ -1401,7 +1404,7 @@ static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan,
 	 * residue = remaining bytes from NDTR + remaining
 	 * periods/sg to be transferred
 	 */
-	if (!chan->desc->cyclic || n_sg != 0)
+	if ((!chan->desc->cyclic && !chan->trig_mdma) || n_sg != 0)
 		for (i = n_sg; i < desc->num_sgs; i++)
 			residue += desc->sg_req[i].len;
 
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 0de234022c6d..bae08b3f55c7 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -777,8 +777,6 @@ static int stm32_mdma_setup_xfer(struct stm32_mdma_chan *chan,
 	/* Enable interrupts */
 	ccr &= ~STM32_MDMA_CCR_IRQ_MASK;
 	ccr |= STM32_MDMA_CCR_TEIE | STM32_MDMA_CCR_CTCIE;
-	if (sg_len > 1)
-		ccr |= STM32_MDMA_CCR_BTIE;
 	desc->ccr = ccr;
 
 	return 0;
@@ -1236,6 +1234,10 @@ static int stm32_mdma_resume(struct dma_chan *c)
 	unsigned long flags;
 	u32 status, reg;
 
+	/* Transfer can be terminated */
+	if (!chan->desc || (stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & STM32_MDMA_CCR_EN))
+		return -EPERM;
+
 	hwdesc = chan->desc->node[chan->curr_hwdesc].hwdesc;
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
@@ -1316,21 +1318,35 @@ static int stm32_mdma_slave_config(struct dma_chan *c,
 
 static size_t stm32_mdma_desc_residue(struct stm32_mdma_chan *chan,
 				      struct stm32_mdma_desc *desc,
-				      u32 curr_hwdesc)
+				      u32 curr_hwdesc,
+				      struct dma_tx_state *state)
 {
 	struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan);
 	struct stm32_mdma_hwdesc *hwdesc;
-	u32 cbndtr, residue, modulo, burst_size;
+	u32 cisr, clar, cbndtr, residue, modulo, burst_size;
 	int i;
 
+	cisr = stm32_mdma_read(dmadev, STM32_MDMA_CISR(chan->id));
+
 	residue = 0;
-	for (i = curr_hwdesc + 1; i < desc->count; i++) {
+	/* Get the next hw descriptor to process from current transfer */
+	clar = stm32_mdma_read(dmadev, STM32_MDMA_CLAR(chan->id));
+	for (i = desc->count - 1; i >= 0; i--) {
 		hwdesc = desc->node[i].hwdesc;
+
+		if (hwdesc->clar == clar)
+			break;/* Current transfer found, stop cumulating */
+
+		/* Cumulate residue of unprocessed hw descriptors */
 		residue += STM32_MDMA_CBNDTR_BNDT(hwdesc->cbndtr);
 	}
 	cbndtr = stm32_mdma_read(dmadev, STM32_MDMA_CBNDTR(chan->id));
 	residue += cbndtr & STM32_MDMA_CBNDTR_BNDT_MASK;
 
+	state->in_flight_bytes = 0;
+	if (chan->chan_config.m2m_hw && (cisr & STM32_MDMA_CISR_CRQA))
+		state->in_flight_bytes = cbndtr & STM32_MDMA_CBNDTR_BNDT_MASK;
+
 	if (!chan->mem_burst)
 		return residue;
 
@@ -1360,11 +1376,10 @@ static enum dma_status stm32_mdma_tx_status(struct dma_chan *c,
 
 	vdesc = vchan_find_desc(&chan->vchan, cookie);
 	if (chan->desc && cookie == chan->desc->vdesc.tx.cookie)
-		residue = stm32_mdma_desc_residue(chan, chan->desc,
-						  chan->curr_hwdesc);
+		residue = stm32_mdma_desc_residue(chan, chan->desc, chan->curr_hwdesc, state);
 	else if (vdesc)
-		residue = stm32_mdma_desc_residue(chan,
-						  to_stm32_mdma_desc(vdesc), 0);
+		residue = stm32_mdma_desc_residue(chan, to_stm32_mdma_desc(vdesc), 0, state);
+
 	dma_set_residue(state, residue);
 
 	spin_unlock_irqrestore(&chan->vchan.lock, flags);