Merge tag 'dmaengine-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "New Support:

   - MT6795 SoC dma controller (AngeloGioacchino Del Regno)

   - qcom-adm controller yaml binding (Christian Marangi)

   - Renesas r8a779g0 dma controller yaml binding (Geert Uytterhoeven)

   - Qualcomm SM6350 GPI dma controller (Luca Weiss)

  Updates:

   - STM32 DMA-MDMA chaining support (Amelie Delaunay)

   - make hsu driver use managed resources (Andy Shevchenko)

   - the usual round of idxd driver updates (Dave Jiang & Jerry
     Snitselaar)

   - apple dma driver iommu and pd properties and remove use
     of devres for irqs (Janne Grunau & Martin Povišer)

   - device_synchronize support for Xilinx zynqmp driver (Swati
     Agarwal)"

* tag 'dmaengine-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (60 commits)
  dmaengine: ioat: remove unused declarations in dma.h
  dmaengine: ti: k3-udma: Respond TX done if DMA_PREP_INTERRUPT is not requested
  dmaengine: zynqmp_dma: Add device_synchronize support
  dt-bindings: dma: add additional pbus reset to qcom,adm
  dt-bindings: dma: rework qcom,adm Documentation to yaml schema
  dt-bindings: dma: apple,admac: Add iommus and power-domains properties
  dmaengine: dw-edma: Remove runtime PM support
  dmaengine: idxd: add configuration for concurrent batch descriptor processing
  dmaengine: idxd: add configuration for concurrent work descriptor processing
  dmaengine: idxd: add WQ operation cap restriction support
  dmanegine: idxd: reformat opcap output to match bitmap_parse() input
  dmaengine: idxd: convert ats_dis to a wq flag
  dmaengine: ioat: stop mod_timer from resurrecting deleted timer in __cleanup()
  dmaengine: qcom-adm: fix wrong calling convention for prep_slave_sg
  dmaengine: qcom-adm: fix wrong sizeof config in slave_config
  dmaengine: ti: k3-psil: add additional TX threads for j721e
  dmaengine: ti: k3-psil: add additional TX threads for j7200
  dmaengine: apple-admac: Trigger shared reset
  dmaengine: apple-admac: Do not use devres for IRQs
  dmaengine: ti: edma: Remove some unused functions
  ...

4 files changed, 173 insertions, 50 deletions

diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 4cbca80ee16e..fa06d7e6d8e3 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -352,12 +352,6 @@ static inline void edma_modify_array(struct edma_cc *ecc, int offset, int i,
 	edma_modify(ecc, offset + (i << 2), and, or);
 }
 
-static inline void edma_or_array(struct edma_cc *ecc, int offset, int i,
-				 unsigned or)
-{
-	edma_or(ecc, offset + (i << 2), or);
-}
-
 static inline void edma_or_array2(struct edma_cc *ecc, int offset, int i, int j,
 				  unsigned or)
 {
@@ -370,11 +364,6 @@ static inline void edma_write_array2(struct edma_cc *ecc, int offset, int i,
 	edma_write(ecc, offset + ((i * 2 + j) << 2), val);
 }
 
-static inline unsigned int edma_shadow0_read(struct edma_cc *ecc, int offset)
-{
-	return edma_read(ecc, EDMA_SHADOW0 + offset);
-}
-
 static inline unsigned int edma_shadow0_read_array(struct edma_cc *ecc,
 						   int offset, int i)
 {
@@ -393,36 +382,12 @@ static inline void edma_shadow0_write_array(struct edma_cc *ecc, int offset,
 	edma_write(ecc, EDMA_SHADOW0 + offset + (i << 2), val);
 }
 
-static inline unsigned int edma_param_read(struct edma_cc *ecc, int offset,
-					   int param_no)
-{
-	return edma_read(ecc, EDMA_PARM + offset + (param_no << 5));
-}
-
-static inline void edma_param_write(struct edma_cc *ecc, int offset,
-				    int param_no, unsigned val)
-{
-	edma_write(ecc, EDMA_PARM + offset + (param_no << 5), val);
-}
-
 static inline void edma_param_modify(struct edma_cc *ecc, int offset,
 				     int param_no, unsigned and, unsigned or)
 {
 	edma_modify(ecc, EDMA_PARM + offset + (param_no << 5), and, or);
 }
 
-static inline void edma_param_and(struct edma_cc *ecc, int offset, int param_no,
-				  unsigned and)
-{
-	edma_and(ecc, EDMA_PARM + offset + (param_no << 5), and);
-}
-
-static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
-				 unsigned or)
-{
-	edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
-}
-
 static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
 					  int priority)
 {
@@ -743,11 +708,6 @@ static void edma_free_channel(struct edma_chan *echan)
 	edma_setup_interrupt(echan, false);
 }
 
-static inline struct edma_cc *to_edma_cc(struct dma_device *d)
-{
-	return container_of(d, struct edma_cc, dma_slave);
-}
-
 static inline struct edma_chan *to_edma_chan(struct dma_chan *c)
 {
 	return container_of(c, struct edma_chan, vchan.chan);
diff --git a/drivers/dma/ti/k3-psil-j7200.c b/drivers/dma/ti/k3-psil-j7200.c
index 5ea63ea74822..e3feff869991 100644
--- a/drivers/dma/ti/k3-psil-j7200.c
+++ b/drivers/dma/ti/k3-psil-j7200.c
@@ -143,6 +143,57 @@ static struct psil_ep j7200_src_ep_map[] = {
 
 /* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
 static struct psil_ep j7200_dst_ep_map[] = {
+	/* PDMA_MCASP - McASP0-2 */
+	PSIL_PDMA_MCASP(0xc400),
+	PSIL_PDMA_MCASP(0xc401),
+	PSIL_PDMA_MCASP(0xc402),
+	/* PDMA_SPI_G0 - SPI0-3 */
+	PSIL_PDMA_XY_PKT(0xc600),
+	PSIL_PDMA_XY_PKT(0xc601),
+	PSIL_PDMA_XY_PKT(0xc602),
+	PSIL_PDMA_XY_PKT(0xc603),
+	PSIL_PDMA_XY_PKT(0xc604),
+	PSIL_PDMA_XY_PKT(0xc605),
+	PSIL_PDMA_XY_PKT(0xc606),
+	PSIL_PDMA_XY_PKT(0xc607),
+	PSIL_PDMA_XY_PKT(0xc608),
+	PSIL_PDMA_XY_PKT(0xc609),
+	PSIL_PDMA_XY_PKT(0xc60a),
+	PSIL_PDMA_XY_PKT(0xc60b),
+	PSIL_PDMA_XY_PKT(0xc60c),
+	PSIL_PDMA_XY_PKT(0xc60d),
+	PSIL_PDMA_XY_PKT(0xc60e),
+	PSIL_PDMA_XY_PKT(0xc60f),
+	/* PDMA_SPI_G1 - SPI4-7 */
+	PSIL_PDMA_XY_PKT(0xc610),
+	PSIL_PDMA_XY_PKT(0xc611),
+	PSIL_PDMA_XY_PKT(0xc612),
+	PSIL_PDMA_XY_PKT(0xc613),
+	PSIL_PDMA_XY_PKT(0xc614),
+	PSIL_PDMA_XY_PKT(0xc615),
+	PSIL_PDMA_XY_PKT(0xc616),
+	PSIL_PDMA_XY_PKT(0xc617),
+	PSIL_PDMA_XY_PKT(0xc618),
+	PSIL_PDMA_XY_PKT(0xc619),
+	PSIL_PDMA_XY_PKT(0xc61a),
+	PSIL_PDMA_XY_PKT(0xc61b),
+	PSIL_PDMA_XY_PKT(0xc61c),
+	PSIL_PDMA_XY_PKT(0xc61d),
+	PSIL_PDMA_XY_PKT(0xc61e),
+	PSIL_PDMA_XY_PKT(0xc61f),
+	/* PDMA_USART_G0 - UART0-1 */
+	PSIL_PDMA_XY_PKT(0xc700),
+	PSIL_PDMA_XY_PKT(0xc701),
+	/* PDMA_USART_G1 - UART2-3 */
+	PSIL_PDMA_XY_PKT(0xc702),
+	PSIL_PDMA_XY_PKT(0xc703),
+	/* PDMA_USART_G2 - UART4-9 */
+	PSIL_PDMA_XY_PKT(0xc704),
+	PSIL_PDMA_XY_PKT(0xc705),
+	PSIL_PDMA_XY_PKT(0xc706),
+	PSIL_PDMA_XY_PKT(0xc707),
+	PSIL_PDMA_XY_PKT(0xc708),
+	PSIL_PDMA_XY_PKT(0xc709),
 	/* CPSW5 */
 	PSIL_ETHERNET(0xca00),
 	PSIL_ETHERNET(0xca01),
@@ -161,6 +212,22 @@ static struct psil_ep j7200_dst_ep_map[] = {
 	PSIL_ETHERNET(0xf005),
 	PSIL_ETHERNET(0xf006),
 	PSIL_ETHERNET(0xf007),
+	/* MCU_PDMA_MISC_G0 - SPI0 */
+	PSIL_PDMA_XY_PKT(0xf100),
+	PSIL_PDMA_XY_PKT(0xf101),
+	PSIL_PDMA_XY_PKT(0xf102),
+	PSIL_PDMA_XY_PKT(0xf103),
+	/* MCU_PDMA_MISC_G1 - SPI1-2 */
+	PSIL_PDMA_XY_PKT(0xf200),
+	PSIL_PDMA_XY_PKT(0xf201),
+	PSIL_PDMA_XY_PKT(0xf202),
+	PSIL_PDMA_XY_PKT(0xf203),
+	PSIL_PDMA_XY_PKT(0xf204),
+	PSIL_PDMA_XY_PKT(0xf205),
+	PSIL_PDMA_XY_PKT(0xf206),
+	PSIL_PDMA_XY_PKT(0xf207),
+	/* MCU_PDMA_MISC_G2 - UART0 */
+	PSIL_PDMA_XY_PKT(0xf300),
 	/* SA2UL */
 	PSIL_SA2UL(0xf500, 1),
 	PSIL_SA2UL(0xf501, 1),
diff --git a/drivers/dma/ti/k3-psil-j721e.c b/drivers/dma/ti/k3-psil-j721e.c
index 34e3fc565a37..e7c83d668bb6 100644
--- a/drivers/dma/ti/k3-psil-j721e.c
+++ b/drivers/dma/ti/k3-psil-j721e.c
@@ -266,6 +266,69 @@ static struct psil_ep j721e_dst_ep_map[] = {
 	PSIL_ETHERNET(0xc205),
 	PSIL_ETHERNET(0xc206),
 	PSIL_ETHERNET(0xc207),
+	/* PDMA6 (PSIL_PDMA_MCASP_G0) - McASP0-2 */
+	PSIL_PDMA_MCASP(0xc400),
+	PSIL_PDMA_MCASP(0xc401),
+	PSIL_PDMA_MCASP(0xc402),
+	/* PDMA7 (PSIL_PDMA_MCASP_G1) - McASP3-11 */
+	PSIL_PDMA_MCASP(0xc500),
+	PSIL_PDMA_MCASP(0xc501),
+	PSIL_PDMA_MCASP(0xc502),
+	PSIL_PDMA_MCASP(0xc503),
+	PSIL_PDMA_MCASP(0xc504),
+	PSIL_PDMA_MCASP(0xc505),
+	PSIL_PDMA_MCASP(0xc506),
+	PSIL_PDMA_MCASP(0xc507),
+	PSIL_PDMA_MCASP(0xc508),
+	/* PDMA8 (PDMA_MISC_G0) - SPI0-1 */
+	PSIL_PDMA_XY_PKT(0xc600),
+	PSIL_PDMA_XY_PKT(0xc601),
+	PSIL_PDMA_XY_PKT(0xc602),
+	PSIL_PDMA_XY_PKT(0xc603),
+	PSIL_PDMA_XY_PKT(0xc604),
+	PSIL_PDMA_XY_PKT(0xc605),
+	PSIL_PDMA_XY_PKT(0xc606),
+	PSIL_PDMA_XY_PKT(0xc607),
+	/* PDMA9 (PDMA_MISC_G1) - SPI2-3 */
+	PSIL_PDMA_XY_PKT(0xc60c),
+	PSIL_PDMA_XY_PKT(0xc60d),
+	PSIL_PDMA_XY_PKT(0xc60e),
+	PSIL_PDMA_XY_PKT(0xc60f),
+	PSIL_PDMA_XY_PKT(0xc610),
+	PSIL_PDMA_XY_PKT(0xc611),
+	PSIL_PDMA_XY_PKT(0xc612),
+	PSIL_PDMA_XY_PKT(0xc613),
+	/* PDMA10 (PDMA_MISC_G2) - SPI4-5 */
+	PSIL_PDMA_XY_PKT(0xc618),
+	PSIL_PDMA_XY_PKT(0xc619),
+	PSIL_PDMA_XY_PKT(0xc61a),
+	PSIL_PDMA_XY_PKT(0xc61b),
+	PSIL_PDMA_XY_PKT(0xc61c),
+	PSIL_PDMA_XY_PKT(0xc61d),
+	PSIL_PDMA_XY_PKT(0xc61e),
+	PSIL_PDMA_XY_PKT(0xc61f),
+	/* PDMA11 (PDMA_MISC_G3) */
+	PSIL_PDMA_XY_PKT(0xc624),
+	PSIL_PDMA_XY_PKT(0xc625),
+	PSIL_PDMA_XY_PKT(0xc626),
+	PSIL_PDMA_XY_PKT(0xc627),
+	PSIL_PDMA_XY_PKT(0xc628),
+	PSIL_PDMA_XY_PKT(0xc629),
+	PSIL_PDMA_XY_PKT(0xc630),
+	PSIL_PDMA_XY_PKT(0xc63a),
+	/* PDMA13 (PDMA_USART_G0) - UART0-1 */
+	PSIL_PDMA_XY_PKT(0xc700),
+	PSIL_PDMA_XY_PKT(0xc701),
+	/* PDMA14 (PDMA_USART_G1) - UART2-3 */
+	PSIL_PDMA_XY_PKT(0xc702),
+	PSIL_PDMA_XY_PKT(0xc703),
+	/* PDMA15 (PDMA_USART_G2) - UART4-9 */
+	PSIL_PDMA_XY_PKT(0xc704),
+	PSIL_PDMA_XY_PKT(0xc705),
+	PSIL_PDMA_XY_PKT(0xc706),
+	PSIL_PDMA_XY_PKT(0xc707),
+	PSIL_PDMA_XY_PKT(0xc708),
+	PSIL_PDMA_XY_PKT(0xc709),
 	/* CPSW9 */
 	PSIL_ETHERNET(0xca00),
 	PSIL_ETHERNET(0xca01),
@@ -284,6 +347,22 @@ static struct psil_ep j721e_dst_ep_map[] = {
 	PSIL_ETHERNET(0xf005),
 	PSIL_ETHERNET(0xf006),
 	PSIL_ETHERNET(0xf007),
+	/* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */
+	PSIL_PDMA_XY_PKT(0xf100),
+	PSIL_PDMA_XY_PKT(0xf101),
+	PSIL_PDMA_XY_PKT(0xf102),
+	PSIL_PDMA_XY_PKT(0xf103),
+	/* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */
+	PSIL_PDMA_XY_PKT(0xf200),
+	PSIL_PDMA_XY_PKT(0xf201),
+	PSIL_PDMA_XY_PKT(0xf202),
+	PSIL_PDMA_XY_PKT(0xf203),
+	PSIL_PDMA_XY_PKT(0xf204),
+	PSIL_PDMA_XY_PKT(0xf205),
+	PSIL_PDMA_XY_PKT(0xf206),
+	PSIL_PDMA_XY_PKT(0xf207),
+	/* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */
+	PSIL_PDMA_XY_PKT(0xf300),
 	/* SA2UL */
 	PSIL_SA2UL(0xf500, 1),
 	PSIL_SA2UL(0xf501, 1),
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 2f0d2c68c93c..7b5081989b3d 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -263,6 +263,7 @@ struct udma_chan_config {
 	enum udma_tp_level channel_tpl; /* Channel Throughput Level */
 
 	u32 tr_trigger_type;
+	unsigned long tx_flags;
 
 	/* PKDMA mapped channel */
 	int mapped_channel_id;
@@ -300,8 +301,6 @@ struct udma_chan {
 
 	struct udma_tx_drain tx_drain;
 
-	u32 bcnt; /* number of bytes completed since the start of the channel */
-
 	/* Channel configuration parameters */
 	struct udma_chan_config config;
 
@@ -757,6 +756,20 @@ static void udma_reset_rings(struct udma_chan *uc)
 	}
 }
 
+static void udma_decrement_byte_counters(struct udma_chan *uc, u32 val)
+{
+	if (uc->desc->dir == DMA_DEV_TO_MEM) {
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+		udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+	} else {
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
+		udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
+		if (!uc->bchan)
+			udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+	}
+}
+
 static void udma_reset_counters(struct udma_chan *uc)
 {
 	u32 val;
@@ -790,8 +803,6 @@ static void udma_reset_counters(struct udma_chan *uc)
 		val = udma_rchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
 		udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
 	}
-
-	uc->bcnt = 0;
 }
 
 static int udma_reset_chan(struct udma_chan *uc, bool hard)
@@ -1045,9 +1056,14 @@ static bool udma_is_desc_really_done(struct udma_chan *uc, struct udma_desc *d)
 {
 	u32 peer_bcnt, bcnt;
 
-	/* Only TX towards PDMA is affected */
+	/*
+	 * Only TX towards PDMA is affected.
+	 * If DMA_PREP_INTERRUPT is not set by consumer then skip the transfer
+	 * completion calculation, consumer must ensure that there is no stale
+	 * data in DMA fabric in this case.
+	 */
 	if (uc->config.ep_type == PSIL_EP_NATIVE ||
-	    uc->config.dir != DMA_MEM_TO_DEV)
+	    uc->config.dir != DMA_MEM_TO_DEV || !(uc->config.tx_flags & DMA_PREP_INTERRUPT))
 		return true;
 
 	peer_bcnt = udma_tchanrt_read(uc, UDMA_CHAN_RT_PEER_BCNT_REG);
@@ -1115,7 +1131,7 @@ static void udma_check_tx_completion(struct work_struct *work)
 		if (uc->desc) {
 			struct udma_desc *d = uc->desc;
 
-			uc->bcnt += d->residue;
+			udma_decrement_byte_counters(uc, d->residue);
 			udma_start(uc);
 			vchan_cookie_complete(&d->vd);
 			break;
@@ -1168,7 +1184,7 @@ static irqreturn_t udma_ring_irq_handler(int irq, void *data)
 				vchan_cyclic_callback(&d->vd);
 			} else {
 				if (udma_is_desc_really_done(uc, d)) {
-					uc->bcnt += d->residue;
+					udma_decrement_byte_counters(uc, d->residue);
 					udma_start(uc);
 					vchan_cookie_complete(&d->vd);
 				} else {
@@ -1204,7 +1220,7 @@ static irqreturn_t udma_udma_irq_handler(int irq, void *data)
 			vchan_cyclic_callback(&d->vd);
 		} else {
 			/* TODO: figure out the real amount of data */
-			uc->bcnt += d->residue;
+			udma_decrement_byte_counters(uc, d->residue);
 			udma_start(uc);
 			vchan_cookie_complete(&d->vd);
 		}
@@ -3408,6 +3424,8 @@ udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!burst)
 		burst = 1;
 
+	uc->config.tx_flags = tx_flags;
+
 	if (uc->config.pkt_mode)
 		d = udma_prep_slave_sg_pkt(uc, sgl, sglen, dir, tx_flags,
 					   context);
@@ -3809,7 +3827,6 @@ static enum dma_status udma_tx_status(struct dma_chan *chan,
 			bcnt = udma_tchanrt_read(uc, UDMA_CHAN_RT_BCNT_REG);
 		}
 
-		bcnt -= uc->bcnt;
 		if (bcnt && !(bcnt % uc->desc->residue))
 			residue = 0;
 		else