All of lore.kernel.org
 help / color / mirror / Atom feed
From: Devendra K Verma <devendra.verma@amd.com>
To: <bhelgaas@google.com>, <mani@kernel.org>, <vkoul@kernel.org>
Cc: <dmaengine@vger.kernel.org>, <linux-pci@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <michal.simek@amd.com>
Subject: [RESEND PATCH v4 2/2] dmaengine: dw-edma: Add non-LL mode
Date: Tue, 30 Sep 2025 18:47:55 +0530	[thread overview]
Message-ID: <20250930131755.3844-3-devendra.verma@amd.com> (raw)
In-Reply-To: <20250930131755.3844-1-devendra.verma@amd.com>

AMD MDB IP supports Linked List (LL) mode as well as non-LL mode.
The current code does not have the mechanisms to enable the
DMA transactions using the non-LL mode. The following two cases
are added with this patch:
- When a valid physical base address is not configured via the
  Xilinx VSEC capability then the IP can still be used in non-LL
  mode. The default mode for all the DMA transactions and for all
  the DMA channels then is non-LL mode.
- When a valid physical base address is configured but the client
  wants to use the non-LL mode for DMA transactions then also the
  flexibility is provided via the peripheral_config struct member of
  dma_slave_config. In this case the channels can be individually
  configured in non-LL mode. This use case is desirable for single
  DMA transfer of a chunk, this saves the effort of preparing the
  Link List.

Signed-off-by: Devendra K Verma <devendra.verma@amd.com>
---
Changes in v4
  No change

Changes in v3
  No change

Changes in v2
  Reverted the function return type to u64 for
  dw_edma_get_phys_addr().

Changes in v1
  Changed the function return type for dw_edma_get_phys_addr().
  Corrected the typo raised in review.
---
 drivers/dma/dw-edma/dw-edma-core.c    | 38 +++++++++++++---
 drivers/dma/dw-edma/dw-edma-core.h    |  1 +
 drivers/dma/dw-edma/dw-edma-pcie.c    | 44 +++++++++++++------
 drivers/dma/dw-edma/dw-hdma-v0-core.c | 62 ++++++++++++++++++++++++++-
 include/linux/dma/edma.h              |  1 +
 5 files changed, 127 insertions(+), 19 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index b43255f914f3..3283ac5ffeeb 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -223,8 +223,28 @@ static int dw_edma_device_config(struct dma_chan *dchan,
 				 struct dma_slave_config *config)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
+	int nollp = 0;
+
+	if (WARN_ON(config->peripheral_config &&
+		    config->peripheral_size != sizeof(int)))
+		return -EINVAL;
 
 	memcpy(&chan->config, config, sizeof(*config));
+
+	/*
+	 * When there is no valid LLP base address available
+	 * then the default DMA ops will use the non-LL mode.
+	 * Cases where LL mode is enabled and client wants
+	 * to use the non-LL mode then also client can do
+	 * so via providing the peripheral_config param.
+	 */
+	if (config->peripheral_config)
+		nollp = *(int *)config->peripheral_config;
+
+	chan->nollp = false;
+	if (chan->dw->chip->nollp || (!chan->dw->chip->nollp && nollp))
+		chan->nollp = true;
+
 	chan->configured = true;
 
 	return 0;
@@ -353,7 +373,7 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
 	enum dma_transfer_direction dir = xfer->direction;
 	struct scatterlist *sg = NULL;
-	struct dw_edma_chunk *chunk;
+	struct dw_edma_chunk *chunk = NULL;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
 	u64 src_addr, dst_addr;
@@ -419,9 +439,11 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 	if (unlikely(!desc))
 		goto err_alloc;
 
-	chunk = dw_edma_alloc_chunk(desc);
-	if (unlikely(!chunk))
-		goto err_alloc;
+	if (!chan->nollp) {
+		chunk = dw_edma_alloc_chunk(desc);
+		if (unlikely(!chunk))
+			goto err_alloc;
+	}
 
 	if (xfer->type == EDMA_XFER_INTERLEAVED) {
 		src_addr = xfer->xfer.il->src_start;
@@ -450,7 +472,13 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer)
 		if (xfer->type == EDMA_XFER_SCATTER_GATHER && !sg)
 			break;
 
-		if (chunk->bursts_alloc == chan->ll_max) {
+		/*
+		 * For non-LL mode, only a single burst can be handled
+		 * in a single chunk unlike LL mode where multiple bursts
+		 * can be configured in a single chunk.
+		 */
+		if ((chunk && chunk->bursts_alloc == chan->ll_max) ||
+		    chan->nollp) {
 			chunk = dw_edma_alloc_chunk(desc);
 			if (unlikely(!chunk))
 				goto err_alloc;
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 71894b9e0b15..2a4ad45fbe01 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -86,6 +86,7 @@ struct dw_edma_chan {
 	u8				configured;
 
 	struct dma_slave_config		config;
+	bool				nollp;
 };
 
 struct dw_edma_irq {
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index b26a55eec5e4..1c4d10c38823 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -260,6 +260,15 @@ static void dw_edma_pcie_get_vsec_dma_data(struct pci_dev *pdev,
 	pdata->devmem_phys_off = off;
 }
 
+static u64 dw_edma_get_phys_addr(struct pci_dev *pdev,
+				 struct dw_edma_pcie_data *pdata,
+				 enum pci_barno bar)
+{
+	if (pdev->vendor == PCI_VENDOR_ID_XILINX)
+		return pdata->devmem_phys_off;
+	return pci_bus_address(pdev, bar);
+}
+
 static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			      const struct pci_device_id *pid)
 {
@@ -269,6 +278,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	struct dw_edma_chip *chip;
 	int err, nr_irqs;
 	int i, mask;
+	bool nollp = false;
 
 	vsec_data = kmalloc(sizeof(*vsec_data), GFP_KERNEL);
 	if (!vsec_data)
@@ -293,21 +303,24 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	if (pdev->vendor == PCI_VENDOR_ID_XILINX) {
 		/*
 		 * There is no valid address found for the LL memory
-		 * space on the device side.
+		 * space on the device side. In the absence of LL base
+		 * address use the non-LL mode or simple mode supported by
+		 * the HDMA IP.
 		 */
 		if (vsec_data->devmem_phys_off == DW_PCIE_AMD_MDB_INVALID_ADDR)
-			return -EINVAL;
+			nollp = true;
 
 		/*
 		 * Configure the channel LL and data blocks if number of
 		 * channels enabled in VSEC capability are more than the
 		 * channels configured in amd_mdb_data.
 		 */
-		dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
-					       DW_PCIE_XILINX_LL_OFF_GAP,
-					       DW_PCIE_XILINX_LL_SIZE,
-					       DW_PCIE_XILINX_DT_OFF_GAP,
-					       DW_PCIE_XILINX_DT_SIZE);
+		if (!nollp)
+			dw_edma_set_chan_region_offset(vsec_data, BAR_2, 0,
+						       DW_PCIE_XILINX_LL_OFF_GAP,
+						       DW_PCIE_XILINX_LL_SIZE,
+						       DW_PCIE_XILINX_DT_OFF_GAP,
+						       DW_PCIE_XILINX_DT_SIZE);
 	}
 
 	/* Mapping PCI BAR regions */
@@ -355,6 +368,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	chip->mf = vsec_data->mf;
 	chip->nr_irqs = nr_irqs;
 	chip->ops = &dw_edma_pcie_plat_ops;
+	chip->nollp = nollp;
 
 	chip->ll_wr_cnt = vsec_data->wr_ch_cnt;
 	chip->ll_rd_cnt = vsec_data->rd_ch_cnt;
@@ -363,7 +377,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	if (!chip->reg_base)
 		return -ENOMEM;
 
-	for (i = 0; i < chip->ll_wr_cnt; i++) {
+	for (i = 0; i < chip->ll_wr_cnt && !nollp; i++) {
 		struct dw_edma_region *ll_region = &chip->ll_region_wr[i];
 		struct dw_edma_region *dt_region = &chip->dt_region_wr[i];
 		struct dw_edma_block *ll_block = &vsec_data->ll_wr[i];
@@ -374,7 +388,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		ll_region->vaddr.io += ll_block->off;
-		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
+		ll_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
@@ -383,12 +398,13 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		dt_region->vaddr.io += dt_block->off;
-		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
+		dt_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
 
-	for (i = 0; i < chip->ll_rd_cnt; i++) {
+	for (i = 0; i < chip->ll_rd_cnt && !nollp; i++) {
 		struct dw_edma_region *ll_region = &chip->ll_region_rd[i];
 		struct dw_edma_region *dt_region = &chip->dt_region_rd[i];
 		struct dw_edma_block *ll_block = &vsec_data->ll_rd[i];
@@ -399,7 +415,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		ll_region->vaddr.io += ll_block->off;
-		ll_region->paddr = pci_bus_address(pdev, ll_block->bar);
+		ll_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 ll_block->bar);
 		ll_region->paddr += ll_block->off;
 		ll_region->sz = ll_block->sz;
 
@@ -408,7 +425,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 			return -ENOMEM;
 
 		dt_region->vaddr.io += dt_block->off;
-		dt_region->paddr = pci_bus_address(pdev, dt_block->bar);
+		dt_region->paddr = dw_edma_get_phys_addr(pdev, vsec_data,
+							 dt_block->bar);
 		dt_region->paddr += dt_block->off;
 		dt_region->sz = dt_block->sz;
 	}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
index e3f8db4fe909..befb9e0c9bd0 100644
--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -225,7 +225,7 @@ static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk)
 		readl(chunk->ll_region.vaddr.io);
 }
 
-static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+static void dw_hdma_v0_core_ll_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma *dw = chan->dw;
@@ -263,6 +263,66 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
 }
 
+static void dw_hdma_v0_core_non_ll_start(struct dw_edma_chunk *chunk)
+{
+	struct dw_edma_chan *chan = chunk->chan;
+	struct dw_edma *dw = chan->dw;
+	struct dw_edma_burst *child;
+	u32 val;
+
+	list_for_each_entry(child, &chunk->burst->list, list) {
+		SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0));
+
+		/* Source address */
+		SET_CH_32(dw, chan->dir, chan->id, sar.lsb,
+			  lower_32_bits(child->sar));
+		SET_CH_32(dw, chan->dir, chan->id, sar.msb,
+			  upper_32_bits(child->sar));
+
+		/* Destination address */
+		SET_CH_32(dw, chan->dir, chan->id, dar.lsb,
+			  lower_32_bits(child->dar));
+		SET_CH_32(dw, chan->dir, chan->id, dar.msb,
+			  upper_32_bits(child->dar));
+
+		/* Transfer size */
+		SET_CH_32(dw, chan->dir, chan->id, transfer_size, child->sz);
+
+		/* Interrupt setup */
+		val = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
+				HDMA_V0_STOP_INT_MASK |
+				HDMA_V0_ABORT_INT_MASK |
+				HDMA_V0_LOCAL_STOP_INT_EN |
+				HDMA_V0_LOCAL_ABORT_INT_EN;
+
+		if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL)) {
+			val |= HDMA_V0_REMOTE_STOP_INT_EN |
+			       HDMA_V0_REMOTE_ABORT_INT_EN;
+		}
+
+		SET_CH_32(dw, chan->dir, chan->id, int_setup, val);
+
+		/* Channel control setup */
+		val = GET_CH_32(dw, chan->dir, chan->id, control1);
+		val &= ~HDMA_V0_LINKLIST_EN;
+		SET_CH_32(dw, chan->dir, chan->id, control1, val);
+
+		/* Ring the doorbell */
+		SET_CH_32(dw, chan->dir, chan->id, doorbell,
+			  HDMA_V0_DOORBELL_START);
+	}
+}
+
+static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+{
+	struct dw_edma_chan *chan = chunk->chan;
+
+	if (!chan->nollp)
+		dw_hdma_v0_core_ll_start(chunk, first);
+	else
+		dw_hdma_v0_core_non_ll_start(chunk);
+}
+
 static void dw_hdma_v0_core_ch_config(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index 3080747689f6..e14e16f4cc79 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -99,6 +99,7 @@ struct dw_edma_chip {
 	enum dw_edma_map_format	mf;
 
 	struct dw_edma		*dw;
+	bool			nollp;
 };
 
 /* Export to the platform drivers */
-- 
2.43.0


      parent reply	other threads:[~2025-09-30 13:18 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-30 13:17 [RESEND PATCH v4 0/2] Add AMD MDB Endpoint and non-LL mode Support Devendra K Verma
2025-09-30 13:17 ` [RESEND PATCH v4 1/2] dmaengine: dw-edma: Add AMD MDB Endpoint Support Devendra K Verma
2025-09-30 13:17 ` Devendra K Verma [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250930131755.3844-3-devendra.verma@amd.com \
    --to=devendra.verma@amd.com \
    --cc=bhelgaas@google.com \
    --cc=dmaengine@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=mani@kernel.org \
    --cc=michal.simek@amd.com \
    --cc=vkoul@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.