Re: [RFC PATCH v4 36/38] PCI: endpoint: pci-epf-test: Add remote eDMA-backed mode

On Sun, Jan 18, 2026 at 10:54:38PM +0900, Koichiro Den wrote:
> Some DesignWare-based endpoints integrate an eDMA engine that can be
> programmed by the host via MMIO. The upcoming NTB transport remote-eDMA
> backend relies on this capability, but there is currently no upstream
> test coverage for the end-to-end control and data path.
>
> Extend pci-epf-test with an optional remote eDMA test backend (built when
> CONFIG_DW_EDMA is enabled).
>
> - Reserve a spare BAR and expose a small 'pcitest_edma_info' header at
>   BAR offset 0. The header carries a magic/version and describes the
>   endpoint eDMA register window, per-direction linked-list (LL)
>   locations and an endpoint test buffer.
> - Map the eDMA registers and LL locations into that BAR using BAR
>   subrange mappings (address-match inbound iATU).
>
> To run this extra testing, two new endpoint commands are added:
>   * COMMAND_REMOTE_EDMA_SETUP
>   * COMMAND_REMOTE_EDMA_CHECKSUM
>
> When the former command is received, the endpoint prepares for the
> remote eDMA transfer. The CHECKSUM command is useful for Host-to-EP
> transfer testing, as the endpoint side is not expected to receive the
> DMA completion interrupt directly. Instead, the host asks the endpoint
> to compute a CRC32 over the transferred data.
>
> This backend is exercised by the host-side pci_endpoint_test driver via a
> new UAPI flag.
>
> Signed-off-by: Koichiro Den <[email protected]>
> ---
>  drivers/pci/endpoint/functions/pci-epf-test.c | 477 ++++++++++++++++++

This patch should be combined into your submap patches, which is one user
of submap.

Frank

>  1 file changed, 477 insertions(+)
>
> diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
> index e560c3becebb..eea10bddcd2a 100644
> --- a/drivers/pci/endpoint/functions/pci-epf-test.c
> +++ b/drivers/pci/endpoint/functions/pci-epf-test.c
> @@ -10,6 +10,7 @@
>  #include <linux/delay.h>
>  #include <linux/dmaengine.h>
>  #include <linux/io.h>
> +#include <linux/iommu.h>
>  #include <linux/module.h>
>  #include <linux/msi.h>
>  #include <linux/slab.h>
> @@ -33,6 +34,8 @@
>  #define COMMAND_COPY			BIT(5)
>  #define COMMAND_ENABLE_DOORBELL		BIT(6)
>  #define COMMAND_DISABLE_DOORBELL	BIT(7)
> +#define COMMAND_REMOTE_EDMA_SETUP	BIT(8)
> +#define COMMAND_REMOTE_EDMA_CHECKSUM	BIT(9)
>
>  #define STATUS_READ_SUCCESS		BIT(0)
>  #define STATUS_READ_FAIL		BIT(1)
> @@ -48,6 +51,10 @@
>  #define STATUS_DOORBELL_ENABLE_FAIL	BIT(11)
>  #define STATUS_DOORBELL_DISABLE_SUCCESS BIT(12)
>  #define STATUS_DOORBELL_DISABLE_FAIL	BIT(13)
> +#define STATUS_REMOTE_EDMA_SETUP_SUCCESS	BIT(14)
> +#define STATUS_REMOTE_EDMA_SETUP_FAIL		BIT(15)
> +#define STATUS_REMOTE_EDMA_CHECKSUM_SUCCESS	BIT(16)
> +#define STATUS_REMOTE_EDMA_CHECKSUM_FAIL	BIT(17)
>
>  #define FLAG_USE_DMA			BIT(0)
>
> @@ -77,6 +84,9 @@ struct pci_epf_test {
>  	bool			dma_private;
>  	const struct pci_epc_features *epc_features;
>  	struct pci_epf_bar	db_bar;
> +
> +	/* For extended tests that rely on vendor-specific features */
> +	void *data;
>  };
>
>  struct pci_epf_test_reg {
> @@ -117,6 +127,454 @@ static enum pci_barno pci_epf_test_next_free_bar(struct pci_epf_test *epf_test)
>  	return bar;
>  }
>
> +#if IS_REACHABLE(CONFIG_DW_EDMA)
> +#include <linux/dma/edma.h>
> +
> +#define PCITEST_EDMA_INFO_MAGIC		0x414d4445U /* 'EDMA' */
> +#define PCITEST_EDMA_INFO_VERSION	0x00010000U
> +#define PCITEST_EDMA_TEST_BUF_SIZE	(1024 * 1024)
> +
> +struct pci_epf_test_edma {
> +	/* Remote eDMA test resources */
> +	bool			enabled;
> +	enum pci_barno		bar;
> +	void			*info;
> +	size_t			total_size;
> +	void			*test_buf;
> +	dma_addr_t		test_buf_phys;
> +	size_t			test_buf_size;
> +
> +	/* DW eDMA specifics */
> +	phys_addr_t		reg_phys;
> +	size_t			reg_submap_sz;
> +	unsigned long		reg_iova;
> +	size_t			reg_iova_sz;
> +	phys_addr_t		ll_rd_phys;
> +	size_t			ll_rd_sz_aligned;
> +	phys_addr_t		ll_wr_phys;
> +	size_t			ll_wr_sz_aligned;
> +};
> +
> +struct pcitest_edma_info {
> +	__le32 magic;
> +	__le32 version;
> +
> +	__le32 reg_off;
> +	__le32 reg_size;
> +
> +	__le64 ll_rd_phys;
> +	__le32 ll_rd_off;
> +	__le32 ll_rd_size;
> +
> +	__le64 ll_wr_phys;
> +	__le32 ll_wr_off;
> +	__le32 ll_wr_size;
> +
> +	__le64 test_buf_phys;
> +	__le32 test_buf_size;
> +};
> +
> +static bool pci_epf_test_bar_is_reserved(struct pci_epf_test *test,
> +					 enum pci_barno barno)
> +{
> +	struct pci_epf_test_edma *edma = test->data;
> +
> +	if (!edma)
> +		return false;
> +
> +	return barno == edma->bar;
> +}
> +
> +static void pci_epf_test_clear_submaps(struct pci_epf_bar *bar)
> +{
> +	kfree(bar->submap);
> +	bar->submap = NULL;
> +	bar->num_submap = 0;
> +}
> +
> +static int pci_epf_test_add_submap(struct pci_epf_bar *bar, phys_addr_t phys,
> +				   size_t size)
> +{
> +	struct pci_epf_bar_submap *submap, *new;
> +
> +	new = krealloc_array(bar->submap, bar->num_submap + 1, sizeof(*new),
> +			     GFP_KERNEL);
> +	if (!new)
> +		return -ENOMEM;
> +
> +	bar->submap = new;
> +	submap = &bar->submap[bar->num_submap];
> +	submap->phys_addr = phys;
> +	submap->size = size;
> +	bar->num_submap++;
> +
> +	return 0;
> +}
> +
> +static void pci_epf_test_clean_remote_edma(struct pci_epf_test *test)
> +{
> +	struct pci_epf_test_edma *edma = test->data;
> +	struct pci_epf *epf = test->epf;
> +	struct pci_epc *epc = epf->epc;
> +	struct device *dev = epc->dev.parent;
> +	struct iommu_domain *dom;
> +	struct pci_epf_bar *bar;
> +	enum pci_barno barno;
> +
> +	if (!edma)
> +		return;
> +
> +	barno = edma->bar;
> +	if (barno == NO_BAR)
> +		return;
> +
> +	bar = &epf->bar[barno];
> +
> +	dom = iommu_get_domain_for_dev(dev);
> +	if (dom && edma->reg_iova_sz) {
> +		iommu_unmap(dom, edma->reg_iova, edma->reg_iova_sz);
> +		edma->reg_iova = 0;
> +		edma->reg_iova_sz = 0;
> +	}
> +
> +	if (edma->test_buf) {
> +		dma_free_coherent(dev, edma->test_buf_size,
> +				  edma->test_buf,
> +				  edma->test_buf_phys);
> +		edma->test_buf = NULL;
> +		edma->test_buf_phys = 0;
> +		edma->test_buf_size = 0;
> +	}
> +
> +	if (edma->info) {
> +		pci_epf_free_space(epf, edma->info, barno, PRIMARY_INTERFACE);
> +		edma->info = NULL;
> +	}
> +
> +	pci_epf_test_clear_submaps(bar);
> +	pci_epc_clear_bar(epc, epf->func_no, epf->vfunc_no, bar);
> +
> +	edma->bar = NO_BAR;
> +	edma->enabled = false;
> +}
> +
> +static int pci_epf_test_init_remote_edma(struct pci_epf_test *test)
> +{
> +	const struct pci_epc_features *epc_features = test->epc_features;
> +	struct pci_epf_test_edma *edma;
> +	struct pci_epf *epf = test->epf;
> +	struct pci_epc *epc = epf->epc;
> +	struct pcitest_edma_info *info;
> +	struct device *dev = epc->dev.parent;
> +	struct dw_edma_region region;
> +	struct iommu_domain *dom;
> +	size_t reg_sz_aligned, ll_rd_sz_aligned, ll_wr_sz_aligned;
> +	phys_addr_t phys, ll_rd_phys, ll_wr_phys;
> +	size_t ll_rd_size, ll_wr_size;
> +	resource_size_t reg_size;
> +	unsigned long iova;
> +	size_t off, size;
> +	int ret;
> +
> +	if (!test->dma_chan_tx || !test->dma_chan_rx)
> +		return -ENODEV;
> +
> +	edma = devm_kzalloc(&epf->dev, sizeof(*edma), GFP_KERNEL);
> +	if (!edma)
> +		return -ENOMEM;
> +	test->data = edma;
> +
> +	edma->bar = pci_epf_test_next_free_bar(test);
> +	if (edma->bar == NO_BAR) {
> +		dev_err(&epf->dev, "No spare BAR for remote eDMA (remote eDMA disabled)\n");
> +		ret = -ENOSPC;
> +		goto err;
> +	}
> +
> +	ret = dw_edma_get_reg_window(epc, &edma->reg_phys, &reg_size);
> +	if (ret) {
> +		dev_err(dev, "failed to get edma reg window: %d\n", ret);
> +		goto err;
> +	}
> +	dom = iommu_get_domain_for_dev(dev);
> +	if (dom) {
> +		phys = edma->reg_phys & PAGE_MASK;
> +		size = PAGE_ALIGN(reg_size + edma->reg_phys - phys);
> +		iova = phys;
> +
> +		ret = iommu_map(dom, iova, phys, size,
> +				IOMMU_READ | IOMMU_WRITE | IOMMU_MMIO,
> +				GFP_KERNEL);
> +		if (ret) {
> +			dev_err(dev, "failed to direct map eDMA reg: %d\n", ret);
> +			goto err;
> +		}
> +		edma->reg_iova = iova;
> +		edma->reg_iova_sz = size;
> +	}
> +
> +	/* Get LL location addresses and sizes */
> +	ret = dw_edma_chan_get_ll_region(test->dma_chan_rx, &region);
> +	if (ret) {
> +		dev_err(dev, "failed to get edma ll region for rx: %d\n", ret);
> +		goto err;
> +	}
> +	ll_rd_phys = region.paddr;
> +	ll_rd_size = region.sz;
> +
> +	ret = dw_edma_chan_get_ll_region(test->dma_chan_tx, &region);
> +	if (ret) {
> +		dev_err(dev, "failed to get edma ll region for tx: %d\n", ret);
> +		goto err;
> +	}
> +	ll_wr_phys = region.paddr;
> +	ll_wr_size = region.sz;
> +
> +	edma->test_buf_size = PCITEST_EDMA_TEST_BUF_SIZE;
> +	edma->test_buf = dma_alloc_coherent(dev, edma->test_buf_size,
> +					    &edma->test_buf_phys, GFP_KERNEL);
> +	if (!edma->test_buf) {
> +		ret = -ENOMEM;
> +		goto err;
> +	}
> +
> +	reg_sz_aligned = PAGE_ALIGN(reg_size);
> +	ll_rd_sz_aligned = PAGE_ALIGN(ll_rd_size);
> +	ll_wr_sz_aligned = PAGE_ALIGN(ll_wr_size);
> +	edma->total_size = PAGE_SIZE + reg_sz_aligned + ll_rd_sz_aligned +
> +			   ll_wr_sz_aligned;
> +	size = roundup_pow_of_two(edma->total_size);
> +
> +	info = pci_epf_alloc_space(epf, size, edma->bar,
> +				   epc_features, PRIMARY_INTERFACE);
> +	if (!info) {
> +		ret = -ENOMEM;
> +		goto err;
> +	}
> +	memset(info, 0, size);
> +
> +	off = PAGE_SIZE;
> +	info->magic = cpu_to_le32(PCITEST_EDMA_INFO_MAGIC);
> +	info->version = cpu_to_le32(PCITEST_EDMA_INFO_VERSION);
> +
> +	info->reg_off = cpu_to_le32(off);
> +	info->reg_size = cpu_to_le32(reg_size);
> +	off += reg_sz_aligned;
> +
> +	info->ll_rd_phys = cpu_to_le64(ll_rd_phys);
> +	info->ll_rd_off = cpu_to_le32(off);
> +	info->ll_rd_size = cpu_to_le32(ll_rd_size);
> +	off += ll_rd_sz_aligned;
> +
> +	info->ll_wr_phys = cpu_to_le64(ll_wr_phys);
> +	info->ll_wr_off = cpu_to_le32(off);
> +	info->ll_wr_size = cpu_to_le32(ll_wr_size);
> +	off += ll_wr_sz_aligned;
> +
> +	info->test_buf_phys = cpu_to_le64(edma->test_buf_phys);
> +	info->test_buf_size = cpu_to_le32(edma->test_buf_size);
> +
> +	edma->info = info;
> +	edma->reg_submap_sz = reg_sz_aligned;
> +	edma->ll_rd_phys = ll_rd_phys;
> +	edma->ll_wr_phys = ll_wr_phys;
> +	edma->ll_rd_sz_aligned = ll_rd_sz_aligned;
> +	edma->ll_wr_sz_aligned = ll_wr_sz_aligned;
> +
> +	ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no,
> +			      &epf->bar[edma->bar]);
> +	if (ret) {
> +		dev_err(dev,
> +			"failed to init BAR%d for remote eDMA: %d\n",
> +			edma->bar, ret);
> +		goto err;
> +	}
> +	dev_info(dev, "BAR%d initialized for remote eDMA\n", edma->bar);
> +
> +	return 0;
> +
> +err:
> +	pci_epf_test_clean_remote_edma(test);
> +	devm_kfree(&epf->dev, edma);
> +	test->data = NULL;
> +	return ret;
> +}
> +
> +static int pci_epf_test_map_remote_edma(struct pci_epf_test *test)
> +{
> +	struct pci_epf_test_edma *edma = test->data;
> +	struct pcitest_edma_info *info;
> +	struct pci_epf *epf = test->epf;
> +	struct pci_epc *epc = epf->epc;
> +	struct pci_epf_bar *bar;
> +	enum pci_barno barno;
> +	struct device *dev = epc->dev.parent;
> +	int ret;
> +
> +	if (!edma)
> +		return -ENODEV;
> +
> +	info = edma->info;
> +	barno = edma->bar;
> +
> +	if (barno == NO_BAR)
> +		return -ENOSPC;
> +	if (!info || !edma->test_buf)
> +		return -ENODEV;
> +
> +	bar = &epf->bar[barno];
> +	pci_epf_test_clear_submaps(bar);
> +
> +	ret = pci_epf_test_add_submap(bar, bar->phys_addr, PAGE_SIZE);
> +	if (ret)
> +		return ret;
> +
> +	ret = pci_epf_test_add_submap(bar, edma->reg_phys, edma->reg_submap_sz);
> +	if (ret)
> +		goto err_submap;
> +
> +	ret = pci_epf_test_add_submap(bar, edma->ll_rd_phys,
> +				      edma->ll_rd_sz_aligned);
> +	if (ret)
> +		goto err_submap;
> +
> +	ret = pci_epf_test_add_submap(bar, edma->ll_wr_phys,
> +				      edma->ll_wr_sz_aligned);
> +	if (ret)
> +		goto err_submap;
> +
> +	if (bar->size > edma->total_size) {
> +		ret = pci_epf_test_add_submap(bar, 0,
> +					      bar->size - edma->total_size);
> +		if (ret)
> +			goto err_submap;
> +	}
> +
> +	ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, bar);
> +	if (ret) {
> +		dev_err(dev, "failed to map BAR%d: %d\n", barno, ret);
> +		goto err_submap;
> +	}
> +
> +	/*
> +	 * Endpoint-local interrupts must be ignored even if the host fails to
> +	 * mask them.
> +	 */
> +	ret = dw_edma_chan_irq_config(test->dma_chan_tx, DW_EDMA_CH_IRQ_REMOTE);
> +	if (ret) {
> +		dev_err(dev, "failed to set irq mode for tx channel: %d\n",
> +			ret);
> +		goto err_bar;
> +	}
> +	ret = dw_edma_chan_irq_config(test->dma_chan_rx, DW_EDMA_CH_IRQ_REMOTE);
> +	if (ret) {
> +		dev_err(dev, "failed to set irq mode for rx channel: %d\n",
> +			ret);
> +		goto err_bar;
> +	}
> +
> +	return 0;
> +err_bar:
> +	pci_epc_clear_bar(epc, epf->func_no, epf->vfunc_no, &epf->bar[barno]);
> +err_submap:
> +	pci_epf_test_clear_submaps(bar);
> +	return ret;
> +}
> +
> +static void pci_epf_test_remote_edma_setup(struct pci_epf_test *epf_test,
> +					   struct pci_epf_test_reg *reg)
> +{
> +	struct pci_epf_test_edma *edma = epf_test->data;
> +	size_t size = le32_to_cpu(reg->size);
> +	void *buf;
> +	int ret;
> +
> +	if (!edma || !edma->test_buf || size > edma->test_buf_size) {
> +		reg->status = cpu_to_le32(STATUS_REMOTE_EDMA_SETUP_FAIL);
> +		return;
> +	}
> +
> +	buf = edma->test_buf;
> +
> +	if (!edma->enabled) {
> +		/* NB. Currently DW eDMA is the only supported backend */
> +		ret = pci_epf_test_map_remote_edma(epf_test);
> +		if (ret) {
> +			WRITE_ONCE(reg->status,
> +				   cpu_to_le32(STATUS_REMOTE_EDMA_SETUP_FAIL));
> +			return;
> +		}
> +		edma->enabled = true;
> +	}
> +
> +	/* Populate the test buffer with random data */
> +	get_random_bytes(buf, size);
> +	reg->checksum = cpu_to_le32(crc32_le(~0, buf, size));
> +
> +	WRITE_ONCE(reg->status, cpu_to_le32(STATUS_REMOTE_EDMA_SETUP_SUCCESS));
> +}
> +
> +static void pci_epf_test_remote_edma_checksum(struct pci_epf_test *epf_test,
> +					      struct pci_epf_test_reg *reg)
> +{
> +	struct pci_epf_test_edma *edma = epf_test->data;
> +	u32 status = le32_to_cpu(reg->status);
> +	size_t size;
> +	void *addr;
> +	u32 crc32;
> +
> +	size = le32_to_cpu(reg->size);
> +	if (!edma || !edma->test_buf || size > edma->test_buf_size) {
> +		status |= STATUS_REMOTE_EDMA_CHECKSUM_FAIL;
> +		reg->status = cpu_to_le32(status);
> +		return;
> +	}
> +
> +	addr = edma->test_buf;
> +	crc32 = crc32_le(~0, addr, size);
> +	status |= STATUS_REMOTE_EDMA_CHECKSUM_SUCCESS;
> +
> +	reg->checksum = cpu_to_le32(crc32);
> +	reg->status = cpu_to_le32(status);
> +}
> +
> +static void pci_epf_test_reset_dma_chan(struct dma_chan *chan)
> +{
> +	dw_edma_chan_irq_config(chan, DW_EDMA_CH_IRQ_DEFAULT);
> +}
> +#else
> +static bool pci_epf_test_bar_is_reserved(struct pci_epf_test *test,
> +					 enum pci_barno barno)
> +{
> +	return false;
> +}
> +
> +static void pci_epf_test_clean_remote_edma(struct pci_epf_test *test)
> +{
> +}
> +
> +static int pci_epf_test_init_remote_edma(struct pci_epf_test *test)
> +{
> +	return -EOPNOTSUPP;
> +}
> +
> +static void pci_epf_test_remote_edma_setup(struct pci_epf_test *epf_test,
> +					   struct pci_epf_test_reg *reg)
> +{
> +	reg->status = cpu_to_le32(STATUS_REMOTE_EDMA_SETUP_FAIL);
> +}
> +
> +static void pci_epf_test_remote_edma_checksum(struct pci_epf_test *epf_test,
> +					      struct pci_epf_test_reg *reg)
> +{
> +	reg->status = cpu_to_le32(STATUS_REMOTE_EDMA_CHECKSUM_FAIL);
> +}
> +
> +static void pci_epf_test_reset_dma_chan(struct dma_chan *chan)
> +{
> +}
> +#endif
> +
>  static void pci_epf_test_dma_callback(void *param)
>  {
>  	struct pci_epf_test *epf_test = param;
> @@ -168,6 +626,8 @@ static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
>  		return -EINVAL;
>  	}
>
> +	pci_epf_test_reset_dma_chan(chan);
> +
>  	if (epf_test->dma_private) {
>  		sconf.direction = dir;
>  		if (dir == DMA_MEM_TO_DEV)
> @@ -870,6 +1330,14 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
>  		pci_epf_test_disable_doorbell(epf_test, reg);
>  		pci_epf_test_raise_irq(epf_test, reg);
>  		break;
> +	case COMMAND_REMOTE_EDMA_SETUP:
> +		pci_epf_test_remote_edma_setup(epf_test, reg);
> +		pci_epf_test_raise_irq(epf_test, reg);
> +		break;
> +	case COMMAND_REMOTE_EDMA_CHECKSUM:
> +		pci_epf_test_remote_edma_checksum(epf_test, reg);
> +		pci_epf_test_raise_irq(epf_test, reg);
> +		break;
>  	default:
>  		dev_err(dev, "Invalid command 0x%x\n", command);
>  		break;
> @@ -961,6 +1429,10 @@ static int pci_epf_test_epc_init(struct pci_epf *epf)
>  	if (ret)
>  		epf_test->dma_supported = false;
>
> +	ret = pci_epf_test_init_remote_edma(epf_test);
> +	if (ret && ret != -EOPNOTSUPP)
> +		dev_warn(dev, "Remote eDMA setup failed\n");
> +
>  	if (epf->vfunc_no <= 1) {
>  		ret = pci_epc_write_header(epc, epf->func_no, epf->vfunc_no, header);
>  		if (ret) {
> @@ -1007,6 +1479,7 @@ static void pci_epf_test_epc_deinit(struct pci_epf *epf)
>  	struct pci_epf_test *epf_test = epf_get_drvdata(epf);
>
>  	cancel_delayed_work_sync(&epf_test->cmd_handler);
> +	pci_epf_test_clean_remote_edma(epf_test);
>  	pci_epf_test_clean_dma_chan(epf_test);
>  	pci_epf_test_clear_bar(epf);
>  }
> @@ -1076,6 +1549,9 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf)
>  		if (bar == test_reg_bar)
>  			continue;
>
> +		if (pci_epf_test_bar_is_reserved(epf_test, bar))
> +			continue;
> +
>  		if (epc_features->bar[bar].type == BAR_FIXED)
>  			test_reg_size = epc_features->bar[bar].fixed_size;
>  		else
> @@ -1146,6 +1622,7 @@ static void pci_epf_test_unbind(struct pci_epf *epf)
>
>  	cancel_delayed_work_sync(&epf_test->cmd_handler);
>  	if (epc->init_complete) {
> +		pci_epf_test_clean_remote_edma(epf_test);
>  		pci_epf_test_clean_dma_chan(epf_test);
>  		pci_epf_test_clear_bar(epf);
>  	}
> --
> 2.51.0
>