[PATCH v2] dma/cnxk: add higher chunk size support

[<pbhagavatula@marvell.com>]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add support to configure higher chunk size by using the new
OPEN_V2 mailbox, this improves performance as the number of
mempool allocs are reduced.
Add timeout when polling for queue idle timeout.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Amit Prakash Shukla <amitprakashs@marvell.com>
---
v2 Changes:
- Update release notes.
- Use timeout when polling for queue idle state.

 doc/guides/rel_notes/release_24_07.rst |  6 +++
 drivers/common/cnxk/roc_dpi.c          | 72 ++++++++++++++++++++++----
 drivers/common/cnxk/roc_dpi.h          |  3 ++
 drivers/common/cnxk/roc_dpi_priv.h     |  3 ++
 drivers/common/cnxk/version.map        |  2 +
 drivers/dma/cnxk/cnxk_dmadev.c         | 37 ++++++++-----
 drivers/dma/cnxk/cnxk_dmadev.h         |  1 +
 7 files changed, 101 insertions(+), 23 deletions(-)

diff --git a/doc/guides/rel_notes/release_24_07.rst b/doc/guides/rel_notes/release_24_07.rst
index a69f24cf99..60b92e4842 100644
--- a/doc/guides/rel_notes/release_24_07.rst
+++ b/doc/guides/rel_notes/release_24_07.rst
@@ -55,6 +55,12 @@ New Features
      Also, make sure to start the actual text at the margin.
      =======================================================

+* **Updated Marvell CNXK DMA driver.**
+
+  * Updated DMA driver internal pool to use higher chunk size, effectively
+    reducing the number of mempool allocs needed, thereby increasing DMA
+    performance.
+

 Removed Items
 -------------
diff --git a/drivers/common/cnxk/roc_dpi.c b/drivers/common/cnxk/roc_dpi.c
index 1ee777d779..892685d185 100644
--- a/drivers/common/cnxk/roc_dpi.c
+++ b/drivers/common/cnxk/roc_dpi.c
@@ -38,6 +38,24 @@ send_msg_to_pf(struct plt_pci_addr *pci_addr, const char *value, int size)
 	return 0;
 }

+int
+roc_dpi_wait_queue_idle(struct roc_dpi *roc_dpi)
+{
+	const uint64_t cyc = (DPI_QUEUE_IDLE_TMO_MS * plt_tsc_hz()) / 1E3;
+	const uint64_t start = plt_tsc_cycles();
+	uint64_t reg;
+
+	/* Wait for SADDR to become idle */
+	reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
+	while (!(reg & BIT_ULL(63))) {
+		reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
+		if (plt_tsc_cycles() - start == cyc)
+			return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
 int
 roc_dpi_enable(struct roc_dpi *dpi)
 {
@@ -57,7 +75,6 @@ roc_dpi_configure(struct roc_dpi *roc_dpi, uint32_t chunk_sz, uint64_t aura, uin
 {
 	struct plt_pci_device *pci_dev;
 	dpi_mbox_msg_t mbox_msg;
-	uint64_t reg;
 	int rc;

 	if (!roc_dpi) {
@@ -68,9 +85,9 @@ roc_dpi_configure(struct roc_dpi *roc_dpi, uint32_t chunk_sz, uint64_t aura, uin
 	pci_dev = roc_dpi->pci_dev;

 	roc_dpi_disable(roc_dpi);
-	reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
-	while (!(reg & BIT_ULL(63)))
-		reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
+	rc = roc_dpi_wait_queue_idle(roc_dpi);
+	if (rc)
+		return rc;

 	plt_write64(0x0, roc_dpi->rbase + DPI_VDMA_REQQ_CTL);
 	plt_write64(chunk_base, roc_dpi->rbase + DPI_VDMA_SADDR);
@@ -87,6 +104,45 @@ roc_dpi_configure(struct roc_dpi *roc_dpi, uint32_t chunk_sz, uint64_t aura, uin
 	if (mbox_msg.s.wqecsoff)
 		mbox_msg.s.wqecs = 1;

+	rc = send_msg_to_pf(&pci_dev->addr, (const char *)&mbox_msg, sizeof(dpi_mbox_msg_t));
+	if (rc < 0)
+		plt_err("Failed to send mbox message %d to DPI PF, err %d", mbox_msg.s.cmd, rc);
+
+	return rc;
+}
+
+int
+roc_dpi_configure_v2(struct roc_dpi *roc_dpi, uint32_t chunk_sz, uint64_t aura, uint64_t chunk_base)
+{
+	struct plt_pci_device *pci_dev;
+	dpi_mbox_msg_t mbox_msg;
+	int rc;
+
+	if (!roc_dpi) {
+		plt_err("roc_dpi is NULL");
+		return -EINVAL;
+	}
+
+	pci_dev = roc_dpi->pci_dev;
+
+	roc_dpi_disable(roc_dpi);
+
+	rc = roc_dpi_wait_queue_idle(roc_dpi);
+	if (rc)
+		return rc;
+
+	plt_write64(0x0, roc_dpi->rbase + DPI_VDMA_REQQ_CTL);
+	plt_write64(chunk_base, roc_dpi->rbase + DPI_VDMA_SADDR);
+	mbox_msg.u[0] = 0;
+	mbox_msg.u[1] = 0;
+	/* DPI PF driver expects vfid starts from index 0 */
+	mbox_msg.s.vfid = roc_dpi->vfid;
+	mbox_msg.s.cmd = DPI_QUEUE_OPEN_V2;
+	mbox_msg.s.csize = chunk_sz / 8;
+	mbox_msg.s.aura = aura;
+	mbox_msg.s.sso_pf_func = idev_sso_pffunc_get();
+	mbox_msg.s.npa_pf_func = idev_npa_pffunc_get();
+
 	rc = send_msg_to_pf(&pci_dev->addr, (const char *)&mbox_msg,
 			    sizeof(dpi_mbox_msg_t));
 	if (rc < 0)
@@ -116,13 +172,11 @@ roc_dpi_dev_fini(struct roc_dpi *roc_dpi)
 {
 	struct plt_pci_device *pci_dev = roc_dpi->pci_dev;
 	dpi_mbox_msg_t mbox_msg;
-	uint64_t reg;
 	int rc;

-	/* Wait for SADDR to become idle */
-	reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
-	while (!(reg & BIT_ULL(63)))
-		reg = plt_read64(roc_dpi->rbase + DPI_VDMA_SADDR);
+	rc = roc_dpi_wait_queue_idle(roc_dpi);
+	if (rc)
+		return rc;

 	mbox_msg.u[0] = 0;
 	mbox_msg.u[1] = 0;
diff --git a/drivers/common/cnxk/roc_dpi.h b/drivers/common/cnxk/roc_dpi.h
index 978e2badb2..7b4f9d4f4f 100644
--- a/drivers/common/cnxk/roc_dpi.h
+++ b/drivers/common/cnxk/roc_dpi.h
@@ -16,7 +16,10 @@ int __roc_api roc_dpi_dev_fini(struct roc_dpi *roc_dpi);

 int __roc_api roc_dpi_configure(struct roc_dpi *dpi, uint32_t chunk_sz, uint64_t aura,
 				uint64_t chunk_base);
+int __roc_api roc_dpi_configure_v2(struct roc_dpi *roc_dpi, uint32_t chunk_sz, uint64_t aura,
+				   uint64_t chunk_base);
 int __roc_api roc_dpi_enable(struct roc_dpi *dpi);
+int __roc_api roc_dpi_wait_queue_idle(struct roc_dpi *dpi);
 int __roc_api roc_dpi_disable(struct roc_dpi *dpi);

 #endif
diff --git a/drivers/common/cnxk/roc_dpi_priv.h b/drivers/common/cnxk/roc_dpi_priv.h
index 52962c8bc0..844e5f37ee 100644
--- a/drivers/common/cnxk/roc_dpi_priv.h
+++ b/drivers/common/cnxk/roc_dpi_priv.h
@@ -15,6 +15,9 @@
 #define DPI_QUEUE_CLOSE 0x2
 #define DPI_REG_DUMP	0x3
 #define DPI_GET_REG_CFG 0x4
+#define DPI_QUEUE_OPEN_V2 0x5
+
+#define DPI_QUEUE_IDLE_TMO_MS 1E3

 typedef union dpi_mbox_msg_t {
 	uint64_t u[2];
diff --git a/drivers/common/cnxk/version.map b/drivers/common/cnxk/version.map
index 424ad7f484..cc9f47e0ad 100644
--- a/drivers/common/cnxk/version.map
+++ b/drivers/common/cnxk/version.map
@@ -82,10 +82,12 @@ INTERNAL {
 	roc_cpt_int_misc_cb_register;
 	roc_cpt_int_misc_cb_unregister;
 	roc_dpi_configure;
+	roc_dpi_configure_v2;
 	roc_dpi_dev_fini;
 	roc_dpi_dev_init;
 	roc_dpi_disable;
 	roc_dpi_enable;
+	roc_dpi_wait_queue_idle;
 	roc_error_msg_get;
 	roc_eswitch_nix_process_repte_notify_cb_register;
 	roc_eswitch_nix_process_repte_notify_cb_unregister;
diff --git a/drivers/dma/cnxk/cnxk_dmadev.c b/drivers/dma/cnxk/cnxk_dmadev.c
index 4ab3cfbdf2..2de0a0a3ce 100644
--- a/drivers/dma/cnxk/cnxk_dmadev.c
+++ b/drivers/dma/cnxk/cnxk_dmadev.c
@@ -291,6 +291,7 @@ cnxk_dmadev_start(struct rte_dma_dev *dev)
 	struct cnxk_dpi_vf_s *dpivf = dev->fp_obj->dev_private;
 	struct cnxk_dpi_conf *dpi_conf;
 	uint32_t chunks, nb_desc = 0;
+	uint32_t queue_buf_sz;
 	int i, j, rc = 0;
 	void *chunk;

@@ -310,34 +311,44 @@ cnxk_dmadev_start(struct rte_dma_dev *dev)
 		dpi_conf->completed_offset = 0;
 	}

-	chunks = CNXK_DPI_CHUNKS_FROM_DESC(CNXK_DPI_QUEUE_BUF_SIZE, nb_desc);
-	rc = cnxk_dmadev_chunk_pool_create(dev, chunks, CNXK_DPI_QUEUE_BUF_SIZE);
+	queue_buf_sz = CNXK_DPI_QUEUE_BUF_SIZE_V2;
+	/* Max block size allowed by cnxk mempool driver is (128 * 1024).
+	 * Block size = elt_size + mp->header + mp->trailer.
+	 *
+	 * Note from cn9k mempool driver:
+	 * In cn9k additional padding of 128 bytes is added to mempool->trailer to
+	 * ensure that the element size always occupies odd number of cachelines
+	 * to ensure even distribution of elements among L1D cache sets.
+	 */
+	if (!roc_model_is_cn10k())
+		queue_buf_sz = CNXK_DPI_QUEUE_BUF_SIZE_V2 - 128;
+
+	chunks = CNXK_DPI_CHUNKS_FROM_DESC(queue_buf_sz, nb_desc);
+	rc = cnxk_dmadev_chunk_pool_create(dev, chunks, queue_buf_sz);
 	if (rc < 0) {
 		plt_err("DMA pool configure failed err = %d", rc);
-		goto done;
+		goto error;
 	}

 	rc = rte_mempool_get(dpivf->chunk_pool, &chunk);
 	if (rc < 0) {
 		plt_err("DMA failed to get chunk pointer err = %d", rc);
 		rte_mempool_free(dpivf->chunk_pool);
-		goto done;
+		goto error;
 	}

-	rc = roc_dpi_configure(&dpivf->rdpi, CNXK_DPI_QUEUE_BUF_SIZE, dpivf->aura, (uint64_t)chunk);
+	rc = roc_dpi_configure_v2(&dpivf->rdpi, queue_buf_sz, dpivf->aura, (uint64_t)chunk);
 	if (rc < 0) {
 		plt_err("DMA configure failed err = %d", rc);
 		rte_mempool_free(dpivf->chunk_pool);
-		goto done;
+		goto error;
 	}
-
 	dpivf->chunk_base = chunk;
 	dpivf->chunk_head = 0;
-	dpivf->chunk_size_m1 = (CNXK_DPI_QUEUE_BUF_SIZE >> 3) - 2;
+	dpivf->chunk_size_m1 = (queue_buf_sz >> 3) - 2;

 	roc_dpi_enable(&dpivf->rdpi);
-
-done:
+error:
 	return rc;
 }

@@ -345,11 +356,9 @@ static int
 cnxk_dmadev_stop(struct rte_dma_dev *dev)
 {
 	struct cnxk_dpi_vf_s *dpivf = dev->fp_obj->dev_private;
-	uint64_t reg;

-	reg = plt_read64(dpivf->rdpi.rbase + DPI_VDMA_SADDR);
-	while (!(reg & BIT_ULL(63)))
-		reg = plt_read64(dpivf->rdpi.rbase + DPI_VDMA_SADDR);
+	if (roc_dpi_wait_queue_idle(&dpivf->rdpi))
+		return -EAGAIN;

 	roc_dpi_disable(&dpivf->rdpi);
 	rte_mempool_free(dpivf->chunk_pool);
diff --git a/drivers/dma/cnxk/cnxk_dmadev.h b/drivers/dma/cnxk/cnxk_dmadev.h
index 610a360ba2..3d8f875ada 100644
--- a/drivers/dma/cnxk/cnxk_dmadev.h
+++ b/drivers/dma/cnxk/cnxk_dmadev.h
@@ -30,6 +30,7 @@
 #define CNXK_DPI_MIN_DESC		    2
 #define CNXK_DPI_MAX_VCHANS_PER_QUEUE	    4
 #define CNXK_DPI_QUEUE_BUF_SIZE		    16256
+#define CNXK_DPI_QUEUE_BUF_SIZE_V2	    130944
 #define CNXK_DPI_POOL_MAX_CACHE_SZ	    (16)
 #define CNXK_DPI_DW_PER_SINGLE_CMD	    8
 #define CNXK_DPI_HDR_LEN		    4
--
2.25.1