[v7 11/15] dma/dpaa: add workaround for ERR050757

[Gagandeep Singh <g.singh@nxp.com>]

From: Jun Yang <jun.yang@nxp.com>

ERR050757 on LS104x indicates:

For outbound PCIe read transactions, a completion buffer is used
to store the PCIe completions till the data is passed back to the
initiator. At most 16 outstanding transactions are allowed and
maximum read request is 256 bytes. The completion buffer size
inside the controller needs to be at least 4KB, but the PCIe
controller has 3 KB of buffer. In case the size of pending
outbound read transactions of more than 3KB, the PCIe controller
may drop the incoming completions without notifying the initiator
of the transaction, leaving transactions unfinished. All
subsequent outbound reads to PCIe are blocked permanently.
To avoid qDMA hang as it keeps waiting for data that was silently
dropped, set stride mode for qDMA.

Signed-off-by: Jun Yang <jun.yang@nxp.com>
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
---
 config/arm/meson.build       |  3 ++-
 doc/guides/dmadevs/dpaa.rst  |  2 ++
 drivers/dma/dpaa/dpaa_qdma.c | 38 +++++++++++++++++++++++++++++++++---
 drivers/dma/dpaa/dpaa_qdma.h | 19 +++++++-----------
 4 files changed, 46 insertions(+), 16 deletions(-)

diff --git a/config/arm/meson.build b/config/arm/meson.build
index a3bdcf1aa2..e49a5f64f0 100644
--- a/config/arm/meson.build
+++ b/config/arm/meson.build
@@ -488,7 +488,8 @@ soc_dpaa = {
         ['RTE_MACHINE', '"dpaa"'],
         ['RTE_LIBRTE_DPAA2_USE_PHYS_IOVA', false],
         ['RTE_MAX_LCORE', 16],
-        ['RTE_MAX_NUMA_NODES', 1]
+        ['RTE_MAX_NUMA_NODES', 1],
+	['RTE_DMA_DPAA_ERRATA_ERR050757', true]
     ],
     'numa': false
 }
diff --git a/doc/guides/dmadevs/dpaa.rst b/doc/guides/dmadevs/dpaa.rst
index f99bfc6087..746919ec6b 100644
--- a/doc/guides/dmadevs/dpaa.rst
+++ b/doc/guides/dmadevs/dpaa.rst
@@ -42,6 +42,8 @@ Compilation
 For builds using ``meson`` and ``ninja``, the driver will be built when the
 target platform is dpaa-based. No additional compilation steps are necessary.
 
+- ``RTE_DMA_DPAA_ERRATA_ERR050757`` - enable software workaround for Errata-A050757
+
 Initialization
 --------------
 
diff --git a/drivers/dma/dpaa/dpaa_qdma.c b/drivers/dma/dpaa/dpaa_qdma.c
index 3ae87fdf80..ffc2a73a17 100644
--- a/drivers/dma/dpaa/dpaa_qdma.c
+++ b/drivers/dma/dpaa/dpaa_qdma.c
@@ -167,7 +167,6 @@ fsl_qdma_pre_comp_sd_desc(struct fsl_qdma_queue *queue)
 
 		/* Descriptor Buffer */
 		sdf->srttype = FSL_QDMA_CMD_RWTTYPE;
-
 		ddf->dwttype = FSL_QDMA_CMD_RWTTYPE;
 		ddf->lwc = FSL_QDMA_CMD_LWC;
 
@@ -449,8 +448,9 @@ fsl_qdma_reg_init(struct fsl_qdma_engine *fsl_qdma)
 
 			/* Initialize the queue mode. */
 			reg = FSL_QDMA_BCQMR_EN;
-			reg |= FSL_QDMA_BCQMR_CD_THLD(ilog2(temp->n_cq) - 4);
-			reg |= FSL_QDMA_BCQMR_CQ_SIZE(ilog2(temp->n_cq) - 6);
+			reg |= FSL_QDMA_BCQMR_CD_THLD(ilog2_qthld(temp->n_cq));
+			reg |= FSL_QDMA_BCQMR_CQ_SIZE(ilog2_qsize(temp->n_cq));
+			temp->le_cqmr = reg;
 			qdma_writel(reg, block + FSL_QDMA_BCQMR(i));
 		}
 
@@ -698,6 +698,9 @@ fsl_qdma_enqueue_desc_single(struct fsl_qdma_queue *fsl_queue,
 	struct fsl_qdma_comp_sg_desc *csgf_src, *csgf_dest;
 	struct fsl_qdma_cmpd_ft *ft;
 	int ret;
+#ifdef RTE_DMA_DPAA_ERRATA_ERR050757
+	struct fsl_qdma_sdf *sdf;
+#endif
 
 	ret = fsl_qdma_enqueue_overflow(fsl_queue);
 	if (unlikely(ret))
@@ -705,6 +708,19 @@ fsl_qdma_enqueue_desc_single(struct fsl_qdma_queue *fsl_queue,
 
 	ft = fsl_queue->ft[fsl_queue->ci];
 
+#ifdef RTE_DMA_DPAA_ERRATA_ERR050757
+	sdf = &ft->df.sdf;
+	sdf->srttype = FSL_QDMA_CMD_RWTTYPE;
+	if (len > FSL_QDMA_CMD_SS_ERR050757_LEN) {
+		sdf->ssen = 1;
+		sdf->sss = FSL_QDMA_CMD_SS_ERR050757_LEN;
+		sdf->ssd = FSL_QDMA_CMD_SS_ERR050757_LEN;
+	} else {
+		sdf->ssen = 0;
+		sdf->sss = 0;
+		sdf->ssd = 0;
+	}
+#endif
 	csgf_src = &ft->desc_sbuf;
 	csgf_dest = &ft->desc_dbuf;
 	qdma_desc_sge_addr_set64(csgf_src, src);
@@ -737,6 +753,9 @@ fsl_qdma_enqueue_desc_sg(struct fsl_qdma_queue *fsl_queue)
 	uint32_t total_len;
 	uint16_t start, idx, num, i, next_idx;
 	int ret;
+#ifdef RTE_DMA_DPAA_ERRATA_ERR050757
+	struct fsl_qdma_sdf *sdf;
+#endif
 
 eq_sg:
 	total_len = 0;
@@ -802,6 +821,19 @@ fsl_qdma_enqueue_desc_sg(struct fsl_qdma_queue *fsl_queue)
 	ft->desc_dsge[num - 1].final = 1;
 	csgf_src->length = total_len;
 	csgf_dest->length = total_len;
+#ifdef RTE_DMA_DPAA_ERRATA_ERR050757
+	sdf = &ft->df.sdf;
+	sdf->srttype = FSL_QDMA_CMD_RWTTYPE;
+	if (total_len > FSL_QDMA_CMD_SS_ERR050757_LEN) {
+		sdf->ssen = 1;
+		sdf->sss = FSL_QDMA_CMD_SS_ERR050757_LEN;
+		sdf->ssd = FSL_QDMA_CMD_SS_ERR050757_LEN;
+	} else {
+		sdf->ssen = 0;
+		sdf->sss = 0;
+		sdf->ssd = 0;
+	}
+#endif
 	ret = fsl_qdma_enqueue_desc_to_ring(fsl_queue, num);
 	if (ret)
 		return ret;
diff --git a/drivers/dma/dpaa/dpaa_qdma.h b/drivers/dma/dpaa/dpaa_qdma.h
index 9b69db517e..171c093117 100644
--- a/drivers/dma/dpaa/dpaa_qdma.h
+++ b/drivers/dma/dpaa/dpaa_qdma.h
@@ -77,8 +77,6 @@
 #define FSL_QDMA_DMR_DQD		0x40000000
 #define FSL_QDMA_DSR_DB			0x80000000
 
-#define FSL_QDMA_COMMAND_BUFFER_SIZE	64
-#define FSL_QDMA_DESCRIPTOR_BUFFER_SIZE 32
 #define FSL_QDMA_CIRCULAR_DESC_SIZE_MIN	64
 #define FSL_QDMA_CIRCULAR_DESC_SIZE_MAX	16384
 #define FSL_QDMA_QUEUE_NUM_MAX		8
@@ -88,18 +86,15 @@
 #define FSL_QDMA_CMD_RWTTYPE		0x4
 #define FSL_QDMA_CMD_LWC		0x2
 
-#define FSL_QDMA_CMD_RWTTYPE_OFFSET	28
-#define FSL_QDMA_CMD_LWC_OFFSET		16
+#define FSL_QDMA_CMD_SS_ERR050757_LEN 128
 
 /* qdma engine attribute */
-#define QDMA_QUEUE_SIZE			64
-#define QDMA_STATUS_SIZE		64
-#define QDMA_CCSR_BASE			0x8380000
-#define VIRT_CHANNELS			32
-#define QDMA_BLOCK_OFFSET		0x10000
-#define QDMA_BLOCKS			4
-#define QDMA_QUEUES			8
-#define QDMA_DELAY			1000
+#define QDMA_QUEUE_SIZE FSL_QDMA_CIRCULAR_DESC_SIZE_MIN
+#define QDMA_STATUS_SIZE QDMA_QUEUE_SIZE
+#define QDMA_CCSR_BASE 0x8380000
+#define QDMA_BLOCK_OFFSET 0x10000
+#define QDMA_BLOCKS 4
+#define QDMA_QUEUES 8
 #define QDMA_QUEUE_CR_WM 32
 
 #define QDMA_BIG_ENDIAN			1
-- 
2.25.1