[dpdk-dev] [PATCH v6 6/9] baseband/la12xx: add enqueue and dequeue support

[nipun.gupta@nxp.com]

From: Hemant Agrawal <hemant.agrawal@nxp.com>

Add support for enqueue and dequeue the LDPC enc/dec
from the modem device.

Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 doc/guides/bbdevs/features/la12xx.ini      |  13 +
 doc/guides/bbdevs/la12xx.rst               |  47 ++-
 drivers/baseband/la12xx/bbdev_la12xx.c     | 328 ++++++++++++++++++++-
 drivers/baseband/la12xx/bbdev_la12xx_ipc.h |  37 +++
 4 files changed, 420 insertions(+), 5 deletions(-)
 create mode 100644 doc/guides/bbdevs/features/la12xx.ini

diff --git a/doc/guides/bbdevs/features/la12xx.ini b/doc/guides/bbdevs/features/la12xx.ini
new file mode 100644
index 0000000000..0aec5eecb6
--- /dev/null
+++ b/doc/guides/bbdevs/features/la12xx.ini
@@ -0,0 +1,13 @@
+;
+; Supported features of the 'la12xx' bbdev driver.
+;
+; Refer to default.ini for the full list of available PMD features.
+;
+[Features]
+Turbo Decoder (4G)     = N
+Turbo Encoder (4G)     = N
+LDPC Decoder (5G)      = Y
+LDPC Encoder (5G)      = Y
+LLR/HARQ Compression   = N
+HW Accelerated         = Y
+BBDEV API              = Y
diff --git a/doc/guides/bbdevs/la12xx.rst b/doc/guides/bbdevs/la12xx.rst
index 3c9ac5c047..b111ec0dd6 100644
--- a/doc/guides/bbdevs/la12xx.rst
+++ b/doc/guides/bbdevs/la12xx.rst
@@ -16,10 +16,11 @@ Features
 
 LA12xx PMD supports the following features:
 
+- LDPC Encode in the DL
+- LDPC Decode in the UL
 - Maximum of 8 UL queues
 - Maximum of 8 DL queues
 - PCIe Gen-3 x8 Interface
-- MSI-X
 
 Installation
 ------------
@@ -79,3 +80,47 @@ For enabling logs, use the following EAL parameter:
 
 Using ``bb.la12xx`` as log matching criteria, all Baseband PMD logs can be
 enabled which are lower than logging ``level``.
+
+Test Application
+----------------
+
+BBDEV provides a test application, ``test-bbdev.py`` and range of test data for testing
+the functionality of LA12xx for FEC encode and decode, depending on the device
+capabilities. The test application is located under app->test-bbdev folder and has the
+following options:
+
+.. code-block:: console
+
+  "-p", "--testapp-path": specifies path to the bbdev test app.
+  "-e", "--eal-params"	: EAL arguments which are passed to the test app.
+  "-t", "--timeout"	: Timeout in seconds (default=300).
+  "-c", "--test-cases"	: Defines test cases to run. Run all if not specified.
+  "-v", "--test-vector"	: Test vector path (default=dpdk_path+/app/test-bbdev/test_vectors/bbdev_null.data).
+  "-n", "--num-ops"	: Number of operations to process on device (default=32).
+  "-b", "--burst-size"	: Operations enqueue/dequeue burst size (default=32).
+  "-s", "--snr"		: SNR in dB used when generating LLRs for bler tests.
+  "-s", "--iter_max"	: Number of iterations for LDPC decoder.
+  "-l", "--num-lcores"	: Number of lcores to run (default=16).
+  "-i", "--init-device" : Initialise PF device with default values.
+
+
+To execute the test application tool using simple decode or encode data,
+type one of the following:
+
+.. code-block:: console
+
+  ./test-bbdev.py -e="--vdev=baseband_la12xx,socket_id=0,max_nb_queues=8" -c validation -n 64 -b 1 -v ./ldpc_dec_default.data
+  ./test-bbdev.py -e="--vdev=baseband_la12xx,socket_id=0,max_nb_queues=8" -c validation -n 64 -b 1 -v ./ldpc_enc_default.data
+
+The test application ``test-bbdev.py``, supports the ability to configure the PF device with
+a default set of values, if the "-i" or "- -init-device" option is included. The default values
+are defined in test_bbdev_perf.c.
+
+
+Test Vectors
+~~~~~~~~~~~~
+
+In addition to the simple LDPC decoder and LDPC encoder tests, bbdev also provides
+a range of additional tests under the test_vectors folder, which may be useful. The results
+of these tests will depend on the LA12xx FEC capabilities which may cause some
+testcases to be skipped, but no failure should be reported.
diff --git a/drivers/baseband/la12xx/bbdev_la12xx.c b/drivers/baseband/la12xx/bbdev_la12xx.c
index c758fe3833..fa16660a77 100644
--- a/drivers/baseband/la12xx/bbdev_la12xx.c
+++ b/drivers/baseband/la12xx/bbdev_la12xx.c
@@ -122,6 +122,10 @@ la12xx_queue_release(struct rte_bbdev *dev, uint16_t q_id)
 		((uint64_t) ((unsigned long) (A) \
 		- ((uint64_t)ipc_priv->hugepg_start.host_vaddr)))
 
+#define MODEM_P2V(A) \
+	((uint64_t) ((unsigned long) (A) \
+		+ (unsigned long)(ipc_priv->peb_start.host_vaddr)))
+
 static int ipc_queue_configure(uint32_t channel_id,
 		ipc_t instance, struct bbdev_la12xx_q_priv *q_priv)
 {
@@ -336,6 +340,318 @@ static const struct rte_bbdev_ops pmd_ops = {
 	.queue_release = la12xx_queue_release,
 	.start = la12xx_start
 };
+
+static inline int
+is_bd_ring_full(uint32_t ci, uint32_t ci_flag,
+		uint32_t pi, uint32_t pi_flag)
+{
+	if (pi == ci) {
+		if (pi_flag != ci_flag)
+			return 1; /* Ring is Full */
+	}
+	return 0;
+}
+
+static inline int
+prepare_ldpc_enc_op(struct rte_bbdev_enc_op *bbdev_enc_op,
+		    struct bbdev_la12xx_q_priv *q_priv __rte_unused,
+		    struct rte_bbdev_op_data *in_op_data __rte_unused,
+		    struct rte_bbdev_op_data *out_op_data)
+{
+	struct rte_bbdev_op_ldpc_enc *ldpc_enc = &bbdev_enc_op->ldpc_enc;
+	uint32_t total_out_bits;
+
+	total_out_bits = (ldpc_enc->tb_params.cab *
+		ldpc_enc->tb_params.ea) + (ldpc_enc->tb_params.c -
+		ldpc_enc->tb_params.cab) * ldpc_enc->tb_params.eb;
+
+	ldpc_enc->output.length = (total_out_bits + 7)/8;
+
+	rte_pktmbuf_append(out_op_data->data, ldpc_enc->output.length);
+
+	return 0;
+}
+
+static inline int
+prepare_ldpc_dec_op(struct rte_bbdev_dec_op *bbdev_dec_op,
+		    struct bbdev_ipc_dequeue_op *bbdev_ipc_op,
+		    struct bbdev_la12xx_q_priv *q_priv  __rte_unused,
+		    struct rte_bbdev_op_data *out_op_data  __rte_unused)
+{
+	struct rte_bbdev_op_ldpc_dec *ldpc_dec = &bbdev_dec_op->ldpc_dec;
+	uint32_t total_out_bits;
+	uint32_t num_code_blocks = 0;
+	uint16_t sys_cols;
+
+	sys_cols = (ldpc_dec->basegraph == 1) ? 22 : 10;
+	if (ldpc_dec->tb_params.c == 1) {
+		total_out_bits = ((sys_cols * ldpc_dec->z_c) -
+				ldpc_dec->n_filler);
+		/* 5G-NR protocol uses 16 bit CRC when output packet
+		 * size <= 3824 (bits). Otherwise 24 bit CRC is used.
+		 * Adjust the output bits accordingly
+		 */
+		if (total_out_bits - 16 <= 3824)
+			total_out_bits -= 16;
+		else
+			total_out_bits -= 24;
+		ldpc_dec->hard_output.length = (total_out_bits / 8);
+	} else {
+		total_out_bits = (((sys_cols * ldpc_dec->z_c) -
+				ldpc_dec->n_filler - 24) *
+				ldpc_dec->tb_params.c);
+		ldpc_dec->hard_output.length = (total_out_bits / 8) - 3;
+	}
+
+	num_code_blocks = ldpc_dec->tb_params.c;
+
+	bbdev_ipc_op->num_code_blocks = rte_cpu_to_be_32(num_code_blocks);
+
+	return 0;
+}
+
+static int
+enqueue_single_op(struct bbdev_la12xx_q_priv *q_priv, void *bbdev_op)
+{
+	struct bbdev_la12xx_private *priv = q_priv->bbdev_priv;
+	ipc_userspace_t *ipc_priv = priv->ipc_priv;
+	ipc_instance_t *ipc_instance = ipc_priv->instance;
+	struct bbdev_ipc_dequeue_op *bbdev_ipc_op;
+	struct rte_bbdev_op_ldpc_enc *ldpc_enc;
+	struct rte_bbdev_op_ldpc_dec *ldpc_dec;
+	uint32_t q_id = q_priv->q_id;
+	uint32_t ci, ci_flag, pi, pi_flag;
+	ipc_ch_t *ch = &(ipc_instance->ch_list[q_id]);
+	ipc_br_md_t *md = &(ch->md);
+	size_t virt;
+	char *huge_start_addr =
+		(char *)q_priv->bbdev_priv->ipc_priv->hugepg_start.host_vaddr;
+	struct rte_bbdev_op_data *in_op_data, *out_op_data;
+	char *data_ptr;
+	uint32_t l1_pcie_addr;
+	int ret;
+
+	ci = IPC_GET_CI_INDEX(q_priv->host_ci);
+	ci_flag = IPC_GET_CI_FLAG(q_priv->host_ci);
+
+	pi = IPC_GET_PI_INDEX(q_priv->host_pi);
+	pi_flag = IPC_GET_PI_FLAG(q_priv->host_pi);
+
+	rte_bbdev_dp_log(DEBUG, "before bd_ring_full: pi: %u, ci: %u,"
+		"pi_flag: %u, ci_flag: %u, ring size: %u",
+		pi, ci, pi_flag, ci_flag, q_priv->queue_size);
+
+	if (is_bd_ring_full(ci, ci_flag, pi, pi_flag)) {
+		rte_bbdev_dp_log(DEBUG, "bd ring full for queue id: %d", q_id);
+		return IPC_CH_FULL;
+	}
+
+	virt = MODEM_P2V(q_priv->host_params->bd_m_modem_ptr[pi]);
+	bbdev_ipc_op = (struct bbdev_ipc_dequeue_op *)virt;
+	q_priv->bbdev_op[pi] = bbdev_op;
+
+	switch (q_priv->op_type) {
+	case RTE_BBDEV_OP_LDPC_ENC:
+		ldpc_enc = &(((struct rte_bbdev_enc_op *)bbdev_op)->ldpc_enc);
+		in_op_data = &ldpc_enc->input;
+		out_op_data = &ldpc_enc->output;
+
+		ret = prepare_ldpc_enc_op(bbdev_op, q_priv,
+					  in_op_data, out_op_data);
+		if (ret) {
+			rte_bbdev_log(ERR, "process_ldpc_enc_op fail, ret: %d",
+				ret);
+			return ret;
+		}
+		break;
+
+	case RTE_BBDEV_OP_LDPC_DEC:
+		ldpc_dec = &(((struct rte_bbdev_dec_op *)bbdev_op)->ldpc_dec);
+		in_op_data = &ldpc_dec->input;
+
+		out_op_data = &ldpc_dec->hard_output;
+
+		ret = prepare_ldpc_dec_op(bbdev_op, bbdev_ipc_op,
+					  q_priv, out_op_data);
+		if (ret) {
+			rte_bbdev_log(ERR, "process_ldpc_dec_op fail, ret: %d",
+				ret);
+			return ret;
+		}
+		break;
+
+	default:
+		rte_bbdev_log(ERR, "unsupported bbdev_ipc op type");
+		return -1;
+	}
+
+	if (in_op_data->data) {
+		data_ptr = rte_pktmbuf_mtod(in_op_data->data, char *);
+		l1_pcie_addr = (uint32_t)GUL_USER_HUGE_PAGE_ADDR +
+			       data_ptr - huge_start_addr;
+		bbdev_ipc_op->in_addr = l1_pcie_addr;
+		bbdev_ipc_op->in_len = in_op_data->length;
+	}
+
+	if (out_op_data->data) {
+		data_ptr = rte_pktmbuf_mtod(out_op_data->data, char *);
+		l1_pcie_addr = (uint32_t)GUL_USER_HUGE_PAGE_ADDR +
+				data_ptr - huge_start_addr;
+		bbdev_ipc_op->out_addr = rte_cpu_to_be_32(l1_pcie_addr);
+		bbdev_ipc_op->out_len = rte_cpu_to_be_32(out_op_data->length);
+	}
+
+	/* Move Producer Index forward */
+	pi++;
+	/* Flip the PI flag, if wrapping */
+	if (unlikely(q_priv->queue_size == pi)) {
+		pi = 0;
+		pi_flag = pi_flag ? 0 : 1;
+	}
+
+	if (pi_flag)
+		IPC_SET_PI_FLAG(pi);
+	else
+		IPC_RESET_PI_FLAG(pi);
+	q_priv->host_pi = pi;
+
+	/* Wait for Data Copy & pi_flag update to complete before updating pi */
+	rte_mb();
+	/* now update pi */
+	md->pi = rte_cpu_to_be_32(pi);
+
+	rte_bbdev_dp_log(DEBUG, "enter: pi: %u, ci: %u,"
+			"pi_flag: %u, ci_flag: %u, ring size: %u",
+			pi, ci, pi_flag, ci_flag, q_priv->queue_size);
+
+	return 0;
+}
+
+/* Enqueue decode burst */
+static uint16_t
+enqueue_dec_ops(struct rte_bbdev_queue_data *q_data,
+		struct rte_bbdev_dec_op **ops, uint16_t nb_ops)
+{
+	struct bbdev_la12xx_q_priv *q_priv = q_data->queue_private;
+	int nb_enqueued, ret;
+
+	for (nb_enqueued = 0; nb_enqueued < nb_ops; nb_enqueued++) {
+		ret = enqueue_single_op(q_priv, ops[nb_enqueued]);
+		if (ret)
+			break;
+	}
+
+	q_data->queue_stats.enqueue_err_count += nb_ops - nb_enqueued;
+	q_data->queue_stats.enqueued_count += nb_enqueued;
+
+	return nb_enqueued;
+}
+
+/* Enqueue encode burst */
+static uint16_t
+enqueue_enc_ops(struct rte_bbdev_queue_data *q_data,
+		struct rte_bbdev_enc_op **ops, uint16_t nb_ops)
+{
+	struct bbdev_la12xx_q_priv *q_priv = q_data->queue_private;
+	int nb_enqueued, ret;
+
+	for (nb_enqueued = 0; nb_enqueued < nb_ops; nb_enqueued++) {
+		ret = enqueue_single_op(q_priv, ops[nb_enqueued]);
+		if (ret)
+			break;
+	}
+
+	q_data->queue_stats.enqueue_err_count += nb_ops - nb_enqueued;
+	q_data->queue_stats.enqueued_count += nb_enqueued;
+
+	return nb_enqueued;
+}
+
+/* Dequeue encode burst */
+static void *
+dequeue_single_op(struct bbdev_la12xx_q_priv *q_priv, void *dst)
+{
+	void *op;
+	uint32_t ci, ci_flag;
+	uint32_t temp_ci;
+
+	temp_ci = q_priv->host_params->ci;
+	if (temp_ci == q_priv->host_ci)
+		return NULL;
+
+	ci = IPC_GET_CI_INDEX(q_priv->host_ci);
+	ci_flag = IPC_GET_CI_FLAG(q_priv->host_ci);
+
+	rte_bbdev_dp_log(DEBUG,
+		"ci: %u, ci_flag: %u, ring size: %u",
+		ci, ci_flag, q_priv->queue_size);
+
+	op = q_priv->bbdev_op[ci];
+
+	rte_memcpy(dst, q_priv->msg_ch_vaddr[ci],
+		sizeof(struct bbdev_ipc_enqueue_op));
+
+	/* Move Consumer Index forward */
+	ci++;
+	/* Flip the CI flag, if wrapping */
+	if (q_priv->queue_size == ci) {
+		ci = 0;
+		ci_flag = ci_flag ? 0 : 1;
+	}
+	if (ci_flag)
+		IPC_SET_CI_FLAG(ci);
+	else
+		IPC_RESET_CI_FLAG(ci);
+
+	q_priv->host_ci = ci;
+
+	rte_bbdev_dp_log(DEBUG,
+		"exit: ci: %u, ci_flag: %u, ring size: %u",
+		ci, ci_flag, q_priv->queue_size);
+
+	return op;
+}
+
+/* Dequeue decode burst */
+static uint16_t
+dequeue_dec_ops(struct rte_bbdev_queue_data *q_data,
+		struct rte_bbdev_dec_op **ops, uint16_t nb_ops)
+{
+	struct bbdev_la12xx_q_priv *q_priv = q_data->queue_private;
+	struct bbdev_ipc_enqueue_op bbdev_ipc_op;
+	int nb_dequeued;
+
+	for (nb_dequeued = 0; nb_dequeued < nb_ops; nb_dequeued++) {
+		ops[nb_dequeued] = dequeue_single_op(q_priv, &bbdev_ipc_op);
+		if (!ops[nb_dequeued])
+			break;
+		ops[nb_dequeued]->status = bbdev_ipc_op.status;
+	}
+	q_data->queue_stats.dequeued_count += nb_dequeued;
+
+	return nb_dequeued;
+}
+
+/* Dequeue encode burst */
+static uint16_t
+dequeue_enc_ops(struct rte_bbdev_queue_data *q_data,
+		struct rte_bbdev_enc_op **ops, uint16_t nb_ops)
+{
+	struct bbdev_la12xx_q_priv *q_priv = q_data->queue_private;
+	struct bbdev_ipc_enqueue_op bbdev_ipc_op;
+	int nb_enqueued;
+
+	for (nb_enqueued = 0; nb_enqueued < nb_ops; nb_enqueued++) {
+		ops[nb_enqueued] = dequeue_single_op(q_priv, &bbdev_ipc_op);
+		if (!ops[nb_enqueued])
+			break;
+		ops[nb_enqueued]->status = bbdev_ipc_op.status;
+	}
+	q_data->queue_stats.enqueued_count += nb_enqueued;
+
+	return nb_enqueued;
+}
+
 static struct hugepage_info *
 get_hugepage_info(void)
 {
@@ -709,10 +1025,14 @@ la12xx_bbdev_create(struct rte_vdev_device *vdev,
 	bbdev->intr_handle = NULL;
 
 	/* register rx/tx burst functions for data path */
-	bbdev->dequeue_enc_ops = NULL;
-	bbdev->dequeue_dec_ops = NULL;
-	bbdev->enqueue_enc_ops = NULL;
-	bbdev->enqueue_dec_ops = NULL;
+	bbdev->dequeue_enc_ops = dequeue_enc_ops;
+	bbdev->dequeue_dec_ops = dequeue_dec_ops;
+	bbdev->enqueue_enc_ops = enqueue_enc_ops;
+	bbdev->enqueue_dec_ops = enqueue_dec_ops;
+	bbdev->dequeue_ldpc_enc_ops = dequeue_enc_ops;
+	bbdev->dequeue_ldpc_dec_ops = dequeue_dec_ops;
+	bbdev->enqueue_ldpc_enc_ops = enqueue_enc_ops;
+	bbdev->enqueue_ldpc_dec_ops = enqueue_dec_ops;
 
 	return 0;
 }
diff --git a/drivers/baseband/la12xx/bbdev_la12xx_ipc.h b/drivers/baseband/la12xx/bbdev_la12xx_ipc.h
index 5f613fb087..b6a7f677d0 100644
--- a/drivers/baseband/la12xx/bbdev_la12xx_ipc.h
+++ b/drivers/baseband/la12xx/bbdev_la12xx_ipc.h
@@ -73,6 +73,25 @@ typedef struct {
 	_IOWR(GUL_IPC_MAGIC, 5, struct ipc_msg *)
 #define IOCTL_GUL_IPC_CHANNEL_RAISE_INTERRUPT _IOW(GUL_IPC_MAGIC, 6, int *)
 
+#define GUL_USER_HUGE_PAGE_OFFSET	(0)
+#define GUL_PCI1_ADDR_BASE	(0x00000000ULL)
+
+#define GUL_USER_HUGE_PAGE_ADDR	(GUL_PCI1_ADDR_BASE + GUL_USER_HUGE_PAGE_OFFSET)
+
+/* IPC PI/CI index & flag manipulation helpers */
+#define IPC_PI_CI_FLAG_MASK	0x80000000 /*  (1<<31) */
+#define IPC_PI_CI_INDEX_MASK	0x7FFFFFFF /* ~(1<<31) */
+
+#define IPC_SET_PI_FLAG(x)	(x |= IPC_PI_CI_FLAG_MASK)
+#define IPC_RESET_PI_FLAG(x)	(x &= IPC_PI_CI_INDEX_MASK)
+#define IPC_GET_PI_FLAG(x)	(x >> 31)
+#define IPC_GET_PI_INDEX(x)	(x & IPC_PI_CI_INDEX_MASK)
+
+#define IPC_SET_CI_FLAG(x)	(x |= IPC_PI_CI_FLAG_MASK)
+#define IPC_RESET_CI_FLAG(x)	(x &= IPC_PI_CI_INDEX_MASK)
+#define IPC_GET_CI_FLAG(x)	(x >> 31)
+#define IPC_GET_CI_INDEX(x)	(x & IPC_PI_CI_INDEX_MASK)
+
 /** buffer ring common metadata */
 typedef struct ipc_bd_ring_md {
 	volatile uint32_t pi;		/**< Producer index and flag (MSB)
@@ -180,6 +199,24 @@ struct bbdev_ipc_enqueue_op {
 	uint32_t rsvd;
 };
 
+/** Structure specifying dequeue operation (dequeue at LA1224) */
+struct bbdev_ipc_dequeue_op {
+	/** Input buffer memory address */
+	uint32_t in_addr;
+	/** Input buffer memory length */
+	uint32_t in_len;
+	/** Output buffer memory address */
+	uint32_t out_addr;
+	/** Output buffer memory length */
+	uint32_t out_len;
+	/* Number of code blocks. Only set when HARQ is used */
+	uint32_t num_code_blocks;
+	/** Dequeue Operation flags */
+	uint32_t op_flags;
+	/** Shared metadata between L1 and L2 */
+	uint32_t shared_metadata;
+};
+
 /* This shared memory would be on the host side which have copy of some
  * of the parameters which are also part of Shared BD ring. Read access
  * of these parameters from the host side would not be over PCI.
-- 
2.17.1