[PATCH 21/50] net/liquidio: add APIs to send packet to device

[Shijith Thotton <shijith.thotton@caviumnetworks.com>]

API to send control and data packets to device. Request list keeps
track of host buffers to be freed till it reaches device.

Signed-off-by: Shijith Thotton <shijith.thotton@caviumnetworks.com>
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Signed-off-by: Derek Chickles <derek.chickles@caviumnetworks.com>
Signed-off-by: Venkat Koppula <venkat.koppula@caviumnetworks.com>
Signed-off-by: Mallesham Jatharakonda <mjatharakonda@oneconvergence.com>
---
 drivers/net/liquidio/base/lio_hw_defs.h |  11 ++
 drivers/net/liquidio/lio_rxtx.c         | 180 ++++++++++++++++++++
 drivers/net/liquidio/lio_rxtx.h         | 291 ++++++++++++++++++++++++++++++++
 drivers/net/liquidio/lio_struct.h       |   6 +
 4 files changed, 488 insertions(+)

diff --git a/drivers/net/liquidio/base/lio_hw_defs.h b/drivers/net/liquidio/base/lio_hw_defs.h
index 2262de3..b581f44 100644
--- a/drivers/net/liquidio/base/lio_hw_defs.h
+++ b/drivers/net/liquidio/base/lio_hw_defs.h
@@ -76,6 +76,8 @@ enum lio_card_type {
 
 #define LIO_23XX_NAME "23xx"
 
+#define LIO_DEV_RUNNING		0xc
+
 #define LIO_NUM_DEF_TX_DESCS_CFG(cfg)					\
 		((cfg)->default_config->num_def_tx_descs)
 
@@ -93,6 +95,15 @@ enum lio_card_type {
 #define LIO_BASE_MINOR_VERSION		5
 #define LIO_BASE_MICRO_VERSION		1
 
+/** Tag types used by Octeon cores in its work. */
+enum octeon_tag_type {
+	OCTEON_ORDERED_TAG	= 0,
+	OCTEON_ATOMIC_TAG	= 1,
+};
+
+/* pre-defined host->NIC tag values */
+#define LIO_CONTROL	(0x11111110)
+
 /* Routines for reading and writing CSRs */
 #ifdef RTE_LIBRTE_LIO_DEBUG_REGS
 #define lio_write_csr(lio_dev, reg_off, value)				\
diff --git a/drivers/net/liquidio/lio_rxtx.c b/drivers/net/liquidio/lio_rxtx.c
index 515ba79..a1fadfa 100644
--- a/drivers/net/liquidio/lio_rxtx.c
+++ b/drivers/net/liquidio/lio_rxtx.c
@@ -207,6 +207,186 @@
 	lio_dev->num_iqs--;
 }
 
+static inline void
+lio_ring_doorbell(struct lio_device *lio_dev,
+		  struct lio_instr_queue *iq)
+{
+	if (rte_atomic64_read(&lio_dev->status) == LIO_DEV_RUNNING) {
+		rte_write32(iq->fill_cnt, iq->doorbell_reg);
+		/* make sure doorbell write goes through */
+		rte_wmb();
+		iq->fill_cnt = 0;
+	}
+}
+
+static inline void
+copy_cmd_into_iq(struct lio_instr_queue *iq, uint8_t *cmd)
+{
+	uint8_t *iqptr, cmdsize;
+
+	cmdsize = ((iq->iqcmd_64B) ? 64 : 32);
+	iqptr = iq->base_addr + (cmdsize * iq->host_write_index);
+
+	rte_memcpy(iqptr, cmd, cmdsize);
+}
+
+static inline struct lio_iq_post_status
+post_command2(struct lio_instr_queue *iq, uint8_t *cmd)
+{
+	struct lio_iq_post_status st;
+
+	st.status = LIO_IQ_SEND_OK;
+
+	/* This ensures that the read index does not wrap around to the same
+	 * position if queue gets full before Octeon could fetch any instr.
+	 */
+	if (rte_atomic64_read(&iq->instr_pending) >=
+			(int32_t)(iq->max_count - 1)) {
+		st.status = LIO_IQ_SEND_FAILED;
+		st.index = -1;
+		return st;
+	}
+
+	if (rte_atomic64_read(&iq->instr_pending) >=
+			(int32_t)(iq->max_count - 2))
+		st.status = LIO_IQ_SEND_STOP;
+
+	copy_cmd_into_iq(iq, cmd);
+
+	/* "index" is returned, host_write_index is modified. */
+	st.index = iq->host_write_index;
+	iq->host_write_index = lio_incr_index(iq->host_write_index, 1,
+					      iq->max_count);
+	iq->fill_cnt++;
+
+	/* Flush the command into memory. We need to be sure the data is in
+	 * memory before indicating that the instruction is pending.
+	 */
+	rte_wmb();
+
+	rte_atomic64_inc(&iq->instr_pending);
+
+	return st;
+}
+
+static inline void
+lio_add_to_request_list(struct lio_instr_queue *iq,
+			int idx, void *buf, int reqtype)
+{
+	iq->request_list[idx].buf = buf;
+	iq->request_list[idx].reqtype = reqtype;
+}
+
+static int
+lio_send_command(struct lio_device *lio_dev, uint32_t iq_no, void *cmd,
+		 void *buf, uint32_t datasize __rte_unused, uint32_t reqtype)
+{
+	struct lio_instr_queue *iq = lio_dev->instr_queue[iq_no];
+	struct lio_iq_post_status st;
+
+	rte_spinlock_lock(&iq->post_lock);
+
+	st = post_command2(iq, cmd);
+
+	if (st.status != LIO_IQ_SEND_FAILED) {
+		lio_add_to_request_list(iq, st.index, buf, reqtype);
+		lio_ring_doorbell(lio_dev, iq);
+	}
+
+	rte_spinlock_unlock(&iq->post_lock);
+
+	return st.status;
+}
+
+void
+lio_prepare_soft_command(struct lio_device *lio_dev,
+			 struct lio_soft_command *sc, uint8_t opcode,
+			 uint8_t subcode, uint32_t irh_ossp, uint64_t ossp0,
+			 uint64_t ossp1)
+{
+	struct octeon_instr_pki_ih3 *pki_ih3;
+	struct octeon_instr_ih3 *ih3;
+	struct octeon_instr_irh *irh;
+	struct octeon_instr_rdp *rdp;
+
+	RTE_ASSERT(opcode <= 15);
+	RTE_ASSERT(subcode <= 127);
+
+	ih3	  = (struct octeon_instr_ih3 *)&sc->cmd.cmd3.ih3;
+
+	ih3->pkind = lio_dev->instr_queue[sc->iq_no]->txpciq.s.pkind;
+
+	pki_ih3 = (struct octeon_instr_pki_ih3 *)&sc->cmd.cmd3.pki_ih3;
+
+	pki_ih3->w	= 1;
+	pki_ih3->raw	= 1;
+	pki_ih3->utag	= 1;
+	pki_ih3->uqpg	= lio_dev->instr_queue[sc->iq_no]->txpciq.s.use_qpg;
+	pki_ih3->utt	= 1;
+
+	pki_ih3->tag	= LIO_CONTROL;
+	pki_ih3->tagtype = OCTEON_ATOMIC_TAG;
+	pki_ih3->qpg	= lio_dev->instr_queue[sc->iq_no]->txpciq.s.qpg;
+	pki_ih3->pm	= 0x7;
+	pki_ih3->sl	= 8;
+
+	if (sc->datasize)
+		ih3->dlengsz = sc->datasize;
+
+	irh		= (struct octeon_instr_irh *)&sc->cmd.cmd3.irh;
+	irh->opcode	= opcode;
+	irh->subcode	= subcode;
+
+	/* opcode/subcode specific parameters (ossp) */
+	irh->ossp = irh_ossp;
+	sc->cmd.cmd3.ossp[0] = ossp0;
+	sc->cmd.cmd3.ossp[1] = ossp1;
+
+	if (sc->rdatasize) {
+		rdp = (struct octeon_instr_rdp *)&sc->cmd.cmd3.rdp;
+		rdp->pcie_port = lio_dev->pcie_port;
+		rdp->rlen      = sc->rdatasize;
+		irh->rflag = 1;
+		/* PKI IH3 */
+		ih3->fsz    = OCTEON_SOFT_CMD_RESP_IH3;
+	} else {
+		irh->rflag = 0;
+		/* PKI IH3 */
+		ih3->fsz    = OCTEON_PCI_CMD_O3;
+	}
+}
+
+int
+lio_send_soft_command(struct lio_device *lio_dev,
+		      struct lio_soft_command *sc)
+{
+	struct octeon_instr_ih3 *ih3;
+	struct octeon_instr_irh *irh;
+	uint32_t len = 0;
+
+	ih3 = (struct octeon_instr_ih3 *)&sc->cmd.cmd3.ih3;
+	if (ih3->dlengsz) {
+		RTE_ASSERT(sc->dmadptr);
+		sc->cmd.cmd3.dptr = sc->dmadptr;
+	}
+
+	irh = (struct octeon_instr_irh *)&sc->cmd.cmd3.irh;
+	if (irh->rflag) {
+		RTE_ASSERT(sc->dmarptr);
+		RTE_ASSERT(sc->status_word != NULL);
+		*sc->status_word = LIO_COMPLETION_WORD_INIT;
+		sc->cmd.cmd3.rptr = sc->dmarptr;
+	}
+
+	len = (uint32_t)ih3->dlengsz;
+
+	if (sc->wait_time)
+		sc->timeout = lio_uptime + sc->wait_time;
+
+	return lio_send_command(lio_dev, sc->iq_no, &sc->cmd, sc, len,
+				LIO_REQTYPE_SOFT_COMMAND);
+}
+
 int
 lio_setup_sc_buffer_pool(struct lio_device *lio_dev)
 {
diff --git a/drivers/net/liquidio/lio_rxtx.h b/drivers/net/liquidio/lio_rxtx.h
index 58e2a6e..d7b7194 100644
--- a/drivers/net/liquidio/lio_rxtx.h
+++ b/drivers/net/liquidio/lio_rxtx.h
@@ -50,11 +50,53 @@
 #define lio_uptime		\
 	(size_t)(rte_get_timer_cycles() / rte_get_timer_hz())
 
+#define LIO_IQ_SEND_OK		0
+#define LIO_IQ_SEND_STOP	1
+#define LIO_IQ_SEND_FAILED	-1
+
+/* conditions */
+#define LIO_REQTYPE_NONE		0
+#define LIO_REQTYPE_NORESP_NET		1
+#define LIO_REQTYPE_NORESP_NET_SG	2
+#define LIO_REQTYPE_SOFT_COMMAND	3
+
 struct lio_request_list {
 	uint32_t reqtype;
 	void *buf;
 };
 
+/*----------------------  INSTRUCTION FORMAT ----------------------------*/
+
+struct lio_instr3_64B {
+	/** Pointer where the input data is available. */
+	uint64_t dptr;
+
+	/** Instruction Header. */
+	uint64_t ih3;
+
+	/** Instruction Header. */
+	uint64_t pki_ih3;
+
+	/** Input Request Header. */
+	uint64_t irh;
+
+	/** opcode/subcode specific parameters */
+	uint64_t ossp[2];
+
+	/** Return Data Parameters */
+	uint64_t rdp;
+
+	/** Pointer where the response for a RAW mode packet will be written
+	 *  by Octeon.
+	 */
+	uint64_t rptr;
+
+};
+
+union lio_instr_64B {
+	struct lio_instr3_64B cmd3;
+};
+
 /** The size of each buffer in soft command buffer pool */
 #define LIO_SOFT_COMMAND_BUFFER_SIZE	1536
 
@@ -67,6 +109,9 @@ struct lio_soft_command {
 	uint64_t dma_addr;
 	uint32_t size;
 
+	/** Command and return status */
+	union lio_instr_64B cmd;
+
 #define LIO_COMPLETION_WORD_INIT	0xffffffffffffffffULL
 	uint64_t *status_word;
 
@@ -93,6 +138,230 @@ struct lio_soft_command {
 	struct rte_mbuf *mbuf;
 };
 
+struct lio_iq_post_status {
+	int status;
+	int index;
+};
+
+/*   wqe
+ *  ---------------  0
+ * |  wqe  word0-3 |
+ *  ---------------  32
+ * |    PCI IH     |
+ *  ---------------  40
+ * |     RPTR      |
+ *  ---------------  48
+ * |    PCI IRH    |
+ *  ---------------  56
+ * |    OCTEON_CMD |
+ *  ---------------  64
+ * | Addtl 8-BData |
+ * |               |
+ *  ---------------
+ */
+
+union octeon_cmd {
+	uint64_t cmd64;
+
+	struct	{
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+		uint64_t cmd : 5;
+
+		uint64_t more : 6; /* How many udd words follow the command */
+
+		uint64_t reserved : 29;
+
+		uint64_t param1 : 16;
+
+		uint64_t param2 : 8;
+
+#elif RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
+		uint64_t param2 : 8;
+
+		uint64_t param1 : 16;
+
+		uint64_t reserved : 29;
+
+		uint64_t more : 6;
+
+		uint64_t cmd : 5;
+
+#endif
+	} s;
+};
+
+#define OCTEON_CMD_SIZE (sizeof(union octeon_cmd))
+
+/* Instruction Header */
+struct octeon_instr_ih3 {
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+
+	/** Reserved3 */
+	uint64_t reserved3 : 1;
+
+	/** Gather indicator 1=gather*/
+	uint64_t gather : 1;
+
+	/** Data length OR no. of entries in gather list */
+	uint64_t dlengsz : 14;
+
+	/** Front Data size */
+	uint64_t fsz : 6;
+
+	/** Reserved2 */
+	uint64_t reserved2 : 4;
+
+	/** PKI port kind - PKIND */
+	uint64_t pkind : 6;
+
+	/** Reserved1 */
+	uint64_t reserved1 : 32;
+
+#elif RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	/** Reserved1 */
+	uint64_t reserved1 : 32;
+
+	/** PKI port kind - PKIND */
+	uint64_t pkind : 6;
+
+	/** Reserved2 */
+	uint64_t reserved2 : 4;
+
+	/** Front Data size */
+	uint64_t fsz : 6;
+
+	/** Data length OR no. of entries in gather list */
+	uint64_t dlengsz : 14;
+
+	/** Gather indicator 1=gather*/
+	uint64_t gather : 1;
+
+	/** Reserved3 */
+	uint64_t reserved3 : 1;
+
+#endif
+};
+
+/* PKI Instruction Header(PKI IH) */
+struct octeon_instr_pki_ih3 {
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+
+	/** Wider bit */
+	uint64_t w : 1;
+
+	/** Raw mode indicator 1 = RAW */
+	uint64_t raw : 1;
+
+	/** Use Tag */
+	uint64_t utag : 1;
+
+	/** Use QPG */
+	uint64_t uqpg : 1;
+
+	/** Reserved2 */
+	uint64_t reserved2 : 1;
+
+	/** Parse Mode */
+	uint64_t pm : 3;
+
+	/** Skip Length */
+	uint64_t sl : 8;
+
+	/** Use Tag Type */
+	uint64_t utt : 1;
+
+	/** Tag type */
+	uint64_t tagtype : 2;
+
+	/** Reserved1 */
+	uint64_t reserved1 : 2;
+
+	/** QPG Value */
+	uint64_t qpg : 11;
+
+	/** Tag Value */
+	uint64_t tag : 32;
+
+#elif RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
+	/** Tag Value */
+	uint64_t tag : 32;
+
+	/** QPG Value */
+	uint64_t qpg : 11;
+
+	/** Reserved1 */
+	uint64_t reserved1 : 2;
+
+	/** Tag type */
+	uint64_t tagtype : 2;
+
+	/** Use Tag Type */
+	uint64_t utt : 1;
+
+	/** Skip Length */
+	uint64_t sl : 8;
+
+	/** Parse Mode */
+	uint64_t pm : 3;
+
+	/** Reserved2 */
+	uint64_t reserved2 : 1;
+
+	/** Use QPG */
+	uint64_t uqpg : 1;
+
+	/** Use Tag */
+	uint64_t utag : 1;
+
+	/** Raw mode indicator 1 = RAW */
+	uint64_t raw : 1;
+
+	/** Wider bit */
+	uint64_t w : 1;
+#endif
+};
+
+/** Input Request Header */
+struct octeon_instr_irh {
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	uint64_t opcode : 4;
+	uint64_t rflag : 1;
+	uint64_t subcode : 7;
+	uint64_t vlan : 12;
+	uint64_t priority : 3;
+	uint64_t reserved : 5;
+	uint64_t ossp : 32; /* opcode/subcode specific parameters */
+#elif RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	uint64_t ossp : 32; /* opcode/subcode specific parameters */
+	uint64_t reserved : 5;
+	uint64_t priority : 3;
+	uint64_t vlan : 12;
+	uint64_t subcode : 7;
+	uint64_t rflag : 1;
+	uint64_t opcode : 4;
+#endif
+};
+
+/* pkiih3 + irh + ossp[0] + ossp[1] + rdp + rptr = 40 bytes */
+#define OCTEON_SOFT_CMD_RESP_IH3	(40 + 8)
+/* pki_h3 + irh + ossp[0] + ossp[1] = 32 bytes */
+#define OCTEON_PCI_CMD_O3		(24 + 8)
+
+/** Return Data Parameters */
+struct octeon_instr_rdp {
+#if RTE_BYTE_ORDER == RTE_BIG_ENDIAN
+	uint64_t reserved : 49;
+	uint64_t pcie_port : 3;
+	uint64_t rlen : 12;
+#elif RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+	uint64_t rlen : 12;
+	uint64_t pcie_port : 3;
+	uint64_t reserved : 49;
+#endif
+};
+
 int lio_setup_sc_buffer_pool(struct lio_device *lio_dev);
 void lio_free_sc_buffer_pool(struct lio_device *lio_dev);
 
@@ -100,6 +369,13 @@ struct lio_soft_command *
 lio_alloc_soft_command(struct lio_device *lio_dev,
 		       uint32_t datasize, uint32_t rdatasize,
 		       uint32_t ctxsize);
+void lio_prepare_soft_command(struct lio_device *lio_dev,
+			      struct lio_soft_command *sc,
+			      uint8_t opcode, uint8_t subcode,
+			      uint32_t irh_ossp, uint64_t ossp0,
+			      uint64_t ossp1);
+int lio_send_soft_command(struct lio_device *lio_dev,
+			  struct lio_soft_command *sc);
 void lio_free_soft_command(struct lio_soft_command *sc);
 
 /** Maximum ordered requests to process in every invocation of
@@ -167,6 +443,21 @@ enum {
 	}
 }
 
+/* Macro to increment index.
+ * Index is incremented by count; if the sum exceeds
+ * max, index is wrapped-around to the start.
+ */
+static inline uint32_t
+lio_incr_index(uint32_t index, uint32_t count, uint32_t max)
+{
+	if ((index + count) >= max)
+		index = index + count - max;
+	else
+		index += count;
+
+	return index;
+}
+
 /** Setup instruction queue zero for the device
  *  @param lio_dev which lio device to setup
  *
diff --git a/drivers/net/liquidio/lio_struct.h b/drivers/net/liquidio/lio_struct.h
index ad67ed1..7bbb0ba 100644
--- a/drivers/net/liquidio/lio_struct.h
+++ b/drivers/net/liquidio/lio_struct.h
@@ -288,6 +288,12 @@ struct lio_device {
 	uint16_t pf_num;
 	uint16_t vf_num;
 
+	/** This device's PCIe port used for traffic. */
+	uint16_t pcie_port;
+
+	/** The state of this device */
+	rte_atomic64_t status;
+
 	uint8_t *hw_addr;
 
 	struct lio_fn_list fn_list;
-- 
1.8.3.1