ixgbe: speed up non-vector Tx

[dpdk.git] / drivers / net / ixgbe / ixgbe_rxtx.h

diff --git a/drivers/net/ixgbe/ixgbe_rxtx.h b/drivers/net/ixgbe/ixgbe_rxtx.h
index 64e6bb9..f9e708f 100644 (file)
--- a/drivers/net/ixgbe/ixgbe_rxtx.h
+++ b/drivers/net/ixgbe/ixgbe_rxtx.h
@@ -34,29 +34,37 @@
 #ifndef _IXGBE_RXTX_H_
 #define _IXGBE_RXTX_H_
 
+/*
+ * Rings setup and release.
+ *
+ * TDBA/RDBA should be aligned on 16 byte boundary. But TDLEN/RDLEN should be
+ * multiple of 128 bytes. So we align TDBA/RDBA on 128 byte boundary. This will
+ * also optimize cache line size effect. H/W supports up to cache line size 128.
+ */
+#define        IXGBE_ALIGN     128
 
-#define RTE_PMD_IXGBE_TX_MAX_BURST 32
-#define RTE_PMD_IXGBE_RX_MAX_BURST 32
+#define IXGBE_RXD_ALIGN        (IXGBE_ALIGN / sizeof(union ixgbe_adv_rx_desc))
+#define IXGBE_TXD_ALIGN        (IXGBE_ALIGN / sizeof(union ixgbe_adv_tx_desc))
 
-#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC
-#define RTE_IXGBE_DESCS_PER_LOOP           4
-#elif defined(RTE_IXGBE_INC_VECTOR)
-#define RTE_IXGBE_DESCS_PER_LOOP           4
-#else
-#define RTE_IXGBE_DESCS_PER_LOOP           1
-#endif
+/*
+ * Maximum number of Ring Descriptors.
+ *
+ * Since RDLEN/TDLEN should be multiple of 128 bytes, the number of ring
+ * descriptors should meet the following condition:
+ *      (num_ring_desc * sizeof(rx/tx descriptor)) % 128 == 0
+ */
+#define        IXGBE_MIN_RING_DESC     32
+#define        IXGBE_MAX_RING_DESC     4096
 
-#define RTE_MBUF_DATA_DMA_ADDR(mb) \
-       (uint64_t) ((mb)->buf_physaddr + (mb)->data_off)
+#define RTE_PMD_IXGBE_TX_MAX_BURST 32
+#define RTE_PMD_IXGBE_RX_MAX_BURST 32
+#define RTE_IXGBE_TX_MAX_FREE_BUF_SZ 64
 
-#define RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb) \
-       (uint64_t) ((mb)->buf_physaddr + RTE_PKTMBUF_HEADROOM)
+#define RTE_IXGBE_DESCS_PER_LOOP    4
 
 #ifdef RTE_IXGBE_INC_VECTOR
-#define RTE_IXGBE_VPMD_RX_BURST         32
-#define RTE_IXGBE_VPMD_TX_BURST         32
-#define RTE_IXGBE_RXQ_REARM_THRESH      RTE_IXGBE_VPMD_RX_BURST
-#define RTE_IXGBE_TX_MAX_FREE_BUF_SZ    64
+#define RTE_IXGBE_RXQ_REARM_THRESH      32
+#define RTE_IXGBE_MAX_RX_BURST          RTE_IXGBE_RXQ_REARM_THRESH
 #endif
 
 #define RX_RING_SZ ((IXGBE_MAX_RING_DESC + RTE_IXGBE_DESCS_PER_LOOP - 1) * \
@@ -116,11 +124,11 @@ struct ixgbe_rx_queue {
        uint16_t            nb_rx_desc; /**< number of RX descriptors. */
        uint16_t            rx_tail;  /**< current value of RDT register. */
        uint16_t            nb_rx_hold; /**< number of held free RX desc. */
-#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC
        uint16_t rx_nb_avail; /**< nr of staged pkts ready to ret to app */
        uint16_t rx_next_avail; /**< idx of next staged pkt to ret to app */
        uint16_t rx_free_trigger; /**< triggers rx buffer allocation */
-#endif
+       uint16_t            rx_using_sse;
+       /**< indicates that vector RX is in use */
 #ifdef RTE_IXGBE_INC_VECTOR
        uint16_t            rxrearm_nb;     /**< number of remaining to be re-armed */
        uint16_t            rxrearm_start;  /**< the idx we start the re-arming from */
@@ -132,12 +140,10 @@ struct ixgbe_rx_queue {
        uint8_t             crc_len;  /**< 0 if CRC stripped, 4 otherwise. */
        uint8_t             drop_en;  /**< If not 0, set SRRCTL.Drop_En. */
        uint8_t             rx_deferred_start; /**< not in global dev start. */
-#ifdef RTE_LIBRTE_IXGBE_RX_ALLOW_BULK_ALLOC
        /** need to alloc dummy mbuf, for wraparound when scanning hw ring */
        struct rte_mbuf fake_mbuf;
        /** hold packets to return to application */
        struct rte_mbuf *rx_stage[RTE_PMD_IXGBE_RX_MAX_BURST*2];
-#endif
 };
 
 /**
@@ -151,7 +157,7 @@ enum ixgbe_advctx_num {
 
 /** Offload features */
 union ixgbe_tx_offload {
-       uint64_t data;
+       uint64_t data[2];
        struct {
                uint64_t l2_len:7; /**< L2 (MAC) Header Length. */
                uint64_t l3_len:9; /**< L3 (IP) Header Length. */
@@ -159,6 +165,10 @@ union ixgbe_tx_offload {
                uint64_t tso_segsz:16; /**< TCP TSO segment size */
                uint64_t vlan_tci:16;
                /**< VLAN Tag Control Identifier (CPU order). */
+
+               /* fields for TX offloading of tunnels */
+               uint64_t outer_l3_len:8; /**< Outer L3 (IP) Hdr Length. */
+               uint64_t outer_l2_len:8; /**< Outer L2 (MAC) Hdr Length. */
        };
 };
 
@@ -191,7 +201,10 @@ struct ixgbe_tx_queue {
        /** TX ring virtual address. */
        volatile union ixgbe_adv_tx_desc *tx_ring;
        uint64_t            tx_ring_phys_addr; /**< TX ring DMA address. */
-       struct ixgbe_tx_entry *sw_ring;      /**< virtual address of SW ring. */
+       union {
+               struct ixgbe_tx_entry *sw_ring; /**< address of SW ring for scalar PMD. */
+               struct ixgbe_tx_entry_v *sw_ring_v; /**< address of SW ring for vector PMD */
+       };
        volatile uint32_t   *tdt_reg_addr; /**< Address of TDT register. */
        uint16_t            nb_tx_desc;    /**< number of TX descriptors. */
        uint16_t            tx_tail;       /**< current value of TDT reg. */
@@ -284,6 +297,7 @@ uint16_t ixgbe_recv_scattered_pkts_vec(void *rx_queue,
                struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
 int ixgbe_rx_vec_dev_conf_condition_check(struct rte_eth_dev *dev);
 int ixgbe_rxq_vec_setup(struct ixgbe_rx_queue *rxq);
+void ixgbe_rx_queue_release_mbufs_vec(struct ixgbe_rx_queue *rxq);
 
 #ifdef RTE_IXGBE_INC_VECTOR