From: Jie Liu <[email protected]> Implement receive and transmit burst functions for sxe2 PMD. Add sxe2_recv_pkts and sxe2_xmit_pkts as the primary data path interfaces.
The implementation includes: - Efficient descriptor fetching and mbuf allocation for Rx. - Descriptor setup and checksum offload handling for Tx. - Buffer recycling and hardware tail pointer updates. - Performance-oriented loop unrolling and prefetching where applicable. Signed-off-by: Jie Liu <[email protected]> --- drivers/common/sxe2/sxe2_common.c | 13 +- drivers/common/sxe2/sxe2_common_log.h | 105 ---- drivers/common/sxe2/sxe2_errno.h | 3 - drivers/common/sxe2/sxe2_ioctl_chnl.c | 20 +- drivers/common/sxe2/sxe2_osal.h | 4 +- drivers/common/sxe2/sxe2_type.h | 1 - drivers/net/sxe2/meson.build | 2 + drivers/net/sxe2/sxe2_ethdev.c | 15 +- drivers/net/sxe2/sxe2_txrx.c | 249 ++++++++ drivers/net/sxe2/sxe2_txrx.h | 21 + drivers/net/sxe2/sxe2_txrx_poll.c | 782 ++++++++++++++++++++++++++ 11 files changed, 1082 insertions(+), 133 deletions(-) create mode 100644 drivers/net/sxe2/sxe2_txrx.c create mode 100644 drivers/net/sxe2/sxe2_txrx.h create mode 100644 drivers/net/sxe2/sxe2_txrx_poll.c diff --git a/drivers/common/sxe2/sxe2_common.c b/drivers/common/sxe2/sxe2_common.c index 537d4e9f6a..d2ed1460a3 100644 --- a/drivers/common/sxe2/sxe2_common.c +++ b/drivers/common/sxe2/sxe2_common.c @@ -28,7 +28,7 @@ static TAILQ_HEAD(sxe2_class_drivers, sxe2_class_driver) sxe2_class_drivers_list static TAILQ_HEAD(sxe2_common_devices, sxe2_common_device) sxe2_common_devices_list = TAILQ_HEAD_INITIALIZER(sxe2_common_devices_list); -static pthread_mutex_t sxe2_common_devices_list_lock; +static rte_spinlock_t sxe2_common_devices_list_lock; static struct rte_pci_id *sxe2_common_pci_id_table; @@ -223,9 +223,9 @@ static struct sxe2_common_device *sxe2_common_device_alloc( cdev->config.kernel_reset = false; rte_ticketlock_init(&cdev->config.lock); - (void)pthread_mutex_lock(&sxe2_common_devices_list_lock); + rte_spinlock_lock(&sxe2_common_devices_list_lock); TAILQ_INSERT_TAIL(&sxe2_common_devices_list, cdev, next); - (void)pthread_mutex_unlock(&sxe2_common_devices_list_lock); + rte_spinlock_unlock(&sxe2_common_devices_list_lock); l_end: return cdev; @@ -233,10 +233,9 @@ static struct sxe2_common_device *sxe2_common_device_alloc( static void sxe2_common_device_free(struct sxe2_common_device *cdev) { - - (void)pthread_mutex_lock(&sxe2_common_devices_list_lock); + rte_spinlock_lock(&sxe2_common_devices_list_lock); TAILQ_REMOVE(&sxe2_common_devices_list, cdev, next); - (void)pthread_mutex_unlock(&sxe2_common_devices_list_lock); + rte_spinlock_unlock(&sxe2_common_devices_list_lock); rte_free(cdev); } @@ -662,7 +661,7 @@ sxe2_common_init(void) if (sxe2_commoin_inited) goto l_end; - pthread_mutex_init(&sxe2_common_devices_list_lock, NULL); + rte_spinlock_init(&sxe2_common_devices_list_lock); #ifdef SXE2_DPDK_DEBUG sxe2_common_log_stream_init(); #endif diff --git a/drivers/common/sxe2/sxe2_common_log.h b/drivers/common/sxe2/sxe2_common_log.h index 8ade49d020..14074fcc4f 100644 --- a/drivers/common/sxe2/sxe2_common_log.h +++ b/drivers/common/sxe2/sxe2_common_log.h @@ -260,109 +260,4 @@ sxe2_common_log_stream_init(void); #define PMD_INIT_FUNC_TRACE() PMD_LOG_DEBUG(INIT, " >>") -#ifdef SXE2_DPDK_DEBUG - -#define LOG_DEBUG(fmt, ...) \ - PMD_LOG_DEBUG(DRV, fmt, ##__VA_ARGS__) - -#define LOG_INFO(fmt, ...) \ - PMD_LOG_INFO(DRV, fmt, ##__VA_ARGS__) - -#define LOG_WARN(fmt, ...) \ - PMD_LOG_WARN(DRV, fmt, ##__VA_ARGS__) - -#define LOG_ERROR(fmt, ...) \ - PMD_LOG_ERR(DRV, fmt, ##__VA_ARGS__) - -#define LOG_DEBUG_BDF(dev_name, fmt, ...) \ - PMD_LOG_DEBUG(HW, fmt, ##__VA_ARGS__) - -#define LOG_INFO_BDF(dev_name, fmt, ...) \ - PMD_LOG_INFO(HW, fmt, ##__VA_ARGS__) - -#define LOG_WARN_BDF(dev_name, fmt, ...) \ - PMD_LOG_WARN(HW, fmt, ##__VA_ARGS__) - -#define LOG_ERROR_BDF(dev_name, fmt, ...) \ - PMD_LOG_ERR(HW, fmt, ##__VA_ARGS__) - -#else -#define LOG_DEBUG(fmt, ...) -#define LOG_INFO(fmt, ...) -#define LOG_WARN(fmt, ...) -#define LOG_ERROR(fmt, ...) -#define LOG_DEBUG_BDF(dev_name, fmt, ...) \ - PMD_LOG_DEBUG(HW, fmt, ##__VA_ARGS__) - -#define LOG_INFO_BDF(dev_name, fmt, ...) \ - PMD_LOG_INFO(HW, fmt, ##__VA_ARGS__) - -#define LOG_WARN_BDF(dev_name, fmt, ...) \ - PMD_LOG_WARN(HW, fmt, ##__VA_ARGS__) - -#define LOG_ERROR_BDF(dev_name, fmt, ...) \ - PMD_LOG_ERR(HW, fmt, ##__VA_ARGS__) -#endif - -#ifdef SXE2_DPDK_DEBUG -#define LOG_DEV_DEBUG(fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_DEBUG_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_DEV_INFO(fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_INFO_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_DEV_WARN(fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_WARN_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_DEV_ERR(fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_ERROR_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_MSG_DEBUG(msglvl, fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_DEBUG_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_MSG_INFO(msglvl, fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_INFO_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_MSG_WARN(msglvl, fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_WARN_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#define LOG_MSG_ERR(msglvl, fmt, ...) \ - do { \ - RTE_SET_USED(adapter); \ - LOG_ERROR_BDF(fmt, ##__VA_ARGS__); \ - } while (0) - -#else - -#define LOG_DEV_DEBUG(fmt, ...) RTE_SET_USED(adapter) -#define LOG_DEV_INFO(fmt, ...) RTE_SET_USED(adapter) -#define LOG_DEV_WARN(fmt, ...) RTE_SET_USED(adapter) -#define LOG_DEV_ERR(fmt, ...) RTE_SET_USED(adapter) -#define LOG_MSG_DEBUG(msglvl, fmt, ...) RTE_SET_USED(adapter) -#define LOG_MSG_INFO(msglvl, fmt, ...) RTE_SET_USED(adapter) -#define LOG_MSG_WARN(msglvl, fmt, ...) RTE_SET_USED(adapter) -#define LOG_MSG_ERR(msglvl, fmt, ...) RTE_SET_USED(adapter) -#endif - #endif /* SXE2_COMMON_LOG_H__ */ diff --git a/drivers/common/sxe2/sxe2_errno.h b/drivers/common/sxe2/sxe2_errno.h index 89a715eaef..1257319edf 100644 --- a/drivers/common/sxe2/sxe2_errno.h +++ b/drivers/common/sxe2/sxe2_errno.h @@ -50,9 +50,6 @@ enum sxe2_status { SXE2_ERR_NOLCK = -ENOLCK, SXE2_ERR_NOSYS = -ENOSYS, SXE2_ERR_NOTEMPTY = -ENOTEMPTY, - SXE2_ERR_ILSEQ = -EILSEQ, - SXE2_ERR_NODATA = -ENODATA, - SXE2_ERR_CANCELED = -ECANCELED, SXE2_ERR_TIMEDOUT = -ETIMEDOUT, SXE2_ERROR = -150, diff --git a/drivers/common/sxe2/sxe2_ioctl_chnl.c b/drivers/common/sxe2/sxe2_ioctl_chnl.c index 1a14d401e7..cb83fb837d 100644 --- a/drivers/common/sxe2/sxe2_ioctl_chnl.c +++ b/drivers/common/sxe2/sxe2_ioctl_chnl.c @@ -37,7 +37,7 @@ sxe2_drv_cmd_exec(struct sxe2_common_device *cdev, if (cdev->config.kernel_reset) { ret = SXE2_ERR_PERM; - PMD_LOG_WARN(COM, "kernel reseted, need restart app."); + PMD_LOG_WARN(COM, "kernel reset, need restart app."); goto l_end; } @@ -123,7 +123,7 @@ sxe2_drv_dev_handshark(struct sxe2_common_device *cdev) if (cdev->config.kernel_reset) { ret = SXE2_ERR_PERM; - PMD_LOG_WARN(COM, "kernel reseted, need restart app."); + PMD_LOG_WARN(COM, "kernel reset, need restart app."); goto l_end; } @@ -168,7 +168,7 @@ void void *virt = NULL; if (cdev->config.kernel_reset) { - PMD_LOG_WARN(COM, "kernel reseted, need restart app."); + PMD_LOG_WARN(COM, "kernel reset, need restart app."); goto l_err; } @@ -178,13 +178,13 @@ void goto l_err; } - PMD_LOG_DEBUG(COM, "fd=%d, bar idx=%d, len=0x%zx, src=0x%"PRIx64", offset=0x%"PRIx64"", + PMD_LOG_DEBUG(COM, "fd=%d, bar idx=%d, len=%"PRIu64", src=0x%"PRIx64", offset=0x%"PRIx64"", bar_idx, cmd_fd, len, offset, SXE2_COM_PCI_OFFSET_GEN(bar_idx, offset)); virt = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_SHARED, cmd_fd, SXE2_COM_PCI_OFFSET_GEN(bar_idx, offset)); if (virt == MAP_FAILED) { - PMD_LOG_ERR(COM, "Failed mmap, cmd_fd=%d, len=0x%zx, offset=0x%"PRIx64", err:%s", + PMD_LOG_ERR(COM, "Failed mmap, cmd_fd=%d, len=%"PRIu64", offset=0x%"PRIx64", err:%s", cmd_fd, len, offset, strerror(errno)); goto l_err; } @@ -206,12 +206,12 @@ sxe2_drv_dev_munmap(struct sxe2_common_device *cdev, void *virt, u64 len) goto l_end; } - PMD_LOG_DEBUG(COM, "Munmap virt=%p, len=0x%zx", + PMD_LOG_DEBUG(COM, "Munmap virt=%p, len=0x%"PRIx64"", virt, len); ret = munmap(virt, len); if (ret < 0) { - PMD_LOG_ERR(COM, "Failed to munmap, virt=%p, len=0x%zx, err:%s", + PMD_LOG_ERR(COM, "Failed to munmap, virt=%p, len=%"PRIu64", err:%s", virt, len, strerror(errno)); ret = SXE2_ERR_IO; goto l_end; @@ -233,7 +233,7 @@ sxe2_drv_dev_dma_map(struct sxe2_common_device *cdev, u64 vaddr, if (cdev->config.kernel_reset) { ret = SXE2_ERR_PERM; - PMD_LOG_WARN(COM, "kernel reseted, need restart app."); + PMD_LOG_WARN(COM, "kernel reset, need restart app."); goto l_end; } @@ -246,7 +246,7 @@ sxe2_drv_dev_dma_map(struct sxe2_common_device *cdev, u64 vaddr, goto l_end; } else if (iova_mode == RTE_IOVA_VA) { if (!cdev->config.support_iommu) { - PMD_LOG_ERR(COM, "no iommu not support va mode, plese use pa mode."); + PMD_LOG_ERR(COM, "no iommu not support va mode, please use pa mode."); ret = SXE2_ERR_IO; goto l_end; } @@ -289,7 +289,7 @@ sxe2_drv_dev_dma_unmap(struct sxe2_common_device *cdev, u64 iova) if (cdev->config.kernel_reset) { ret = SXE2_ERR_PERM; - PMD_LOG_WARN(COM, "kernel reseted, need restart app."); + PMD_LOG_WARN(COM, "kernel reset, need restart app."); goto l_end; } diff --git a/drivers/common/sxe2/sxe2_osal.h b/drivers/common/sxe2/sxe2_osal.h index fd6823fe98..23882f3f52 100644 --- a/drivers/common/sxe2/sxe2_osal.h +++ b/drivers/common/sxe2/sxe2_osal.h @@ -29,8 +29,6 @@ #define BIT_ULL(a) (1ULL << (a)) #endif -#define MIN(a, b) ((a) < (b) ? (a) : (b)) - #define BITS_PER_BYTE 8 #define IS_UNICAST_ETHER_ADDR(addr) \ @@ -88,7 +86,7 @@ (((n) + (typeof(n))(d) - (typeof(n))1) / (typeof(n))(d)) #endif -#define usleep_range(min, max) msleep(DIV_ROUND_UP(min, 1000)) +#define usleep_range(min) msleep(DIV_ROUND_UP(min, 1000)) #define __bf_shf(x) ((uint32_t)rte_bsf64(x)) diff --git a/drivers/common/sxe2/sxe2_type.h b/drivers/common/sxe2/sxe2_type.h index 56d0a11f48..fbf4a6674f 100644 --- a/drivers/common/sxe2/sxe2_type.h +++ b/drivers/common/sxe2/sxe2_type.h @@ -8,7 +8,6 @@ #include <sys/time.h> #include <stdlib.h> -#include <stdio.h> #include <errno.h> #include <stdarg.h> #include <unistd.h> diff --git a/drivers/net/sxe2/meson.build b/drivers/net/sxe2/meson.build index 61467a4e31..b331451160 100644 --- a/drivers/net/sxe2/meson.build +++ b/drivers/net/sxe2/meson.build @@ -25,6 +25,8 @@ sources += files( 'sxe2_queue.c', 'sxe2_tx.c', 'sxe2_rx.c', + 'sxe2_txrx_poll.c', + 'sxe2_txrx.c', ) allow_internal_get_api = true diff --git a/drivers/net/sxe2/sxe2_ethdev.c b/drivers/net/sxe2/sxe2_ethdev.c index c1a65f25ce..68d7e36cf1 100644 --- a/drivers/net/sxe2/sxe2_ethdev.c +++ b/drivers/net/sxe2/sxe2_ethdev.c @@ -26,6 +26,7 @@ #include "sxe2_cmd_chnl.h" #include "sxe2_tx.h" #include "sxe2_rx.h" +#include "sxe2_txrx.h" #include "sxe2_common.h" #include "sxe2_common_log.h" #include "sxe2_host_regs.h" @@ -131,6 +132,9 @@ static s32 sxe2_dev_start(struct rte_eth_dev *dev) goto l_end; } + sxe2_rx_mode_func_set(dev); + sxe2_tx_mode_func_set(dev); + ret = sxe2_queues_start(dev); if (ret) { PMD_LOG_ERR(INIT, "enable queues failed"); @@ -363,8 +367,8 @@ void __iomem *sxe2_pci_map_addr_get(struct sxe2_adapter *adapter, for (i = 0; i < bar_info->map_cnt; i++) { seg_info = &bar_info->seg_info[i]; if (res_type == seg_info->type) { - addr = (void __iomem *)((uintptr_t)seg_info->addr + - seg_info->page_inner_offset + reg_width * idx_in_func); + addr = (uint8_t __iomem *)seg_info->addr + + seg_info->page_inner_offset + reg_width * idx_in_func; goto l_end; } } @@ -475,8 +479,9 @@ s32 sxe2_dev_pci_seg_map(struct sxe2_adapter *adapter, map_addr = sxe2_drv_dev_mmap(adapter->cdev, bar_info->bar_idx, aligned_len, aligned_offset); if (!map_addr) { - PMD_LOG_ERR(INIT, "Failed to mmap BAR space, type=%d, len=%zu, page_size=%zu", - res_type, org_len, page_size); + PMD_LOG_ERR(INIT, "Failed to mmap BAR space, type=%d, len=%" PRIu64 + ", offset=%" PRIu64 ", page_size=%zu", + res_type, org_len, org_offset, page_size); ret = SXE2_ERR_FAULT; goto l_end; } @@ -760,6 +765,8 @@ static s32 sxe2_dev_init(struct rte_eth_dev *dev, struct sxe2_dev_kvargs_info *k PMD_INIT_FUNC_TRACE(); + sxe2_set_common_function(dev); + dev->dev_ops = &sxe2_eth_dev_ops; ret = sxe2_hw_init(dev); diff --git a/drivers/net/sxe2/sxe2_txrx.c b/drivers/net/sxe2/sxe2_txrx.c new file mode 100644 index 0000000000..3e88ab5241 --- /dev/null +++ b/drivers/net/sxe2/sxe2_txrx.c @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd. + */ + +#include <rte_common.h> +#include <rte_net.h> +#include <rte_vect.h> +#include <rte_malloc.h> +#include <rte_memzone.h> +#include <ethdev_driver.h> +#include <unistd.h> + +#include "sxe2_txrx.h" +#include "sxe2_txrx_common.h" +#include "sxe2_txrx_poll.h" +#include "sxe2_ethdev.h" + +#include "sxe2_common_log.h" +#include "sxe2_errno.h" +#include "sxe2_osal.h" +#include "sxe2_cmd_chnl.h" +#if defined(RTE_ARCH_ARM64) +#include <rte_cpuflags.h> +#endif + +static s32 sxe2_tx_desciptor_status(void *tx_queue, u16 offset) +{ + struct sxe2_tx_queue *txq = (struct sxe2_tx_queue *)tx_queue; + s32 ret; + u16 desc_idx; + + if (unlikely(offset >= txq->ring_depth)) { + ret = SXE2_ERR_INVAL; + goto l_end; + } + + desc_idx = txq->next_use + offset; + desc_idx = DIV_ROUND_UP(desc_idx, txq->rs_thresh) * (txq->rs_thresh); + if (desc_idx >= txq->ring_depth) { + desc_idx -= txq->ring_depth; + if (desc_idx >= txq->ring_depth) + desc_idx -= txq->ring_depth; + } + + if (desc_idx == 0) + desc_idx = txq->rs_thresh - 1; + else + desc_idx -= 1; + + if (rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_DESC_DONE) == + (txq->desc_ring[desc_idx].wb.dd & + rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_DESC_MASK))) + ret = RTE_ETH_TX_DESC_DONE; + else + ret = RTE_ETH_TX_DESC_FULL; + +l_end: + return ret; +} + +static inline s32 sxe2_tx_mbuf_empty_check(struct rte_mbuf *mbuf) +{ + struct rte_mbuf *m_seg = mbuf; + + while (m_seg != NULL) { + if (m_seg->data_len == 0) + return SXE2_ERR_INVAL; + m_seg = m_seg->next; + } + + return SXE2_SUCCESS; +} + +u16 sxe2_tx_pkts_prepare(__rte_unused void *tx_queue, + struct rte_mbuf **tx_pkts, u16 nb_pkts) +{ + struct sxe2_tx_queue *txq = tx_queue; + struct rte_mbuf *mbuf; + u64 ol_flags = 0; + s32 ret = SXE2_SUCCESS; + s32 i = 0; + + for (i = 0; i < nb_pkts; i++) { + mbuf = tx_pkts[i]; + if (!mbuf) + continue; + ol_flags = mbuf->ol_flags; + if (!(ol_flags & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_UDP_SEG))) { + if (mbuf->nb_segs > SXE2_TX_MTU_SEG_MAX || + mbuf->pkt_len > SXE2_FRAME_SIZE_MAX) { + rte_errno = -SXE2_ERR_INVAL; + goto l_end; + } + } else if ((mbuf->tso_segsz < SXE2_MIN_TSO_MSS) || + (mbuf->tso_segsz > SXE2_MAX_TSO_MSS) || + (mbuf->nb_segs > txq->ring_depth) || + (mbuf->pkt_len > SXE2_TX_TSO_PKTLEN_MAX)) { + rte_errno = -SXE2_ERR_INVAL; + goto l_end; + } + + if (mbuf->pkt_len < SXE2_TX_MIN_PKT_LEN) { + rte_errno = -SXE2_ERR_INVAL; + goto l_end; + } + +#ifdef RTE_ETHDEV_DEBUG_TX + ret = rte_validate_tx_offload(mbuf); + if (ret != SXE2_SUCCESS) { + rte_errno = -ret; + goto l_end; + } +#endif + ret = rte_net_intel_cksum_prepare(mbuf); + if (ret != SXE2_SUCCESS) { + rte_errno = -ret; + goto l_end; + } + + ret = sxe2_tx_mbuf_empty_check(mbuf); + if (ret != SXE2_SUCCESS) { + rte_errno = -ret; + goto l_end; + } + } + +l_end: + return i; +} + +void sxe2_tx_mode_func_set(struct rte_eth_dev *dev) +{ + struct sxe2_adapter *adapter = SXE2_DEV_PRIVATE_TO_ADAPTER(dev); + u32 tx_mode_flags = 0; + + PMD_INIT_FUNC_TRACE(); + + dev->tx_pkt_prepare = sxe2_tx_pkts_prepare; + dev->tx_pkt_burst = sxe2_tx_pkts; + adapter->q_ctxt.tx_mode_flags = tx_mode_flags; + PMD_LOG_DEBUG(TX, "Tx mode flags:0x%016x port_id:%u.", + tx_mode_flags, dev->data->port_id); +} + +static s32 sxe2_rx_desciptor_status(void *rx_queue, u16 offset) +{ + struct sxe2_rx_queue *rxq = (struct sxe2_rx_queue *)rx_queue; + volatile union sxe2_rx_desc *desc; + s32 ret; + + if (unlikely(offset >= rxq->ring_depth)) { + ret = SXE2_ERR_INVAL; + goto l_end; + } + + if (offset >= rxq->ring_depth - rxq->hold_num) { + ret = RTE_ETH_RX_DESC_UNAVAIL; + goto l_end; + } + + if (rxq->processing_idx + offset >= rxq->ring_depth) + desc = &rxq->desc_ring[rxq->processing_idx + offset - rxq->ring_depth]; + else + desc = &rxq->desc_ring[rxq->processing_idx + offset]; + + if (rte_le_to_cpu_64(desc->wb.status_err_ptype_len) & SXE2_RX_DESC_STATUS_DD_MASK) + ret = RTE_ETH_RX_DESC_DONE; + else + ret = RTE_ETH_RX_DESC_AVAIL; + +l_end: + PMD_LOG_DEBUG(RX, "Rx queue desc[%u] status:%d queue_id:%u port_id:%u", + offset, ret, rxq->queue_id, rxq->port_id); + return ret; +} + +static s32 sxe2_rx_queue_count(void *rx_queue) +{ + struct sxe2_rx_queue *rxq = (struct sxe2_rx_queue *)rx_queue; + volatile union sxe2_rx_desc *desc; + u16 done_num = 0; + + desc = &rxq->desc_ring[rxq->processing_idx]; + while ((done_num < rxq->ring_depth) && + (rte_le_to_cpu_64(desc->wb.status_err_ptype_len) & + SXE2_RX_DESC_STATUS_DD_MASK)) { + done_num += SXE2_RX_QUEUE_CHECK_INTERVAL_NUM; + if (rxq->processing_idx + done_num >= rxq->ring_depth) + desc = &rxq->desc_ring[rxq->processing_idx + done_num - rxq->ring_depth]; + else + desc += SXE2_RX_QUEUE_CHECK_INTERVAL_NUM; + } + + PMD_LOG_DEBUG(RX, "Rx queue done desc count:%u queue_id:%u port_id:%u", + done_num, rxq->queue_id, rxq->port_id); + + return done_num; +} + +static bool __rte_cold sxe2_rx_offload_en_check(struct rte_eth_dev *dev, u64 offload) +{ + struct sxe2_rx_queue *rxq; + bool en = false; + u16 i; + + for (i = 0; i < dev->data->nb_rx_queues; ++i) { + rxq = (struct sxe2_rx_queue *)dev->data->rx_queues[i]; + if (rxq == NULL) + continue; + + if (0 != (rxq->offloads & offload)) { + en = true; + goto l_end; + } + } + +l_end: + return en; +} + +void sxe2_rx_mode_func_set(struct rte_eth_dev *dev) +{ + struct sxe2_adapter *adapter = SXE2_DEV_PRIVATE_TO_ADAPTER(dev); + u32 rx_mode_flags = 0; + + PMD_INIT_FUNC_TRACE(); + + if (sxe2_rx_offload_en_check(dev, RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT)) + dev->rx_pkt_burst = sxe2_rx_pkts_scattered_split; + else + dev->rx_pkt_burst = sxe2_rx_pkts_scattered; + + PMD_LOG_DEBUG(RX, "Rx mode flags:0x%016x port_id:%u.", + rx_mode_flags, dev->data->port_id); + adapter->q_ctxt.rx_mode_flags = rx_mode_flags; +} + +void sxe2_set_common_function(struct rte_eth_dev *dev) +{ + PMD_INIT_FUNC_TRACE(); + + dev->rx_queue_count = sxe2_rx_queue_count; + dev->rx_descriptor_status = sxe2_rx_desciptor_status; + dev->rx_pkt_burst = sxe2_rx_pkts_scattered; + + dev->tx_descriptor_status = sxe2_tx_desciptor_status; + dev->tx_pkt_prepare = sxe2_tx_pkts_prepare; + dev->tx_pkt_burst = sxe2_tx_pkts; +} diff --git a/drivers/net/sxe2/sxe2_txrx.h b/drivers/net/sxe2/sxe2_txrx.h new file mode 100644 index 0000000000..cd9ebfa32f --- /dev/null +++ b/drivers/net/sxe2/sxe2_txrx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd. + */ + +#ifndef SXE2_TXRX_H +#define SXE2_TXRX_H +#include <ethdev_driver.h> +#include "sxe2_queue.h" + +void sxe2_set_common_function(struct rte_eth_dev *dev); + +u16 sxe2_tx_pkts_prepare(__rte_unused void *tx_queue, + struct rte_mbuf **tx_pkts, u16 nb_pkts); + +void sxe2_tx_mode_func_set(struct rte_eth_dev *dev); + +void __rte_cold sxe2_rx_queue_reset(struct sxe2_rx_queue *rxq); + +void sxe2_rx_mode_func_set(struct rte_eth_dev *dev); + +#endif diff --git a/drivers/net/sxe2/sxe2_txrx_poll.c b/drivers/net/sxe2/sxe2_txrx_poll.c new file mode 100644 index 0000000000..55bea8b74c --- /dev/null +++ b/drivers/net/sxe2/sxe2_txrx_poll.c @@ -0,0 +1,782 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd. + */ + +#include <rte_common.h> +#include <rte_net.h> +#include <rte_vect.h> +#include <rte_malloc.h> +#include <rte_memzone.h> +#include <ethdev_driver.h> +#include <unistd.h> + +#include "sxe2_osal.h" +#include "sxe2_txrx_common.h" +#include "sxe2_txrx_poll.h" +#include "sxe2_txrx.h" +#include "sxe2_queue.h" +#include "sxe2_ethdev.h" +#include "sxe2_common_log.h" +#include "sxe2_errno.h" + +static inline s32 sxe2_tx_cleanup(struct sxe2_tx_queue *txq) +{ + s32 ret = SXE2_SUCCESS; + volatile union sxe2_tx_data_desc *desc_ring = txq->desc_ring; + struct sxe2_tx_buffer *buffer_ring = txq->buffer_ring; + u16 ring_depth = txq->ring_depth; + u16 next_clean = txq->next_clean; + u16 clean_last; + u16 clean_num; + + clean_last = next_clean + txq->rs_thresh; + if (clean_last >= ring_depth) + clean_last = clean_last - ring_depth; + + clean_last = buffer_ring[clean_last].last_id; + if (rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_DESC_DONE) != + (txq->desc_ring[clean_last].wb.dd & rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_MASK))) { + PMD_LOG_TX_DEBUG("desc[%u] is not done.port_id=%u queue_id=%u val=0x%" PRIx64, + clean_last, txq->port_id, + txq->queue_id, txq->desc_ring[clean_last].wb.dd); + SXE2_TX_STATS_CNT(txq, tx_desc_not_done, 1); + ret = SXE2_ERR_DESC_NO_DONE; + goto l_end; + } + + if (clean_last > next_clean) + clean_num = clean_last - next_clean; + else + clean_num = ring_depth - next_clean + clean_last; + + desc_ring[clean_last].wb.dd = 0; + + txq->next_clean = clean_last; + txq->desc_free_num += clean_num; + + ret = SXE2_SUCCESS; + +l_end: + return ret; +} + +static __rte_always_inline u16 +sxe2_tx_pkt_data_desc_count(struct rte_mbuf *tx_pkt) +{ + struct rte_mbuf *m_seg = tx_pkt; + u16 count = 0; + + while (m_seg != NULL) { + count += DIV_ROUND_UP(m_seg->data_len, + SXE2_TX_MAX_DATA_NUM_PER_DESC); + m_seg = m_seg->next; + } + + return count; +} + +static __rte_always_inline void +sxe2_tx_desc_checksum_fill(u64 offloads, u32 *desc_cmd, u32 *desc_offset, + union sxe2_tx_offload_info ol_info) +{ + if (offloads & RTE_MBUF_F_TX_IP_CKSUM) { + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_IIPT_IPV4_CSUM; + *desc_offset |= SXE2_TX_DATA_DESC_IPLEN_VAL(ol_info.l3_len); + } else if (offloads & RTE_MBUF_F_TX_IPV4) { + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_IIPT_IPV4; + *desc_offset |= SXE2_TX_DATA_DESC_IPLEN_VAL(ol_info.l3_len); + } else if (offloads & RTE_MBUF_F_TX_IPV6) { + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_IIPT_IPV6; + *desc_offset |= SXE2_TX_DATA_DESC_IPLEN_VAL(ol_info.l3_len); + } + + if (offloads & RTE_MBUF_F_TX_TCP_SEG) { + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_L4T_EOFT_TCP; + *desc_offset |= SXE2_TX_DATA_DESC_L4LEN_VAL(ol_info.l4_len); + goto l_end; + } + + if (offloads & RTE_MBUF_F_TX_UDP_SEG) { + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_L4T_EOFT_UDP; + *desc_offset |= SXE2_TX_DATA_DESC_L4LEN_VAL(ol_info.l4_len); + goto l_end; + } + + switch (offloads & RTE_MBUF_F_TX_L4_MASK) { + case RTE_MBUF_F_TX_TCP_CKSUM: + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_L4T_EOFT_TCP; + *desc_offset |= SXE2_TX_DATA_DESC_L4LEN_VAL(ol_info.l4_len); + break; + case RTE_MBUF_F_TX_SCTP_CKSUM: + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_L4T_EOFT_SCTP; + *desc_offset |= SXE2_TX_DATA_DESC_L4LEN_VAL(ol_info.l4_len); + break; + case RTE_MBUF_F_TX_UDP_CKSUM: + *desc_cmd |= SXE2_TX_DATA_DESC_CMD_L4T_EOFT_UDP; + *desc_offset |= SXE2_TX_DATA_DESC_L4LEN_VAL(ol_info.l4_len); + break; + default: + + break; + } + +l_end: + return; +} + +static __rte_always_inline u64 +sxe2_tx_data_desc_build_cobt(u32 cmd, u32 offset, u16 buf_size, u16 l2tag) +{ + return rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_DATA | + (((u64)cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT) | + (((u64)offset) << SXE2_TX_DATA_DESC_OFFSET_SHIFT) | + (((u64)buf_size) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT) | + (((u64)l2tag) << SXE2_TX_DATA_DESC_L2TAG1_SHIFT)); +} + +u16 sxe2_tx_pkts(void *tx_queue, struct rte_mbuf **tx_pkts, u16 nb_pkts) +{ + struct sxe2_tx_queue *txq = tx_queue; + struct sxe2_tx_buffer *buffer_ring; + struct sxe2_tx_buffer *buffer; + struct sxe2_tx_buffer *next_buffer; + struct rte_mbuf *tx_pkt; + struct rte_mbuf *m_seg; + volatile union sxe2_tx_data_desc *desc_ring; + volatile union sxe2_tx_data_desc *desc; + volatile struct sxe2_tx_context_desc *ctxt_desc; + union sxe2_tx_offload_info ol_info; + struct sxe2_vsi *vsi = txq->vsi; + rte_iova_t buf_dma_addr; + u64 offloads; + u64 desc_type_cmd_tso_mss; + u32 desc_cmd; + u32 desc_offset; + u32 desc_tag; + u32 desc_tunneling_params; + u16 ipsec_offset; + u16 ctxt_desc_num; + u16 desc_sum_num; + u16 tx_num; + u16 seg_len; + u16 next_use; + u16 last_use; + u16 desc_l2tag2; + + buffer_ring = txq->buffer_ring; + desc_ring = txq->desc_ring; + next_use = txq->next_use; + buffer = &buffer_ring[next_use]; + + if (txq->desc_free_num < txq->free_thresh) + (void)sxe2_tx_cleanup(txq); + + for (tx_num = 0; tx_num < nb_pkts; tx_num++) { + tx_pkt = *tx_pkts++; + desc_cmd = 0; + desc_offset = 0; + desc_tag = 0; + desc_tunneling_params = 0; + ipsec_offset = 0; + offloads = tx_pkt->ol_flags; + ol_info.l2_len = tx_pkt->l2_len; + ol_info.l3_len = tx_pkt->l3_len; + ol_info.l4_len = tx_pkt->l4_len; + ol_info.tso_segsz = tx_pkt->tso_segsz; + ol_info.outer_l2_len = tx_pkt->outer_l2_len; + ol_info.outer_l3_len = tx_pkt->outer_l3_len; + + ctxt_desc_num = (offloads & + SXE2_TX_OFFLOAD_CTXT_NEEDCK_MASK) ? 1 : 0; + if (unlikely(vsi->vsi_type == SXE2_VSI_T_DPDK_ESW)) + ctxt_desc_num = 1; + + if (offloads & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_UDP_SEG)) + desc_sum_num = sxe2_tx_pkt_data_desc_count(tx_pkt) + ctxt_desc_num; + else + desc_sum_num = tx_pkt->nb_segs + ctxt_desc_num; + + last_use = next_use + desc_sum_num - 1; + if (last_use >= txq->ring_depth) + last_use = last_use - txq->ring_depth; + + if (desc_sum_num > txq->desc_free_num) { + if (unlikely(sxe2_tx_cleanup(txq) != 0)) + goto l_exit_logic; + + if (unlikely(desc_sum_num > txq->rs_thresh)) { + while (desc_sum_num > txq->desc_free_num) + if (unlikely(sxe2_tx_cleanup(txq) != 0)) + goto l_exit_logic; + } + } + + desc_offset |= SXE2_TX_DATA_DESC_MACLEN_VAL(ol_info.l2_len); + + if (offloads & SXE2_TX_OFFLOAD_CKSUM_MASK) { + sxe2_tx_desc_checksum_fill(offloads, &desc_cmd, + &desc_offset, ol_info); + } + + if (offloads & (RTE_MBUF_F_TX_VLAN | RTE_MBUF_F_TX_QINQ)) { + desc_cmd |= SXE2_TX_DATA_DESC_CMD_IL2TAG1; + desc_tag = tx_pkt->vlan_tci; + } + + if (ctxt_desc_num) { + ctxt_desc = (volatile struct sxe2_tx_context_desc *) + &desc_ring[next_use]; + desc_l2tag2 = 0; + desc_type_cmd_tso_mss = SXE2_TX_DESC_DTYPE_CTXT; + + next_buffer = &buffer_ring[buffer->next_id]; + RTE_MBUF_PREFETCH_TO_FREE(next_buffer->mbuf); + + if (buffer->mbuf) { + rte_pktmbuf_free_seg(buffer->mbuf); + buffer->mbuf = NULL; + } + + if (offloads & RTE_MBUF_F_TX_QINQ) { + desc_l2tag2 = tx_pkt->vlan_tci_outer; + desc_type_cmd_tso_mss |= SXE2_TX_CTXT_DESC_CMD_IL2TAG2_MASK; + } + + ctxt_desc->tunneling_params = + rte_cpu_to_le_32(desc_tunneling_params); + ctxt_desc->l2tag2 = rte_cpu_to_le_16(desc_l2tag2); + ctxt_desc->type_cmd_tso_mss = rte_cpu_to_le_64(desc_type_cmd_tso_mss); + ctxt_desc->ipsec_offset = rte_cpu_to_le_64(ipsec_offset); + + buffer->last_id = last_use; + next_use = buffer->next_id; + buffer = next_buffer; + } + + m_seg = tx_pkt; + + do { + desc = &desc_ring[next_use]; + next_buffer = &buffer_ring[buffer->next_id]; + RTE_MBUF_PREFETCH_TO_FREE(next_buffer->mbuf); + if (buffer->mbuf) { + rte_pktmbuf_free_seg(buffer->mbuf); + buffer->mbuf = NULL; + } + + buffer->mbuf = m_seg; + seg_len = m_seg->data_len; + buf_dma_addr = rte_mbuf_data_iova(m_seg); + while ((offloads & (RTE_MBUF_F_TX_TCP_SEG | RTE_MBUF_F_TX_UDP_SEG)) && + unlikely(seg_len > SXE2_TX_MAX_DATA_NUM_PER_DESC)) { + desc->read.buf_addr = rte_cpu_to_le_64(buf_dma_addr); + desc->read.type_cmd_off_bsz_l2t = + sxe2_tx_data_desc_build_cobt(desc_cmd, desc_offset, + SXE2_TX_MAX_DATA_NUM_PER_DESC, + desc_tag); + buf_dma_addr += SXE2_TX_MAX_DATA_NUM_PER_DESC; + seg_len -= SXE2_TX_MAX_DATA_NUM_PER_DESC; + buffer->last_id = last_use; + next_use = buffer->next_id; + buffer = next_buffer; + desc = &desc_ring[next_use]; + next_buffer = &buffer_ring[buffer->next_id]; + RTE_MBUF_PREFETCH_TO_FREE(next_buffer->mbuf); + } + + desc->read.buf_addr = rte_cpu_to_le_64(buf_dma_addr); + desc->read.type_cmd_off_bsz_l2t = + sxe2_tx_data_desc_build_cobt(desc_cmd, + desc_offset, seg_len, desc_tag); + + buffer->last_id = last_use; + next_use = buffer->next_id; + buffer = next_buffer; + + m_seg = m_seg->next; + } while (m_seg); + + desc_cmd |= SXE2_TX_DATA_DESC_CMD_EOP; + txq->desc_used_num += desc_sum_num; + txq->desc_free_num -= desc_sum_num; + + if (txq->desc_used_num >= txq->rs_thresh) { + PMD_LOG_TX_DEBUG("Tx pkts set RS bit." + "last_use=%u port_id=%u, queue_id=%u", + last_use, txq->port_id, txq->queue_id); + desc_cmd |= SXE2_TX_DATA_DESC_CMD_RS; + + txq->desc_used_num = 0; + } + + desc->read.type_cmd_off_bsz_l2t |= + rte_cpu_to_le_64(((u64)desc_cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT); + } + +l_exit_logic: + if (tx_num == 0) + goto l_end; + goto l_end_of_tx; + +l_end_of_tx: + SXE2_PCI_REG_WRITE_WC(txq->tdt_reg_addr, next_use); + PMD_LOG_TX_DEBUG("port_id=%u queue_id=%u next_use=%u send_pkts=%u", + txq->port_id, txq->queue_id, next_use, tx_num); + SXE2_TX_STATS_CNT(txq, tx_pkts_num, tx_num); + + txq->next_use = next_use; + +l_end: + return tx_num; +} + +static inline void +sxe2_update_rx_tail(struct sxe2_rx_queue *rxq, u16 hold_num, u16 rx_id) +{ + hold_num += rxq->hold_num; + + if (hold_num > rxq->rx_free_thresh) { + rx_id = (u16)((rx_id == 0) ? (rxq->ring_depth - 1) : (rx_id - 1)); + SXE2_PCI_REG_WRITE_WC(rxq->rdt_reg_addr, rx_id); + hold_num = 0; + } + rxq->hold_num = hold_num; +} + +static inline u64 +sxe2_rx_desc_error_para(__rte_unused struct sxe2_rx_queue *rxq, + union sxe2_rx_desc *desc) +{ + u64 flags = 0; + u64 desc_qw1 = rte_le_to_cpu_64(desc->wb.status_err_ptype_len); + + if (unlikely(0 == (desc_qw1 & SXE2_RX_DESC_STATUS_L3L4_P_MASK))) + goto l_end; + + if (likely(0 == (desc->wb.rxdid_src & SXE2_RX_DESC_EUDPE_MASK))) { + flags = RTE_MBUF_F_RX_OUTER_L4_CKSUM_GOOD; + } else { + flags = RTE_MBUF_F_RX_OUTER_L4_CKSUM_BAD; + SXE2_RX_STATS_CNT(rxq, outer_l4_csum_err, 1); + } + + if (likely(0 == (desc_qw1 & SXE2_RX_DESC_QW1_ERRORS_MASK))) { + flags |= (RTE_MBUF_F_RX_IP_CKSUM_GOOD | + RTE_MBUF_F_RX_L4_CKSUM_GOOD | + RTE_MBUF_F_RX_OUTER_L4_CKSUM_GOOD); + goto l_end; + } + + if (likely(0 == (desc_qw1 & SXE2_RX_DESC_ERROR_CSUM_IPE_MASK))) { + flags |= RTE_MBUF_F_RX_IP_CKSUM_GOOD; + } else { + flags |= RTE_MBUF_F_RX_IP_CKSUM_BAD; + SXE2_RX_STATS_CNT(rxq, ip_csum_err, 1); + } + + if (likely(0 == (desc_qw1 & SXE2_RX_DESC_ERROR_CSUM_L4_MASK))) { + flags |= RTE_MBUF_F_RX_L4_CKSUM_GOOD; + } else { + flags |= RTE_MBUF_F_RX_L4_CKSUM_BAD; + SXE2_RX_STATS_CNT(rxq, l4_csum_err, 1); + } + + if (unlikely(0 != (desc_qw1 & SXE2_RX_DESC_ERROR_CSUM_EIP_MASK))) { + flags |= RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD; + SXE2_RX_STATS_CNT(rxq, outer_ip_csum_err, 1); + } + +l_end: + return flags; +} + +static __rte_always_inline void +sxe2_rx_mbuf_common_fields_fill(struct sxe2_rx_queue *rxq, struct rte_mbuf *mbuf, + union sxe2_rx_desc *rxd) +{ + u32 *ptype_tbl = rxq->vsi->adapter->ptype_tbl; + u64 qword1; + u64 pkt_flags; + qword1 = rte_le_to_cpu_64(rxd->wb.status_err_ptype_len); + + mbuf->ol_flags = 0; + mbuf->packet_type = ptype_tbl[SXE2_RX_DESC_PTYPE_VAL_GET(qword1)]; + + pkt_flags = sxe2_rx_desc_error_para(rxq, rxd); + + SXE2_RX_STATS_CNT(rxq, ptype_pkts[SXE2_RX_DESC_PTYPE_VAL_GET(qword1)], 1); + SXE2_RX_STATS_CNT(rxq, rx_pkts_num, 1); + mbuf->ol_flags |= pkt_flags; +} + +static __rte_always_inline void +sxe2_rx_sw_stats_update(struct sxe2_rx_queue *rxq, struct rte_mbuf *mbuf, + union sxe2_rx_desc *rxd) +{ + u64 qword1 = rte_le_to_cpu_64(rxd->wb.status_err_ptype_len); + rte_atomic_fetch_add_explicit(&rxq->sw_stats.pkts, 1, + rte_memory_order_relaxed); + rte_atomic_fetch_add_explicit(&rxq->sw_stats.bytes, + mbuf->pkt_len + RTE_ETHER_CRC_LEN, + rte_memory_order_relaxed); + switch (SXE2_RX_DESC_STATUS_UMBCAST_VAL_GET(qword1)) { + case SXE2_RX_DESC_STATUS_UNICAST: + rte_atomic_fetch_add_explicit(&rxq->sw_stats.unicast_pkts, 1, + rte_memory_order_relaxed); + break; + case SXE2_RX_DESC_STATUS_MUTICAST: + rte_atomic_fetch_add_explicit(&rxq->sw_stats.multicast_pkts, 1, + rte_memory_order_relaxed); + break; + case SXE2_RX_DESC_STATUS_BOARDCAST: + rte_atomic_fetch_add_explicit(&rxq->sw_stats.broadcast_pkts, 1, + rte_memory_order_relaxed); + break; + default: + break; + } +} + +u16 sxe2_rx_pkts_scattered(void *rx_queue, struct rte_mbuf **rx_pkts, u16 nb_pkts) +{ + struct sxe2_rx_queue *rxq = (struct sxe2_rx_queue *)rx_queue; + volatile union sxe2_rx_desc *desc_ring; + volatile union sxe2_rx_desc *desc; + union sxe2_rx_desc desc_tmp; + struct rte_mbuf **buffer_ring; + struct rte_mbuf **cur_buffer; + struct rte_mbuf *cur_mbuf; + struct rte_mbuf *new_mbuf; + struct rte_mbuf *first_seg; + struct rte_mbuf *last_seg; + u64 qword1; + u16 done_num; + u16 hold_num; + u16 cur_idx; + u16 pkt_len; + + desc_ring = rxq->desc_ring; + buffer_ring = rxq->buffer_ring; + cur_idx = rxq->processing_idx; + first_seg = rxq->pkt_first_seg; + last_seg = rxq->pkt_last_seg; + done_num = 0; + hold_num = 0; + while (done_num < nb_pkts) { + desc = &desc_ring[cur_idx]; + qword1 = rte_le_to_cpu_64(desc->wb.status_err_ptype_len); + if (0 == (SXE2_RX_DESC_STATUS_DD_MASK & qword1)) + break; + + new_mbuf = rte_mbuf_raw_alloc(rxq->mb_pool); + if (unlikely(new_mbuf == NULL)) { + rxq->vsi->adapter->dev_info.dev_data->rx_mbuf_alloc_failed++; + PMD_LOG_INFO(RX, "Rx new_mbuf alloc failed port_id:%u " + "queue_id:%u", rxq->port_id, rxq->queue_id); + break; + } + + hold_num++; + desc_tmp = *desc; + cur_buffer = &buffer_ring[cur_idx]; + cur_idx++; + if (unlikely(cur_idx == rxq->ring_depth)) + cur_idx = 0; + + rte_prefetch0(buffer_ring[cur_idx]); + + if (0 == (cur_idx & 0x3)) { + rte_prefetch0(&desc_ring[cur_idx]); + rte_prefetch0(&buffer_ring[cur_idx]); + } + + cur_mbuf = *cur_buffer; + + *cur_buffer = new_mbuf; + + desc->read.hdr_addr = 0; + desc->read.pkt_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(new_mbuf)); + + pkt_len = SXE2_RX_DESC_PKT_LEN_VAL_GET(qword1); + cur_mbuf->data_len = pkt_len; + cur_mbuf->data_off = RTE_PKTMBUF_HEADROOM; + + if (first_seg == NULL) { + first_seg = cur_mbuf; + first_seg->nb_segs = 1; + first_seg->pkt_len = pkt_len; + } else { + first_seg->pkt_len += pkt_len; + first_seg->nb_segs++; + last_seg->next = cur_mbuf; + } + + if (0 == (qword1 & SXE2_RX_DESC_STATUS_EOP_MASK)) { + last_seg = cur_mbuf; + continue; + } + + if (unlikely(qword1 & SXE2_RX_DESC_ERROR_RXE_MASK) || + unlikely(qword1 & SXE2_RX_DESC_ERROR_OVERSIZE_MASK)) { + rte_atomic_fetch_add_explicit(&rxq->sw_stats.drop_pkts, 1, + rte_memory_order_relaxed); + rte_atomic_fetch_add_explicit(&rxq->sw_stats.drop_bytes, + first_seg->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN, + rte_memory_order_relaxed); + rte_pktmbuf_free(first_seg); + first_seg = NULL; + continue; + } + + cur_mbuf->next = NULL; + if (unlikely(rxq->crc_len > 0)) { + first_seg->pkt_len -= RTE_ETHER_CRC_LEN; + + if (pkt_len <= RTE_ETHER_CRC_LEN) { + rte_pktmbuf_free_seg(cur_mbuf); + first_seg->nb_segs--; + last_seg->data_len = last_seg->data_len + pkt_len - + RTE_ETHER_CRC_LEN; + last_seg->next = NULL; + } else { + cur_mbuf->data_len = pkt_len - RTE_ETHER_CRC_LEN; + } + + } else if (pkt_len == 0) { + rte_pktmbuf_free_seg(cur_mbuf); + first_seg->nb_segs--; + last_seg->next = NULL; + } + + rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr, first_seg->data_off)); + first_seg->port = rxq->port_id; + + sxe2_rx_mbuf_common_fields_fill(rxq, first_seg, &desc_tmp); + + if (rxq->vsi->adapter->devargs.sw_stats_en) + sxe2_rx_sw_stats_update(rxq, first_seg, &desc_tmp); + + rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr, first_seg->data_off)); + + rx_pkts[done_num] = first_seg; + done_num++; + + first_seg = NULL; + } + + rxq->processing_idx = cur_idx; + rxq->pkt_first_seg = first_seg; + rxq->pkt_last_seg = last_seg; + + sxe2_update_rx_tail(rxq, hold_num, cur_idx); + + return done_num; +} + +u16 sxe2_rx_pkts_scattered_split(void *rx_queue, struct rte_mbuf **rx_pkts, u16 nb_pkts) +{ + struct sxe2_rx_queue *rxq = (struct sxe2_rx_queue *)rx_queue; + volatile union sxe2_rx_desc *desc_ring; + volatile union sxe2_rx_desc *desc; + union sxe2_rx_desc desc_tmp; + struct rte_mbuf **buffer_ring; + struct rte_mbuf **cur_buffer; + struct rte_mbuf *cur_mbuf; + struct rte_mbuf *cur_mbuf_pay; + struct rte_mbuf *new_mbuf; + struct rte_mbuf *new_mbuf_pay; + struct rte_mbuf *first_seg; + struct rte_mbuf *last_seg; + u64 qword1; + u16 done_num; + u16 hold_num; + u16 cur_idx; + u16 pkt_len; + u16 hdr_len; + + desc_ring = rxq->desc_ring; + buffer_ring = rxq->buffer_ring; + cur_idx = rxq->processing_idx; + first_seg = rxq->pkt_first_seg; + last_seg = rxq->pkt_last_seg; + done_num = 0; + hold_num = 0; + new_mbuf = NULL; + + while (done_num < nb_pkts) { + desc = &desc_ring[cur_idx]; + qword1 = rte_le_to_cpu_64(desc->wb.status_err_ptype_len); + + if (0 == (SXE2_RX_DESC_STATUS_DD_MASK & qword1)) + break; + + if ((rxq->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) == 0 || + first_seg == NULL) { + new_mbuf = rte_mbuf_raw_alloc(rxq->mb_pool); + if (unlikely(new_mbuf == NULL)) { + rxq->vsi->adapter->dev_info.dev_data->rx_mbuf_alloc_failed++; + PMD_LOG_RX_INFO("Rx new_mbuf alloc failed port_id=%u " + "queue_id=%u", rxq->port_id, + rxq->idx_in_pf); + break; + } + } + + if (rxq->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) { + new_mbuf_pay = rte_mbuf_raw_alloc(rxq->rx_seg[1].mp); + if (unlikely(new_mbuf_pay == NULL)) { + rxq->vsi->adapter->dev_info.dev_data->rx_mbuf_alloc_failed++; + PMD_LOG_RX_INFO("Rx new_mbuf_pay alloc failed port_id=%u " + "queue_id=%u", rxq->port_id, + rxq->idx_in_pf); + if (new_mbuf != NULL) + rte_pktmbuf_free(new_mbuf); + new_mbuf = NULL; + break; + } + } + + hold_num++; + desc_tmp = *desc; + cur_buffer = &buffer_ring[cur_idx]; + cur_idx++; + if (unlikely(cur_idx == rxq->ring_depth)) + cur_idx = 0; + rte_prefetch0(buffer_ring[cur_idx]); + if (0 == (cur_idx & 0x3)) { + rte_prefetch0(&desc_ring[cur_idx]); + rte_prefetch0(&buffer_ring[cur_idx]); + } + cur_mbuf = *cur_buffer; + if (0 == (rxq->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT)) { + *cur_buffer = new_mbuf; + desc->read.hdr_addr = 0; + desc->read.pkt_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(new_mbuf)); + } else { + if (first_seg == NULL) { + *cur_buffer = new_mbuf; + new_mbuf->next = new_mbuf_pay; + new_mbuf->data_off = RTE_PKTMBUF_HEADROOM; + new_mbuf_pay->next = NULL; + new_mbuf_pay->data_off = RTE_PKTMBUF_HEADROOM; + desc->read.hdr_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(new_mbuf)); + desc->read.pkt_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(new_mbuf_pay)); + } else { + cur_mbuf_pay = cur_mbuf->next; + cur_mbuf->next = new_mbuf_pay; + new_mbuf_pay->next = NULL; + new_mbuf_pay->data_off = RTE_PKTMBUF_HEADROOM; + desc->read.hdr_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(cur_mbuf)); + desc->read.pkt_addr = + rte_cpu_to_le_64(rte_mbuf_data_iova_default(new_mbuf_pay)); + cur_mbuf = cur_mbuf_pay; + } + } + + if (0 == (rxq->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT)) { + pkt_len = SXE2_RX_DESC_PKT_LEN_VAL_GET(qword1); + cur_mbuf->data_len = pkt_len; + cur_mbuf->data_off = RTE_PKTMBUF_HEADROOM; + if (first_seg == NULL) { + first_seg = cur_mbuf; + first_seg->nb_segs = 1; + first_seg->pkt_len = pkt_len; + } else { + first_seg->pkt_len += pkt_len; + first_seg->nb_segs++; + last_seg->next = cur_mbuf; + } + } else { + if (first_seg == NULL) { + cur_mbuf->nb_segs = 2; + cur_mbuf->next->next = NULL; + pkt_len = SXE2_RX_DESC_PKT_LEN_VAL_GET(qword1); + hdr_len = SXE2_RX_DESC_HDR_LEN_VAL_GET(qword1); + cur_mbuf->data_len = hdr_len; + cur_mbuf->pkt_len = hdr_len + pkt_len; + cur_mbuf->next->data_len = pkt_len; + first_seg = cur_mbuf; + cur_mbuf = cur_mbuf->next; + last_seg = cur_mbuf; + } else { + cur_mbuf->nb_segs = 1; + cur_mbuf->next = NULL; + pkt_len = SXE2_RX_DESC_PKT_LEN_VAL_GET(qword1); + cur_mbuf->data_len = pkt_len; + + first_seg->pkt_len += pkt_len; + first_seg->nb_segs++; + last_seg->next = cur_mbuf; + } + } + +#ifdef RTE_ETHDEV_DEBUG_RX + + rte_pktmbuf_dump(stdout, first_seg, rte_pktmbuf_pkt_len(first_seg)); +#endif + + if (0 == (rte_le_to_cpu_64(desc_tmp.wb.status_err_ptype_len) & + SXE2_RX_DESC_STATUS_EOP_MASK)) { + last_seg = cur_mbuf; + continue; + } + + if (unlikely(qword1 & SXE2_RX_DESC_ERROR_RXE_MASK) || + unlikely(qword1 & SXE2_RX_DESC_ERROR_OVERSIZE_MASK)) { + rte_atomic_fetch_add_explicit(&rxq->sw_stats.drop_pkts, 1, + rte_memory_order_relaxed); + rte_atomic_fetch_add_explicit(&rxq->sw_stats.drop_bytes, + first_seg->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN, + rte_memory_order_relaxed); + rte_pktmbuf_free(first_seg); + first_seg = NULL; + continue; + } + + cur_mbuf->next = NULL; + if (unlikely(rxq->crc_len > 0)) { + first_seg->pkt_len -= RTE_ETHER_CRC_LEN; + if (pkt_len <= RTE_ETHER_CRC_LEN) { + rte_pktmbuf_free_seg(cur_mbuf); + cur_mbuf = NULL; + first_seg->nb_segs--; + last_seg->data_len = last_seg->data_len + + pkt_len - RTE_ETHER_CRC_LEN; + last_seg->next = NULL; + } else { + cur_mbuf->data_len = pkt_len - RTE_ETHER_CRC_LEN; + } + } else if (pkt_len == 0) { + rte_pktmbuf_free_seg(cur_mbuf); + cur_mbuf = NULL; + first_seg->nb_segs--; + last_seg->next = NULL; + } + + first_seg->port = rxq->port_id; + sxe2_rx_mbuf_common_fields_fill(rxq, first_seg, &desc_tmp); + + if (rxq->vsi->adapter->devargs.sw_stats_en) + sxe2_rx_sw_stats_update(rxq, first_seg, &desc_tmp); + + rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr, first_seg->data_off)); + + rx_pkts[done_num] = first_seg; + done_num++; + + first_seg = NULL; + } + + rxq->processing_idx = cur_idx; + rxq->pkt_first_seg = first_seg; + rxq->pkt_last_seg = last_seg; + + sxe2_update_rx_tail(rxq, hold_num, cur_idx); + + return done_num; +} -- 2.47.3
