* [PATCH v5 05/23] net/sxe2: add link update callback
From: liujie5 @ 2026-06-22 9:24 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260622092324.3091185-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
Implement dev_link_update ethdev callback for sxe2 PMD.
The driver reads the link status, speed, and duplex mode from the
hardware registers and updates the ethdev link status using the
appropriate atomic operations.
Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
---
drivers/net/sxe2/meson.build | 1 +
drivers/net/sxe2/sxe2_cmd_chnl.c | 22 +++++
drivers/net/sxe2/sxe2_cmd_chnl.h | 2 +
drivers/net/sxe2/sxe2_drv_cmd.h | 6 ++
drivers/net/sxe2/sxe2_ethdev.c | 158 +++++++++++++++++++++++++------
drivers/net/sxe2/sxe2_ethdev.h | 19 ++--
drivers/net/sxe2/sxe2_mac.c | 98 +++++++++++++++++++
drivers/net/sxe2/sxe2_mac.h | 50 ++++++++++
8 files changed, 316 insertions(+), 40 deletions(-)
create mode 100644 drivers/net/sxe2/sxe2_mac.c
create mode 100644 drivers/net/sxe2/sxe2_mac.h
diff --git a/drivers/net/sxe2/meson.build b/drivers/net/sxe2/meson.build
index c225dd7cd8..b14b5120c1 100644
--- a/drivers/net/sxe2/meson.build
+++ b/drivers/net/sxe2/meson.build
@@ -60,4 +60,5 @@ sources += files(
'sxe2_txrx_poll.c',
'sxe2_txrx.c',
'sxe2_txrx_vec.c',
+ 'sxe2_mac.c',
)
diff --git a/drivers/net/sxe2/sxe2_cmd_chnl.c b/drivers/net/sxe2/sxe2_cmd_chnl.c
index d16b6528d0..07eeb7f38c 100644
--- a/drivers/net/sxe2/sxe2_cmd_chnl.c
+++ b/drivers/net/sxe2/sxe2_cmd_chnl.c
@@ -321,3 +321,25 @@ int32_t sxe2_drv_txq_switch(struct sxe2_adapter *adapter, struct sxe2_tx_queue *
return ret;
}
+
+int32_t sxe2_drv_mac_link_status_get(struct sxe2_adapter *adapter)
+{
+ int32_t ret = 0;
+ struct sxe2_common_device *cdev = adapter->cdev;
+ struct sxe2_drv_cmd_params param = {0};
+ struct sxe2_drv_link_info_resp resp = {0};
+
+ sxe2_drv_cmd_params_fill(adapter, ¶m, SXE2_DRV_CMD_LINK_STATUS_GET,
+ NULL, 0,
+ &resp, sizeof(resp));
+ ret = sxe2_drv_cmd_exec(cdev, ¶m);
+ if (ret) {
+ PMD_DEV_LOG_ERR(adapter, DRV, "link status get failed, ret=%d", ret);
+ goto l_end;
+ }
+ adapter->link_ctxt.speed = resp.speed;
+ adapter->link_ctxt.link_up = resp.status;
+
+l_end:
+ return ret;
+}
diff --git a/drivers/net/sxe2/sxe2_cmd_chnl.h b/drivers/net/sxe2/sxe2_cmd_chnl.h
index ed5e842346..cda676ed97 100644
--- a/drivers/net/sxe2/sxe2_cmd_chnl.h
+++ b/drivers/net/sxe2/sxe2_cmd_chnl.h
@@ -34,4 +34,6 @@ int32_t sxe2_drv_txq_ctxt_cfg(struct sxe2_adapter *adapter,
struct sxe2_tx_queue *txq,
uint16_t txq_cnt);
+int32_t sxe2_drv_mac_link_status_get(struct sxe2_adapter *adapter);
+
#endif /* SXE2_CMD_CHNL_H */
diff --git a/drivers/net/sxe2/sxe2_drv_cmd.h b/drivers/net/sxe2/sxe2_drv_cmd.h
index ccc9c20ef4..a0f08b5184 100644
--- a/drivers/net/sxe2/sxe2_drv_cmd.h
+++ b/drivers/net/sxe2/sxe2_drv_cmd.h
@@ -227,6 +227,12 @@ struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_info_get_resp {
struct sxe2_drv_msix_caps used_msix;
} __rte_packed_end;
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_link_info_resp {
+ uint32_t speed;
+ uint8_t status;
+ uint8_t rsv[3];
+} __rte_packed_end;
+
enum sxe2_drv_cmd_module {
SXE2_DRV_CMD_MODULE_HANDSHAKE = 0,
SXE2_DRV_CMD_MODULE_DEV = 1,
diff --git a/drivers/net/sxe2/sxe2_ethdev.c b/drivers/net/sxe2/sxe2_ethdev.c
index 066e1faf7e..c00569f05b 100644
--- a/drivers/net/sxe2/sxe2_ethdev.c
+++ b/drivers/net/sxe2/sxe2_ethdev.c
@@ -27,6 +27,7 @@
#include "sxe2_tx.h"
#include "sxe2_rx.h"
#include "sxe2_txrx.h"
+#include "sxe2_mac.h"
#include "sxe2_common.h"
#include "sxe2_common_log.h"
#include "sxe2_host_regs.h"
@@ -78,6 +79,41 @@ static struct sxe2_pci_map_addr_info sxe2_net_map_addr_info_pf[SXE2_PCI_MAP_RES_
.reg_width = 10},
};
+static int32_t sxe2_dev_configure(struct rte_eth_dev *dev);
+static int32_t sxe2_dev_start(struct rte_eth_dev *dev);
+static int32_t sxe2_dev_stop(struct rte_eth_dev *dev);
+static int32_t sxe2_dev_close(struct rte_eth_dev *dev);
+static int32_t sxe2_dev_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info);
+static const uint32_t *sxe2_buffer_split_supported_hdr_ptypes_get(struct rte_eth_dev *dev
+ __rte_unused, size_t *no_of_elements __rte_unused);
+
+static const struct eth_dev_ops sxe2_eth_dev_ops = {
+ .dev_configure = sxe2_dev_configure,
+ .dev_start = sxe2_dev_start,
+ .dev_stop = sxe2_dev_stop,
+ .dev_close = sxe2_dev_close,
+ .dev_infos_get = sxe2_dev_infos_get,
+ .dev_supported_ptypes_get = sxe2_dev_supported_ptypes_get,
+ .link_update = sxe2_link_update,
+
+ .rx_queue_start = sxe2_rx_queue_start,
+ .rx_queue_stop = sxe2_rx_queue_stop,
+ .tx_queue_start = sxe2_tx_queue_start,
+ .tx_queue_stop = sxe2_tx_queue_stop,
+ .rx_queue_setup = sxe2_rx_queue_setup,
+ .rx_queue_release = sxe2_rx_queue_release,
+ .tx_queue_setup = sxe2_tx_queue_setup,
+ .tx_queue_release = sxe2_tx_queue_release,
+ .rxq_info_get = sxe2_rx_queue_info_get,
+ .txq_info_get = sxe2_tx_queue_info_get,
+ .rx_burst_mode_get = sxe2_rx_burst_mode_get,
+ .tx_burst_mode_get = sxe2_tx_burst_mode_get,
+ .tx_done_cleanup = sxe2_tx_done_cleanup,
+
+ .mtu_set = sxe2_mtu_set,
+ .buffer_split_supported_hdr_ptypes_get = sxe2_buffer_split_supported_hdr_ptypes_get,
+};
+
static int32_t sxe2_dev_configure(struct rte_eth_dev *dev)
{
int32_t ret = 0;
@@ -122,6 +158,12 @@ static int32_t sxe2_dev_start(struct rte_eth_dev *dev)
sxe2_rx_mode_func_set(dev);
sxe2_tx_mode_func_set(dev);
+ ret = sxe2_link_update_init(dev);
+ if (ret) {
+ PMD_LOG_ERR(INIT, "Failed to initialize link update, ret:%d", ret);
+ goto l_end;
+ }
+
ret = sxe2_queues_start(dev);
if (ret) {
PMD_LOG_ERR(INIT, "enable queues failed");
@@ -136,16 +178,6 @@ static int32_t sxe2_dev_start(struct rte_eth_dev *dev)
return ret;
}
-static int32_t sxe2_dev_close(struct rte_eth_dev *dev)
-{
- (void)sxe2_dev_stop(dev);
- (void)sxe2_queues_release(dev);
- sxe2_vsi_uninit(dev);
- sxe2_dev_pci_map_uinit(dev);
-
- return 0;
-}
-
static int32_t sxe2_dev_infos_get(struct rte_eth_dev *dev,
struct rte_eth_dev_info *dev_info)
{
@@ -270,28 +302,49 @@ static int32_t sxe2_dev_infos_get(struct rte_eth_dev *dev,
return 0;
}
-static const struct eth_dev_ops sxe2_eth_dev_ops = {
- .dev_configure = sxe2_dev_configure,
- .dev_start = sxe2_dev_start,
- .dev_stop = sxe2_dev_stop,
- .dev_close = sxe2_dev_close,
- .dev_infos_get = sxe2_dev_infos_get,
-
- .rx_queue_start = sxe2_rx_queue_start,
- .rx_queue_stop = sxe2_rx_queue_stop,
- .tx_queue_start = sxe2_tx_queue_start,
- .tx_queue_stop = sxe2_tx_queue_stop,
- .rx_queue_setup = sxe2_rx_queue_setup,
- .rx_queue_release = sxe2_rx_queue_release,
- .tx_queue_setup = sxe2_tx_queue_setup,
- .tx_queue_release = sxe2_tx_queue_release,
+static const uint32_t *
+sxe2_buffer_split_supported_hdr_ptypes_get(struct rte_eth_dev *dev __rte_unused,
+ size_t *no_of_elements __rte_unused)
+{
+ static const uint32_t ptypes[] = {
+ RTE_PTYPE_L2_ETHER,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_L4_UDP,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_L4_TCP,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_L4_SCTP,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_L4_UDP,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_L4_TCP,
+ RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_L4_SCTP,
+
+ RTE_PTYPE_TUNNEL_GRENAT,
+
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN,
+
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+
+ RTE_PTYPE_UNKNOWN
+ };
- .rxq_info_get = sxe2_rx_queue_info_get,
- .txq_info_get = sxe2_tx_queue_info_get,
- .rx_burst_mode_get = sxe2_rx_burst_mode_get,
- .tx_burst_mode_get = sxe2_tx_burst_mode_get,
- .tx_done_cleanup = sxe2_tx_done_cleanup,
-};
+ return ptypes;
+}
struct sxe2_pci_map_bar_info *sxe2_dev_get_bar_info(struct sxe2_adapter *adapter,
enum sxe2_pci_map_resource res_type)
@@ -360,6 +413,29 @@ void *sxe2_pci_map_addr_get(struct sxe2_adapter *adapter,
return addr;
}
+static int32_t sxe2_eth_init(struct rte_eth_dev *dev)
+{
+ int32_t ret = 0;
+
+ ret = sxe2_link_update_init(dev);
+ if (ret) {
+ PMD_LOG_ERR(INIT, "Failed to initialize link update, ret:%d", ret);
+ goto l_end;
+ }
+
+ ret = sxe2_mtu_set(dev, dev->data->mtu);
+ if (ret) {
+ PMD_LOG_ERR(INIT, "Failed to set mtu, ret=%d", ret);
+ goto l_end;
+ }
+l_end:
+ return ret;
+}
+
+static void sxe2_eth_uinit(struct rte_eth_dev *dev __rte_unused)
+{
+}
+
static void sxe2_drv_dev_caps_set(struct sxe2_adapter *adapter,
struct sxe2_drv_dev_caps_resp *dev_caps)
{
@@ -789,18 +865,38 @@ static int32_t sxe2_dev_init(struct rte_eth_dev *dev,
goto init_dev_info_err;
}
+ ret = sxe2_eth_init(dev);
+ if (ret) {
+ PMD_LOG_ERR(INIT, "Failed to initialize eth parameters, ret=%d", ret);
+ goto init_eth_err;
+ }
+
goto l_end;
+init_eth_err:
init_dev_info_err:
sxe2_vsi_uninit(dev);
init_vsi_err:
+ sxe2_dev_pci_map_uinit(dev);
l_end:
return ret;
}
+static int32_t sxe2_dev_close(struct rte_eth_dev *dev)
+{
+ (void)sxe2_dev_stop(dev);
+ (void)sxe2_queues_release(dev);
+ sxe2_vsi_uninit(dev);
+ sxe2_dev_pci_map_uinit(dev);
+ sxe2_eth_uinit(dev);
+
+ return 0;
+}
+
static int32_t sxe2_dev_uninit(struct rte_eth_dev *dev)
{
int32_t ret = 0;
+
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
goto l_end;
diff --git a/drivers/net/sxe2/sxe2_ethdev.h b/drivers/net/sxe2/sxe2_ethdev.h
index 97d1d1fe14..4193603306 100644
--- a/drivers/net/sxe2/sxe2_ethdev.h
+++ b/drivers/net/sxe2/sxe2_ethdev.h
@@ -120,12 +120,6 @@ enum {
SXE2_FLAGS_NBITS
};
-struct sxe2_link_context {
- rte_spinlock_t link_lock;
- bool link_up;
- uint32_t speed;
-};
-
struct sxe2_devargs {
uint8_t flow_dup_pattern_mode;
uint8_t func_flow_direct_en;
@@ -266,6 +260,12 @@ struct sxe2_sched_hw_cap {
uint8_t adj_lvl;
};
+struct sxe2_link_context {
+ rte_spinlock_t link_lock;
+ bool link_up;
+ uint32_t speed;
+};
+
struct sxe2_adapter {
struct sxe2_common_device *cdev;
struct sxe2_dev_info dev_info;
@@ -275,9 +275,10 @@ struct sxe2_adapter {
struct sxe2_irq_context irq_ctxt;
struct sxe2_queue_context q_ctxt;
struct sxe2_vsi_context vsi_ctxt;
- struct sxe2_devargs devargs;
- uint16_t dev_port_id;
- uint64_t cap_flags;
+ struct sxe2_link_context link_ctxt;
+ struct sxe2_devargs devargs;
+ uint16_t dev_port_id;
+ uint64_t cap_flags;
enum sxe2_dev_type dev_type;
struct rte_ether_addr mac_addr;
uint8_t port_idx;
diff --git a/drivers/net/sxe2/sxe2_mac.c b/drivers/net/sxe2/sxe2_mac.c
new file mode 100644
index 0000000000..027e831c97
--- /dev/null
+++ b/drivers/net/sxe2/sxe2_mac.c
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd.
+ */
+
+#include <rte_os.h>
+#include "sxe2_osal.h"
+#include "sxe2_mac.h"
+#include "sxe2_common_log.h"
+#include "sxe2_ethdev.h"
+#include "sxe2_cmd_chnl.h"
+#include "sxe2_host_regs.h"
+
+int32_t sxe2_link_update_init(struct rte_eth_dev *dev)
+{
+ struct sxe2_adapter *adapter = SXE2_DEV_PRIVATE_TO_ADAPTER(dev);
+ int32_t ret;
+
+ PMD_INIT_FUNC_TRACE();
+
+ rte_spinlock_init(&adapter->link_ctxt.link_lock);
+
+ ret = sxe2_drv_mac_link_status_get(adapter);
+ if (ret) {
+ PMD_DEV_LOG_ERR(adapter, DRV, "Failed to get link status, ret=%d", ret);
+ goto l_end;
+ }
+
+ (void)sxe2_link_update(dev, 0);
+
+l_end:
+ return ret;
+}
+int32_t sxe2_link_update(struct rte_eth_dev *dev, __rte_unused int32_t wait_to_complete)
+{
+ struct rte_eth_link new_link;
+ struct sxe2_adapter *adapter = SXE2_DEV_PRIVATE_TO_ADAPTER(dev);
+
+ memset(&new_link, 0, sizeof(new_link));
+
+ switch (adapter->link_ctxt.speed) {
+ case 0:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_NONE;
+ break;
+ case 10:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_10M;
+ break;
+ case 100:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_100M;
+ break;
+ case 1000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_1G;
+ break;
+ case 10000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_10G;
+ break;
+ case 20000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_20G;
+ break;
+ case 25000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_25G;
+ break;
+ case 40000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_40G;
+ break;
+ case 50000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_50G;
+ break;
+ case 100000:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_100G;
+ break;
+ default:
+ new_link.link_speed = RTE_ETH_SPEED_NUM_NONE;
+ break;
+ }
+
+ new_link.link_duplex = RTE_ETH_LINK_FULL_DUPLEX;
+ new_link.link_status = adapter->link_ctxt.link_up ? RTE_ETH_LINK_UP :
+ RTE_ETH_LINK_DOWN;
+ new_link.link_autoneg = !(dev->data->dev_conf.link_speeds &
+ RTE_ETH_LINK_SPEED_FIXED);
+
+ return rte_eth_linkstatus_set(dev, &new_link);
+}
+
+int32_t sxe2_mtu_set(struct rte_eth_dev *dev, uint16_t mtu __rte_unused)
+{
+ struct sxe2_adapter *adapter = SXE2_DEV_PRIVATE_TO_ADAPTER(dev);
+
+ PMD_INIT_FUNC_TRACE();
+
+ if (dev->data->dev_started != 0) {
+ PMD_DEV_LOG_ERR(adapter, DRV, "port %d must be stopped before configuration",
+ dev->data->port_id);
+ return -EBUSY;
+ }
+
+ return 0;
+}
diff --git a/drivers/net/sxe2/sxe2_mac.h b/drivers/net/sxe2/sxe2_mac.h
new file mode 100644
index 0000000000..f2f3edaeff
--- /dev/null
+++ b/drivers/net/sxe2/sxe2_mac.h
@@ -0,0 +1,50 @@
+
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd.
+ */
+
+#ifndef __SXE2_MAC_H__
+#define __SXE2_MAC_H__
+#include <ethdev_driver.h>
+#include "sxe2_host_regs.h"
+
+#define SXE2_NUM_MACADDR_MAX 64
+
+#define SXE2_DPDK_OFFLOAD_OUTER_INSERT_8021Q SXE2_VSI_L2TAGSTXVALID_ID_OUT_VLAN1
+#define SXE2_DPDK_OFFLOAD_OUTER_INSERT_8021AD SXE2_VSI_L2TAGSTXVALID_ID_STAG
+#define SXE2_DPDK_OFFLOAD_OUTER_INSERT_QINQ1 SXE2_VSI_L2TAGSTXVALID_ID_OUT_VLAN2
+#define SXE2_DPDK_OFFLOAD_OUTER_INSERT_VLAN SXE2_VSI_L2TAGSTXVALID_ID_VLAN
+
+#define SXE2_DPDK_OFFLOAD_OUTER_INSERT_ENABLE SXE2_VSI_L2TAGSTXVALID_L2TAG1_VALID
+
+#define SXE2_DPDK_OFFLOAD_OUTER_STRIP_8021Q SXE2_VSI_TSR_ID_OUT_VLAN1
+#define SXE2_DPDK_OFFLOAD_OUTER_STRIP_8021AD SXE2_VSI_TSR_ID_STAG
+#define SXE2_DPDK_OFFLOAD_OUTER_STRIP_QINQ1 SXE2_VSI_TSR_ID_OUT_VLAN2
+
+#define SXE2_DPDK_OFFLOAD_INNER_INSERT_QINQ1 SXE2_VSI_L2TAGSTXVALID_ID_VLAN
+#define SXE2_DPDK_OFFLOAD_INNER_INSERT_ENABLE SXE2_VSI_L2TAGSTXVALID_L2TAG2_VALID
+
+#define SXE2_DPDK_OFFLOAD_INNER_STRIP_QINQ1 SXE2_VSI_TSR_ID_VLAN
+
+#define SXE2_DPDK_OFFLOAD_FIELD (0X0F)
+#define SXE2_DPDK_OFFLOAD_TAGID_FIELD (0X07)
+
+#define SXE2_DPDK_OFFLOAD_OUTER_STRIP_MASK (SXE2_DPDK_OFFLOAD_OUTER_STRIP_8021Q | \
+ SXE2_DPDK_OFFLOAD_OUTER_STRIP_8021AD | \
+ SXE2_DPDK_OFFLOAD_OUTER_STRIP_QINQ1)
+#define SXE2_DPDK_OFFLOAD_STRIP_OFFSET SXE2_VSI_TSR_SHOW_TAG_S
+
+#define SXE2_DPDK_OFFLOAD_INSERT_ENABLE (RTE_BIT32(3))
+
+struct sxe2_mac_mc_list {
+ uint32_t count;
+ struct rte_ether_addr addr[SXE2_NUM_MACADDR_MAX];
+};
+
+int32_t sxe2_link_update_init(struct rte_eth_dev *dev);
+
+int32_t sxe2_link_update(struct rte_eth_dev *dev, __rte_unused int32_t wait_to_complete);
+
+int32_t sxe2_mtu_set(struct rte_eth_dev *dev, uint16_t mtu);
+
+#endif /* __SXE2_MAC_H__ */
--
2.52.0
^ permalink raw reply related
* [PATCH v5 04/23] net/sxe2: add AVX2 vector data path for Rx and Tx
From: liujie5 @ 2026-06-22 9:24 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260622092324.3091185-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
Added AVX256 vectorized versions of Rx and Tx data path functions to
improve packet processing performance.
The vector path uses AVX2 SIMD instructions to process multiple
descriptors per loop, significantly reducing the per-packet overhead.
Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
net/sxe2: support AVX512 vectorized path for Rx and Tx
---
drivers/net/sxe2/meson.build | 9 +
drivers/net/sxe2/sxe2_txrx.c | 38 +-
drivers/net/sxe2/sxe2_txrx_vec.h | 12 +-
drivers/net/sxe2/sxe2_txrx_vec_avx2.c | 747 ++++++++++++++++++++++++++
4 files changed, 801 insertions(+), 5 deletions(-)
create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx2.c
diff --git a/drivers/net/sxe2/meson.build b/drivers/net/sxe2/meson.build
index 7bd0d8120c..c225dd7cd8 100644
--- a/drivers/net/sxe2/meson.build
+++ b/drivers/net/sxe2/meson.build
@@ -39,6 +39,15 @@ if arch_subdir == 'x86'
c_args: avx512_args)
objs += sxe2_avx512_lib.extract_objects('sxe2_txrx_vec_avx512.c')
endif
+ sxe2_avx2_lib = static_library('sxe2_avx2_lib',
+ 'sxe2_txrx_vec_avx2.c',
+ dependencies: [static_rte_ethdev,
+ static_rte_kvargs, static_rte_hash,
+ static_rte_security, static_rte_cryptodev,
+ static_rte_bus_pci],
+ include_directories: includes,
+ c_args: [cflags, '-mavx2'])
+ objs += sxe2_avx2_lib.extract_objects('sxe2_txrx_vec_avx2.c')
endif
sources += files(
diff --git a/drivers/net/sxe2/sxe2_txrx.c b/drivers/net/sxe2/sxe2_txrx.c
index 14179b87a4..00307f2fcc 100644
--- a/drivers/net/sxe2/sxe2_txrx.c
+++ b/drivers/net/sxe2/sxe2_txrx.c
@@ -167,8 +167,14 @@ void sxe2_tx_mode_func_set(struct rte_eth_dev *dev)
PMD_LOG_INFO(TX, "AVX512 is not supported in build env.");
#endif
}
- if ((tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) == 0)
- tx_mode_flags |= SXE2_TX_MODE_VEC_SSE;
+ if (((tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) == 0) &&
+ ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2) == 1) ||
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1)) &&
+ (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_256))
+ tx_mode_flags |= SXE2_TX_MODE_VEC_AVX2;
+
+ if ((0 == (tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK)))
+ tx_mode_flags |= SXE2_TX_MODE_VEC_SSE;
#endif
if (tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) {
ret = sxe2_tx_queues_vec_prepare(dev);
@@ -197,6 +203,13 @@ void sxe2_tx_mode_func_set(struct rte_eth_dev *dev)
dev->tx_pkt_burst = sxe2_tx_pkts_vec_avx512_simple;
}
#endif
+ } else if (tx_mode_flags & SXE2_TX_MODE_VEC_AVX2) {
+ if (tx_mode_flags & SXE2_TX_MODE_VEC_OFFLOAD) {
+ dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_avx2;
+ } else {
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_avx2_simple;
+ }
} else {
if (tx_mode_flags & SXE2_TX_MODE_VEC_OFFLOAD) {
dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
@@ -231,6 +244,10 @@ static const struct {
{ sxe2_tx_pkts_vec_avx512_simple,
"Vector AVX512 Simple" },
#endif
+ { sxe2_tx_pkts_vec_avx2,
+ "Vector AVX2" },
+ { sxe2_tx_pkts_vec_avx2_simple,
+ "Vector AVX2 Simple" },
{ sxe2_tx_pkts_vec_sse,
"Vector SSE" },
{ sxe2_tx_pkts_vec_sse_simple,
@@ -330,7 +347,13 @@ void sxe2_rx_mode_func_set(struct rte_eth_dev *dev)
PMD_LOG_INFO(RX, "AVX512 support detected but not enabled");
#endif
}
- if ((rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) == 0 &&
+ if (((rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) == 0) &&
+ ((rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2) == 1) ||
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1)) &&
+ (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_256))
+ rx_mode_flags |= SXE2_RX_MODE_VEC_AVX2;
+
+ if (((rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) == 0) &&
rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
rx_mode_flags |= SXE2_RX_MODE_VEC_SSE;
#endif
@@ -354,6 +377,11 @@ void sxe2_rx_mode_func_set(struct rte_eth_dev *dev)
else
dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_avx512;
#endif
+ } else if (rx_mode_flags & SXE2_RX_MODE_VEC_AVX2) {
+ if (rx_mode_flags & SXE2_RX_MODE_VEC_OFFLOAD)
+ dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_avx2_offload;
+ else
+ dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_avx2;
} else {
dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_sse_offload;
}
@@ -381,6 +409,10 @@ static const struct {
{ sxe2_rx_pkts_scattered_vec_avx512_offload,
"Offload Vector AVX512 Scattered" },
#endif
+ { sxe2_rx_pkts_scattered_vec_avx2,
+ "Vector AVX2 Scattered" },
+ { sxe2_rx_pkts_scattered_vec_avx2_offload,
+ "Offload Vector AVX2 Scattered" },
{ sxe2_rx_pkts_scattered_vec_sse_offload,
"Vector SSE Scattered" },
#endif
diff --git a/drivers/net/sxe2/sxe2_txrx_vec.h b/drivers/net/sxe2/sxe2_txrx_vec.h
index af7c8d12b2..369777606f 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec.h
+++ b/drivers/net/sxe2/sxe2_txrx_vec.h
@@ -11,19 +11,21 @@
#define SXE2_RX_MODE_VEC_SIMPLE RTE_BIT32(0)
#define SXE2_RX_MODE_VEC_OFFLOAD RTE_BIT32(1)
#define SXE2_RX_MODE_VEC_SSE RTE_BIT32(2)
+#define SXE2_RX_MODE_VEC_AVX2 RTE_BIT32(3)
#define SXE2_RX_MODE_VEC_AVX512 RTE_BIT32(4)
#define SXE2_RX_MODE_BATCH_ALLOC RTE_BIT32(10)
#define SXE2_RX_MODE_VEC_SET_MASK (SXE2_RX_MODE_VEC_SIMPLE | \
SXE2_RX_MODE_VEC_OFFLOAD | SXE2_RX_MODE_VEC_SSE | \
- SXE2_RX_MODE_VEC_AVX512)
+ SXE2_RX_MODE_VEC_AVX2 | SXE2_RX_MODE_VEC_AVX512)
#define SXE2_TX_MODE_VEC_SIMPLE RTE_BIT32(0)
#define SXE2_TX_MODE_VEC_OFFLOAD RTE_BIT32(1)
#define SXE2_TX_MODE_VEC_SSE RTE_BIT32(2)
+#define SXE2_TX_MODE_VEC_AVX2 RTE_BIT32(3)
#define SXE2_TX_MODE_VEC_AVX512 RTE_BIT32(4)
#define SXE2_TX_MODE_SIMPLE_BATCH RTE_BIT32(10)
#define SXE2_TX_MODE_VEC_SET_MASK (SXE2_TX_MODE_VEC_SIMPLE | \
SXE2_TX_MODE_VEC_OFFLOAD | SXE2_TX_MODE_VEC_SSE | \
- SXE2_TX_MODE_VEC_AVX512)
+ SXE2_TX_MODE_VEC_AVX2 | SXE2_TX_MODE_VEC_AVX512)
#define SXE2_TX_VEC_NO_SUPPORT_OFFLOAD ( \
RTE_ETH_TX_OFFLOAD_MULTI_SEGS | \
RTE_ETH_TX_OFFLOAD_QINQ_INSERT | \
@@ -68,6 +70,12 @@ uint16_t sxe2_rx_pkts_scattered_vec_avx512(void *rx_queue,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
uint16_t sxe2_rx_pkts_scattered_vec_avx512_offload(void *rx_queue,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_tx_pkts_vec_avx2_simple(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_tx_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_rx_pkts_scattered_vec_avx2(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_rx_pkts_scattered_vec_avx2_offload(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
#endif
int32_t __rte_cold sxe2_tx_vec_support_check(struct rte_eth_dev *dev, uint32_t *vec_flags);
int32_t __rte_cold sxe2_tx_queues_vec_prepare(struct rte_eth_dev *dev);
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_avx2.c b/drivers/net/sxe2/sxe2_txrx_vec_avx2.c
new file mode 100644
index 0000000000..0618e6d988
--- /dev/null
+++ b/drivers/net/sxe2/sxe2_txrx_vec_avx2.c
@@ -0,0 +1,747 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd.
+ */
+
+#include <rte_vect.h>
+
+#include "sxe2_ethdev.h"
+#include "sxe2_common_log.h"
+#include "sxe2_queue.h"
+#include "sxe2_txrx_vec.h"
+#include "sxe2_txrx_vec_common.h"
+#include "sxe2_vsi.h"
+
+static inline void
+sxe2_tx_desc_fill_one_avx2(volatile union sxe2_tx_data_desc *desc, struct rte_mbuf *pkt,
+ uint64_t desc_cmd, bool with_offloads)
+{
+ __m128i data_desc;
+ uint64_t desc_qw1;
+ uint32_t desc_offset;
+
+ desc_qw1 = (SXE2_TX_DESC_DTYPE_DATA |
+ ((uint64_t)desc_cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT |
+ ((uint64_t)pkt->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+
+ desc_offset = SXE2_TX_DATA_DESC_MACLEN_VAL(pkt->l2_len);
+ desc_qw1 |= ((uint64_t)desc_offset) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkt, &desc_qw1);
+
+ data_desc = _mm_set_epi64x(desc_qw1, rte_pktmbuf_iova(pkt));
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, desc), data_desc);
+}
+
+static __rte_always_inline void
+sxe2_tx_desc_fill_avx2(volatile union sxe2_tx_data_desc *desc, struct rte_mbuf **pkts,
+ uint16_t pkts_num, uint64_t desc_cmd, bool with_offloads)
+{
+ __m256i desc_group0;
+ __m256i desc_group1;
+ uint64_t desc0_qw1;
+ uint64_t desc1_qw1;
+ uint64_t desc2_qw1;
+ uint64_t desc3_qw1;
+
+ const uint64_t desc_qw1_com = (SXE2_TX_DESC_DTYPE_DATA |
+ ((uint64_t)desc_cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT);
+ uint32_t desc_offset[4] = {0};
+
+ if (((uint64_t)desc & 0x1F) != 0 && pkts_num != 0) {
+ sxe2_tx_desc_fill_one_avx2(desc, *pkts, desc_cmd, with_offloads);
+ pkts_num--;
+ desc++;
+ pkts++;
+ }
+
+ while (pkts_num > 3) {
+ desc3_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[3]->data_len)
+ << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+
+ desc_offset[3] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[3]->l2_len);
+ desc3_qw1 |= ((uint64_t)desc_offset[3]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[3], &desc3_qw1);
+
+ desc2_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[2]->data_len)
+ << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset[2] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[2]->l2_len);
+ desc2_qw1 |= ((uint64_t)desc_offset[2]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[2], &desc2_qw1);
+
+ desc1_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[1]->data_len)
+ << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset[1] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[1]->l2_len);
+ desc1_qw1 |= ((uint64_t)desc_offset[1]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[1], &desc1_qw1);
+
+ desc0_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[0]->data_len)
+ << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset[0] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[0]->l2_len);
+ desc0_qw1 |= ((uint64_t)desc_offset[0]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[0], &desc0_qw1);
+
+ desc_group1 = _mm256_set_epi64x(desc3_qw1, rte_pktmbuf_iova(pkts[3]),
+ desc2_qw1, rte_pktmbuf_iova(pkts[2]));
+
+ desc_group0 = _mm256_set_epi64x(desc1_qw1, rte_pktmbuf_iova(pkts[1]),
+ desc0_qw1, rte_pktmbuf_iova(pkts[0]));
+
+ _mm256_store_si256(RTE_CAST_PTR(__m256i *, desc + 2), desc_group1);
+ _mm256_store_si256(RTE_CAST_PTR(__m256i *, desc), desc_group0);
+
+ pkts_num -= 4;
+ desc += 4;
+ pkts += 4;
+ }
+
+ while (pkts_num) {
+ sxe2_tx_desc_fill_one_avx2(desc, *pkts, desc_cmd, with_offloads);
+ pkts_num--;
+ desc++;
+ pkts++;
+ }
+}
+
+static __rte_always_inline uint16_t
+sxe2_tx_pkts_vec_avx2_batch(struct sxe2_tx_queue *txq, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts, bool with_offloads)
+{
+ volatile union sxe2_tx_data_desc *desc;
+ struct sxe2_tx_buffer *buffer;
+ uint16_t next_use;
+ uint16_t res_num;
+ uint16_t tx_num;
+
+ if (txq->desc_free_num < txq->free_thresh)
+ (void)sxe2_tx_bufs_free_vec(txq);
+
+ nb_pkts = RTE_MIN(txq->desc_free_num, nb_pkts);
+ if (unlikely(nb_pkts == 0)) {
+ PMD_LOG_DEBUG(TX, "Tx pkts avx2 batch: may not enough free desc, "
+ "free_desc=%u, need_tx_pkts=%u",
+ txq->desc_free_num, nb_pkts);
+ goto l_end;
+ }
+ tx_num = nb_pkts;
+
+ next_use = txq->next_use;
+ desc = &txq->desc_ring[next_use];
+ buffer = &txq->buffer_ring[next_use];
+
+ txq->desc_free_num -= nb_pkts;
+
+ res_num = txq->ring_depth - txq->next_use;
+
+ if (tx_num >= res_num) {
+ sxe2_tx_pkts_mbuf_fill(buffer, tx_pkts, res_num);
+
+ sxe2_tx_desc_fill_avx2(desc, tx_pkts, res_num,
+ SXE2_TX_DATA_DESC_CMD_EOP, with_offloads);
+ tx_pkts += (res_num - 1);
+ desc += (res_num - 1);
+
+ sxe2_tx_desc_fill_one_avx2(desc, *tx_pkts++,
+ (SXE2_TX_DATA_DESC_CMD_EOP | SXE2_TX_DATA_DESC_CMD_RS),
+ with_offloads);
+
+ tx_num -= res_num;
+
+ next_use = 0;
+ txq->next_rs = txq->rs_thresh - 1;
+ desc = &txq->desc_ring[next_use];
+ buffer = &txq->buffer_ring[next_use];
+ }
+
+ sxe2_tx_pkts_mbuf_fill(buffer, tx_pkts, tx_num);
+
+ sxe2_tx_desc_fill_avx2(desc, tx_pkts, tx_num,
+ SXE2_TX_DATA_DESC_CMD_EOP, with_offloads);
+
+ next_use += tx_num;
+ if (next_use > txq->next_rs) {
+ txq->desc_ring[txq->next_rs].read.type_cmd_off_bsz_l2t |=
+ rte_cpu_to_le_64(SXE2_TX_DATA_DESC_CMD_RS_MASK);
+
+ txq->next_rs += txq->rs_thresh;
+ }
+ txq->next_use = next_use;
+ SXE2_PCI_REG_WRITE_WC(txq->tdt_reg_addr, next_use);
+ PMD_LOG_DEBUG(TX, "port_id=%u queue_id=%u next_use=%u send_pkts=%u",
+ txq->port_id, txq->queue_id, next_use, nb_pkts);
+l_end:
+ return nb_pkts;
+}
+
+static __rte_always_inline uint16_t
+sxe2_tx_pkts_vec_avx2_common(struct sxe2_tx_queue *txq, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts, bool with_offloads)
+{
+ uint16_t tx_done_num = 0;
+ uint16_t tx_once_num;
+ uint16_t tx_need_num;
+
+ while (nb_pkts) {
+ tx_need_num = RTE_MIN(nb_pkts, txq->rs_thresh);
+ tx_once_num = sxe2_tx_pkts_vec_avx2_batch(txq,
+ tx_pkts + tx_done_num, tx_need_num, with_offloads);
+
+ nb_pkts -= tx_once_num;
+ tx_done_num += tx_once_num;
+
+ if (tx_once_num < tx_need_num)
+ break;
+ }
+ return tx_done_num;
+}
+
+uint16_t sxe2_tx_pkts_vec_avx2_simple(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_tx_pkts_vec_avx2_common(tx_queue, tx_pkts, nb_pkts, false);
+}
+
+uint16_t sxe2_tx_pkts_vec_avx2(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_tx_pkts_vec_avx2_common(tx_queue, tx_pkts, nb_pkts, true);
+}
+
+static inline void sxe2_rx_queue_rearm_avx2(struct sxe2_rx_queue *rxq)
+{
+ volatile union sxe2_rx_desc *desc;
+ struct rte_mbuf **buffer;
+ struct rte_mbuf *mbuf0, *mbuf1;
+ __m128i dma_addr0, dma_addr1;
+ __m128i virt_addr0, virt_addr1;
+ __m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM, RTE_PKTMBUF_HEADROOM);
+ int32_t ret;
+ uint16_t i;
+ uint16_t new_tail;
+
+ buffer = &rxq->buffer_ring[rxq->realloc_start];
+ desc = &rxq->desc_ring[rxq->realloc_start];
+
+ ret = rte_mempool_get_bulk(rxq->mb_pool, (void *)buffer, SXE2_RX_REARM_THRESH_VEC);
+ if (ret != 0) {
+ if ((rxq->realloc_num + SXE2_RX_REARM_THRESH_VEC) >= rxq->ring_depth) {
+ dma_addr0 = _mm_setzero_si128();
+ for (i = 0; i < SXE2_RX_NUM_PER_LOOP_AVX; ++i) {
+ buffer[i] = &rxq->fake_mbuf;
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc[i].read), dma_addr0);
+ }
+ }
+
+ rxq->vsi->adapter->dev_info.dev_data->rx_mbuf_alloc_failed +=
+ SXE2_RX_REARM_THRESH_VEC;
+ return;
+ }
+
+ for (i = 0; i < SXE2_RX_REARM_THRESH_VEC; i += 2, buffer += 2) {
+ mbuf0 = buffer[0];
+ mbuf1 = buffer[1];
+#if RTE_IOVA_IN_MBUF
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+ offsetof(struct rte_mbuf, buf_addr) + 8);
+#endif
+ virt_addr0 = _mm_loadu_si128((__m128i *)&mbuf0->buf_addr);
+ virt_addr1 = _mm_loadu_si128((__m128i *)&mbuf1->buf_addr);
+
+#if RTE_IOVA_IN_MBUF
+
+ dma_addr0 = _mm_unpackhi_epi64(virt_addr0, virt_addr0);
+ dma_addr1 = _mm_unpackhi_epi64(virt_addr1, virt_addr1);
+#else
+
+ dma_addr0 = _mm_unpacklo_epi64(virt_addr0, virt_addr0);
+ dma_addr1 = _mm_unpacklo_epi64(virt_addr1, virt_addr1);
+#endif
+
+ dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+ dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
+
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc++->read), dma_addr0);
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc++->read), dma_addr1);
+ }
+
+ rxq->realloc_start += SXE2_RX_REARM_THRESH_VEC;
+ if (rxq->realloc_start >= rxq->ring_depth)
+ rxq->realloc_start = 0;
+ rxq->realloc_num -= SXE2_RX_REARM_THRESH_VEC;
+
+ new_tail = (rxq->realloc_start == 0) ?
+ (rxq->ring_depth - 1) : (rxq->realloc_start - 1);
+ SXE2_PCI_REG_WRITE_WC(rxq->rdt_reg_addr, new_tail);
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_common_vec_avx2(struct sxe2_rx_queue *rxq,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts, uint8_t *split_rxe_flags,
+ uint8_t *umbcast_flags, bool do_offload)
+{
+ const __m256i mbuf_init = _mm256_set_epi64x(0, 0, 0, rxq->mbuf_init_value);
+ struct rte_mbuf **buffer;
+ volatile union sxe2_rx_desc *desc;
+ __m256i mbufs6_7, mbufs4_5, mbufs2_3, mbufs0_1;
+ uint32_t bit_num;
+ uint16_t done_num;
+ uint16_t i = 0;
+ uint16_t j = 0;
+
+ buffer = &rxq->buffer_ring[rxq->processing_idx];
+ desc = &rxq->desc_ring[rxq->processing_idx];
+ done_num = 0;
+
+ rte_prefetch0(desc);
+
+ nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, SXE2_RX_NUM_PER_LOOP_AVX);
+
+ if (rxq->realloc_num > SXE2_RX_REARM_THRESH_VEC)
+ sxe2_rx_queue_rearm_avx2(rxq);
+
+ if (0 == (rte_le_to_cpu_64(desc->wb.status_err_ptype_len) &
+ SXE2_RX_DESC_STATUS_DD_MASK))
+ goto l_end;
+
+ const __m256i crc_adjust =
+ _mm256_set_epi16(0, 0, 0, -rxq->crc_len,
+ 0, -rxq->crc_len, 0,
+ 0, 0, 0, 0,
+ -rxq->crc_len, 0, -rxq->crc_len, 0, 0);
+
+ const __m256i dd_mask = _mm256_set1_epi32(1);
+ const __m256i rvp_shuf_mask =
+ _mm256_set_epi8(7, 6, 5, 4,
+ 3, 2, 13, 12,
+ 0xFF, 0xFF, 13, 12,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 7, 6, 5, 4,
+ 3, 2, 13, 12,
+ 0xFF, 0xFF, 13, 12,
+ 0xFF, 0xFF, 0xFF, 0xFF);
+
+ const __m128i eop_shuf_mask =
+ _mm_set_epi8(0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 0xFF, 0xFF,
+ 8, 0, 10, 2,
+ 12, 4, 14, 6);
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);
+
+ for (i = 0; i < nb_pkts; i += SXE2_RX_NUM_PER_LOOP_AVX,
+ desc += SXE2_RX_NUM_PER_LOOP_AVX) {
+ _mm256_storeu_si256((void *)&rx_pkts[i],
+ _mm256_loadu_si256((void *)&buffer[i]));
+#ifdef RTE_ARCH_X86_64
+ _mm256_storeu_si256((void *)&rx_pkts[i + 4],
+ _mm256_loadu_si256((void *)&buffer[i + 4]));
+#endif
+
+ const __m128i desc7 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 7));
+ rte_compiler_barrier();
+ const __m128i desc6 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 6));
+ rte_compiler_barrier();
+ const __m128i desc5 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 5));
+ rte_compiler_barrier();
+ const __m128i desc4 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 4));
+ rte_compiler_barrier();
+ const __m128i desc3 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 3));
+ rte_compiler_barrier();
+ const __m128i desc2 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 2));
+ rte_compiler_barrier();
+ const __m128i desc1 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 1));
+ rte_compiler_barrier();
+ const __m128i desc0 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 0));
+
+ const __m256i descs6_7 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc6), desc7, 1);
+ const __m256i descs4_5 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc4), desc5, 1);
+ const __m256i descs2_3 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc2), desc3, 1);
+ const __m256i descs0_1 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc0), desc1, 1);
+
+ if (split_rxe_flags) {
+ for (j = 0; j < SXE2_RX_NUM_PER_LOOP_AVX; j++)
+ rte_mbuf_prefetch_part2(rx_pkts[i + j]);
+ }
+
+ mbufs6_7 = _mm256_shuffle_epi8(descs6_7, rvp_shuf_mask);
+ mbufs4_5 = _mm256_shuffle_epi8(descs4_5, rvp_shuf_mask);
+
+ mbufs6_7 = _mm256_add_epi16(mbufs6_7, crc_adjust);
+ mbufs4_5 = _mm256_add_epi16(mbufs4_5, crc_adjust);
+
+ const __m256i ptype_mask = _mm256_set1_epi32(SXE2_RX_DESC_PTYPE_MASK);
+
+ const __m256i staterrs4_7 = _mm256_unpackhi_epi32(descs6_7, descs4_5);
+
+ __m256i ptypes4_7 = _mm256_and_si256(staterrs4_7, ptype_mask);
+
+ const uint16_t ptype7 = _mm256_extract_epi16(ptypes4_7, 9);
+ const uint16_t ptype6 = _mm256_extract_epi16(ptypes4_7, 1);
+ const uint16_t ptype5 = _mm256_extract_epi16(ptypes4_7, 11);
+ const uint16_t ptype4 = _mm256_extract_epi16(ptypes4_7, 3);
+
+ mbufs6_7 = _mm256_insert_epi32(mbufs6_7, sxe2_ptype_tbl[ptype7], 4);
+ mbufs6_7 = _mm256_insert_epi32(mbufs6_7, sxe2_ptype_tbl[ptype6], 0);
+ mbufs4_5 = _mm256_insert_epi32(mbufs4_5, sxe2_ptype_tbl[ptype5], 4);
+ mbufs4_5 = _mm256_insert_epi32(mbufs4_5, sxe2_ptype_tbl[ptype4], 0);
+
+ mbufs2_3 = _mm256_shuffle_epi8(descs2_3, rvp_shuf_mask);
+ mbufs0_1 = _mm256_shuffle_epi8(descs0_1, rvp_shuf_mask);
+
+ mbufs2_3 = _mm256_add_epi16(mbufs2_3, crc_adjust);
+ mbufs0_1 = _mm256_add_epi16(mbufs0_1, crc_adjust);
+
+ const __m256i staterrs0_3 = _mm256_unpackhi_epi32(descs2_3, descs0_1);
+
+ __m256i ptypes0_3 = _mm256_and_si256(staterrs0_3, ptype_mask);
+
+ const uint16_t ptype3 = _mm256_extract_epi16(ptypes0_3, 9);
+ const uint16_t ptype2 = _mm256_extract_epi16(ptypes0_3, 1);
+ const uint16_t ptype1 = _mm256_extract_epi16(ptypes0_3, 11);
+ const uint16_t ptype0 = _mm256_extract_epi16(ptypes0_3, 3);
+
+ mbufs2_3 = _mm256_insert_epi32(mbufs2_3, sxe2_ptype_tbl[ptype3], 4);
+ mbufs2_3 = _mm256_insert_epi32(mbufs2_3, sxe2_ptype_tbl[ptype2], 0);
+ mbufs0_1 = _mm256_insert_epi32(mbufs0_1, sxe2_ptype_tbl[ptype1], 4);
+ mbufs0_1 = _mm256_insert_epi32(mbufs0_1, sxe2_ptype_tbl[ptype0], 0);
+
+ __m256i staterrs0_7 = _mm256_unpacklo_epi64(staterrs4_7, staterrs0_3);
+
+ __m256i stu_len0_7 = _mm256_unpackhi_epi64(staterrs4_7, staterrs0_3);
+ __m256i mbuf_flags = _mm256_setzero_si256();
+
+ if (do_offload) {
+ const __m256i desc_flags_mask = _mm256_set1_epi32(0x00001C04);
+ const __m256i desc_flags_rss_mask = _mm256_set1_epi32(0x20000000);
+ const __m256i vlan_flags =
+ _mm256_set_epi8
+ (0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0,
+ RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0,
+ RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED,
+ 0, 0, 0, 0);
+
+ const __m256i rss_flags =
+ _mm256_set_epi8
+ (0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_RSS_HASH, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_RSS_HASH, 0, 0, 0, 0);
+
+ const __m256i cksum_flags =
+ _mm256_set_epi8
+ (0, 0, 0, 0, 0, 0, 0, 0,
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD |
+ RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1));
+
+ const __m256i cksum_mask =
+ _mm256_set1_epi32
+ (RTE_MBUF_F_RX_IP_CKSUM_MASK |
+ RTE_MBUF_F_RX_L4_CKSUM_MASK |
+ RTE_MBUF_F_RX_OUTER_L4_CKSUM_MASK |
+ RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD);
+ const __m256i vlan_mask =
+ _mm256_set1_epi32
+ (RTE_MBUF_F_RX_VLAN | RTE_MBUF_F_RX_VLAN_STRIPPED);
+
+ __m256i tmp_flags;
+ __m256i descs_flags = _mm256_and_si256(staterrs0_7, desc_flags_mask);
+ stu_len0_7 = _mm256_and_si256(stu_len0_7, desc_flags_rss_mask);
+
+ tmp_flags = _mm256_shuffle_epi8(vlan_flags, descs_flags);
+ mbuf_flags = _mm256_and_si256(tmp_flags, vlan_mask);
+
+ descs_flags = _mm256_srli_epi32(descs_flags, 10);
+ tmp_flags = _mm256_shuffle_epi8(cksum_flags, descs_flags);
+ tmp_flags = _mm256_slli_epi32(tmp_flags, 1);
+ tmp_flags = _mm256_and_si256(tmp_flags, cksum_mask);
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+ descs_flags = _mm256_srli_epi32(stu_len0_7, 27);
+ tmp_flags = _mm256_shuffle_epi8(rss_flags, descs_flags);
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+#ifndef RTE_LIBRTE_SXE2_16BYTE_RX_DESC
+
+ if (rxq->fnav_enable) {
+ __m256i fnav_vld0_3, fnav_vld4_7;
+ __m256i fnav_vld0_7;
+ __m256i v_zeros, v_ffff, v_u32_one;
+ const __m256i fdir_flags =
+ _mm256_set1_epi32
+ (RTE_MBUF_F_RX_FDIR | RTE_MBUF_F_RX_FDIR_ID);
+ fnav_vld0_3 = _mm256_unpacklo_epi32(descs2_3, descs0_1);
+ fnav_vld4_7 = _mm256_unpacklo_epi32(descs6_7, descs4_5);
+
+ fnav_vld0_7 = _mm256_unpacklo_epi64(fnav_vld4_7, fnav_vld0_3);
+
+ fnav_vld0_7 = _mm256_slli_epi32(fnav_vld0_7, 26);
+ fnav_vld0_7 = _mm256_srli_epi32(fnav_vld0_7, 31);
+
+ v_zeros = _mm256_setzero_si256();
+ v_ffff = _mm256_cmpeq_epi32(v_zeros, v_zeros);
+ v_u32_one = _mm256_srli_epi32(v_ffff, 31);
+
+ tmp_flags = _mm256_cmpeq_epi32(fnav_vld0_7, v_u32_one);
+
+ tmp_flags = _mm256_and_si256(tmp_flags, fdir_flags);
+
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+ rx_pkts[i + 0]->hash.fdir.hi = desc[0].wb.fd_filter_id;
+ rx_pkts[i + 1]->hash.fdir.hi = desc[1].wb.fd_filter_id;
+ rx_pkts[i + 2]->hash.fdir.hi = desc[2].wb.fd_filter_id;
+ rx_pkts[i + 3]->hash.fdir.hi = desc[3].wb.fd_filter_id;
+ rx_pkts[i + 4]->hash.fdir.hi = desc[4].wb.fd_filter_id;
+ rx_pkts[i + 5]->hash.fdir.hi = desc[5].wb.fd_filter_id;
+ rx_pkts[i + 6]->hash.fdir.hi = desc[6].wb.fd_filter_id;
+ rx_pkts[i + 7]->hash.fdir.hi = desc[7].wb.fd_filter_id;
+ }
+#endif
+ }
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+ offsetof(struct rte_mbuf, rearm_data) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rx_descriptor_fields1) !=
+ offsetof(struct rte_mbuf, rearm_data) + 16);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
+ RTE_ALIGN(offsetof(struct rte_mbuf, rearm_data), 16));
+
+ __m256i rearm_arr[8];
+
+ rearm_arr[6] = _mm256_blend_epi32(mbuf_init, _mm256_slli_si256(mbuf_flags, 8), 4);
+ rearm_arr[4] = _mm256_blend_epi32(mbuf_init, _mm256_slli_si256(mbuf_flags, 4), 4);
+ rearm_arr[2] = _mm256_blend_epi32(mbuf_init, mbuf_flags, 4);
+ rearm_arr[0] = _mm256_blend_epi32(mbuf_init, _mm256_srli_si256(mbuf_flags, 4), 4);
+
+ rearm_arr[6] = _mm256_permute2f128_si256(rearm_arr[6], mbufs6_7, 0x20);
+ rearm_arr[4] = _mm256_permute2f128_si256(rearm_arr[4], mbufs4_5, 0x20);
+ rearm_arr[2] = _mm256_permute2f128_si256(rearm_arr[2], mbufs2_3, 0x20);
+ rearm_arr[0] = _mm256_permute2f128_si256(rearm_arr[0], mbufs0_1, 0x20);
+
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 6]->rearm_data, rearm_arr[6]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 4]->rearm_data, rearm_arr[4]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 2]->rearm_data, rearm_arr[2]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 0]->rearm_data, rearm_arr[0]);
+
+ const __m256i tmp_mbuf_flags =
+ _mm256_castsi128_si256(_mm256_extracti128_si256(mbuf_flags, 1));
+
+ rearm_arr[7] =
+ _mm256_blend_epi32(mbuf_init, _mm256_slli_si256(tmp_mbuf_flags, 8), 4);
+ rearm_arr[5] =
+ _mm256_blend_epi32(mbuf_init, _mm256_slli_si256(tmp_mbuf_flags, 4), 4);
+ rearm_arr[3] =
+ _mm256_blend_epi32(mbuf_init, tmp_mbuf_flags, 4);
+ rearm_arr[1] =
+ _mm256_blend_epi32(mbuf_init, _mm256_srli_si256(tmp_mbuf_flags, 4), 4);
+
+ rearm_arr[7] = _mm256_blend_epi32(rearm_arr[7], mbufs6_7, 0XF0);
+ rearm_arr[5] = _mm256_blend_epi32(rearm_arr[5], mbufs4_5, 0XF0);
+ rearm_arr[3] = _mm256_blend_epi32(rearm_arr[3], mbufs2_3, 0XF0);
+ rearm_arr[1] = _mm256_blend_epi32(rearm_arr[1], mbufs0_1, 0XF0);
+
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 7]->rearm_data, rearm_arr[7]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 5]->rearm_data, rearm_arr[5]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 3]->rearm_data, rearm_arr[3]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 1]->rearm_data, rearm_arr[1]);
+
+ if (umbcast_flags != NULL) {
+ const __m256i umbcast_mask =
+ _mm256_set1_epi32(SXE2_RX_DESC_STATUS_UMBCAST_MASK);
+ __m256i umbcast_bits_256 = _mm256_and_si256(staterrs0_7,
+ umbcast_mask);
+
+ umbcast_bits_256 = _mm256_srli_epi32(umbcast_bits_256, 24);
+
+ __m128i umbcast_bits_128 = _mm_packs_epi32
+ (_mm256_castsi256_si128(umbcast_bits_256),
+ _mm256_extractf128_si256
+ (umbcast_bits_256, 1));
+
+ umbcast_bits_128 = _mm_shuffle_epi8(umbcast_bits_128, eop_shuf_mask);
+
+ *(uint64_t *)umbcast_flags = _mm_cvtsi128_si64(umbcast_bits_128);
+ umbcast_flags += SXE2_RX_NUM_PER_LOOP_AVX;
+ }
+
+ if (split_rxe_flags != NULL) {
+ const __m256i eop_rxe_mask = _mm256_set1_epi32
+ (SXE2_RX_DESC_STATUS_EOP_MASK |
+ SXE2_RX_DESC_ERROR_RXE_MASK |
+ SXE2_RX_DESC_ERROR_OVERSIZE_MASK);
+
+ const __m128i eop_mask_128 = _mm_set1_epi16(SXE2_RX_DESC_STATUS_EOP_MASK);
+ const __m128i rxe_mask_128 = _mm_set1_epi16(SXE2_RX_DESC_ERROR_RXE_MASK |
+ SXE2_RX_DESC_ERROR_OVERSIZE_MASK);
+
+ const __m256i tmp_stats = _mm256_and_si256(staterrs0_7, eop_rxe_mask);
+
+ const __m128i eop_rxe_bits = _mm_packs_epi32
+ (_mm256_castsi256_si128(tmp_stats),
+ _mm256_extractf128_si256(tmp_stats, 1));
+
+ __m128i not_eop_bits = _mm_andnot_si128(eop_rxe_bits, eop_mask_128);
+
+ not_eop_bits = _mm_or_si128
+ (not_eop_bits,
+ _mm_srli_epi16
+ (_mm_and_si128(eop_rxe_bits, rxe_mask_128),
+ 7));
+
+ not_eop_bits = _mm_shuffle_epi8(not_eop_bits, eop_shuf_mask);
+
+ *(uint64_t *)split_rxe_flags = _mm_cvtsi128_si64(not_eop_bits);
+ split_rxe_flags += SXE2_RX_NUM_PER_LOOP_AVX;
+ }
+
+ staterrs0_7 = _mm256_and_si256(staterrs0_7, dd_mask);
+
+ staterrs0_7 = _mm256_packs_epi32(staterrs0_7, _mm256_setzero_si256());
+ bit_num = rte_popcount64
+ (_mm_cvtsi128_si64(_mm256_extracti128_si256(staterrs0_7, 1)));
+ bit_num += rte_popcount64
+ (_mm_cvtsi128_si64(_mm256_castsi256_si128(staterrs0_7)));
+
+ done_num += bit_num;
+
+ if (bit_num != SXE2_RX_NUM_PER_LOOP_AVX)
+ break;
+ }
+
+ rxq->processing_idx += done_num;
+ rxq->processing_idx &= (rxq->ring_depth - 1);
+ if ((1 == (rxq->processing_idx & 1)) && done_num > 1) {
+ rxq->processing_idx--;
+ done_num--;
+ }
+ rxq->realloc_num += done_num;
+
+l_end:
+ PMD_LOG_DEBUG(RX, "port_id=%u queue_id=%u last_id=%u recv_pkts=%d",
+ rxq->port_id, rxq->queue_id, rxq->processing_idx, done_num);
+ return done_num;
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_scattered_batch_vec_avx2(struct sxe2_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, bool do_offload)
+{
+ uint8_t split_rxe_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
+ uint8_t umbcast_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
+ uint16_t rx_done_num;
+ uint16_t rx_pkt_done_num;
+
+ rx_pkt_done_num = 0;
+
+ rx_done_num = sxe2_rx_pkts_common_vec_avx2(rxq, rx_pkts, nb_pkts,
+ split_rxe_flags, umbcast_flags, do_offload);
+ if (rx_done_num == 0)
+ goto l_end;
+
+ rx_pkt_done_num += sxe2_rx_pkts_refactor(rxq, &rx_pkts[rx_pkt_done_num],
+ rx_done_num - rx_pkt_done_num, &split_rxe_flags[rx_pkt_done_num],
+ &umbcast_flags[rx_pkt_done_num]);
+
+l_end:
+ return rx_pkt_done_num;
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_scattered_common_vec_avx2(struct sxe2_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, bool do_offload)
+{
+ uint16_t done_num = 0;
+ uint16_t once_num;
+
+ while (nb_pkts > SXE2_RX_PKTS_BURST_BATCH_NUM) {
+ once_num =
+ sxe2_rx_pkts_scattered_batch_vec_avx2(rxq,
+ rx_pkts + done_num,
+ SXE2_RX_PKTS_BURST_BATCH_NUM,
+ do_offload);
+ done_num += once_num;
+ nb_pkts -= once_num;
+ if (once_num < SXE2_RX_PKTS_BURST_BATCH_NUM)
+ goto l_end;
+ }
+
+ done_num += sxe2_rx_pkts_scattered_batch_vec_avx2(rxq,
+ rx_pkts + done_num, nb_pkts, do_offload);
+l_end:
+ return done_num;
+}
+
+uint16_t sxe2_rx_pkts_scattered_vec_avx2(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_rx_pkts_scattered_common_vec_avx2(rx_queue,
+ rx_pkts, nb_pkts, false);
+}
+
+uint16_t sxe2_rx_pkts_scattered_vec_avx2_offload(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_rx_pkts_scattered_common_vec_avx2(rx_queue,
+ rx_pkts, nb_pkts, true);
+}
--
2.52.0
^ permalink raw reply related
* [PATCH v5 03/23] net/sxe2: support AVX512 vectorized path for Rx and Tx
From: liujie5 @ 2026-06-22 9:24 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260622092324.3091185-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
Add AVX512 vector data path for Rx and Tx burst functions.
The decision to use AVX512 is based on:
1. CPU hardware flags (AVX512F, AVX512BW).
2. Compiler support (CC_AVX512_SUPPORT).
3. Max SIMD bitwidth configuration.
Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
---
drivers/net/sxe2/meson.build | 24 +
drivers/net/sxe2/sxe2_drv_cmd.h | 80 +--
drivers/net/sxe2/sxe2_txrx.c | 92 ++-
drivers/net/sxe2/sxe2_txrx_vec.c | 46 +-
drivers/net/sxe2/sxe2_txrx_vec.h | 18 +-
drivers/net/sxe2/sxe2_txrx_vec_avx512.c | 867 ++++++++++++++++++++++++
6 files changed, 1068 insertions(+), 59 deletions(-)
create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx512.c
diff --git a/drivers/net/sxe2/meson.build b/drivers/net/sxe2/meson.build
index 6b2eb75b0e..7bd0d8120c 100644
--- a/drivers/net/sxe2/meson.build
+++ b/drivers/net/sxe2/meson.build
@@ -15,6 +15,30 @@ includes += include_directories('../../common/sxe2')
if arch_subdir == 'x86'
sources += files('sxe2_txrx_vec_sse.c')
+
+ sxe2_avx512_cpu_support =(
+ cc.get_define('__AVX512F__', args: machine_args) != '' and
+ cc.get_define('__AVX512BW__', args: machine_args) != '')
+
+ sxe2_avx512_cc_support = (
+ not machine_args.contains('-mno-avx512f') and
+ cc.has_argument('-mavx512f') and
+ cc.has_argument('-mavx512bw'))
+
+ if sxe2_avx512_cpu_support == true or sxe2_avx512_cc_support == true
+ cflags += ['-DCC_AVX512_SUPPORT']
+ avx512_args = [cflags, '-mavx512f', '-mavx512bw']
+ if cc.has_argument('-march=skylake-avx512')
+ avx512_args += '-march=skylake-avx512'
+ endif
+ sxe2_avx512_lib = static_library('sxe2_avx512_lib', 'sxe2_txrx_vec_avx512.c',
+ dependencies: [static_rte_ethdev,
+ static_rte_kvargs, static_rte_hash,
+ static_rte_security, static_rte_cryptodev, static_rte_bus_pci],
+ include_directories: includes,
+ c_args: avx512_args)
+ objs += sxe2_avx512_lib.extract_objects('sxe2_txrx_vec_avx512.c')
+ endif
endif
sources += files(
diff --git a/drivers/net/sxe2/sxe2_drv_cmd.h b/drivers/net/sxe2/sxe2_drv_cmd.h
index bba6476c2e..ccc9c20ef4 100644
--- a/drivers/net/sxe2/sxe2_drv_cmd.h
+++ b/drivers/net/sxe2/sxe2_drv_cmd.h
@@ -67,20 +67,20 @@ enum sxe2_dev_type {
SXE2_DEV_T_MAX,
};
-struct sxe2_drv_queue_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_queue_caps {
uint16_t queues_cnt;
uint16_t base_idx_in_pf;
-};
+} __rte_packed_end;
-struct sxe2_drv_msix_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_msix_caps {
uint16_t msix_vectors_cnt;
uint16_t base_idx_in_func;
-};
+} __rte_packed_end;
-struct sxe2_drv_rss_hash_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_rss_hash_caps {
uint16_t hash_key_size;
uint16_t lut_key_size;
-};
+} __rte_packed_end;
enum sxe2_vf_vsi_valid {
SXE2_VF_VSI_BOTH = 0,
@@ -89,18 +89,18 @@ enum sxe2_vf_vsi_valid {
SXE2_VF_VSI_MAX,
};
-struct sxe2_drv_vsi_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_caps {
uint16_t func_id;
uint16_t dpdk_vsi_id;
uint16_t kernel_vsi_id;
uint16_t vsi_type;
-};
+} __rte_packed_end;
-struct sxe2_drv_representor_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_representor_caps {
uint16_t cnt_repr_vf;
uint8_t rsv[2];
struct sxe2_drv_vsi_caps repr_vf_id[256];
-};
+} __rte_packed_end;
enum sxe2_phys_port_name_type {
SXE2_PHYS_PORT_NAME_TYPE_NOTSET = 0,
@@ -111,25 +111,25 @@ enum sxe2_phys_port_name_type {
SXE2_PHYS_PORT_NAME_TYPE_UNKNOWN,
};
-struct sxe2_switchdev_mode_info {
+struct __rte_aligned(4) __rte_packed_begin sxe2_switchdev_mode_info {
uint8_t pf_id;
uint8_t is_switchdev;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_switchdev_cpvsi_info {
+struct __rte_aligned(4) __rte_packed_begin sxe2_switchdev_cpvsi_info {
uint16_t cp_vsi_id;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_txsch_caps {
+struct __rte_aligned(4) __rte_packed_begin sxe2_txsch_caps {
uint8_t layer_cap;
uint8_t tm_mid_node_num;
uint8_t prio_num;
uint8_t rev;
-};
+} __rte_packed_end;
-struct sxe2_drv_dev_caps_resp {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_dev_caps_resp {
struct sxe2_drv_queue_caps queue_caps;
struct sxe2_drv_msix_caps msix_caps;
struct sxe2_drv_rss_hash_caps rss_hash_caps;
@@ -141,24 +141,24 @@ struct sxe2_drv_dev_caps_resp {
uint8_t dev_type;
uint8_t rev;
uint32_t cap_flags;
-};
+} __rte_packed_end;
-struct sxe2_drv_dev_info_resp {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_dev_info_resp {
uint64_t dsn;
uint16_t vsi_id;
uint8_t rsv[2];
uint8_t mac_addr[SXE2_ETH_ALEN];
uint8_t rsv2[2];
-};
+} __rte_packed_end;
-struct sxe2_drv_dev_fw_info_resp {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_dev_fw_info_resp {
uint8_t main_version_id;
uint8_t sub_version_id;
uint8_t fix_version_id;
uint8_t build_id;
-};
+} __rte_packed_end;
-struct sxe2_drv_rxq_ctxt {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_rxq_ctxt {
uint64_t dma_addr;
uint32_t max_lro_size;
uint32_t split_type_mask;
@@ -170,62 +170,62 @@ struct sxe2_drv_rxq_ctxt {
uint8_t keep_crc_en;
uint8_t split_en;
uint8_t desc_size;
-};
+} __rte_packed_end;
-struct sxe2_drv_rxq_cfg_req {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_rxq_cfg_req {
uint16_t q_cnt;
uint16_t vsi_id;
uint16_t max_frame_size;
uint8_t rsv[2];
struct sxe2_drv_rxq_ctxt cfg[];
-};
+} __rte_packed_end;
-struct sxe2_drv_txq_ctxt {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_txq_ctxt {
uint64_t dma_addr;
uint32_t sched_mode;
uint16_t queue_id;
uint16_t depth;
uint16_t vsi_id;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_drv_txq_cfg_req {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_txq_cfg_req {
uint16_t q_cnt;
uint16_t vsi_id;
struct sxe2_drv_txq_ctxt cfg[];
-};
+} __rte_packed_end;
-struct sxe2_drv_q_switch_req {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_q_switch_req {
uint16_t q_idx;
uint16_t vsi_id;
uint8_t is_enable;
uint8_t sched_mode;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_drv_vsi_create_req_resp {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_create_req_resp {
uint16_t vsi_id;
uint16_t vsi_type;
struct sxe2_drv_queue_caps used_queues;
struct sxe2_drv_msix_caps used_msix;
-};
+} __rte_packed_end;
-struct sxe2_drv_vsi_free_req {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_free_req {
uint16_t vsi_id;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_drv_vsi_info_get_req {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_info_get_req {
uint16_t vsi_id;
uint8_t rsv[2];
-};
+} __rte_packed_end;
-struct sxe2_drv_vsi_info_get_resp {
+struct __rte_aligned(4) __rte_packed_begin sxe2_drv_vsi_info_get_resp {
uint16_t vsi_id;
uint16_t vsi_type;
struct sxe2_drv_queue_caps used_queues;
struct sxe2_drv_msix_caps used_msix;
-};
+} __rte_packed_end;
enum sxe2_drv_cmd_module {
SXE2_DRV_CMD_MODULE_HANDSHAKE = 0,
diff --git a/drivers/net/sxe2/sxe2_txrx.c b/drivers/net/sxe2/sxe2_txrx.c
index fe4b79352d..14179b87a4 100644
--- a/drivers/net/sxe2/sxe2_txrx.c
+++ b/drivers/net/sxe2/sxe2_txrx.c
@@ -157,6 +157,19 @@ void sxe2_tx_mode_func_set(struct rte_eth_dev *dev)
if (ret == 0 &&
rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128) {
tx_mode_flags = vec_flags;
+#ifdef RTE_ARCH_X86
+ if ((rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512) &&
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1) &&
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) == 1)) {
+#ifdef CC_AVX512_SUPPORT
+ tx_mode_flags |= SXE2_TX_MODE_VEC_AVX512;
+#else
+ PMD_LOG_INFO(TX, "AVX512 is not supported in build env.");
+#endif
+ }
+ if ((tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) == 0)
+ tx_mode_flags |= SXE2_TX_MODE_VEC_SSE;
+#endif
if (tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) {
ret = sxe2_tx_queues_vec_prepare(dev);
if (ret != 0)
@@ -172,14 +185,25 @@ void sxe2_tx_mode_func_set(struct rte_eth_dev *dev)
tx_mode_flags = adapter->q_ctxt.tx_mode_flags;
}
-#ifdef RTE_ARCH_X86
if (tx_mode_flags & SXE2_TX_MODE_VEC_SET_MASK) {
- if (tx_mode_flags & SXE2_TX_MODE_VEC_OFFLOAD) {
- dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
- dev->tx_pkt_burst = sxe2_tx_pkts_vec_sse;
+ dev->tx_pkt_prepare = NULL;
+#ifdef RTE_ARCH_X86
+ if (tx_mode_flags & SXE2_TX_MODE_VEC_AVX512) {
+#ifdef CC_AVX512_SUPPORT
+ if (tx_mode_flags & SXE2_TX_MODE_VEC_OFFLOAD) {
+ dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_avx512;
+ } else {
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_avx512_simple;
+ }
+#endif
} else {
- dev->tx_pkt_prepare = NULL;
- dev->tx_pkt_burst = sxe2_tx_pkts_vec_sse_simple;
+ if (tx_mode_flags & SXE2_TX_MODE_VEC_OFFLOAD) {
+ dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_sse;
+ } else {
+ dev->tx_pkt_burst = sxe2_tx_pkts_vec_sse_simple;
+ }
}
} else {
#endif
@@ -201,8 +225,16 @@ static const struct {
} sxe2_tx_burst_infos[] = {
{ sxe2_tx_pkts, "Scalar" },
#ifdef RTE_ARCH_X86
- { sxe2_tx_pkts_vec_sse, "Vector SSE" },
- { sxe2_tx_pkts_vec_sse_simple, "Vector SSE Simple" },
+#ifdef CC_AVX512_SUPPORT
+ { sxe2_tx_pkts_vec_avx512,
+ "Vector AVX512" },
+ { sxe2_tx_pkts_vec_avx512_simple,
+ "Vector AVX512 Simple" },
+#endif
+ { sxe2_tx_pkts_vec_sse,
+ "Vector SSE" },
+ { sxe2_tx_pkts_vec_sse_simple,
+ "Vector SSE Simple" },
#endif
};
@@ -288,6 +320,20 @@ void sxe2_rx_mode_func_set(struct rte_eth_dev *dev)
if (ret == 0 &&
rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128) {
rx_mode_flags = vec_flags;
+#ifdef RTE_ARCH_X86
+ if ((rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512) &&
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) == 1) &&
+ (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW) == 1)) {
+#ifdef CC_AVX512_SUPPORT
+ rx_mode_flags |= SXE2_RX_MODE_VEC_AVX512;
+#else
+ PMD_LOG_INFO(RX, "AVX512 support detected but not enabled");
+#endif
+ }
+ if ((rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) == 0 &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+ rx_mode_flags |= SXE2_RX_MODE_VEC_SSE;
+#endif
if ((rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) != 0) {
ret = sxe2_rx_queues_vec_prepare(dev);
if (ret != 0)
@@ -301,7 +347,16 @@ void sxe2_rx_mode_func_set(struct rte_eth_dev *dev)
#ifdef RTE_ARCH_X86
if (rx_mode_flags & SXE2_RX_MODE_VEC_SET_MASK) {
- dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_sse_offload;
+ if (rx_mode_flags & SXE2_RX_MODE_VEC_AVX512) {
+#ifdef CC_AVX512_SUPPORT
+ if (rx_mode_flags & SXE2_RX_MODE_VEC_OFFLOAD)
+ dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_avx512_offload;
+ else
+ dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_avx512;
+#endif
+ } else {
+ dev->rx_pkt_burst = sxe2_rx_pkts_scattered_vec_sse_offload;
+ }
return;
}
#endif
@@ -315,19 +370,30 @@ static const struct {
eth_rx_burst_t rx_burst;
const char *info;
} sxe2_rx_burst_infos[] = {
- { sxe2_rx_pkts_scattered, "Scalar Scattered" },
- { sxe2_rx_pkts_scattered_split, "Scalar Scattered split" },
+ { sxe2_rx_pkts_scattered,
+ "Scalar Scattered" },
+ { sxe2_rx_pkts_scattered_split,
+ "Scalar Scattered split" },
#ifdef RTE_ARCH_X86
- { sxe2_rx_pkts_scattered_vec_sse_offload, "Vector SSE Scattered" },
+#ifdef CC_AVX512_SUPPORT
+ { sxe2_rx_pkts_scattered_vec_avx512,
+ "Vector AVX512 Scattered" },
+ { sxe2_rx_pkts_scattered_vec_avx512_offload,
+ "Offload Vector AVX512 Scattered" },
+#endif
+ { sxe2_rx_pkts_scattered_vec_sse_offload,
+ "Vector SSE Scattered" },
#endif
};
int32_t sxe2_rx_burst_mode_get(struct rte_eth_dev *dev,
- __rte_unused uint16_t queue_id, struct rte_eth_burst_mode *mode)
+ __rte_unused uint16_t queue_id,
+ struct rte_eth_burst_mode *mode)
{
eth_rx_burst_t pkt_burst = dev->rx_pkt_burst;
int32_t ret = -EINVAL;
uint32_t i, size;
+
size = RTE_DIM(sxe2_rx_burst_infos);
for (i = 0; i < size; ++i) {
if (pkt_burst == sxe2_rx_burst_infos[i].rx_burst) {
diff --git a/drivers/net/sxe2/sxe2_txrx_vec.c b/drivers/net/sxe2/sxe2_txrx_vec.c
index 8df4954d86..cf004f5eb2 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec.c
+++ b/drivers/net/sxe2/sxe2_txrx_vec.c
@@ -165,16 +165,54 @@ static void sxe2_tx_queue_mbufs_release_vec(struct sxe2_tx_queue *txq)
return;
}
i = txq->next_dd - (txq->rs_thresh - 1);
- buffer = txq->buffer_ring;
- if (txq->next_use < i) {
- for ( ; i < txq->ring_depth; ++i) {
+#ifdef CC_AVX512_SUPPORT
+ struct rte_eth_dev *dev;
+ struct sxe2_tx_buffer_vec *buffer_vec;
+
+ dev = &rte_eth_devices[txq->port_id];
+
+ if (dev->tx_pkt_burst == sxe2_tx_pkts_vec_avx512 ||
+ dev->tx_pkt_burst == sxe2_tx_pkts_vec_avx512_simple) {
+ buffer_vec = (struct sxe2_tx_buffer_vec *)txq->buffer_ring;
+
+ if (txq->next_use < i) {
+ for ( ; i < txq->ring_depth; ++i) {
+ if (buffer_vec[i].mbuf != NULL) {
+ rte_pktmbuf_free_seg(buffer_vec[i].mbuf);
+ buffer_vec[i].mbuf = NULL;
+ }
+ }
+ i = 0;
+ }
+ for ( ; i < txq->next_use; ++i) {
+ if (buffer_vec[i].mbuf != NULL) {
+ rte_pktmbuf_free_seg(buffer_vec[i].mbuf);
+ buffer_vec[i].mbuf = NULL;
+ }
+ }
+ } else {
+#endif
+ buffer = txq->buffer_ring;
+ buffer = txq->buffer_ring;
+ if (txq->next_use < i) {
+ for ( ; i < txq->ring_depth; ++i) {
+ if (buffer[i].mbuf != NULL) {
+ rte_pktmbuf_free_seg(buffer[i].mbuf);
+ buffer[i].mbuf = NULL;
+ }
+ }
+ i = 0;
+ }
+ for (; i < txq->next_use; ++i) {
if (buffer[i].mbuf != NULL) {
rte_pktmbuf_free_seg(buffer[i].mbuf);
buffer[i].mbuf = NULL;
}
}
- i = 0;
+#ifdef CC_AVX512_SUPPORT
}
+#endif
+
for (; i < txq->next_use; ++i) {
if (buffer[i].mbuf != NULL) {
rte_pktmbuf_free_seg(buffer[i].mbuf);
diff --git a/drivers/net/sxe2/sxe2_txrx_vec.h b/drivers/net/sxe2/sxe2_txrx_vec.h
index 04ff4d96a5..af7c8d12b2 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec.h
+++ b/drivers/net/sxe2/sxe2_txrx_vec.h
@@ -11,15 +11,19 @@
#define SXE2_RX_MODE_VEC_SIMPLE RTE_BIT32(0)
#define SXE2_RX_MODE_VEC_OFFLOAD RTE_BIT32(1)
#define SXE2_RX_MODE_VEC_SSE RTE_BIT32(2)
+#define SXE2_RX_MODE_VEC_AVX512 RTE_BIT32(4)
#define SXE2_RX_MODE_BATCH_ALLOC RTE_BIT32(10)
#define SXE2_RX_MODE_VEC_SET_MASK (SXE2_RX_MODE_VEC_SIMPLE | \
- SXE2_RX_MODE_VEC_OFFLOAD | SXE2_RX_MODE_VEC_SSE)
+ SXE2_RX_MODE_VEC_OFFLOAD | SXE2_RX_MODE_VEC_SSE | \
+ SXE2_RX_MODE_VEC_AVX512)
#define SXE2_TX_MODE_VEC_SIMPLE RTE_BIT32(0)
#define SXE2_TX_MODE_VEC_OFFLOAD RTE_BIT32(1)
#define SXE2_TX_MODE_VEC_SSE RTE_BIT32(2)
+#define SXE2_TX_MODE_VEC_AVX512 RTE_BIT32(4)
#define SXE2_TX_MODE_SIMPLE_BATCH RTE_BIT32(10)
#define SXE2_TX_MODE_VEC_SET_MASK (SXE2_TX_MODE_VEC_SIMPLE | \
- SXE2_TX_MODE_VEC_OFFLOAD | SXE2_TX_MODE_VEC_SSE)
+ SXE2_TX_MODE_VEC_OFFLOAD | SXE2_TX_MODE_VEC_SSE | \
+ SXE2_TX_MODE_VEC_AVX512)
#define SXE2_TX_VEC_NO_SUPPORT_OFFLOAD ( \
RTE_ETH_TX_OFFLOAD_MULTI_SEGS | \
RTE_ETH_TX_OFFLOAD_QINQ_INSERT | \
@@ -54,6 +58,16 @@ uint16_t sxe2_tx_pkts_vec_sse(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_
uint16_t sxe2_tx_pkts_vec_sse_simple(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
uint16_t sxe2_rx_pkts_scattered_vec_sse_offload(void *rx_queue,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_tx_pkts_vec_avx512_simple(void *tx_queue,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_tx_pkts_vec_avx512(void *tx_queue,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_tx_pkts_vec_avx512_ctx_offload(void *tx_queue,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_rx_pkts_scattered_vec_avx512(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
+uint16_t sxe2_rx_pkts_scattered_vec_avx512_offload(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts);
#endif
int32_t __rte_cold sxe2_tx_vec_support_check(struct rte_eth_dev *dev, uint32_t *vec_flags);
int32_t __rte_cold sxe2_tx_queues_vec_prepare(struct rte_eth_dev *dev);
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_avx512.c b/drivers/net/sxe2/sxe2_txrx_vec_avx512.c
new file mode 100644
index 0000000000..a830c7a33b
--- /dev/null
+++ b/drivers/net/sxe2/sxe2_txrx_vec_avx512.c
@@ -0,0 +1,867 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (C), 2025, Wuxi Stars Micro System Technologies Co., Ltd.
+ */
+
+#ifndef SXE2_TEST
+#include <rte_vect.h>
+
+#include "sxe2_ethdev.h"
+#include "sxe2_common_log.h"
+#include "sxe2_queue.h"
+#include "sxe2_txrx_vec.h"
+#include "sxe2_txrx_vec_common.h"
+#include "sxe2_vsi.h"
+
+static __rte_always_inline int32_t sxe2_tx_bufs_free_vec_avx512(struct sxe2_tx_queue *txq)
+{
+ struct sxe2_tx_buffer_vec *buffer;
+ struct rte_mbuf *mbuf;
+ struct rte_mbuf *mbuf_free_arr[SXE2_TX_FREE_BUFFER_SIZE_MAX_VEC];
+ struct rte_mempool *mp;
+ struct rte_mempool_cache *cache;
+ void **cache_objs;
+ uint32_t copied;
+ uint32_t i;
+ int32_t ret;
+ uint16_t rs_thresh;
+ uint16_t free_num;
+
+ if (rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_DESC_DONE) !=
+ (txq->desc_ring[txq->next_dd].wb.dd &
+ rte_cpu_to_le_64(SXE2_TX_DESC_DTYPE_MASK))) {
+ ret = 0;
+ goto l_end;
+ }
+
+ rs_thresh = txq->rs_thresh;
+
+ buffer = (struct sxe2_tx_buffer_vec *)txq->buffer_ring;
+ buffer += txq->next_dd - (rs_thresh - 1);
+
+ if ((txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) &&
+ (rs_thresh & 31) == 0) {
+ mp = buffer[0].mbuf->pool;
+ cache = rte_mempool_default_cache(mp, rte_lcore_id());
+
+ if (cache == NULL || cache->len)
+ goto normal;
+
+ if (rs_thresh > RTE_MEMPOOL_CACHE_MAX_SIZE) {
+ (void)rte_mempool_ops_enqueue_bulk(mp, (void *)buffer, rs_thresh);
+ goto done;
+ }
+ cache_objs = &cache->objs[cache->len];
+
+ copied = 0;
+ while (copied < rs_thresh) {
+ const __m512i objs0 = _mm512_loadu_si512(&buffer[copied]);
+ const __m512i objs1 = _mm512_loadu_si512(&buffer[copied + 8]);
+ const __m512i objs2 = _mm512_loadu_si512(&buffer[copied + 16]);
+ const __m512i objs3 = _mm512_loadu_si512(&buffer[copied + 24]);
+
+ _mm512_storeu_si512(&cache_objs[copied], objs0);
+ _mm512_storeu_si512(&cache_objs[copied + 8], objs1);
+ _mm512_storeu_si512(&cache_objs[copied + 16], objs2);
+ _mm512_storeu_si512(&cache_objs[copied + 24], objs3);
+ copied += 32;
+ }
+ cache->len += rs_thresh;
+
+ if (cache->len >= cache->flushthresh) {
+ (void)rte_mempool_ops_enqueue_bulk(mp,
+ &cache->objs[cache->size], cache->len - cache->size);
+ cache->len = cache->size;
+ }
+ goto done;
+ }
+
+normal:
+ mbuf = rte_pktmbuf_prefree_seg(buffer[0].mbuf);
+
+ if (likely(mbuf)) {
+ mbuf_free_arr[0] = mbuf;
+ free_num = 1;
+
+ for (i = 1; i < rs_thresh; ++i) {
+ mbuf = rte_pktmbuf_prefree_seg(buffer[i].mbuf);
+
+ if (likely(mbuf)) {
+ if (likely(mbuf->pool == mbuf_free_arr[0]->pool)) {
+ mbuf_free_arr[free_num] = mbuf;
+ free_num++;
+ } else {
+ rte_mempool_put_bulk(mbuf_free_arr[0]->pool,
+ (void *)mbuf_free_arr, free_num);
+
+ mbuf_free_arr[0] = mbuf;
+ free_num = 1;
+ }
+ }
+ }
+
+ rte_mempool_put_bulk(mbuf_free_arr[0]->pool,
+ (void *)mbuf_free_arr, free_num);
+ } else {
+ for (i = 1; i < rs_thresh; ++i) {
+ mbuf = rte_pktmbuf_prefree_seg(buffer[i].mbuf);
+ if (mbuf != NULL)
+ rte_mempool_put(mbuf->pool, mbuf);
+ }
+ }
+
+done:
+ txq->desc_free_num += txq->rs_thresh;
+ txq->next_dd += txq->rs_thresh;
+ if (txq->next_dd >= txq->ring_depth)
+ txq->next_dd = txq->rs_thresh - 1;
+ ret = rs_thresh;
+
+l_end:
+ return ret;
+}
+
+static __rte_always_inline void
+sxe2_tx_desc_fill_one_avx512(volatile union sxe2_tx_data_desc *desc, struct rte_mbuf *pkt,
+ uint64_t desc_cmd, bool with_offloads)
+{
+ __m128i data_desc;
+ uint64_t desc_qw1;
+ uint32_t desc_offset;
+
+ desc_qw1 = (SXE2_TX_DESC_DTYPE_DATA |
+ ((uint64_t)desc_cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT |
+ ((uint64_t)pkt->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset = SXE2_TX_DATA_DESC_MACLEN_VAL(pkt->l2_len);
+ desc_qw1 |= ((uint64_t)desc_offset) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkt, &desc_qw1);
+
+ data_desc = _mm_set_epi64x(desc_qw1, rte_pktmbuf_iova(pkt));
+
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, desc), data_desc);
+}
+
+static __rte_always_inline
+void sxe2_tx_desc_fill_avx512(volatile union sxe2_tx_data_desc *desc, struct rte_mbuf **pkts,
+ uint16_t pkts_num, uint64_t desc_cmd, bool with_offloads)
+{
+ __m512i desc_group;
+ uint64_t desc0_qw1;
+ uint64_t desc1_qw1;
+ uint64_t desc2_qw1;
+ uint64_t desc3_qw1;
+
+ const uint64_t desc_qw1_com = (SXE2_TX_DESC_DTYPE_DATA |
+ ((uint64_t)desc_cmd) << SXE2_TX_DATA_DESC_CMD_SHIFT);
+ uint32_t desc_offset[4] = {0};
+
+ while (pkts_num > 3) {
+ desc3_qw1 = desc_qw1_com |
+ ((uint64_t)pkts[3]->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT;
+
+ desc_offset[3] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[3]->l2_len);
+ desc3_qw1 |= ((uint64_t)desc_offset[3]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[3], &desc3_qw1);
+
+ desc2_qw1 = desc_qw1_com |
+ ((uint64_t)pkts[2]->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT;
+ desc_offset[2] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[2]->l2_len);
+ desc2_qw1 |= ((uint64_t)desc_offset[2]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[2], &desc2_qw1);
+
+ desc1_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[1]->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset[1] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[1]->l2_len);
+ desc1_qw1 |= ((uint64_t)desc_offset[1]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[1], &desc1_qw1);
+
+ desc0_qw1 = (desc_qw1_com |
+ ((uint64_t)pkts[0]->data_len) << SXE2_TX_DATA_DESC_BUF_SZ_SHIFT);
+ desc_offset[0] = SXE2_TX_DATA_DESC_MACLEN_VAL(pkts[0]->l2_len);
+ desc0_qw1 |= ((uint64_t)desc_offset[0]) << SXE2_TX_DATA_DESC_OFFSET_SHIFT;
+ if (with_offloads)
+ sxe2_tx_desc_fill_offloads(pkts[0], &desc0_qw1);
+
+ desc_group =
+ _mm512_set_epi64(desc3_qw1, rte_pktmbuf_iova(pkts[3]),
+ desc2_qw1, rte_pktmbuf_iova(pkts[2]),
+ desc1_qw1, rte_pktmbuf_iova(pkts[1]),
+ desc0_qw1, rte_pktmbuf_iova(pkts[0]));
+
+ _mm512_storeu_si512(RTE_CAST_PTR(void *, desc), desc_group);
+
+ pkts_num -= 4;
+ desc += 4;
+ pkts += 4;
+ }
+
+ while (pkts_num) {
+ sxe2_tx_desc_fill_one_avx512(desc, *pkts, desc_cmd, with_offloads);
+
+ pkts_num--;
+ desc++;
+ pkts++;
+ }
+}
+
+static __rte_always_inline void
+sxe2_tx_pkts_mbuf_fill_avx512(struct sxe2_tx_buffer_vec *buffer,
+ struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ uint16_t i;
+
+ for (i = 0; i < nb_pkts; ++i)
+ buffer[i].mbuf = tx_pkts[i];
+}
+
+static __rte_always_inline uint16_t
+sxe2_tx_pkts_vec_avx512_batch(struct sxe2_tx_queue *txq, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts, bool with_offloads)
+{
+ volatile union sxe2_tx_data_desc *desc;
+ struct sxe2_tx_buffer_vec *buffer;
+ uint16_t next_use;
+ uint16_t res_num;
+ uint16_t tx_num;
+
+ if (txq->desc_free_num < txq->free_thresh)
+ (void)sxe2_tx_bufs_free_vec_avx512(txq);
+
+ nb_pkts = RTE_MIN(txq->desc_free_num, nb_pkts);
+ if (unlikely(nb_pkts == 0)) {
+ PMD_LOG_DEBUG(TX, "Tx pkts avx512 batch: may not enough free desc, "
+ "free_desc=%u, need_tx_pkts=%u",
+ txq->desc_free_num, nb_pkts);
+ goto l_end;
+ }
+ tx_num = nb_pkts;
+
+ next_use = txq->next_use;
+ desc = &txq->desc_ring[next_use];
+ buffer = (struct sxe2_tx_buffer_vec *)txq->buffer_ring;
+ buffer += next_use;
+
+ txq->desc_free_num -= nb_pkts;
+
+ res_num = txq->ring_depth - txq->next_use;
+
+ if (tx_num >= res_num) {
+ sxe2_tx_pkts_mbuf_fill_avx512(buffer, tx_pkts, res_num);
+
+ sxe2_tx_desc_fill_avx512(desc, tx_pkts, res_num,
+ SXE2_TX_DATA_DESC_CMD_EOP, with_offloads);
+ tx_pkts += (res_num - 1);
+ desc += (res_num - 1);
+
+ sxe2_tx_desc_fill_one_avx512(desc, *tx_pkts++,
+ (SXE2_TX_DATA_DESC_CMD_EOP | SXE2_TX_DATA_DESC_CMD_RS),
+ with_offloads);
+
+ tx_num -= res_num;
+
+ next_use = 0;
+ txq->next_rs = txq->rs_thresh - 1;
+ desc = txq->desc_ring;
+ buffer = (struct sxe2_tx_buffer_vec *)txq->buffer_ring;
+ }
+
+ sxe2_tx_pkts_mbuf_fill_avx512(buffer, tx_pkts, tx_num);
+
+ sxe2_tx_desc_fill_avx512(desc, tx_pkts, tx_num,
+ SXE2_TX_DATA_DESC_CMD_EOP, with_offloads);
+
+ next_use += tx_num;
+ if (next_use > txq->next_rs) {
+ txq->desc_ring[txq->next_rs].read.type_cmd_off_bsz_l2t |=
+ rte_cpu_to_le_64(SXE2_TX_DATA_DESC_CMD_RS_MASK);
+
+ txq->next_rs += txq->rs_thresh;
+ }
+ txq->next_use = next_use;
+
+ SXE2_PCI_REG_WRITE_WC(txq->tdt_reg_addr, next_use);
+ PMD_LOG_DEBUG(TX, "port_id=%u queue_id=%u next_use=%u send_pkts=%u",
+ txq->port_id, txq->queue_id, next_use, nb_pkts);
+l_end:
+ return nb_pkts;
+}
+
+static __rte_always_inline uint16_t
+sxe2_tx_pkts_vec_avx512_common(struct sxe2_tx_queue *txq, struct rte_mbuf **tx_pkts,
+ uint16_t nb_pkts, bool with_offloads)
+{
+ uint16_t tx_done_num = 0;
+ uint16_t tx_once_num;
+ uint16_t tx_need_num;
+
+ while (nb_pkts) {
+ tx_need_num = RTE_MIN(nb_pkts, txq->rs_thresh);
+ tx_once_num =
+ sxe2_tx_pkts_vec_avx512_batch(txq, tx_pkts + tx_done_num,
+ tx_need_num, with_offloads);
+ nb_pkts -= tx_once_num;
+ tx_done_num += tx_once_num;
+ if (tx_once_num < tx_need_num)
+ break;
+ }
+
+ return tx_done_num;
+}
+
+uint16_t sxe2_tx_pkts_vec_avx512_simple(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_tx_pkts_vec_avx512_common((struct sxe2_tx_queue *)tx_queue,
+ tx_pkts, nb_pkts, false);
+}
+
+uint16_t sxe2_tx_pkts_vec_avx512(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_tx_pkts_vec_avx512_common((struct sxe2_tx_queue *)tx_queue,
+ tx_pkts, nb_pkts, true);
+}
+
+static inline void sxe2_rx_queue_rearm_avx512(struct sxe2_rx_queue *rxq)
+{
+ volatile union sxe2_rx_desc *desc;
+ struct rte_mbuf **buffer;
+ struct rte_mbuf *mbuf0, *mbuf1;
+ __m128i dma_addr0, dma_addr1;
+ __m128i virt_addr0, virt_addr1;
+ __m128i hdr_room = _mm_set_epi64x(RTE_PKTMBUF_HEADROOM, RTE_PKTMBUF_HEADROOM);
+ int32_t ret;
+ uint16_t i;
+ uint16_t new_tail;
+
+ buffer = &rxq->buffer_ring[rxq->realloc_start];
+ desc = &rxq->desc_ring[rxq->realloc_start];
+
+ ret = rte_mempool_get_bulk(rxq->mb_pool, (void *)buffer, SXE2_RX_REARM_THRESH_VEC);
+ if (ret != 0) {
+ if ((rxq->realloc_num + SXE2_RX_REARM_THRESH_VEC) >= rxq->ring_depth) {
+ dma_addr0 = _mm_setzero_si128();
+ for (i = 0; i < SXE2_RX_NUM_PER_LOOP_AVX; ++i) {
+ buffer[i] = &rxq->fake_mbuf;
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc[i].read),
+ dma_addr0);
+ }
+ }
+
+ rxq->vsi->adapter->dev_info.dev_data->rx_mbuf_alloc_failed +=
+ SXE2_RX_REARM_THRESH_VEC;
+ goto l_end;
+ }
+
+ for (i = 0; i < SXE2_RX_REARM_THRESH_VEC; i += 2, buffer += 2) {
+ mbuf0 = buffer[0];
+ mbuf1 = buffer[1];
+
+#if RTE_IOVA_IN_MBUF
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, buf_iova) !=
+ offsetof(struct rte_mbuf, buf_addr) + 8);
+#endif
+ virt_addr0 = _mm_loadu_si128((__m128i *)&mbuf0->buf_addr);
+ virt_addr1 = _mm_loadu_si128((__m128i *)&mbuf1->buf_addr);
+
+#if RTE_IOVA_IN_MBUF
+
+ dma_addr0 = _mm_unpackhi_epi64(virt_addr0, virt_addr0);
+ dma_addr1 = _mm_unpackhi_epi64(virt_addr1, virt_addr1);
+#else
+
+ dma_addr0 = _mm_unpacklo_epi64(virt_addr0, virt_addr0);
+ dma_addr1 = _mm_unpacklo_epi64(virt_addr1, virt_addr1);
+#endif
+
+ dma_addr0 = _mm_add_epi64(dma_addr0, hdr_room);
+ dma_addr1 = _mm_add_epi64(dma_addr1, hdr_room);
+
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc++->read), dma_addr0);
+ _mm_store_si128(RTE_CAST_PTR(__m128i *, &desc++->read), dma_addr1);
+ }
+
+ rxq->realloc_start += SXE2_RX_REARM_THRESH_VEC;
+ if (rxq->realloc_start >= rxq->ring_depth)
+ rxq->realloc_start = 0;
+ rxq->realloc_num -= SXE2_RX_REARM_THRESH_VEC;
+
+ new_tail = (rxq->realloc_start == 0) ? (rxq->ring_depth - 1) :
+ (rxq->realloc_start - 1);
+
+ SXE2_PCI_REG_WRITE_WC(rxq->rdt_reg_addr, new_tail);
+
+l_end:
+ return;
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_common_vec_avx512(struct sxe2_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, uint8_t *split_rxe_flags,
+ uint8_t *umbcast_flags, bool do_offload)
+{
+ const __m256i mbuf_init = _mm256_set_epi64x(0, 0, 0, rxq->mbuf_init_value);
+ struct rte_mbuf **buffer;
+ volatile union sxe2_rx_desc *desc;
+ __m512i mbufs4_7;
+ __m512i mbufs0_3;
+ __m256i mbufs6_7;
+ __m256i mbufs4_5;
+ __m256i mbufs2_3;
+ __m256i mbufs0_1;
+ uint32_t bit_num = 0;
+ uint16_t done_num = 0;
+ uint16_t i = 0;
+ uint16_t j = 0;
+
+ buffer = &rxq->buffer_ring[rxq->processing_idx];
+ desc = &rxq->desc_ring[rxq->processing_idx];
+
+ rte_prefetch0(desc);
+
+ nb_pkts = RTE_ALIGN_FLOOR(nb_pkts, SXE2_RX_NUM_PER_LOOP_AVX);
+
+ if (rxq->realloc_num > SXE2_RX_REARM_THRESH_VEC)
+ sxe2_rx_queue_rearm_avx512(rxq);
+
+ if (0 == (rte_le_to_cpu_64(desc->wb.status_err_ptype_len) & SXE2_RX_DESC_STATUS_DD_MASK))
+ goto l_end;
+
+ const __m512i crc_adjust =
+ _mm512_set4_epi32(0, -rxq->crc_len, -rxq->crc_len, 0);
+
+ const __m256i dd_mask = _mm256_set1_epi32(1);
+
+ const __m512i rvp_shuf_mask =
+ _mm512_set4_epi32((7 << 24) | (6 << 16) | (5 << 8) | 4,
+ (3 << 24) | (2 << 16) | (13 << 8) | 12,
+ (0xFFU << 24) | (0xFF << 16) | (13 << 8) | 12,
+ 0xFFFFFFFF);
+
+ const __m128i eop_shuf_mask =
+ _mm_set_epi8(0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
+ 0xFF, 0xFF, 8, 0, 10, 2, 12, 4, 14, 6);
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, pkt_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 4);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, data_len) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, vlan_tci) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 10);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, hash) !=
+ offsetof(struct rte_mbuf, rx_descriptor_fields1) + 12);
+
+ for (i = 0; i < nb_pkts; i += SXE2_RX_NUM_PER_LOOP_AVX,
+ desc += SXE2_RX_NUM_PER_LOOP_AVX) {
+ _mm256_storeu_si256((void *)&rx_pkts[i],
+ _mm256_loadu_si256((void *)&buffer[i]));
+#ifdef RTE_ARCH_X86_64
+ _mm256_storeu_si256((void *)&rx_pkts[i + 4],
+ _mm256_loadu_si256((void *)&buffer[i + 4]));
+#endif
+
+ const __m128i desc7 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 7));
+ rte_compiler_barrier();
+ const __m128i desc6 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 6));
+ rte_compiler_barrier();
+ const __m128i desc5 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 5));
+ rte_compiler_barrier();
+ const __m128i desc4 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 4));
+ rte_compiler_barrier();
+ const __m128i desc3 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 3));
+ rte_compiler_barrier();
+ const __m128i desc2 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 2));
+ rte_compiler_barrier();
+ const __m128i desc1 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 1));
+ rte_compiler_barrier();
+ const __m128i desc0 = _mm_loadu_si128(RTE_CAST_PTR(const __m128i *, desc + 0));
+
+ const __m256i descs6_7 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc6), desc7, 1);
+ const __m256i descs4_5 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc4), desc5, 1);
+ const __m256i descs2_3 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc2), desc3, 1);
+ const __m256i descs0_1 =
+ _mm256_inserti128_si256(_mm256_castsi128_si256(desc0), desc1, 1);
+
+ const __m512i descs4_7 =
+ _mm512_inserti64x4(_mm512_castsi256_si512(descs4_5), descs6_7, 1);
+ const __m512i descs0_3 =
+ _mm512_inserti64x4(_mm512_castsi256_si512(descs0_1), descs2_3, 1);
+
+ if (split_rxe_flags != NULL) {
+ for (j = 0; j < SXE2_RX_NUM_PER_LOOP_AVX; j++)
+ rte_mbuf_prefetch_part2(rx_pkts[i + j]);
+ }
+
+ mbufs4_7 = _mm512_shuffle_epi8(descs4_7, rvp_shuf_mask);
+ mbufs0_3 = _mm512_shuffle_epi8(descs0_3, rvp_shuf_mask);
+
+ mbufs4_7 = _mm512_add_epi32(mbufs4_7, crc_adjust);
+ mbufs0_3 = _mm512_add_epi32(mbufs0_3, crc_adjust);
+
+ const __m512i ptype_mask = _mm512_set1_epi64(SXE2_RX_FLEX_DESC_PTYPE_M <<
+ SXE2_RX_FLEX_DESC_PTYPE_S);
+
+ __m512i ptypes4_7 = _mm512_and_si512(descs4_7, ptype_mask);
+ __m512i ptypes0_3 = _mm512_and_si512(descs0_3, ptype_mask);
+
+ const __m256i ptypes6_7 = _mm512_extracti64x4_epi64(ptypes4_7, 1);
+ const __m256i ptypes4_5 = _mm512_extracti64x4_epi64(ptypes4_7, 0);
+ const __m256i ptypes2_3 = _mm512_extracti64x4_epi64(ptypes0_3, 1);
+ const __m256i ptypes0_1 = _mm512_extracti64x4_epi64(ptypes0_3, 0);
+
+ const uint16_t ptype7 = _mm256_extract_epi16(ptypes6_7, 13);
+ const uint16_t ptype6 = _mm256_extract_epi16(ptypes6_7, 5);
+ const uint16_t ptype5 = _mm256_extract_epi16(ptypes4_5, 13);
+ const uint16_t ptype4 = _mm256_extract_epi16(ptypes4_5, 5);
+ const uint16_t ptype3 = _mm256_extract_epi16(ptypes2_3, 13);
+ const uint16_t ptype2 = _mm256_extract_epi16(ptypes2_3, 5);
+ const uint16_t ptype1 = _mm256_extract_epi16(ptypes0_1, 13);
+ const uint16_t ptype0 = _mm256_extract_epi16(ptypes0_1, 5);
+
+ const __m512i ptype_mask4_7 =
+ _mm512_set_epi32(0, 0, 0, sxe2_ptype_tbl[ptype7],
+ 0, 0, 0, sxe2_ptype_tbl[ptype6],
+ 0, 0, 0, sxe2_ptype_tbl[ptype5],
+ 0, 0, 0, sxe2_ptype_tbl[ptype4]);
+ const __m512i ptype_mask0_3 =
+ _mm512_set_epi32(0, 0, 0, sxe2_ptype_tbl[ptype3],
+ 0, 0, 0, sxe2_ptype_tbl[ptype2],
+ 0, 0, 0, sxe2_ptype_tbl[ptype1],
+ 0, 0, 0, sxe2_ptype_tbl[ptype0]);
+
+ mbufs4_7 = _mm512_or_si512(mbufs4_7, ptype_mask4_7);
+ mbufs0_3 = _mm512_or_si512(mbufs0_3, ptype_mask0_3);
+
+ mbufs6_7 = _mm512_extracti64x4_epi64(mbufs4_7, 1);
+ mbufs4_5 = _mm512_extracti64x4_epi64(mbufs4_7, 0);
+ mbufs2_3 = _mm512_extracti64x4_epi64(mbufs0_3, 1);
+ mbufs0_1 = _mm512_extracti64x4_epi64(mbufs0_3, 0);
+
+ const __m512i staterr_per_mask =
+ _mm512_set_epi32(0x17, 0x1F, 0x07, 0x0F,
+ 0x13, 0x1B, 0x03, 0x0B,
+ 0x16, 0x1E, 0x06, 0x0E,
+ 0x12, 0x1A, 0x02, 0x0A);
+ __m512i qw1_0_7 = _mm512_permutex2var_epi32(descs4_7,
+ staterr_per_mask,
+ descs0_3);
+
+ __m256i staterrs0_7 = _mm512_extracti64x4_epi64(qw1_0_7, 0);
+
+ __m256i stu_len0_7 = _mm512_extracti64x4_epi64(qw1_0_7, 1);
+ __m256i mbuf_flags = _mm256_setzero_si256();
+
+ if (do_offload) {
+ const __m256i desc_flags_mask = _mm256_set1_epi32(0xC0001C04);
+ const __m256i desc_flags_rss_mask = _mm256_set1_epi32(0x20000000);
+ const __m256i vlan_flags =
+ _mm256_set_epi8(0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_VLAN |
+ RTE_MBUF_F_RX_VLAN_STRIPPED,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_VLAN |
+ RTE_MBUF_F_RX_VLAN_STRIPPED,
+ 0, 0, 0, 0);
+
+ const __m256i rss_flags =
+ _mm256_set_epi8(0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_RSS_HASH,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, 0,
+ 0, 0, 0, RTE_MBUF_F_RX_RSS_HASH,
+ 0, 0, 0, 0);
+
+ const __m256i cksum_flags =
+ _mm256_set_epi8(0, 0, 0, 0, 0, 0, 0,
+ 0,
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD | RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_BAD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD | RTE_MBUF_F_RX_L4_CKSUM_GOOD |
+ RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_BAD | RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD | RTE_MBUF_F_RX_IP_CKSUM_BAD) >> 1),
+ ((RTE_MBUF_F_RX_L4_CKSUM_GOOD | RTE_MBUF_F_RX_IP_CKSUM_GOOD) >> 1));
+
+ const __m256i cksum_mask =
+ _mm256_set1_epi32(RTE_MBUF_F_RX_IP_CKSUM_MASK |
+ RTE_MBUF_F_RX_L4_CKSUM_MASK |
+ RTE_MBUF_F_RX_OUTER_L4_CKSUM_MASK |
+ RTE_MBUF_F_RX_OUTER_IP_CKSUM_BAD);
+
+ const __m256i vlan_mask =
+ _mm256_set1_epi32(RTE_MBUF_F_RX_VLAN |
+ RTE_MBUF_F_RX_VLAN_STRIPPED);
+
+ __m256i tmp_flags;
+ __m256i descs_flags = _mm256_and_si256(staterrs0_7, desc_flags_mask);
+ stu_len0_7 = _mm256_and_si256(stu_len0_7, desc_flags_rss_mask);
+
+ tmp_flags = _mm256_shuffle_epi8(vlan_flags, descs_flags);
+ mbuf_flags = _mm256_and_si256(tmp_flags, vlan_mask);
+
+ descs_flags = _mm256_srli_epi32(descs_flags, 10);
+ tmp_flags = _mm256_shuffle_epi8(cksum_flags, descs_flags);
+ tmp_flags = _mm256_slli_epi32(tmp_flags, 1);
+ tmp_flags = _mm256_and_si256(tmp_flags, cksum_mask);
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+ descs_flags = _mm256_srli_epi32(stu_len0_7, 27);
+ tmp_flags = _mm256_shuffle_epi8(rss_flags, descs_flags);
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+#ifndef RTE_LIBRTE_SXE2_16BYTE_RX_DESC
+ if (rxq->fnav_enable) {
+ __m256i fnav_vld0_3, fnav_vld4_7;
+ __m256i fnav_vld0_7;
+ __m256i v_zeros, v_ffff, v_u32_one;
+ const __m256i fdir_flags =
+ _mm256_set1_epi32(RTE_MBUF_F_RX_FDIR |
+ RTE_MBUF_F_RX_FDIR_ID);
+ fnav_vld0_3 = _mm256_unpacklo_epi32(descs2_3, descs0_1);
+ fnav_vld4_7 = _mm256_unpacklo_epi32(descs6_7, descs4_5);
+
+ fnav_vld0_7 = _mm256_unpacklo_epi64(fnav_vld4_7, fnav_vld0_3);
+
+ fnav_vld0_7 = _mm256_slli_epi32(fnav_vld0_7, 26);
+ fnav_vld0_7 = _mm256_srli_epi32(fnav_vld0_7, 31);
+
+ v_zeros = _mm256_setzero_si256();
+ v_ffff = _mm256_cmpeq_epi32(v_zeros, v_zeros);
+ v_u32_one = _mm256_srli_epi32(v_ffff, 31);
+
+ tmp_flags = _mm256_cmpeq_epi32(fnav_vld0_7, v_u32_one);
+
+ tmp_flags = _mm256_and_si256(tmp_flags, fdir_flags);
+
+ mbuf_flags = _mm256_or_si256(mbuf_flags, tmp_flags);
+
+ rx_pkts[i + 0]->hash.fdir.hi = desc[0].wb.fd_filter_id;
+ rx_pkts[i + 1]->hash.fdir.hi = desc[1].wb.fd_filter_id;
+ rx_pkts[i + 2]->hash.fdir.hi = desc[2].wb.fd_filter_id;
+ rx_pkts[i + 3]->hash.fdir.hi = desc[3].wb.fd_filter_id;
+ rx_pkts[i + 4]->hash.fdir.hi = desc[4].wb.fd_filter_id;
+ rx_pkts[i + 5]->hash.fdir.hi = desc[5].wb.fd_filter_id;
+ rx_pkts[i + 6]->hash.fdir.hi = desc[6].wb.fd_filter_id;
+ rx_pkts[i + 7]->hash.fdir.hi = desc[7].wb.fd_filter_id;
+ }
+#endif
+ }
+
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, ol_flags) !=
+ offsetof(struct rte_mbuf, rearm_data) + 8);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rx_descriptor_fields1) !=
+ offsetof(struct rte_mbuf, rearm_data) + 16);
+ RTE_BUILD_BUG_ON(offsetof(struct rte_mbuf, rearm_data) !=
+ RTE_ALIGN(offsetof(struct rte_mbuf, rearm_data), 16));
+
+ __m256i rearm_arr[8];
+
+ rearm_arr[6] = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(mbuf_flags, 8), 0x04);
+ rearm_arr[4] = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(mbuf_flags, 4), 0x04);
+ rearm_arr[2] = _mm256_blend_epi32(mbuf_init, mbuf_flags, 0x04);
+ rearm_arr[0] = _mm256_blend_epi32(mbuf_init,
+ _mm256_srli_si256(mbuf_flags, 4), 0x04);
+
+ rearm_arr[6] = _mm256_permute2f128_si256(rearm_arr[6], mbufs6_7, 0x20);
+ rearm_arr[4] = _mm256_permute2f128_si256(rearm_arr[4], mbufs4_5, 0x20);
+ rearm_arr[2] = _mm256_permute2f128_si256(rearm_arr[2], mbufs2_3, 0x20);
+ rearm_arr[0] = _mm256_permute2f128_si256(rearm_arr[0], mbufs0_1, 0x20);
+
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 6]->rearm_data, rearm_arr[6]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 4]->rearm_data, rearm_arr[4]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 2]->rearm_data, rearm_arr[2]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 0]->rearm_data, rearm_arr[0]);
+
+ const __m256i tmp_mbuf_flags =
+ _mm256_castsi128_si256(_mm256_extracti128_si256(mbuf_flags, 1));
+
+ rearm_arr[7] = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(tmp_mbuf_flags, 8), 4);
+ rearm_arr[5] = _mm256_blend_epi32(mbuf_init,
+ _mm256_slli_si256(tmp_mbuf_flags, 4), 4);
+ rearm_arr[3] = _mm256_blend_epi32(mbuf_init, tmp_mbuf_flags, 4);
+ rearm_arr[1] = _mm256_blend_epi32(mbuf_init,
+ _mm256_srli_si256(tmp_mbuf_flags, 4), 4);
+
+ rearm_arr[7] = _mm256_blend_epi32(rearm_arr[7], mbufs6_7, 0XF0);
+ rearm_arr[5] = _mm256_blend_epi32(rearm_arr[5], mbufs4_5, 0XF0);
+ rearm_arr[3] = _mm256_blend_epi32(rearm_arr[3], mbufs2_3, 0XF0);
+ rearm_arr[1] = _mm256_blend_epi32(rearm_arr[1], mbufs0_1, 0XF0);
+
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 7]->rearm_data, rearm_arr[7]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 5]->rearm_data, rearm_arr[5]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 3]->rearm_data, rearm_arr[3]);
+ _mm256_storeu_si256((__m256i *)&rx_pkts[i + 1]->rearm_data, rearm_arr[1]);
+
+ if (umbcast_flags) {
+ const __m256i umbcast_mask =
+ _mm256_set1_epi32(SXE2_RX_DESC_STATUS_UMBCAST_MASK);
+ __m256i umbcast_bits_256 =
+ _mm256_and_si256(staterrs0_7, umbcast_mask);
+
+ umbcast_bits_256 = _mm256_srli_epi32(umbcast_bits_256, 24);
+ __m128i umbcast_bits_128 =
+ _mm_packs_epi32(_mm256_castsi256_si128(umbcast_bits_256),
+ _mm256_extractf128_si256(umbcast_bits_256, 1));
+
+ umbcast_bits_128 = _mm_shuffle_epi8(umbcast_bits_128, eop_shuf_mask);
+
+ *(uint64_t *)umbcast_flags = _mm_cvtsi128_si64(umbcast_bits_128);
+ umbcast_flags += SXE2_RX_NUM_PER_LOOP_AVX;
+ }
+
+ if (split_rxe_flags) {
+ const __m256i eop_rxe_mask =
+ _mm256_set1_epi32(SXE2_RX_DESC_STATUS_EOP_MASK |
+ SXE2_RX_DESC_ERROR_RXE_MASK |
+ SXE2_RX_DESC_ERROR_OVERSIZE_MASK);
+ const __m128i eop_mask_128 =
+ _mm_set1_epi16(SXE2_RX_DESC_STATUS_EOP_MASK);
+ const __m128i rxe_mask_128 =
+ _mm_set1_epi16(SXE2_RX_DESC_ERROR_RXE_MASK |
+ SXE2_RX_DESC_ERROR_OVERSIZE_MASK);
+
+ const __m256i tmp_stats = _mm256_and_si256(staterrs0_7, eop_rxe_mask);
+
+ const __m128i eop_rxe_bits = _mm_packs_epi32
+ (_mm256_castsi256_si128(tmp_stats),
+ _mm256_extractf128_si256(tmp_stats, 1));
+
+ __m128i not_eop_bits = _mm_andnot_si128(eop_rxe_bits, eop_mask_128);
+
+ not_eop_bits =
+ _mm_or_si128(not_eop_bits,
+ _mm_srli_epi16(_mm_and_si128(eop_rxe_bits,
+ rxe_mask_128),
+ 7));
+
+ not_eop_bits = _mm_shuffle_epi8(not_eop_bits, eop_shuf_mask);
+
+ *(uint64_t *)split_rxe_flags = _mm_cvtsi128_si64(not_eop_bits);
+ split_rxe_flags += SXE2_RX_NUM_PER_LOOP_AVX;
+ }
+
+ staterrs0_7 = _mm256_and_si256(staterrs0_7, dd_mask);
+
+ staterrs0_7 = _mm256_packs_epi32(staterrs0_7, _mm256_setzero_si256());
+
+ bit_num = rte_popcount64
+ (_mm_cvtsi128_si64(_mm256_extracti128_si256(staterrs0_7, 1)));
+ bit_num += rte_popcount64
+ (_mm_cvtsi128_si64(_mm256_castsi256_si128(staterrs0_7)));
+ done_num += bit_num;
+
+ if (bit_num != SXE2_RX_NUM_PER_LOOP_AVX)
+ break;
+ }
+
+ rxq->processing_idx += done_num;
+ rxq->processing_idx &= (rxq->ring_depth - 1);
+ if ((rxq->processing_idx & 1) == 1 && done_num > 1) {
+ rxq->processing_idx--;
+ done_num--;
+ }
+ rxq->realloc_num += done_num;
+
+l_end:
+ PMD_LOG_DEBUG(RX, "port_id=%u queue_id=%u last_id=%u recv_pkts=%d",
+ rxq->port_id, rxq->queue_id, rxq->processing_idx, done_num);
+ return done_num;
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_scattered_batch_vec_avx512(struct sxe2_rx_queue *rxq, struct rte_mbuf **rx_pkts,
+ uint16_t nb_pkts, bool do_offload)
+{
+ uint8_t split_rxe_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
+ uint8_t umbcast_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
+ uint16_t rx_done_num;
+ uint16_t rx_pkt_done_num;
+
+ rx_pkt_done_num = 0;
+
+ rx_done_num = sxe2_rx_pkts_common_vec_avx512(rxq, rx_pkts,
+ nb_pkts, split_rxe_flags,
+ umbcast_flags, do_offload);
+ if (rx_done_num == 0)
+ goto l_end;
+
+ rx_pkt_done_num += sxe2_rx_pkts_refactor(rxq, &rx_pkts[rx_pkt_done_num],
+ rx_done_num - rx_pkt_done_num, &split_rxe_flags[rx_pkt_done_num],
+ &umbcast_flags[rx_pkt_done_num]);
+
+l_end:
+
+ return rx_pkt_done_num;
+}
+
+static __rte_always_inline uint16_t
+sxe2_rx_pkts_scattered_common_vec_avx512(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts, bool offload)
+{
+ uint16_t done_num = 0;
+ uint16_t once_num = 0;
+
+ while (nb_pkts > SXE2_RX_PKTS_BURST_BATCH_NUM) {
+ once_num = sxe2_rx_pkts_scattered_batch_vec_avx512(rx_queue, rx_pkts + done_num,
+ SXE2_RX_PKTS_BURST_BATCH_NUM, offload);
+
+ done_num += once_num;
+ nb_pkts -= once_num;
+
+ if (once_num < SXE2_RX_PKTS_BURST_BATCH_NUM)
+ goto end;
+ }
+
+ done_num += sxe2_rx_pkts_scattered_batch_vec_avx512(rx_queue,
+ rx_pkts + done_num, nb_pkts, offload);
+
+end:
+ return done_num;
+}
+
+uint16_t sxe2_rx_pkts_scattered_vec_avx512(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_rx_pkts_scattered_common_vec_avx512(rx_queue,
+ rx_pkts, nb_pkts, false);
+}
+
+uint16_t sxe2_rx_pkts_scattered_vec_avx512_offload(void *rx_queue,
+ struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
+{
+ return sxe2_rx_pkts_scattered_common_vec_avx512(rx_queue,
+ rx_pkts, nb_pkts, true);
+}
+
+#endif
--
2.52.0
^ permalink raw reply related
* [PATCH v5 02/23] net/sxe2: add Rx framework and packet types callback
From: liujie5 @ 2026-06-22 9:24 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260622092324.3091185-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
Implement dev_supported_ptypes_get ethdev callback for sxe2 PMD.
This allows applications to query the packet types the driver
is capable of identifying, such as L2, L3 (IPv4/IPv6), and
L4 (TCP/UDP/SCTP) layers.
Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
---
drivers/net/sxe2/sxe2_ethdev.h | 1 -
drivers/net/sxe2/sxe2_txrx.c | 1782 +++++++++++++++++++++++
drivers/net/sxe2/sxe2_txrx.h | 5 +
drivers/net/sxe2/sxe2_txrx_poll.c | 3 +-
drivers/net/sxe2/sxe2_txrx_vec_common.h | 1 +
drivers/net/sxe2/sxe2_txrx_vec_sse.c | 9 +-
6 files changed, 1793 insertions(+), 8 deletions(-)
diff --git a/drivers/net/sxe2/sxe2_ethdev.h b/drivers/net/sxe2/sxe2_ethdev.h
index 8015d9a064..97d1d1fe14 100644
--- a/drivers/net/sxe2/sxe2_ethdev.h
+++ b/drivers/net/sxe2/sxe2_ethdev.h
@@ -279,7 +279,6 @@ struct sxe2_adapter {
uint16_t dev_port_id;
uint64_t cap_flags;
enum sxe2_dev_type dev_type;
- uint32_t ptype_tbl[SXE2_MAX_PTYPE_NUM];
struct rte_ether_addr mac_addr;
uint8_t port_idx;
uint8_t pf_idx;
diff --git a/drivers/net/sxe2/sxe2_txrx.c b/drivers/net/sxe2/sxe2_txrx.c
index 8d17535301..fe4b79352d 100644
--- a/drivers/net/sxe2/sxe2_txrx.c
+++ b/drivers/net/sxe2/sxe2_txrx.c
@@ -349,3 +349,1785 @@ void sxe2_set_common_function(struct rte_eth_dev *dev)
dev->tx_descriptor_status = sxe2_tx_descriptor_status;
dev->tx_pkt_prepare = sxe2_tx_pkts_prepare;
}
+
+const alignas(RTE_CACHE_LINE_SIZE) uint32_t sxe2_ptype_tbl[SXE2_MAX_PTYPE_NUM] = {
+ /* [0] reserved */
+ [1] = RTE_PTYPE_L2_ETHER,
+ [2] = RTE_PTYPE_L2_ETHER_TIMESYNC,
+ /* [3] - [5] reserved */
+ [6] = RTE_PTYPE_L2_ETHER_LLDP,
+ /* ECP */
+ [7] = RTE_PTYPE_UNKNOWN,
+ /* [8] - [9] reserved */
+ /* EAPol */
+ [10] = RTE_PTYPE_UNKNOWN,
+ [11] = RTE_PTYPE_L2_ETHER_ARP,
+ /* [12] - [21] reserved */
+
+ /* Non tunneled IPv4 */
+ [22] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG,
+ [23] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [24] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ /* [25] reserved */
+ [26] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [27] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_SCTP,
+ [28] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_ICMP,
+
+ /* IPv4 --> IPv4 */
+ [29] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [30] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [31] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [32] reserved */
+ [33] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [34] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [35] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 --> IPv6 */
+ [36] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [37] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [38] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [39] reserved */
+ [40] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [41] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [42] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN */
+ [43] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN --> IPv4 */
+ [44] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [45] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [46] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [47] reserved */
+ [48] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [49] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [50] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN --> IPv6 */
+ [51] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [52] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [53] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [54] reserved */
+ [55] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [56] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [57] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC */
+ [58] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC --> IPv4 */
+ [59] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [60] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [61] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [62] reserved */
+ [63] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [64] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [65] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC --> IPv6 */
+ [66] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [67] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [68] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [69] reserved */
+ [70] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [71] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [72] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC/VLAN */
+ [73] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC/VLAN --> IPv4 */
+ [74] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [75] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [76] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ /* [77] reserved */
+ [78] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ [79] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+ [80] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 --> GRE/GENEVE/VXLAN --> MAC/VLAN --> IPv6 */
+ [81] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_FRAG,
+ [82] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [83] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ /* [64] reserved */
+ [85] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ [86] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+ [87] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_ICMP,
+ /* Non tunneled IPv6 */
+ [88] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG,
+ [89] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [90] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ /* [91] reserved */
+ [92] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [93] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_SCTP,
+ [94] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_ICMP,
+
+ /* IPv6 --> IPv4 */
+ [95] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [96] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [97] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [98] reserved */
+ [99] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [100] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [101] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> IPv6 */
+ [102] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [103] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [104] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [105] reserved */
+ [106] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [107] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [108] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN */
+ [109] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> IPv4 */
+ [110] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [111] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [112] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [113] reserved */
+ [114] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [115] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [116] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> IPv6 */
+ [117] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [118] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [119] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [120] reserved */
+ [121] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [122] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [123] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC */
+ [124] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC --> IPv4 */
+ [125] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [126] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [127] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [128] reserved */
+ [129] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [130] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [131] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC --> IPv6 */
+ [132] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [133] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [134] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [135] reserved */
+ [136] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [137] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [138] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC/VLAN */
+ [139] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC/VLAN --> IPv4 */
+ [140] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [141] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [142] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ /* [143] reserved */
+ [144] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ [145] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+ [146] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 --> GRE/GENEVE/VXLAN --> MAC/VLAN --> IPv6 */
+ [147] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [148] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [149] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP,
+ /* [150] reserved */
+ [151] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_TCP,
+ [152] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_SCTP,
+ [153] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_ICMP,
+ /* [154] - [159] reserved */
+ /* IPSec */
+ [160] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_ESP,
+ [161] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_ESP,
+ /* AH */
+ [162] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [163] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* NAT-T-ESP */
+ [164] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_ESP,
+ [165] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_ESP,
+ /* SDN-ESP */
+ [166] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_ESP,
+ [167] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_ESP,
+ /* [168] - [271] reserved */
+ /* IPV4 --> VRRP */
+ [272] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPV4 --> OSPF */
+ [273] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPV6 --> VRRP */
+ [274] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPV6 --> VRRP */
+ [275] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* ATAoE */
+ [276] = RTE_PTYPE_UNKNOWN,
+ /* Control */
+ [278] = RTE_PTYPE_UNKNOWN,
+ /* [279] - [324] reserved */
+ /* GTP */
+ [325] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPC,
+ [326] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPC,
+ [327] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPC,
+ [328] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPC,
+ [329] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU,
+ [330] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU,
+ [331] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [332] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [333] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [334] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [335] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ [336] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [337] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [338] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [339] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [340] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ [341] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [342] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [343] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [344] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [345] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ [346] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [347] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [348] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [349] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [350] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_GTPU |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* PFCP */
+ [351] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [352] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [353] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [354] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ /* [355] - [359] reserved */
+ /* L2TPv3 */
+ [360] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_L2TP,
+ [361] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_L2TP,
+ /* [362] - [370] reserved */
+ /* eCPRI */
+ [371] = RTE_PTYPE_UNKNOWN,
+ [381] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [391] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [396] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, IGMP */
+ [397] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, EIGRP */
+ [398] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, EIGRP */
+ [399] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, PIM */
+ [400] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, PIM */
+ [401] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, IGMP */
+ [402] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, IGMP */
+ [403] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, EIGRP */
+ [404] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, EIGRP */
+ [405] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, PIM */
+ [406] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, PIM */
+ [407] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, VRRP */
+ [408] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, VRRP */
+ [409] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, VRRP */
+ [410] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, VRRP */
+ [411] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, OSPF */
+ [412] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, OSPF */
+ [413] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, OSPF */
+ [414] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, OSPF */
+ [415] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, L2_TP_V3 */
+ [416] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, L2_TP_V3 */
+ [417] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, L2_TP_V3 */
+ [418] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, L2_TP_V3 */
+ [419] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, AH */
+ [420] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, AH */
+ [421] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, AH */
+ [422] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, AH */
+ [423] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv4, ESP */
+ [424] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv4, ESP */
+ [425] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv4, UDP, TUN, MAC, IPv6, ESP */
+ [426] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* MAC, IPv6, UDP, TUN, MAC, IPv6, ESP */
+ [427] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ /* TP-TUN GTPU */
+ [450] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [451] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [452] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [453] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [454] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [455] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [456] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [457] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [458] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [459] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [460] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [461] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [462] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [463] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [464] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [465] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [466] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [467] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [468] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [469] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [470] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [471] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [472] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [473] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [474] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [475] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [476] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [477] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [478] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [479] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [480] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [481] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [482] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [483] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [484] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [485] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [486] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [487] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [488] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [489] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [490] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [491] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [492] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [493] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [494] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [495] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [496] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [497] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_IP | RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ /* [498] - [767] reserved */
+ /* L2(NETWORK CPU) */
+ /* ISIS */
+ [768] = RTE_PTYPE_UNKNOWN,
+ /* SDF */
+ [769] = RTE_PTYPE_UNKNOWN,
+ /* PPoE_NEGO */
+ [770] = RTE_PTYPE_L2_ETHER_PPPOE,
+ /* PPoE_PROTOCOL */
+ [771] = RTE_PTYPE_L2_ETHER_PPPOE,
+ [772] = RTE_PTYPE_L2_ETHER_PPPOE,
+ /* LACP */
+ [773] = RTE_PTYPE_UNKNOWN,
+ /* [774] - [775] reserved */
+ /* IPv4 L3(NETWORK CPU) */
+ [776] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_IGMP,
+ /* EIGRP */
+ [777] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* PIM */
+ [778] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [779] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ [780] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ [781] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ /* [782] - [783] reserved */
+ /* IPv6 L3(NETWORK CPU) */
+ [784] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_IGMP,
+ /* EIGRP */
+ [785] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* PIM */
+ [786] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [787] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ [788] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ [789] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP | RTE_PTYPE_TUNNEL_L2TP,
+ /* [790] - [791] reserved */
+ /* IPv4 L4(NETWORK CPU) */
+ [792] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [793] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [794] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [795] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [796] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [797] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [798] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [799] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [800] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [801] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ /* [802] - [807] reserved */
+ /* IPv6 L4(NETWORK CPU) */
+ [808] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [809] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP,
+ [810] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [811] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [812] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [813] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [814] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [815] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [816] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ [817] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP,
+ /* [818] - [819] reserved */
+ /* IPv6 -> MAC */
+ [820] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPv6 -> MAC -> IPv4*/
+ [821] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [822] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [823] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [824] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [825] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [826] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPv6 -> MAC -> IPv4*/
+ [827] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [828] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [829] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [830] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [831] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [832] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* [833] - [834] reserved */
+ /* IPv6 -> MAC/VLAN */
+ [835] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPv6 -> MAC/VLAN -> IPv4 */
+ [836] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [837] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [838] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [839] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [840] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [841] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ /* IPv6 -> MAC/VLAN -> IPv6 */
+ [842] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [843] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [844] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [845] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [846] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+ [847] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> PAY */
+ [878] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> IPv4 */
+ [877] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [876] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [879] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [880] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [875] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [874] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> IPv6 */
+ [871] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [870] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [872] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [873] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [869] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [868] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> PAY */
+ [891] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> IPv4 */
+ [890] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [889] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [892] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [893] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [888] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [887] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> IPv6 */
+ [884] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [883] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [885] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [886] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [882] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [881] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> GRE -> PAY */
+ [904] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+ /* IPv6 -> UDP -> GRE -> IPv4 */
+ [903] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [902] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [905] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [906] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [901] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [900] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv6 -> UDP -> GRE -> IPv6 */
+ [897] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [896] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [898] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [899] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [895] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [894] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> GRE -> PAY */
+ [917] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT,
+ /* IPv4 -> UDP -> GRE -> IPv4 */
+ [916] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [915] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [918] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [919] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [914] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [913] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> GRE -> IPv6 */
+ [910] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [909] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [911] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [912] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [908] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [907] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MACVLAN -> PAY */
+ [930] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MACVLAN -> IPv4 */
+ [929] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [928] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [931] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [932] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [927] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [926] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MACVLAN -> IPv6 */
+ [923] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [922] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [924] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [925] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [921] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [920] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MACVLAN -> PAY */
+ [943] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MACVLAN -> IPv4 */
+ [942] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [941] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [944] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [945] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [940] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [939] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MACVLAN -> IPv6 */
+ [936] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [935] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [937] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [938] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [934] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [933] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 > UDP -> GRE -> MACVLAN -> PAY */
+ [956] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+ /* IPv6 -> UDP -> GRE -> MACVLAN -> IPv4 */
+ [955] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [954] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [957] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [958] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [953] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [952] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv6 -> UDP -> GRE -> MACVLAN -> IPv6 */
+ [949] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [948] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [950] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [951] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [947] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [946] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> GRE -> MACVLAN -> PAY */
+ [969] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN,
+ /* IPv4 -> UDP -> GRE -> MACVLAN -> IPv4 */
+ [968] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [967] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [970] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [971] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [966] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [965] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> GRE -> MACVLAN -> IPv6 */
+ [962] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [961] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [963] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [964] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [960] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [959] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER_VLAN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MAC -> PAY */
+ [982] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MAC -> IPv4 */
+ [981] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [980] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [983] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [984] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [979] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [978] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 -> UDP -> VXLAN/GENEVE -> MAC -> IPv6 */
+ [975] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [974] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [976] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [977] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [973] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [972] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MAC -> PAY */
+ [995] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MAC -> IPv4 */
+ [994] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [993] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [996] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [997] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [992] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [991] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> VXLAN/GENEVE -> MAC -> IPv6 */
+ [988] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [987] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [989] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [990] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [986] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [985] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv6 > UDP -> GRE -> MAC -> PAY */
+ [1008] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+ /* IPv6 -> UDP -> GRE -> MAC -> IPv4 */
+ [1007] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [1006] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [1009] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [1010] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [1005] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [1004] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv6 -> UDP -> GRE -> MAC -> IPv6 */
+ [1001] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [1000] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [1002] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [1003] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [999] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [998] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+
+ /* IPv4 -> UDP -> GRE -> MAC -> PAY */
+ [1021] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER,
+ /* IPv4 -> UDP -> GRE -> MAC -> IPv4 */
+ [1020] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [1019] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [1022] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [1023] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [1018] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [1017] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+ /* IPv4 -> UDP -> GRE -> MAC -> IPv6 */
+ [1014] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG,
+ [1013] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ [1015] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP,
+ [1016] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP,
+ [1012] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_SCTP,
+ [1011] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_ICMP,
+};
+const uint32_t *
+sxe2_dev_supported_ptypes_get(struct rte_eth_dev *dev, size_t *no_of_elements)
+{
+ const uint32_t *ret = NULL;
+
+ static const uint32_t ptypes[] = {
+ RTE_PTYPE_L2_ETHER,
+ RTE_PTYPE_L2_ETHER_TIMESYNC,
+ RTE_PTYPE_L2_ETHER_LLDP,
+ RTE_PTYPE_L2_ETHER_ARP,
+ RTE_PTYPE_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_L4_FRAG,
+ RTE_PTYPE_L4_ICMP,
+ RTE_PTYPE_L4_NONFRAG,
+ RTE_PTYPE_L4_SCTP,
+ RTE_PTYPE_L4_TCP,
+ RTE_PTYPE_L4_UDP,
+ RTE_PTYPE_TUNNEL_GRENAT,
+ RTE_PTYPE_TUNNEL_IP,
+ RTE_PTYPE_INNER_L2_ETHER,
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN,
+ RTE_PTYPE_INNER_L4_FRAG,
+ RTE_PTYPE_INNER_L4_ICMP,
+ RTE_PTYPE_INNER_L4_NONFRAG,
+ RTE_PTYPE_INNER_L4_SCTP,
+ RTE_PTYPE_INNER_L4_TCP,
+ RTE_PTYPE_INNER_L4_UDP,
+ RTE_PTYPE_UNKNOWN
+ };
+
+ if (dev->rx_pkt_burst != NULL) {
+ *no_of_elements = RTE_DIM(ptypes);
+ ret = ptypes;
+ } else {
+ ret = NULL;
+ }
+
+ return ret;
+}
diff --git a/drivers/net/sxe2/sxe2_txrx.h b/drivers/net/sxe2/sxe2_txrx.h
index 6f6ff3e3d1..1fa8f34bb2 100644
--- a/drivers/net/sxe2/sxe2_txrx.h
+++ b/drivers/net/sxe2/sxe2_txrx.h
@@ -23,4 +23,9 @@ int32_t sxe2_tx_burst_mode_get(struct rte_eth_dev *dev,
int32_t sxe2_rx_burst_mode_get(struct rte_eth_dev *dev,
__rte_unused uint16_t queue_id, struct rte_eth_burst_mode *mode);
+extern const uint32_t sxe2_ptype_tbl[];
+
+const uint32_t *sxe2_dev_supported_ptypes_get(struct rte_eth_dev *dev,
+ size_t *no_of_elements);
+
#endif /* SXE2_TXRX_H */
diff --git a/drivers/net/sxe2/sxe2_txrx_poll.c b/drivers/net/sxe2/sxe2_txrx_poll.c
index 947a5247ed..241e47e02c 100644
--- a/drivers/net/sxe2/sxe2_txrx_poll.c
+++ b/drivers/net/sxe2/sxe2_txrx_poll.c
@@ -664,13 +664,12 @@ 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)
{
- uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
uint64_t qword1;
uint64_t 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)];
+ mbuf->packet_type = sxe2_ptype_tbl[SXE2_RX_DESC_PTYPE_VAL_GET(qword1)];
pkt_flags = sxe2_rx_desc_error_para(rxq, rxd);
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_common.h b/drivers/net/sxe2/sxe2_txrx_vec_common.h
index cc74f6e582..f004970949 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec_common.h
+++ b/drivers/net/sxe2/sxe2_txrx_vec_common.h
@@ -12,6 +12,7 @@
#include "sxe2_rx.h"
#include "sxe2_queue.h"
#include "sxe2_tx.h"
+#include "sxe2_txrx.h"
#include "sxe2_vsi.h"
#include "sxe2_ethdev.h"
#define SXE2_RX_NUM_PER_LOOP_SSE 4
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_sse.c b/drivers/net/sxe2/sxe2_txrx_vec_sse.c
index 182a7dfc17..c3e8a2983b 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec_sse.c
+++ b/drivers/net/sxe2/sxe2_txrx_vec_sse.c
@@ -338,7 +338,6 @@ sxe2_rx_pkts_common_vec_sse(struct sxe2_rx_queue *rxq,
uint32_t i;
uint32_t bit_num;
uint16_t done_num = 0;
- const uint32_t *ptype_tbl = rxq->vsi->adapter->ptype_tbl;
const __m128i crc_adjust =
_mm_set_epi16(0, 0, 0,
-rxq->crc_len,
@@ -461,10 +460,10 @@ sxe2_rx_pkts_common_vec_sse(struct sxe2_rx_queue *rxq,
mbuf_arr[1]);
_mm_storeu_si128((void *)&rx_pkts[i]->rx_descriptor_fields1,
mbuf_arr[0]);
- rx_pkts[i + 3]->packet_type = ptype_tbl[_mm_extract_epi16(ptype_all, 3)];
- rx_pkts[i + 2]->packet_type = ptype_tbl[_mm_extract_epi16(ptype_all, 7)];
- rx_pkts[i + 1]->packet_type = ptype_tbl[_mm_extract_epi16(ptype_all, 1)];
- rx_pkts[i]->packet_type = ptype_tbl[_mm_extract_epi16(ptype_all, 5)];
+ rx_pkts[i + 3]->packet_type = sxe2_ptype_tbl[_mm_extract_epi16(ptype_all, 3)];
+ rx_pkts[i + 2]->packet_type = sxe2_ptype_tbl[_mm_extract_epi16(ptype_all, 7)];
+ rx_pkts[i + 1]->packet_type = sxe2_ptype_tbl[_mm_extract_epi16(ptype_all, 1)];
+ rx_pkts[i]->packet_type = sxe2_ptype_tbl[_mm_extract_epi16(ptype_all, 5)];
bit_num = rte_popcount64(_mm_cvtsi128_si64(staterr));
done_num += bit_num;
if (likely(bit_num != SXE2_RX_NUM_PER_LOOP_SSE))
--
2.52.0
^ permalink raw reply related
* [PATCH v5 01/23] net/sxe2: remove software statistics devargs
From: liujie5 @ 2026-06-22 9:23 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260622092324.3091185-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
Remove the optional drv-sw-stats device argument and make software
statistics always-on. Per-queue software statistics are point-in-time
measurements used for accumulation at queue stop/dump, so atomic
operations with rte_memory_order_relaxed add unnecessary overhead
without correctness benefit.
Also rename high_performance_mode field to no_sched_mode to match
the devargs string definition.
Changes:
- Remove sw_stats_en field from struct sxe2_devargs
- Remove RTE_ATOMIC qualifiers from sxe2_rxq_sw_stats fields
- Replace rte_atomic_fetch_add_explicit(relaxed) with plain addition
- Replace rte_atomic_store/load_explicit(relaxed) with plain assignment
- Remove sw_stats_en conditional checks in Rx fast path
- Always pass umbcast_flags to vec Rx functions
- Remove unused #include <rte_stdatomic.h>
- Rename high_performance_mode → no_sched_mode in devargs struct
- Fix int → int32_t for return type in sxe2_parse_eth_devargs
Signed-off-by: Jie Liu <liujie5@linkdatatechnology.com>
---
drivers/net/sxe2/sxe2_ethdev.c | 2 +-
drivers/net/sxe2/sxe2_ethdev.h | 3 +-
drivers/net/sxe2/sxe2_queue.h | 15 ++++---
drivers/net/sxe2/sxe2_rx.c | 55 +++++++------------------
drivers/net/sxe2/sxe2_txrx_poll.c | 38 ++++++-----------
drivers/net/sxe2/sxe2_txrx_vec_common.h | 52 ++++++++++-------------
drivers/net/sxe2/sxe2_txrx_vec_sse.c | 29 +------------
7 files changed, 61 insertions(+), 133 deletions(-)
diff --git a/drivers/net/sxe2/sxe2_ethdev.c b/drivers/net/sxe2/sxe2_ethdev.c
index b6cc8703a7..066e1faf7e 100644
--- a/drivers/net/sxe2/sxe2_ethdev.c
+++ b/drivers/net/sxe2/sxe2_ethdev.c
@@ -891,7 +891,7 @@ static int32_t sxe2_eth_pmd_probe_pf(struct sxe2_common_device *cdev,
static int32_t sxe2_parse_eth_devargs(struct rte_device *dev,
struct rte_eth_devargs *eth_da)
{
- int ret = 0;
+ int32_t ret = 0;
if (dev->devargs == NULL)
return 0;
diff --git a/drivers/net/sxe2/sxe2_ethdev.h b/drivers/net/sxe2/sxe2_ethdev.h
index a3706945e8..8015d9a064 100644
--- a/drivers/net/sxe2/sxe2_ethdev.h
+++ b/drivers/net/sxe2/sxe2_ethdev.h
@@ -130,9 +130,8 @@ struct sxe2_devargs {
uint8_t flow_dup_pattern_mode;
uint8_t func_flow_direct_en;
uint8_t fnav_stat_type;
- uint8_t high_performance_mode;
+ uint8_t no_sched_mode;
uint8_t sched_layer_mode;
- uint8_t sw_stats_en;
uint8_t rx_low_latency;
};
diff --git a/drivers/net/sxe2/sxe2_queue.h b/drivers/net/sxe2/sxe2_queue.h
index adb4be1214..a300b66771 100644
--- a/drivers/net/sxe2/sxe2_queue.h
+++ b/drivers/net/sxe2/sxe2_queue.h
@@ -7,7 +7,6 @@
#include <rte_ethdev.h>
#include <rte_io.h>
-#include <rte_stdatomic.h>
#include <ethdev_driver.h>
#include "sxe2_drv_cmd.h"
@@ -123,13 +122,13 @@ struct sxe2_rxq_stats {
};
struct sxe2_rxq_sw_stats {
- RTE_ATOMIC(uint64_t)pkts;
- RTE_ATOMIC(uint64_t)bytes;
- RTE_ATOMIC(uint64_t)drop_pkts;
- RTE_ATOMIC(uint64_t)drop_bytes;
- RTE_ATOMIC(uint64_t)unicast_pkts;
- RTE_ATOMIC(uint64_t)multicast_pkts;
- RTE_ATOMIC(uint64_t)broadcast_pkts;
+ uint64_t pkts;
+ uint64_t bytes;
+ uint64_t drop_pkts;
+ uint64_t drop_bytes;
+ uint64_t unicast_pkts;
+ uint64_t multicast_pkts;
+ uint64_t broadcast_pkts;
};
struct sxe2_rx_queue {
diff --git a/drivers/net/sxe2/sxe2_rx.c b/drivers/net/sxe2/sxe2_rx.c
index 28832d5f71..543d825166 100644
--- a/drivers/net/sxe2/sxe2_rx.c
+++ b/drivers/net/sxe2/sxe2_rx.c
@@ -479,20 +479,13 @@ int32_t __rte_cold sxe2_rxqs_all_start(struct rte_eth_dev *dev)
goto l_free_started_queue;
}
- rte_atomic_store_explicit(&rxq->sw_stats.pkts, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.bytes, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.drop_pkts, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.drop_bytes, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.unicast_pkts, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.broadcast_pkts, 0,
- rte_memory_order_relaxed);
- rte_atomic_store_explicit(&rxq->sw_stats.multicast_pkts, 0,
- rte_memory_order_relaxed);
+ rxq->sw_stats.pkts = 0;
+ rxq->sw_stats.bytes = 0;
+ rxq->sw_stats.drop_pkts = 0;
+ rxq->sw_stats.drop_bytes = 0;
+ rxq->sw_stats.unicast_pkts = 0;
+ rxq->sw_stats.broadcast_pkts = 0;
+ rxq->sw_stats.multicast_pkts = 0;
}
ret = 0;
goto l_end;
@@ -524,31 +517,15 @@ void __rte_cold sxe2_rxqs_all_stop(struct rte_eth_dev *dev)
rxq = dev->data->rx_queues[nb_rxq];
if (rxq) {
- sw_stats_prev->ipackets +=
- rte_atomic_load_explicit(&rxq->sw_stats.pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->ierrors +=
- rte_atomic_load_explicit(&rxq->sw_stats.drop_pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->ibytes +=
- rte_atomic_load_explicit(&rxq->sw_stats.bytes,
- rte_memory_order_relaxed);
-
- sw_stats_prev->rx_sw_unicast_packets +=
- rte_atomic_load_explicit(&rxq->sw_stats.unicast_pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->rx_sw_broadcast_packets +=
- rte_atomic_load_explicit(&rxq->sw_stats.broadcast_pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->rx_sw_multicast_packets +=
- rte_atomic_load_explicit(&rxq->sw_stats.multicast_pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->rx_sw_drop_packets +=
- rte_atomic_load_explicit(&rxq->sw_stats.drop_pkts,
- rte_memory_order_relaxed);
- sw_stats_prev->rx_sw_drop_bytes +=
- rte_atomic_load_explicit(&rxq->sw_stats.drop_bytes,
- rte_memory_order_relaxed);
+ sw_stats_prev->ipackets += rxq->sw_stats.pkts;
+ sw_stats_prev->ierrors += rxq->sw_stats.drop_pkts;
+ sw_stats_prev->ibytes += rxq->sw_stats.bytes;
+
+ sw_stats_prev->rx_sw_unicast_packets += rxq->sw_stats.unicast_pkts;
+ sw_stats_prev->rx_sw_broadcast_packets += rxq->sw_stats.broadcast_pkts;
+ sw_stats_prev->rx_sw_multicast_packets += rxq->sw_stats.multicast_pkts;
+ sw_stats_prev->rx_sw_drop_packets += rxq->sw_stats.drop_pkts;
+ sw_stats_prev->rx_sw_drop_bytes += rxq->sw_stats.drop_bytes;
}
}
}
diff --git a/drivers/net/sxe2/sxe2_txrx_poll.c b/drivers/net/sxe2/sxe2_txrx_poll.c
index b9d34afb31..947a5247ed 100644
--- a/drivers/net/sxe2/sxe2_txrx_poll.c
+++ b/drivers/net/sxe2/sxe2_txrx_poll.c
@@ -682,23 +682,17 @@ sxe2_rx_sw_stats_update(struct sxe2_rx_queue *rxq, struct rte_mbuf *mbuf,
union sxe2_rx_desc *rxd)
{
uint64_t 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);
+ rxq->sw_stats.pkts += 1;
+ rxq->sw_stats.bytes += mbuf->pkt_len + RTE_ETHER_CRC_LEN;
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);
+ rxq->sw_stats.unicast_pkts += 1;
break;
case SXE2_RX_DESC_STATUS_MULTICAST:
- rte_atomic_fetch_add_explicit(&rxq->sw_stats.multicast_pkts, 1,
- rte_memory_order_relaxed);
+ rxq->sw_stats.multicast_pkts += 1;
break;
case SXE2_RX_DESC_STATUS_BROADCAST:
- rte_atomic_fetch_add_explicit(&rxq->sw_stats.broadcast_pkts, 1,
- rte_memory_order_relaxed);
+ rxq->sw_stats.broadcast_pkts += 1;
break;
default:
break;
@@ -787,11 +781,9 @@ uint16_t sxe2_rx_pkts_scattered(void *rx_queue, struct rte_mbuf **rx_pkts, uint1
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);
+ rxq->sw_stats.drop_pkts += 1;
+ rxq->sw_stats.drop_bytes +=
+ first_seg->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN;
rte_pktmbuf_free(first_seg);
first_seg = NULL;
continue;
@@ -822,8 +814,7 @@ uint16_t sxe2_rx_pkts_scattered(void *rx_queue, struct rte_mbuf **rx_pkts, uint1
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);
+ sxe2_rx_sw_stats_update(rxq, first_seg, &desc_tmp);
rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr, first_seg->data_off));
@@ -990,11 +981,9 @@ uint16_t sxe2_rx_pkts_scattered_split(void *rx_queue, struct rte_mbuf **rx_pkts,
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);
+ rxq->sw_stats.drop_pkts += 1;
+ rxq->sw_stats.drop_bytes +=
+ first_seg->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN;
rte_pktmbuf_free(first_seg);
first_seg = NULL;
continue;
@@ -1023,8 +1012,7 @@ uint16_t sxe2_rx_pkts_scattered_split(void *rx_queue, struct rte_mbuf **rx_pkts,
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);
+ sxe2_rx_sw_stats_update(rxq, first_seg, &desc_tmp);
rte_prefetch0(RTE_PTR_ADD(first_seg->buf_addr, first_seg->data_off));
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_common.h b/drivers/net/sxe2/sxe2_txrx_vec_common.h
index 6b1649c390..cc74f6e582 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec_common.h
+++ b/drivers/net/sxe2/sxe2_txrx_vec_common.h
@@ -130,27 +130,20 @@ sxe2_tx_desc_fill_offloads(struct rte_mbuf *mbuf, uint64_t *desc_qw1)
static inline void sxe2_vf_rx_vec_sw_stats_cnt(struct sxe2_rx_queue *rxq,
struct rte_mbuf *mbuf, uint8_t umbcast_flag)
{
- if (rxq->vsi->adapter->devargs.sw_stats_en) {
- 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_UMBCAST_FLAGS_VAL_GET(umbcast_flag)) {
- 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_MULTICAST:
- rte_atomic_fetch_add_explicit(&rxq->sw_stats.multicast_pkts, 1,
- rte_memory_order_relaxed);
- break;
- case SXE2_RX_DESC_STATUS_BROADCAST:
- rte_atomic_fetch_add_explicit(&rxq->sw_stats.broadcast_pkts, 1,
- rte_memory_order_relaxed);
- break;
- default:
- break;
- }
+ rxq->sw_stats.pkts += 1;
+ rxq->sw_stats.bytes += mbuf->pkt_len + RTE_ETHER_CRC_LEN;
+ switch (SXE2_RX_UMBCAST_FLAGS_VAL_GET(umbcast_flag)) {
+ case SXE2_RX_DESC_STATUS_UNICAST:
+ rxq->sw_stats.unicast_pkts += 1;
+ break;
+ case SXE2_RX_DESC_STATUS_MULTICAST:
+ rxq->sw_stats.multicast_pkts += 1;
+ break;
+ case SXE2_RX_DESC_STATUS_BROADCAST:
+ rxq->sw_stats.broadcast_pkts += 1;
+ break;
+ default:
+ break;
}
}
@@ -196,11 +189,9 @@ sxe2_rx_pkts_refactor(struct sxe2_rx_queue *rxq,
} else if (split_rxe_flags[buf_idx] & SXE2_RX_DESC_STATUS_EOP_MASK) {
continue;
} else {
- 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);
+ rxq->sw_stats.drop_pkts += 1;
+ rxq->sw_stats.drop_bytes +=
+ first_seg->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN;
rte_pktmbuf_free(first_seg);
first_seg = NULL;
last_seg = NULL;
@@ -218,11 +209,10 @@ sxe2_rx_pkts_refactor(struct sxe2_rx_queue *rxq,
mbuf_bufs[buf_idx]->data_len += rxq->crc_len;
mbuf_bufs[buf_idx]->pkt_len += rxq->crc_len;
} else {
- 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,
- mbuf_bufs[buf_idx]->pkt_len - rxq->crc_len + RTE_ETHER_CRC_LEN,
- rte_memory_order_relaxed);
+ rxq->sw_stats.drop_pkts += 1;
+ rxq->sw_stats.drop_bytes +=
+ mbuf_bufs[buf_idx]->pkt_len - rxq->crc_len +
+ RTE_ETHER_CRC_LEN;
rte_pktmbuf_free_seg(mbuf_bufs[buf_idx]);
continue;
}
diff --git a/drivers/net/sxe2/sxe2_txrx_vec_sse.c b/drivers/net/sxe2/sxe2_txrx_vec_sse.c
index f6e3f45937..182a7dfc17 100644
--- a/drivers/net/sxe2/sxe2_txrx_vec_sse.c
+++ b/drivers/net/sxe2/sxe2_txrx_vec_sse.c
@@ -483,41 +483,16 @@ static __rte_always_inline uint16_t
sxe2_rx_pkts_scattered_batch_vec_sse(struct sxe2_rx_queue *rxq,
struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
{
- const uint64_t *split_rxe_flags64;
uint8_t split_rxe_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
uint8_t umbcast_flags[SXE2_RX_PKTS_BURST_BATCH_NUM_VEC] = {0};
uint16_t rx_done_num;
uint16_t rx_pkt_done_num;
rx_pkt_done_num = 0;
- if (rxq->vsi->adapter->devargs.sw_stats_en) {
- rx_done_num = sxe2_rx_pkts_common_vec_sse(rxq, rx_pkts,
- nb_pkts, split_rxe_flags, umbcast_flags);
- } else {
- rx_done_num = sxe2_rx_pkts_common_vec_sse(rxq, rx_pkts,
- nb_pkts, split_rxe_flags, NULL);
- }
+ rx_done_num = sxe2_rx_pkts_common_vec_sse(rxq, rx_pkts,
+ nb_pkts, split_rxe_flags, umbcast_flags);
if (rx_done_num == 0)
goto l_end;
- if (!rxq->vsi->adapter->devargs.sw_stats_en) {
- split_rxe_flags64 = (uint64_t *)split_rxe_flags;
- if (rxq->pkt_first_seg == NULL &&
- split_rxe_flags64[0] == 0 &&
- split_rxe_flags64[1] == 0 &&
- split_rxe_flags64[2] == 0 &&
- split_rxe_flags64[3] == 0) {
- rx_pkt_done_num = rx_done_num;
- goto l_end;
- }
- if (rxq->pkt_first_seg == NULL) {
- while (rx_pkt_done_num < rx_done_num &&
- split_rxe_flags[rx_pkt_done_num] == 0)
- rx_pkt_done_num++;
- if (rx_pkt_done_num == rx_done_num)
- goto l_end;
- rxq->pkt_first_seg = rx_pkts[rx_pkt_done_num];
- }
- }
rx_pkt_done_num += sxe2_rx_pkts_refactor(rxq, &rx_pkts[rx_pkt_done_num],
rx_done_num - rx_pkt_done_num, &split_rxe_flags[rx_pkt_done_num],
&umbcast_flags[rx_pkt_done_num]);
--
2.52.0
^ permalink raw reply related
* [PATCH v5 00/23] net/sxe2: added Linkdata sxe2 ethernet driver
From: liujie5 @ 2026-06-22 9:23 UTC (permalink / raw)
To: stephen; +Cc: dev, Jie Liu
In-Reply-To: <20260619081304.1546974-1-liujie5@linkdatatechnology.com>
From: Jie Liu <liujie5@linkdatatechnology.com>
This patch set implements core functionality for the SXE2 PMD,
including basic driver framework, data path setup, and advanced
offload features (VLAN, RSS,TM, PTP etc.).
V5:
Refactored sxe2_ptype_tbl from adapter-indirection pattern (adapter->ptype_tbl[])
to extern const direct-access pattern, matching txgbe PMD convention
All vector/SIMD Rx paths (SSE, AVX2, AVX512, NEON) index sxe2_ptype_tbl[] directly without local pointer indirection
Jie Liu (23):
net/sxe2: remove software statistics devargs
net/sxe2: add Rx framework and packet types callback
net/sxe2: support AVX512 vectorized path for Rx and Tx
net/sxe2: add AVX2 vector data path for Rx and Tx
net/sxe2: add link update callback
net/sxe2: support L2 filtering and MAC config
drivers: support RSS feature
net/sxe2: support TM hierarchy and shaping
net/sxe2: support IPsec inline protocol offload
net/sxe2: support statistics and multi-process
drivers: interrupt handling
net/sxe2: add NEON vec Rx/Tx burst functions
drivers: add support for VF representors
net/sxe2: add support for custom UDP tunnel ports
net/sxe2: support firmware version reading
net/sxe2: implement get monitor address
common/sxe2: add shared SFP module definitions
net/sxe2: support SFP module info and EEPROM access
net/sxe2: implement private dump info
net/sxe2: add mbuf validation in Tx debug mode
common/sxe2: add callback for memory event handling
net/sxe2: add private devargs parsing
net/sxe2: update sxe2 feature matrix docs
doc/guides/nics/features/sxe2.ini | 56 +
doc/guides/nics/sxe2.rst | 164 ++
drivers/common/sxe2/sxe2_common.c | 156 ++
drivers/common/sxe2/sxe2_common.h | 4 +
drivers/common/sxe2/sxe2_flow_public.h | 633 +++++++
drivers/common/sxe2/sxe2_ioctl_chnl.c | 178 +-
drivers/common/sxe2/sxe2_ioctl_chnl_func.h | 18 +
drivers/common/sxe2/sxe2_msg.h | 118 ++
drivers/net/sxe2/meson.build | 52 +
drivers/net/sxe2/sxe2_cmd_chnl.c | 1587 +++++++++++++++-
drivers/net/sxe2/sxe2_cmd_chnl.h | 139 ++
drivers/net/sxe2/sxe2_drv_cmd.h | 523 +++++-
drivers/net/sxe2/sxe2_dump.c | 302 +++
drivers/net/sxe2/sxe2_dump.h | 12 +
drivers/net/sxe2/sxe2_ethdev.c | 1511 ++++++++++++++-
drivers/net/sxe2/sxe2_ethdev.h | 111 +-
drivers/net/sxe2/sxe2_ethdev_repr.c | 609 ++++++
drivers/net/sxe2/sxe2_ethdev_repr.h | 32 +
drivers/net/sxe2/sxe2_filter.c | 895 +++++++++
drivers/net/sxe2/sxe2_filter.h | 100 +
drivers/net/sxe2/sxe2_flow.c | 1394 ++++++++++++++
drivers/net/sxe2/sxe2_flow.h | 30 +
drivers/net/sxe2/sxe2_flow_define.h | 144 ++
drivers/net/sxe2/sxe2_flow_parse_action.c | 1182 ++++++++++++
drivers/net/sxe2/sxe2_flow_parse_action.h | 23 +
drivers/net/sxe2/sxe2_flow_parse_engine.c | 106 ++
drivers/net/sxe2/sxe2_flow_parse_engine.h | 13 +
drivers/net/sxe2/sxe2_flow_parse_pattern.c | 1935 +++++++++++++++++++
drivers/net/sxe2/sxe2_flow_parse_pattern.h | 46 +
drivers/net/sxe2/sxe2_ipsec.c | 1565 ++++++++++++++++
drivers/net/sxe2/sxe2_ipsec.h | 254 +++
drivers/net/sxe2/sxe2_irq.c | 1026 ++++++++++
drivers/net/sxe2/sxe2_irq.h | 25 +
drivers/net/sxe2/sxe2_mac.c | 530 ++++++
drivers/net/sxe2/sxe2_mac.h | 84 +
drivers/net/sxe2/sxe2_mp.c | 414 +++++
drivers/net/sxe2/sxe2_mp.h | 67 +
drivers/net/sxe2/sxe2_queue.c | 17 +-
drivers/net/sxe2/sxe2_queue.h | 15 +-
drivers/net/sxe2/sxe2_rss.c | 584 ++++++
drivers/net/sxe2/sxe2_rss.h | 81 +
drivers/net/sxe2/sxe2_rx.c | 93 +-
drivers/net/sxe2/sxe2_rx.h | 2 +
drivers/net/sxe2/sxe2_security.c | 335 ++++
drivers/net/sxe2/sxe2_security.h | 77 +
drivers/net/sxe2/sxe2_stats.c | 586 ++++++
drivers/net/sxe2/sxe2_stats.h | 39 +
drivers/net/sxe2/sxe2_switchdev.c | 332 ++++
drivers/net/sxe2/sxe2_switchdev.h | 33 +
drivers/net/sxe2/sxe2_tm.c | 1151 ++++++++++++
drivers/net/sxe2/sxe2_tm.h | 76 +
drivers/net/sxe2/sxe2_tx.c | 7 +
drivers/net/sxe2/sxe2_txrx.c | 1958 +++++++++++++++++++-
drivers/net/sxe2/sxe2_txrx.h | 8 +
drivers/net/sxe2/sxe2_txrx_check_mbuf.c | 595 ++++++
drivers/net/sxe2/sxe2_txrx_check_mbuf.h | 38 +
drivers/net/sxe2/sxe2_txrx_poll.c | 284 ++-
drivers/net/sxe2/sxe2_txrx_vec.c | 46 +-
drivers/net/sxe2/sxe2_txrx_vec.h | 38 +-
drivers/net/sxe2/sxe2_txrx_vec_avx2.c | 747 ++++++++
drivers/net/sxe2/sxe2_txrx_vec_avx512.c | 867 +++++++++
drivers/net/sxe2/sxe2_txrx_vec_common.h | 54 +-
drivers/net/sxe2/sxe2_txrx_vec_neon.c | 689 +++++++
drivers/net/sxe2/sxe2_txrx_vec_sse.c | 38 +-
drivers/net/sxe2/sxe2_vsi.c | 146 ++
drivers/net/sxe2/sxe2_vsi.h | 12 +-
drivers/net/sxe2/sxe2vf_regs.h | 85 +
67 files changed, 24798 insertions(+), 273 deletions(-)
create mode 100644 drivers/common/sxe2/sxe2_flow_public.h
create mode 100644 drivers/common/sxe2/sxe2_msg.h
create mode 100644 drivers/net/sxe2/sxe2_dump.c
create mode 100644 drivers/net/sxe2/sxe2_dump.h
create mode 100644 drivers/net/sxe2/sxe2_ethdev_repr.c
create mode 100644 drivers/net/sxe2/sxe2_ethdev_repr.h
create mode 100644 drivers/net/sxe2/sxe2_filter.c
create mode 100644 drivers/net/sxe2/sxe2_filter.h
create mode 100644 drivers/net/sxe2/sxe2_flow.c
create mode 100644 drivers/net/sxe2/sxe2_flow.h
create mode 100644 drivers/net/sxe2/sxe2_flow_define.h
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_action.c
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_action.h
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_engine.c
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_engine.h
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_pattern.c
create mode 100644 drivers/net/sxe2/sxe2_flow_parse_pattern.h
create mode 100644 drivers/net/sxe2/sxe2_ipsec.c
create mode 100644 drivers/net/sxe2/sxe2_ipsec.h
create mode 100644 drivers/net/sxe2/sxe2_irq.c
create mode 100644 drivers/net/sxe2/sxe2_mac.c
create mode 100644 drivers/net/sxe2/sxe2_mac.h
create mode 100644 drivers/net/sxe2/sxe2_mp.c
create mode 100644 drivers/net/sxe2/sxe2_mp.h
create mode 100644 drivers/net/sxe2/sxe2_rss.c
create mode 100644 drivers/net/sxe2/sxe2_rss.h
create mode 100644 drivers/net/sxe2/sxe2_security.c
create mode 100644 drivers/net/sxe2/sxe2_security.h
create mode 100644 drivers/net/sxe2/sxe2_stats.c
create mode 100644 drivers/net/sxe2/sxe2_stats.h
create mode 100644 drivers/net/sxe2/sxe2_switchdev.c
create mode 100644 drivers/net/sxe2/sxe2_switchdev.h
create mode 100644 drivers/net/sxe2/sxe2_tm.c
create mode 100644 drivers/net/sxe2/sxe2_tm.h
create mode 100644 drivers/net/sxe2/sxe2_txrx_check_mbuf.c
create mode 100644 drivers/net/sxe2/sxe2_txrx_check_mbuf.h
create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx2.c
create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_avx512.c
create mode 100644 drivers/net/sxe2/sxe2_txrx_vec_neon.c
create mode 100644 drivers/net/sxe2/sxe2vf_regs.h
--
2.52.0
^ permalink raw reply
* Re: [PATCH v5 04/24] net/ena: replace use of rte_atomicNN
From: saeed bishara @ 2026-06-22 8:46 UTC (permalink / raw)
To: Stephen Hemminger
Cc: dev, Shai Brandes, Evgeny Schemeilin, Ron Beider, Amit Bernstein,
Wajeeh Atrash
In-Reply-To: <20260620023134.42877-5-stephen@networkplumber.org>
> * Do not use rte_atomic for statistics
> The DPDK PMD model is that statistics do not have to be exact
> in face of contention.
These are only error cases, so shouldn't have performance contention concerns.
^ permalink raw reply
* Re: [PATCH v1 0/5] prefix lcore role enum values
From: David Marchand @ 2026-06-22 8:18 UTC (permalink / raw)
To: lihuisong (C)
Cc: Stephen Hemminger, Morten Brørup, thomas, andrew.rybchenko,
dev, zhanjie9
In-Reply-To: <15b95ab5-af2e-40d2-8ea8-a5d14a52dfc0@huawei.com>
Hello all,
On Mon, 22 Jun 2026 at 03:23, lihuisong (C) <lihuisong@huawei.com> wrote:
> On 6/19/2026 10:03 AM, Stephen Hemminger wrote:
> > On Wed, 17 Jun 2026 13:48:37 +0200
> > Morten Brørup <mb@smartsharesystems.com> wrote:
> >
> >>> From: Huisong Li [mailto:lihuisong@huawei.com]
> >>> Sent: Wednesday, 17 June 2026 12.28
> >>>
> >>> Add the RTE_LCORE_ prefix to the lcore role enum values in
> >>> rte_lcore_role_t
> >>> to follow DPDK naming conventions.
> >>>
> >>> - ROLE_RTE -> RTE_LCORE_ROLE_RTE
> >>> - ROLE_OFF -> RTE_LCORE_ROLE_OFF
> >>> - ROLE_SERVICE -> RTE_LCORE_ROLE_SERVICE
> >>> - ROLE_NON_EAL -> RTE_LCORE_ROLE_NON_EAL
> >>>
> >>> Old names are kept as macros aliasing to the new names to preserve
> >>> backward compatibility.
> >>>
> >> Series-Acked-by: Morten Brørup <mb@smartsharesystems.com>
> >>
> > The problem with this patch it causes build failures now with abi diff.
> >
> > Example build log...
> >
> >
> > 2 functions with some indirect sub-type change:
> >
> >
> >
> >
> >
> > [C] 'function rte_lcore_role_t rte_eal_lcore_role(unsigned int)' at eal_common_lcore.c:74:1 has some indirect sub-type changes:
> >
> > return type changed:
> >
> > type size hasn't changed
> >
> > 4 enumerator deletions:
> >
> > 'rte_lcore_role_t::ROLE_RTE' value '0'
> >
> > 'rte_lcore_role_t::ROLE_OFF' value '1'
> >
> > 'rte_lcore_role_t::ROLE_SERVICE' value '2'
> >
> > 'rte_lcore_role_t::ROLE_NON_EAL' value '3'
> >
> > 4 enumerator insertions:
> >
> > 'rte_lcore_role_t::RTE_LCORE_ROLE_RTE' value '0'
> >
> > 'rte_lcore_role_t::RTE_LCORE_ROLE_OFF' value '1'
> >
> > 'rte_lcore_role_t::RTE_LCORE_ROLE_SERVICE' value '2'
> >
> > 'rte_lcore_role_t::RTE_LCORE_ROLE_NON_EAL' value '3'
> >
> >
> >
> >
> >
> > [C] 'function int rte_lcore_has_role(unsigned int, rte_lcore_role_t)' at eal_common_lcore.c:85:1 has some indirect sub-type changes:
> >
> > parameter 2 of type 'enum rte_lcore_role_t' has sub-type changes:
> >
> > enum type 'enum rte_lcore_role_t' changed at rte_lcore.h:33:1, as reported earlier
> >
> >
> >
> >
> >
> >
> >
> > Error: ABI issue reported for abidiff --suppr /home/runner/work/dpdk/dpdk/devtools/libabigail.abignore --no-added-syms --headers-dir1 reference/usr/local/include --headers-dir2 install/usr/local/include reference/usr/local/lib/librte_eal.so.26.1 install/usr/local/lib/librte_eal.so.26.2
> We just came back from the Dragon Boat Festival.
> I also received this ABI change warning. But I didn't have any good
> ideas yet.
> Thanks for helping to handle this.
> Sorry for the inconvenience.
There is nothing broken from a ABI pov.
This is a limitation in earlier versions of libabigail.
I can't reproduce with libabigail 2.9 (update in progress as I see
2.10 is available now).
I think it was solved in libabigail 2.8
(https://sourceware.org/git/?p=libabigail.git;a=commit;h=6f5f91564bdd).
If we want to go with the enum renaming before 26.11, bumping
libabigail to 2.10 in the CI is an option (latest upstream version,
and this is the version in f43 and f44).
I tried it in GHA:
https://github.com/david-marchand/dpdk/actions/runs/27937595115/job/82662953500
--
David Marchand
^ permalink raw reply
* Re: [PATCH v2 1/1] ml/cnxk: fix overwriting layer name during load
From: Jerin Jacob @ 2026-06-22 8:04 UTC (permalink / raw)
To: Srikanth Yalavarthi; +Cc: dev, jerinj
In-Reply-To: <20260609035251.912771-1-syalavarthi@marvell.com>
On Tue, Jun 9, 2026 at 9:31 AM Srikanth Yalavarthi
<syalavarthi@marvell.com> wrote:
>
> Layer name is initialized during metadata fetch and parsing
> stage and should not be overwritten during model load. Fix
> overwriting the layer name during layer load.
>
> Fixes: cc254869ae19 ("ml/cnxk: update model load/unload functions")
>
> Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
> ---
Applied to dpdk-next-net-mrvl/for-main. Thanks
^ permalink raw reply
* [PATCH] common/mlx5: add ConnectX-10 NVLink-C2C device ID
From: Raslan Darawsheh @ 2026-06-22 8:01 UTC (permalink / raw)
To: dev
Cc: Dariusz Sosnowski, Viacheslav Ovsiienko, Bing Zhao, Ori Kam,
Suanming Mou, Matan Azrad
This adds the ConnectX-10 NVLink-C2C device ID to the list of
NVIDIA devices that run the mlx5 drivers.
The device is still in development stage.
Signed-off-by: Raslan Darawsheh <rasland@nvidia.com>
---
drivers/common/mlx5/mlx5_common.h | 1 +
drivers/crypto/mlx5/mlx5_crypto.c | 4 ++++
drivers/net/mlx5/mlx5.c | 4 ++++
3 files changed, 9 insertions(+)
diff --git a/drivers/common/mlx5/mlx5_common.h b/drivers/common/mlx5/mlx5_common.h
index 3e66c9e6c8..3767020823 100644
--- a/drivers/common/mlx5/mlx5_common.h
+++ b/drivers/common/mlx5/mlx5_common.h
@@ -157,6 +157,7 @@ enum {
PCI_DEVICE_ID_MELLANOX_CONNECTX9 = 0x1025,
PCI_DEVICE_ID_MELLANOX_BLUEFIELD4 = 0xa2df,
PCI_DEVICE_ID_MELLANOX_CONNECTX10 = 0x1027,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX10C2C = 0x2101,
};
/* Maximum number of simultaneous unicast MAC addresses. */
diff --git a/drivers/crypto/mlx5/mlx5_crypto.c b/drivers/crypto/mlx5/mlx5_crypto.c
index dd0aabb6d7..c9aa858a54 100644
--- a/drivers/crypto/mlx5/mlx5_crypto.c
+++ b/drivers/crypto/mlx5/mlx5_crypto.c
@@ -499,6 +499,10 @@ static const struct rte_pci_id mlx5_crypto_pci_id_map[] = {
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
PCI_DEVICE_ID_MELLANOX_CONNECTX10)
},
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX10C2C)
+ },
{
.vendor_id = 0
}
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 61c26d1206..3fa38694e5 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -3936,6 +3936,10 @@ static const struct rte_pci_id mlx5_pci_id_map[] = {
RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
PCI_DEVICE_ID_MELLANOX_CONNECTX10)
},
+ {
+ RTE_PCI_DEVICE(PCI_VENDOR_ID_MELLANOX,
+ PCI_DEVICE_ID_MELLANOX_CONNECTX10C2C)
+ },
{
.vendor_id = 0
}
--
2.53.0
^ permalink raw reply related
* [v3] crypto/qat: require IPsec MB for HMAC precomputes
From: Emma Finn @ 2026-06-22 7:56 UTC (permalink / raw)
To: Kai Ji; +Cc: dev, Emma Finn
In-Reply-To: <20260619135330.1821985-1-emma.finn@intel.com>
IPsec MB library (v1.4.0+) is now required for HMAC precomputes as
OpenSSL 3.0 removed SHA*_Transform APIs. OpenSSL remains optional
for DOCSIS BPI cipher fallback via EVP API.
On x86: IPsec MB required, OpenSSL optional (DOCSIS fallback)
On ARM: IPsec MB required, OpenSSL required (DOCSIS support)
Signed-off-by: Emma Finn <emma.finn@intel.com>
---
v2:
* Fix resource leak in ossl_legacy_provider_load()
* Added release note
v3:
* Removed checks for openssl <= 3.0
---
doc/guides/cryptodevs/qat.rst | 28 +-
doc/guides/rel_notes/release_26_07.rst | 8 +
drivers/common/qat/meson.build | 56 ++--
drivers/crypto/qat/qat_sym_session.c | 448 ++-----------------------
4 files changed, 97 insertions(+), 443 deletions(-)
diff --git a/doc/guides/cryptodevs/qat.rst b/doc/guides/cryptodevs/qat.rst
index 0c2b85444e..4e60e8343c 100644
--- a/doc/guides/cryptodevs/qat.rst
+++ b/doc/guides/cryptodevs/qat.rst
@@ -352,15 +352,25 @@ To use this feature the user must set the devarg on process start as a device ad
-a 03:01.1,qat_sym_cipher_crc_enable=1
-Running QAT PMD with Intel IPsec MB library for symmetric precomputes function
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-The QAT PMD uses Intel IPsec MB library for partial hash calculation
-in symmetric precomputes function by default,
-the minimum required version of IPsec MB library is v1.4.
-If this version of IPsec is not met, it will fallback to use OpenSSL.
-ARM will always default to using OpenSSL
-as ARM IPsec MB does not support the necessary algorithms.
+Running QAT PMD with Intel IPsec MB library
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The QAT PMD requires IPsec MB library for HMAC partial hash calculation
+in symmetric precomputes function. OpenSSL 3.0+ removed the low-level SHA*_Transform APIs
+that were previously used for HMAC precomputes.
+
+**On x86 platforms:**
+
+* Intel IPsec MB library (v1.4.0+) is required for HMAC precomputes
+* OpenSSL (3.0+) is optional for DOCSIS BPI cipher fallback
+
+**On ARM platforms:**
+
+* ARM IPsec MB library from ``gitlab.arm.com/arm-reference-solutions/ipsec-mb``
+ is required for HMAC precomputes.
+* OpenSSL (3.0+) is required for DOCSIS BPI cipher algorithms. ARM IPsec MB does not
+ implement CFB-one-byte cipher modes needed for DOCSIS. Without OpenSSL, DOCSIS
+ algorithms will not be available on ARM.
Device and driver naming
diff --git a/doc/guides/rel_notes/release_26_07.rst b/doc/guides/rel_notes/release_26_07.rst
index 34809a4850..809ec19d66 100644
--- a/doc/guides/rel_notes/release_26_07.rst
+++ b/doc/guides/rel_notes/release_26_07.rst
@@ -155,6 +155,14 @@ New Features
Added AGENTS.md file for AI review
and supporting scripts to review patches and documentation.
+* **Updated QAT PMD dependency requirements.**
+
+ The QAT crypto PMD now requires IPsec MB library (v1.4.0+) for HMAC precomputes
+ on all platforms. OpenSSL 3.0+ is now optional and used only for DOCSIS BPI cipher
+ fallback. Previously, QAT could build with OpenSSL-only on x86.
+
+ On ARM, both IPsec MB and OpenSSL are required for full functionality.
+
Removed Items
-------------
diff --git a/drivers/common/qat/meson.build b/drivers/common/qat/meson.build
index 31e06f4376..969ff9e8ee 100644
--- a/drivers/common/qat/meson.build
+++ b/drivers/common/qat/meson.build
@@ -27,47 +27,61 @@ if disable_drivers.contains(qat_compress_path)
'Explicitly disabled via build config')
endif
-libcrypto = dependency('libcrypto', required: false, method: 'pkg-config')
+# IPsec MB is REQUIRED for HMAC precomputes (no OpenSSL 3.0 alternative)
+# OpenSSL is OPTIONAL for DOCSIS BPI cipher fallback
+IMB_required_ver = '1.4.0'
-if arch_subdir == 'arm'
- if libcrypto.found()
- ext_deps += libcrypto
- dpdk_conf.set('RTE_QAT_OPENSSL', true)
+# Only check IPsec MB if qat_crypto wasn't already disabled
+if qat_crypto
+ if arch_subdir == 'arm'
+ IMB_header = '#include<ipsec-mb.h>'
else
- qat_crypto = false
- dpdk_drvs_disabled += qat_crypto_path
- set_variable('drv_' + qat_crypto_path.underscorify() + '_disable_reason',
- 'missing dependency for Arm, libcrypto')
+ IMB_header = '#include<intel-ipsec-mb.h>'
endif
-else
- IMB_required_ver = '1.4.0'
- IMB_header = '#include<intel-ipsec-mb.h>'
+
+ # Check for IPsec MB library (required)
libipsecmb = cc.find_library('IPSec_MB', required: false)
if libipsecmb.found() and cc.links(
'int main(void) {return 0;}', dependencies: libipsecmb)
- # version comes with quotes, so we split based on " and take the middle
imb_ver = cc.get_define('IMB_VERSION_STR',
prefix : IMB_header).split('"')[1]
if (imb_ver.version_compare('>=' + IMB_required_ver))
ext_deps += libipsecmb
- elif libcrypto.found()
- ext_deps += libcrypto
- dpdk_conf.set('RTE_QAT_OPENSSL', true)
+ dpdk_conf.set('RTE_QAT_IPSECMB', true)
else
qat_crypto = false
dpdk_drvs_disabled += qat_crypto_path
set_variable('drv_' + qat_crypto_path.underscorify() + '_disable_reason',
- 'missing dependency, libipsecmb or libcrypto')
+ 'IPSec_MB version >= @0@ is required, found version @1@'.format(
+ IMB_required_ver, imb_ver))
endif
- elif libcrypto.found()
- ext_deps += libcrypto
- dpdk_conf.set('RTE_QAT_OPENSSL', true)
else
qat_crypto = false
dpdk_drvs_disabled += qat_crypto_path
set_variable('drv_' + qat_crypto_path.underscorify() + '_disable_reason',
- 'missing dependency, libipsecmb or libcrypto')
+ 'missing required dependency, libIPSec_MB >= @0@'.format(IMB_required_ver))
+ endif
+endif
+
+# Check for OpenSSL (optional, for DOCSIS BPI cipher fallback)
+openssl_required_ver = '3.0.0'
+if qat_crypto
+ libcrypto = dependency('libcrypto', required: false, method: 'pkg-config', version: '>= ' + openssl_required_ver)
+ if libcrypto.found()
+ ext_deps += libcrypto
+ dpdk_conf.set('RTE_QAT_OPENSSL', true)
+ if arch_subdir == 'arm'
+ message('QAT: Using OpenSSL @0@ for DOCSIS on ARM'.format(libcrypto.version()))
+ else
+ message('QAT: OpenSSL @0@ available for DOCSIS fallback'.format(libcrypto.version()))
+ endif
+ else
+ if arch_subdir == 'arm'
+ warning('QAT: OpenSSL >= @0@ not found - DOCSIS algorithms will not be available on ARM'.format(openssl_required_ver))
+ else
+ message('QAT: OpenSSL >= @0@ not found - DOCSIS will use IPsec MB only'.format(openssl_required_ver))
+ endif
endif
endif
diff --git a/drivers/crypto/qat/qat_sym_session.c b/drivers/crypto/qat/qat_sym_session.c
index ff01db4372..486eb5b54a 100644
--- a/drivers/crypto/qat/qat_sym_session.c
+++ b/drivers/crypto/qat/qat_sym_session.c
@@ -2,19 +2,18 @@
* Copyright(c) 2015-2022 Intel Corporation
*/
-#define OPENSSL_API_COMPAT 0x10100000L
-
-#ifdef RTE_QAT_OPENSSL
-#include <openssl/sha.h> /* Needed to calculate pre-compute values */
-#include <openssl/aes.h> /* Needed to calculate pre-compute values */
-#include <openssl/md5.h> /* Needed to calculate pre-compute values */
-#include <openssl/evp.h> /* Needed for bpi runt block processing */
-#endif
-
-#ifndef RTE_QAT_OPENSSL
-#ifndef RTE_ARCH_ARM
+/* IPsec MB is required for HMAC precomputes (OpenSSL 3.0 removed Transform APIs)
+ * OpenSSL is optional for DOCSIS BPI cipher fallback
+ */
+#ifdef RTE_ARCH_ARM
+#include <ipsec-mb.h>
+#else
#include <intel-ipsec-mb.h>
#endif
+
+#ifdef RTE_QAT_OPENSSL
+#define OPENSSL_API_COMPAT 0x30000000L
+#include <openssl/evp.h> /* For DOCSIS BPI cipher fallback */
#endif
#include <rte_memcpy.h>
@@ -32,15 +31,13 @@
#include "qat_sym.h"
#ifdef RTE_QAT_OPENSSL
-#if (OPENSSL_VERSION_NUMBER >= 0x30000000L)
#include <openssl/provider.h>
static OSSL_PROVIDER * legacy_lib;
static OSSL_PROVIDER *default_lib;
-/* Some cryptographic algorithms such as MD and DES are now considered legacy
- * and not enabled by default in OpenSSL 3.0. Load up lagacy provider as MD5
- * DES are needed in QAT pre-computes and secure session creation.
+/* DES is considered legacy and not enabled by default in OpenSSL 3.0.
+ * Load legacy provider for DES-DOCSISBPI cipher fallback support.
*/
static int ossl_legacy_provider_load(void)
{
@@ -52,7 +49,8 @@ static int ossl_legacy_provider_load(void)
default_lib = OSSL_PROVIDER_load(NULL, "default");
if (default_lib == NULL) {
OSSL_PROVIDER_unload(legacy_lib);
- return -EINVAL;
+ legacy_lib = NULL;
+ return -EINVAL;
}
return 0;
@@ -60,11 +58,16 @@ static int ossl_legacy_provider_load(void)
static void ossl_legacy_provider_unload(void)
{
- OSSL_PROVIDER_unload(legacy_lib);
- OSSL_PROVIDER_unload(default_lib);
+ if (legacy_lib != NULL) {
+ OSSL_PROVIDER_unload(legacy_lib);
+ legacy_lib = NULL;
+ }
+ if (default_lib != NULL) {
+ OSSL_PROVIDER_unload(default_lib);
+ default_lib = NULL;
+ }
}
#endif
-#endif
#define ETH_CRC32_POLYNOMIAL 0x04c11db7
#define ETH_CRC32_INIT_VAL 0xffffffff
@@ -634,9 +637,9 @@ qat_sym_session_configure(struct rte_cryptodev *dev,
int ret;
#ifdef RTE_QAT_OPENSSL
-#if (OPENSSL_VERSION_NUMBER >= 0x30000000L)
- ossl_legacy_provider_load();
-#endif
+ ret = ossl_legacy_provider_load();
+ if (ret != 0)
+ return ret;
#endif
ret = qat_sym_session_set_parameters(dev, xform,
CRYPTODEV_GET_SYM_SESS_PRIV(sess),
@@ -644,15 +647,15 @@ qat_sym_session_configure(struct rte_cryptodev *dev,
if (ret != 0) {
QAT_LOG(ERR,
"Crypto QAT PMD: failed to configure session parameters");
-
+#ifdef RTE_QAT_OPENSSL
+ ossl_legacy_provider_unload();
+#endif
return ret;
}
#ifdef RTE_QAT_OPENSSL
-# if (OPENSSL_VERSION_NUMBER >= 0x30000000L)
ossl_legacy_provider_unload();
-# endif
-# endif
+#endif
return 0;
}
@@ -1412,339 +1415,9 @@ static int qat_hash_get_block_size(enum icp_qat_hw_auth_algo qat_hash_alg)
#define HMAC_OPAD_VALUE 0x5c
#define HASH_XCBC_PRECOMP_KEY_NUM 3
-#ifdef RTE_QAT_OPENSSL
-static int partial_hash_sha1(uint8_t *data_in, uint8_t *data_out)
-{
- SHA_CTX ctx;
-
- if (!SHA1_Init(&ctx))
- return -EFAULT;
- SHA1_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, SHA_DIGEST_LENGTH);
- return 0;
-}
-
-static int partial_hash_sha224(uint8_t *data_in, uint8_t *data_out)
-{
- SHA256_CTX ctx;
-
- if (!SHA224_Init(&ctx))
- return -EFAULT;
- SHA256_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, SHA256_DIGEST_LENGTH);
- return 0;
-}
-
-static int partial_hash_sha256(uint8_t *data_in, uint8_t *data_out)
-{
- SHA256_CTX ctx;
-
- if (!SHA256_Init(&ctx))
- return -EFAULT;
- SHA256_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, SHA256_DIGEST_LENGTH);
- return 0;
-}
-
-static int partial_hash_sha384(uint8_t *data_in, uint8_t *data_out)
-{
- SHA512_CTX ctx;
-
- if (!SHA384_Init(&ctx))
- return -EFAULT;
- SHA512_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, SHA512_DIGEST_LENGTH);
- return 0;
-}
-
-static int partial_hash_sha512(uint8_t *data_in, uint8_t *data_out)
-{
- SHA512_CTX ctx;
-
- if (!SHA512_Init(&ctx))
- return -EFAULT;
- SHA512_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, SHA512_DIGEST_LENGTH);
- return 0;
-}
-
-static int partial_hash_md5(uint8_t *data_in, uint8_t *data_out)
-{
- MD5_CTX ctx;
-
- if (!MD5_Init(&ctx))
- return -EFAULT;
- MD5_Transform(&ctx, data_in);
- rte_memcpy(data_out, &ctx, MD5_DIGEST_LENGTH);
-
- return 0;
-}
-
-static void aes_cmac_key_derive(uint8_t *base, uint8_t *derived)
-{
- int i;
-
- derived[0] = base[0] << 1;
- for (i = 1; i < ICP_QAT_HW_AES_BLK_SZ ; i++) {
- derived[i] = base[i] << 1;
- derived[i - 1] |= base[i] >> 7;
- }
-
- if (base[0] & 0x80)
- derived[ICP_QAT_HW_AES_BLK_SZ - 1] ^= QAT_AES_CMAC_CONST_RB;
-}
-
-static int
-partial_hash_compute(enum icp_qat_hw_auth_algo hash_alg,
- uint8_t *data_in, uint8_t *data_out)
-{
- int digest_size;
- uint8_t digest[qat_hash_get_digest_size(
- ICP_QAT_HW_AUTH_ALGO_DELIMITER)];
- uint32_t *hash_state_out_be32;
- uint64_t *hash_state_out_be64;
- int i;
-
- /* Initialize to avoid gcc warning */
- memset(digest, 0, sizeof(digest));
-
- digest_size = qat_hash_get_digest_size(hash_alg);
- if (digest_size <= 0)
- return -EFAULT;
-
- hash_state_out_be32 = (uint32_t *)data_out;
- hash_state_out_be64 = (uint64_t *)data_out;
-
- switch (hash_alg) {
- case ICP_QAT_HW_AUTH_ALGO_SHA1:
- if (partial_hash_sha1(data_in, digest))
- return -EFAULT;
- for (i = 0; i < digest_size >> 2; i++, hash_state_out_be32++)
- *hash_state_out_be32 =
- rte_bswap32(*(((uint32_t *)digest)+i));
- break;
- case ICP_QAT_HW_AUTH_ALGO_SHA224:
- if (partial_hash_sha224(data_in, digest))
- return -EFAULT;
- for (i = 0; i < digest_size >> 2; i++, hash_state_out_be32++)
- *hash_state_out_be32 =
- rte_bswap32(*(((uint32_t *)digest)+i));
- break;
- case ICP_QAT_HW_AUTH_ALGO_SHA256:
- if (partial_hash_sha256(data_in, digest))
- return -EFAULT;
- for (i = 0; i < digest_size >> 2; i++, hash_state_out_be32++)
- *hash_state_out_be32 =
- rte_bswap32(*(((uint32_t *)digest)+i));
- break;
- case ICP_QAT_HW_AUTH_ALGO_SHA384:
- if (partial_hash_sha384(data_in, digest))
- return -EFAULT;
- for (i = 0; i < digest_size >> 3; i++, hash_state_out_be64++)
- *hash_state_out_be64 =
- rte_bswap64(*(((uint64_t *)digest)+i));
- break;
- case ICP_QAT_HW_AUTH_ALGO_SHA512:
- if (partial_hash_sha512(data_in, digest))
- return -EFAULT;
- for (i = 0; i < digest_size >> 3; i++, hash_state_out_be64++)
- *hash_state_out_be64 =
- rte_bswap64(*(((uint64_t *)digest)+i));
- break;
- case ICP_QAT_HW_AUTH_ALGO_MD5:
- if (partial_hash_md5(data_in, data_out))
- return -EFAULT;
- break;
- default:
- QAT_LOG(ERR, "invalid hash alg %u", hash_alg);
- return -EFAULT;
- }
-
- return 0;
-}
-
-static const uint8_t AES_CMAC_SEED[ICP_QAT_HW_AES_128_KEY_SZ];
-
-static int qat_sym_do_precomputes(enum icp_qat_hw_auth_algo hash_alg,
- const uint8_t *auth_key,
- uint16_t auth_keylen,
- uint8_t *p_state_buf,
- uint16_t *p_state_len,
- uint8_t aes_cmac)
-{
- int block_size;
- uint8_t ipad[qat_hash_get_block_size(ICP_QAT_HW_AUTH_ALGO_DELIMITER)];
- uint8_t opad[qat_hash_get_block_size(ICP_QAT_HW_AUTH_ALGO_DELIMITER)];
- int i;
-
- if (hash_alg == ICP_QAT_HW_AUTH_ALGO_AES_XCBC_MAC) {
-
- /* CMAC */
- if (aes_cmac) {
- AES_KEY enc_key;
- uint8_t *in = NULL;
- uint8_t k0[ICP_QAT_HW_AES_128_KEY_SZ];
- uint8_t *k1, *k2;
-
- auth_keylen = ICP_QAT_HW_AES_128_KEY_SZ;
-
- in = rte_zmalloc("AES CMAC K1",
- ICP_QAT_HW_AES_128_KEY_SZ, 16);
-
- if (in == NULL) {
- QAT_LOG(ERR, "Failed to alloc memory");
- return -ENOMEM;
- }
-
- rte_memcpy(in, AES_CMAC_SEED,
- ICP_QAT_HW_AES_128_KEY_SZ);
- rte_memcpy(p_state_buf, auth_key, auth_keylen);
-
- if (AES_set_encrypt_key(auth_key, auth_keylen << 3,
- &enc_key) != 0) {
- rte_free_sensitive(in);
- return -EFAULT;
- }
-
- AES_encrypt(in, k0, &enc_key);
-
- k1 = p_state_buf + ICP_QAT_HW_AES_XCBC_MAC_STATE1_SZ;
- k2 = k1 + ICP_QAT_HW_AES_XCBC_MAC_STATE1_SZ;
-
- aes_cmac_key_derive(k0, k1);
- aes_cmac_key_derive(k1, k2);
-
- rte_memzero_explicit(k0, ICP_QAT_HW_AES_128_KEY_SZ);
- *p_state_len = ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ;
- rte_free_sensitive(in);
- goto out;
- } else {
- static uint8_t qat_aes_xcbc_key_seed[
- ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ] = {
- 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
- 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
- 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02,
- 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02,
- 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
- 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
- };
-
- uint8_t *in = NULL;
- uint8_t *out = p_state_buf;
- int x;
- AES_KEY enc_key;
-
- in = rte_zmalloc("working mem for key",
- ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ, 16);
- if (in == NULL) {
- QAT_LOG(ERR, "Failed to alloc memory");
- return -ENOMEM;
- }
-
- rte_memcpy(in, qat_aes_xcbc_key_seed,
- ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ);
- for (x = 0; x < HASH_XCBC_PRECOMP_KEY_NUM; x++) {
- if (AES_set_encrypt_key(auth_key,
- auth_keylen << 3,
- &enc_key) != 0) {
- rte_free_sensitive(in -
- (x * ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ));
- rte_memzero_explicit(out -
- (x * ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ),
- ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ);
- return -EFAULT;
- }
- AES_encrypt(in, out, &enc_key);
- in += ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ;
- out += ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ;
- }
- *p_state_len = ICP_QAT_HW_AES_XCBC_MAC_STATE2_SZ;
- rte_free_sensitive(in - x*ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ);
- goto out;
- }
-
- } else if ((hash_alg == ICP_QAT_HW_AUTH_ALGO_GALOIS_128) ||
- (hash_alg == ICP_QAT_HW_AUTH_ALGO_GALOIS_64)) {
- uint8_t *in = NULL;
- uint8_t *out = p_state_buf;
- AES_KEY enc_key;
-
- memset(p_state_buf, 0, ICP_QAT_HW_GALOIS_H_SZ +
- ICP_QAT_HW_GALOIS_LEN_A_SZ +
- ICP_QAT_HW_GALOIS_E_CTR0_SZ);
- in = rte_zmalloc("working mem for key",
- ICP_QAT_HW_GALOIS_H_SZ, 16);
- if (in == NULL) {
- QAT_LOG(ERR, "Failed to alloc memory");
- return -ENOMEM;
- }
-
- rte_memzero_explicit(in, ICP_QAT_HW_GALOIS_H_SZ);
- if (AES_set_encrypt_key(auth_key, auth_keylen << 3,
- &enc_key) != 0) {
- return -EFAULT;
- }
- AES_encrypt(in, out, &enc_key);
- *p_state_len = ICP_QAT_HW_GALOIS_H_SZ +
- ICP_QAT_HW_GALOIS_LEN_A_SZ +
- ICP_QAT_HW_GALOIS_E_CTR0_SZ;
- rte_free_sensitive(in);
- return 0;
- }
-
- block_size = qat_hash_get_block_size(hash_alg);
- if (block_size < 0)
- return block_size;
- /* init ipad and opad from key and xor with fixed values */
- memset(ipad, 0, block_size);
- memset(opad, 0, block_size);
-
- if (auth_keylen > (unsigned int)block_size) {
- QAT_LOG(ERR, "invalid keylen %u", auth_keylen);
- return -EFAULT;
- }
-
- RTE_VERIFY(auth_keylen <= sizeof(ipad));
- RTE_VERIFY(auth_keylen <= sizeof(opad));
-
- rte_memcpy(ipad, auth_key, auth_keylen);
- rte_memcpy(opad, auth_key, auth_keylen);
-
- for (i = 0; i < block_size; i++) {
- uint8_t *ipad_ptr = ipad + i;
- uint8_t *opad_ptr = opad + i;
- *ipad_ptr ^= HMAC_IPAD_VALUE;
- *opad_ptr ^= HMAC_OPAD_VALUE;
- }
-
- /* do partial hash of ipad and copy to state1 */
- if (partial_hash_compute(hash_alg, ipad, p_state_buf)) {
- rte_memzero_explicit(ipad, block_size);
- rte_memzero_explicit(opad, block_size);
- QAT_LOG(ERR, "ipad precompute failed");
- return -EFAULT;
- }
-
- /*
- * State len is a multiple of 8, so may be larger than the digest.
- * Put the partial hash of opad state_len bytes after state1
- */
- *p_state_len = qat_hash_get_state1_size(hash_alg);
- if (partial_hash_compute(hash_alg, opad, p_state_buf + *p_state_len)) {
- rte_memzero_explicit(ipad, block_size);
- rte_memzero_explicit(opad, block_size);
- QAT_LOG(ERR, "opad precompute failed");
- return -EFAULT;
- }
-
- /* don't leave data lying around */
- rte_memzero_explicit(ipad, block_size);
- rte_memzero_explicit(opad, block_size);
-out:
- return 0;
-}
-
-#else
+/* HMAC precomputes always use IPsec MB (OpenSSL 3.0 removed SHA*_Transform APIs)
+ * OpenSSL is only used for DOCSIS BPI cipher fallback (via EVP API)
+ */
static int aes_ipsecmb_job(uint8_t *in, uint8_t *out, IMB_MGR *m,
const uint8_t *key, uint16_t auth_keylen)
@@ -1992,7 +1665,6 @@ static int qat_sym_do_precomputes_ipsec_mb(enum icp_qat_hw_auth_algo hash_alg,
free_mb_mgr(m);
return ret;
}
-#endif
static void
qat_sym_session_init_common_hdr(struct qat_sym_session *session)
@@ -2482,16 +2154,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
break;
}
/* SHA-1 HMAC */
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_SHA1, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_SHA1,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(SHA)precompute failed");
@@ -2509,15 +2174,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
break;
}
/* SHA-224 HMAC */
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_SHA224, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_SHA224,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(SHA)precompute failed");
return -EFAULT;
@@ -2534,15 +2193,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
break;
}
/* SHA-256 HMAC */
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_SHA256, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_SHA256,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(SHA)precompute failed");
return -EFAULT;
@@ -2559,15 +2212,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
break;
}
/* SHA-384 HMAC */
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_SHA384, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_SHA384,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(SHA)precompute failed");
return -EFAULT;
@@ -2584,15 +2231,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
break;
}
/* SHA-512 HMAC */
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_SHA512, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_SHA512,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(SHA)precompute failed");
return -EFAULT;
@@ -2628,16 +2269,10 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
if (cdesc->aes_cmac)
memset(cdesc->cd_cur_ptr, 0, state1_size);
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_AES_XCBC_MAC,
- authkey, authkeylen, cdesc->cd_cur_ptr + state1_size,
- &state2_size, cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(
ICP_QAT_HW_AUTH_ALGO_AES_XCBC_MAC,
authkey, authkeylen, cdesc->cd_cur_ptr + state1_size,
&state2_size, cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(%s)precompute failed",
cdesc->aes_cmac ? "CMAC" : "XCBC");
@@ -2654,15 +2289,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
case ICP_QAT_HW_AUTH_ALGO_GALOIS_64:
cdesc->qat_proto_flag = QAT_CRYPTO_PROTO_FLAG_GCM;
state1_size = ICP_QAT_HW_GALOIS_128_STATE1_SZ;
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(cdesc->qat_hash_alg, authkey,
- authkeylen, cdesc->cd_cur_ptr + state1_size,
- &state2_size, cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(cdesc->qat_hash_alg, authkey,
authkeylen, cdesc->cd_cur_ptr + state1_size,
&state2_size, cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(GCM)precompute failed");
return -EFAULT;
@@ -2734,15 +2363,9 @@ static int qat_sym_cd_auth_set(struct qat_sym_session *cdesc,
auth_param->hash_state_sz = ICP_QAT_HW_ZUC_256_IV_SZ >> 3;
break;
case ICP_QAT_HW_AUTH_ALGO_MD5:
-#ifdef RTE_QAT_OPENSSL
- ret = qat_sym_do_precomputes(ICP_QAT_HW_AUTH_ALGO_MD5, authkey,
- authkeylen, cdesc->cd_cur_ptr, &state1_size,
- cdesc->aes_cmac);
-#else
ret = qat_sym_do_precomputes_ipsec_mb(ICP_QAT_HW_AUTH_ALGO_MD5,
authkey, authkeylen, cdesc->cd_cur_ptr, &state1_size,
cdesc->aes_cmac);
-#endif
if (ret) {
QAT_LOG(ERR, "(MD5)precompute failed");
return -EFAULT;
@@ -3188,22 +2811,21 @@ qat_security_session_create(void *dev,
}
#ifdef RTE_QAT_OPENSSL
-#if (OPENSSL_VERSION_NUMBER >= 0x30000000L)
if (ossl_legacy_provider_load())
return -EINVAL;
-#endif
#endif
ret = qat_sec_session_set_docsis_parameters(cdev, conf,
sess_private_data, SECURITY_GET_SESS_PRIV_IOVA(sess));
if (ret != 0) {
QAT_LOG(ERR, "Failed to configure session parameters");
+#ifdef RTE_QAT_OPENSSL
+ ossl_legacy_provider_unload();
+#endif
return ret;
}
#ifdef RTE_QAT_OPENSSL
-#if (OPENSSL_VERSION_NUMBER >= 0x30000000L)
ossl_legacy_provider_unload();
-#endif
#endif
return 0;
}
--
2.43.0
^ permalink raw reply related
* [PATCH v3] drivers: update relaxed ordering policy for mlx5 mkeys
From: Maayan Kashani @ 2026-06-22 7:54 UTC (permalink / raw)
To: dev
Cc: mkashani, rasland, Viacheslav Ovsiienko, Dariusz Sosnowski,
Bing Zhao, Ori Kam, Suanming Mou, Matan Azrad
In-Reply-To: <20260616122355.39114-1-mkashani@nvidia.com>
New adapters expose additional ordering capabilities.
Query the new caps and apply them when creating DevX mkeys via
mlx5_devx_mkey_attr_set_ordering(), which sets PCI relaxed ordering
and RAW=RO when relaxed order is supported.
Use this helper on Windows (still gated by Haswell/Broadwell) and for
Linux wrapped mkeys and crypto/regex/vdpa indirect mkeys when
relaxed order only flag is set.
Linux wrapped mkeys continue to use the legacy Haswell/Broadwell rule for
IBV_ACCESS_RELAXED_ORDERING on the verbs MR.
Upcoming FW will requires setting the correct ordering attributes,
otherwise it fails to create the memory key.
Signed-off-by: Maayan Kashani <mkashani@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
drivers/common/mlx5/linux/mlx5_common_os.c | 10 +++++++
drivers/common/mlx5/mlx5_devx_cmds.c | 31 ++++++++++++++++++++
drivers/common/mlx5/mlx5_devx_cmds.h | 9 ++++++
drivers/common/mlx5/mlx5_prm.h | 18 ++++++++++--
drivers/common/mlx5/windows/mlx5_common_os.c | 8 ++---
drivers/crypto/mlx5/mlx5_crypto.c | 4 +++
drivers/regex/mlx5/mlx5_regex_fastpath.c | 5 ++++
drivers/regex/mlx5/mlx5_rxp.c | 4 +++
drivers/vdpa/mlx5/mlx5_vdpa_mem.c | 4 +++
9 files changed, 85 insertions(+), 8 deletions(-)
diff --git a/drivers/common/mlx5/linux/mlx5_common_os.c b/drivers/common/mlx5/linux/mlx5_common_os.c
index e3db6c41245..3e9cd86062f 100644
--- a/drivers/common/mlx5/linux/mlx5_common_os.c
+++ b/drivers/common/mlx5/linux/mlx5_common_os.c
@@ -997,6 +997,7 @@ int
mlx5_os_wrapped_mkey_create(void *ctx, void *pd, uint32_t pdn, void *addr,
size_t length, struct mlx5_pmd_wrapped_mr *pmd_mr)
{
+ struct mlx5_hca_attr hca_attr = { 0 };
struct mlx5_klm klm = {
.byte_count = length,
.address = (uintptr_t)addr,
@@ -1007,6 +1008,7 @@ mlx5_os_wrapped_mkey_create(void *ctx, void *pd, uint32_t pdn, void *addr,
.klm_num = 1,
};
struct mlx5_devx_obj *mkey;
+ int ret;
struct ibv_mr *ibv_mr = mlx5_glue->reg_mr(pd, addr, length,
IBV_ACCESS_LOCAL_WRITE |
(mlx5_haswell_broadwell_cpu ? 0 :
@@ -1019,6 +1021,14 @@ mlx5_os_wrapped_mkey_create(void *ctx, void *pd, uint32_t pdn, void *addr,
klm.mkey = ibv_mr->lkey;
mkey_attr.addr = (uintptr_t)addr;
mkey_attr.size = length;
+ ret = mlx5_devx_cmd_query_hca_attr(ctx, &hca_attr);
+ if (ret != 0) {
+ claim_zero(mlx5_glue->dereg_mr(ibv_mr));
+ return ret;
+ }
+ /* Apply MKC ordering when FW requires relaxed-order-only mode. */
+ if (hca_attr.mkc_order_write_after_write_ro_only)
+ mlx5_devx_mkey_attr_set_ordering(&mkey_attr, &hca_attr);
mkey = mlx5_devx_cmd_mkey_create(ctx, &mkey_attr);
if (!mkey) {
claim_zero(mlx5_glue->dereg_mr(ibv_mr));
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c
index c4ac2aaceed..140b057ab47 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.c
+++ b/drivers/common/mlx5/mlx5_devx_cmds.c
@@ -331,6 +331,29 @@ mlx5_devx_cmd_flow_counter_query(struct mlx5_devx_obj *dcs,
return 0;
}
+/**
+ * Apply PCI relaxed-ordering and read-after-write ordering to mkey attributes.
+ *
+ * @param[in, out] mkey_attr
+ * Mkey attributes to update.
+ * @param[in] hca_attr
+ * HCA capabilities from mlx5_devx_cmd_query_hca_attr().
+ */
+RTE_EXPORT_INTERNAL_SYMBOL(mlx5_devx_mkey_attr_set_ordering)
+void
+mlx5_devx_mkey_attr_set_ordering(struct mlx5_devx_mkey_attr *mkey_attr,
+ const struct mlx5_hca_attr *hca_attr)
+{
+ if (!mkey_attr || !hca_attr)
+ return;
+
+ mkey_attr->relaxed_ordering_write = hca_attr->relaxed_ordering_write;
+ mkey_attr->relaxed_ordering_read =
+ hca_attr->relaxed_ordering_read || hca_attr->pci_relaxed_ordered_read;
+ if (hca_attr->mkc_order_read_after_write)
+ mkey_attr->read_after_write_ordering = MLX5_MKC_RAW_ORDERING_RO;
+}
+
/**
* Create a new mkey.
*
@@ -417,6 +440,8 @@ mlx5_devx_cmd_mkey_create(void *ctx,
MLX5_SET(mkc, mkc, relaxed_ordering_write,
attr->relaxed_ordering_write);
MLX5_SET(mkc, mkc, relaxed_ordering_read, attr->relaxed_ordering_read);
+ MLX5_SET(mkc, mkc, order_read_after_write,
+ attr->read_after_write_ordering);
MLX5_SET64(mkc, mkc, start_addr, attr->addr);
MLX5_SET64(mkc, mkc, len, attr->size);
MLX5_SET(mkc, mkc, crypto_en, attr->crypto_en);
@@ -1003,6 +1028,12 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
relaxed_ordering_write);
attr->relaxed_ordering_read = MLX5_GET(cmd_hca_cap, hcattr,
relaxed_ordering_read);
+ attr->pci_relaxed_ordered_read = MLX5_GET(cmd_hca_cap, hcattr,
+ pci_relaxed_ordered_read);
+ attr->mkc_order_read_after_write = MLX5_GET(cmd_hca_cap, hcattr,
+ mkc_order_read_after_write);
+ attr->mkc_order_write_after_write_ro_only = MLX5_GET(cmd_hca_cap, hcattr,
+ mkc_order_write_after_write_ro_only);
attr->access_register_user = MLX5_GET(cmd_hca_cap, hcattr,
access_register_user);
attr->eth_net_offloads = MLX5_GET(cmd_hca_cap, hcattr,
diff --git a/drivers/common/mlx5/mlx5_devx_cmds.h b/drivers/common/mlx5/mlx5_devx_cmds.h
index 82d949972bb..90beb2e9e6c 100644
--- a/drivers/common/mlx5/mlx5_devx_cmds.h
+++ b/drivers/common/mlx5/mlx5_devx_cmds.h
@@ -34,6 +34,7 @@ struct mlx5_devx_mkey_attr {
uint32_t pg_access:1;
uint32_t relaxed_ordering_write:1;
uint32_t relaxed_ordering_read:1;
+ uint32_t read_after_write_ordering:2;
uint32_t umr_en:1;
uint32_t crypto_en:2;
uint32_t set_remote_rw:1;
@@ -237,6 +238,9 @@ struct mlx5_hca_attr {
uint32_t vhca_id:16;
uint32_t relaxed_ordering_write:1;
uint32_t relaxed_ordering_read:1;
+ uint32_t pci_relaxed_ordered_read:1;
+ uint32_t mkc_order_read_after_write:1;
+ uint32_t mkc_order_write_after_write_ro_only:1;
uint32_t access_register_user:1;
uint32_t wqe_index_ignore:1;
uint32_t cross_channel:1;
@@ -748,6 +752,11 @@ int mlx5_devx_cmd_query_hca_attr(void *ctx,
__rte_internal
struct mlx5_devx_obj *mlx5_devx_cmd_mkey_create(void *ctx,
struct mlx5_devx_mkey_attr *attr);
+
+__rte_internal
+void
+mlx5_devx_mkey_attr_set_ordering(struct mlx5_devx_mkey_attr *mkey_attr,
+ const struct mlx5_hca_attr *hca_attr);
__rte_internal
int mlx5_devx_get_out_command_status(void *out);
__rte_internal
diff --git a/drivers/common/mlx5/mlx5_prm.h b/drivers/common/mlx5/mlx5_prm.h
index 3bb072a7fec..c2810194f8e 100644
--- a/drivers/common/mlx5/mlx5_prm.h
+++ b/drivers/common/mlx5/mlx5_prm.h
@@ -1463,7 +1463,9 @@ struct mlx5_ifc_mkc_bits {
u8 bsf_octword_size[0x20];
u8 reserved_at_120[0x80];
u8 translations_octword_size[0x20];
- u8 reserved_at_1c0[0x19];
+ u8 reserved_at_1c0[0x16];
+ u8 order_read_after_write[0x2];
+ u8 reserved_at_1d8[0x1];
u8 relaxed_ordering_read[0x1];
u8 reserved_at_1da[0x1];
u8 log_page_size[0x5];
@@ -1478,6 +1480,13 @@ enum {
MLX5_MKEY_CRYPTO_ENABLED = 0x1,
};
+/* MKC read_after_write_ordering field (2-bit, dword 0x38 bits 9:8). */
+enum mlx5_mkc_raw_ordering {
+ MLX5_MKC_RAW_ORDERING_SO = 0x0,
+ MLX5_MKC_RAW_ORDERING_SAO = 0x1,
+ MLX5_MKC_RAW_ORDERING_RO = 0x2,
+};
+
struct mlx5_ifc_create_mkey_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];
@@ -1827,7 +1836,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 log_max_mcg[0x8];
u8 reserved_at_320[0x3];
u8 log_max_transport_domain[0x5];
- u8 reserved_at_328[0x3];
+ u8 reserved_at_328[0x2];
+ u8 pci_relaxed_ordered_read[0x1];
u8 log_max_pd[0x5];
u8 reserved_at_330[0xb];
u8 log_max_xrcd[0x5];
@@ -1860,7 +1870,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 ext_stride_num_range[0x1];
u8 reserved_at_3a1[0x2];
u8 log_max_stride_sz_rq[0x5];
- u8 reserved_at_3a8[0x3];
+ u8 mkc_order_read_after_write[0x1];
+ u8 mkc_order_write_after_write_ro_only[0x1];
+ u8 reserved_at_3aa[0x1];
u8 log_min_stride_sz_rq[0x5];
u8 reserved_at_3b0[0x3];
u8 log_max_stride_sz_sq[0x5];
diff --git a/drivers/common/mlx5/windows/mlx5_common_os.c b/drivers/common/mlx5/windows/mlx5_common_os.c
index c790c9a4aeb..bdafb95df98 100644
--- a/drivers/common/mlx5/windows/mlx5_common_os.c
+++ b/drivers/common/mlx5/windows/mlx5_common_os.c
@@ -384,7 +384,7 @@ mlx5_os_reg_mr(void *pd,
{
struct mlx5_devx_mkey_attr mkey_attr;
struct mlx5_pd *mlx5_pd = (struct mlx5_pd *)pd;
- struct mlx5_hca_attr attr;
+ struct mlx5_hca_attr attr = { 0 };
struct mlx5_devx_obj *mkey;
void *obj;
@@ -403,10 +403,8 @@ mlx5_os_reg_mr(void *pd,
mkey_attr.size = length;
mkey_attr.umem_id = ((struct mlx5_devx_umem *)(obj))->umem_id;
mkey_attr.pd = mlx5_pd->pdn;
- if (!mlx5_haswell_broadwell_cpu) {
- mkey_attr.relaxed_ordering_write = attr.relaxed_ordering_write;
- mkey_attr.relaxed_ordering_read = attr.relaxed_ordering_read;
- }
+ if (!mlx5_haswell_broadwell_cpu)
+ mlx5_devx_mkey_attr_set_ordering(&mkey_attr, &attr);
mkey = mlx5_devx_cmd_mkey_create(mlx5_pd->devx_ctx, &mkey_attr);
if (!mkey) {
claim_zero(mlx5_os_umem_dereg(obj));
diff --git a/drivers/crypto/mlx5/mlx5_crypto.c b/drivers/crypto/mlx5/mlx5_crypto.c
index dd0aabb6d75..448dd0c5a4e 100644
--- a/drivers/crypto/mlx5/mlx5_crypto.c
+++ b/drivers/crypto/mlx5/mlx5_crypto.c
@@ -97,7 +97,11 @@ mlx5_crypto_indirect_mkeys_prepare(struct mlx5_crypto_priv *priv,
mlx5_crypto_mkey_update_t update_cb)
{
uint32_t i;
+ struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
+ /* If only relaxed order is allowed. */
+ if (hca_attr->mkc_order_write_after_write_ro_only)
+ mlx5_devx_mkey_attr_set_ordering(attr, hca_attr);
for (i = 0; i < qp->entries_n; i++) {
attr->klm_array = update_cb(priv, qp, i);
qp->mkey[i] = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, attr);
diff --git a/drivers/regex/mlx5/mlx5_regex_fastpath.c b/drivers/regex/mlx5/mlx5_regex_fastpath.c
index 3207bcbc603..55f7411593a 100644
--- a/drivers/regex/mlx5/mlx5_regex_fastpath.c
+++ b/drivers/regex/mlx5/mlx5_regex_fastpath.c
@@ -755,9 +755,14 @@ mlx5_regexdev_setup_fastpath(struct mlx5_regex_priv *priv, uint32_t qp_id)
setup_qps(priv, qp);
if (priv->has_umr) {
+ struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
+
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
attr.pd = priv->cdev->pdn;
#endif
+ /* If only relaxed order is allowed. */
+ if (hca_attr->mkc_order_write_after_write_ro_only)
+ mlx5_devx_mkey_attr_set_ordering(&attr, hca_attr);
for (i = 0; i < qp->nb_desc; i++) {
attr.klm_num = MLX5_REGEX_MAX_KLM_NUM;
attr.klm_array = qp->jobs[i].imkey_array;
diff --git a/drivers/regex/mlx5/mlx5_rxp.c b/drivers/regex/mlx5/mlx5_rxp.c
index dda4a7fdb0b..b865c08b53c 100644
--- a/drivers/regex/mlx5/mlx5_rxp.c
+++ b/drivers/regex/mlx5/mlx5_rxp.c
@@ -54,6 +54,7 @@ rxp_create_mkey(struct mlx5_regex_priv *priv, void *ptr, size_t size,
uint32_t access, struct mlx5_regex_mkey *mkey)
{
struct mlx5_devx_mkey_attr mkey_attr;
+ struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
/* Register the memory. */
mkey->umem = mlx5_glue->devx_umem_reg(priv->cdev->ctx, ptr, size, access);
@@ -72,6 +73,9 @@ rxp_create_mkey(struct mlx5_regex_priv *priv, void *ptr, size_t size,
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
mkey_attr.pd = priv->cdev->pdn;
#endif
+ /* If only relaxed order is allowed. */
+ if (hca_attr->mkc_order_write_after_write_ro_only)
+ mlx5_devx_mkey_attr_set_ordering(&mkey_attr, hca_attr);
mkey->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
if (!mkey->mkey) {
DRV_LOG(ERR, "Failed to create direct mkey!");
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_mem.c b/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
index 4dfe800b8fc..8c9d169d2a8 100644
--- a/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_mem.c
@@ -179,6 +179,7 @@ static int
mlx5_vdpa_create_indirect_mkey(struct mlx5_vdpa_priv *priv)
{
struct mlx5_devx_mkey_attr mkey_attr;
+ struct mlx5_hca_attr *hca_attr = &priv->cdev->config.hca_attr;
struct mlx5_vdpa_query_mr *mrs =
(struct mlx5_vdpa_query_mr *)priv->mrs;
struct mlx5_vdpa_query_mr *entry;
@@ -242,6 +243,9 @@ mlx5_vdpa_create_indirect_mkey(struct mlx5_vdpa_priv *priv)
mkey_attr.pg_access = 0;
mkey_attr.klm_array = klm_array;
mkey_attr.klm_num = klm_index;
+ /* If only relaxed order is allowed. */
+ if (hca_attr->mkc_order_write_after_write_ro_only)
+ mlx5_devx_mkey_attr_set_ordering(&mkey_attr, hca_attr);
entry = &mrs[mem->nregions];
entry->mkey = mlx5_devx_cmd_mkey_create(priv->cdev->ctx, &mkey_attr);
if (!entry->mkey) {
--
2.21.0
^ permalink raw reply related
* Re: [PATCH 2/2] common/cnxk: fix thread-unsafe NIX telemetry parsing
From: Jerin Jacob @ 2026-06-22 7:34 UTC (permalink / raw)
To: Stephen Hemminger
Cc: dev, stable, Nithin Dabilpuram, Kiran Kumar K, Sunil Kumar Kori,
Satha Rao, Harman Kalra, Gowrishankar Muthukrishnan, Jerin Jacob
In-Reply-To: <20260605224514.651081-3-stephen@networkplumber.org>
On Sat, Jun 6, 2026 at 4:15 AM Stephen Hemminger
<stephen@networkplumber.org> wrote:
>
> cnxk_nix_tel_handle_info_x() backs the /cnxk/nix/{rq,cq,sq}/{info,ctx}
> telemetry commands and parsed its "<pcidev>,<queue_id>" parameter with
> strtok(), which keeps non-reentrant state and races when telemetry
> callbacks run on per-connection threads.
>
> Split the parameter with strchr() and parse the queue id with strtoul().
> While here, copy the full parameter (the length was capped at
> PCI_PRI_STR_SIZE + 1, truncating the id for longer device addresses) and
> reject non-numeric or out-of-range ids instead of letting strtol() alias
> them to queue 0.
>
> Fixes: af75aac78978 ("common/cnxk: support telemetry for NIX")
> Cc: stable@dpdk.org
>
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Series applied to dpdk-next-net-mrvl/for-main. Thanks
^ permalink raw reply
* RE: |WARNING| [v5] graph: add optional profiling stats
From: Morten Brørup @ 2026-06-22 7:08 UTC (permalink / raw)
To: dpdklab, test-report, dev, Jerin Jacob, Kiran Kumar K,
Nithin Dabilpuram, Zhirun Yan
In-Reply-To: <6a3846f1.bcbae00d.1a8c6d.fd01SMTPIN_ADDED_MISSING@mx.google.com>
> From: dpdklab@iol.unh.edu [mailto:dpdklab@iol.unh.edu]
> Sent: Sunday, 21 June 2026 22.18
>
> Test-Label: ai-code-review
> Test-Status: WARNING
> https://dpdk.org/patch/165897
>
> _AI Code Review_
>
> === Patch Review: series.patch (via Claude) ===
> Review date: 2026-06-21
>
> # DPDK Patch Review
>
> ## Summary
>
> This patch adds optional profiling statistics to the graph library. The
> code is generally well-structured, but there are several issues that
> need to be addressed.
>
> ---
>
> ## Errors
>
> ### 1. Integer signedness mismatch in RTE_MAX call (Correctness)
>
> **File:** `lib/graph/graph_debug.c`
>
> **Issue:** `RTE_MAX` is used with `INT64_C(0)` (signed) and unsigned
> integer arithmetic results.
Rubbish.
The second parameter passed to RTE_MAX() is explicitly cast to signed integer (int64_t).
> This can cause incorrect comparisons when
> the unsigned result is large enough to be interpreted as negative when
> cast to signed.
>
> ```c
> calls = RTE_MAX(INT64_C(0), (int64_t)(n->total_calls -
> (n->usage_stats[0].calls + n->usage_stats[1].calls)));
> uint64_t cycles = RTE_MAX(INT64_C(0), (int64_t)(n->total_cycles -
> (n->usage_stats[0].cycles + n->usage_stats[1].cycles)));
> uint64_t objs = RTE_MAX(INT64_C(0), (int64_t)(n->total_objs -
> n->usage_stats[1].calls));
> ```
>
> **Why it matters:** If the subtraction underflows (e.g., due to
> uninitialized stats or race conditions), casting a large unsigned value
> to `int64_t` produces a negative number, which `RTE_MAX` correctly
> clamps to 0. However, the result is then assigned back to `uint64_t`,
> where `-1` would become `UINT64_MAX`. While the current code happens to
> work, mixing signed and unsigned types in this way is fragile.
Rubbish.
When clamping to 0, it cannot be -1.
>
> **Suggested fix:** Either use unsigned saturating subtraction or add a
> comment explaining the intentional signed clamping:
>
> ```c
> /* Clamp to 0 if stats haven't been fully initialized */
> calls = (uint64_t)RTE_MAX(INT64_C(0), (int64_t)(n->total_calls -
> (n->usage_stats[0].calls + n->usage_stats[1].calls)));
> ```
>
> Or use a more explicit pattern:
>
> ```c
> uint64_t sum_calls = n->usage_stats[0].calls + n->usage_stats[1].calls;
> calls = (n->total_calls > sum_calls) ? (n->total_calls - sum_calls) :
> 0;
> ```
>
> ---
>
> ### 2. Missing release notes entry
>
> **Issue:** This patch adds a new build-time configuration option
> (`RTE_GRAPH_PROFILE`) and new profiling features, but does not update
> the release notes.
>
> **Why it matters:** DPDK contribution guidelines require release notes
> for significant changes, especially new features and configuration
> options.
Disagree.
IMHO, this option is not significant enough to mention in the release notes.
The overall profiling details are already shown.
This option only adds profiling details for a few specific burst sizes.
>
> **Suggested fix:** Add an entry to
> `doc/guides/rel_notes/release_26_07.rst` (or the appropriate release
> notes file) documenting:
> - The new `RTE_GRAPH_PROFILE` configuration option
> - What profiling statistics it enables
> - Performance impact when enabled
>
> ---
>
> ### 3. `RTE_GRAPH_PROFILE` not defined as commented-out in rte_config.h
>
> **File:** `config/rte_config.h`
>
> **Issue:** The patch adds a comment `/* RTE_GRAPH_PROFILE is not set
> */`, but for consistency with other disabled options in DPDK (and to
> support build system detection), it should be defined to 0 or use
> `#undef`.
>
> ```c
> /* RTE_GRAPH_PROFILE is not set */
> ```
>
> **Why it matters:** DPDK coding standards (per AGENTS.md) specify that
> disabled config options should use `// XXX is not set` format or be
> explicitly set to 0 for clarity.
Rubbish.
It follows the existing coding style in that file.
>
> **Suggested fix:**
>
> ```c
> // RTE_GRAPH_PROFILE is not set
> ```
>
> Or define it explicitly:
>
> ```c
> /* #define RTE_GRAPH_PROFILE 1 */
> ```
>
> ---
>
> ## Warnings
>
> ### 1. Inconsistent format specifier for total_calls
>
> **File:** `lib/graph/graph_debug.c`
>
> **Before:**
> ```c
> fprintf(f, " total_calls=%" PRId64 "\n", n->total_calls);
> ```
>
> **After:**
> ```c
> fprintf(f, " total_calls=%" PRIu64 "\n", n->total_calls);
> ```
>
> **Issue:** This change from `PRId64` to `PRIu64` is correct (since
> `total_calls` is unsigned), but it's technically unrelated to the
> profiling feature addition. Consider splitting this bugfix into a
> separate preparatory patch.
>
> **Suggested action:** Either mention this fix in the commit message or
> split it into a separate bugfix patch with a `Fixes:` tag.
Disagree.
IMO, such minor drive-by changes like this should not be mentioned.
Mentioning them would be noise, and take focus from the actual changes.
>
> ---
>
> ### 2. Potential cache line alignment impact not documented
>
> **File:** `lib/graph/rte_graph_worker_common.h`
>
> **Issue:** When `RTE_GRAPH_PROFILE` is enabled, the `rte_node`
> structure grows significantly (adds ~64 bytes for profiling stats). The
> patch removes the compile-time assertion checking that node metadata
> fits in one cache line.
>
> ```c
> #ifndef RTE_GRAPH_PROFILE
> /* Limit Node specific metadata to one cacheline on 64B CL machine */
> RTE_BUILD_BUG_ON((offsetof(struct rte_node, nodes) -
> offsetof(struct rte_node, ctx)) !=
> RTE_CACHE_LINE_MIN_SIZE);
> #endif
> ```
>
> **Why it matters:** This increases memory footprint and potentially
> impacts cache performance. The documentation update mentions enabling
> profiling but doesn't warn about the performance cost.
>
> **Suggested fix:** Add a note in the documentation
> (prog_guide/graph_lib.rst) about the cache line impact:
>
> ```rst
> - Enable the ``RTE_GRAPH_PROFILE`` config option for detailed profiling
> statistics.
> Note: This increases the ``rte_node`` structure size and may impact
> cache performance.
> ```
Disagree.
The memory footprint increase is completely insignificant.
Yes, there's a potential performance cost; but not mainly from the increased structure size.
Any added instrumentation comes with a performance cost, which I consider too obvious to mention.
>
> ---
>
> ### 3. Division by zero checks use ternary instead of explicit if
>
> **File:** `lib/graph/graph_debug.c`
>
> **Issue:** Multiple instances use ternary operators for division-by-
> zero protection:
>
> ```c
> calls == 0 ? 0.0 : (double)cycles / (double)calls
> ```
>
> **Why it matters:** While correct, explicit `if` statements are
> generally more readable for complex calculations, especially when the
> expression appears multiple times.
>
> **Suggested fix:** This is acceptable as-is for simple cases, but
> consider extracting repeated calculations to helper functions if this
> pattern becomes more complex in the future.
>
Disagree.
It's a matter of taste.
In this case, I think the ternary is easier to read.
> ---
>
> ## Info
>
> ### 1. Consider helper macro for safe division
>
> **Observation:** The pattern `calls == 0 ? 0.0 : (double)cycles /
> (double)calls` appears many times.
>
> **Suggestion:** Consider defining a helper macro at the top of the
> file:
>
> ```c
> #define SAFE_DIV(num, den) ((den) == 0 ? 0.0 : (double)(num) /
> (double)(den))
> ```
>
> Then use: `SAFE_DIV(cycles, calls)`
>
> This would reduce code duplication and make the division-by-zero
> protection more obvious.
Disagree.
Again, it's a matter of taste.
In this case, I think the ternary is easier to read.
>
> ---
>
> ### 2. Profiling statistics initialization
>
> **Observation:** The new profiling fields in `rte_node` are not
> explicitly initialized in the patch.
>
> **Question:** Are these fields zeroed during node creation? If they
> rely on `rte_zmalloc()` or similar, this should be verified. If nodes
> are allocated differently, explicit initialization may be needed.
>
> **Suggested verification:** Confirm that node allocation zero-
> initializes the structure, or add explicit initialization in `node.c`.
The node is allocated with calloc() in node.c.
No need for further initialization.
>
> ---
>
> ### 3. Half-burst tracking precision
>
> **Observation:** The code tracks exactly `RTE_GRAPH_BURST_SIZE / 2` and
> `RTE_GRAPH_BURST_SIZE` but not other common burst sizes.
>
> **Suggestion:** Consider if tracking ranges (e.g., `[2..BURST_SIZE/2-
> 1]`, `[BURST_SIZE/2+1..BURST_SIZE-1]`) would provide more complete
> profiling data. The current approach gives precise data for three
> specific cases (0, 1, half, full) and aggregates everything else into
> "more."
>
> This is not a defect, just a design consideration for future
> enhancement.
Tracking ranges does not provide more information.
Tracking specific burst sizes provide relevant information.
Larger burst sizes approximately fit into: cycles = A + B * nb_objs.
Burst sizes of 0 and 1 are frequent instances; they usually don't fit on the linear approximation for larger burst sizes, so tracking them separately provides relevant information.
>
> ---
>
> ## Conclusion
>
> The patch is well-implemented overall with good documentation and
> appropriate use of conditional compilation. The main issues are:
>
> 1. **Error:** Mixed signed/unsigned integer comparison needs
> clarification or refactoring
> 2. **Error:** Missing release notes entry
> 3. **Error:** Config file comment format should follow DPDK convention
> 4. **Warning:** Performance impact of cache line expansion should be
> documented
>
> After addressing these issues, the patch will be ready for integration.
My conclusion:
No changes required. The patch is ready for integration as is.
^ permalink raw reply
* [PATCH 2/2] test/dma: add functions to verify zero and one fill
From: Tejasree Kondoj @ 2026-06-22 3:06 UTC (permalink / raw)
To: Akhil Goyal, Chengwen Feng, Kevin Laatz, Bruce Richardson
Cc: Vidya Sagar Velumuri, Anoob Joseph, dev
In-Reply-To: <20260622030623.86094-1-ktejasree@marvell.com>
Add test cases to verify zero fill and one fill
Signed-off-by: Vidya Sagar Velumuri <vvelumuri@marvell.com>
---
app/test/test.h | 4 +++
app/test/test_dmadev.c | 57 ++++++++++++++++++++++++------------------
2 files changed, 37 insertions(+), 24 deletions(-)
diff --git a/app/test/test.h b/app/test/test.h
index 1f12fc5397..5fc2d7d048 100644
--- a/app/test/test.h
+++ b/app/test/test.h
@@ -28,6 +28,10 @@
#include <rte_test.h>
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
#define TEST_ASSERT RTE_TEST_ASSERT
#define TEST_ASSERT_EQUAL RTE_TEST_ASSERT_EQUAL
diff --git a/app/test/test_dmadev.c b/app/test/test_dmadev.c
index b30f2214e5..d4299e501d 100644
--- a/app/test/test_dmadev.c
+++ b/app/test/test_dmadev.c
@@ -931,42 +931,51 @@ test_completion_handling(int16_t dev_id, uint16_t vchan)
static int
test_enqueue_fill(int16_t dev_id, uint16_t vchan)
{
+ uint64_t pattern[3] = {0x0, 0xfedcba9876543210, 0xffffffffffffffff};
const unsigned int lengths[] = {8, 64, 1024, 50, 100, 89};
+ unsigned int i, j, k;
struct rte_mbuf *dst;
char *dst_data;
- uint64_t pattern = 0xfedcba9876543210;
- unsigned int i, j;
dst = rte_pktmbuf_alloc(pool);
if (dst == NULL)
ERR_RETURN("Failed to allocate mbuf\n");
dst_data = rte_pktmbuf_mtod(dst, char *);
- for (i = 0; i < RTE_DIM(lengths); i++) {
- /* reset dst_data */
- memset(dst_data, 0, rte_pktmbuf_data_len(dst));
+ for (k = 0; k < ARRAY_SIZE(pattern); k++) {
+ for (i = 0; i < RTE_DIM(lengths); i++) {
+ /* reset dst_data */
+ memset(dst_data, 0, rte_pktmbuf_data_len(dst));
+
+ /* perform the fill operation */
+ int id = rte_dma_fill(dev_id, vchan, pattern[k],
+ rte_pktmbuf_iova(dst), lengths[i], RTE_DMA_OP_FLAG_SUBMIT);
+ if (id < 0) {
+ if (id == -ENOTSUP) {
+ rte_pktmbuf_free(dst);
+ return 0;
+ }
+ ERR_RETURN("Error with rte_dma_fill\n");
+ }
+ await_hw(dev_id, vchan);
- /* perform the fill operation */
- int id = rte_dma_fill(dev_id, vchan, pattern,
- rte_pktmbuf_iova(dst), lengths[i], RTE_DMA_OP_FLAG_SUBMIT);
- if (id < 0)
- ERR_RETURN("Error with rte_dma_fill\n");
- await_hw(dev_id, vchan);
+ if (rte_dma_completed(dev_id, vchan, 1, NULL, NULL) != 1)
+ ERR_RETURN("Error: fill operation failed (length: %u)\n",
+ lengths[i]);
+ /* check the data from the fill operation is correct */
+ for (j = 0; j < lengths[i]; j++) {
+ char pat_byte = ((char *)&pattern[k])[j % 8];
- if (rte_dma_completed(dev_id, vchan, 1, NULL, NULL) != 1)
- ERR_RETURN("Error: fill operation failed (length: %u)\n", lengths[i]);
- /* check the data from the fill operation is correct */
- for (j = 0; j < lengths[i]; j++) {
- char pat_byte = ((char *)&pattern)[j % 8];
- if (dst_data[j] != pat_byte)
- ERR_RETURN("Error with fill operation (lengths = %u): got (%x), not (%x)\n",
- lengths[i], dst_data[j], pat_byte);
+ if (dst_data[j] != pat_byte)
+ ERR_RETURN("Error with fill operation (lengths = %u): got (%x), not (%x)\n",
+ lengths[i], dst_data[j], pat_byte);
+ }
+ /* check that the data after the fill operation was not written to */
+ for (; j < rte_pktmbuf_data_len(dst); j++)
+ if (dst_data[j] != 0)
+ ERR_RETURN("Error, fill operation wrote too far (lengths = %u): got (%x), not (%x)\n",
+ lengths[i], dst_data[j], 0);
}
- /* check that the data after the fill operation was not written to */
- for (; j < rte_pktmbuf_data_len(dst); j++)
- if (dst_data[j] != 0)
- ERR_RETURN("Error, fill operation wrote too far (lengths = %u): got (%x), not (%x)\n",
- lengths[i], dst_data[j], 0);
}
rte_pktmbuf_free(dst);
--
2.34.1
^ permalink raw reply related
* [PATCH 1/2] test/dma: update the sg test to verify wrap around case
From: Tejasree Kondoj @ 2026-06-22 3:06 UTC (permalink / raw)
To: Akhil Goyal, Chengwen Feng, Kevin Laatz, Bruce Richardson
Cc: Vidya Sagar Velumuri, Anoob Joseph, dev
In-Reply-To: <20260622030623.86094-1-ktejasree@marvell.com>
Run the sg test in a loop to verify wrap around case.
Total number commands submitted to be more than the number descriptors
allocated to verify the scenario.
Signed-off-by: Vidya Sagar Velumuri <vvelumuri@marvell.com>
---
app/test/test_dmadev.c | 45 ++++++++++++++++++++++++--------------
app/test/test_dmadev_api.c | 1 -
app/test/test_dmadev_api.h | 2 ++
3 files changed, 31 insertions(+), 17 deletions(-)
diff --git a/app/test/test_dmadev.c b/app/test/test_dmadev.c
index 5488a1af33..b30f2214e5 100644
--- a/app/test/test_dmadev.c
+++ b/app/test/test_dmadev.c
@@ -393,36 +393,28 @@ test_stop_start(int16_t dev_id, uint16_t vchan)
}
static int
-test_enqueue_sg_copies(int16_t dev_id, uint16_t vchan)
+test_enqueue_sg(int16_t dev_id, uint16_t vchan, unsigned int n_sge, unsigned int test_len)
{
- unsigned int src_len, dst_len, n_sge, len, i, j, k;
char orig_src[COPY_LEN], orig_dst[COPY_LEN];
- struct rte_dma_info info = { 0 };
+ unsigned int src_len, dst_len, i, j, k;
enum rte_dma_status_code status;
uint16_t id, n_src, n_dst;
- if (rte_dma_info_get(dev_id, &info) < 0)
- ERR_RETURN("Failed to get dev info");
-
- if (info.max_sges < 2)
- ERR_RETURN("Test needs minimum 2 SG pointers");
-
- n_sge = info.max_sges;
-
for (n_src = 1; n_src <= n_sge; n_src++) {
for (n_dst = 1; n_dst <= n_sge; n_dst++) {
/* Normalize SG buffer lengths */
- len = COPY_LEN;
- len -= (len % (n_src * n_dst));
- dst_len = len / n_dst;
- src_len = len / n_src;
-
struct rte_dma_sge *sg_src = alloca(sizeof(struct rte_dma_sge) * n_sge);
struct rte_dma_sge *sg_dst = alloca(sizeof(struct rte_dma_sge) * n_sge);
struct rte_mbuf **src = alloca(sizeof(struct rte_mbuf *) * n_sge);
struct rte_mbuf **dst = alloca(sizeof(struct rte_mbuf *) * n_sge);
char **src_data = alloca(sizeof(char *) * n_sge);
char **dst_data = alloca(sizeof(char *) * n_sge);
+ unsigned int len = test_len - (test_len % (n_src * n_dst));
+
+ dst_len = len / n_dst;
+ src_len = len / n_src;
+ if (dst_len == 0 || src_len == 0)
+ continue;
for (i = 0 ; i < len; i++)
orig_src[i] = rte_rand() & 0xFF;
@@ -514,6 +506,27 @@ test_enqueue_sg_copies(int16_t dev_id, uint16_t vchan)
return 0;
}
+static int
+test_enqueue_sg_copies(int16_t dev_id, uint16_t vchan)
+{
+ struct rte_dma_info info = { 0 };
+ unsigned int n_sge, len;
+ int loop_count = 0;
+
+ if (rte_dma_info_get(dev_id, &info) < 0)
+ ERR_RETURN("Failed to get dev info");
+
+ n_sge = RTE_MIN(info.max_sges, TEST_SG_MAX);
+ len = COPY_LEN;
+
+ do {
+ test_enqueue_sg(dev_id, vchan, n_sge, len);
+ loop_count++;
+ } while (loop_count * n_sge * n_sge < TEST_RINGSIZE * 3);
+
+ return 0;
+}
+
static int
test_single_sva_copy(int16_t dev_id, uint16_t vchan, const char *mem_src,
char *src, char *dst, uint32_t len)
diff --git a/app/test/test_dmadev_api.c b/app/test/test_dmadev_api.c
index 1ba053696b..4bb8f9e820 100644
--- a/app/test/test_dmadev_api.c
+++ b/app/test/test_dmadev_api.c
@@ -16,7 +16,6 @@ extern int test_dma_api(uint16_t dev_id);
#define TEST_MEMCPY_SIZE 1024
#define TEST_WAIT_US_VAL 50000
-#define TEST_SG_MAX 64
static int16_t test_dev_id;
static int16_t invalid_dev_id;
diff --git a/app/test/test_dmadev_api.h b/app/test/test_dmadev_api.h
index 33fbc5bd41..a03f7acd4f 100644
--- a/app/test/test_dmadev_api.h
+++ b/app/test/test_dmadev_api.h
@@ -2,4 +2,6 @@
* Copyright(c) 2021 HiSilicon Limited
*/
+#define TEST_SG_MAX 64
+
int test_dma_api(uint16_t dev_id);
--
2.34.1
^ permalink raw reply related
* [PATCH 0/2] test/dma: improve dmadev tests
From: Tejasree Kondoj @ 2026-06-22 3:06 UTC (permalink / raw)
To: Akhil Goyal, Chengwen Feng, Kevin Laatz, Bruce Richardson
Cc: Vidya Sagar Velumuri, Anoob Joseph, dev
Extend dmadev tests for SG wrap-around and zero/one fill coverage.
Tejasree Kondoj (2):
test/dma: update the sg test to verify wrap around case
test/dma: add functions to verify zero and one fill
app/test/test.h | 4 ++
app/test/test_dmadev.c | 102 +++++++++++++++++------------
app/test/test_dmadev_api.c | 1 -
app/test/test_dmadev_api.h | 2 ++
4 files changed, 72 insertions(+), 25 deletions(-)
--
2.34.1
^ permalink raw reply
* Re: [PATCH v1 0/5] prefix lcore role enum values
From: lihuisong (C) @ 2026-06-22 1:22 UTC (permalink / raw)
To: Stephen Hemminger, Morten Brørup, thomas
Cc: andrew.rybchenko, dev, zhanjie9
In-Reply-To: <20260618190339.2fc76616@phoenix.local>
On 6/19/2026 10:03 AM, Stephen Hemminger wrote:
> On Wed, 17 Jun 2026 13:48:37 +0200
> Morten Brørup <mb@smartsharesystems.com> wrote:
>
>>> From: Huisong Li [mailto:lihuisong@huawei.com]
>>> Sent: Wednesday, 17 June 2026 12.28
>>>
>>> Add the RTE_LCORE_ prefix to the lcore role enum values in
>>> rte_lcore_role_t
>>> to follow DPDK naming conventions.
>>>
>>> - ROLE_RTE -> RTE_LCORE_ROLE_RTE
>>> - ROLE_OFF -> RTE_LCORE_ROLE_OFF
>>> - ROLE_SERVICE -> RTE_LCORE_ROLE_SERVICE
>>> - ROLE_NON_EAL -> RTE_LCORE_ROLE_NON_EAL
>>>
>>> Old names are kept as macros aliasing to the new names to preserve
>>> backward compatibility.
>>>
>> Series-Acked-by: Morten Brørup <mb@smartsharesystems.com>
>>
> The problem with this patch it causes build failures now with abi diff.
>
> Example build log...
>
>
> 2 functions with some indirect sub-type change:
>
>
>
>
>
> [C] 'function rte_lcore_role_t rte_eal_lcore_role(unsigned int)' at eal_common_lcore.c:74:1 has some indirect sub-type changes:
>
> return type changed:
>
> type size hasn't changed
>
> 4 enumerator deletions:
>
> 'rte_lcore_role_t::ROLE_RTE' value '0'
>
> 'rte_lcore_role_t::ROLE_OFF' value '1'
>
> 'rte_lcore_role_t::ROLE_SERVICE' value '2'
>
> 'rte_lcore_role_t::ROLE_NON_EAL' value '3'
>
> 4 enumerator insertions:
>
> 'rte_lcore_role_t::RTE_LCORE_ROLE_RTE' value '0'
>
> 'rte_lcore_role_t::RTE_LCORE_ROLE_OFF' value '1'
>
> 'rte_lcore_role_t::RTE_LCORE_ROLE_SERVICE' value '2'
>
> 'rte_lcore_role_t::RTE_LCORE_ROLE_NON_EAL' value '3'
>
>
>
>
>
> [C] 'function int rte_lcore_has_role(unsigned int, rte_lcore_role_t)' at eal_common_lcore.c:85:1 has some indirect sub-type changes:
>
> parameter 2 of type 'enum rte_lcore_role_t' has sub-type changes:
>
> enum type 'enum rte_lcore_role_t' changed at rte_lcore.h:33:1, as reported earlier
>
>
>
>
>
>
>
> Error: ABI issue reported for abidiff --suppr /home/runner/work/dpdk/dpdk/devtools/libabigail.abignore --no-added-syms --headers-dir1 reference/usr/local/include --headers-dir2 install/usr/local/include reference/usr/local/lib/librte_eal.so.26.1 install/usr/local/lib/librte_eal.so.26.2
We just came back from the Dragon Boat Festival.
I also received this ABI change warning. But I didn't have any good
ideas yet.
Thanks for helping to handle this.
Sorry for the inconvenience.
^ permalink raw reply
* [PATCH v5] graph: add optional profiling stats
From: Morten Brørup @ 2026-06-21 18:41 UTC (permalink / raw)
To: dev, Jerin Jacob, Kiran Kumar K, Nithin Dabilpuram, Zhirun Yan
Cc: Morten Brørup
In-Reply-To: <20260619202047.2809165-1-mb@smartsharesystems.com>
Added graph node profiling stats, build time configurable by enabling
RTE_GRAPH_PROFILE in rte_config.h.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
---
v5:
* Added stats for a half burst and a full burst.
v4:
* Added documentation. (AI)
* Added more comments. (AI)
* Improved dump. (AI)
* Debug shows both cycles/call and cycles/obj.
v3:
* Debug shows cycles/obj instead of cycles/call.
* Fixed missing --in-reply-to.
v2:
* Fixed indentation.
---
config/rte_config.h | 1 +
doc/guides/prog_guide/graph_lib.rst | 1 +
lib/graph/graph_debug.c | 57 ++++++++++++++++++++++++++++-
lib/graph/node.c | 2 +
lib/graph/rte_graph_worker_common.h | 33 +++++++++++++++--
5 files changed, 90 insertions(+), 4 deletions(-)
diff --git a/config/rte_config.h b/config/rte_config.h
index 0447cdf2ad..1942c1b1ec 100644
--- a/config/rte_config.h
+++ b/config/rte_config.h
@@ -106,6 +106,7 @@
/* rte_graph defines */
#define RTE_GRAPH_BURST_SIZE 256
#define RTE_LIBRTE_GRAPH_STATS 1
+/* RTE_GRAPH_PROFILE is not set */
/****** driver defines ********/
diff --git a/doc/guides/prog_guide/graph_lib.rst b/doc/guides/prog_guide/graph_lib.rst
index 8dd49c19d2..bc36042296 100644
--- a/doc/guides/prog_guide/graph_lib.rst
+++ b/doc/guides/prog_guide/graph_lib.rst
@@ -49,6 +49,7 @@ Performance tuning parameters
RTE_GRAPH_BURST_SIZE config option.
The testing shows, on x86 and arm64 servers, The sweet spot is 256 burst
size. While on arm64 embedded SoCs, it is either 64 or 128.
+- Enable the ``RTE_GRAPH_PROFILE`` config option for more profiling details.
- Disable node statistics (using ``RTE_LIBRTE_GRAPH_STATS`` config option)
if not needed.
diff --git a/lib/graph/graph_debug.c b/lib/graph/graph_debug.c
index e3b8cccdc1..7c97e23748 100644
--- a/lib/graph/graph_debug.c
+++ b/lib/graph/graph_debug.c
@@ -92,7 +92,62 @@ rte_graph_obj_dump(FILE *f, struct rte_graph *g, bool all)
fprintf(f, " total_sched_fail=%" PRId64 "\n",
n->dispatch.total_sched_fail);
}
- fprintf(f, " total_calls=%" PRId64 "\n", n->total_calls);
+ fprintf(f, " total_calls=%" PRIu64 "\n", n->total_calls);
+ if (rte_graph_has_stats_feature()) {
+ fprintf(f, " total_cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ n->total_cycles,
+ n->total_calls == 0 ? (double)0 :
+ (double)n->total_cycles / (double)n->total_calls);
+ }
+#ifdef RTE_GRAPH_PROFILE
+ uint64_t calls = n->usage_stats[0].calls;
+ fprintf(f, " objs[0]\n");
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ calls,
+ n->usage_stats[0].cycles,
+ calls == 0 ? 0.0 :
+ (double)n->usage_stats[0].cycles / (double)calls);
+ calls = n->usage_stats[1].calls;
+ fprintf(f, " objs[1]\n");
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ calls,
+ n->usage_stats[1].cycles,
+ calls == 0 ? 0.0 :
+ (double)n->usage_stats[1].cycles / (double)calls);
+ calls = RTE_MAX(INT64_C(0), (int64_t)(n->total_calls -
+ (n->usage_stats[0].calls + n->usage_stats[1].calls)));
+ uint64_t cycles = RTE_MAX(INT64_C(0), (int64_t)(n->total_cycles -
+ (n->usage_stats[0].cycles + n->usage_stats[1].cycles)));
+ uint64_t objs = RTE_MAX(INT64_C(0), (int64_t)(n->total_objs -
+ n->usage_stats[1].calls));
+ double objs_per_call = calls == 0 ? 0.0 : (double)objs / (double)calls;
+ fprintf(f, " objs[more], avg objs/call=%.1f\n", objs_per_call);
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f"
+ ", avg cycles/obj=%.1f\n",
+ calls,
+ cycles,
+ calls == 0 ? 0.0 : (double)cycles / (double)calls,
+ calls == 0 || objs_per_call == 0.0 ? 0.0 :
+ (double)cycles / (double)calls / objs_per_call);
+ calls = n->half_burst_calls;
+ fprintf(f, " objs[%u]\n", RTE_GRAPH_BURST_SIZE / 2);
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f"
+ ", avg cycles/obj=%.1f\n",
+ calls,
+ n->half_burst_cycles,
+ calls == 0 ? 0.0 : (double)n->half_burst_cycles / (double)calls,
+ calls == 0 ? 0.0 : (double)n->half_burst_cycles / (double)calls /
+ (double)(RTE_GRAPH_BURST_SIZE / 2));
+ calls = n->full_burst_calls;
+ fprintf(f, " objs[%u]\n", RTE_GRAPH_BURST_SIZE);
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f"
+ ", avg cycles/obj=%.1f\n",
+ calls,
+ n->full_burst_cycles,
+ calls == 0 ? 0.0 : (double)n->full_burst_cycles / (double)calls,
+ calls == 0 ? 0.0 : (double)n->full_burst_cycles / (double)calls /
+ (double)RTE_GRAPH_BURST_SIZE);
+#endif
for (i = 0; i < n->nb_edges; i++)
fprintf(f, " edge[%d] <%s>\n", i,
n->nodes[i]->name);
diff --git a/lib/graph/node.c b/lib/graph/node.c
index 1fce3e6632..19b38881ae 100644
--- a/lib/graph/node.c
+++ b/lib/graph/node.c
@@ -110,10 +110,12 @@ __rte_node_register(const struct rte_node_register *reg)
rte_edge_t i;
size_t sz;
+#ifndef RTE_GRAPH_PROFILE
/* Limit Node specific metadata to one cacheline on 64B CL machine */
RTE_BUILD_BUG_ON((offsetof(struct rte_node, nodes) -
offsetof(struct rte_node, ctx)) !=
RTE_CACHE_LINE_MIN_SIZE);
+#endif
graph_spinlock_lock();
diff --git a/lib/graph/rte_graph_worker_common.h b/lib/graph/rte_graph_worker_common.h
index 4ab53a533e..0d8039575d 100644
--- a/lib/graph/rte_graph_worker_common.h
+++ b/lib/graph/rte_graph_worker_common.h
@@ -144,12 +144,26 @@ struct __rte_cache_aligned rte_node {
rte_node_process_t process; /**< Process function. */
uint64_t process_u64;
};
+ /** Fast path area cache line 3. */
+#ifdef RTE_GRAPH_PROFILE
+ struct {
+ uint64_t calls; /**< Calls processing resp. 0 or 1 objects. */
+ uint64_t cycles; /**< Cycles spent processing resp. 0 or 1 objects. */
+ } usage_stats[2]; /**< Usage when this node processed 0 or 1 objects. */
+ uint64_t full_burst_calls; /**< Calls processing a full burst of objects. */
+ uint64_t full_burst_cycles; /**< Cycles spent processing a full burst of objects. */
+ uint64_t half_burst_calls; /**< Calls processing a half burst of objects. */
+ uint64_t half_burst_cycles; /**< Cycles spent processing a half burst of objects. */
+ /** Fast path area cache line 4. */
+#endif
alignas(RTE_CACHE_LINE_MIN_SIZE) struct rte_node *nodes[]; /**< Next nodes. */
};
};
+#ifndef RTE_GRAPH_PROFILE
static_assert(offsetof(struct rte_node, nodes) - offsetof(struct rte_node, ctx)
== RTE_CACHE_LINE_MIN_SIZE, "rte_node fast path area must fit in 64 bytes");
+#endif
/**
* @internal
@@ -197,7 +211,7 @@ void __rte_node_stream_alloc_size(struct rte_graph *graph,
static __rte_always_inline void
__rte_node_process(struct rte_graph *graph, struct rte_node *node)
{
- uint64_t start;
+ uint64_t cycles;
uint16_t rc;
void **objs;
@@ -206,11 +220,24 @@ __rte_node_process(struct rte_graph *graph, struct rte_node *node)
rte_prefetch0(objs);
if (rte_graph_has_stats_feature()) {
- start = rte_rdtsc();
+ cycles = -rte_rdtsc();
rc = node->process(graph, node, objs, node->idx);
- node->total_cycles += rte_rdtsc() - start;
+ cycles += rte_rdtsc();
+ node->total_cycles += cycles;
node->total_calls++;
node->total_objs += rc;
+#ifdef RTE_GRAPH_PROFILE
+ if (rc <= 1) {
+ node->usage_stats[rc].calls++;
+ node->usage_stats[rc].cycles += cycles;
+ } else if (rc == RTE_GRAPH_BURST_SIZE) {
+ node->full_burst_calls++;
+ node->full_burst_cycles += cycles;
+ } else if (rc == RTE_GRAPH_BURST_SIZE / 2) {
+ node->half_burst_calls++;
+ node->half_burst_cycles += cycles;
+ }
+#endif
} else {
node->process(graph, node, objs, node->idx);
}
--
2.43.0
^ permalink raw reply related
* [PATCH v4] graph: add optional profiling stats
From: Morten Brørup @ 2026-06-21 17:55 UTC (permalink / raw)
To: dev, Jerin Jacob, Kiran Kumar K, Nithin Dabilpuram, Zhirun Yan
Cc: Morten Brørup
In-Reply-To: <20260619202047.2809165-1-mb@smartsharesystems.com>
Added graph node profiling stats, build time configurable by enabling
RTE_GRAPH_PROFILE in rte_config.h.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
---
v4:
* Added documentation. (AI)
* Added more comments. (AI)
* Improved dump. (AI)
v3:
* Debug shows cycles/obj instead of cycles/call.
* Fixed missing --in-reply-to.
v2:
* Fixed indentation.
---
config/rte_config.h | 1 +
doc/guides/prog_guide/graph_lib.rst | 1 +
lib/graph/graph_debug.c | 39 ++++++++++++++++++++++++++++-
lib/graph/node.c | 2 ++
lib/graph/rte_graph_worker_common.h | 23 ++++++++++++++---
5 files changed, 62 insertions(+), 4 deletions(-)
diff --git a/config/rte_config.h b/config/rte_config.h
index 0447cdf2ad..1942c1b1ec 100644
--- a/config/rte_config.h
+++ b/config/rte_config.h
@@ -106,6 +106,7 @@
/* rte_graph defines */
#define RTE_GRAPH_BURST_SIZE 256
#define RTE_LIBRTE_GRAPH_STATS 1
+/* RTE_GRAPH_PROFILE is not set */
/****** driver defines ********/
diff --git a/doc/guides/prog_guide/graph_lib.rst b/doc/guides/prog_guide/graph_lib.rst
index 8dd49c19d2..bc36042296 100644
--- a/doc/guides/prog_guide/graph_lib.rst
+++ b/doc/guides/prog_guide/graph_lib.rst
@@ -49,6 +49,7 @@ Performance tuning parameters
RTE_GRAPH_BURST_SIZE config option.
The testing shows, on x86 and arm64 servers, The sweet spot is 256 burst
size. While on arm64 embedded SoCs, it is either 64 or 128.
+- Enable the ``RTE_GRAPH_PROFILE`` config option for more profiling details.
- Disable node statistics (using ``RTE_LIBRTE_GRAPH_STATS`` config option)
if not needed.
diff --git a/lib/graph/graph_debug.c b/lib/graph/graph_debug.c
index e3b8cccdc1..2aa1e4d22f 100644
--- a/lib/graph/graph_debug.c
+++ b/lib/graph/graph_debug.c
@@ -92,7 +92,44 @@ rte_graph_obj_dump(FILE *f, struct rte_graph *g, bool all)
fprintf(f, " total_sched_fail=%" PRId64 "\n",
n->dispatch.total_sched_fail);
}
- fprintf(f, " total_calls=%" PRId64 "\n", n->total_calls);
+ fprintf(f, " total_calls=%" PRIu64 "\n", n->total_calls);
+ if (rte_graph_has_stats_feature()) {
+ fprintf(f, " total_cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ n->total_cycles,
+ n->total_calls == 0 ? (double)0 :
+ (double)n->total_cycles / (double)n->total_calls);
+ }
+#ifdef RTE_GRAPH_PROFILE
+ uint64_t calls = n->usage_stats[0].calls;
+ fprintf(f, " objs[0]\n");
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ calls,
+ n->usage_stats[0].cycles,
+ calls == 0 ? 0.0 :
+ (double)n->usage_stats[0].cycles / (double)calls);
+ calls = n->usage_stats[1].calls;
+ fprintf(f, " objs[1]\n");
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f\n",
+ calls,
+ n->usage_stats[1].cycles,
+ calls == 0 ? 0.0 :
+ (double)n->usage_stats[1].cycles / (double)calls);
+ calls = RTE_MAX(INT64_C(0), (int64_t)(n->total_calls -
+ (n->usage_stats[0].calls + n->usage_stats[1].calls)));
+ uint64_t cycles = RTE_MAX(INT64_C(0), (int64_t)(n->total_cycles -
+ (n->usage_stats[0].cycles + n->usage_stats[1].cycles)));
+ uint64_t objs = RTE_MAX(INT64_C(0), (int64_t)(n->total_objs -
+ n->usage_stats[1].calls));
+ double objs_per_call = calls == 0 ? 0.0 : (double)objs / (double)calls;
+ fprintf(f, " objs[more], avg objs/call=%.1f\n", objs_per_call);
+ fprintf(f, " calls=%" PRIu64 ", cycles=%" PRIu64 ", avg cycles/call=%.1f"
+ ", avg cycles/obj=%.1f\n",
+ calls,
+ cycles,
+ calls == 0 ? 0.0 : (double)cycles / (double)calls,
+ calls == 0 || objs_per_call == 0.0 ? 0.0 :
+ (double)cycles / (double)calls / objs_per_call);
+#endif
for (i = 0; i < n->nb_edges; i++)
fprintf(f, " edge[%d] <%s>\n", i,
n->nodes[i]->name);
diff --git a/lib/graph/node.c b/lib/graph/node.c
index 1fce3e6632..19b38881ae 100644
--- a/lib/graph/node.c
+++ b/lib/graph/node.c
@@ -110,10 +110,12 @@ __rte_node_register(const struct rte_node_register *reg)
rte_edge_t i;
size_t sz;
+#ifndef RTE_GRAPH_PROFILE
/* Limit Node specific metadata to one cacheline on 64B CL machine */
RTE_BUILD_BUG_ON((offsetof(struct rte_node, nodes) -
offsetof(struct rte_node, ctx)) !=
RTE_CACHE_LINE_MIN_SIZE);
+#endif
graph_spinlock_lock();
diff --git a/lib/graph/rte_graph_worker_common.h b/lib/graph/rte_graph_worker_common.h
index 4ab53a533e..10a52a540b 100644
--- a/lib/graph/rte_graph_worker_common.h
+++ b/lib/graph/rte_graph_worker_common.h
@@ -144,12 +144,22 @@ struct __rte_cache_aligned rte_node {
rte_node_process_t process; /**< Process function. */
uint64_t process_u64;
};
+ /** Fast path area cache line 3. */
+#ifdef RTE_GRAPH_PROFILE
+ struct {
+ uint64_t calls; /**< Calls processing resp. 0 or 1 objects. */
+ uint64_t cycles; /**< Cycles spent processing resp. 0 or 1 objects. */
+ } usage_stats[2]; /**< Usage when this node processed 0 or 1 objects. */
+ /** Fast path area cache line 4. */
+#endif
alignas(RTE_CACHE_LINE_MIN_SIZE) struct rte_node *nodes[]; /**< Next nodes. */
};
};
+#ifndef RTE_GRAPH_PROFILE
static_assert(offsetof(struct rte_node, nodes) - offsetof(struct rte_node, ctx)
== RTE_CACHE_LINE_MIN_SIZE, "rte_node fast path area must fit in 64 bytes");
+#endif
/**
* @internal
@@ -197,7 +207,7 @@ void __rte_node_stream_alloc_size(struct rte_graph *graph,
static __rte_always_inline void
__rte_node_process(struct rte_graph *graph, struct rte_node *node)
{
- uint64_t start;
+ uint64_t cycles;
uint16_t rc;
void **objs;
@@ -206,11 +216,18 @@ __rte_node_process(struct rte_graph *graph, struct rte_node *node)
rte_prefetch0(objs);
if (rte_graph_has_stats_feature()) {
- start = rte_rdtsc();
+ cycles = -rte_rdtsc();
rc = node->process(graph, node, objs, node->idx);
- node->total_cycles += rte_rdtsc() - start;
+ cycles += rte_rdtsc();
+ node->total_cycles += cycles;
node->total_calls++;
node->total_objs += rc;
+#ifdef RTE_GRAPH_PROFILE
+ if (rc <= 1) {
+ node->usage_stats[rc].calls++;
+ node->usage_stats[rc].cycles += cycles;
+ }
+#endif
} else {
node->process(graph, node, objs, node->idx);
}
--
2.43.0
^ permalink raw reply related
* [PATCH v4 19/19] net/dpaa: add ONIC port checks
From: Hemant Agrawal @ 2026-06-21 17:27 UTC (permalink / raw)
To: stephen, david.marchand, dev; +Cc: Vanshika Shukla
In-Reply-To: <20260621172731.2916346-1-hemant.agrawal@nxp.com>
From: Vanshika Shukla <vanshika.shukla@nxp.com>
Add fman_onic MAC type handling to get_rx_port_type() so that ONIC
and offline-internal ports are mapped to OH_OFFLINE_PARSING, consistent
with how the VSP port configuration handles these types. Without this,
ONIC ports used an incorrect port type in flow configuration, leading
to failed FMC operations.
Signed-off-by: Vanshika Shukla <vanshika.shukla@nxp.com>
---
drivers/net/dpaa/dpaa_ethdev.c | 26 ++++---
drivers/net/dpaa/dpaa_ethdev.h | 11 ++-
drivers/net/dpaa/dpaa_flow.c | 129 +++++++++++++++++----------------
drivers/net/dpaa/dpaa_flow.h | 7 +-
4 files changed, 93 insertions(+), 80 deletions(-)
diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index 83210ff775..51ecf04c3c 100644
--- a/drivers/net/dpaa/dpaa_ethdev.c
+++ b/drivers/net/dpaa/dpaa_ethdev.c
@@ -490,7 +490,7 @@ static int dpaa_eth_dev_stop(struct rte_eth_dev *dev)
PMD_INIT_FUNC_TRACE();
dev->data->dev_started = 0;
- if (!fif->is_shared_mac) {
+ if (!fif->is_shared_mac && fif->mac_type != fman_onic) {
fman_if_bmi_stats_disable(fif);
fman_if_disable_rx(fif);
}
@@ -590,7 +590,7 @@ static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
}
}
if (fif->num_profiles) {
- ret = dpaa_port_vsp_cleanup(dpaa_intf, fif);
+ ret = dpaa_port_vsp_cleanup(dpaa_intf);
if (ret) {
DPAA_PMD_WARN("%s: cleanup VSP failed(%d)",
dev->data->name, ret);
@@ -676,7 +676,7 @@ static int dpaa_eth_dev_close(struct rte_eth_dev *dev)
}
}
if (fif->num_profiles) {
- ret = dpaa_port_vsp_cleanup(dpaa_intf, fif);
+ ret = dpaa_port_vsp_cleanup(dpaa_intf);
if (ret) {
DPAA_PMD_WARN("%s: cleanup VSP failed(%d)",
dev->data->name, ret);
@@ -1136,8 +1136,8 @@ static inline int dpaa_eth_rx_queue_bp_check(struct rte_eth_dev *dev,
vsp_id = 0;
}
- if (dpaa_intf->vsp_bpid[vsp_id] &&
- bpid != dpaa_intf->vsp_bpid[vsp_id]) {
+ if (dpaa_intf->vsp[vsp_id].vsp_bp[0] &&
+ bpid != dpaa_intf->vsp[vsp_id].vsp_bp[0]->bpid) {
DPAA_PMD_ERR("Various MPs are assigned to RXQs with same VSP");
return -1;
@@ -1234,9 +1234,9 @@ int dpaa_eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
int8_t vsp_id = rxq->vsp_id;
if (vsp_id >= 0) {
- ret = dpaa_port_vsp_update(dpaa_intf, fmc_q, vsp_id,
- DPAA_MEMPOOL_TO_POOL_INFO(mp)->bpid,
- fif, buffsz + RTE_PKTMBUF_HEADROOM);
+ dpaa_intf->vsp[vsp_id].vsp_bp[0] = DPAA_MEMPOOL_TO_POOL_INFO(mp);
+ dpaa_intf->vsp[vsp_id].bp_num = 1;
+ ret = dpaa_port_vsp_update(dpaa_intf, fmc_q, vsp_id, fif);
if (ret) {
DPAA_PMD_ERR("dpaa_port_vsp_update failed");
return ret;
@@ -1249,12 +1249,14 @@ int dpaa_eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
" to shared interface on DPDK.");
return -EINVAL;
}
- dpaa_intf->vsp_bpid[fif->base_profile_id] =
- DPAA_MEMPOOL_TO_POOL_INFO(mp)->bpid;
+ dpaa_intf->vsp[fif->base_profile_id].vsp_bp[0] =
+ DPAA_MEMPOOL_TO_POOL_INFO(mp);
+ dpaa_intf->vsp[fif->base_profile_id].bp_num = 1;
}
} else {
- dpaa_intf->vsp_bpid[0] =
- DPAA_MEMPOOL_TO_POOL_INFO(mp)->bpid;
+ dpaa_intf->vsp[0].vsp_bp[0] =
+ DPAA_MEMPOOL_TO_POOL_INFO(mp);
+ dpaa_intf->vsp[0].bp_num = 1;
}
dpaa_intf->valid = 1;
diff --git a/drivers/net/dpaa/dpaa_ethdev.h b/drivers/net/dpaa/dpaa_ethdev.h
index d342d98f23..d3e005b556 100644
--- a/drivers/net/dpaa/dpaa_ethdev.h
+++ b/drivers/net/dpaa/dpaa_ethdev.h
@@ -118,6 +118,13 @@ enum {
#define FMC_FILE "/tmp/fmc.bin"
+struct dpaa_if_vsp {
+ struct dpaa_bp_info *vsp_bp[FMAN_PORT_MAX_EXT_POOLS_NUM];
+ uint8_t bp_num;
+ uint32_t max_size;
+ void *vsp_handle;
+};
+
extern struct rte_mempool *dpaa_tx_sg_pool;
/* PMD related logs */
@@ -164,8 +171,8 @@ struct dpaa_if {
*/
struct qman_fq *next_tx_conf_queue;
- void *vsp_handle[DPAA_VSP_PROFILE_MAX_NUM];
- uint32_t vsp_bpid[DPAA_VSP_PROFILE_MAX_NUM];
+ struct dpaa_if_vsp vsp[DPAA_VSP_PROFILE_MAX_NUM];
+ uint8_t base_vsp;
};
struct dpaa_if_stats {
diff --git a/drivers/net/dpaa/dpaa_flow.c b/drivers/net/dpaa/dpaa_flow.c
index 559850ced7..a10ca0cb56 100644
--- a/drivers/net/dpaa/dpaa_flow.c
+++ b/drivers/net/dpaa/dpaa_flow.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright 2017-2019,2021-2025 NXP
+ * Copyright 2017-2019,2021-2026 NXP
*/
/* System headers */
@@ -8,6 +8,7 @@
#include <unistd.h>
#include <sys/types.h>
+#include <dpaa_mempool.h>
#include <dpaa_ethdev.h>
#include <dpaa_flow.h>
#include <rte_dpaa_logs.h>
@@ -724,9 +725,6 @@ int dpaa_fm_deconfig(struct dpaa_if *dpaa_intf,
PMD_INIT_FUNC_TRACE();
- if (!dpaa_intf->port_handle)
- return 0;
-
/* FM PORT Disable */
ret = fm_port_disable(dpaa_intf->port_handle);
if (ret != E_OK) {
@@ -786,8 +784,10 @@ int dpaa_fm_config(struct rte_eth_dev *dev, uint64_t req_dist_set)
unsigned int i = 0;
PMD_INIT_FUNC_TRACE();
- if (dpaa_fm_deconfig(dpaa_intf, fif))
- DPAA_PMD_ERR("DPAA FM deconfig failed");
+ if (dpaa_intf->port_handle) {
+ if (dpaa_fm_deconfig(dpaa_intf, fif))
+ DPAA_PMD_ERR("DPAA FM deconfig failed");
+ }
if (!dev->data->nb_rx_queues)
return 0;
@@ -806,8 +806,7 @@ int dpaa_fm_config(struct rte_eth_dev *dev, uint64_t req_dist_set)
if (fif->num_profiles) {
for (i = 0; i < dev->data->nb_rx_queues; i++)
- dpaa_intf->rx_queues[i].vsp_id =
- fm_default_vsp_id(fif);
+ dpaa_intf->rx_queues[i].vsp_id = fm_default_vsp_id(fif);
i = 0;
}
@@ -939,27 +938,16 @@ int dpaa_fm_term(void)
}
static int dpaa_port_vsp_configure(struct dpaa_if *dpaa_intf,
- uint8_t vsp_id, t_handle fman_handle,
- struct fman_if *fif, u32 mbuf_data_room_size)
+ uint8_t vsp_id, t_handle fman_handle, struct fman_if *fif)
{
+ struct dpaa_if_vsp *vsp;
t_fm_vsp_params vsp_params;
t_fm_buffer_prefix_content buf_prefix_cont;
- uint8_t idx = mac_idx[fif->mac_idx];
+ uint8_t idx = mac_idx[fif->mac_idx], i;
int ret;
+ struct t_fm_ext_pools *pools;
- if (vsp_id == fif->base_profile_id && fif->is_shared_mac) {
- /* For shared interface, VSP of base
- * profile is default pool located in kernel.
- */
- dpaa_intf->vsp_bpid[vsp_id] = 0;
- return 0;
- }
-
- if (vsp_id >= DPAA_VSP_PROFILE_MAX_NUM) {
- DPAA_PMD_ERR("VSP ID %d exceeds MAX number %d",
- vsp_id, DPAA_VSP_PROFILE_MAX_NUM);
- return -1;
- }
+ vsp = &dpaa_intf->vsp[vsp_id];
memset(&vsp_params, 0, sizeof(vsp_params));
vsp_params.h_fm = fman_handle;
@@ -973,17 +961,21 @@ static int dpaa_port_vsp_configure(struct dpaa_if *dpaa_intf,
vsp_params.port_params.port_type = get_rx_port_type(fif);
if (vsp_params.port_params.port_type == e_FM_PORT_TYPE_DUMMY) {
DPAA_PMD_ERR("Mac type %d error", fif->mac_type);
- return -1;
+ return -EINVAL;
}
- vsp_params.ext_buf_pools.num_of_pools_used = 1;
- vsp_params.ext_buf_pools.ext_buf_pool[0].id = dpaa_intf->vsp_bpid[vsp_id];
- vsp_params.ext_buf_pools.ext_buf_pool[0].size = mbuf_data_room_size;
+ pools = &vsp_params.ext_buf_pools;
- dpaa_intf->vsp_handle[vsp_id] = fm_vsp_config(&vsp_params);
- if (!dpaa_intf->vsp_handle[vsp_id]) {
- DPAA_PMD_ERR("fm_vsp_config error for profile %d", vsp_id);
- return -EINVAL;
+ pools->num_of_pools_used = vsp->bp_num;
+ for (i = 0; i < vsp->bp_num; i++) {
+ pools->ext_buf_pool[i].id = vsp->vsp_bp[i]->bpid;
+ pools->ext_buf_pool[i].size = vsp->vsp_bp[i]->size;
+ }
+
+ vsp->vsp_handle = fm_vsp_config(&vsp_params);
+ if (!vsp->vsp_handle) {
+ DPAA_PMD_ERR("Configure VSP[%d] failed!", vsp_id);
+ return -EIO;
}
/* configure the application buffer (structure, size and
@@ -1001,19 +993,18 @@ static int dpaa_port_vsp_configure(struct dpaa_if *dpaa_intf,
buf_prefix_cont.manip_ext_space =
RTE_PKTMBUF_HEADROOM - DPAA_MBUF_HW_ANNOTATION;
- ret = fm_vsp_config_buffer_prefix_content(dpaa_intf->vsp_handle[vsp_id],
- &buf_prefix_cont);
+ ret = fm_vsp_config_buffer_prefix_content(vsp->vsp_handle,
+ &buf_prefix_cont);
if (ret != E_OK) {
- DPAA_PMD_ERR("fm_vsp_config_buffer_prefix_content error for profile %d err: %d",
- vsp_id, ret);
+ DPAA_PMD_ERR("Configure VSP[%d]'s buffer prefix failed(%d)!",
+ vsp_id, ret);
return ret;
}
/* initialize the FM VSP module */
- ret = fm_vsp_init(dpaa_intf->vsp_handle[vsp_id]);
+ ret = fm_vsp_init(vsp->vsp_handle);
if (ret != E_OK) {
- DPAA_PMD_ERR("fm_vsp_init error for profile %d err:%d",
- vsp_id, ret);
+ DPAA_PMD_ERR("Init VSP[%d] failed(%d)!", vsp_id, ret);
return ret;
}
@@ -1021,29 +1012,44 @@ static int dpaa_port_vsp_configure(struct dpaa_if *dpaa_intf,
}
int dpaa_port_vsp_update(struct dpaa_if *dpaa_intf,
- bool fmc_mode, uint8_t vsp_id, uint32_t bpid,
- struct fman_if *fif, u32 mbuf_data_room_size)
+ bool fmc_mode, uint8_t vsp_id, struct fman_if *fif)
{
int ret = 0;
t_handle fman_handle;
+ struct dpaa_if_vsp *vsp;
- if (!fif->num_profiles)
- return 0;
+ if (!fif->num_profiles) {
+ DPAA_PMD_ERR("%s: No multiple VSPs specified!",
+ dpaa_intf->name);
+ return -EINVAL;
+ }
- if (vsp_id >= fif->num_profiles)
- return 0;
+ if (vsp_id >= (fif->base_profile_id + fif->num_profiles)) {
+ DPAA_PMD_ERR("%s: Invalid VSP ID(%d) >= base(%d) + num(%d)",
+ dpaa_intf->name, vsp_id, fif->base_profile_id,
+ fif->num_profiles);
+ return -EINVAL;
+ }
- if (dpaa_intf->vsp_bpid[vsp_id] == bpid)
+ if (vsp_id == fif->base_profile_id && fif->is_shared_mac) {
+ /* For shared interface, VSP of base
+ * profile is default pool located in kernel.
+ */
+ dpaa_intf->vsp[vsp_id].bp_num = 0;
+ dpaa_intf->vsp[vsp_id].vsp_handle = NULL;
return 0;
+ }
+
+ vsp = &dpaa_intf->vsp[vsp_id];
- if (dpaa_intf->vsp_handle[vsp_id]) {
- ret = fm_vsp_free(dpaa_intf->vsp_handle[vsp_id]);
+ if (vsp->vsp_handle) {
+ ret = fm_vsp_free(vsp->vsp_handle);
if (ret != E_OK) {
- DPAA_PMD_ERR("Error fm_vsp_free: err %d vsp_handle[%d]",
- ret, vsp_id);
+ DPAA_PMD_ERR("Free VSP[%d]'s handle failed(%d)",
+ vsp_id, ret);
return ret;
}
- dpaa_intf->vsp_handle[vsp_id] = 0;
+ vsp->vsp_handle = NULL;
}
if (fmc_mode)
@@ -1051,24 +1057,23 @@ int dpaa_port_vsp_update(struct dpaa_if *dpaa_intf,
else
fman_handle = fm_info.fman_handle;
- dpaa_intf->vsp_bpid[vsp_id] = bpid;
-
- return dpaa_port_vsp_configure(dpaa_intf, vsp_id, fman_handle, fif,
- mbuf_data_room_size);
+ return dpaa_port_vsp_configure(dpaa_intf, vsp_id, fman_handle, fif);
}
-int dpaa_port_vsp_cleanup(struct dpaa_if *dpaa_intf, struct fman_if *fif)
+int dpaa_port_vsp_cleanup(struct dpaa_if *dpaa_intf)
{
- int idx, ret;
+ int ret;
+ uint8_t idx;
- for (idx = 0; idx < (uint8_t)fif->num_profiles; idx++) {
- if (dpaa_intf->vsp_handle[idx]) {
- ret = fm_vsp_free(dpaa_intf->vsp_handle[idx]);
+ for (idx = 0; idx < DPAA_VSP_PROFILE_MAX_NUM; idx++) {
+ if (dpaa_intf->vsp[idx].vsp_handle) {
+ ret = fm_vsp_free(dpaa_intf->vsp[idx].vsp_handle);
if (ret != E_OK) {
- DPAA_PMD_ERR("Error fm_vsp_free: err %d"
- " vsp_handle[%d]", ret, idx);
+ DPAA_PMD_ERR("Free VSP[%d] failed(%d)",
+ idx, ret);
return ret;
}
+ dpaa_intf->vsp[idx].vsp_handle = NULL;
}
}
diff --git a/drivers/net/dpaa/dpaa_flow.h b/drivers/net/dpaa/dpaa_flow.h
index 4742b8dd0a..6a949d6dd4 100644
--- a/drivers/net/dpaa/dpaa_flow.h
+++ b/drivers/net/dpaa/dpaa_flow.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright 2017,2019,2022 NXP
+ * Copyright 2017,2019,2022,2026 NXP
*/
#ifndef __DPAA_FLOW_H__
@@ -11,9 +11,8 @@ int dpaa_fm_config(struct rte_eth_dev *dev, uint64_t req_dist_set);
int dpaa_fm_deconfig(struct dpaa_if *dpaa_intf, struct fman_if *fif);
void dpaa_write_fm_config_to_file(void);
int dpaa_port_vsp_update(struct dpaa_if *dpaa_intf,
- bool fmc_mode, uint8_t vsp_id, uint32_t bpid, struct fman_if *fif,
- u32 mbuf_data_room_size);
-int dpaa_port_vsp_cleanup(struct dpaa_if *dpaa_intf, struct fman_if *fif);
+ bool fmc_mode, uint8_t vsp_id, struct fman_if *fif);
+int dpaa_port_vsp_cleanup(struct dpaa_if *dpaa_intf);
int dpaa_port_fmc_init(struct fman_if *fif,
uint32_t *fqids, int8_t *vspids, int max_nb_rxq);
--
2.25.1
^ permalink raw reply related
* [PATCH v4 18/19] dma/dpaa: add SG data validation and ERR050757 fix
From: Hemant Agrawal @ 2026-06-21 17:27 UTC (permalink / raw)
To: stephen, david.marchand, dev; +Cc: Gagandeep Singh
In-Reply-To: <20260621172731.2916346-1-hemant.agrawal@nxp.com>
From: Gagandeep Singh <g.singh@nxp.com>
Add scatter-gather (SG) support to the QDMA driver, enabled by default
via the s_sg_enable flag. Add optional data validation mode controlled
by the s_data_validation flag for debugging transfer correctness.
Add a workaround for hardware errata ERR050757: when
RTE_DMA_DPAA_ERRATA_ERR050757 is defined, configure the source frame
descriptor with stride settings (sss/ssd = FSL_QDMA_CMD_SS_ERR050757_LEN)
to force PCI read transactions to stay within the errata-safe length
limit, preventing data corruption on affected silicon.
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
---
drivers/dma/dpaa/dpaa_qdma.c | 79 +++++++++++++++++++++++++-----------
1 file changed, 55 insertions(+), 24 deletions(-)
diff --git a/drivers/dma/dpaa/dpaa_qdma.c b/drivers/dma/dpaa/dpaa_qdma.c
index af6083d2fe..d0d7998e5e 100644
--- a/drivers/dma/dpaa/dpaa_qdma.c
+++ b/drivers/dma/dpaa/dpaa_qdma.c
@@ -9,9 +9,14 @@
#include "dpaa_qdma.h"
#include "dpaa_qdma_logs.h"
+static int s_data_validation;
+static int s_hw_err_check;
+static int s_sg_enable = 1;
static uint32_t s_sg_max_entry_sz = 2000;
-static bool s_hw_err_check;
+#ifdef RTE_DMA_DPAA_ERRATA_ERR050757
+static int s_pci_read = 1;
+#endif
#define DPAA_DMA_ERROR_CHECK "dpaa_dma_err_check"
static inline void
@@ -112,7 +117,8 @@ dma_pool_alloc(char *nm, int size, int aligned, dma_addr_t *phy_addr)
if (!virt_addr)
return NULL;
- *phy_addr = rte_mem_virt2iova(virt_addr);
+ if (phy_addr)
+ *phy_addr = rte_mem_virt2iova(virt_addr);
return virt_addr;
}
@@ -392,6 +398,8 @@ fsl_qdma_data_validation(struct fsl_qdma_desc *desc[],
char err_msg[512];
int offset;
+ if (likely(!s_data_validation))
+ return;
offset = sprintf(err_msg, "Fatal TC%d/queue%d: ",
fsl_queue->block_id,
@@ -716,19 +724,21 @@ 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 (s_pci_read) {
+ sdf = &ft->df.sdf;
+ sdf->srttype = FSL_QDMA_CMD_RWTTYPE;
#ifdef RTE_DMA_DPAA_ERRATA_ERR050265
- sdf->prefetch = 1;
+ sdf->prefetch = 1;
#endif
- 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;
+ 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;
@@ -832,19 +842,21 @@ fsl_qdma_enqueue_desc_sg(struct fsl_qdma_queue *fsl_queue)
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 (s_pci_read) {
+ sdf = &ft->df.sdf;
+ sdf->srttype = FSL_QDMA_CMD_RWTTYPE;
#ifdef RTE_DMA_DPAA_ERRATA_ERR050265
- sdf->prefetch = 1;
+ sdf->prefetch = 1;
#endif
- 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;
+ 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);
@@ -883,6 +895,25 @@ fsl_qdma_enqueue_desc(struct fsl_qdma_queue *fsl_queue)
fsl_queue->pending_num = 0;
}
return ret;
+ } else if (!s_sg_enable) {
+ while (fsl_queue->pending_num > 0) {
+ ret = fsl_qdma_enqueue_desc_single(fsl_queue,
+ fsl_queue->pending_desc[start].dst,
+ fsl_queue->pending_desc[start].src,
+ fsl_queue->pending_desc[start].len);
+ if (!ret) {
+ start = (start + 1) &
+ (fsl_queue->pending_max - 1);
+ fsl_queue->pending_start = start;
+ fsl_queue->pending_num--;
+ } else {
+ DPAA_QDMA_ERR("Eq pending desc failed(%d)",
+ ret);
+ return -EIO;
+ }
+ }
+
+ return 0;
}
return fsl_qdma_enqueue_desc_sg(fsl_queue);
--
2.25.1
^ permalink raw reply related
* [PATCH v4 17/19] drivers: release DPAA bpid on driver destructor
From: Hemant Agrawal @ 2026-06-21 17:27 UTC (permalink / raw)
To: stephen, david.marchand, dev; +Cc: Jun Yang
In-Reply-To: <20260621172731.2916346-1-hemant.agrawal@nxp.com>
From: Jun Yang <jun.yang@nxp.com>
Track allocated BPIDs in a static per-BPID flag table and register a
driver destructor that releases any BPIDs still marked as in use at
process exit. This prevents BPID leaks when an application exits without
calling rte_mempool_free(). Also tune the per-lcore mempool cache flush
threshold to match the hardware bulk release size (DPAA_MBUF_MAX_ACQ_REL)
so that buffers are returned to HW in optimal burst sizes.
Signed-off-by: Jun Yang <jun.yang@nxp.com>
---
drivers/bus/dpaa/base/qbman/bman.c | 8 +++
drivers/bus/dpaa/dpaa_bus_base_symbols.c | 1 +
drivers/bus/dpaa/include/fsl_bman.h | 3 ++
drivers/mempool/dpaa/dpaa_mempool.c | 67 ++++++++++++++++++++++--
drivers/mempool/dpaa/dpaa_mempool.h | 3 +-
5 files changed, 78 insertions(+), 4 deletions(-)
diff --git a/drivers/bus/dpaa/base/qbman/bman.c b/drivers/bus/dpaa/base/qbman/bman.c
index 01357d6446..b69394b0cc 100644
--- a/drivers/bus/dpaa/base/qbman/bman.c
+++ b/drivers/bus/dpaa/base/qbman/bman.c
@@ -237,6 +237,14 @@ void bman_free_pool(struct bman_pool *pool)
kfree(pool);
}
+void bman_free_bpid(u8 bpid, u32 flags)
+{
+ if (flags & BMAN_POOL_FLAG_THRESH)
+ bm_pool_set(bpid, zero_thresholds);
+ if (flags & BMAN_POOL_FLAG_DYNAMIC_BPID)
+ bman_release_bpid(bpid);
+}
+
const struct bman_pool_params *bman_get_params(const struct bman_pool *pool)
{
return &pool->params;
diff --git a/drivers/bus/dpaa/dpaa_bus_base_symbols.c b/drivers/bus/dpaa/dpaa_bus_base_symbols.c
index 514ab7b1f1..8bd1a9bc6e 100644
--- a/drivers/bus/dpaa/dpaa_bus_base_symbols.c
+++ b/drivers/bus/dpaa/dpaa_bus_base_symbols.c
@@ -46,6 +46,7 @@ RTE_EXPORT_INTERNAL_SYMBOL(netcfg_acquire)
RTE_EXPORT_INTERNAL_SYMBOL(netcfg_release)
RTE_EXPORT_INTERNAL_SYMBOL(bman_new_pool)
RTE_EXPORT_INTERNAL_SYMBOL(bman_free_pool)
+RTE_EXPORT_INTERNAL_SYMBOL(bman_free_bpid)
RTE_EXPORT_INTERNAL_SYMBOL(bman_get_params)
RTE_EXPORT_INTERNAL_SYMBOL(bman_release)
RTE_EXPORT_INTERNAL_SYMBOL(bman_acquire)
diff --git a/drivers/bus/dpaa/include/fsl_bman.h b/drivers/bus/dpaa/include/fsl_bman.h
index 67a7a09618..6079eedff5 100644
--- a/drivers/bus/dpaa/include/fsl_bman.h
+++ b/drivers/bus/dpaa/include/fsl_bman.h
@@ -317,6 +317,9 @@ struct bman_pool *bman_new_pool(const struct bman_pool_params *params);
__rte_internal
void bman_free_pool(struct bman_pool *pool);
+__rte_internal
+void bman_free_bpid(u8 bpid, u32 flags);
+
/**
* bman_get_params - Returns a pool object's parameters.
* @pool: the pool object
diff --git a/drivers/mempool/dpaa/dpaa_mempool.c b/drivers/mempool/dpaa/dpaa_mempool.c
index 3fdbcba646..210ea3bcf9 100644
--- a/drivers/mempool/dpaa/dpaa_mempool.c
+++ b/drivers/mempool/dpaa/dpaa_mempool.c
@@ -25,10 +25,22 @@
#include <rte_eal.h>
#include <rte_malloc.h>
#include <rte_ring.h>
+#include <rte_common.h>
#include <dpaa_mempool.h>
#include <dpaax_iova_table.h>
+struct dpaa_bpid_flag {
+ uint32_t flags;
+ int used;
+};
+
+/** Be referenced in destructor to release bpid allocated.
+ * Destructor can't access bman_pool from eal mem,
+ * we release ID with flag directly.
+ */
+static struct dpaa_bpid_flag s_dpaa_bpid_allocated_flag[DPAA_MAX_BPOOLS];
+
#define FMAN_ERRATA_BOUNDARY ((uint64_t)4096)
#define FMAN_ERRATA_BOUNDARY_MASK (~(FMAN_ERRATA_BOUNDARY - 1))
@@ -58,6 +70,8 @@ dpaa_mbuf_create_pool(struct rte_mempool *mp)
struct bman_pool_params params = {
.flags = BMAN_POOL_FLAG_DYNAMIC_BPID
};
+ unsigned int lcore_id;
+ struct rte_mempool_cache *cache;
MEMPOOL_INIT_FUNC_TRACE();
@@ -115,7 +129,7 @@ dpaa_mbuf_create_pool(struct rte_mempool *mp)
rte_dpaa_bpid_info[bpid].ptov_off = 0;
rte_dpaa_bpid_info[bpid].flags = 0;
- bp_info = rte_malloc(NULL,
+ bp_info = rte_zmalloc(NULL,
sizeof(struct dpaa_bp_info),
RTE_CACHE_LINE_SIZE);
if (!bp_info) {
@@ -127,6 +141,20 @@ dpaa_mbuf_create_pool(struct rte_mempool *mp)
rte_memcpy(bp_info, (void *)&rte_dpaa_bpid_info[bpid],
sizeof(struct dpaa_bp_info));
mp->pool_data = (void *)bp_info;
+ s_dpaa_bpid_allocated_flag[bpid].flags = params.flags;
+ s_dpaa_bpid_allocated_flag[bpid].used = true;
+ /* Update per core mempool cache threshold to optimal value which is
+ * number of buffers that can be released to HW buffer pool in
+ * a single API call.
+ */
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+ cache = &mp->local_cache[lcore_id];
+ DPAA_MEMPOOL_DEBUG("lCore %d: cache->flushthresh %d -> %d",
+ lcore_id, cache->flushthresh,
+ (uint32_t)(cache->size + DPAA_MBUF_MAX_ACQ_REL));
+ if (cache->flushthresh)
+ cache->flushthresh = cache->size + DPAA_MBUF_MAX_ACQ_REL;
+ }
DPAA_MEMPOOL_INFO("BMAN pool created for bpid =%d", bpid);
return 0;
@@ -136,6 +164,7 @@ static void
dpaa_mbuf_free_pool(struct rte_mempool *mp)
{
struct dpaa_bp_info *bp_info = DPAA_MEMPOOL_TO_POOL_INFO(mp);
+ uint16_t i;
MEMPOOL_INIT_FUNC_TRACE();
@@ -143,10 +172,25 @@ dpaa_mbuf_free_pool(struct rte_mempool *mp)
bman_free_pool(bp_info->bp);
DPAA_MEMPOOL_INFO("BMAN pool freed for bpid =%d",
bp_info->bpid);
- rte_free(mp->pool_data);
- bp_info->bp = NULL;
+ rte_dpaa_bpid_info[bp_info->bpid].mp = NULL;
+ rte_dpaa_bpid_info[bp_info->bpid].bp = NULL;
+ s_dpaa_bpid_allocated_flag[bp_info->bpid].used = false;
+ rte_free(bp_info);
mp->pool_data = NULL;
}
+
+ if (!rte_dpaa_bpid_info)
+ return;
+
+ for (i = 0; i < DPAA_MAX_BPOOLS; i++) {
+ if (rte_dpaa_bpid_info[i].mp)
+ break;
+ }
+
+ if (i == DPAA_MAX_BPOOLS) {
+ rte_free(rte_dpaa_bpid_info);
+ rte_dpaa_bpid_info = NULL;
+ }
}
static int
@@ -481,4 +525,21 @@ static const struct rte_mempool_ops dpaa_mpool_ops = {
.populate = dpaa_populate,
};
+#define RTE_PRIORITY_104 104
+
+RTE_FINI_PRIO(dpaa_mpool_finish, 104)
+{
+ uint16_t bpid;
+
+ for (bpid = 0; bpid < DPAA_MAX_BPOOLS; bpid++) {
+ if (s_dpaa_bpid_allocated_flag[bpid].used) {
+ bman_free_bpid(bpid, s_dpaa_bpid_allocated_flag[bpid].flags);
+ s_dpaa_bpid_allocated_flag[bpid].used = false;
+ }
+ }
+ /** The rte_dpaa_bpid_info and bman_pool from EAL mem have been released
+ * with EAL mem pool being destroyed.
+ */
+}
+
RTE_MEMPOOL_REGISTER_OPS(dpaa_mpool_ops);
diff --git a/drivers/mempool/dpaa/dpaa_mempool.h b/drivers/mempool/dpaa/dpaa_mempool.h
index 865b533b8f..d7ee49b557 100644
--- a/drivers/mempool/dpaa/dpaa_mempool.h
+++ b/drivers/mempool/dpaa/dpaa_mempool.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: BSD-3-Clause
*
- * Copyright 2017,2019,2024 -2025 NXP
+ * Copyright 2017,2019,2024 -2026 NXP
*
*/
#ifndef __DPAA_MEMPOOL_H__
@@ -24,6 +24,7 @@
/* total number of bpools on SoC */
#define DPAA_MAX_BPOOLS 256
+#define DPAA_INVALID_BPID DPAA_MAX_BPOOLS
/* Maximum release/acquire from BMAN */
#define DPAA_MBUF_MAX_ACQ_REL FSL_BM_BURST_MAX
--
2.25.1
^ permalink raw reply related
* [PATCH v4 16/19] drivers: optimize DPAA multi-entry buffer pool operations
From: Hemant Agrawal @ 2026-06-21 17:27 UTC (permalink / raw)
To: stephen, david.marchand, dev; +Cc: Jun Yang
In-Reply-To: <20260621172731.2916346-1-hemant.agrawal@nxp.com>
From: Jun Yang <jun.yang@nxp.com>
Replace the hardcoded buffer acquire count of 8 with the FSL_BM_BURST_MAX
constant when acquiring buffers from the buffer pool. Use a single
bm_hw_buf_desc structure for HW initialization of the first entry and copy
it to remaining entries, ensuring consistent HW descriptor state across
all entries in the pool.
Signed-off-by: Jun Yang <jun.yang@nxp.com>
---
drivers/bus/dpaa/base/qbman/bman.c | 51 +++++++----------------------
drivers/bus/dpaa/include/fsl_bman.h | 46 +++++++++++++++++++++-----
drivers/mempool/dpaa/dpaa_mempool.c | 8 ++---
3 files changed, 54 insertions(+), 51 deletions(-)
diff --git a/drivers/bus/dpaa/base/qbman/bman.c b/drivers/bus/dpaa/base/qbman/bman.c
index ee4232d0a0..01357d6446 100644
--- a/drivers/bus/dpaa/base/qbman/bman.c
+++ b/drivers/bus/dpaa/base/qbman/bman.c
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
*
* Copyright 2008-2016 Freescale Semiconductor Inc.
- * Copyright 2017, 2024 NXP
+ * Copyright 2017, 2024-2026 NXP
*
*/
#include <rte_memcpy.h>
@@ -17,20 +17,6 @@
#define IRQNAME "BMan portal %d"
#define MAX_IRQNAME 16 /* big enough for "BMan portal %d" */
-
-#define MAX_U16 UINT16_MAX
-#define MAX_U32 UINT32_MAX
-#ifndef BIT_SIZE
-#define BIT_SIZE(t) (sizeof(t) * 8)
-#endif
-#define MAX_U48 \
- ((((uint64_t)MAX_U16) << BIT_SIZE(uint32_t)) | MAX_U32)
-#define HI16_OF_U48(x) \
- (((x) >> BIT_SIZE(rte_be32_t)) & MAX_U16)
-#define LO32_OF_U48(x) ((x) & MAX_U32)
-#define U48_BY_HI16_LO32(hi, lo) \
- (((hi) << BIT_SIZE(uint32_t)) | (lo))
-
struct bman_portal {
struct bm_portal p;
/* 2-element array. pools[0] is mask, pools[1] is snapshot. */
@@ -273,7 +259,7 @@ bman_release_fast(struct bman_pool *pool, const uint64_t *bufs,
struct bm_rcr_entry *r;
uint8_t i, avail;
uint64_t bpid = pool->params.bpid;
- struct bm_hw_buf_desc bm_bufs[FSL_BM_BURST_MAX];
+ struct bm_buffer bm_bufs[FSL_BM_BURST_MAX];
#ifdef RTE_LIBRTE_DPAA_HWDEBUG
if (!num || (num > FSL_BM_BURST_MAX))
@@ -290,19 +276,17 @@ bman_release_fast(struct bman_pool *pool, const uint64_t *bufs,
if (unlikely(!r))
return -EBUSY;
+ bm_bufs[0].be_desc.bpid = bpid;
+ for (i = 0; i < num; i++)
+ bm_buffer_set64_to_be(&bm_bufs[i], bufs[i]);
/*
* we can copy all but the first entry, as this can trigger badness
* with the valid-bit
*/
- bm_bufs[0].bpid = bpid;
- bm_bufs[0].hi_addr = cpu_to_be16(HI16_OF_U48(bufs[0]));
- bm_bufs[0].lo_addr = cpu_to_be32(LO32_OF_U48(bufs[0]));
- for (i = 1; i < num; i++) {
- bm_bufs[i].hi_addr = cpu_to_be16(HI16_OF_U48(bufs[i]));
- bm_bufs[i].lo_addr = cpu_to_be32(LO32_OF_U48(bufs[i]));
- }
-
- memcpy(r->bufs, bm_bufs, sizeof(struct bm_buffer) * num);
+ r->bufs[0].opaque = bm_bufs[0].opaque;
+ if (num > 1)
+ rte_memcpy(&r->bufs[1], &bm_bufs[1],
+ sizeof(struct bm_buffer) * (num - 1));
bm_rcr_pvb_commit(&p->p, BM_RCR_VERB_CMD_BPID_SINGLE |
(num & BM_RCR_VERB_BUFCOUNT_MASK));
@@ -360,16 +344,6 @@ __rte_unused bman_extract_addr(struct bm_buffer *buf)
return buf->addr;
}
-static inline uint64_t
-bman_hw_extract_addr(struct bm_hw_buf_desc *buf)
-{
- uint64_t hi, lo;
-
- hi = be16_to_cpu(buf->hi_addr);
- lo = be32_to_cpu(buf->lo_addr);
- return U48_BY_HI16_LO32(hi, lo);
-}
-
RTE_EXPORT_INTERNAL_SYMBOL(bman_acquire_fast)
int
bman_acquire_fast(struct bman_pool *pool, uint64_t *bufs, uint8_t num)
@@ -378,7 +352,7 @@ bman_acquire_fast(struct bman_pool *pool, uint64_t *bufs, uint8_t num)
struct bm_mc_command *mcc;
struct bm_mc_result *mcr;
uint8_t i, rst;
- struct bm_hw_buf_desc bm_bufs[FSL_BM_BURST_MAX];
+ struct bm_buffer bm_bufs[FSL_BM_BURST_MAX];
#ifdef RTE_LIBRTE_DPAA_HWDEBUG
if (!num || (num > FSL_BM_BURST_MAX))
@@ -397,11 +371,10 @@ bman_acquire_fast(struct bman_pool *pool, uint64_t *bufs, uint8_t num)
if (unlikely(rst < 1 || rst > FSL_BM_BURST_MAX))
return -EINVAL;
- rte_memcpy(bm_bufs, mcr->acquire.bufs,
- sizeof(struct bm_buffer) * rst);
+ rte_memcpy(bm_bufs, mcr->acquire.bufs, sizeof(struct bm_buffer) * rst);
for (i = 0; i < rst; i++)
- bufs[i] = bman_hw_extract_addr(&bm_bufs[i]);
+ bufs[i] = bm_buffer_get64_from_be(&bm_bufs[i]);
return rst;
}
diff --git a/drivers/bus/dpaa/include/fsl_bman.h b/drivers/bus/dpaa/include/fsl_bman.h
index 2d24b89889..67a7a09618 100644
--- a/drivers/bus/dpaa/include/fsl_bman.h
+++ b/drivers/bus/dpaa/include/fsl_bman.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
*
* Copyright 2008-2012 Freescale Semiconductor, Inc.
- * Copyright 2024 NXP
+ * Copyright 2024-2026 NXP
*
*/
@@ -42,6 +42,13 @@ struct bm_mc_result; /* MC result */
* pool id specific to this buffer is needed (BM_RCR_VERB_CMD_BPID_MULTI,
* BM_MCC_VERB_ACQUIRE), the 'bpid' field is used.
*/
+struct __rte_packed_begin bm_hw_buf_desc {
+ uint8_t rsv;
+ uint8_t bpid;
+ rte_be16_t hi; /* High 16-bits of 48-bit address */
+ rte_be32_t lo; /* Low 32-bits of 48-bit address */
+} __rte_packed_end;
+
struct __rte_aligned(8) bm_buffer {
union {
struct {
@@ -66,17 +73,11 @@ struct __rte_aligned(8) bm_buffer {
u64 __notaddress:16;
#endif
};
+ struct bm_hw_buf_desc be_desc;
u64 opaque;
};
};
-struct __rte_packed_begin bm_hw_buf_desc {
- uint8_t rsv;
- uint8_t bpid;
- rte_be16_t hi_addr; /* High 16-bits of 48-bit address */
- rte_be32_t lo_addr; /* Low 32-bits of 48-bit address */
-} __rte_packed_end;
-
static inline u64 bm_buffer_get64(const struct bm_buffer *buf)
{
return buf->addr;
@@ -87,6 +88,17 @@ static inline dma_addr_t bm_buf_addr(const struct bm_buffer *buf)
return (dma_addr_t)buf->addr;
}
+#ifndef BIT_SIZE
+#define BIT_SIZE(t) (sizeof(t) * 8)
+#endif
+#define MAX_U48 \
+ ((((uint64_t)UINT16_MAX) << BIT_SIZE(uint32_t)) | UINT32_MAX)
+#define HI16_OF_U48(x) \
+ (((x) >> BIT_SIZE(uint32_t)) & UINT16_MAX)
+#define LO32_OF_U48(x) ((x) & UINT32_MAX)
+#define U48_BY_HI16_LO32(hi, lo) \
+ (((hi) << BIT_SIZE(uint32_t)) | (lo))
+
#define bm_buffer_set64(buf, v) \
do { \
struct bm_buffer *__buf931 = (buf); \
@@ -94,6 +106,24 @@ static inline dma_addr_t bm_buf_addr(const struct bm_buffer *buf)
__buf931->lo = lower_32_bits(v); \
} while (0)
+#define bm_buffer_set64_to_be(buf, v) \
+ do { \
+ struct bm_buffer *__buf931 = (buf); \
+ \
+ __buf931->be_desc.hi = cpu_to_be16(HI16_OF_U48(v)); \
+ __buf931->be_desc.lo = cpu_to_be32(LO32_OF_U48(v)); \
+ } while (0)
+
+#define bm_buffer_get64_from_be(buf) \
+ ({ \
+ uint64_t hi, lo; \
+ struct bm_buffer *__buf931 = (buf); \
+ \
+ hi = be16_to_cpu(__buf931->be_desc.hi); \
+ lo = be32_to_cpu(__buf931->be_desc.lo); \
+ U48_BY_HI16_LO32(hi, lo); \
+ })
+
#define FSL_BM_BURST_MAX 8
/* See 1.5.3.5.4: "Release Command" */
diff --git a/drivers/mempool/dpaa/dpaa_mempool.c b/drivers/mempool/dpaa/dpaa_mempool.c
index 2f8555a026..3fdbcba646 100644
--- a/drivers/mempool/dpaa/dpaa_mempool.c
+++ b/drivers/mempool/dpaa/dpaa_mempool.c
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: BSD-3-Clause
*
- * Copyright 2017,2019,2023-2025 NXP
+ * Copyright 2017,2019,2023-2026 NXP
*
*/
@@ -50,7 +50,7 @@ static int
dpaa_mbuf_create_pool(struct rte_mempool *mp)
{
struct bman_pool *bp;
- struct bm_buffer bufs[8];
+ struct bm_buffer bufs[FSL_BM_BURST_MAX];
struct dpaa_bp_info *bp_info;
uint8_t bpid;
int num_bufs = 0, ret = 0;
@@ -83,8 +83,8 @@ dpaa_mbuf_create_pool(struct rte_mempool *mp)
* then in 1s for the remainder.
*/
if (ret != 1)
- ret = bman_acquire(bp, bufs, 8, 0);
- if (ret < 8)
+ ret = bman_acquire(bp, bufs, FSL_BM_BURST_MAX, 0);
+ if (ret < FSL_BM_BURST_MAX)
ret = bman_acquire(bp, bufs, 1, 0);
if (ret > 0)
num_bufs += ret;
--
2.25.1
^ permalink raw reply related
* [PATCH v4 15/19] net/dpaa: report error on using deferred start
From: Hemant Agrawal @ 2026-06-21 17:27 UTC (permalink / raw)
To: stephen, david.marchand, dev
In-Reply-To: <20260621172731.2916346-1-hemant.agrawal@nxp.com>
This patch add support to report on error
for rx and tx deferred start config
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
drivers/net/dpaa/dpaa_ethdev.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index 2e3757ca03..83210ff775 100644
--- a/drivers/net/dpaa/dpaa_ethdev.c
+++ b/drivers/net/dpaa/dpaa_ethdev.c
@@ -1174,6 +1174,12 @@ int dpaa_eth_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
rxq->nb_desc = UINT16_MAX;
rxq->offloads = rx_conf->offloads;
+ /* Rx deferred start is not supported */
+ if (rx_conf->rx_deferred_start) {
+ DPAA_PMD_ERR("%p:Rx deferred start not supported", (void *)dev);
+ return -EINVAL;
+ }
+
DPAA_PMD_INFO("Rx queue setup for queue index: %d fq_id (0x%x)",
queue_idx, rxq->fqid);
@@ -1480,6 +1486,12 @@ int dpaa_eth_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
txq->nb_desc = UINT16_MAX;
txq->offloads = tx_conf->offloads;
+ /* Tx deferred start is not supported */
+ if (tx_conf->tx_deferred_start) {
+ DPAA_PMD_ERR("%p:Tx deferred start not supported", (void *)dev);
+ return -EINVAL;
+ }
+
if (queue_idx >= dev->data->nb_tx_queues) {
rte_errno = EOVERFLOW;
DPAA_PMD_ERR("%p: queue index out of range (%u >= %u)",
--
2.25.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox