/*-
* BSD LICENSE
- *
+ *
* Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
* All rights reserved.
- *
+ *
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
- *
+ *
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* * Neither the name of Intel Corporation nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
- *
+ *
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
#include <rte_ethdev.h>
#include <rte_log.h>
#include <rte_string_fns.h>
+#include <rte_malloc.h>
#include "main.h"
#include "virtio-net.h"
(num_switching_cores*RTE_TEST_TX_DESC_DEFAULT) +\
(num_switching_cores*MBUF_CACHE_SIZE))
-#define MBUF_CACHE_SIZE 128
+#define MBUF_CACHE_SIZE 128
#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)
+/*
+ * No frame data buffer allocated from host are required for zero copy
+ * implementation, guest will allocate the frame data buffer, and vhost
+ * directly use it.
+ */
+#define VIRTIO_DESCRIPTOR_LEN_ZCP 1518
+#define MBUF_SIZE_ZCP (VIRTIO_DESCRIPTOR_LEN_ZCP + sizeof(struct rte_mbuf) \
+ + RTE_PKTMBUF_HEADROOM)
+#define MBUF_CACHE_SIZE_ZCP 0
+
/*
* RX and TX Prefetch, Host, and Write-back threshold values should be
* carefully set for optimal performance. Consult the network
#define BURST_RX_WAIT_US 15 /* Defines how long we wait between retries on RX */
#define BURST_RX_RETRIES 4 /* Number of retries on RX. */
+#define JUMBO_FRAME_MAX_SIZE 0x2600
+
/* State of virtio device. */
#define DEVICE_MAC_LEARNING 0
#define DEVICE_RX 1
#define ACK_DEV_REMOVAL 0
/* Configurable number of RX/TX ring descriptors */
-#define RTE_TEST_RX_DESC_DEFAULT 1024
+#define RTE_TEST_RX_DESC_DEFAULT 1024
#define RTE_TEST_TX_DESC_DEFAULT 512
+/*
+ * Need refine these 2 macros for legacy and DPDK based front end:
+ * Max vring avail descriptor/entries from guest - MAX_PKT_BURST
+ * And then adjust power 2.
+ */
+/*
+ * For legacy front end, 128 descriptors,
+ * half for virtio header, another half for mbuf.
+ */
+#define RTE_TEST_RX_DESC_DEFAULT_ZCP 32 /* legacy: 32, DPDK virt FE: 128. */
+#define RTE_TEST_TX_DESC_DEFAULT_ZCP 64 /* legacy: 64, DPDK virt FE: 64. */
+
+/* Get first 4 bytes in mbuf headroom. */
+#define MBUF_HEADROOM_UINT32(mbuf) (*(uint32_t *)((uint8_t *)(mbuf) \
+ + sizeof(struct rte_mbuf)))
+
+/* true if x is a power of 2 */
+#define POWEROF2(x) ((((x)-1) & (x)) == 0)
+
#define INVALID_PORT_ID 0xFF
/* Max number of devices. Limited by vmdq. */
#define MAX_DEVICES 64
-/* Size of buffers used for rte_snprintfs. */
+/* Size of buffers used for snprintfs. */
#define MAX_PRINT_BUFF 6072
/* Maximum character device basename size. */
static uint32_t num_queues = 0;
uint32_t num_devices = 0;
+/*
+ * Enable zero copy, pkts buffer will directly dma to hw descriptor,
+ * disabled on default.
+ */
+static uint32_t zero_copy;
+
+/* number of descriptors to apply*/
+static uint32_t num_rx_descriptor = RTE_TEST_RX_DESC_DEFAULT_ZCP;
+static uint32_t num_tx_descriptor = RTE_TEST_TX_DESC_DEFAULT_ZCP;
+
+/* max ring descriptor, ixgbe, i40e, e1000 all are 4096. */
+#define MAX_RING_DESC 4096
+
+struct vpool {
+ struct rte_mempool *pool;
+ struct rte_ring *ring;
+ uint32_t buf_size;
+} vpool_array[MAX_QUEUES+MAX_QUEUES];
+
/* Enable VM2VM communications. If this is disabled then the MAC address compare is skipped. */
-static uint32_t enable_vm2vm = 1;
+typedef enum {
+ VM2VM_DISABLED = 0,
+ VM2VM_SOFTWARE = 1,
+ VM2VM_HARDWARE = 2,
+ VM2VM_LAST
+} vm2vm_type;
+static vm2vm_type vm2vm_mode = VM2VM_SOFTWARE;
+
+/* The type of host physical address translated from guest physical address. */
+typedef enum {
+ PHYS_ADDR_CONTINUOUS = 0,
+ PHYS_ADDR_CROSS_SUBREG = 1,
+ PHYS_ADDR_INVALID = 2,
+ PHYS_ADDR_LAST
+} hpa_type;
+
/* Enable stats. */
static uint32_t enable_stats = 0;
/* Enable retries on RX. */
extern uint64_t VHOST_FEATURES;
/* Default configuration for rx and tx thresholds etc. */
-static const struct rte_eth_rxconf rx_conf_default = {
+static struct rte_eth_rxconf rx_conf_default = {
.rx_thresh = {
.pthresh = RX_PTHRESH,
.hthresh = RX_HTHRESH,
* Controller and the DPDK ixgbe/igb PMD. Consider using other values for other
* network controllers and/or network drivers.
*/
-static const struct rte_eth_txconf tx_conf_default = {
+static struct rte_eth_txconf tx_conf_default = {
.tx_thresh = {
.pthresh = TX_PTHRESH,
.hthresh = TX_HTHRESH,
};
/* empty vmdq configuration structure. Filled in programatically */
-static const struct rte_eth_conf vmdq_conf_default = {
+static struct rte_eth_conf vmdq_conf_default = {
.rxmode = {
.mq_mode = ETH_MQ_RX_VMDQ_ONLY,
.split_hdr_size = 0,
static uint8_t ports[RTE_MAX_ETHPORTS];
static unsigned num_ports = 0; /**< The number of ports specified in command line */
+static const uint16_t external_pkt_default_vlan_tag = 2000;
const uint16_t vlan_tags[] = {
1000, 1001, 1002, 1003, 1004, 1005, 1006, 1007,
1008, 1009, 1010, 1011, 1012, 1013, 1014, 1015,
/* TX queue for each data core. */
struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE];
+/* TX queue fori each virtio device for zero copy. */
+struct mbuf_table tx_queue_zcp[MAX_QUEUES];
+
/* Vlan header struct used to insert vlan tags on TX. */
struct vlan_ethhdr {
unsigned char h_dest[ETH_ALEN];
__be16 h_vlan_encapsulated_proto;
};
+/* IPv4 Header */
+struct ipv4_hdr {
+ uint8_t version_ihl; /**< version and header length */
+ uint8_t type_of_service; /**< type of service */
+ uint16_t total_length; /**< length of packet */
+ uint16_t packet_id; /**< packet ID */
+ uint16_t fragment_offset; /**< fragmentation offset */
+ uint8_t time_to_live; /**< time to live */
+ uint8_t next_proto_id; /**< protocol ID */
+ uint16_t hdr_checksum; /**< header checksum */
+ uint32_t src_addr; /**< source address */
+ uint32_t dst_addr; /**< destination address */
+} __attribute__((__packed__));
+
/* Header lengths. */
#define VLAN_HLEN 4
#define VLAN_ETH_HLEN 18
/* Per-device statistics struct */
struct device_statistics {
uint64_t tx_total;
- rte_atomic64_t rx_total;
+ rte_atomic64_t rx_total_atomic;
+ uint64_t rx_total;
uint64_t tx;
- rte_atomic64_t rx;
+ rte_atomic64_t rx_atomic;
+ uint64_t rx;
} __rte_cache_aligned;
struct device_statistics dev_statistics[MAX_DEVICES];
memset(&conf, 0, sizeof(conf));
conf.nb_queue_pools = (enum rte_eth_nb_pools)num_devices;
conf.nb_pool_maps = num_devices;
+ conf.enable_loop_back =
+ vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back;
for (i = 0; i < conf.nb_pool_maps; i++) {
conf.pool_map[i].vlan_id = vlan_tags[ i ];
}
/*
- * Validate the device number according to the max pool number gotten form dev_info
- * If the device number is invalid, give the error message and return -1.
- * Each device must have its own pool.
+ * Validate the device number according to the max pool number gotten form
+ * dev_info. If the device number is invalid, give the error message and
+ * return -1. Each device must have its own pool.
*/
static inline int
validate_num_devices(uint32_t max_nb_devices)
{
if (num_devices > max_nb_devices) {
- RTE_LOG(ERR, PORT, "invalid number of devices\n");
+ RTE_LOG(ERR, VHOST_PORT, "invalid number of devices\n");
return -1;
}
return 0;
* coming from the mbuf_pool passed as parameter
*/
static inline int
-port_init(uint8_t port, struct rte_mempool *mbuf_pool)
+port_init(uint8_t port)
{
struct rte_eth_dev_info dev_info;
struct rte_eth_conf port_conf;
- uint16_t rx_rings, tx_rings = (uint16_t)rte_lcore_count();
- const uint16_t rx_ring_size = RTE_TEST_RX_DESC_DEFAULT, tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
+ uint16_t rx_rings, tx_rings;
+ uint16_t rx_ring_size, tx_ring_size;
int retval;
uint16_t q;
num_devices = dev_info.max_vmdq_pools;
num_queues = dev_info.max_rx_queues;
+ if (zero_copy) {
+ rx_ring_size = num_rx_descriptor;
+ tx_ring_size = num_tx_descriptor;
+ tx_rings = dev_info.max_tx_queues;
+ } else {
+ rx_ring_size = RTE_TEST_RX_DESC_DEFAULT;
+ tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
+ tx_rings = (uint16_t)rte_lcore_count();
+ }
+
retval = validate_num_devices(MAX_DEVICES);
if (retval < 0)
return retval;
for (q = 0; q < rx_rings; q ++) {
retval = rte_eth_rx_queue_setup(port, q, rx_ring_size,
rte_eth_dev_socket_id(port), &rx_conf_default,
- mbuf_pool);
+ vpool_array[q].pool);
if (retval < 0)
return retval;
}
/* Start the device. */
retval = rte_eth_dev_start(port);
- if (retval < 0)
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_DATA, "Failed to start the device.\n");
return retval;
+ }
rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]);
- RTE_LOG(INFO, PORT, "Max virtio devices supported: %u\n", num_devices);
- RTE_LOG(INFO, PORT, "Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
+ RTE_LOG(INFO, VHOST_PORT, "Max virtio devices supported: %u\n", num_devices);
+ RTE_LOG(INFO, VHOST_PORT, "Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8
" %02"PRIx8" %02"PRIx8" %02"PRIx8"\n",
(unsigned)port,
vmdq_ports_eth_addr[port].addr_bytes[0],
if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ)
return -1;
else
- rte_snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);
+ snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);
return 0;
}
static void
us_vhost_usage(const char *prgname)
{
- RTE_LOG(INFO, CONFIG, "%s [EAL options] -- -p PORTMASK --vm2vm [0|1] --rx_retry [0|1] --mergeable [0|1] --stats [0-N] --dev-basename <name> --dev-index [0-N] --nb-devices ND\n"
+ RTE_LOG(INFO, VHOST_CONFIG, "%s [EAL options] -- -p PORTMASK\n"
+ " --vm2vm [0|1|2]\n"
+ " --rx_retry [0|1] --mergeable [0|1] --stats [0-N]\n"
+ " --dev-basename <name> --dev-index [0-N]\n"
+ " --nb-devices ND\n"
" -p PORTMASK: Set mask for ports to be used by application\n"
- " --vm2vm [0|1]: disable/enable(default) vm2vm comms\n"
+ " --vm2vm [0|1|2]: disable/software(default)/hardware vm2vm comms\n"
" --rx-retry [0|1]: disable/enable(default) retries on rx. Enable retry if destintation queue is full\n"
" --rx-retry-delay [0-N]: timeout(in usecond) between retries on RX. This makes effect only if retries on rx enabled\n"
" --rx-retry-num [0-N]: the number of retries on rx. This makes effect only if retries on rx enabled\n"
" --mergeable [0|1]: disable(default)/enable RX mergeable buffers\n"
" --stats [0-N]: 0: Disable stats, N: Time in seconds to print stats\n"
" --dev-basename: The basename to be used for the character device.\n"
- " --dev-index [0-N]: Defaults to zero if not used. Index is appended to basename.\n",
+ " --dev-index [0-N]: Defaults to zero if not used. Index is appended to basename.\n"
+ " --zero-copy [0|1]: disable(default)/enable rx/tx "
+ "zero copy\n"
+ " --rx-desc-num [0-N]: the number of descriptors on rx, "
+ "used only when zero copy is enabled.\n"
+ " --tx-desc-num [0-N]: the number of descriptors on tx, "
+ "used only when zero copy is enabled.\n",
prgname);
}
{"stats", required_argument, NULL, 0},
{"dev-basename", required_argument, NULL, 0},
{"dev-index", required_argument, NULL, 0},
- {NULL, 0, 0, 0}
+ {"zero-copy", required_argument, NULL, 0},
+ {"rx-desc-num", required_argument, NULL, 0},
+ {"tx-desc-num", required_argument, NULL, 0},
+ {NULL, 0, 0, 0},
};
/* Parse command line */
case 'p':
enabled_port_mask = parse_portmask(optarg);
if (enabled_port_mask == 0) {
- RTE_LOG(INFO, CONFIG, "Invalid portmask\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid portmask\n");
us_vhost_usage(prgname);
return -1;
}
case 0:
/* Enable/disable vm2vm comms. */
- if (!strncmp(long_option[option_index].name, "vm2vm", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, 1);
+ if (!strncmp(long_option[option_index].name, "vm2vm",
+ MAX_LONG_OPT_SZ)) {
+ ret = parse_num_opt(optarg, (VM2VM_LAST - 1));
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for vm2vm [0|1]\n");
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for "
+ "vm2vm [0|1|2]\n");
us_vhost_usage(prgname);
return -1;
} else {
- enable_vm2vm = ret;
+ vm2vm_mode = (vm2vm_type)ret;
}
}
if (!strncmp(long_option[option_index].name, "rx-retry", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, 1);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry [0|1]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry [0|1]\n");
us_vhost_usage(prgname);
return -1;
} else {
if (!strncmp(long_option[option_index].name, "rx-retry-delay", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-delay [0-N]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-delay [0-N]\n");
us_vhost_usage(prgname);
return -1;
} else {
if (!strncmp(long_option[option_index].name, "rx-retry-num", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for rx-retry-num [0-N]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for rx-retry-num [0-N]\n");
us_vhost_usage(prgname);
return -1;
} else {
if (!strncmp(long_option[option_index].name, "mergeable", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, 1);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for mergeable [0|1]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for mergeable [0|1]\n");
us_vhost_usage(prgname);
return -1;
} else {
- if (ret)
+ if (ret) {
+ vmdq_conf_default.rxmode.jumbo_frame = 1;
+ vmdq_conf_default.rxmode.max_rx_pkt_len
+ = JUMBO_FRAME_MAX_SIZE;
VHOST_FEATURES = (1ULL << VIRTIO_NET_F_MRG_RXBUF);
+ }
}
}
if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for stats [0..N]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for stats [0..N]\n");
us_vhost_usage(prgname);
return -1;
} else {
/* Set character device basename. */
if (!strncmp(long_option[option_index].name, "dev-basename", MAX_LONG_OPT_SZ)) {
if (us_vhost_parse_basename(optarg) == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ);
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ);
us_vhost_usage(prgname);
return -1;
}
if (!strncmp(long_option[option_index].name, "dev-index", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
if (ret == -1) {
- RTE_LOG(INFO, CONFIG, "Invalid argument for character device index [0..N]\n");
+ RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device index [0..N]\n");
us_vhost_usage(prgname);
return -1;
- } else {
+ } else
dev_index = ret;
+ }
+
+ /* Enable/disable rx/tx zero copy. */
+ if (!strncmp(long_option[option_index].name,
+ "zero-copy", MAX_LONG_OPT_SZ)) {
+ ret = parse_num_opt(optarg, 1);
+ if (ret == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument"
+ " for zero-copy [0|1]\n");
+ us_vhost_usage(prgname);
+ return -1;
+ } else
+ zero_copy = ret;
+
+ if (zero_copy) {
+#ifdef RTE_MBUF_REFCNT
+ RTE_LOG(ERR, VHOST_CONFIG, "Before running "
+ "zero copy vhost APP, please "
+ "disable RTE_MBUF_REFCNT\n"
+ "in config file and then rebuild DPDK "
+ "core lib!\n"
+ "Otherwise please disable zero copy "
+ "flag in command line!\n");
+ return -1;
+#endif
+ }
+ }
+
+ /* Specify the descriptor number on RX. */
+ if (!strncmp(long_option[option_index].name,
+ "rx-desc-num", MAX_LONG_OPT_SZ)) {
+ ret = parse_num_opt(optarg, MAX_RING_DESC);
+ if ((ret == -1) || (!POWEROF2(ret))) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for rx-desc-num[0-N],"
+ "power of 2 required.\n");
+ us_vhost_usage(prgname);
+ return -1;
+ } else {
+ num_rx_descriptor = ret;
+ }
+ }
+
+ /* Specify the descriptor number on TX. */
+ if (!strncmp(long_option[option_index].name,
+ "tx-desc-num", MAX_LONG_OPT_SZ)) {
+ ret = parse_num_opt(optarg, MAX_RING_DESC);
+ if ((ret == -1) || (!POWEROF2(ret))) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for tx-desc-num [0-N],"
+ "power of 2 required.\n");
+ us_vhost_usage(prgname);
+ return -1;
+ } else {
+ num_tx_descriptor = ret;
}
}
}
if ((num_ports == 0) || (num_ports > MAX_SUP_PORTS)) {
- RTE_LOG(INFO, PORT, "Current enabled port number is %u,"
+ RTE_LOG(INFO, VHOST_PORT, "Current enabled port number is %u,"
"but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS);
return -1;
}
+ if ((zero_copy == 1) && (vm2vm_mode == VM2VM_SOFTWARE)) {
+ RTE_LOG(INFO, VHOST_PORT,
+ "Vhost zero copy doesn't support software vm2vm,"
+ "please specify 'vm2vm 2' to use hardware vm2vm.\n");
+ return -1;
+ }
+
+ if ((zero_copy == 1) && (vmdq_conf_default.rxmode.jumbo_frame == 1)) {
+ RTE_LOG(INFO, VHOST_PORT,
+ "Vhost zero copy doesn't support jumbo frame,"
+ "please specify '--mergeable 0' to disable the "
+ "mergeable feature.\n");
+ return -1;
+ }
+
return 0;
}
unsigned portid;
if (num_ports > nb_ports) {
- RTE_LOG(INFO, PORT, "\nSpecified port number(%u) exceeds total system port number(%u)\n",
+ RTE_LOG(INFO, VHOST_PORT, "\nSpecified port number(%u) exceeds total system port number(%u)\n",
num_ports, nb_ports);
num_ports = nb_ports;
}
for (portid = 0; portid < num_ports; portid ++) {
if (ports[portid] >= nb_ports) {
- RTE_LOG(INFO, PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n",
+ RTE_LOG(INFO, VHOST_PORT, "\nSpecified port ID(%u) exceeds max system port ID(%u)\n",
ports[portid], (nb_ports - 1));
ports[portid] = INVALID_PORT_ID;
valid_num_ports--;
char packet[MAX_PRINT_BUFF]; \
\
if ((header)) \
- rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \
+ snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Header size %d: ", (device->device_fh), (size)); \
else \
- rte_snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \
+ snprintf(packet, MAX_PRINT_BUFF, "(%"PRIu64") Packet size %d: ", (device->device_fh), (size)); \
for (index = 0; index < (size); index++) { \
- rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \
+ snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), \
"%02hhx ", pkt_addr[index]); \
} \
- rte_snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \
+ snprintf(packet + strnlen(packet, MAX_PRINT_BUFF), MAX_PRINT_BUFF - strnlen(packet, MAX_PRINT_BUFF), "\n"); \
\
- LOG_DEBUG(DATA, "%s", packet); \
+ LOG_DEBUG(VHOST_DATA, "%s", packet); \
} while(0)
#else
#define PRINT_PACKET(device, addr, size, header) do{} while(0)
break;
}
}
- LOG_DEBUG(DATA, "(%"PRIu64") GPA %p| VVA %p\n",
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") GPA %p| VVA %p\n",
dev->device_fh, (void*)(uintptr_t)guest_pa, (void*)(uintptr_t)vhost_va);
return vhost_va;
}
+/*
+ * Function to convert guest physical addresses to vhost physical addresses.
+ * This is used to convert virtio buffer addresses.
+ */
+static inline uint64_t __attribute__((always_inline))
+gpa_to_hpa(struct virtio_net *dev, uint64_t guest_pa,
+ uint32_t buf_len, hpa_type *addr_type)
+{
+ struct virtio_memory_regions_hpa *region;
+ uint32_t regionidx;
+ uint64_t vhost_pa = 0;
+
+ *addr_type = PHYS_ADDR_INVALID;
+
+ for (regionidx = 0; regionidx < dev->mem->nregions_hpa; regionidx++) {
+ region = &dev->mem->regions_hpa[regionidx];
+ if ((guest_pa >= region->guest_phys_address) &&
+ (guest_pa <= region->guest_phys_address_end)) {
+ vhost_pa = region->host_phys_addr_offset + guest_pa;
+ if (likely((guest_pa + buf_len - 1)
+ <= region->guest_phys_address_end))
+ *addr_type = PHYS_ADDR_CONTINUOUS;
+ else
+ *addr_type = PHYS_ADDR_CROSS_SUBREG;
+ break;
+ }
+ }
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") GPA %p| HPA %p\n",
+ dev->device_fh, (void *)(uintptr_t)guest_pa,
+ (void *)(uintptr_t)vhost_pa);
+
+ return vhost_pa;
+}
+
/*
* This function adds buffers to the virtio devices RX virtqueue. Buffers can
* be received from the physical port or from another virtio device. A packet
* count is returned to indicate the number of packets that were succesfully
- * added to the RX queue.
+ * added to the RX queue. This function works when mergeable is disabled.
*/
static inline uint32_t __attribute__((always_inline))
virtio_dev_rx(struct virtio_net *dev, struct rte_mbuf **pkts, uint32_t count)
uint64_t buff_hdr_addr = 0;
uint32_t head[MAX_PKT_BURST], packet_len = 0;
uint32_t head_idx, packet_success = 0;
- uint32_t mergeable, mrg_count = 0;
uint32_t retry = 0;
uint16_t avail_idx, res_cur_idx;
uint16_t res_base_idx, res_end_idx;
uint16_t free_entries;
uint8_t success = 0;
- LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
vq = dev->virtqueue[VIRTIO_RXQ];
count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count;
+
/* As many data cores may want access to available buffers, they need to be reserved. */
do {
res_base_idx = vq->last_used_idx_res;
avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- free_entries = (avail_idx - res_base_idx);
+ free_entries = (avail_idx - res_base_idx);
/* If retry is enabled and the queue is full then we wait and retry to avoid packet loss. */
if (enable_retry && unlikely(count > free_entries)) {
for (retry = 0; retry < burst_rx_retry_num; retry++) {
res_end_idx);
} while (unlikely(success == 0));
res_cur_idx = res_base_idx;
- LOG_DEBUG(DATA, "(%"PRIu64") Current Index %d| End Index %d\n", dev->device_fh, res_cur_idx, res_end_idx);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| End Index %d\n", dev->device_fh, res_cur_idx, res_end_idx);
/* Prefetch available ring to retrieve indexes. */
rte_prefetch0(&vq->avail->ring[res_cur_idx & (vq->size - 1)]);
- /* Check if the VIRTIO_NET_F_MRG_RXBUF feature is enabled. */
- mergeable = dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF);
-
/* Retrieve all of the head indexes first to avoid caching issues. */
for (head_idx = 0; head_idx < count; head_idx++)
head[head_idx] = vq->avail->ring[(res_cur_idx + head_idx) & (vq->size - 1)];
/* Prefetch buffer address. */
rte_prefetch0((void*)(uintptr_t)buff_addr);
- if (mergeable && (mrg_count != 0)) {
- desc->len = packet_len = rte_pktmbuf_data_len(buff);
- } else {
- /* Copy virtio_hdr to packet and increment buffer address */
- buff_hdr_addr = buff_addr;
- packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen;
+ /* Copy virtio_hdr to packet and increment buffer address */
+ buff_hdr_addr = buff_addr;
+ packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen;
- /*
- * If the descriptors are chained the header and data are placed in
- * separate buffers.
- */
- if (desc->flags & VRING_DESC_F_NEXT) {
- desc->len = vq->vhost_hlen;
- desc = &vq->desc[desc->next];
- /* Buffer address translation. */
- buff_addr = gpa_to_vva(dev, desc->addr);
- desc->len = rte_pktmbuf_data_len(buff);
- } else {
- buff_addr += vq->vhost_hlen;
- desc->len = packet_len;
- }
+ /*
+ * If the descriptors are chained the header and data are
+ * placed in separate buffers.
+ */
+ if (desc->flags & VRING_DESC_F_NEXT) {
+ desc->len = vq->vhost_hlen;
+ desc = &vq->desc[desc->next];
+ /* Buffer address translation. */
+ buff_addr = gpa_to_vva(dev, desc->addr);
+ desc->len = rte_pktmbuf_data_len(buff);
+ } else {
+ buff_addr += vq->vhost_hlen;
+ desc->len = packet_len;
}
- PRINT_PACKET(dev, (uintptr_t)buff_addr, rte_pktmbuf_data_len(buff), 0);
-
/* Update used ring with desc information */
vq->used->ring[res_cur_idx & (vq->size - 1)].id = head[packet_success];
vq->used->ring[res_cur_idx & (vq->size - 1)].len = packet_len;
/* Copy mbuf data to buffer */
- rte_memcpy((void *)(uintptr_t)buff_addr, (const void*)buff->pkt.data, rte_pktmbuf_data_len(buff));
+ rte_memcpy((void *)(uintptr_t)buff_addr,
+ (const void *)buff->pkt.data,
+ rte_pktmbuf_data_len(buff));
+ PRINT_PACKET(dev, (uintptr_t)buff_addr,
+ rte_pktmbuf_data_len(buff), 0);
res_cur_idx++;
packet_success++;
- /* If mergeable is disabled then a header is required per buffer. */
- if (!mergeable) {
- rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen);
- PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
- } else {
- mrg_count++;
- /* Merge buffer can only handle so many buffers at a time. Tell the guest if this limit is reached. */
- if ((mrg_count == MAX_MRG_PKT_BURST) || (res_cur_idx == res_end_idx)) {
- virtio_hdr.num_buffers = mrg_count;
- LOG_DEBUG(DATA, "(%"PRIu64") RX: Num merge buffers %d\n", dev->device_fh, virtio_hdr.num_buffers);
- rte_memcpy((void *)(uintptr_t)buff_hdr_addr, (const void*)&virtio_hdr, vq->vhost_hlen);
- PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
- mrg_count = 0;
- }
- }
+ rte_memcpy((void *)(uintptr_t)buff_hdr_addr,
+ (const void *)&virtio_hdr, vq->vhost_hlen);
+
+ PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
+
if (res_cur_idx < res_end_idx) {
/* Prefetch descriptor index. */
rte_prefetch0(&vq->desc[head[packet_success]]);
return count;
}
+static inline uint32_t __attribute__((always_inline))
+copy_from_mbuf_to_vring(struct virtio_net *dev,
+ uint16_t res_base_idx, uint16_t res_end_idx,
+ struct rte_mbuf *pkt)
+{
+ uint32_t vec_idx = 0;
+ uint32_t entry_success = 0;
+ struct vhost_virtqueue *vq;
+ /* The virtio_hdr is initialised to 0. */
+ struct virtio_net_hdr_mrg_rxbuf virtio_hdr = {
+ {0, 0, 0, 0, 0, 0}, 0};
+ uint16_t cur_idx = res_base_idx;
+ uint64_t vb_addr = 0;
+ uint64_t vb_hdr_addr = 0;
+ uint32_t seg_offset = 0;
+ uint32_t vb_offset = 0;
+ uint32_t seg_avail;
+ uint32_t vb_avail;
+ uint32_t cpy_len, entry_len;
+
+ if (pkt == NULL)
+ return 0;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| "
+ "End Index %d\n",
+ dev->device_fh, cur_idx, res_end_idx);
+
+ /*
+ * Convert from gpa to vva
+ * (guest physical addr -> vhost virtual addr)
+ */
+ vq = dev->virtqueue[VIRTIO_RXQ];
+ vb_addr =
+ gpa_to_vva(dev, vq->buf_vec[vec_idx].buf_addr);
+ vb_hdr_addr = vb_addr;
+
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+
+ virtio_hdr.num_buffers = res_end_idx - res_base_idx;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") RX: Num merge buffers %d\n",
+ dev->device_fh, virtio_hdr.num_buffers);
+
+ rte_memcpy((void *)(uintptr_t)vb_hdr_addr,
+ (const void *)&virtio_hdr, vq->vhost_hlen);
+
+ PRINT_PACKET(dev, (uintptr_t)vb_hdr_addr, vq->vhost_hlen, 1);
+
+ seg_avail = rte_pktmbuf_data_len(pkt);
+ vb_offset = vq->vhost_hlen;
+ vb_avail =
+ vq->buf_vec[vec_idx].buf_len - vq->vhost_hlen;
+
+ entry_len = vq->vhost_hlen;
+
+ if (vb_avail == 0) {
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vq->vhost_hlen;
+
+ if ((vq->desc[desc_idx].flags
+ & VRING_DESC_F_NEXT) == 0) {
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ }
+
+ vec_idx++;
+ vb_addr =
+ gpa_to_vva(dev, vq->buf_vec[vec_idx].buf_addr);
+
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+ vb_offset = 0;
+ vb_avail = vq->buf_vec[vec_idx].buf_len;
+ }
+
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+
+ while (cpy_len > 0) {
+ /* Copy mbuf data to vring buffer */
+ rte_memcpy((void *)(uintptr_t)(vb_addr + vb_offset),
+ (const void *)(rte_pktmbuf_mtod(pkt, char*) + seg_offset),
+ cpy_len);
+
+ PRINT_PACKET(dev,
+ (uintptr_t)(vb_addr + vb_offset),
+ cpy_len, 0);
+
+ seg_offset += cpy_len;
+ vb_offset += cpy_len;
+ seg_avail -= cpy_len;
+ vb_avail -= cpy_len;
+ entry_len += cpy_len;
+
+ if (seg_avail != 0) {
+ /*
+ * The virtio buffer in this vring
+ * entry reach to its end.
+ * But the segment doesn't complete.
+ */
+ if ((vq->desc[vq->buf_vec[vec_idx].desc_idx].flags &
+ VRING_DESC_F_NEXT) == 0) {
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ }
+
+ vec_idx++;
+ vb_addr = gpa_to_vva(dev,
+ vq->buf_vec[vec_idx].buf_addr);
+ vb_offset = 0;
+ vb_avail = vq->buf_vec[vec_idx].buf_len;
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ } else {
+ /*
+ * This current segment complete, need continue to
+ * check if the whole packet complete or not.
+ */
+ pkt = pkt->pkt.next;
+ if (pkt != NULL) {
+ /*
+ * There are more segments.
+ */
+ if (vb_avail == 0) {
+ /*
+ * This current buffer from vring is
+ * used up, need fetch next buffer
+ * from buf_vec.
+ */
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vb_offset;
+
+ if ((vq->desc[desc_idx].flags &
+ VRING_DESC_F_NEXT) == 0) {
+ uint16_t wrapped_idx =
+ cur_idx & (vq->size - 1);
+ /*
+ * Update used ring with the
+ * descriptor information
+ */
+ vq->used->ring[wrapped_idx].id
+ = desc_idx;
+ vq->used->ring[wrapped_idx].len
+ = entry_len;
+ entry_success++;
+ entry_len = 0;
+ cur_idx++;
+ }
+
+ /* Get next buffer from buf_vec. */
+ vec_idx++;
+ vb_addr = gpa_to_vva(dev,
+ vq->buf_vec[vec_idx].buf_addr);
+ vb_avail =
+ vq->buf_vec[vec_idx].buf_len;
+ vb_offset = 0;
+ }
+
+ seg_offset = 0;
+ seg_avail = rte_pktmbuf_data_len(pkt);
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ } else {
+ /*
+ * This whole packet completes.
+ */
+ uint32_t desc_idx =
+ vq->buf_vec[vec_idx].desc_idx;
+ vq->desc[desc_idx].len = vb_offset;
+
+ while (vq->desc[desc_idx].flags &
+ VRING_DESC_F_NEXT) {
+ desc_idx = vq->desc[desc_idx].next;
+ vq->desc[desc_idx].len = 0;
+ }
+
+ /* Update used ring with desc information */
+ vq->used->ring[cur_idx & (vq->size - 1)].id
+ = vq->buf_vec[vec_idx].desc_idx;
+ vq->used->ring[cur_idx & (vq->size - 1)].len
+ = entry_len;
+ entry_len = 0;
+ cur_idx++;
+ entry_success++;
+ seg_avail = 0;
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ }
+ }
+ }
+
+ return entry_success;
+}
+
+/*
+ * This function adds buffers to the virtio devices RX virtqueue. Buffers can
+ * be received from the physical port or from another virtio device. A packet
+ * count is returned to indicate the number of packets that were succesfully
+ * added to the RX queue. This function works for mergeable RX.
+ */
+static inline uint32_t __attribute__((always_inline))
+virtio_dev_merge_rx(struct virtio_net *dev, struct rte_mbuf **pkts,
+ uint32_t count)
+{
+ struct vhost_virtqueue *vq;
+ uint32_t pkt_idx = 0, entry_success = 0;
+ uint32_t retry = 0;
+ uint16_t avail_idx, res_cur_idx;
+ uint16_t res_base_idx, res_end_idx;
+ uint8_t success = 0;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_merge_rx()\n",
+ dev->device_fh);
+ vq = dev->virtqueue[VIRTIO_RXQ];
+ count = RTE_MIN((uint32_t)MAX_PKT_BURST, count);
+
+ if (count == 0)
+ return 0;
+
+ for (pkt_idx = 0; pkt_idx < count; pkt_idx++) {
+ uint32_t secure_len = 0;
+ uint16_t need_cnt;
+ uint32_t vec_idx = 0;
+ uint32_t pkt_len = pkts[pkt_idx]->pkt.pkt_len + vq->vhost_hlen;
+ uint16_t i, id;
+
+ do {
+ /*
+ * As many data cores may want access to available
+ * buffers, they need to be reserved.
+ */
+ res_base_idx = vq->last_used_idx_res;
+ res_cur_idx = res_base_idx;
+
+ do {
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+ if (unlikely(res_cur_idx == avail_idx)) {
+ /*
+ * If retry is enabled and the queue is
+ * full then we wait and retry to avoid
+ * packet loss.
+ */
+ if (enable_retry) {
+ uint8_t cont = 0;
+ for (retry = 0; retry < burst_rx_retry_num; retry++) {
+ rte_delay_us(burst_rx_delay_time);
+ avail_idx =
+ *((volatile uint16_t *)&vq->avail->idx);
+ if (likely(res_cur_idx != avail_idx)) {
+ cont = 1;
+ break;
+ }
+ }
+ if (cont == 1)
+ continue;
+ }
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") Failed "
+ "to get enough desc from "
+ "vring\n",
+ dev->device_fh);
+ return pkt_idx;
+ } else {
+ uint16_t wrapped_idx =
+ (res_cur_idx) & (vq->size - 1);
+ uint32_t idx =
+ vq->avail->ring[wrapped_idx];
+ uint8_t next_desc;
+
+ do {
+ next_desc = 0;
+ secure_len += vq->desc[idx].len;
+ if (vq->desc[idx].flags &
+ VRING_DESC_F_NEXT) {
+ idx = vq->desc[idx].next;
+ next_desc = 1;
+ }
+ } while (next_desc);
+
+ res_cur_idx++;
+ }
+ } while (pkt_len > secure_len);
+
+ /* vq->last_used_idx_res is atomically updated. */
+ success = rte_atomic16_cmpset(&vq->last_used_idx_res,
+ res_base_idx,
+ res_cur_idx);
+ } while (success == 0);
+
+ id = res_base_idx;
+ need_cnt = res_cur_idx - res_base_idx;
+
+ for (i = 0; i < need_cnt; i++, id++) {
+ uint16_t wrapped_idx = id & (vq->size - 1);
+ uint32_t idx = vq->avail->ring[wrapped_idx];
+ uint8_t next_desc;
+ do {
+ next_desc = 0;
+ vq->buf_vec[vec_idx].buf_addr =
+ vq->desc[idx].addr;
+ vq->buf_vec[vec_idx].buf_len =
+ vq->desc[idx].len;
+ vq->buf_vec[vec_idx].desc_idx = idx;
+ vec_idx++;
+
+ if (vq->desc[idx].flags & VRING_DESC_F_NEXT) {
+ idx = vq->desc[idx].next;
+ next_desc = 1;
+ }
+ } while (next_desc);
+ }
+
+ res_end_idx = res_cur_idx;
+
+ entry_success = copy_from_mbuf_to_vring(dev, res_base_idx,
+ res_end_idx, pkts[pkt_idx]);
+
+ rte_compiler_barrier();
+
+ /*
+ * Wait until it's our turn to add our buffer
+ * to the used ring.
+ */
+ while (unlikely(vq->last_used_idx != res_base_idx))
+ rte_pause();
+
+ *(volatile uint16_t *)&vq->used->idx += entry_success;
+ vq->last_used_idx = res_end_idx;
+
+ /* Kick the guest if necessary. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+ }
+
+ return count;
+}
+
/*
* Compares a packet destination MAC address to a device MAC address.
*/
while (dev_ll != NULL) {
if (ether_addr_cmp(&(pkt_hdr->s_addr), &dev_ll->dev->mac_address)) {
- RTE_LOG(INFO, DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh);
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") WARNING: This device is using an existing MAC address and has not been registered.\n", dev->device_fh);
return -1;
}
dev_ll = dev_ll->next;
/* vlan_tag currently uses the device_id. */
dev->vlan_tag = vlan_tags[dev->device_fh];
- dev->vmdq_rx_q = dev->device_fh * (num_queues/num_devices);
/* Print out VMDQ registration info. */
- RTE_LOG(INFO, DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
dev->device_fh,
dev->mac_address.addr_bytes[0], dev->mac_address.addr_bytes[1],
dev->mac_address.addr_bytes[2], dev->mac_address.addr_bytes[3],
/* Register the MAC address. */
ret = rte_eth_dev_mac_addr_add(ports[0], &dev->mac_address, (uint32_t)dev->device_fh);
if (ret)
- RTE_LOG(ERR, DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
+ RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
dev->device_fh);
/* Enable stripping of the vlan tag as we handle routing. */
/* Drop the packet if the TX packet is destined for the TX device. */
if (dev_ll->dev->device_fh == dev->device_fh) {
- LOG_DEBUG(DATA, "(%"PRIu64") TX: Source and destination MAC addresses are the same. Dropping packet.\n",
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: Source and destination MAC addresses are the same. Dropping packet.\n",
dev_ll->dev->device_fh);
return 0;
}
- LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is local\n", dev_ll->dev->device_fh);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is local\n", dev_ll->dev->device_fh);
if (dev_ll->dev->remove) {
/*drop the packet if the device is marked for removal*/
- LOG_DEBUG(DATA, "(%"PRIu64") Device is marked for removal\n", dev_ll->dev->device_fh);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Device is marked for removal\n", dev_ll->dev->device_fh);
} else {
+ uint32_t mergeable =
+ dev_ll->dev->features &
+ (1 << VIRTIO_NET_F_MRG_RXBUF);
+
/*send the packet to the local virtio device*/
- ret = virtio_dev_rx(dev_ll->dev, &m, 1);
+ if (likely(mergeable == 0))
+ ret = virtio_dev_rx(dev_ll->dev, &m, 1);
+ else
+ ret = virtio_dev_merge_rx(dev_ll->dev,
+ &m, 1);
+
if (enable_stats) {
- rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, 1);
- rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret);
+ rte_atomic64_add(
+ &dev_statistics[dev_ll->dev->device_fh].rx_total_atomic,
+ 1);
+ rte_atomic64_add(
+ &dev_statistics[dev_ll->dev->device_fh].rx_atomic,
+ ret);
dev_statistics[dev->device_fh].tx_total++;
dev_statistics[dev->device_fh].tx += ret;
}
struct mbuf_table *tx_q;
struct vlan_ethhdr *vlan_hdr;
struct rte_mbuf **m_table;
- struct rte_mbuf *mbuf;
- unsigned len, ret;
+ struct rte_mbuf *mbuf, *prev;
+ unsigned len, ret, offset = 0;
const uint16_t lcore_id = rte_lcore_id();
+ struct virtio_net_data_ll *dev_ll = ll_root_used;
+ struct ether_hdr *pkt_hdr = (struct ether_hdr *)m->pkt.data;
/*check if destination is local VM*/
- if (enable_vm2vm && (virtio_tx_local(dev, m) == 0)) {
+ if ((vm2vm_mode == VM2VM_SOFTWARE) && (virtio_tx_local(dev, m) == 0))
return;
+
+ if (vm2vm_mode == VM2VM_HARDWARE) {
+ while (dev_ll != NULL) {
+ if ((dev_ll->dev->ready == DEVICE_RX)
+ && ether_addr_cmp(&(pkt_hdr->d_addr),
+ &dev_ll->dev->mac_address)) {
+ /*
+ * Drop the packet if the TX packet is
+ * destined for the TX device.
+ */
+ if (dev_ll->dev->device_fh == dev->device_fh) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: Source and destination"
+ " MAC addresses are the same. Dropping "
+ "packet.\n",
+ dev_ll->dev->device_fh);
+ return;
+ }
+ offset = 4;
+ vlan_tag =
+ (uint16_t)
+ vlan_tags[(uint16_t)dev_ll->dev->device_fh];
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: pkt to local VM device id:"
+ "(%"PRIu64") vlan tag: %d.\n",
+ dev->device_fh, dev_ll->dev->device_fh,
+ vlan_tag);
+
+ break;
+ }
+ dev_ll = dev_ll->next;
+ }
}
- LOG_DEBUG(DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") TX: MAC address is external\n", dev->device_fh);
/*Add packet to the port tx queue*/
tx_q = &lcore_tx_queue[lcore_id];
/* Allocate an mbuf and populate the structure. */
mbuf = rte_pktmbuf_alloc(mbuf_pool);
if (unlikely(mbuf == NULL)) {
- RTE_LOG(ERR, DATA, "Failed to allocate memory for mbuf.\n");
+ RTE_LOG(ERR, VHOST_DATA,
+ "Failed to allocate memory for mbuf.\n");
return;
}
- mbuf->pkt.data_len = m->pkt.data_len + VLAN_HLEN;
- mbuf->pkt.pkt_len = mbuf->pkt.data_len;
+ mbuf->pkt.data_len = m->pkt.data_len + VLAN_HLEN + offset;
+ mbuf->pkt.pkt_len = m->pkt.pkt_len + VLAN_HLEN + offset;
+ mbuf->pkt.nb_segs = m->pkt.nb_segs;
/* Copy ethernet header to mbuf. */
rte_memcpy((void*)mbuf->pkt.data, (const void*)m->pkt.data, ETH_HLEN);
/* Copy the remaining packet contents to the mbuf. */
rte_memcpy((void*) ((uint8_t*)mbuf->pkt.data + VLAN_ETH_HLEN),
(const void*) ((uint8_t*)m->pkt.data + ETH_HLEN), (m->pkt.data_len - ETH_HLEN));
+
+ /* Copy the remaining segments for the whole packet. */
+ prev = mbuf;
+ while (m->pkt.next) {
+ /* Allocate an mbuf and populate the structure. */
+ struct rte_mbuf *next_mbuf = rte_pktmbuf_alloc(mbuf_pool);
+ if (unlikely(next_mbuf == NULL)) {
+ rte_pktmbuf_free(mbuf);
+ RTE_LOG(ERR, VHOST_DATA,
+ "Failed to allocate memory for mbuf.\n");
+ return;
+ }
+
+ m = m->pkt.next;
+ prev->pkt.next = next_mbuf;
+ prev = next_mbuf;
+ next_mbuf->pkt.data_len = m->pkt.data_len;
+
+ /* Copy data to next mbuf. */
+ rte_memcpy(rte_pktmbuf_mtod(next_mbuf, void *),
+ rte_pktmbuf_mtod(m, const void *), m->pkt.data_len);
+ }
+
tx_q->m_table[len] = mbuf;
len++;
if (enable_stats) {
if (vq->last_used_idx == avail_idx)
return;
- LOG_DEBUG(DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
/* Prefetch available ring to retrieve head indexes. */
rte_prefetch0(&vq->avail->ring[vq->last_used_idx & (vq->size - 1)]);
if (free_entries > MAX_PKT_BURST)
free_entries = MAX_PKT_BURST;
- LOG_DEBUG(DATA, "(%"PRIu64") Buffers available %d\n", dev->device_fh, free_entries);
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n", dev->device_fh, free_entries);
/* Retrieve all of the head indexes first to avoid caching issues. */
for (i = 0; i < free_entries; i++)
head[i] = vq->avail->ring[(vq->last_used_idx + i) & (vq->size - 1)];
/* Discard first buffer as it is the virtio header */
desc = &vq->desc[desc->next];
-
+
/* Buffer address translation. */
buff_addr = gpa_to_vva(dev, desc->addr);
/* Prefetch buffer address. */
rte_prefetch0((void*)(uintptr_t)buff_addr);
-
+
used_idx = vq->last_used_idx & (vq->size - 1);
-
+
if (packet_success < (free_entries - 1)) {
/* Prefetch descriptor index. */
rte_prefetch0(&vq->desc[head[packet_success+1]]);
/* Setup dummy mbuf. This is copied to a real mbuf if transmitted out the physical port. */
m.pkt.data_len = desc->len;
+ m.pkt.pkt_len = desc->len;
m.pkt.data = (void*)(uintptr_t)buff_addr;
PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0);
eventfd_write((int)vq->kickfd, 1);
}
-/*
- * This function is called by each data core. It handles all RX/TX registered with the
- * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
- * with all devices in the main linked list.
- */
-static int
-switch_worker(__attribute__((unused)) void *arg)
+/* This function works for TX packets with mergeable feature enabled. */
+static inline void __attribute__((always_inline))
+virtio_dev_merge_tx(struct virtio_net *dev, struct rte_mempool *mbuf_pool)
{
- struct rte_mempool *mbuf_pool = arg;
- struct virtio_net *dev = NULL;
- struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
- struct virtio_net_data_ll *dev_ll;
- struct mbuf_table *tx_q;
- volatile struct lcore_ll_info *lcore_ll;
- const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
- uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
- unsigned ret, i;
- const uint16_t lcore_id = rte_lcore_id();
- const uint16_t num_cores = (uint16_t)rte_lcore_count();
- uint16_t rx_count = 0;
+ struct rte_mbuf *m, *prev;
+ struct vhost_virtqueue *vq;
+ struct vring_desc *desc;
+ uint64_t vb_addr = 0;
+ uint32_t head[MAX_PKT_BURST];
+ uint32_t used_idx;
+ uint32_t i;
+ uint16_t free_entries, entry_success = 0;
+ uint16_t avail_idx;
+ uint32_t buf_size = MBUF_SIZE - (sizeof(struct rte_mbuf)
+ + RTE_PKTMBUF_HEADROOM);
- RTE_LOG(INFO, DATA, "Procesing on Core %u started \n", lcore_id);
- lcore_ll = lcore_info[lcore_id].lcore_ll;
- prev_tsc = 0;
+ vq = dev->virtqueue[VIRTIO_TXQ];
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
- tx_q = &lcore_tx_queue[lcore_id];
- for (i = 0; i < num_cores; i ++) {
- if (lcore_ids[i] == lcore_id) {
- tx_q->txq_id = i;
- break;
- }
- }
+ /* If there are no available buffers then return. */
+ if (vq->last_used_idx == avail_idx)
+ return;
- while(1) {
- cur_tsc = rte_rdtsc();
- /*
- * TX burst queue drain
- */
- diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > drain_tsc)) {
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_merge_tx()\n",
+ dev->device_fh);
- if (tx_q->len) {
- LOG_DEBUG(DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len);
+ /* Prefetch available ring to retrieve head indexes. */
+ rte_prefetch0(&vq->avail->ring[vq->last_used_idx & (vq->size - 1)]);
- /*Tx any packets in the queue*/
- ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id,
- (struct rte_mbuf **)tx_q->m_table,
+ /*get the number of free entries in the ring*/
+ free_entries = (avail_idx - vq->last_used_idx);
+
+ /* Limit to MAX_PKT_BURST. */
+ free_entries = RTE_MIN(free_entries, MAX_PKT_BURST);
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n",
+ dev->device_fh, free_entries);
+ /* Retrieve all of the head indexes first to avoid caching issues. */
+ for (i = 0; i < free_entries; i++)
+ head[i] = vq->avail->ring[(vq->last_used_idx + i) & (vq->size - 1)];
+
+ /* Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[entry_success]]);
+ rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]);
+
+ while (entry_success < free_entries) {
+ uint32_t vb_avail, vb_offset;
+ uint32_t seg_avail, seg_offset;
+ uint32_t cpy_len;
+ uint32_t seg_num = 0;
+ struct rte_mbuf *cur;
+ uint8_t alloc_err = 0;
+
+ desc = &vq->desc[head[entry_success]];
+
+ /* Discard first buffer as it is the virtio header */
+ desc = &vq->desc[desc->next];
+
+ /* Buffer address translation. */
+ vb_addr = gpa_to_vva(dev, desc->addr);
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+
+ used_idx = vq->last_used_idx & (vq->size - 1);
+
+ if (entry_success < (free_entries - 1)) {
+ /* Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[entry_success+1]]);
+ rte_prefetch0(&vq->used->ring[(used_idx + 1) & (vq->size - 1)]);
+ }
+
+ /* Update used index buffer information. */
+ vq->used->ring[used_idx].id = head[entry_success];
+ vq->used->ring[used_idx].len = 0;
+
+ vb_offset = 0;
+ vb_avail = desc->len;
+ seg_offset = 0;
+ seg_avail = buf_size;
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+
+ PRINT_PACKET(dev, (uintptr_t)vb_addr, desc->len, 0);
+
+ /* Allocate an mbuf and populate the structure. */
+ m = rte_pktmbuf_alloc(mbuf_pool);
+ if (unlikely(m == NULL)) {
+ RTE_LOG(ERR, VHOST_DATA,
+ "Failed to allocate memory for mbuf.\n");
+ return;
+ }
+
+ seg_num++;
+ cur = m;
+ prev = m;
+ while (cpy_len != 0) {
+ rte_memcpy((void *)(rte_pktmbuf_mtod(cur, char *) + seg_offset),
+ (void *)((uintptr_t)(vb_addr + vb_offset)),
+ cpy_len);
+
+ seg_offset += cpy_len;
+ vb_offset += cpy_len;
+ vb_avail -= cpy_len;
+ seg_avail -= cpy_len;
+
+ if (vb_avail != 0) {
+ /*
+ * The segment reachs to its end,
+ * while the virtio buffer in TX vring has
+ * more data to be copied.
+ */
+ cur->pkt.data_len = seg_offset;
+ m->pkt.pkt_len += seg_offset;
+ /* Allocate mbuf and populate the structure. */
+ cur = rte_pktmbuf_alloc(mbuf_pool);
+ if (unlikely(cur == NULL)) {
+ RTE_LOG(ERR, VHOST_DATA, "Failed to "
+ "allocate memory for mbuf.\n");
+ rte_pktmbuf_free(m);
+ alloc_err = 1;
+ break;
+ }
+
+ seg_num++;
+ prev->pkt.next = cur;
+ prev = cur;
+ seg_offset = 0;
+ seg_avail = buf_size;
+ } else {
+ if (desc->flags & VRING_DESC_F_NEXT) {
+ /*
+ * There are more virtio buffers in
+ * same vring entry need to be copied.
+ */
+ if (seg_avail == 0) {
+ /*
+ * The current segment hasn't
+ * room to accomodate more
+ * data.
+ */
+ cur->pkt.data_len = seg_offset;
+ m->pkt.pkt_len += seg_offset;
+ /*
+ * Allocate an mbuf and
+ * populate the structure.
+ */
+ cur = rte_pktmbuf_alloc(mbuf_pool);
+ if (unlikely(cur == NULL)) {
+ RTE_LOG(ERR,
+ VHOST_DATA,
+ "Failed to "
+ "allocate memory "
+ "for mbuf\n");
+ rte_pktmbuf_free(m);
+ alloc_err = 1;
+ break;
+ }
+ seg_num++;
+ prev->pkt.next = cur;
+ prev = cur;
+ seg_offset = 0;
+ seg_avail = buf_size;
+ }
+
+ desc = &vq->desc[desc->next];
+
+ /* Buffer address translation. */
+ vb_addr = gpa_to_vva(dev, desc->addr);
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)vb_addr);
+ vb_offset = 0;
+ vb_avail = desc->len;
+
+ PRINT_PACKET(dev, (uintptr_t)vb_addr,
+ desc->len, 0);
+ } else {
+ /* The whole packet completes. */
+ cur->pkt.data_len = seg_offset;
+ m->pkt.pkt_len += seg_offset;
+ vb_avail = 0;
+ }
+ }
+
+ cpy_len = RTE_MIN(vb_avail, seg_avail);
+ }
+
+ if (unlikely(alloc_err == 1))
+ break;
+
+ m->pkt.nb_segs = seg_num;
+
+ /*
+ * If this is the first received packet we need to learn
+ * the MAC and setup VMDQ
+ */
+ if (dev->ready == DEVICE_MAC_LEARNING) {
+ if (dev->remove || (link_vmdq(dev, m) == -1)) {
+ /*
+ * Discard frame if device is scheduled for
+ * removal or a duplicate MAC address is found.
+ */
+ entry_success = free_entries;
+ vq->last_used_idx += entry_success;
+ rte_pktmbuf_free(m);
+ break;
+ }
+ }
+
+ virtio_tx_route(dev, m, mbuf_pool, (uint16_t)dev->device_fh);
+ vq->last_used_idx++;
+ entry_success++;
+ rte_pktmbuf_free(m);
+ }
+
+ rte_compiler_barrier();
+ vq->used->idx += entry_success;
+ /* Kick guest if required. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+
+}
+
+/*
+ * This function is called by each data core. It handles all RX/TX registered with the
+ * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
+ * with all devices in the main linked list.
+ */
+static int
+switch_worker(__attribute__((unused)) void *arg)
+{
+ struct rte_mempool *mbuf_pool = arg;
+ struct virtio_net *dev = NULL;
+ struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ struct virtio_net_data_ll *dev_ll;
+ struct mbuf_table *tx_q;
+ volatile struct lcore_ll_info *lcore_ll;
+ const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
+ uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
+ unsigned ret, i;
+ const uint16_t lcore_id = rte_lcore_id();
+ const uint16_t num_cores = (uint16_t)rte_lcore_count();
+ uint16_t rx_count = 0;
+ uint32_t mergeable = 0;
+
+ RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id);
+ lcore_ll = lcore_info[lcore_id].lcore_ll;
+ prev_tsc = 0;
+
+ tx_q = &lcore_tx_queue[lcore_id];
+ for (i = 0; i < num_cores; i ++) {
+ if (lcore_ids[i] == lcore_id) {
+ tx_q->txq_id = i;
+ break;
+ }
+ }
+
+ while(1) {
+ cur_tsc = rte_rdtsc();
+ /*
+ * TX burst queue drain
+ */
+ diff_tsc = cur_tsc - prev_tsc;
+ if (unlikely(diff_tsc > drain_tsc)) {
+
+ if (tx_q->len) {
+ LOG_DEBUG(VHOST_DATA, "TX queue drained after timeout with burst size %u \n", tx_q->len);
+
+ /*Tx any packets in the queue*/
+ ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id,
+ (struct rte_mbuf **)tx_q->m_table,
(uint16_t)tx_q->len);
if (unlikely(ret < tx_q->len)) {
do {
} while (++ret < tx_q->len);
}
- tx_q->len = 0;
+ tx_q->len = 0;
+ }
+
+ prev_tsc = cur_tsc;
+
+ }
+
+ rte_prefetch0(lcore_ll->ll_root_used);
+ /*
+ * Inform the configuration core that we have exited the linked list and that no devices are
+ * in use if requested.
+ */
+ if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL)
+ lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
+
+ /*
+ * Process devices
+ */
+ dev_ll = lcore_ll->ll_root_used;
+
+ while (dev_ll != NULL) {
+ /*get virtio device ID*/
+ dev = dev_ll->dev;
+ mergeable =
+ dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF);
+
+ if (dev->remove) {
+ dev_ll = dev_ll->next;
+ unlink_vmdq(dev);
+ dev->ready = DEVICE_SAFE_REMOVE;
+ continue;
+ }
+ if (likely(dev->ready == DEVICE_RX)) {
+ /*Handle guest RX*/
+ rx_count = rte_eth_rx_burst(ports[0],
+ (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
+
+ if (rx_count) {
+ if (likely(mergeable == 0))
+ ret_count =
+ virtio_dev_rx(dev,
+ pkts_burst, rx_count);
+ else
+ ret_count =
+ virtio_dev_merge_rx(dev,
+ pkts_burst, rx_count);
+
+ if (enable_stats) {
+ rte_atomic64_add(
+ &dev_statistics[dev_ll->dev->device_fh].rx_total_atomic,
+ rx_count);
+ rte_atomic64_add(
+ &dev_statistics[dev_ll->dev->device_fh].rx_atomic, ret_count);
+ }
+ while (likely(rx_count)) {
+ rx_count--;
+ rte_pktmbuf_free(pkts_burst[rx_count]);
+ }
+
+ }
+ }
+
+ if (!dev->remove) {
+ /*Handle guest TX*/
+ if (likely(mergeable == 0))
+ virtio_dev_tx(dev, mbuf_pool);
+ else
+ virtio_dev_merge_tx(dev, mbuf_pool);
+ }
+
+ /*move to the next device in the list*/
+ dev_ll = dev_ll->next;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * This function gets available ring number for zero copy rx.
+ * Only one thread will call this funciton for a paticular virtio device,
+ * so, it is designed as non-thread-safe function.
+ */
+static inline uint32_t __attribute__((always_inline))
+get_available_ring_num_zcp(struct virtio_net *dev)
+{
+ struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ];
+ uint16_t avail_idx;
+
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+ return (uint32_t)(avail_idx - vq->last_used_idx_res);
+}
+
+/*
+ * This function gets available ring index for zero copy rx,
+ * it will retry 'burst_rx_retry_num' times till it get enough ring index.
+ * Only one thread will call this funciton for a paticular virtio device,
+ * so, it is designed as non-thread-safe function.
+ */
+static inline uint32_t __attribute__((always_inline))
+get_available_ring_index_zcp(struct virtio_net *dev,
+ uint16_t *res_base_idx, uint32_t count)
+{
+ struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_RXQ];
+ uint16_t avail_idx;
+ uint32_t retry = 0;
+ uint16_t free_entries;
+
+ *res_base_idx = vq->last_used_idx_res;
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+ free_entries = (avail_idx - *res_base_idx);
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") in get_available_ring_index_zcp: "
+ "avail idx: %d, "
+ "res base idx:%d, free entries:%d\n",
+ dev->device_fh, avail_idx, *res_base_idx,
+ free_entries);
+
+ /*
+ * If retry is enabled and the queue is full then we wait
+ * and retry to avoid packet loss.
+ */
+ if (enable_retry && unlikely(count > free_entries)) {
+ for (retry = 0; retry < burst_rx_retry_num; retry++) {
+ rte_delay_us(burst_rx_delay_time);
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+ free_entries = (avail_idx - *res_base_idx);
+ if (count <= free_entries)
+ break;
+ }
+ }
+
+ /*check that we have enough buffers*/
+ if (unlikely(count > free_entries))
+ count = free_entries;
+
+ if (unlikely(count == 0)) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") Fail in get_available_ring_index_zcp: "
+ "avail idx: %d, res base idx:%d, free entries:%d\n",
+ dev->device_fh, avail_idx,
+ *res_base_idx, free_entries);
+ return 0;
+ }
+
+ vq->last_used_idx_res = *res_base_idx + count;
+
+ return count;
+}
+
+/*
+ * This function put descriptor back to used list.
+ */
+static inline void __attribute__((always_inline))
+put_desc_to_used_list_zcp(struct vhost_virtqueue *vq, uint16_t desc_idx)
+{
+ uint16_t res_cur_idx = vq->last_used_idx;
+ vq->used->ring[res_cur_idx & (vq->size - 1)].id = (uint32_t)desc_idx;
+ vq->used->ring[res_cur_idx & (vq->size - 1)].len = 0;
+ rte_compiler_barrier();
+ *(volatile uint16_t *)&vq->used->idx += 1;
+ vq->last_used_idx += 1;
+
+ /* Kick the guest if necessary. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+}
+
+/*
+ * This function get available descriptor from vitio vring and un-attached mbuf
+ * from vpool->ring, and then attach them together. It needs adjust the offset
+ * for buff_addr and phys_addr accroding to PMD implementation, otherwise the
+ * frame data may be put to wrong location in mbuf.
+ */
+static inline void __attribute__((always_inline))
+attach_rxmbuf_zcp(struct virtio_net *dev)
+{
+ uint16_t res_base_idx, desc_idx;
+ uint64_t buff_addr, phys_addr;
+ struct vhost_virtqueue *vq;
+ struct vring_desc *desc;
+ struct rte_mbuf *mbuf = NULL;
+ struct vpool *vpool;
+ hpa_type addr_type;
+
+ vpool = &vpool_array[dev->vmdq_rx_q];
+ vq = dev->virtqueue[VIRTIO_RXQ];
+
+ do {
+ if (unlikely(get_available_ring_index_zcp(dev, &res_base_idx,
+ 1) != 1))
+ return;
+ desc_idx = vq->avail->ring[(res_base_idx) & (vq->size - 1)];
+
+ desc = &vq->desc[desc_idx];
+ if (desc->flags & VRING_DESC_F_NEXT) {
+ desc = &vq->desc[desc->next];
+ buff_addr = gpa_to_vva(dev, desc->addr);
+ phys_addr = gpa_to_hpa(dev, desc->addr, desc->len,
+ &addr_type);
+ } else {
+ buff_addr = gpa_to_vva(dev,
+ desc->addr + vq->vhost_hlen);
+ phys_addr = gpa_to_hpa(dev,
+ desc->addr + vq->vhost_hlen,
+ desc->len, &addr_type);
+ }
+
+ if (unlikely(addr_type == PHYS_ADDR_INVALID)) {
+ RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Invalid frame buffer"
+ " address found when attaching RX frame buffer"
+ " address!\n", dev->device_fh);
+ put_desc_to_used_list_zcp(vq, desc_idx);
+ continue;
+ }
+
+ /*
+ * Check if the frame buffer address from guest crosses
+ * sub-region or not.
+ */
+ if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) {
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%"PRIu64") Frame buffer address cross "
+ "sub-regioin found when attaching RX frame "
+ "buffer address!\n",
+ dev->device_fh);
+ put_desc_to_used_list_zcp(vq, desc_idx);
+ continue;
+ }
+ } while (unlikely(phys_addr == 0));
+
+ rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
+ if (unlikely(mbuf == NULL)) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in attach_rxmbuf_zcp: "
+ "ring_sc_dequeue fail.\n",
+ dev->device_fh);
+ put_desc_to_used_list_zcp(vq, desc_idx);
+ return;
+ }
+
+ if (unlikely(vpool->buf_size > desc->len)) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in attach_rxmbuf_zcp: frame buffer "
+ "length(%d) of descriptor idx: %d less than room "
+ "size required: %d\n",
+ dev->device_fh, desc->len, desc_idx, vpool->buf_size);
+ put_desc_to_used_list_zcp(vq, desc_idx);
+ rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
+ return;
+ }
+
+ mbuf->buf_addr = (void *)(uintptr_t)(buff_addr - RTE_PKTMBUF_HEADROOM);
+ mbuf->pkt.data = (void *)(uintptr_t)(buff_addr);
+ mbuf->buf_physaddr = phys_addr - RTE_PKTMBUF_HEADROOM;
+ mbuf->pkt.data_len = desc->len;
+ MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in attach_rxmbuf_zcp: res base idx:%d, "
+ "descriptor idx:%d\n",
+ dev->device_fh, res_base_idx, desc_idx);
+
+ __rte_mbuf_raw_free(mbuf);
+
+ return;
+}
+
+/*
+ * Detach an attched packet mbuf -
+ * - restore original mbuf address and length values.
+ * - reset pktmbuf data and data_len to their default values.
+ * All other fields of the given packet mbuf will be left intact.
+ *
+ * @param m
+ * The attached packet mbuf.
+ */
+static inline void pktmbuf_detach_zcp(struct rte_mbuf *m)
+{
+ const struct rte_mempool *mp = m->pool;
+ void *buf = RTE_MBUF_TO_BADDR(m);
+ uint32_t buf_ofs;
+ uint32_t buf_len = mp->elt_size - sizeof(*m);
+ m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof(*m);
+
+ m->buf_addr = buf;
+ m->buf_len = (uint16_t)buf_len;
+
+ buf_ofs = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
+ RTE_PKTMBUF_HEADROOM : m->buf_len;
+ m->pkt.data = (char *) m->buf_addr + buf_ofs;
+
+ m->pkt.data_len = 0;
+}
+
+/*
+ * This function is called after packets have been transimited. It fetchs mbuf
+ * from vpool->pool, detached it and put into vpool->ring. It also update the
+ * used index and kick the guest if necessary.
+ */
+static inline uint32_t __attribute__((always_inline))
+txmbuf_clean_zcp(struct virtio_net *dev, struct vpool *vpool)
+{
+ struct rte_mbuf *mbuf;
+ struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ];
+ uint32_t used_idx = vq->last_used_idx & (vq->size - 1);
+ uint32_t index = 0;
+ uint32_t mbuf_count = rte_mempool_count(vpool->pool);
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool before "
+ "clean is: %d\n",
+ dev->device_fh, mbuf_count);
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring before "
+ "clean is : %d\n",
+ dev->device_fh, rte_ring_count(vpool->ring));
+
+ for (index = 0; index < mbuf_count; index++) {
+ mbuf = __rte_mbuf_raw_alloc(vpool->pool);
+ if (likely(RTE_MBUF_INDIRECT(mbuf)))
+ pktmbuf_detach_zcp(mbuf);
+ rte_ring_sp_enqueue(vpool->ring, mbuf);
+
+ /* Update used index buffer information. */
+ vq->used->ring[used_idx].id = MBUF_HEADROOM_UINT32(mbuf);
+ vq->used->ring[used_idx].len = 0;
+
+ used_idx = (used_idx + 1) & (vq->size - 1);
+ }
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in mempool after "
+ "clean is: %d\n",
+ dev->device_fh, rte_mempool_count(vpool->pool));
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: mbuf count in ring after "
+ "clean is : %d\n",
+ dev->device_fh, rte_ring_count(vpool->ring));
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: before updated "
+ "vq->last_used_idx:%d\n",
+ dev->device_fh, vq->last_used_idx);
+
+ vq->last_used_idx += mbuf_count;
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in txmbuf_clean_zcp: after updated "
+ "vq->last_used_idx:%d\n",
+ dev->device_fh, vq->last_used_idx);
+
+ rte_compiler_barrier();
+
+ *(volatile uint16_t *)&vq->used->idx += mbuf_count;
+
+ /* Kick guest if required. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+
+ return 0;
+}
+
+/*
+ * This function is called when a virtio device is destroy.
+ * It fetchs mbuf from vpool->pool, and detached it, and put into vpool->ring.
+ */
+static void mbuf_destroy_zcp(struct vpool *vpool)
+{
+ struct rte_mbuf *mbuf = NULL;
+ uint32_t index, mbuf_count = rte_mempool_count(vpool->pool);
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "in mbuf_destroy_zcp: mbuf count in mempool before "
+ "mbuf_destroy_zcp is: %d\n",
+ mbuf_count);
+ LOG_DEBUG(VHOST_CONFIG,
+ "in mbuf_destroy_zcp: mbuf count in ring before "
+ "mbuf_destroy_zcp is : %d\n",
+ rte_ring_count(vpool->ring));
+
+ for (index = 0; index < mbuf_count; index++) {
+ mbuf = __rte_mbuf_raw_alloc(vpool->pool);
+ if (likely(mbuf != NULL)) {
+ if (likely(RTE_MBUF_INDIRECT(mbuf)))
+ pktmbuf_detach_zcp(mbuf);
+ rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
+ }
+ }
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "in mbuf_destroy_zcp: mbuf count in mempool after "
+ "mbuf_destroy_zcp is: %d\n",
+ rte_mempool_count(vpool->pool));
+ LOG_DEBUG(VHOST_CONFIG,
+ "in mbuf_destroy_zcp: mbuf count in ring after "
+ "mbuf_destroy_zcp is : %d\n",
+ rte_ring_count(vpool->ring));
+}
+
+/*
+ * This function update the use flag and counter.
+ */
+static inline uint32_t __attribute__((always_inline))
+virtio_dev_rx_zcp(struct virtio_net *dev, struct rte_mbuf **pkts,
+ uint32_t count)
+{
+ struct vhost_virtqueue *vq;
+ struct vring_desc *desc;
+ struct rte_mbuf *buff;
+ /* The virtio_hdr is initialised to 0. */
+ struct virtio_net_hdr_mrg_rxbuf virtio_hdr
+ = {{0, 0, 0, 0, 0, 0}, 0};
+ uint64_t buff_hdr_addr = 0;
+ uint32_t head[MAX_PKT_BURST], packet_len = 0;
+ uint32_t head_idx, packet_success = 0;
+ uint16_t res_cur_idx;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_rx()\n", dev->device_fh);
+
+ if (count == 0)
+ return 0;
+
+ vq = dev->virtqueue[VIRTIO_RXQ];
+ count = (count > MAX_PKT_BURST) ? MAX_PKT_BURST : count;
+
+ res_cur_idx = vq->last_used_idx;
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Current Index %d| End Index %d\n",
+ dev->device_fh, res_cur_idx, res_cur_idx + count);
+
+ /* Retrieve all of the head indexes first to avoid caching issues. */
+ for (head_idx = 0; head_idx < count; head_idx++)
+ head[head_idx] = MBUF_HEADROOM_UINT32(pkts[head_idx]);
+
+ /*Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[packet_success]]);
+
+ while (packet_success != count) {
+ /* Get descriptor from available ring */
+ desc = &vq->desc[head[packet_success]];
+
+ buff = pkts[packet_success];
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in dev_rx_zcp: update the used idx for "
+ "pkt[%d] descriptor idx: %d\n",
+ dev->device_fh, packet_success,
+ MBUF_HEADROOM_UINT32(buff));
+
+ PRINT_PACKET(dev,
+ (uintptr_t)(((uint64_t)(uintptr_t)buff->buf_addr)
+ + RTE_PKTMBUF_HEADROOM),
+ rte_pktmbuf_data_len(buff), 0);
+
+ /* Buffer address translation for virtio header. */
+ buff_hdr_addr = gpa_to_vva(dev, desc->addr);
+ packet_len = rte_pktmbuf_data_len(buff) + vq->vhost_hlen;
+
+ /*
+ * If the descriptors are chained the header and data are
+ * placed in separate buffers.
+ */
+ if (desc->flags & VRING_DESC_F_NEXT) {
+ desc->len = vq->vhost_hlen;
+ desc = &vq->desc[desc->next];
+ desc->len = rte_pktmbuf_data_len(buff);
+ } else {
+ desc->len = packet_len;
+ }
+
+ /* Update used ring with desc information */
+ vq->used->ring[res_cur_idx & (vq->size - 1)].id
+ = head[packet_success];
+ vq->used->ring[res_cur_idx & (vq->size - 1)].len
+ = packet_len;
+ res_cur_idx++;
+ packet_success++;
+
+ /* A header is required per buffer. */
+ rte_memcpy((void *)(uintptr_t)buff_hdr_addr,
+ (const void *)&virtio_hdr, vq->vhost_hlen);
+
+ PRINT_PACKET(dev, (uintptr_t)buff_hdr_addr, vq->vhost_hlen, 1);
+
+ if (likely(packet_success < count)) {
+ /* Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[packet_success]]);
+ }
+ }
+
+ rte_compiler_barrier();
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in dev_rx_zcp: before update used idx: "
+ "vq.last_used_idx: %d, vq->used->idx: %d\n",
+ dev->device_fh, vq->last_used_idx, vq->used->idx);
+
+ *(volatile uint16_t *)&vq->used->idx += count;
+ vq->last_used_idx += count;
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in dev_rx_zcp: after update used idx: "
+ "vq.last_used_idx: %d, vq->used->idx: %d\n",
+ dev->device_fh, vq->last_used_idx, vq->used->idx);
+
+ /* Kick the guest if necessary. */
+ if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT))
+ eventfd_write((int)vq->kickfd, 1);
+
+ return count;
+}
+
+/*
+ * This function routes the TX packet to the correct interface.
+ * This may be a local device or the physical port.
+ */
+static inline void __attribute__((always_inline))
+virtio_tx_route_zcp(struct virtio_net *dev, struct rte_mbuf *m,
+ uint32_t desc_idx, uint8_t need_copy)
+{
+ struct mbuf_table *tx_q;
+ struct rte_mbuf **m_table;
+ struct rte_mbuf *mbuf = NULL;
+ unsigned len, ret, offset = 0;
+ struct vpool *vpool;
+ struct virtio_net_data_ll *dev_ll = ll_root_used;
+ struct ether_hdr *pkt_hdr = (struct ether_hdr *)m->pkt.data;
+ uint16_t vlan_tag = (uint16_t)vlan_tags[(uint16_t)dev->device_fh];
+
+ /*Add packet to the port tx queue*/
+ tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
+ len = tx_q->len;
+
+ /* Allocate an mbuf and populate the structure. */
+ vpool = &vpool_array[MAX_QUEUES + (uint16_t)dev->vmdq_rx_q];
+ rte_ring_sc_dequeue(vpool->ring, (void **)&mbuf);
+ if (unlikely(mbuf == NULL)) {
+ struct vhost_virtqueue *vq = dev->virtqueue[VIRTIO_TXQ];
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%"PRIu64") Failed to allocate memory for mbuf.\n",
+ dev->device_fh);
+ put_desc_to_used_list_zcp(vq, desc_idx);
+ return;
+ }
+
+ if (vm2vm_mode == VM2VM_HARDWARE) {
+ /* Avoid using a vlan tag from any vm for external pkt, such as
+ * vlan_tags[dev->device_fh], oterwise, it conflicts when pool
+ * selection, MAC address determines it as an external pkt
+ * which should go to network, while vlan tag determine it as
+ * a vm2vm pkt should forward to another vm. Hardware confuse
+ * such a ambiguous situation, so pkt will lost.
+ */
+ vlan_tag = external_pkt_default_vlan_tag;
+ while (dev_ll != NULL) {
+ if (likely(dev_ll->dev->ready == DEVICE_RX) &&
+ ether_addr_cmp(&(pkt_hdr->d_addr),
+ &dev_ll->dev->mac_address)) {
+
+ /*
+ * Drop the packet if the TX packet is destined
+ * for the TX device.
+ */
+ if (unlikely(dev_ll->dev->device_fh
+ == dev->device_fh)) {
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: Source and destination"
+ "MAC addresses are the same. Dropping "
+ "packet.\n",
+ dev_ll->dev->device_fh);
+ MBUF_HEADROOM_UINT32(mbuf)
+ = (uint32_t)desc_idx;
+ __rte_mbuf_raw_free(mbuf);
+ return;
+ }
+
+ /*
+ * Packet length offset 4 bytes for HW vlan
+ * strip when L2 switch back.
+ */
+ offset = 4;
+ vlan_tag =
+ (uint16_t)
+ vlan_tags[(uint16_t)dev_ll->dev->device_fh];
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") TX: pkt to local VM device id:"
+ "(%"PRIu64") vlan tag: %d.\n",
+ dev->device_fh, dev_ll->dev->device_fh,
+ vlan_tag);
+
+ break;
}
+ dev_ll = dev_ll->next;
+ }
+ }
- prev_tsc = cur_tsc;
+ mbuf->pkt.nb_segs = m->pkt.nb_segs;
+ mbuf->pkt.next = m->pkt.next;
+ mbuf->pkt.data_len = m->pkt.data_len + offset;
+ mbuf->pkt.pkt_len = mbuf->pkt.data_len;
+ if (unlikely(need_copy)) {
+ /* Copy the packet contents to the mbuf. */
+ rte_memcpy((void *)((uint8_t *)mbuf->pkt.data),
+ (const void *) ((uint8_t *)m->pkt.data),
+ m->pkt.data_len);
+ } else {
+ mbuf->pkt.data = m->pkt.data;
+ mbuf->buf_physaddr = m->buf_physaddr;
+ mbuf->buf_addr = m->buf_addr;
+ }
+ mbuf->ol_flags = PKT_TX_VLAN_PKT;
+ mbuf->pkt.vlan_macip.f.vlan_tci = vlan_tag;
+ mbuf->pkt.vlan_macip.f.l2_len = sizeof(struct ether_hdr);
+ mbuf->pkt.vlan_macip.f.l3_len = sizeof(struct ipv4_hdr);
+ MBUF_HEADROOM_UINT32(mbuf) = (uint32_t)desc_idx;
+
+ tx_q->m_table[len] = mbuf;
+ len++;
+
+ LOG_DEBUG(VHOST_DATA,
+ "(%"PRIu64") in tx_route_zcp: pkt: nb_seg: %d, next:%s\n",
+ dev->device_fh,
+ mbuf->pkt.nb_segs,
+ (mbuf->pkt.next == NULL) ? "null" : "non-null");
+
+ if (enable_stats) {
+ dev_statistics[dev->device_fh].tx_total++;
+ dev_statistics[dev->device_fh].tx++;
+ }
+ if (unlikely(len == MAX_PKT_BURST)) {
+ m_table = (struct rte_mbuf **)tx_q->m_table;
+ ret = rte_eth_tx_burst(ports[0],
+ (uint16_t)tx_q->txq_id, m_table, (uint16_t) len);
+
+ /*
+ * Free any buffers not handled by TX and update
+ * the port stats.
+ */
+ if (unlikely(ret < len)) {
+ do {
+ rte_pktmbuf_free(m_table[ret]);
+ } while (++ret < len);
}
- rte_prefetch0(lcore_ll->ll_root_used);
- /*
- * Inform the configuration core that we have exited the linked list and that no devices are
- * in use if requested.
+ len = 0;
+ txmbuf_clean_zcp(dev, vpool);
+ }
+
+ tx_q->len = len;
+
+ return;
+}
+
+/*
+ * This function TX all available packets in virtio TX queue for one
+ * virtio-net device. If it is first packet, it learns MAC address and
+ * setup VMDQ.
+ */
+static inline void __attribute__((always_inline))
+virtio_dev_tx_zcp(struct virtio_net *dev)
+{
+ struct rte_mbuf m;
+ struct vhost_virtqueue *vq;
+ struct vring_desc *desc;
+ uint64_t buff_addr = 0, phys_addr;
+ uint32_t head[MAX_PKT_BURST];
+ uint32_t i;
+ uint16_t free_entries, packet_success = 0;
+ uint16_t avail_idx;
+ uint8_t need_copy = 0;
+ hpa_type addr_type;
+
+ vq = dev->virtqueue[VIRTIO_TXQ];
+ avail_idx = *((volatile uint16_t *)&vq->avail->idx);
+
+ /* If there are no available buffers then return. */
+ if (vq->last_used_idx_res == avail_idx)
+ return;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") virtio_dev_tx()\n", dev->device_fh);
+
+ /* Prefetch available ring to retrieve head indexes. */
+ rte_prefetch0(&vq->avail->ring[vq->last_used_idx_res & (vq->size - 1)]);
+
+ /* Get the number of free entries in the ring */
+ free_entries = (avail_idx - vq->last_used_idx_res);
+
+ /* Limit to MAX_PKT_BURST. */
+ free_entries
+ = (free_entries > MAX_PKT_BURST) ? MAX_PKT_BURST : free_entries;
+
+ LOG_DEBUG(VHOST_DATA, "(%"PRIu64") Buffers available %d\n",
+ dev->device_fh, free_entries);
+
+ /* Retrieve all of the head indexes first to avoid caching issues. */
+ for (i = 0; i < free_entries; i++)
+ head[i]
+ = vq->avail->ring[(vq->last_used_idx_res + i)
+ & (vq->size - 1)];
+
+ vq->last_used_idx_res += free_entries;
+
+ /* Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[packet_success]]);
+ rte_prefetch0(&vq->used->ring[vq->last_used_idx & (vq->size - 1)]);
+
+ while (packet_success < free_entries) {
+ desc = &vq->desc[head[packet_success]];
+
+ /* Discard first buffer as it is the virtio header */
+ desc = &vq->desc[desc->next];
+
+ /* Buffer address translation. */
+ buff_addr = gpa_to_vva(dev, desc->addr);
+ phys_addr = gpa_to_hpa(dev, desc->addr, desc->len, &addr_type);
+
+ if (likely(packet_success < (free_entries - 1)))
+ /* Prefetch descriptor index. */
+ rte_prefetch0(&vq->desc[head[packet_success + 1]]);
+
+ if (unlikely(addr_type == PHYS_ADDR_INVALID)) {
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%"PRIu64") Invalid frame buffer address found"
+ "when TX packets!\n",
+ dev->device_fh);
+ packet_success++;
+ continue;
+ }
+
+ /* Prefetch buffer address. */
+ rte_prefetch0((void *)(uintptr_t)buff_addr);
+
+ /*
+ * Setup dummy mbuf. This is copied to a real mbuf if
+ * transmitted out the physical port.
*/
- if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL)
- lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
+ m.pkt.data_len = desc->len;
+ m.pkt.nb_segs = 1;
+ m.pkt.next = NULL;
+ m.pkt.data = (void *)(uintptr_t)buff_addr;
+ m.buf_addr = m.pkt.data;
+ m.buf_physaddr = phys_addr;
/*
- * Process devices
+ * Check if the frame buffer address from guest crosses
+ * sub-region or not.
+ */
+ if (unlikely(addr_type == PHYS_ADDR_CROSS_SUBREG)) {
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%"PRIu64") Frame buffer address cross "
+ "sub-regioin found when attaching TX frame "
+ "buffer address!\n",
+ dev->device_fh);
+ need_copy = 1;
+ } else
+ need_copy = 0;
+
+ PRINT_PACKET(dev, (uintptr_t)buff_addr, desc->len, 0);
+
+ /*
+ * If this is the first received packet we need to learn
+ * the MAC and setup VMDQ
+ */
+ if (unlikely(dev->ready == DEVICE_MAC_LEARNING)) {
+ if (dev->remove || (link_vmdq(dev, &m) == -1)) {
+ /*
+ * Discard frame if device is scheduled for
+ * removal or a duplicate MAC address is found.
+ */
+ packet_success += free_entries;
+ vq->last_used_idx += packet_success;
+ break;
+ }
+ }
+
+ virtio_tx_route_zcp(dev, &m, head[packet_success], need_copy);
+ packet_success++;
+ }
+}
+
+/*
+ * This function is called by each data core. It handles all RX/TX registered
+ * with the core. For TX the specific lcore linked list is used. For RX, MAC
+ * addresses are compared with all devices in the main linked list.
+ */
+static int
+switch_worker_zcp(__attribute__((unused)) void *arg)
+{
+ struct virtio_net *dev = NULL;
+ struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ struct virtio_net_data_ll *dev_ll;
+ struct mbuf_table *tx_q;
+ volatile struct lcore_ll_info *lcore_ll;
+ const uint64_t drain_tsc
+ = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S
+ * BURST_TX_DRAIN_US;
+ uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
+ unsigned ret;
+ const uint16_t lcore_id = rte_lcore_id();
+ uint16_t count_in_ring, rx_count = 0;
+
+ RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id);
+
+ lcore_ll = lcore_info[lcore_id].lcore_ll;
+ prev_tsc = 0;
+
+ while (1) {
+ cur_tsc = rte_rdtsc();
+
+ /* TX burst queue drain */
+ diff_tsc = cur_tsc - prev_tsc;
+ if (unlikely(diff_tsc > drain_tsc)) {
+ /*
+ * Get mbuf from vpool.pool and detach mbuf and
+ * put back into vpool.ring.
+ */
+ dev_ll = lcore_ll->ll_root_used;
+ while ((dev_ll != NULL) && (dev_ll->dev != NULL)) {
+ /* Get virtio device ID */
+ dev = dev_ll->dev;
+
+ if (likely(!dev->remove)) {
+ tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
+ if (tx_q->len) {
+ LOG_DEBUG(VHOST_DATA,
+ "TX queue drained after timeout"
+ " with burst size %u\n",
+ tx_q->len);
+
+ /*
+ * Tx any packets in the queue
+ */
+ ret = rte_eth_tx_burst(
+ ports[0],
+ (uint16_t)tx_q->txq_id,
+ (struct rte_mbuf **)
+ tx_q->m_table,
+ (uint16_t)tx_q->len);
+ if (unlikely(ret < tx_q->len)) {
+ do {
+ rte_pktmbuf_free(
+ tx_q->m_table[ret]);
+ } while (++ret < tx_q->len);
+ }
+ tx_q->len = 0;
+
+ txmbuf_clean_zcp(dev,
+ &vpool_array[MAX_QUEUES+dev->vmdq_rx_q]);
+ }
+ }
+ dev_ll = dev_ll->next;
+ }
+ prev_tsc = cur_tsc;
+ }
+
+ rte_prefetch0(lcore_ll->ll_root_used);
+
+ /*
+ * Inform the configuration core that we have exited the linked
+ * list and that no devices are in use if requested.
*/
+ if (lcore_ll->dev_removal_flag == REQUEST_DEV_REMOVAL)
+ lcore_ll->dev_removal_flag = ACK_DEV_REMOVAL;
+
+ /* Process devices */
dev_ll = lcore_ll->ll_root_used;
- while (dev_ll != NULL) {
- /*get virtio device ID*/
+ while ((dev_ll != NULL) && (dev_ll->dev != NULL)) {
dev = dev_ll->dev;
-
- if (dev->remove) {
+ if (unlikely(dev->remove)) {
dev_ll = dev_ll->next;
unlink_vmdq(dev);
dev->ready = DEVICE_SAFE_REMOVE;
continue;
}
+
if (likely(dev->ready == DEVICE_RX)) {
- /*Handle guest RX*/
+ uint32_t index = dev->vmdq_rx_q;
+ uint16_t i;
+ count_in_ring
+ = rte_ring_count(vpool_array[index].ring);
+ uint16_t free_entries
+ = (uint16_t)get_available_ring_num_zcp(dev);
+
+ /*
+ * Attach all mbufs in vpool.ring and put back
+ * into vpool.pool.
+ */
+ for (i = 0;
+ i < RTE_MIN(free_entries,
+ RTE_MIN(count_in_ring, MAX_PKT_BURST));
+ i++)
+ attach_rxmbuf_zcp(dev);
+
+ /* Handle guest RX */
rx_count = rte_eth_rx_burst(ports[0],
- (uint16_t)dev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
+ (uint16_t)dev->vmdq_rx_q, pkts_burst,
+ MAX_PKT_BURST);
if (rx_count) {
- ret_count = virtio_dev_rx(dev, pkts_burst, rx_count);
+ ret_count = virtio_dev_rx_zcp(dev,
+ pkts_burst, rx_count);
if (enable_stats) {
- rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx_total, rx_count);
- rte_atomic64_add(&dev_statistics[dev_ll->dev->device_fh].rx, ret_count);
+ dev_statistics[dev->device_fh].rx_total
+ += rx_count;
+ dev_statistics[dev->device_fh].rx
+ += ret_count;
}
while (likely(rx_count)) {
rx_count--;
- rte_pktmbuf_free_seg(pkts_burst[rx_count]);
+ pktmbuf_detach_zcp(
+ pkts_burst[rx_count]);
+ rte_ring_sp_enqueue(
+ vpool_array[index].ring,
+ (void *)pkts_burst[rx_count]);
}
-
}
}
- if (!dev->remove)
- /*Handle guest TX*/
- virtio_dev_tx(dev, mbuf_pool);
+ if (likely(!dev->remove))
+ /* Handle guest TX */
+ virtio_dev_tx_zcp(dev);
- /*move to the next device in the list*/
+ /* Move to the next device in the list */
dev_ll = dev_ll->next;
}
}
return 0;
}
+
/*
- * Add an entry to a used linked list. A free entry must first be found in the free linked list
- * using get_data_ll_free_entry();
+ * Add an entry to a used linked list. A free entry must first be found
+ * in the free linked list using get_data_ll_free_entry();
*/
static void
-add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev)
+add_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
+ struct virtio_net_data_ll *ll_dev)
{
struct virtio_net_data_ll *ll = *ll_root_addr;
}
/*
- * Remove an entry from a used linked list. The entry must then be added to the free linked list
- * using put_data_ll_free_entry().
+ * Remove an entry from a used linked list. The entry must then be added to
+ * the free linked list using put_data_ll_free_entry().
*/
static void
-rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev, struct virtio_net_data_ll *ll_dev_last)
+rm_data_ll_entry(struct virtio_net_data_ll **ll_root_addr,
+ struct virtio_net_data_ll *ll_dev,
+ struct virtio_net_data_ll *ll_dev_last)
{
struct virtio_net_data_ll *ll = *ll_root_addr;
-
+
if (unlikely((ll == NULL) || (ll_dev == NULL)))
return;
if (likely(ll_dev_last != NULL))
ll_dev_last->next = ll_dev->next;
else
- RTE_LOG(ERR, CONFIG, "Remove entry form ll failed.\n");
+ RTE_LOG(ERR, VHOST_CONFIG, "Remove entry form ll failed.\n");
}
/*
* Place an entry back on to the free linked list.
*/
static void
-put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr, struct virtio_net_data_ll *ll_dev)
+put_data_ll_free_entry(struct virtio_net_data_ll **ll_root_addr,
+ struct virtio_net_data_ll *ll_dev)
{
struct virtio_net_data_ll *ll_free = *ll_root_addr;
/* Malloc and then chain the linked list. */
ll_new = malloc(size * sizeof(struct virtio_net_data_ll));
if (ll_new == NULL) {
- RTE_LOG(ERR, CONFIG, "Failed to allocate memory for ll_new.\n");
+ RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for ll_new.\n");
return NULL;
}
RTE_LCORE_FOREACH_SLAVE(lcore) {
lcore_info[lcore].lcore_ll = malloc(sizeof(struct lcore_ll_info));
if (lcore_info[lcore].lcore_ll == NULL) {
- RTE_LOG(ERR, CONFIG, "Failed to allocate memory for lcore_ll.\n");
+ RTE_LOG(ERR, VHOST_CONFIG, "Failed to allocate memory for lcore_ll.\n");
return -1;
}
}
/*
- * Remove a device from the specific data core linked list and from the main linked list. Synchonization
- * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
+ * Remove a device from the specific data core linked list and from the main linked list. Synchonization
+ * occurs through the use of the lcore dev_removal_flag. Device is made volatile here to avoid re-ordering
* of dev->remove=1 which can cause an infinite loop in the rte_pause loop.
*/
static void
}
if (ll_lcore_dev_cur == NULL) {
- RTE_LOG(ERR, CONFIG, "Failed to find the dev to be destroy.\n");
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "(%"PRIu64") Failed to find the dev to be destroy.\n",
+ dev->device_fh);
return;
}
RTE_LCORE_FOREACH_SLAVE(lcore) {
lcore_info[lcore].lcore_ll->dev_removal_flag = REQUEST_DEV_REMOVAL;
}
-
- /*
+
+ /*
* Once each core has set the dev_removal_flag to ACK_DEV_REMOVAL we can be sure that
* they can no longer access the device removed from the linked lists and that the devices
* are no longer in use.
/* Add the entries back to the lcore and main free ll.*/
put_data_ll_free_entry(&lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->ll_root_free, ll_lcore_dev_cur);
put_data_ll_free_entry(&ll_root_free, ll_main_dev_cur);
-
+
/* Decrement number of device on the lcore. */
lcore_info[ll_lcore_dev_cur->dev->coreid].lcore_ll->device_num--;
-
- RTE_LOG(INFO, DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
+
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been removed from data core\n", dev->device_fh);
+
+ if (zero_copy) {
+ struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
+
+ /* Stop the RX queue. */
+ if (rte_eth_dev_rx_queue_stop(ports[0], dev->vmdq_rx_q) != 0) {
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") In destroy_device: Failed to stop "
+ "rx queue:%d\n",
+ dev->device_fh,
+ dev->vmdq_rx_q);
+ }
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") in destroy_device: Start put mbuf in "
+ "mempool back to ring for RX queue: %d\n",
+ dev->device_fh, dev->vmdq_rx_q);
+
+ mbuf_destroy_zcp(vpool);
+
+ /* Stop the TX queue. */
+ if (rte_eth_dev_tx_queue_stop(ports[0], dev->vmdq_rx_q) != 0) {
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") In destroy_device: Failed to "
+ "stop tx queue:%d\n",
+ dev->device_fh, dev->vmdq_rx_q);
+ }
+
+ vpool = &vpool_array[dev->vmdq_rx_q + MAX_QUEUES];
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") destroy_device: Start put mbuf in mempool "
+ "back to ring for TX queue: %d, dev:(%"PRIu64")\n",
+ dev->device_fh, (dev->vmdq_rx_q + MAX_QUEUES),
+ dev->device_fh);
+
+ mbuf_destroy_zcp(vpool);
+ }
+
}
/*
/* Add device to main ll */
ll_dev = get_data_ll_free_entry(&ll_root_free);
if (ll_dev == NULL) {
- RTE_LOG(INFO, DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") No free entry found in linked list. Device limit "
"of %d devices per core has been reached\n",
dev->device_fh, num_devices);
return -1;
}
ll_dev->dev = dev;
add_data_ll_entry(&ll_root_used, ll_dev);
+ ll_dev->dev->vmdq_rx_q
+ = ll_dev->dev->device_fh * (num_queues / num_devices);
+
+ if (zero_copy) {
+ uint32_t index = ll_dev->dev->vmdq_rx_q;
+ uint32_t count_in_ring, i;
+ struct mbuf_table *tx_q;
+
+ count_in_ring = rte_ring_count(vpool_array[index].ring);
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") in new_device: mbuf count in mempool "
+ "before attach is: %d\n",
+ dev->device_fh,
+ rte_mempool_count(vpool_array[index].pool));
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") in new_device: mbuf count in ring "
+ "before attach is : %d\n",
+ dev->device_fh, count_in_ring);
+
+ /*
+ * Attach all mbufs in vpool.ring and put back intovpool.pool.
+ */
+ for (i = 0; i < count_in_ring; i++)
+ attach_rxmbuf_zcp(dev);
+
+ LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in "
+ "mempool after attach is: %d\n",
+ dev->device_fh,
+ rte_mempool_count(vpool_array[index].pool));
+ LOG_DEBUG(VHOST_CONFIG, "(%"PRIu64") in new_device: mbuf count in "
+ "ring after attach is : %d\n",
+ dev->device_fh,
+ rte_ring_count(vpool_array[index].ring));
+
+ tx_q = &tx_queue_zcp[(uint16_t)dev->vmdq_rx_q];
+ tx_q->txq_id = dev->vmdq_rx_q;
+
+ if (rte_eth_dev_tx_queue_start(ports[0], dev->vmdq_rx_q) != 0) {
+ struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") In new_device: Failed to start "
+ "tx queue:%d\n",
+ dev->device_fh, dev->vmdq_rx_q);
+
+ mbuf_destroy_zcp(vpool);
+ return -1;
+ }
+
+ if (rte_eth_dev_rx_queue_start(ports[0], dev->vmdq_rx_q) != 0) {
+ struct vpool *vpool = &vpool_array[dev->vmdq_rx_q];
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") In new_device: Failed to start "
+ "rx queue:%d\n",
+ dev->device_fh, dev->vmdq_rx_q);
+
+ /* Stop the TX queue. */
+ if (rte_eth_dev_tx_queue_stop(ports[0],
+ dev->vmdq_rx_q) != 0) {
+ LOG_DEBUG(VHOST_CONFIG,
+ "(%"PRIu64") In new_device: Failed to "
+ "stop tx queue:%d\n",
+ dev->device_fh, dev->vmdq_rx_q);
+ }
+
+ mbuf_destroy_zcp(vpool);
+ return -1;
+ }
+
+ }
/*reset ready flag*/
dev->ready = DEVICE_MAC_LEARNING;
ll_dev->dev->coreid = core_add;
ll_dev = get_data_ll_free_entry(&lcore_info[ll_dev->dev->coreid].lcore_ll->ll_root_free);
if (ll_dev == NULL) {
- RTE_LOG(INFO, DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Failed to add device to data core\n", dev->device_fh);
+ dev->ready = DEVICE_SAFE_REMOVE;
destroy_device(dev);
return -1;
}
lcore_info[ll_dev->dev->coreid].lcore_ll->device_num++;
dev->flags |= VIRTIO_DEV_RUNNING;
- RTE_LOG(INFO, DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, dev->coreid);
+ RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, dev->coreid);
return 0;
}
tx_total = dev_statistics[device_fh].tx_total;
tx = dev_statistics[device_fh].tx;
tx_dropped = tx_total - tx;
- rx_total = rte_atomic64_read(&dev_statistics[device_fh].rx_total);
- rx = rte_atomic64_read(&dev_statistics[device_fh].rx);
+ if (zero_copy == 0) {
+ rx_total = rte_atomic64_read(
+ &dev_statistics[device_fh].rx_total_atomic);
+ rx = rte_atomic64_read(
+ &dev_statistics[device_fh].rx_atomic);
+ } else {
+ rx_total = dev_statistics[device_fh].rx_total;
+ rx = dev_statistics[device_fh].rx;
+ }
rx_dropped = rx_total - rx;
printf("\nStatistics for device %"PRIu32" ------------------------------"
}
}
+static void
+setup_mempool_tbl(int socket, uint32_t index, char *pool_name,
+ char *ring_name, uint32_t nb_mbuf)
+{
+ uint16_t roomsize = VIRTIO_DESCRIPTOR_LEN_ZCP + RTE_PKTMBUF_HEADROOM;
+ vpool_array[index].pool
+ = rte_mempool_create(pool_name, nb_mbuf, MBUF_SIZE_ZCP,
+ MBUF_CACHE_SIZE_ZCP, sizeof(struct rte_pktmbuf_pool_private),
+ rte_pktmbuf_pool_init, (void *)(uintptr_t)roomsize,
+ rte_pktmbuf_init, NULL, socket, 0);
+ if (vpool_array[index].pool != NULL) {
+ vpool_array[index].ring
+ = rte_ring_create(ring_name,
+ rte_align32pow2(nb_mbuf + 1),
+ socket, RING_F_SP_ENQ | RING_F_SC_DEQ);
+ if (likely(vpool_array[index].ring != NULL)) {
+ LOG_DEBUG(VHOST_CONFIG,
+ "in setup_mempool_tbl: mbuf count in "
+ "mempool is: %d\n",
+ rte_mempool_count(vpool_array[index].pool));
+ LOG_DEBUG(VHOST_CONFIG,
+ "in setup_mempool_tbl: mbuf count in "
+ "ring is: %d\n",
+ rte_ring_count(vpool_array[index].ring));
+ } else {
+ rte_exit(EXIT_FAILURE, "ring_create(%s) failed",
+ ring_name);
+ }
+
+ /* Need consider head room. */
+ vpool_array[index].buf_size = roomsize - RTE_PKTMBUF_HEADROOM;
+ } else {
+ rte_exit(EXIT_FAILURE, "mempool_create(%s) failed", pool_name);
+ }
+}
+
+
/*
* Main function, does initialisation and calls the per-lcore functions. The CUSE
* device is also registered here to handle the IOCTLs.
int
MAIN(int argc, char *argv[])
{
- struct rte_mempool *mbuf_pool;
+ struct rte_mempool *mbuf_pool = NULL;
unsigned lcore_id, core_id = 0;
unsigned nb_ports, valid_num_ports;
int ret;
- uint8_t portid;
+ uint8_t portid, queue_id = 0;
static pthread_t tid;
/* init EAL */
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid argument\n");
- if (rte_pmd_init_all() != 0 || rte_eal_pci_probe() != 0)
+ if (rte_eal_pci_probe() != 0)
rte_exit(EXIT_FAILURE, "Error with NIC driver initialization\n");
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id ++)
nb_ports = RTE_MAX_ETHPORTS;
/*
- * Update the global var NUM_PORTS and global array PORTS
- * and get value of var VALID_NUM_PORTS according to system ports number
- */
+ * Update the global var NUM_PORTS and global array PORTS
+ * and get value of var VALID_NUM_PORTS according to system ports number
+ */
valid_num_ports = check_ports_num(nb_ports);
if ((valid_num_ports == 0) || (valid_num_ports > MAX_SUP_PORTS)) {
- RTE_LOG(INFO, PORT, "Current enabled port number is %u,"
+ RTE_LOG(INFO, VHOST_PORT, "Current enabled port number is %u,"
"but only %u port can be enabled\n",num_ports, MAX_SUP_PORTS);
return -1;
}
- /* Create the mbuf pool. */
- mbuf_pool = rte_mempool_create("MBUF_POOL", NUM_MBUFS_PER_PORT * valid_num_ports,
- MBUF_SIZE, MBUF_CACHE_SIZE,
- sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, NULL,
- rte_pktmbuf_init, NULL,
- rte_socket_id(), 0);
- if (mbuf_pool == NULL)
- rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
+ if (zero_copy == 0) {
+ /* Create the mbuf pool. */
+ mbuf_pool = rte_mempool_create(
+ "MBUF_POOL",
+ NUM_MBUFS_PER_PORT
+ * valid_num_ports,
+ MBUF_SIZE, MBUF_CACHE_SIZE,
+ sizeof(struct rte_pktmbuf_pool_private),
+ rte_pktmbuf_pool_init, NULL,
+ rte_pktmbuf_init, NULL,
+ rte_socket_id(), 0);
+ if (mbuf_pool == NULL)
+ rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
+
+ for (queue_id = 0; queue_id < MAX_QUEUES + 1; queue_id++)
+ vpool_array[queue_id].pool = mbuf_pool;
+
+ if (vm2vm_mode == VM2VM_HARDWARE) {
+ /* Enable VT loop back to let L2 switch to do it. */
+ vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1;
+ LOG_DEBUG(VHOST_CONFIG,
+ "Enable loop back for L2 switch in vmdq.\n");
+ }
+ } else {
+ uint32_t nb_mbuf;
+ char pool_name[RTE_MEMPOOL_NAMESIZE];
+ char ring_name[RTE_MEMPOOL_NAMESIZE];
+
+ rx_conf_default.start_rx_per_q = (uint8_t)zero_copy;
+ rx_conf_default.rx_drop_en = 0;
+ tx_conf_default.start_tx_per_q = (uint8_t)zero_copy;
+ nb_mbuf = num_rx_descriptor
+ + num_switching_cores * MBUF_CACHE_SIZE_ZCP
+ + num_switching_cores * MAX_PKT_BURST;
+
+ for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) {
+ snprintf(pool_name, sizeof(pool_name),
+ "rxmbuf_pool_%u", queue_id);
+ snprintf(ring_name, sizeof(ring_name),
+ "rxmbuf_ring_%u", queue_id);
+ setup_mempool_tbl(rte_socket_id(), queue_id,
+ pool_name, ring_name, nb_mbuf);
+ }
+
+ nb_mbuf = num_tx_descriptor
+ + num_switching_cores * MBUF_CACHE_SIZE_ZCP
+ + num_switching_cores * MAX_PKT_BURST;
+
+ for (queue_id = 0; queue_id < MAX_QUEUES; queue_id++) {
+ snprintf(pool_name, sizeof(pool_name),
+ "txmbuf_pool_%u", queue_id);
+ snprintf(ring_name, sizeof(ring_name),
+ "txmbuf_ring_%u", queue_id);
+ setup_mempool_tbl(rte_socket_id(),
+ (queue_id + MAX_QUEUES),
+ pool_name, ring_name, nb_mbuf);
+ }
+ if (vm2vm_mode == VM2VM_HARDWARE) {
+ /* Enable VT loop back to let L2 switch to do it. */
+ vmdq_conf_default.rx_adv_conf.vmdq_rx_conf.enable_loop_back = 1;
+ LOG_DEBUG(VHOST_CONFIG,
+ "Enable loop back for L2 switch in vmdq.\n");
+ }
+ }
/* Set log level. */
rte_set_log_level(LOG_LEVEL);
for (portid = 0; portid < nb_ports; portid++) {
/* skip ports that are not enabled */
if ((enabled_port_mask & (1 << portid)) == 0) {
- RTE_LOG(INFO, PORT, "Skipping disabled port %d\n", portid);
+ RTE_LOG(INFO, VHOST_PORT,
+ "Skipping disabled port %d\n", portid);
continue;
}
- if (port_init(portid, mbuf_pool) != 0)
- rte_exit(EXIT_FAILURE, "Cannot initialize network ports\n");
+ if (port_init(portid) != 0)
+ rte_exit(EXIT_FAILURE,
+ "Cannot initialize network ports\n");
}
/* Initialise all linked lists. */
pthread_create(&tid, NULL, (void*)print_stats, NULL );
/* Launch all data cores. */
- RTE_LCORE_FOREACH_SLAVE(lcore_id) {
- rte_eal_remote_launch(switch_worker, mbuf_pool, lcore_id);
+ if (zero_copy == 0) {
+ RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+ rte_eal_remote_launch(switch_worker,
+ mbuf_pool, lcore_id);
+ }
+ } else {
+ uint32_t count_in_mempool, index, i;
+ for (index = 0; index < 2*MAX_QUEUES; index++) {
+ /* For all RX and TX queues. */
+ count_in_mempool
+ = rte_mempool_count(vpool_array[index].pool);
+
+ /*
+ * Transfer all un-attached mbufs from vpool.pool
+ * to vpoo.ring.
+ */
+ for (i = 0; i < count_in_mempool; i++) {
+ struct rte_mbuf *mbuf
+ = __rte_mbuf_raw_alloc(
+ vpool_array[index].pool);
+ rte_ring_sp_enqueue(vpool_array[index].ring,
+ (void *)mbuf);
+ }
+
+ LOG_DEBUG(VHOST_CONFIG,
+ "in MAIN: mbuf count in mempool at initial "
+ "is: %d\n", count_in_mempool);
+ LOG_DEBUG(VHOST_CONFIG,
+ "in MAIN: mbuf count in ring at initial is :"
+ " %d\n",
+ rte_ring_count(vpool_array[index].ring));
+ }
+
+ RTE_LCORE_FOREACH_SLAVE(lcore_id)
+ rte_eal_remote_launch(switch_worker_zcp, NULL,
+ lcore_id);
}
/* Register CUSE device to handle IOCTLs. */
git.droids-corp.org / dpdk.git / blobdiff