@@ -3,15 +3,24 @@
enable_tap_rss = false
+# Loading BPF requires libbpf
libbpf = dependency('libbpf', required: false, method: 'pkg-config')
if not libbpf.found()
message('net/tap: no RSS support missing libbpf')
subdir_done()
endif
+# Making skeleton needs bpftool
# Debian install this in /usr/sbin which is not in $PATH
-bpftool = find_program('bpftool', '/usr/sbin/bpftool', required: false, version: '>= 5.6.0')
-if not bpftool.found()
+bpftool_supports_skel = false
+bpftool = find_program('bpftool', '/usr/sbin/bpftool', required: false)
+if bpftool.found()
+ # Some Ubuntu has non-functional bpftool
+ bpftool_supports_skel = run_command(bpftool, 'gen', 'help',
+ check:false).returncode() == 0
+endif
+
+if not bpftool_supports_skel
message('net/tap: no RSS support missing bpftool')
subdir_done()
endif
@@ -42,6 +51,7 @@ clang_flags = [
'-O2',
'-Wall',
'-Wextra',
+ max_queues,
'-target',
'bpf',
'-g',
@@ -67,6 +77,22 @@ skel_h_cmd = [
'@INPUT@'
]
+vmlinux_h_cmd = [
+ bpftool,
+ 'btf',
+ 'dump',
+ 'file',
+ '/sys/kernel/btf/vmlinux',
+ 'format',
+ 'c'
+]
+
+vmlinux_h = custom_target(
+ 'vmlinux.h',
+ output: 'vmlinux.h',
+ command: vmlinux_h_cmd,
+ capture: true)
+
tap_rss_o = custom_target(
'tap_rss.bpf.o',
input: 'tap_rss.c',
@@ -203,23 +203,6 @@ parse_ipv6(const struct __sk_buff *skb, __u32 hash_type, const __u32 *key)
return 0;
}
-/*
- * Compute RSS hash for packets.
- * Returns 0 if no hash is possible.
- */
-static __u32 __attribute__((always_inline))
-calculate_rss_hash(const struct __sk_buff *skb, const struct rss_key *rsskey)
-{
- const __u32 *key = (const __u32 *)rsskey->key;
-
- if (skb->protocol == bpf_htons(ETH_P_IP))
- return parse_ipv4(skb, rsskey->hash_fields, key);
- else if (skb->protocol == bpf_htons(ETH_P_IPV6))
- return parse_ipv6(skb, rsskey->hash_fields, key);
- else
- return 0;
-}
-
/*
* Scale value to be into range [0, n)
* Assumes val is large (ie hash covers whole u32 range)
@@ -244,20 +227,40 @@ SEC("action") int
rss_flow_action(struct __sk_buff *skb)
{
const struct rss_key *rsskey;
- __u32 mark = skb->mark;
+ const __u32 *key;
+ __be16 proto;
+ __u32 mark;
__u32 hash;
+ __u16 queue;
+
+ __builtin_preserve_access_index(({
+ mark = skb->mark;
+ proto = skb->protocol;
+ }));
/* Lookup RSS configuration for that BPF class */
rsskey = bpf_map_lookup_elem(&rss_map, &mark);
if (rsskey == NULL)
return TC_ACT_OK;
- hash = calculate_rss_hash(skb, rsskey);
- if (!hash)
+ key = (const __u32 *)rsskey->key;
+
+ if (proto == bpf_htons(ETH_P_IP))
+ hash = parse_ipv4(skb, rsskey->hash_fields, key);
+ else if (proto == bpf_htons(ETH_P_IPV6))
+ hash = parse_ipv6(skb, rsskey->hash_fields, key);
+ else
+ hash = 0;
+
+ if (hash == 0)
return TC_ACT_OK;
/* Fold hash to the number of queues configured */
- skb->queue_mapping = reciprocal_scale(hash, rsskey->nb_queues);
+ queue = reciprocal_scale(hash, rsskey->nb_queues);
+
+ __builtin_preserve_access_index(({
+ skb->queue_mapping = queue;
+ }));
return TC_ACT_PIPE;
}
@@ -15,28 +15,22 @@ endif
sources = files(
'rte_eth_tap.c',
- 'tap_bpf_api.c',
'tap_flow.c',
'tap_intr.c',
'tap_netlink.c',
'tap_tcmsgs.c',
-)
+ )
deps = ['bus_vdev', 'gso', 'hash']
-cflags += '-DTAP_MAX_QUEUES=8'
-
-# input array for meson symbol search:
-# [ "MACRO to define if found", "header for the search",
-# "enum/define", "symbol to search" ]
-#
-args = [
- [ 'HAVE_TC_ACT_BPF', 'linux/tc_act/tc_bpf.h', 'TCA_ACT_BPF_UNSPEC' ],
-]
-config = configuration_data()
-foreach arg:args
- config.set(arg[0], cc.has_header_symbol(arg[1], arg[2]))
-endforeach
-configure_file(output : 'tap_autoconf.h', configuration : config)
+max_queues = '-DTAP_MAX_QUEUES=16'
+cflags += max_queues
require_iova_in_mbuf = false
+
+subdir('bpf')
+if enable_tap_rss
+ cflags += '-DHAVE_BPF_RSS'
+ ext_deps += libbpf
+ sources += tap_rss_skel_h
+endif
@@ -1129,6 +1129,7 @@ tap_dev_close(struct rte_eth_dev *dev)
tap_flow_implicit_flush(internals, NULL);
tap_nl_final(internals->nlsk_fd);
internals->nlsk_fd = -1;
+ tap_flow_bpf_destroy(internals);
}
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
@@ -1941,6 +1942,7 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name,
strlcpy(pmd->name, tap_name, sizeof(pmd->name));
pmd->type = type;
pmd->ka_fd = -1;
+ pmd->rss = NULL;
pmd->nlsk_fd = -1;
pmd->gso_ctx_mp = NULL;
@@ -2021,12 +2023,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name,
/* Make network device persist after application exit */
pmd->persist = persist;
- pmd->if_index = if_nametoindex(pmd->name);
- if (!pmd->if_index) {
- TAP_LOG(ERR, "%s: failed to get if_index.", pmd->name);
- goto disable_rte_flow;
- }
-
/*
* Set up everything related to rte_flow:
* - netlink socket
@@ -2041,6 +2037,11 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, const char *tap_name,
pmd->name);
goto disable_rte_flow;
}
+ pmd->if_index = if_nametoindex(pmd->name);
+ if (!pmd->if_index) {
+ TAP_LOG(ERR, "%s: failed to get if_index.", pmd->name);
+ goto disable_rte_flow;
+ }
if (qdisc_create_multiq(pmd->nlsk_fd, pmd->if_index) < 0) {
TAP_LOG(ERR, "%s: failed to create multiq qdisc.",
pmd->name);
@@ -79,10 +79,8 @@ struct pmd_internals {
int ioctl_sock; /* socket for ioctl calls */
int nlsk_fd; /* Netlink socket fd */
int flow_isolate; /* 1 if flow isolation is enabled */
- int rss_enabled; /* 1 if RSS is enabled, else 0 */
- /* implicit rules set when RSS is enabled */
- int map_fd; /* BPF RSS map fd */
- int bpf_fd[RTE_PMD_TAP_MAX_QUEUES];/* List of bpf fds per queue */
+
+ struct tap_rss *rss; /* BPF program */
LIST_HEAD(tap_flows, rte_flow) flows; /* rte_flow rules */
/* implicit rte_flow rules set when a remote device is active */
@@ -15,25 +15,19 @@
#include <rte_random.h>
#include <rte_malloc.h>
#include <rte_eth_tap.h>
+#include <rte_uuid.h>
#include <tap_flow.h>
-#include <tap_autoconf.h>
#include <tap_tcmsgs.h>
#include <tap_rss.h>
-/* RSS key management */
-enum bpf_rss_key_e {
- KEY_CMD_GET = 1,
- KEY_CMD_RELEASE,
- KEY_CMD_INIT,
- KEY_CMD_DEINIT,
-};
-
-enum key_status_e {
- KEY_STAT_UNSPEC,
- KEY_STAT_USED,
- KEY_STAT_AVAILABLE,
-};
+#ifdef HAVE_BPF_RSS
+/* Workaround for warning in bpftool generated skeleton code */
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wcast-qual"
+#include "tap_rss.skel.h"
+#pragma GCC diagnostic pop
+#endif
#define ISOLATE_HANDLE 1
#define REMOTE_PROMISCUOUS_HANDLE 2
@@ -41,8 +35,6 @@ enum key_status_e {
struct rte_flow {
LIST_ENTRY(rte_flow) next; /* Pointer to the next rte_flow structure */
struct rte_flow *remote_flow; /* associated remote flow */
- int bpf_fd[SEC_MAX]; /* list of bfs fds per ELF section */
- uint32_t key_idx; /* RSS rule key index into BPF map */
struct nlmsg msg;
};
@@ -69,9 +61,11 @@ struct action_data {
struct skbedit {
struct tc_skbedit skbedit;
uint16_t queue;
+ uint32_t mark;
} skbedit;
struct bpf {
struct tc_act_bpf bpf;
+ uint32_t map_key;
int bpf_fd;
const char *annotation;
} bpf;
@@ -112,13 +106,12 @@ tap_flow_isolate(struct rte_eth_dev *dev,
int set,
struct rte_flow_error *error);
-static int bpf_rss_key(enum bpf_rss_key_e cmd, __u32 *key_idx);
-static int rss_enable(struct pmd_internals *pmd,
- const struct rte_flow_attr *attr,
- struct rte_flow_error *error);
+#ifdef HAVE_BPF_RSS
+static int rss_enable(struct pmd_internals *pmd, struct rte_flow_error *error);
static int rss_add_actions(struct rte_flow *flow, struct pmd_internals *pmd,
const struct rte_flow_action_rss *rss,
struct rte_flow_error *error);
+#endif
static const struct rte_flow_ops tap_flow_ops = {
.validate = tap_flow_validate,
@@ -853,10 +846,11 @@ add_action(struct rte_flow *flow, size_t *act_index, struct action_data *adata)
&adata->mirred);
} else if (strcmp("skbedit", adata->id) == 0) {
tap_nlattr_add(&msg->nh, TCA_SKBEDIT_PARMS,
- sizeof(adata->skbedit.skbedit),
- &adata->skbedit.skbedit);
- tap_nlattr_add16(&msg->nh, TCA_SKBEDIT_QUEUE_MAPPING,
- adata->skbedit.queue);
+ sizeof(adata->skbedit.skbedit), &adata->skbedit.skbedit);
+ if (adata->skbedit.mark)
+ tap_nlattr_add32(&msg->nh, TCA_SKBEDIT_MARK, adata->skbedit.mark);
+ else
+ tap_nlattr_add16(&msg->nh, TCA_SKBEDIT_QUEUE_MAPPING, adata->skbedit.queue);
} else if (strcmp("bpf", adata->id) == 0) {
tap_nlattr_add32(&msg->nh, TCA_ACT_BPF_FD, adata->bpf.bpf_fd);
tap_nlattr_add(&msg->nh, TCA_ACT_BPF_NAME,
@@ -1104,8 +1098,7 @@ priv_flow_process(struct pmd_internals *pmd,
},
};
- err = add_actions(flow, 1, &adata,
- TCA_FLOWER_ACT);
+ err = add_actions(flow, 1, &adata, TCA_FLOWER_ACT);
}
} else if (actions->type == RTE_FLOW_ACTION_TYPE_QUEUE) {
const struct rte_flow_action_queue *queue =
@@ -1135,6 +1128,7 @@ priv_flow_process(struct pmd_internals *pmd,
err = add_actions(flow, 1, &adata,
TCA_FLOWER_ACT);
}
+#ifdef HAVE_BPF_RSS
} else if (actions->type == RTE_FLOW_ACTION_TYPE_RSS) {
const struct rte_flow_action_rss *rss =
(const struct rte_flow_action_rss *)
@@ -1143,13 +1137,14 @@ priv_flow_process(struct pmd_internals *pmd,
if (action++)
goto exit_action_not_supported;
- if (!pmd->rss_enabled) {
- err = rss_enable(pmd, attr, error);
+ if (pmd->rss == NULL) {
+ err = rss_enable(pmd, error);
if (err)
goto exit_return_error;
}
if (flow)
err = rss_add_actions(flow, pmd, rss, error);
+#endif
} else {
goto exit_action_not_supported;
}
@@ -1246,26 +1241,17 @@ tap_flow_set_handle(struct rte_flow *flow)
*
*/
static void
-tap_flow_free(struct pmd_internals *pmd, struct rte_flow *flow)
+tap_flow_free(struct pmd_internals *pmd __rte_unused, struct rte_flow *flow)
{
- int i;
-
if (!flow)
return;
- if (pmd->rss_enabled) {
- /* Close flow BPF file descriptors */
- for (i = 0; i < SEC_MAX; i++)
- if (flow->bpf_fd[i] != 0) {
- close(flow->bpf_fd[i]);
- flow->bpf_fd[i] = 0;
- }
-
- /* Release the map key for this RSS rule */
- bpf_rss_key(KEY_CMD_RELEASE, &flow->key_idx);
- flow->key_idx = 0;
- }
-
+#ifdef HAVE_BPF_RSS
+ struct tap_rss *rss = pmd->rss;
+ if (rss)
+ bpf_map__delete_elem(rss->maps.rss_map,
+ &flow->msg.t.tcm_handle, sizeof(uint32_t), 0);
+#endif
/* Free flow allocated memory */
rte_free(flow);
}
@@ -1733,14 +1719,18 @@ tap_flow_implicit_flush(struct pmd_internals *pmd, struct rte_flow_error *error)
return 0;
}
-#define MAX_RSS_KEYS 256
-#define KEY_IDX_OFFSET (3 * MAX_RSS_KEYS)
-#define SEC_NAME_CLS_Q "cls_q"
-
-static const char *sec_name[SEC_MAX] = {
- [SEC_L3_L4] = "l3_l4",
-};
+/**
+ * Cleanup when device is closed
+ */
+void tap_flow_bpf_destroy(struct pmd_internals *pmd __rte_unused)
+{
+#ifdef HAVE_BPF_RSS
+ tap_rss__destroy(pmd->rss);
+ pmd->rss = NULL;
+#endif
+}
+#ifdef HAVE_BPF_RSS
/**
* Enable RSS on tap: create TC rules for queuing.
*
@@ -1755,225 +1745,32 @@ static const char *sec_name[SEC_MAX] = {
*
* @return 0 on success, negative value on failure.
*/
-static int rss_enable(struct pmd_internals *pmd,
- const struct rte_flow_attr *attr,
- struct rte_flow_error *error)
+static int rss_enable(struct pmd_internals *pmd, struct rte_flow_error *error)
{
- struct rte_flow *rss_flow = NULL;
- struct nlmsg *msg = NULL;
- /* 4096 is the maximum number of instructions for a BPF program */
- char annotation[64];
- int i;
- int err = 0;
-
- /* unlimit locked memory */
- struct rlimit memlock_limit = {
- .rlim_cur = RLIM_INFINITY,
- .rlim_max = RLIM_INFINITY,
- };
- setrlimit(RLIMIT_MEMLOCK, &memlock_limit);
-
- /* Get a new map key for a new RSS rule */
- err = bpf_rss_key(KEY_CMD_INIT, NULL);
- if (err < 0) {
- rte_flow_error_set(
- error, EINVAL, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
- "Failed to initialize BPF RSS keys");
-
- return -1;
- }
-
- /*
- * Create BPF RSS MAP
- */
- pmd->map_fd = tap_flow_bpf_rss_map_create(sizeof(__u32), /* key size */
- sizeof(struct rss_key),
- MAX_RSS_KEYS);
- if (pmd->map_fd < 0) {
- TAP_LOG(ERR,
- "Failed to create BPF map (%d): %s",
- errno, strerror(errno));
- rte_flow_error_set(
- error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
- "Kernel too old or not configured "
- "to support BPF maps");
-
- return -ENOTSUP;
- }
-
- /*
- * Add a rule per queue to match reclassified packets and direct them to
- * the correct queue.
- */
- for (i = 0; i < pmd->dev->data->nb_rx_queues; i++) {
- pmd->bpf_fd[i] = tap_flow_bpf_cls_q(i);
- if (pmd->bpf_fd[i] < 0) {
- TAP_LOG(ERR,
- "Failed to load BPF section %s for queue %d",
- SEC_NAME_CLS_Q, i);
- rte_flow_error_set(
- error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE,
- NULL,
- "Kernel too old or not configured "
- "to support BPF programs loading");
-
- return -ENOTSUP;
- }
-
- rss_flow = rte_zmalloc(__func__, sizeof(struct rte_flow), 0);
- if (!rss_flow) {
- TAP_LOG(ERR,
- "Cannot allocate memory for rte_flow");
- return -1;
- }
- msg = &rss_flow->msg;
- tc_init_msg(msg, pmd->if_index, RTM_NEWTFILTER, NLM_F_REQUEST |
- NLM_F_ACK | NLM_F_EXCL | NLM_F_CREATE);
- msg->t.tcm_info = TC_H_MAKE(0, htons(ETH_P_ALL));
- tap_flow_set_handle(rss_flow);
- uint16_t group = attr->group << GROUP_SHIFT;
- uint16_t prio = group | (i + PRIORITY_OFFSET);
- msg->t.tcm_info = TC_H_MAKE(prio << 16, msg->t.tcm_info);
- msg->t.tcm_parent = TC_H_MAKE(MULTIQ_MAJOR_HANDLE, 0);
-
- tap_nlattr_add(&msg->nh, TCA_KIND, sizeof("bpf"), "bpf");
- if (tap_nlattr_nested_start(msg, TCA_OPTIONS) < 0)
- return -1;
- tap_nlattr_add32(&msg->nh, TCA_BPF_FD, pmd->bpf_fd[i]);
- snprintf(annotation, sizeof(annotation), "[%s%d]",
- SEC_NAME_CLS_Q, i);
- tap_nlattr_add(&msg->nh, TCA_BPF_NAME, strlen(annotation) + 1,
- annotation);
- /* Actions */
- {
- struct action_data adata = {
- .id = "skbedit",
- .skbedit = {
- .skbedit = {
- .action = TC_ACT_PIPE,
- },
- .queue = i,
- },
- };
- if (add_actions(rss_flow, 1, &adata, TCA_BPF_ACT) < 0)
- return -1;
- }
- tap_nlattr_nested_finish(msg); /* nested TCA_OPTIONS */
+ int err;
- /* Netlink message is now ready to be sent */
- if (tap_nl_send(pmd->nlsk_fd, &msg->nh) < 0)
- return -1;
- err = tap_nl_recv_ack(pmd->nlsk_fd);
- if (err < 0) {
- TAP_LOG(ERR,
- "Kernel refused TC filter rule creation (%d): %s",
- errno, strerror(errno));
- return err;
- }
+ /* Load the BPF program (defined in tap_bpf.h from skeleton) */
+ pmd->rss = tap_rss__open_and_load();
+ if (pmd->rss == NULL) {
+ TAP_LOG(ERR, "Failed to load BPF object: %s", strerror(errno));
+ rte_flow_error_set(error, errno, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+ "BPF object could not be loaded");
+ return -errno;
}
- pmd->rss_enabled = 1;
- return err;
-}
-
-/**
- * Manage bpf RSS keys repository with operations: init, get, release
- *
- * @param[in] cmd
- * Command on RSS keys: init, get, release
- *
- * @param[in, out] key_idx
- * Pointer to RSS Key index (out for get command, in for release command)
- *
- * @return -1 if couldn't get, release or init the RSS keys, 0 otherwise.
- */
-static int bpf_rss_key(enum bpf_rss_key_e cmd, __u32 *key_idx)
-{
- __u32 i;
- int err = 0;
- static __u32 num_used_keys;
- static __u32 rss_keys[MAX_RSS_KEYS] = {KEY_STAT_UNSPEC};
- static __u32 rss_keys_initialized;
- __u32 key;
-
- switch (cmd) {
- case KEY_CMD_GET:
- if (!rss_keys_initialized) {
- err = -1;
- break;
- }
-
- if (num_used_keys == RTE_DIM(rss_keys)) {
- err = -1;
- break;
- }
-
- *key_idx = num_used_keys % RTE_DIM(rss_keys);
- while (rss_keys[*key_idx] == KEY_STAT_USED)
- *key_idx = (*key_idx + 1) % RTE_DIM(rss_keys);
-
- rss_keys[*key_idx] = KEY_STAT_USED;
-
- /*
- * Add an offset to key_idx in order to handle a case of
- * RSS and non RSS flows mixture.
- * If a non RSS flow is destroyed it has an eBPF map
- * index 0 (initialized on flow creation) and might
- * unintentionally remove RSS entry 0 from eBPF map.
- * To avoid this issue, add an offset to the real index
- * during a KEY_CMD_GET operation and subtract this offset
- * during a KEY_CMD_RELEASE operation in order to restore
- * the real index.
- */
- *key_idx += KEY_IDX_OFFSET;
- num_used_keys++;
- break;
-
- case KEY_CMD_RELEASE:
- if (!rss_keys_initialized)
- break;
-
- /*
- * Subtract offset to restore real key index
- * If a non RSS flow is falsely trying to release map
- * entry 0 - the offset subtraction will calculate the real
- * map index as an out-of-range value and the release operation
- * will be silently ignored.
- */
- key = *key_idx - KEY_IDX_OFFSET;
- if (key >= RTE_DIM(rss_keys))
- break;
-
- if (rss_keys[key] == KEY_STAT_USED) {
- rss_keys[key] = KEY_STAT_AVAILABLE;
- num_used_keys--;
- }
- break;
-
- case KEY_CMD_INIT:
- for (i = 0; i < RTE_DIM(rss_keys); i++)
- rss_keys[i] = KEY_STAT_AVAILABLE;
-
- rss_keys_initialized = 1;
- num_used_keys = 0;
- break;
-
- case KEY_CMD_DEINIT:
- for (i = 0; i < RTE_DIM(rss_keys); i++)
- rss_keys[i] = KEY_STAT_UNSPEC;
-
- rss_keys_initialized = 0;
- num_used_keys = 0;
- break;
-
- default:
- break;
+ /* Attach the maps defined in BPF program */
+ err = tap_rss__attach(pmd->rss);
+ if (err < 0) {
+ TAP_LOG(ERR, "Failed to attach BPF object: %d", err);
+ rte_flow_error_set(error, -err, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
+ "BPF object could not be attached");
+ tap_flow_bpf_destroy(pmd);
+ return err;
}
- return err;
+ return 0;
}
-
/* Default RSS hash key also used by mlx devices */
static const uint8_t rss_hash_default_key[] = {
0x2c, 0xc6, 0x81, 0xd1,
@@ -2006,9 +1803,11 @@ static int rss_add_actions(struct rte_flow *flow, struct pmd_internals *pmd,
const struct rte_flow_action_rss *rss,
struct rte_flow_error *error)
{
+ const struct bpf_program *rss_prog = pmd->rss->progs.rss_flow_action;
struct rss_key rss_entry = { };
const uint8_t *key_in;
uint32_t hash_type = 0;
+ uint32_t handle = flow->msg.t.tcm_handle;
unsigned int i;
int err;
@@ -2057,34 +1856,24 @@ static int rss_add_actions(struct rte_flow *flow, struct pmd_internals *pmd,
else if (rss->types & (RTE_ETH_RSS_IPV6 | RTE_ETH_RSS_FRAG_IPV6 | RTE_ETH_RSS_IPV6_EX))
hash_type |= RTE_BIT32(HASH_FIELD_IPV6_L3);
- /* Get a new map key for a new RSS rule */
- err = bpf_rss_key(KEY_CMD_GET, &flow->key_idx);
- if (err < 0) {
- rte_flow_error_set(
- error, EINVAL, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
- "Failed to get BPF RSS key");
-
- return -1;
- }
+ rss_entry.hash_fields = hash_type;
+ rte_convert_rss_key((const uint32_t *)key_in, (uint32_t *)rss_entry.key,
+ TAP_RSS_HASH_KEY_SIZE);
/* Update RSS map entry with queues */
rss_entry.nb_queues = rss->queue_num;
for (i = 0; i < rss->queue_num; i++)
rss_entry.queues[i] = rss->queue[i];
- rss_entry.hash_fields = hash_type;
- rte_convert_rss_key((const uint32_t *)key_in, (uint32_t *)rss_entry.key,
- TAP_RSS_HASH_KEY_SIZE);
-
-
- /* Add this RSS entry to map */
- err = tap_flow_bpf_update_rss_elem(pmd->map_fd,
- &flow->key_idx, &rss_entry);
+ /* Add this way for BPF to find entry in map */
+ err = bpf_map__update_elem(pmd->rss->maps.rss_map,
+ &handle, sizeof(handle),
+ &rss_entry, sizeof(rss_entry), 0);
if (err) {
TAP_LOG(ERR,
- "Failed to update BPF map entry #%u (%d): %s",
- flow->key_idx, errno, strerror(errno));
+ "Failed to update BPF map entry %#x (%d): %s",
+ handle, errno, strerror(errno));
rte_flow_error_set(
error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
"Kernel too old or not configured "
@@ -2093,47 +1882,28 @@ static int rss_add_actions(struct rte_flow *flow, struct pmd_internals *pmd,
return -ENOTSUP;
}
-
- /*
- * Load bpf rules to calculate hash for this key_idx
- */
-
- flow->bpf_fd[SEC_L3_L4] =
- tap_flow_bpf_calc_l3_l4_hash(flow->key_idx, pmd->map_fd);
- if (flow->bpf_fd[SEC_L3_L4] < 0) {
- TAP_LOG(ERR,
- "Failed to load BPF section %s (%d): %s",
- sec_name[SEC_L3_L4], errno, strerror(errno));
- rte_flow_error_set(
- error, ENOTSUP, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
- "Kernel too old or not configured "
- "to support BPF program loading");
-
- return -ENOTSUP;
- }
-
- /* Actions */
- {
- struct action_data adata[] = {
- {
- .id = "bpf",
- .bpf = {
- .bpf_fd = flow->bpf_fd[SEC_L3_L4],
- .annotation = sec_name[SEC_L3_L4],
- .bpf = {
- .action = TC_ACT_PIPE,
- },
- },
+ /* Add actions to mark packet then run the RSS BPF program */
+ struct action_data adata[] = {
+ {
+ .id = "skbedit",
+ .skbedit = {
+ .skbedit.action = TC_ACT_PIPE,
+ .mark = handle,
},
- };
-
- if (add_actions(flow, RTE_DIM(adata), adata,
- TCA_FLOWER_ACT) < 0)
- return -1;
- }
+ },
+ {
+ .id = "bpf",
+ .bpf = {
+ .bpf.action = TC_ACT_PIPE,
+ .annotation = "tap_rss",
+ .bpf_fd = bpf_program__fd(rss_prog),
+ },
+ },
+ };
- return 0;
+ return add_actions(flow, RTE_DIM(adata), adata, TCA_FLOWER_ACT);
}
+#endif
/**
* Get rte_flow operations.
@@ -9,7 +9,11 @@
#include <rte_flow.h>
#include <rte_flow_driver.h>
#include <rte_eth_tap.h>
-#include <tap_autoconf.h>
+
+/**
+ * Mask of unsupported RSS types
+ */
+#define TAP_RSS_HF_MASK (~(RTE_ETH_RSS_IP | RTE_ETH_RSS_UDP | RTE_ETH_RSS_TCP))
/**
* In TC, priority 0 means we require the kernel to allocate one for us.
@@ -41,11 +45,6 @@ enum implicit_rule_index {
TAP_REMOTE_MAX_IDX,
};
-enum bpf_fd_idx {
- SEC_L3_L4,
- SEC_MAX,
-};
-
int tap_dev_flow_ops_get(struct rte_eth_dev *dev,
const struct rte_flow_ops **ops);
int tap_flow_flush(struct rte_eth_dev *dev, struct rte_flow_error *error);
@@ -57,10 +56,6 @@ int tap_flow_implicit_destroy(struct pmd_internals *pmd,
int tap_flow_implicit_flush(struct pmd_internals *pmd,
struct rte_flow_error *error);
-int tap_flow_bpf_cls_q(__u32 queue_idx);
-int tap_flow_bpf_calc_l3_l4_hash(__u32 key_idx, int map_fd);
-int tap_flow_bpf_rss_map_create(unsigned int key_size, unsigned int value_size,
- unsigned int max_entries);
-int tap_flow_bpf_update_rss_elem(int fd, void *key, void *value);
+void tap_flow_bpf_destroy(struct pmd_internals *pmd);
#endif /* _TAP_FLOW_H_ */
@@ -5,16 +5,14 @@
#ifndef _TAP_RSS_H_
#define _TAP_RSS_H_
-#ifndef TAP_MAX_QUEUES
-#define TAP_MAX_QUEUES 16
+/* Size of the map from BPF classid to queue table */
+#ifndef TAP_RSS_MAX
+#define TAP_RSS_MAX 32
#endif
-/* Fixed RSS hash key size in bytes. */
+/* Standard Toeplitz hash key size */
#define TAP_RSS_HASH_KEY_SIZE 40
-/* Supported RSS */
-#define TAP_RSS_HF_MASK (~(RTE_ETH_RSS_IP | RTE_ETH_RSS_UDP | RTE_ETH_RSS_TCP))
-
/* hashed fields for RSS */
enum hash_field {
HASH_FIELD_IPV4_L3, /* IPv4 src/dst addr */
@@ -6,7 +6,6 @@
#ifndef _TAP_TCMSGS_H_
#define _TAP_TCMSGS_H_
-#include <tap_autoconf.h>
#include <linux/if_ether.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_sched.h>
@@ -14,9 +13,8 @@
#include <linux/tc_act/tc_mirred.h>
#include <linux/tc_act/tc_gact.h>
#include <linux/tc_act/tc_skbedit.h>
-#ifdef HAVE_TC_ACT_BPF
#include <linux/tc_act/tc_bpf.h>
-#endif
+
#include <inttypes.h>
#include <rte_ether.h>