#include <rte_errno.h>
#include <rte_lcore.h>
#include <rte_log.h>
+#include <rte_tailq.h>
#include "eal_private.h"
#include "eal_filesystem.h"
struct rte_mp_msg msg;
};
+struct async_request_param {
+ rte_mp_async_reply_t clb;
+ struct rte_mp_reply user_reply;
+ struct timespec end;
+ int n_responses_processed;
+};
+
struct pending_request {
TAILQ_ENTRY(pending_request) next;
- int reply_received;
+ enum {
+ REQUEST_TYPE_SYNC,
+ REQUEST_TYPE_ASYNC
+ } type;
char dst[PATH_MAX];
struct rte_mp_msg *request;
struct rte_mp_msg *reply;
- pthread_cond_t cond;
+ int reply_received;
+ RTE_STD_C11
+ union {
+ struct {
+ struct async_request_param *param;
+ } async;
+ struct {
+ pthread_cond_t cond;
+ } sync;
+ };
};
TAILQ_HEAD(pending_request_list, pending_request);
static struct {
struct pending_request_list requests;
pthread_mutex_t lock;
+ pthread_cond_t async_cond;
} pending_requests = {
.requests = TAILQ_HEAD_INITIALIZER(pending_requests.requests),
- .lock = PTHREAD_MUTEX_INITIALIZER
+ .lock = PTHREAD_MUTEX_INITIALIZER,
+ .async_cond = PTHREAD_COND_INITIALIZER
+ /**< used in async requests only */
};
/* forward declarations */
memcpy(sync_req->reply, msg, sizeof(*msg));
/* -1 indicates that we've been asked to ignore */
sync_req->reply_received = m->type == MP_REP ? 1 : -1;
- pthread_cond_signal(&sync_req->cond);
+
+ if (sync_req->type == REQUEST_TYPE_SYNC)
+ pthread_cond_signal(&sync_req->sync.cond);
+ else if (sync_req->type == REQUEST_TYPE_ASYNC)
+ pthread_cond_signal(
+ &pending_requests.async_cond);
} else
RTE_LOG(ERR, EAL, "Drop mp reply: %s\n", msg->name);
pthread_mutex_unlock(&pending_requests.lock);
return NULL;
}
+static int
+timespec_cmp(const struct timespec *a, const struct timespec *b)
+{
+ if (a->tv_sec < b->tv_sec)
+ return -1;
+ if (a->tv_sec > b->tv_sec)
+ return 1;
+ if (a->tv_nsec < b->tv_nsec)
+ return -1;
+ if (a->tv_nsec > b->tv_nsec)
+ return 1;
+ return 0;
+}
+
+enum async_action {
+ ACTION_NONE, /**< don't do anything */
+ ACTION_FREE, /**< free the action entry, but don't trigger callback */
+ ACTION_TRIGGER /**< trigger callback, then free action entry */
+};
+
+static enum async_action
+process_async_request(struct pending_request *sr, const struct timespec *now)
+{
+ struct async_request_param *param;
+ struct rte_mp_reply *reply;
+ bool timeout, received, last_msg;
+
+ param = sr->async.param;
+ reply = ¶m->user_reply;
+
+ /* did we timeout? */
+ timeout = timespec_cmp(¶m->end, now) <= 0;
+
+ /* did we receive a response? */
+ received = sr->reply_received != 0;
+
+ /* if we didn't time out, and we didn't receive a response, ignore */
+ if (!timeout && !received)
+ return ACTION_NONE;
+
+ /* if we received a response, adjust relevant data and copy mesasge. */
+ if (sr->reply_received == 1 && sr->reply) {
+ struct rte_mp_msg *msg, *user_msgs, *tmp;
+
+ msg = sr->reply;
+ user_msgs = reply->msgs;
+
+ tmp = realloc(user_msgs, sizeof(*msg) *
+ (reply->nb_received + 1));
+ if (!tmp) {
+ RTE_LOG(ERR, EAL, "Fail to alloc reply for request %s:%s\n",
+ sr->dst, sr->request->name);
+ /* this entry is going to be removed and its message
+ * dropped, but we don't want to leak memory, so
+ * continue.
+ */
+ } else {
+ user_msgs = tmp;
+ reply->msgs = user_msgs;
+ memcpy(&user_msgs[reply->nb_received],
+ msg, sizeof(*msg));
+ reply->nb_received++;
+ }
+
+ /* mark this request as processed */
+ param->n_responses_processed++;
+ } else if (sr->reply_received == -1) {
+ /* we were asked to ignore this process */
+ reply->nb_sent--;
+ }
+ free(sr->reply);
+
+ last_msg = param->n_responses_processed == reply->nb_sent;
+
+ return last_msg ? ACTION_TRIGGER : ACTION_FREE;
+}
+
+static void
+trigger_async_action(struct pending_request *sr)
+{
+ struct async_request_param *param;
+ struct rte_mp_reply *reply;
+
+ param = sr->async.param;
+ reply = ¶m->user_reply;
+
+ param->clb(sr->request, reply);
+
+ /* clean up */
+ free(sr->async.param->user_reply.msgs);
+ free(sr->async.param);
+ free(sr->request);
+}
+
+static void *
+async_reply_handle(void *arg __rte_unused)
+{
+ struct pending_request *sr;
+ struct timeval now;
+ struct timespec timeout, ts_now;
+ while (1) {
+ struct pending_request *trigger = NULL;
+ int ret;
+ bool nowait = false;
+ bool timedwait = false;
+
+ pthread_mutex_lock(&pending_requests.lock);
+
+ /* scan through the list and see if there are any timeouts that
+ * are earlier than our current timeout.
+ */
+ TAILQ_FOREACH(sr, &pending_requests.requests, next) {
+ if (sr->type != REQUEST_TYPE_ASYNC)
+ continue;
+ if (!timedwait || timespec_cmp(&sr->async.param->end,
+ &timeout) < 0) {
+ memcpy(&timeout, &sr->async.param->end,
+ sizeof(timeout));
+ timedwait = true;
+ }
+
+ /* sometimes, we don't even wait */
+ if (sr->reply_received) {
+ nowait = true;
+ break;
+ }
+ }
+
+ if (nowait)
+ ret = 0;
+ else if (timedwait)
+ ret = pthread_cond_timedwait(
+ &pending_requests.async_cond,
+ &pending_requests.lock, &timeout);
+ else
+ ret = pthread_cond_wait(&pending_requests.async_cond,
+ &pending_requests.lock);
+
+ if (gettimeofday(&now, NULL) < 0) {
+ RTE_LOG(ERR, EAL, "Cannot get current time\n");
+ break;
+ }
+ ts_now.tv_nsec = now.tv_usec * 1000;
+ ts_now.tv_sec = now.tv_sec;
+
+ if (ret == 0 || ret == ETIMEDOUT) {
+ struct pending_request *next;
+ /* we've either been woken up, or we timed out */
+
+ /* we have still the lock, check if anything needs
+ * processing.
+ */
+ TAILQ_FOREACH_SAFE(sr, &pending_requests.requests, next,
+ next) {
+ enum async_action action;
+ if (sr->type != REQUEST_TYPE_ASYNC)
+ continue;
+
+ action = process_async_request(sr, &ts_now);
+ if (action == ACTION_FREE) {
+ TAILQ_REMOVE(&pending_requests.requests,
+ sr, next);
+ free(sr);
+ } else if (action == ACTION_TRIGGER &&
+ trigger == NULL) {
+ TAILQ_REMOVE(&pending_requests.requests,
+ sr, next);
+ trigger = sr;
+ }
+ }
+ }
+ pthread_mutex_unlock(&pending_requests.lock);
+ if (trigger) {
+ trigger_async_action(trigger);
+ free(trigger);
+ }
+ };
+
+ RTE_LOG(ERR, EAL, "ERROR: asynchronous requests disabled\n");
+
+ return NULL;
+}
+
static int
open_socket_fd(void)
{
char thread_name[RTE_MAX_THREAD_NAME_LEN];
char path[PATH_MAX];
int dir_fd;
- pthread_t tid;
+ pthread_t mp_handle_tid, async_reply_handle_tid;
/* create filter path */
create_socket_path("*", path, sizeof(path));
return -1;
}
- if (pthread_create(&tid, NULL, mp_handle, NULL) < 0) {
+ if (pthread_create(&mp_handle_tid, NULL, mp_handle, NULL) < 0) {
+ RTE_LOG(ERR, EAL, "failed to create mp thead: %s\n",
+ strerror(errno));
+ close(mp_fd);
+ mp_fd = -1;
+ return -1;
+ }
+
+ if (pthread_create(&async_reply_handle_tid, NULL,
+ async_reply_handle, NULL) < 0) {
RTE_LOG(ERR, EAL, "failed to create mp thead: %s\n",
strerror(errno));
close(mp_fd);
/* try best to set thread name */
snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "rte_mp_handle");
- rte_thread_setname(tid, thread_name);
+ rte_thread_setname(mp_handle_tid, thread_name);
+
+ /* try best to set thread name */
+ snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "rte_mp_async_handle");
+ rte_thread_setname(async_reply_handle_tid, thread_name);
/* unlock the directory */
flock(dir_fd, LOCK_UN);
}
static int
-mp_request_one(const char *dst, struct rte_mp_msg *req,
+mp_request_async(const char *dst, struct rte_mp_msg *req,
+ struct async_request_param *param)
+{
+ struct rte_mp_msg *reply_msg;
+ struct pending_request *sync_req, *exist;
+ int ret;
+
+ sync_req = malloc(sizeof(*sync_req));
+ reply_msg = malloc(sizeof(*reply_msg));
+ if (sync_req == NULL || reply_msg == NULL) {
+ RTE_LOG(ERR, EAL, "Could not allocate space for sync request\n");
+ rte_errno = ENOMEM;
+ ret = -1;
+ goto fail;
+ }
+
+ memset(sync_req, 0, sizeof(*sync_req));
+ memset(reply_msg, 0, sizeof(*reply_msg));
+
+ sync_req->type = REQUEST_TYPE_ASYNC;
+ strcpy(sync_req->dst, dst);
+ sync_req->request = req;
+ sync_req->reply = reply_msg;
+ sync_req->async.param = param;
+
+ /* queue already locked by caller */
+
+ exist = find_sync_request(dst, req->name);
+ if (!exist) {
+ TAILQ_INSERT_TAIL(&pending_requests.requests, sync_req, next);
+ } else {
+ RTE_LOG(ERR, EAL, "A pending request %s:%s\n", dst, req->name);
+ rte_errno = EEXIST;
+ ret = -1;
+ goto fail;
+ }
+
+ ret = send_msg(dst, req, MP_REQ);
+ if (ret < 0) {
+ RTE_LOG(ERR, EAL, "Fail to send request %s:%s\n",
+ dst, req->name);
+ ret = -1;
+ goto fail;
+ } else if (ret == 0) {
+ ret = 0;
+ goto fail;
+ }
+
+ param->user_reply.nb_sent++;
+
+ return 0;
+fail:
+ free(sync_req);
+ free(reply_msg);
+ return ret;
+}
+
+static int
+mp_request_sync(const char *dst, struct rte_mp_msg *req,
struct rte_mp_reply *reply, const struct timespec *ts)
{
int ret;
struct rte_mp_msg msg, *tmp;
struct pending_request sync_req, *exist;
+ sync_req.type = REQUEST_TYPE_SYNC;
sync_req.reply_received = 0;
strcpy(sync_req.dst, dst);
sync_req.request = req;
sync_req.reply = &msg;
- pthread_cond_init(&sync_req.cond, NULL);
+ pthread_cond_init(&sync_req.sync.cond, NULL);
pthread_mutex_lock(&pending_requests.lock);
exist = find_sync_request(dst, req->name);
reply->nb_sent++;
do {
- ret = pthread_cond_timedwait(&sync_req.cond,
+ ret = pthread_cond_timedwait(&sync_req.sync.cond,
&pending_requests.lock, ts);
} while (ret != 0 && ret != ETIMEDOUT);
/* for secondary process, send request to the primary process only */
if (rte_eal_process_type() == RTE_PROC_SECONDARY)
- return mp_request_one(eal_mp_socket_path(), req, reply, &end);
+ return mp_request_sync(eal_mp_socket_path(), req, reply, &end);
/* for primary process, broadcast request, and collect reply 1 by 1 */
mp_dir = opendir(mp_dir_path);
snprintf(path, sizeof(path), "%s/%s", mp_dir_path,
ent->d_name);
- if (mp_request_one(path, req, reply, &end))
+ if (mp_request_sync(path, req, reply, &end))
ret = -1;
}
/* unlock the directory */
}
int __rte_experimental
-rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
+rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
+ rte_mp_async_reply_t clb)
{
+ struct rte_mp_msg *copy;
+ struct pending_request *dummy;
+ struct async_request_param *param;
+ struct rte_mp_reply *reply;
+ int dir_fd, ret = 0;
+ DIR *mp_dir;
+ struct dirent *ent;
+ struct timeval now;
+ struct timespec *end;
+ bool dummy_used = false;
+
+ RTE_LOG(DEBUG, EAL, "request: %s\n", req->name);
+
+ if (check_input(req) == false)
+ return -1;
+ if (gettimeofday(&now, NULL) < 0) {
+ RTE_LOG(ERR, EAL, "Faile to get current time\n");
+ rte_errno = errno;
+ return -1;
+ }
+ copy = malloc(sizeof(*copy));
+ dummy = malloc(sizeof(*dummy));
+ param = malloc(sizeof(*param));
+ if (copy == NULL || dummy == NULL || param == NULL) {
+ RTE_LOG(ERR, EAL, "Failed to allocate memory for async reply\n");
+ rte_errno = ENOMEM;
+ goto fail;
+ }
+
+ memset(copy, 0, sizeof(*copy));
+ memset(dummy, 0, sizeof(*dummy));
+ memset(param, 0, sizeof(*param));
+
+ /* copy message */
+ memcpy(copy, req, sizeof(*copy));
+
+ param->n_responses_processed = 0;
+ param->clb = clb;
+ end = ¶m->end;
+ reply = ¶m->user_reply;
+
+ end->tv_nsec = (now.tv_usec * 1000 + ts->tv_nsec) % 1000000000;
+ end->tv_sec = now.tv_sec + ts->tv_sec +
+ (now.tv_usec * 1000 + ts->tv_nsec) / 1000000000;
+ reply->nb_sent = 0;
+ reply->nb_received = 0;
+ reply->msgs = NULL;
+
+ /* we have to lock the request queue here, as we will be adding a bunch
+ * of requests to the queue at once, and some of the replies may arrive
+ * before we add all of the requests to the queue.
+ */
+ pthread_mutex_lock(&pending_requests.lock);
+ /* we have to ensure that callback gets triggered even if we don't send
+ * anything, therefore earlier we have allocated a dummy request. fill
+ * it, and put it on the queue if we don't send any requests.
+ */
+ dummy->type = REQUEST_TYPE_ASYNC;
+ dummy->request = copy;
+ dummy->reply = NULL;
+ dummy->async.param = param;
+ dummy->reply_received = 1; /* short-circuit the timeout */
+
+ /* for secondary process, send request to the primary process only */
+ if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ ret = mp_request_async(eal_mp_socket_path(), copy, param);
+
+ /* if we didn't send anything, put dummy request on the queue */
+ if (ret == 0 && reply->nb_sent == 0) {
+ TAILQ_INSERT_TAIL(&pending_requests.requests, dummy,
+ next);
+ dummy_used = true;
+ }
+
+ pthread_mutex_unlock(&pending_requests.lock);
+
+ /* if we couldn't send anything, clean up */
+ if (ret != 0)
+ goto fail;
+ return 0;
+ }
+
+ /* for primary process, broadcast request */
+ mp_dir = opendir(mp_dir_path);
+ if (!mp_dir) {
+ RTE_LOG(ERR, EAL, "Unable to open directory %s\n", mp_dir_path);
+ rte_errno = errno;
+ goto unlock_fail;
+ }
+ dir_fd = dirfd(mp_dir);
+
+ /* lock the directory to prevent processes spinning up while we send */
+ if (flock(dir_fd, LOCK_EX)) {
+ RTE_LOG(ERR, EAL, "Unable to lock directory %s\n",
+ mp_dir_path);
+ rte_errno = errno;
+ goto closedir_fail;
+ }
+
+ while ((ent = readdir(mp_dir))) {
+ char path[PATH_MAX];
+
+ if (fnmatch(mp_filter, ent->d_name, 0) != 0)
+ continue;
+
+ snprintf(path, sizeof(path), "%s/%s", mp_dir_path,
+ ent->d_name);
+
+ if (mp_request_async(path, copy, param))
+ ret = -1;
+ }
+ /* if we didn't send anything, put dummy request on the queue */
+ if (ret == 0 && reply->nb_sent == 0) {
+ TAILQ_INSERT_HEAD(&pending_requests.requests, dummy, next);
+ dummy_used = true;
+ }
+
+ /* trigger async request thread wake up */
+ pthread_cond_signal(&pending_requests.async_cond);
+
+ /* finally, unlock the queue */
+ pthread_mutex_unlock(&pending_requests.lock);
+
+ /* unlock the directory */
+ flock(dir_fd, LOCK_UN);
+
+ /* dir_fd automatically closed on closedir */
+ closedir(mp_dir);
+
+ /* if dummy was unused, free it */
+ if (!dummy_used)
+ free(dummy);
+
+ return ret;
+closedir_fail:
+ closedir(mp_dir);
+unlock_fail:
+ pthread_mutex_unlock(&pending_requests.lock);
+fail:
+ free(dummy);
+ free(param);
+ free(copy);
+ return -1;
+}
+
+int __rte_experimental
+rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
+{
RTE_LOG(DEBUG, EAL, "reply: %s\n", msg->name);
if (check_input(msg) == false)