[PATCH] eal: factorize lcore main loop

[PATCH] eal: factorize lcore main loop

[David Marchand]

All OS implementations provide the same main loop.
Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
between main and threads and factorize the rest as common code.
Thread id are now logged as string in a common format across OS.

Signed-off-by: David Marchand <david.marchand@redhat.com>
---
I had this patch in store for a long time.
I don't particularly care about it, it's not fixing anything.
But it seems a good cleanup/consolidation, so I rebased it and I am
sending it to get feedback.

---
 lib/eal/common/eal_common_launch.c |  36 +++++++-
 lib/eal/common/eal_common_thread.c |  72 +++++++++++++++
 lib/eal/common/eal_thread.h        |  27 ++++++
 lib/eal/freebsd/eal.c              |   7 +-
 lib/eal/freebsd/eal_thread.c       | 138 ----------------------------
 lib/eal/linux/eal.c                |   4 +-
 lib/eal/linux/eal_thread.c         | 139 +----------------------------
 lib/eal/unix/eal_unix_thread.c     |  63 +++++++++++++
 lib/eal/unix/meson.build           |   5 +-
 lib/eal/windows/eal_thread.c       | 137 +++++++---------------------
 10 files changed, 236 insertions(+), 392 deletions(-)
 create mode 100644 lib/eal/unix/eal_unix_thread.c

diff --git a/lib/eal/common/eal_common_launch.c b/lib/eal/common/eal_common_launch.c
index 9f393b9bda..5770803172 100644
--- a/lib/eal/common/eal_common_launch.c
+++ b/lib/eal/common/eal_common_launch.c
@@ -5,11 +5,13 @@
 #include <errno.h>
 
 #include <rte_launch.h>
+#include <rte_eal_trace.h>
 #include <rte_atomic.h>
 #include <rte_pause.h>
 #include <rte_lcore.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 
 /*
  * Wait until a lcore finished its job.
@@ -18,12 +20,44 @@ int
 rte_eal_wait_lcore(unsigned worker_id)
 {
 	while (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
+			__ATOMIC_ACQUIRE) != WAIT)
 		rte_pause();
 
 	return lcore_config[worker_id].ret;
 }
 
+/*
+ * Send a message to a worker lcore identified by worker_id to call a
+ * function f with argument arg. Once the execution is done, the
+ * remote lcore switches to WAIT state.
+ */
+int
+rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
+{
+	int rc = -EBUSY;
+
+	/* Check if the worker is in 'WAIT' state. Use acquire order
+	 * since 'state' variable is used as the guard variable.
+	 */
+	if (__atomic_load_n(&lcore_config[worker_id].state,
+			__ATOMIC_ACQUIRE) != WAIT)
+		goto finish;
+
+	lcore_config[worker_id].arg = arg;
+	/* Ensure that all the memory operations are completed
+	 * before the worker thread starts running the function.
+	 * Use worker thread function as the guard variable.
+	 */
+	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
+
+	eal_thread_wake_worker(worker_id);
+	rc = 0;
+
+finish:
+	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
+	return rc;
+}
+
 /*
  * Check that every WORKER lcores are in WAIT state, then call
  * rte_eal_remote_launch() for all of them. If call_main is true
diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
index 684bea166c..256de91abc 100644
--- a/lib/eal/common/eal_common_thread.c
+++ b/lib/eal/common/eal_common_thread.c
@@ -9,6 +9,7 @@
 #include <assert.h>
 #include <string.h>
 
+#include <rte_eal_trace.h>
 #include <rte_errno.h>
 #include <rte_lcore.h>
 #include <rte_log.h>
@@ -163,6 +164,77 @@ __rte_thread_uninit(void)
 	RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
 }
 
+/* main loop of threads */
+__rte_noreturn void *
+eal_thread_loop(__rte_unused void *arg)
+{
+	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	pthread_t thread_id = pthread_self();
+	unsigned int lcore_id;
+	int ret;
+
+	/* retrieve our lcore_id from the configuration structure */
+	RTE_LCORE_FOREACH_WORKER(lcore_id) {
+		if (thread_id == lcore_config[lcore_id].thread_id)
+			break;
+	}
+	if (lcore_id == RTE_MAX_LCORE)
+		rte_panic("cannot retrieve lcore id\n");
+
+	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
+
+	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
+	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		lcore_id, (uintptr_t)thread_id, cpuset,
+		ret == 0 ? "" : "...");
+
+	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
+
+	/* read on our pipe to get commands */
+	while (1) {
+		lcore_function_t *f;
+		void *fct_arg;
+
+		eal_thread_wait_command();
+
+		/* Set the state to 'RUNNING'. Use release order
+		 * since 'state' variable is used as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
+			__ATOMIC_RELEASE);
+
+		eal_thread_ack_command();
+
+		/* Load 'f' with acquire order to ensure that
+		 * the memory operations from the main thread
+		 * are accessed only after update to 'f' is visible.
+		 * Wait till the update to 'f' is visible to the worker.
+		 */
+		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
+				__ATOMIC_ACQUIRE)) == NULL)
+			rte_pause();
+
+		/* call the function and store the return value */
+		fct_arg = lcore_config[lcore_id].arg;
+		ret = f(fct_arg);
+		lcore_config[lcore_id].ret = ret;
+		lcore_config[lcore_id].f = NULL;
+		lcore_config[lcore_id].arg = NULL;
+
+		/* Store the state with release order to ensure that
+		 * the memory operations from the worker thread
+		 * are completed before the state is updated.
+		 * Use 'state' as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
+			__ATOMIC_RELEASE);
+	}
+
+	/* never reached */
+	/* pthread_exit(NULL); */
+	/* return NULL; */
+}
+
 enum __rte_ctrl_thread_status {
 	CTRL_THREAD_LAUNCHING, /* Yet to call pthread_create function */
 	CTRL_THREAD_RUNNING, /* Control thread is running successfully */
diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index 4a49117be8..b08dcf34b5 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -58,4 +58,31 @@ eal_thread_dump_affinity(rte_cpuset_t *cpuset, char *str, unsigned int size);
 int
 eal_thread_dump_current_affinity(char *str, unsigned int size);
 
+/**
+ * Called by the main thread to wake up a worker in 'WAIT' state.
+ * This function blocks until the worker acknowledge it started processing a
+ * new command.
+ * This function is private to EAL.
+ *
+ * @param worker_id
+ *   The lcore_id of a worker thread.
+ */
+void
+eal_thread_wake_worker(unsigned int worker_id);
+
+/**
+ * Called by a worker thread to sleep after entering 'WAIT' state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_wait_command(void);
+
+/**
+ * Called by a worker thread to acknowledge new command after leaving 'WAIT'
+ * state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_ack_command(void);
+
 #endif /* EAL_THREAD_H */
diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index 71993fe25b..80bc3d25e0 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -579,7 +579,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
@@ -604,8 +603,6 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-	thread_id = pthread_self();
-
 	eal_reset_internal_config(internal_conf);
 
 	/* clone argv to report out later in telemetry */
@@ -794,8 +791,8 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 
-	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		config->main_lcore, thread_id, cpuset,
+	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/freebsd/eal_thread.c b/lib/eal/freebsd/eal_thread.c
index 3b18030d73..ab81b527bc 100644
--- a/lib/eal/freebsd/eal_thread.c
+++ b/lib/eal/freebsd/eal_thread.c
@@ -20,148 +20,10 @@
 #include <rte_per_lcore.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
-{
-	char c;
-	int n, ret;
-	unsigned lcore_id;
-	pthread_t thread_id;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		lcore_id, thread_id, cpuset, ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 025e5cc10d..8a405d1d59 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -862,7 +862,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	const char *p;
@@ -890,7 +889,6 @@ rte_eal_init(int argc, char **argv)
 
 	p = strrchr(argv[0], '/');
 	strlcpy(logid, p ? p + 1 : argv[0], sizeof(logid));
-	thread_id = pthread_self();
 
 	eal_reset_internal_config(internal_conf);
 
@@ -1129,7 +1127,7 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		config->main_lcore, (uintptr_t)thread_id, cpuset,
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/linux/eal_thread.c b/lib/eal/linux/eal_thread.c
index fa6cd7e2c4..820cc905e0 100644
--- a/lib/eal/linux/eal_thread.c
+++ b/lib/eal/linux/eal_thread.c
@@ -14,148 +14,11 @@
 #include <rte_log.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
+#include <rte_string_fns.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function pointer as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
-{
-	char c;
-	int n, ret;
-	unsigned lcore_id;
-	pthread_t thread_id;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset, ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/unix/eal_unix_thread.c b/lib/eal/unix/eal_unix_thread.c
new file mode 100644
index 0000000000..70b5ba6b98
--- /dev/null
+++ b/lib/eal/unix/eal_unix_thread.c
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Red Hat, Inc.
+ */
+
+#include <errno.h>
+#include <unistd.h>
+
+#include <rte_debug.h>
+
+#include "eal_private.h"
+
+void
+eal_thread_wake_worker(unsigned int worker_id)
+{
+	int m2w = lcore_config[worker_id].pipe_main2worker[1];
+	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
+
+	do {
+		n = write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+
+	do {
+		n = read(w2m, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_wait_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
+	char c;
+	int n;
+
+	m2w = lcore_config[lcore_id].pipe_main2worker[0];
+	do {
+		n = read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
+
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+}
diff --git a/lib/eal/unix/meson.build b/lib/eal/unix/meson.build
index a22ea7cabc..781505ca90 100644
--- a/lib/eal/unix/meson.build
+++ b/lib/eal/unix/meson.build
@@ -3,9 +3,10 @@
 
 sources += files(
         'eal_file.c',
+        'eal_filesystem.c',
+        'eal_firmware.c',
         'eal_unix_memory.c',
+        'eal_unix_thread.c',
         'eal_unix_timer.c',
-        'eal_firmware.c',
-        'eal_filesystem.c',
         'rte_thread.c',
 )
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index 54fa93fa62..de1c0078a5 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -11,135 +11,62 @@
 #include <rte_per_lcore.h>
 #include <rte_common.h>
 #include <rte_memory.h>
-#include <eal_thread.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 #include "eal_windows.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
+void
+eal_thread_wake_worker(unsigned int worker_id)
 {
-	int n;
-	char c = 0;
 	int m2w = lcore_config[worker_id].pipe_main2worker[1];
 	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
 
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		return -EBUSY;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
+	do {
 		n = _write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
 	if (n < 0)
 		rte_panic("cannot write on configuration pipe\n");
 
-	/* wait ack */
 	do {
 		n = _read(w2m, &c, 1);
 	} while (n < 0 && errno == EINTR);
-
 	if (n <= 0)
 		rte_panic("cannot read on configuration pipe\n");
-
-	return 0;
 }
 
-/* main loop of threads */
-void *
-eal_thread_loop(void *arg __rte_unused)
+void
+eal_thread_wait_command(void)
 {
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
 	char c;
-	int n, ret;
-	unsigned int lcore_id;
-	pthread_t thread_id;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
+	int n;
 
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
 
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = _read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = _write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
 }
 
 /* function to create threads */
-- 
2.23.0

RE: [PATCH] eal: factorize lcore main loop

[Morten Brørup]

> From: David Marchand [mailto:david.marchand@redhat.com]
> Sent: Wednesday, 23 March 2022 10.30
> 
> All OS implementations provide the same main loop.
> Introduce helpers (shared for Linux and FreeBSD) to handle
> synchronisation
> between main and threads and factorize the rest as common code.
> Thread id are now logged as string in a common format across OS.
> 
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> ---
> I had this patch in store for a long time.
> I don't particularly care about it, it's not fixing anything.
> But it seems a good cleanup/consolidation, so I rebased it and I am
> sending it to get feedback.
> 

LGTM. I'm always in favor of cleaning up! :-)

Thank you, David.

Acked-By: Morten Brørup <mb@smartsharesystems.com>

Re: [PATCH] eal: factorize lcore main loop

[Tyler Retzlaff]

On Wed, Mar 23, 2022 at 10:30:01AM +0100, David Marchand wrote:
> All OS implementations provide the same main loop.
> Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
> between main and threads and factorize the rest as common code.
> Thread id are now logged as string in a common format across OS.
> 
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> ---
> I had this patch in store for a long time.
> I don't particularly care about it, it's not fixing anything.
> But it seems a good cleanup/consolidation, so I rebased it and I am
> sending it to get feedback.
> 

... snip ...

> diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
> index 684bea166c..256de91abc 100644
> --- a/lib/eal/common/eal_common_thread.c
> +++ b/lib/eal/common/eal_common_thread.c
> @@ -9,6 +9,7 @@
>  #include <assert.h>
>  #include <string.h>
>  
> +#include <rte_eal_trace.h>
>  #include <rte_errno.h>
>  #include <rte_lcore.h>
>  #include <rte_log.h>
> @@ -163,6 +164,77 @@ __rte_thread_uninit(void)
>  	RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
>  }
>  
> +/* main loop of threads */
> +__rte_noreturn void *
> +eal_thread_loop(__rte_unused void *arg)
> +{
> +	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> +	pthread_t thread_id = pthread_self();
> +	unsigned int lcore_id;
> +	int ret;
> +
> +	/* retrieve our lcore_id from the configuration structure */
> +	RTE_LCORE_FOREACH_WORKER(lcore_id) {
> +		if (thread_id == lcore_config[lcore_id].thread_id)
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

i can see that in practice this isn't a problem since the linux
implementation of pthread_create(3) stores to pthread_t *thread before
executing start_routine.

but strictly speaking i don't think the pthread_create api contractually
guarantees that the thread id is stored before start_routine runs. so this
is relying on an internal implementation detail.

https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_create.html

  "Upon successful completion, pthread_create() shall store the ID of the
   created thread in the location referenced by thread."

https://man7.org/linux/man-pages/man3/pthread_create.3.html

  "Before returning, a successful call to pthread_create() stores
   the ID of the new thread in the buffer pointed to by thread; this
   identifier is used to refer to the thread in subsequent calls to
   other pthreads functions."

it doesn't really say when it does this in relation to start_routine running.
depends how hair splitty you want to be about it. but since you're revamping
the code you might be interested in addressing it.

ty

Re: [PATCH] eal: factorize lcore main loop

[David Marchand]

On Thu, Mar 24, 2022 at 9:31 AM Tyler Retzlaff
<roretzla@linux.microsoft.com> wrote:
> > diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
> > index 684bea166c..256de91abc 100644
> > --- a/lib/eal/common/eal_common_thread.c
> > +++ b/lib/eal/common/eal_common_thread.c
> > @@ -9,6 +9,7 @@
> >  #include <assert.h>
> >  #include <string.h>
> >
> > +#include <rte_eal_trace.h>
> >  #include <rte_errno.h>
> >  #include <rte_lcore.h>
> >  #include <rte_log.h>
> > @@ -163,6 +164,77 @@ __rte_thread_uninit(void)
> >       RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
> >  }
> >
> > +/* main loop of threads */
> > +__rte_noreturn void *
> > +eal_thread_loop(__rte_unused void *arg)
> > +{
> > +     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> > +     pthread_t thread_id = pthread_self();
> > +     unsigned int lcore_id;
> > +     int ret;
> > +
> > +     /* retrieve our lcore_id from the configuration structure */
> > +     RTE_LCORE_FOREACH_WORKER(lcore_id) {
> > +             if (thread_id == lcore_config[lcore_id].thread_id)
>                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
>
> i can see that in practice this isn't a problem since the linux
> implementation of pthread_create(3) stores to pthread_t *thread before
> executing start_routine.
>
> but strictly speaking i don't think the pthread_create api contractually
> guarantees that the thread id is stored before start_routine runs. so this
> is relying on an internal implementation detail.
>
> https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_create.html
>
>   "Upon successful completion, pthread_create() shall store the ID of the
>    created thread in the location referenced by thread."
>
> https://man7.org/linux/man-pages/man3/pthread_create.3.html
>
>   "Before returning, a successful call to pthread_create() stores
>    the ID of the new thread in the buffer pointed to by thread; this
>    identifier is used to refer to the thread in subsequent calls to
>    other pthreads functions."
>
> it doesn't really say when it does this in relation to start_routine running.
> depends how hair splitty you want to be about it. but since you're revamping
> the code you might be interested in addressing it.

I had wondered about this part too in the past.

I don't see a reason to keep this loop (even considering baremetal,
since this code is within the linux implementation of EAL).
And this comment seems a good reason to cleanup the code (like simply
pass lcore_id via arg).

Something like:

Author: David Marchand <david.marchand@redhat.com>
Date:   Thu Mar 24 11:29:46 2022 +0100

    eal: cleanup lcore hand-over from main thread

    As noted by Tyler, there is nothing in the pthread API that strictly
    guarantees that the new thread won't start running eal_thread_loop
    before pthread_create writes to &lcore_config[xx].thread_id.

    Rather than rely on thread id, the main thread can directly pass the
    worker thread lcore.

    Signed-off-by: David Marchand <david.marchand@redhat.com>

diff --git a/lib/eal/common/eal_common_thread.c
b/lib/eal/common/eal_common_thread.c
index 256de91abc..962b7e9ac4 100644
--- a/lib/eal/common/eal_common_thread.c
+++ b/lib/eal/common/eal_common_thread.c
@@ -166,26 +166,17 @@ __rte_thread_uninit(void)

 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+    unsigned int lcore_id = (uintptr_t)arg;
     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-    pthread_t thread_id = pthread_self();
-    unsigned int lcore_id;
     int ret;

-    /* retrieve our lcore_id from the configuration structure */
-    RTE_LCORE_FOREACH_WORKER(lcore_id) {
-        if (thread_id == lcore_config[lcore_id].thread_id)
-            break;
-    }
-    if (lcore_id == RTE_MAX_LCORE)
-        rte_panic("cannot retrieve lcore id\n");
-
     __rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);

     ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
     RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-        lcore_id, (uintptr_t)thread_id, cpuset,
+        lcore_id, (uintptr_t)pthread_self(), cpuset,
         ret == 0 ? "" : "...");

     rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index b08dcf34b5..0fde33e70c 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -11,7 +11,7 @@
  * basic loop of thread, called for each thread by eal_init().
  *
  * @param arg
- *   opaque pointer
+ *   The lcore_id (passed as an integer) of this worker thread.
  */
 __rte_noreturn void *eal_thread_loop(void *arg);

diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index 80bc3d25e0..a6b20960f2 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -810,7 +810,7 @@ rte_eal_init(int argc, char **argv)

         /* create a thread for each lcore */
         ret = pthread_create(&lcore_config[i].thread_id, NULL,
-                     eal_thread_loop, NULL);
+                     eal_thread_loop, (void *)(uintptr_t)i);
         if (ret != 0)
             rte_panic("Cannot create thread\n");

diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 8a405d1d59..1ef263434a 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -1145,7 +1145,7 @@ rte_eal_init(int argc, char **argv)

         /* create a thread for each lcore */
         ret = pthread_create(&lcore_config[i].thread_id, NULL,
-                     eal_thread_loop, NULL);
+                     eal_thread_loop, (void *)(uintptr_t)i);
         if (ret != 0)
             rte_panic("Cannot create thread\n");

diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
index ca3c41aaa7..1874f9f6d7 100644
--- a/lib/eal/windows/eal.c
+++ b/lib/eal/windows/eal.c
@@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
         lcore_config[i].state = WAIT;

         /* create a thread for each lcore */
-        if (eal_thread_create(&lcore_config[i].thread_id) != 0)
+        if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
             rte_panic("Cannot create thread\n");
         ret = pthread_setaffinity_np(lcore_config[i].thread_id,
             sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index de1c0078a5..704781a83c 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -71,13 +71,14 @@ eal_thread_ack_command(void)

 /* function to create threads */
 int
-eal_thread_create(pthread_t *thread)
+eal_thread_create(pthread_t *thread, unsigned int lcore_id)
 {
     HANDLE th;

     th = CreateThread(NULL, 0,
         (LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
-                        NULL, 0, (LPDWORD)thread);
+                        (LPVOID)(uintptr_t)lcore_id, 0,
+                        (LPDWORD)thread);
     if (!th)
         return -1;



But seeing how this code has been there from day 1, I would not
request a backport.


-- 
David Marchand

Re: [PATCH] eal: factorize lcore main loop

[Tyler Retzlaff]

On Thu, Mar 24, 2022 at 03:44:23PM +0100, David Marchand wrote:
> On Thu, Mar 24, 2022 at 9:31 AM Tyler Retzlaff
> <roretzla@linux.microsoft.com> wrote:
> > > diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
> > > index 684bea166c..256de91abc 100644
> > > --- a/lib/eal/common/eal_common_thread.c
> > > +++ b/lib/eal/common/eal_common_thread.c
> > > @@ -9,6 +9,7 @@
> > >  #include <assert.h>
> > >  #include <string.h>
> > >
> > > +#include <rte_eal_trace.h>
> > >  #include <rte_errno.h>
> > >  #include <rte_lcore.h>
> > >  #include <rte_log.h>
> > > @@ -163,6 +164,77 @@ __rte_thread_uninit(void)
> > >       RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
> > >  }
> > >
> > > +/* main loop of threads */
> > > +__rte_noreturn void *
> > > +eal_thread_loop(__rte_unused void *arg)
> > > +{
> > > +     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> > > +     pthread_t thread_id = pthread_self();
> > > +     unsigned int lcore_id;
> > > +     int ret;
> > > +
> > > +     /* retrieve our lcore_id from the configuration structure */
> > > +     RTE_LCORE_FOREACH_WORKER(lcore_id) {
> > > +             if (thread_id == lcore_config[lcore_id].thread_id)
> >                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> >
> > i can see that in practice this isn't a problem since the linux
> > implementation of pthread_create(3) stores to pthread_t *thread before
> > executing start_routine.
> >
> > but strictly speaking i don't think the pthread_create api contractually
> > guarantees that the thread id is stored before start_routine runs. so this
> > is relying on an internal implementation detail.
> >
> > https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_create.html
> >
> >   "Upon successful completion, pthread_create() shall store the ID of the
> >    created thread in the location referenced by thread."
> >
> > https://man7.org/linux/man-pages/man3/pthread_create.3.html
> >
> >   "Before returning, a successful call to pthread_create() stores
> >    the ID of the new thread in the buffer pointed to by thread; this
> >    identifier is used to refer to the thread in subsequent calls to
> >    other pthreads functions."
> >
> > it doesn't really say when it does this in relation to start_routine running.
> > depends how hair splitty you want to be about it. but since you're revamping
> > the code you might be interested in addressing it.
> 
> I had wondered about this part too in the past.
> 
> I don't see a reason to keep this loop (even considering baremetal,
> since this code is within the linux implementation of EAL).
> And this comment seems a good reason to cleanup the code (like simply
> pass lcore_id via arg).
> 
> Something like:
> 
> Author: David Marchand <david.marchand@redhat.com>
> Date:   Thu Mar 24 11:29:46 2022 +0100
> 
>     eal: cleanup lcore hand-over from main thread
> 
>     As noted by Tyler, there is nothing in the pthread API that strictly
>     guarantees that the new thread won't start running eal_thread_loop
>     before pthread_create writes to &lcore_config[xx].thread_id.
> 
>     Rather than rely on thread id, the main thread can directly pass the
>     worker thread lcore.
> 
>     Signed-off-by: David Marchand <david.marchand@redhat.com>
> 
> diff --git a/lib/eal/common/eal_common_thread.c
> b/lib/eal/common/eal_common_thread.c
> index 256de91abc..962b7e9ac4 100644
> --- a/lib/eal/common/eal_common_thread.c
> +++ b/lib/eal/common/eal_common_thread.c
> @@ -166,26 +166,17 @@ __rte_thread_uninit(void)
> 
>  /* main loop of threads */
>  __rte_noreturn void *
> -eal_thread_loop(__rte_unused void *arg)
> +eal_thread_loop(void *arg)
>  {
> +    unsigned int lcore_id = (uintptr_t)arg;
>      char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> -    pthread_t thread_id = pthread_self();
> -    unsigned int lcore_id;
>      int ret;
> 
> -    /* retrieve our lcore_id from the configuration structure */
> -    RTE_LCORE_FOREACH_WORKER(lcore_id) {
> -        if (thread_id == lcore_config[lcore_id].thread_id)
> -            break;
> -    }
> -    if (lcore_id == RTE_MAX_LCORE)
> -        rte_panic("cannot retrieve lcore id\n");
> -
>      __rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
> 
>      ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
>      RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
> -        lcore_id, (uintptr_t)thread_id, cpuset,
> +        lcore_id, (uintptr_t)pthread_self(), cpuset,
>          ret == 0 ? "" : "...");
> 
>      rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
> diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
> index b08dcf34b5..0fde33e70c 100644
> --- a/lib/eal/common/eal_thread.h
> +++ b/lib/eal/common/eal_thread.h
> @@ -11,7 +11,7 @@
>   * basic loop of thread, called for each thread by eal_init().
>   *
>   * @param arg
> - *   opaque pointer
> + *   The lcore_id (passed as an integer) of this worker thread.
>   */
>  __rte_noreturn void *eal_thread_loop(void *arg);
> 
> diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
> index 80bc3d25e0..a6b20960f2 100644
> --- a/lib/eal/freebsd/eal.c
> +++ b/lib/eal/freebsd/eal.c
> @@ -810,7 +810,7 @@ rte_eal_init(int argc, char **argv)
> 
>          /* create a thread for each lcore */
>          ret = pthread_create(&lcore_config[i].thread_id, NULL,
> -                     eal_thread_loop, NULL);
> +                     eal_thread_loop, (void *)(uintptr_t)i);
>          if (ret != 0)
>              rte_panic("Cannot create thread\n");
> 
> diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
> index 8a405d1d59..1ef263434a 100644
> --- a/lib/eal/linux/eal.c
> +++ b/lib/eal/linux/eal.c
> @@ -1145,7 +1145,7 @@ rte_eal_init(int argc, char **argv)
> 
>          /* create a thread for each lcore */
>          ret = pthread_create(&lcore_config[i].thread_id, NULL,
> -                     eal_thread_loop, NULL);
> +                     eal_thread_loop, (void *)(uintptr_t)i);
>          if (ret != 0)
>              rte_panic("Cannot create thread\n");
> 
> diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
> index ca3c41aaa7..1874f9f6d7 100644
> --- a/lib/eal/windows/eal.c
> +++ b/lib/eal/windows/eal.c
> @@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
>          lcore_config[i].state = WAIT;
> 
>          /* create a thread for each lcore */
> -        if (eal_thread_create(&lcore_config[i].thread_id) != 0)
> +        if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
>              rte_panic("Cannot create thread\n");
>          ret = pthread_setaffinity_np(lcore_config[i].thread_id,
>              sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
> diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
> index de1c0078a5..704781a83c 100644
> --- a/lib/eal/windows/eal_thread.c
> +++ b/lib/eal/windows/eal_thread.c
> @@ -71,13 +71,14 @@ eal_thread_ack_command(void)
> 
>  /* function to create threads */
>  int
> -eal_thread_create(pthread_t *thread)
> +eal_thread_create(pthread_t *thread, unsigned int lcore_id)
>  {
>      HANDLE th;
> 
>      th = CreateThread(NULL, 0,
>          (LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
> -                        NULL, 0, (LPDWORD)thread);
> +                        (LPVOID)(uintptr_t)lcore_id, 0,
> +                        (LPDWORD)thread);
>      if (!th)
>          return -1;
> 
> 
> 
> But seeing how this code has been there from day 1, I would not
> request a backport.

this looks better to me it ends up being a bit less code and it solves
the problem in a general fashion for platforms including windows.

on windows the implementation does run the start_routine before assigning
thread which was addressed with this patch. (still not merged)
http://patchwork.dpdk.org/project/dpdk/list/?series=22094

it's likely your patch will be merged before mine so when that happens
i'll just quietly abandon mine.  however if some desire exists for a
backport the simpler patch i provided could be used.

on our downstream UT pipelines the bug was causing intermittent failure
of around 30% of the tests. i'm surprised the bug hasn't had a more
negative impact on the dpdk CI pipelines.

Re: [PATCH] eal: factorize lcore main loop

[Tyler Retzlaff]

On Wed, Mar 23, 2022 at 10:30:01AM +0100, David Marchand wrote:
> All OS implementations provide the same main loop.
> Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
> between main and threads and factorize the rest as common code.
> Thread id are now logged as string in a common format across OS.
> 
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> ---
> I had this patch in store for a long time.
> I don't particularly care about it, it's not fixing anything.
> But it seems a good cleanup/consolidation, so I rebased it and I am
> sending it to get feedback.

Acked-By: Tyler Retzlaff <roretzla@linux.microsoft.com>

Re: [PATCH] eal: factorize lcore main loop

[Thomas Monjalon]

25/03/2022 13:11, Tyler Retzlaff:
> On Thu, Mar 24, 2022 at 03:44:23PM +0100, David Marchand wrote:
> > On Thu, Mar 24, 2022 at 9:31 AM Tyler Retzlaff
> > <roretzla@linux.microsoft.com> wrote:
> > > > diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
> > > > index 684bea166c..256de91abc 100644
> > > > --- a/lib/eal/common/eal_common_thread.c
> > > > +++ b/lib/eal/common/eal_common_thread.c
> > > > @@ -9,6 +9,7 @@
> > > >  #include <assert.h>
> > > >  #include <string.h>
> > > >
> > > > +#include <rte_eal_trace.h>
> > > >  #include <rte_errno.h>
> > > >  #include <rte_lcore.h>
> > > >  #include <rte_log.h>
> > > > @@ -163,6 +164,77 @@ __rte_thread_uninit(void)
> > > >       RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
> > > >  }
> > > >
> > > > +/* main loop of threads */
> > > > +__rte_noreturn void *
> > > > +eal_thread_loop(__rte_unused void *arg)
> > > > +{
> > > > +     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> > > > +     pthread_t thread_id = pthread_self();
> > > > +     unsigned int lcore_id;
> > > > +     int ret;
> > > > +
> > > > +     /* retrieve our lcore_id from the configuration structure */
> > > > +     RTE_LCORE_FOREACH_WORKER(lcore_id) {
> > > > +             if (thread_id == lcore_config[lcore_id].thread_id)
> > >                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> > >
> > > i can see that in practice this isn't a problem since the linux
> > > implementation of pthread_create(3) stores to pthread_t *thread before
> > > executing start_routine.
> > >
> > > but strictly speaking i don't think the pthread_create api contractually
> > > guarantees that the thread id is stored before start_routine runs. so this
> > > is relying on an internal implementation detail.
> > >
> > > https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_create.html
> > >
> > >   "Upon successful completion, pthread_create() shall store the ID of the
> > >    created thread in the location referenced by thread."
> > >
> > > https://man7.org/linux/man-pages/man3/pthread_create.3.html
> > >
> > >   "Before returning, a successful call to pthread_create() stores
> > >    the ID of the new thread in the buffer pointed to by thread; this
> > >    identifier is used to refer to the thread in subsequent calls to
> > >    other pthreads functions."
> > >
> > > it doesn't really say when it does this in relation to start_routine running.
> > > depends how hair splitty you want to be about it. but since you're revamping
> > > the code you might be interested in addressing it.
> > 
> > I had wondered about this part too in the past.
> > 
> > I don't see a reason to keep this loop (even considering baremetal,
> > since this code is within the linux implementation of EAL).
> > And this comment seems a good reason to cleanup the code (like simply
> > pass lcore_id via arg).
> > 
> > Something like:
> > 
> > Author: David Marchand <david.marchand@redhat.com>
> > Date:   Thu Mar 24 11:29:46 2022 +0100
> > 
> >     eal: cleanup lcore hand-over from main thread
> > 
> >     As noted by Tyler, there is nothing in the pthread API that strictly
> >     guarantees that the new thread won't start running eal_thread_loop
> >     before pthread_create writes to &lcore_config[xx].thread_id.
> > 
> >     Rather than rely on thread id, the main thread can directly pass the
> >     worker thread lcore.
> > 
> >     Signed-off-by: David Marchand <david.marchand@redhat.com>
> > 
> > diff --git a/lib/eal/common/eal_common_thread.c
> > b/lib/eal/common/eal_common_thread.c
> > index 256de91abc..962b7e9ac4 100644
> > --- a/lib/eal/common/eal_common_thread.c
> > +++ b/lib/eal/common/eal_common_thread.c
> > @@ -166,26 +166,17 @@ __rte_thread_uninit(void)
> > 
> >  /* main loop of threads */
> >  __rte_noreturn void *
> > -eal_thread_loop(__rte_unused void *arg)
> > +eal_thread_loop(void *arg)
> >  {
> > +    unsigned int lcore_id = (uintptr_t)arg;
> >      char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> > -    pthread_t thread_id = pthread_self();
> > -    unsigned int lcore_id;
> >      int ret;
> > 
> > -    /* retrieve our lcore_id from the configuration structure */
> > -    RTE_LCORE_FOREACH_WORKER(lcore_id) {
> > -        if (thread_id == lcore_config[lcore_id].thread_id)
> > -            break;
> > -    }
> > -    if (lcore_id == RTE_MAX_LCORE)
> > -        rte_panic("cannot retrieve lcore id\n");
> > -
> >      __rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
> > 
> >      ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
> >      RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
> > -        lcore_id, (uintptr_t)thread_id, cpuset,
> > +        lcore_id, (uintptr_t)pthread_self(), cpuset,
> >          ret == 0 ? "" : "...");
> > 
> >      rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
> > diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
> > index b08dcf34b5..0fde33e70c 100644
> > --- a/lib/eal/common/eal_thread.h
> > +++ b/lib/eal/common/eal_thread.h
> > @@ -11,7 +11,7 @@
> >   * basic loop of thread, called for each thread by eal_init().
> >   *
> >   * @param arg
> > - *   opaque pointer
> > + *   The lcore_id (passed as an integer) of this worker thread.
> >   */
> >  __rte_noreturn void *eal_thread_loop(void *arg);
> > 
> > diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
> > index 80bc3d25e0..a6b20960f2 100644
> > --- a/lib/eal/freebsd/eal.c
> > +++ b/lib/eal/freebsd/eal.c
> > @@ -810,7 +810,7 @@ rte_eal_init(int argc, char **argv)
> > 
> >          /* create a thread for each lcore */
> >          ret = pthread_create(&lcore_config[i].thread_id, NULL,
> > -                     eal_thread_loop, NULL);
> > +                     eal_thread_loop, (void *)(uintptr_t)i);
> >          if (ret != 0)
> >              rte_panic("Cannot create thread\n");
> > 
> > diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
> > index 8a405d1d59..1ef263434a 100644
> > --- a/lib/eal/linux/eal.c
> > +++ b/lib/eal/linux/eal.c
> > @@ -1145,7 +1145,7 @@ rte_eal_init(int argc, char **argv)
> > 
> >          /* create a thread for each lcore */
> >          ret = pthread_create(&lcore_config[i].thread_id, NULL,
> > -                     eal_thread_loop, NULL);
> > +                     eal_thread_loop, (void *)(uintptr_t)i);
> >          if (ret != 0)
> >              rte_panic("Cannot create thread\n");
> > 
> > diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
> > index ca3c41aaa7..1874f9f6d7 100644
> > --- a/lib/eal/windows/eal.c
> > +++ b/lib/eal/windows/eal.c
> > @@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
> >          lcore_config[i].state = WAIT;
> > 
> >          /* create a thread for each lcore */
> > -        if (eal_thread_create(&lcore_config[i].thread_id) != 0)
> > +        if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
> >              rte_panic("Cannot create thread\n");
> >          ret = pthread_setaffinity_np(lcore_config[i].thread_id,
> >              sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
> > diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
> > index de1c0078a5..704781a83c 100644
> > --- a/lib/eal/windows/eal_thread.c
> > +++ b/lib/eal/windows/eal_thread.c
> > @@ -71,13 +71,14 @@ eal_thread_ack_command(void)
> > 
> >  /* function to create threads */
> >  int
> > -eal_thread_create(pthread_t *thread)
> > +eal_thread_create(pthread_t *thread, unsigned int lcore_id)
> >  {
> >      HANDLE th;
> > 
> >      th = CreateThread(NULL, 0,
> >          (LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
> > -                        NULL, 0, (LPDWORD)thread);
> > +                        (LPVOID)(uintptr_t)lcore_id, 0,
> > +                        (LPDWORD)thread);
> >      if (!th)
> >          return -1;
> > 
> > 
> > 
> > But seeing how this code has been there from day 1, I would not
> > request a backport.
> 
> this looks better to me it ends up being a bit less code and it solves
> the problem in a general fashion for platforms including windows.
> 
> on windows the implementation does run the start_routine before assigning
> thread which was addressed with this patch. (still not merged)
> http://patchwork.dpdk.org/project/dpdk/list/?series=22094
> 
> it's likely your patch will be merged before mine so when that happens
> i'll just quietly abandon mine.  however if some desire exists for a
> backport the simpler patch i provided could be used.

Your patch could be merged now that we start a new cycle.
What do you prefer? Is David's solution better?
In this case, should we reject your patch?

Re: [PATCH] eal: factorize lcore main loop

[David Marchand]

On Fri, Mar 25, 2022 at 3:58 PM Thomas Monjalon <thomas@monjalon.net> wrote:
> > > But seeing how this code has been there from day 1, I would not
> > > request a backport.
> >
> > this looks better to me it ends up being a bit less code and it solves
> > the problem in a general fashion for platforms including windows.
> >
> > on windows the implementation does run the start_routine before assigning
> > thread which was addressed with this patch. (still not merged)
> > http://patchwork.dpdk.org/project/dpdk/list/?series=22094
> >
> > it's likely your patch will be merged before mine so when that happens
> > i'll just quietly abandon mine.  however if some desire exists for a
> > backport the simpler patch i provided could be used.
>
> Your patch could be merged now that we start a new cycle.
> What do you prefer? Is David's solution better?
> In this case, should we reject your patch?

We can merge Tyler fix right away because it is a real issue on
Windows and it can be backported.

My series can be rebased and merged later as a cleanup/unified
solution for all OS.


-- 
David Marchand

Re: [PATCH] eal: factorize lcore main loop

[Tyler Retzlaff]

On Fri, Mar 25, 2022 at 04:09:50PM +0100, David Marchand wrote:
> On Fri, Mar 25, 2022 at 3:58 PM Thomas Monjalon <thomas@monjalon.net> wrote:
> > > > But seeing how this code has been there from day 1, I would not
> > > > request a backport.
> > >
> > > this looks better to me it ends up being a bit less code and it solves
> > > the problem in a general fashion for platforms including windows.
> > >
> > > on windows the implementation does run the start_routine before assigning
> > > thread which was addressed with this patch. (still not merged)
> > > http://patchwork.dpdk.org/project/dpdk/list/?series=22094
> > >
> > > it's likely your patch will be merged before mine so when that happens
> > > i'll just quietly abandon mine.  however if some desire exists for a
> > > backport the simpler patch i provided could be used.
> >
> > Your patch could be merged now that we start a new cycle.
> > What do you prefer? Is David's solution better?
> > In this case, should we reject your patch?
> 
> We can merge Tyler fix right away because it is a real issue on
> Windows and it can be backported.
> 
> My series can be rebased and merged later as a cleanup/unified
> solution for all OS.

sounds about right to me. no objection here.

> 
> 
> -- 
> David Marchand

[PATCH v2 1/2] eal: cleanup lcore ID hand-over

[David Marchand]

So far, a worker thread has been using its thread_id to discover which
lcore has been assigned to it.

On the other hand, as noted by Tyler, the pthread API does not strictly
guarantee that a new thread won't start running eal_thread_loop before
pthread_create writes to &lcore_config[xx].thread_id.

Though all OS implementations supported in DPDK (recently) ensure this
property, it is more robust to have the main thread directly pass
the worker thread lcore.

Signed-off-by: David Marchand <david.marchand@redhat.com>
---
 lib/eal/common/eal_thread.h  |  4 ++--
 lib/eal/freebsd/eal.c        |  2 +-
 lib/eal/freebsd/eal_thread.c | 16 +++-------------
 lib/eal/linux/eal.c          |  2 +-
 lib/eal/linux/eal_thread.c   | 17 ++++-------------
 lib/eal/windows/eal.c        |  2 +-
 lib/eal/windows/eal_thread.c | 23 +++++++----------------
 7 files changed, 19 insertions(+), 47 deletions(-)

diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index 4a49117be8..3c84efd553 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -8,10 +8,10 @@
 #include <rte_lcore.h>
 
 /**
- * basic loop of thread, called for each thread by eal_init().
+ * Basic loop of EAL thread, called for each worker thread by rte_eal_init().
  *
  * @param arg
- *   opaque pointer
+ *   The lcore_id (passed as an integer) of this worker thread.
  */
 __rte_noreturn void *eal_thread_loop(void *arg);
 
diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index 71993fe25b..e233e57184 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -813,7 +813,7 @@ rte_eal_init(int argc, char **argv)
 
 		/* create a thread for each lcore */
 		ret = pthread_create(&lcore_config[i].thread_id, NULL,
-				     eal_thread_loop, NULL);
+				     eal_thread_loop, (void *)(uintptr_t)i);
 		if (ret != 0)
 			rte_panic("Cannot create thread\n");
 
diff --git a/lib/eal/freebsd/eal_thread.c b/lib/eal/freebsd/eal_thread.c
index 3b18030d73..9044d70ef7 100644
--- a/lib/eal/freebsd/eal_thread.c
+++ b/lib/eal/freebsd/eal_thread.c
@@ -76,25 +76,15 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id)
 
 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
 	unsigned lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
 
@@ -102,7 +92,7 @@ eal_thread_loop(__rte_unused void *arg)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		lcore_id, thread_id, cpuset, ret == 0 ? "" : "...");
+		lcore_id, pthread_self(), cpuset, ret == 0 ? "" : "...");
 
 	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
 
diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 025e5cc10d..98c6838026 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -1147,7 +1147,7 @@ rte_eal_init(int argc, char **argv)
 
 		/* create a thread for each lcore */
 		ret = pthread_create(&lcore_config[i].thread_id, NULL,
-				     eal_thread_loop, NULL);
+				     eal_thread_loop, (void *)(uintptr_t)i);
 		if (ret != 0)
 			rte_panic("Cannot create thread\n");
 
diff --git a/lib/eal/linux/eal_thread.c b/lib/eal/linux/eal_thread.c
index fa6cd7e2c4..26b0a7d48a 100644
--- a/lib/eal/linux/eal_thread.c
+++ b/lib/eal/linux/eal_thread.c
@@ -70,24 +70,14 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
 
 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
-	unsigned lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
 
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
@@ -96,7 +86,8 @@ eal_thread_loop(__rte_unused void *arg)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset, ret == 0 ? "" : "...");
+		lcore_id, (uintptr_t)pthread_self(), cpuset,
+		ret == 0 ? "" : "...");
 
 	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
 
diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
index ca3c41aaa7..1874f9f6d7 100644
--- a/lib/eal/windows/eal.c
+++ b/lib/eal/windows/eal.c
@@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
 		lcore_config[i].state = WAIT;
 
 		/* create a thread for each lcore */
-		if (eal_thread_create(&lcore_config[i].thread_id) != 0)
+		if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
 			rte_panic("Cannot create thread\n");
 		ret = pthread_setaffinity_np(lcore_config[i].thread_id,
 			sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index ff84cb42af..95e96548de 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -63,32 +63,21 @@ rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
 
 /* main loop of threads */
 void *
-eal_thread_loop(void *arg __rte_unused)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
-	unsigned int lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
 
 	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
 
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset);
+		lcore_id, (uintptr_t)pthread_self(), cpuset);
 
 	/* read on our pipe to get commands */
 	while (1) {
@@ -144,13 +133,15 @@ eal_thread_loop(void *arg __rte_unused)
 
 /* function to create threads */
 int
-eal_thread_create(pthread_t *thread)
+eal_thread_create(pthread_t *thread, unsigned int lcore_id)
 {
 	HANDLE th;
 
 	th = CreateThread(NULL, 0,
 		(LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
-						NULL, CREATE_SUSPENDED, (LPDWORD)thread);
+						(LPVOID)(uintptr_t)lcore_id,
+						CREATE_SUSPENDED,
+						(LPDWORD)thread);
 	if (!th)
 		return -1;
 
-- 
2.23.0

[PATCH v2 2/2] eal: factorize lcore main loop

[David Marchand]

All OS implementations provide the same main loop.
Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
between main and threads and factorize the rest as common code.
Thread id are now logged as string in a common format across OS.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
Changes since v1:
- rebased on top of Tyler fix for Windows and new cleanup,

---
 lib/eal/common/eal_common_launch.c |  36 +++++++-
 lib/eal/common/eal_common_thread.c |  63 ++++++++++++++
 lib/eal/common/eal_thread.h        |  27 ++++++
 lib/eal/freebsd/eal.c              |   7 +-
 lib/eal/freebsd/eal_thread.c       | 128 ----------------------------
 lib/eal/linux/eal.c                |   4 +-
 lib/eal/linux/eal_thread.c         | 130 +----------------------------
 lib/eal/unix/eal_unix_thread.c     |  63 ++++++++++++++
 lib/eal/unix/meson.build           |   5 +-
 lib/eal/windows/eal_thread.c       | 126 +++++++---------------------
 10 files changed, 227 insertions(+), 362 deletions(-)
 create mode 100644 lib/eal/unix/eal_unix_thread.c

diff --git a/lib/eal/common/eal_common_launch.c b/lib/eal/common/eal_common_launch.c
index 9f393b9bda..5770803172 100644
--- a/lib/eal/common/eal_common_launch.c
+++ b/lib/eal/common/eal_common_launch.c
@@ -5,11 +5,13 @@
 #include <errno.h>
 
 #include <rte_launch.h>
+#include <rte_eal_trace.h>
 #include <rte_atomic.h>
 #include <rte_pause.h>
 #include <rte_lcore.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 
 /*
  * Wait until a lcore finished its job.
@@ -18,12 +20,44 @@ int
 rte_eal_wait_lcore(unsigned worker_id)
 {
 	while (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
+			__ATOMIC_ACQUIRE) != WAIT)
 		rte_pause();
 
 	return lcore_config[worker_id].ret;
 }
 
+/*
+ * Send a message to a worker lcore identified by worker_id to call a
+ * function f with argument arg. Once the execution is done, the
+ * remote lcore switches to WAIT state.
+ */
+int
+rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
+{
+	int rc = -EBUSY;
+
+	/* Check if the worker is in 'WAIT' state. Use acquire order
+	 * since 'state' variable is used as the guard variable.
+	 */
+	if (__atomic_load_n(&lcore_config[worker_id].state,
+			__ATOMIC_ACQUIRE) != WAIT)
+		goto finish;
+
+	lcore_config[worker_id].arg = arg;
+	/* Ensure that all the memory operations are completed
+	 * before the worker thread starts running the function.
+	 * Use worker thread function as the guard variable.
+	 */
+	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
+
+	eal_thread_wake_worker(worker_id);
+	rc = 0;
+
+finish:
+	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
+	return rc;
+}
+
 /*
  * Check that every WORKER lcores are in WAIT state, then call
  * rte_eal_remote_launch() for all of them. If call_main is true
diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
index 684bea166c..962b7e9ac4 100644
--- a/lib/eal/common/eal_common_thread.c
+++ b/lib/eal/common/eal_common_thread.c
@@ -9,6 +9,7 @@
 #include <assert.h>
 #include <string.h>
 
+#include <rte_eal_trace.h>
 #include <rte_errno.h>
 #include <rte_lcore.h>
 #include <rte_log.h>
@@ -163,6 +164,68 @@ __rte_thread_uninit(void)
 	RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
 }
 
+/* main loop of threads */
+__rte_noreturn void *
+eal_thread_loop(void *arg)
+{
+	unsigned int lcore_id = (uintptr_t)arg;
+	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	int ret;
+
+	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
+
+	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
+	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		lcore_id, (uintptr_t)pthread_self(), cpuset,
+		ret == 0 ? "" : "...");
+
+	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
+
+	/* read on our pipe to get commands */
+	while (1) {
+		lcore_function_t *f;
+		void *fct_arg;
+
+		eal_thread_wait_command();
+
+		/* Set the state to 'RUNNING'. Use release order
+		 * since 'state' variable is used as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
+			__ATOMIC_RELEASE);
+
+		eal_thread_ack_command();
+
+		/* Load 'f' with acquire order to ensure that
+		 * the memory operations from the main thread
+		 * are accessed only after update to 'f' is visible.
+		 * Wait till the update to 'f' is visible to the worker.
+		 */
+		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
+				__ATOMIC_ACQUIRE)) == NULL)
+			rte_pause();
+
+		/* call the function and store the return value */
+		fct_arg = lcore_config[lcore_id].arg;
+		ret = f(fct_arg);
+		lcore_config[lcore_id].ret = ret;
+		lcore_config[lcore_id].f = NULL;
+		lcore_config[lcore_id].arg = NULL;
+
+		/* Store the state with release order to ensure that
+		 * the memory operations from the worker thread
+		 * are completed before the state is updated.
+		 * Use 'state' as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
+			__ATOMIC_RELEASE);
+	}
+
+	/* never reached */
+	/* pthread_exit(NULL); */
+	/* return NULL; */
+}
+
 enum __rte_ctrl_thread_status {
 	CTRL_THREAD_LAUNCHING, /* Yet to call pthread_create function */
 	CTRL_THREAD_RUNNING, /* Control thread is running successfully */
diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index 3c84efd553..ca3378d463 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -58,4 +58,31 @@ eal_thread_dump_affinity(rte_cpuset_t *cpuset, char *str, unsigned int size);
 int
 eal_thread_dump_current_affinity(char *str, unsigned int size);
 
+/**
+ * Called by the main thread to wake up a worker in 'WAIT' state.
+ * This function blocks until the worker acknowledge it started processing a
+ * new command.
+ * This function is private to EAL.
+ *
+ * @param worker_id
+ *   The lcore_id of a worker thread.
+ */
+void
+eal_thread_wake_worker(unsigned int worker_id);
+
+/**
+ * Called by a worker thread to sleep after entering 'WAIT' state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_wait_command(void);
+
+/**
+ * Called by a worker thread to acknowledge new command after leaving 'WAIT'
+ * state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_ack_command(void);
+
 #endif /* EAL_THREAD_H */
diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index e233e57184..a6b20960f2 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -579,7 +579,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
@@ -604,8 +603,6 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-	thread_id = pthread_self();
-
 	eal_reset_internal_config(internal_conf);
 
 	/* clone argv to report out later in telemetry */
@@ -794,8 +791,8 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 
-	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		config->main_lcore, thread_id, cpuset,
+	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/freebsd/eal_thread.c b/lib/eal/freebsd/eal_thread.c
index 9044d70ef7..ab81b527bc 100644
--- a/lib/eal/freebsd/eal_thread.c
+++ b/lib/eal/freebsd/eal_thread.c
@@ -20,138 +20,10 @@
 #include <rte_per_lcore.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(void *arg)
-{
-	unsigned int lcore_id = (uintptr_t)arg;
-	char c;
-	int n, ret;
-	unsigned lcore_id;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		lcore_id, pthread_self(), cpuset, ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 98c6838026..1ef263434a 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -862,7 +862,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	const char *p;
@@ -890,7 +889,6 @@ rte_eal_init(int argc, char **argv)
 
 	p = strrchr(argv[0], '/');
 	strlcpy(logid, p ? p + 1 : argv[0], sizeof(logid));
-	thread_id = pthread_self();
 
 	eal_reset_internal_config(internal_conf);
 
@@ -1129,7 +1127,7 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		config->main_lcore, (uintptr_t)thread_id, cpuset,
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/linux/eal_thread.c b/lib/eal/linux/eal_thread.c
index 26b0a7d48a..820cc905e0 100644
--- a/lib/eal/linux/eal_thread.c
+++ b/lib/eal/linux/eal_thread.c
@@ -14,139 +14,11 @@
 #include <rte_log.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
+#include <rte_string_fns.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function pointer as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(void *arg)
-{
-	unsigned int lcore_id = (uintptr_t)arg;
-	char c;
-	int n, ret;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		lcore_id, (uintptr_t)pthread_self(), cpuset,
-		ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/unix/eal_unix_thread.c b/lib/eal/unix/eal_unix_thread.c
new file mode 100644
index 0000000000..70b5ba6b98
--- /dev/null
+++ b/lib/eal/unix/eal_unix_thread.c
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Red Hat, Inc.
+ */
+
+#include <errno.h>
+#include <unistd.h>
+
+#include <rte_debug.h>
+
+#include "eal_private.h"
+
+void
+eal_thread_wake_worker(unsigned int worker_id)
+{
+	int m2w = lcore_config[worker_id].pipe_main2worker[1];
+	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
+
+	do {
+		n = write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+
+	do {
+		n = read(w2m, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_wait_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
+	char c;
+	int n;
+
+	m2w = lcore_config[lcore_id].pipe_main2worker[0];
+	do {
+		n = read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
+
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+}
diff --git a/lib/eal/unix/meson.build b/lib/eal/unix/meson.build
index a22ea7cabc..781505ca90 100644
--- a/lib/eal/unix/meson.build
+++ b/lib/eal/unix/meson.build
@@ -3,9 +3,10 @@
 
 sources += files(
         'eal_file.c',
+        'eal_filesystem.c',
+        'eal_firmware.c',
         'eal_unix_memory.c',
+        'eal_unix_thread.c',
         'eal_unix_timer.c',
-        'eal_firmware.c',
-        'eal_filesystem.c',
         'rte_thread.c',
 )
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index 95e96548de..f3c61b4456 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -11,124 +11,62 @@
 #include <rte_per_lcore.h>
 #include <rte_common.h>
 #include <rte_memory.h>
-#include <eal_thread.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 #include "eal_windows.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
+void
+eal_thread_wake_worker(unsigned int worker_id)
 {
-	int n;
-	char c = 0;
 	int m2w = lcore_config[worker_id].pipe_main2worker[1];
 	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
 
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		return -EBUSY;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
+	do {
 		n = _write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
 	if (n < 0)
 		rte_panic("cannot write on configuration pipe\n");
 
-	/* wait ack */
 	do {
 		n = _read(w2m, &c, 1);
 	} while (n < 0 && errno == EINTR);
-
 	if (n <= 0)
 		rte_panic("cannot read on configuration pipe\n");
-
-	return 0;
 }
 
-/* main loop of threads */
-void *
-eal_thread_loop(void *arg)
+void
+eal_thread_wait_command(void)
 {
-	unsigned int lcore_id = (uintptr_t)arg;
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
 	char c;
-	int n, ret;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	int n;
 
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
 
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s])\n",
-		lcore_id, (uintptr_t)pthread_self(), cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = _read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = _write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
+
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
 }
 
 /* function to create threads */
-- 
2.23.0

Re: [PATCH v2 2/2] eal: factorize lcore main loop

[David Marchand]

On Fri, Apr 1, 2022 at 10:44 AM David Marchand
<david.marchand@redhat.com> wrote:
>
> All OS implementations provide the same main loop.
> Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
> between main and threads and factorize the rest as common code.
> Thread id are now logged as string in a common format across OS.
>
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> Acked-by: Morten Brørup <mb@smartsharesystems.com>
> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> ---
> Changes since v1:
> - rebased on top of Tyler fix for Windows and new cleanup,

FYI, this series needs a respin to fix Windows build (/me hides..).
There is also a false positive ABI breakage reported by libabigail
that Dodji is looking into.


-- 
David Marchand

[PATCH v3 1/2] eal: cleanup lcore ID hand-over

[David Marchand]

So far, a worker thread has been using its thread_id to discover which
lcore has been assigned to it.

On the other hand, as noted by Tyler, the pthread API does not strictly
guarantee that a new thread won't start running eal_thread_loop before
pthread_create writes to &lcore_config[xx].thread_id.

Though all OS implementations supported in DPDK (recently) ensure this
property, it is more robust to have the main thread directly pass
the worker thread lcore.

Signed-off-by: David Marchand <david.marchand@redhat.com>
---
Changes since v2:
- fixed Windows compilation,

---
 lib/eal/common/eal_thread.h   |  4 ++--
 lib/eal/freebsd/eal.c         |  2 +-
 lib/eal/freebsd/eal_thread.c  | 16 +++-------------
 lib/eal/linux/eal.c           |  2 +-
 lib/eal/linux/eal_thread.c    | 17 ++++-------------
 lib/eal/windows/eal.c         |  2 +-
 lib/eal/windows/eal_thread.c  | 23 +++++++----------------
 lib/eal/windows/eal_windows.h |  4 +++-
 8 files changed, 22 insertions(+), 48 deletions(-)

diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index 4a49117be8..3c84efd553 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -8,10 +8,10 @@
 #include <rte_lcore.h>
 
 /**
- * basic loop of thread, called for each thread by eal_init().
+ * Basic loop of EAL thread, called for each worker thread by rte_eal_init().
  *
  * @param arg
- *   opaque pointer
+ *   The lcore_id (passed as an integer) of this worker thread.
  */
 __rte_noreturn void *eal_thread_loop(void *arg);
 
diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index 71993fe25b..e233e57184 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -813,7 +813,7 @@ rte_eal_init(int argc, char **argv)
 
 		/* create a thread for each lcore */
 		ret = pthread_create(&lcore_config[i].thread_id, NULL,
-				     eal_thread_loop, NULL);
+				     eal_thread_loop, (void *)(uintptr_t)i);
 		if (ret != 0)
 			rte_panic("Cannot create thread\n");
 
diff --git a/lib/eal/freebsd/eal_thread.c b/lib/eal/freebsd/eal_thread.c
index 3b18030d73..9044d70ef7 100644
--- a/lib/eal/freebsd/eal_thread.c
+++ b/lib/eal/freebsd/eal_thread.c
@@ -76,25 +76,15 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id)
 
 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
 	unsigned lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
 
@@ -102,7 +92,7 @@ eal_thread_loop(__rte_unused void *arg)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		lcore_id, thread_id, cpuset, ret == 0 ? "" : "...");
+		lcore_id, pthread_self(), cpuset, ret == 0 ? "" : "...");
 
 	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
 
diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 025e5cc10d..98c6838026 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -1147,7 +1147,7 @@ rte_eal_init(int argc, char **argv)
 
 		/* create a thread for each lcore */
 		ret = pthread_create(&lcore_config[i].thread_id, NULL,
-				     eal_thread_loop, NULL);
+				     eal_thread_loop, (void *)(uintptr_t)i);
 		if (ret != 0)
 			rte_panic("Cannot create thread\n");
 
diff --git a/lib/eal/linux/eal_thread.c b/lib/eal/linux/eal_thread.c
index fa6cd7e2c4..26b0a7d48a 100644
--- a/lib/eal/linux/eal_thread.c
+++ b/lib/eal/linux/eal_thread.c
@@ -70,24 +70,14 @@ rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
 
 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
-	unsigned lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
 
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
@@ -96,7 +86,8 @@ eal_thread_loop(__rte_unused void *arg)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset, ret == 0 ? "" : "...");
+		lcore_id, (uintptr_t)pthread_self(), cpuset,
+		ret == 0 ? "" : "...");
 
 	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
 
diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
index ca3c41aaa7..1874f9f6d7 100644
--- a/lib/eal/windows/eal.c
+++ b/lib/eal/windows/eal.c
@@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
 		lcore_config[i].state = WAIT;
 
 		/* create a thread for each lcore */
-		if (eal_thread_create(&lcore_config[i].thread_id) != 0)
+		if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
 			rte_panic("Cannot create thread\n");
 		ret = pthread_setaffinity_np(lcore_config[i].thread_id,
 			sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index ff84cb42af..95e96548de 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -63,32 +63,21 @@ rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
 
 /* main loop of threads */
 void *
-eal_thread_loop(void *arg __rte_unused)
+eal_thread_loop(void *arg)
 {
+	unsigned int lcore_id = (uintptr_t)arg;
 	char c;
 	int n, ret;
-	unsigned int lcore_id;
-	pthread_t thread_id;
 	int m2w, w2m;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
 
-	thread_id = pthread_self();
-
-	/* retrieve our lcore_id from the configuration structure */
-	RTE_LCORE_FOREACH_WORKER(lcore_id) {
-		if (thread_id == lcore_config[lcore_id].thread_id)
-			break;
-	}
-	if (lcore_id == RTE_MAX_LCORE)
-		rte_panic("cannot retrieve lcore id\n");
-
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
 	w2m = lcore_config[lcore_id].pipe_worker2main[1];
 
 	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
 
 	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s])\n",
-		lcore_id, (uintptr_t)thread_id, cpuset);
+		lcore_id, (uintptr_t)pthread_self(), cpuset);
 
 	/* read on our pipe to get commands */
 	while (1) {
@@ -144,13 +133,15 @@ eal_thread_loop(void *arg __rte_unused)
 
 /* function to create threads */
 int
-eal_thread_create(pthread_t *thread)
+eal_thread_create(pthread_t *thread, unsigned int lcore_id)
 {
 	HANDLE th;
 
 	th = CreateThread(NULL, 0,
 		(LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
-						NULL, CREATE_SUSPENDED, (LPDWORD)thread);
+						(LPVOID)(uintptr_t)lcore_id,
+						CREATE_SUSPENDED,
+						(LPDWORD)thread);
 	if (!th)
 		return -1;
 
diff --git a/lib/eal/windows/eal_windows.h b/lib/eal/windows/eal_windows.h
index 245aa60344..e4c46705c6 100644
--- a/lib/eal/windows/eal_windows.h
+++ b/lib/eal/windows/eal_windows.h
@@ -40,10 +40,12 @@ int eal_create_cpu_map(void);
  *
  * @param thread
  *   The location to store the thread id if successful.
+ * @param lcore_id
+ *   The lcore_id of this worker thread.
  * @return
  *   0 for success, -1 if the thread is not created.
  */
-int eal_thread_create(pthread_t *thread);
+int eal_thread_create(pthread_t *thread, unsigned int lcore_id);
 
 /**
  * Get system NUMA node number for a socket ID.
-- 
2.23.0

[PATCH v3 2/2] eal: factorize lcore main loop

[David Marchand]

All OS implementations provide the same main loop.
Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
between main and threads and factorize the rest as common code.
Thread id are now logged as string in a common format across OS.

Note: libabigail flags this change as breaking ABI in clang builds:

1 function with some indirect sub-type change:

  [C] 'function int rte_eal_remote_launch(int (void*)*, void*, unsigned
      int)' at eal_common_launch.c:35:1 has some indirect sub-type
      changes:
    parameter 1 of type 'int (void*)*' changed:
      in pointed to type 'function type int (void*)' at rte_launch.h:31:1:
        entity changed from 'function type int (void*)' to 'typedef
          lcore_function_t' at rte_launch.h:31:1
        type size hasn't changed

This is being investigated on libabigail side.
For now, we don't have much choice but to waive reports on this symbol.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
Changes since v2:
- aligned rte_eal_remote_launch definition to prototype,
- waived false positive ABI breakage for clang builds,

Changes since v1:
- rebased on top of Tyler fix for Windows and new cleanup,

---
 devtools/libabigail.abignore       |   4 +
 lib/eal/common/eal_common_launch.c |  36 +++++++-
 lib/eal/common/eal_common_thread.c |  63 ++++++++++++++
 lib/eal/common/eal_thread.h        |  27 ++++++
 lib/eal/freebsd/eal.c              |   7 +-
 lib/eal/freebsd/eal_thread.c       | 128 ----------------------------
 lib/eal/linux/eal.c                |   4 +-
 lib/eal/linux/eal_thread.c         | 130 +----------------------------
 lib/eal/unix/eal_unix_thread.c     |  63 ++++++++++++++
 lib/eal/unix/meson.build           |   5 +-
 lib/eal/windows/eal_thread.c       | 126 +++++++---------------------
 11 files changed, 231 insertions(+), 362 deletions(-)
 create mode 100644 lib/eal/unix/eal_unix_thread.c

diff --git a/devtools/libabigail.abignore b/devtools/libabigail.abignore
index 5be5c28dc3..79ff15dc4e 100644
--- a/devtools/libabigail.abignore
+++ b/devtools/libabigail.abignore
@@ -52,3 +52,7 @@
 ; Ignore visibility fix of local functions in experimental gpudev library
 [suppress_file]
         soname_regexp = ^librte_gpudev\.
+
+; Ignore libabigail false-positive in clang builds, after moving code.
+[suppress_function]
+	name = rte_eal_remote_launch
diff --git a/lib/eal/common/eal_common_launch.c b/lib/eal/common/eal_common_launch.c
index 9f393b9bda..992f8e4631 100644
--- a/lib/eal/common/eal_common_launch.c
+++ b/lib/eal/common/eal_common_launch.c
@@ -5,11 +5,13 @@
 #include <errno.h>
 
 #include <rte_launch.h>
+#include <rte_eal_trace.h>
 #include <rte_atomic.h>
 #include <rte_pause.h>
 #include <rte_lcore.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 
 /*
  * Wait until a lcore finished its job.
@@ -18,12 +20,44 @@ int
 rte_eal_wait_lcore(unsigned worker_id)
 {
 	while (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
+			__ATOMIC_ACQUIRE) != WAIT)
 		rte_pause();
 
 	return lcore_config[worker_id].ret;
 }
 
+/*
+ * Send a message to a worker lcore identified by worker_id to call a
+ * function f with argument arg. Once the execution is done, the
+ * remote lcore switches to WAIT state.
+ */
+int
+rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
+{
+	int rc = -EBUSY;
+
+	/* Check if the worker is in 'WAIT' state. Use acquire order
+	 * since 'state' variable is used as the guard variable.
+	 */
+	if (__atomic_load_n(&lcore_config[worker_id].state,
+			__ATOMIC_ACQUIRE) != WAIT)
+		goto finish;
+
+	lcore_config[worker_id].arg = arg;
+	/* Ensure that all the memory operations are completed
+	 * before the worker thread starts running the function.
+	 * Use worker thread function as the guard variable.
+	 */
+	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
+
+	eal_thread_wake_worker(worker_id);
+	rc = 0;
+
+finish:
+	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
+	return rc;
+}
+
 /*
  * Check that every WORKER lcores are in WAIT state, then call
  * rte_eal_remote_launch() for all of them. If call_main is true
diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
index 684bea166c..962b7e9ac4 100644
--- a/lib/eal/common/eal_common_thread.c
+++ b/lib/eal/common/eal_common_thread.c
@@ -9,6 +9,7 @@
 #include <assert.h>
 #include <string.h>
 
+#include <rte_eal_trace.h>
 #include <rte_errno.h>
 #include <rte_lcore.h>
 #include <rte_log.h>
@@ -163,6 +164,68 @@ __rte_thread_uninit(void)
 	RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
 }
 
+/* main loop of threads */
+__rte_noreturn void *
+eal_thread_loop(void *arg)
+{
+	unsigned int lcore_id = (uintptr_t)arg;
+	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	int ret;
+
+	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
+
+	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
+	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		lcore_id, (uintptr_t)pthread_self(), cpuset,
+		ret == 0 ? "" : "...");
+
+	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
+
+	/* read on our pipe to get commands */
+	while (1) {
+		lcore_function_t *f;
+		void *fct_arg;
+
+		eal_thread_wait_command();
+
+		/* Set the state to 'RUNNING'. Use release order
+		 * since 'state' variable is used as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
+			__ATOMIC_RELEASE);
+
+		eal_thread_ack_command();
+
+		/* Load 'f' with acquire order to ensure that
+		 * the memory operations from the main thread
+		 * are accessed only after update to 'f' is visible.
+		 * Wait till the update to 'f' is visible to the worker.
+		 */
+		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
+				__ATOMIC_ACQUIRE)) == NULL)
+			rte_pause();
+
+		/* call the function and store the return value */
+		fct_arg = lcore_config[lcore_id].arg;
+		ret = f(fct_arg);
+		lcore_config[lcore_id].ret = ret;
+		lcore_config[lcore_id].f = NULL;
+		lcore_config[lcore_id].arg = NULL;
+
+		/* Store the state with release order to ensure that
+		 * the memory operations from the worker thread
+		 * are completed before the state is updated.
+		 * Use 'state' as the guard variable.
+		 */
+		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
+			__ATOMIC_RELEASE);
+	}
+
+	/* never reached */
+	/* pthread_exit(NULL); */
+	/* return NULL; */
+}
+
 enum __rte_ctrl_thread_status {
 	CTRL_THREAD_LAUNCHING, /* Yet to call pthread_create function */
 	CTRL_THREAD_RUNNING, /* Control thread is running successfully */
diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index 3c84efd553..ca3378d463 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -58,4 +58,31 @@ eal_thread_dump_affinity(rte_cpuset_t *cpuset, char *str, unsigned int size);
 int
 eal_thread_dump_current_affinity(char *str, unsigned int size);
 
+/**
+ * Called by the main thread to wake up a worker in 'WAIT' state.
+ * This function blocks until the worker acknowledge it started processing a
+ * new command.
+ * This function is private to EAL.
+ *
+ * @param worker_id
+ *   The lcore_id of a worker thread.
+ */
+void
+eal_thread_wake_worker(unsigned int worker_id);
+
+/**
+ * Called by a worker thread to sleep after entering 'WAIT' state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_wait_command(void);
+
+/**
+ * Called by a worker thread to acknowledge new command after leaving 'WAIT'
+ * state.
+ * This function is private to EAL.
+ */
+void
+eal_thread_ack_command(void);
+
 #endif /* EAL_THREAD_H */
diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index e233e57184..a6b20960f2 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -579,7 +579,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
@@ -604,8 +603,6 @@ rte_eal_init(int argc, char **argv)
 		return -1;
 	}
 
-	thread_id = pthread_self();
-
 	eal_reset_internal_config(internal_conf);
 
 	/* clone argv to report out later in telemetry */
@@ -794,8 +791,8 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 
-	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		config->main_lcore, thread_id, cpuset,
+	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/freebsd/eal_thread.c b/lib/eal/freebsd/eal_thread.c
index 9044d70ef7..ab81b527bc 100644
--- a/lib/eal/freebsd/eal_thread.c
+++ b/lib/eal/freebsd/eal_thread.c
@@ -20,138 +20,10 @@
 #include <rte_per_lcore.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(void *arg)
-{
-	unsigned int lcore_id = (uintptr_t)arg;
-	char c;
-	int n, ret;
-	unsigned lcore_id;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%p;cpuset=[%s%s])\n",
-		lcore_id, pthread_self(), cpuset, ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 98c6838026..1ef263434a 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -862,7 +862,6 @@ int
 rte_eal_init(int argc, char **argv)
 {
 	int i, fctret, ret;
-	pthread_t thread_id;
 	static uint32_t run_once;
 	uint32_t has_run = 0;
 	const char *p;
@@ -890,7 +889,6 @@ rte_eal_init(int argc, char **argv)
 
 	p = strrchr(argv[0], '/');
 	strlcpy(logid, p ? p + 1 : argv[0], sizeof(logid));
-	thread_id = pthread_self();
 
 	eal_reset_internal_config(internal_conf);
 
@@ -1129,7 +1127,7 @@ rte_eal_init(int argc, char **argv)
 
 	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
 	RTE_LOG(DEBUG, EAL, "Main lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		config->main_lcore, (uintptr_t)thread_id, cpuset,
+		config->main_lcore, (uintptr_t)pthread_self(), cpuset,
 		ret == 0 ? "" : "...");
 
 	RTE_LCORE_FOREACH_WORKER(i) {
diff --git a/lib/eal/linux/eal_thread.c b/lib/eal/linux/eal_thread.c
index 26b0a7d48a..820cc905e0 100644
--- a/lib/eal/linux/eal_thread.c
+++ b/lib/eal/linux/eal_thread.c
@@ -14,139 +14,11 @@
 #include <rte_log.h>
 #include <rte_eal.h>
 #include <rte_lcore.h>
-#include <rte_eal_trace.h>
+#include <rte_string_fns.h>
 
 #include "eal_private.h"
 #include "eal_thread.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned int worker_id)
-{
-	int n;
-	char c = 0;
-	int m2w = lcore_config[worker_id].pipe_main2worker[1];
-	int w2m = lcore_config[worker_id].pipe_worker2main[0];
-	int rc = -EBUSY;
-
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		goto finish;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function pointer as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
-		n = write(m2w, &c, 1);
-	if (n < 0)
-		rte_panic("cannot write on configuration pipe\n");
-
-	/* wait ack */
-	do {
-		n = read(w2m, &c, 1);
-	} while (n < 0 && errno == EINTR);
-
-	if (n <= 0)
-		rte_panic("cannot read on configuration pipe\n");
-
-	rc = 0;
-finish:
-	rte_eal_trace_thread_remote_launch(f, arg, worker_id, rc);
-	return rc;
-}
-
-/* main loop of threads */
-__rte_noreturn void *
-eal_thread_loop(void *arg)
-{
-	unsigned int lcore_id = (uintptr_t)arg;
-	char c;
-	int n, ret;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-
-
-	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
-
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-		lcore_id, (uintptr_t)pthread_self(), cpuset,
-		ret == 0 ? "" : "...");
-
-	rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
-
-	/* never reached */
-	/* pthread_exit(NULL); */
-	/* return NULL; */
-}
-
 /* require calling thread tid by gettid() */
 int rte_sys_gettid(void)
 {
diff --git a/lib/eal/unix/eal_unix_thread.c b/lib/eal/unix/eal_unix_thread.c
new file mode 100644
index 0000000000..70b5ba6b98
--- /dev/null
+++ b/lib/eal/unix/eal_unix_thread.c
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2022 Red Hat, Inc.
+ */
+
+#include <errno.h>
+#include <unistd.h>
+
+#include <rte_debug.h>
+
+#include "eal_private.h"
+
+void
+eal_thread_wake_worker(unsigned int worker_id)
+{
+	int m2w = lcore_config[worker_id].pipe_main2worker[1];
+	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
+
+	do {
+		n = write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+
+	do {
+		n = read(w2m, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_wait_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
+	char c;
+	int n;
+
+	m2w = lcore_config[lcore_id].pipe_main2worker[0];
+	do {
+		n = read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
+
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
+
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
+}
diff --git a/lib/eal/unix/meson.build b/lib/eal/unix/meson.build
index a22ea7cabc..781505ca90 100644
--- a/lib/eal/unix/meson.build
+++ b/lib/eal/unix/meson.build
@@ -3,9 +3,10 @@
 
 sources += files(
         'eal_file.c',
+        'eal_filesystem.c',
+        'eal_firmware.c',
         'eal_unix_memory.c',
+        'eal_unix_thread.c',
         'eal_unix_timer.c',
-        'eal_firmware.c',
-        'eal_filesystem.c',
         'rte_thread.c',
 )
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index 95e96548de..f3c61b4456 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -11,124 +11,62 @@
 #include <rte_per_lcore.h>
 #include <rte_common.h>
 #include <rte_memory.h>
-#include <eal_thread.h>
 
 #include "eal_private.h"
+#include "eal_thread.h"
 #include "eal_windows.h"
 
-/*
- * Send a message to a worker lcore identified by worker_id to call a
- * function f with argument arg. Once the execution is done, the
- * remote lcore switches to WAIT state.
- */
-int
-rte_eal_remote_launch(lcore_function_t *f, void *arg, unsigned int worker_id)
+void
+eal_thread_wake_worker(unsigned int worker_id)
 {
-	int n;
-	char c = 0;
 	int m2w = lcore_config[worker_id].pipe_main2worker[1];
 	int w2m = lcore_config[worker_id].pipe_worker2main[0];
+	char c = 0;
+	int n;
 
-	/* Check if the worker is in 'WAIT' state. Use acquire order
-	 * since 'state' variable is used as the guard variable.
-	 */
-	if (__atomic_load_n(&lcore_config[worker_id].state,
-					__ATOMIC_ACQUIRE) != WAIT)
-		return -EBUSY;
-
-	lcore_config[worker_id].arg = arg;
-	/* Ensure that all the memory operations are completed
-	 * before the worker thread starts running the function.
-	 * Use worker thread function as the guard variable.
-	 */
-	__atomic_store_n(&lcore_config[worker_id].f, f, __ATOMIC_RELEASE);
-
-	/* send message */
-	n = 0;
-	while (n == 0 || (n < 0 && errno == EINTR))
+	do {
 		n = _write(m2w, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
 	if (n < 0)
 		rte_panic("cannot write on configuration pipe\n");
 
-	/* wait ack */
 	do {
 		n = _read(w2m, &c, 1);
 	} while (n < 0 && errno == EINTR);
-
 	if (n <= 0)
 		rte_panic("cannot read on configuration pipe\n");
-
-	return 0;
 }
 
-/* main loop of threads */
-void *
-eal_thread_loop(void *arg)
+void
+eal_thread_wait_command(void)
 {
-	unsigned int lcore_id = (uintptr_t)arg;
+	unsigned int lcore_id = rte_lcore_id();
+	int m2w;
 	char c;
-	int n, ret;
-	int m2w, w2m;
-	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	int n;
 
 	m2w = lcore_config[lcore_id].pipe_main2worker[0];
-	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _read(m2w, &c, 1);
+	} while (n < 0 && errno == EINTR);
+	if (n <= 0)
+		rte_panic("cannot read on configuration pipe\n");
+}
 
-	__rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);
-
-	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s])\n",
-		lcore_id, (uintptr_t)pthread_self(), cpuset);
-
-	/* read on our pipe to get commands */
-	while (1) {
-		lcore_function_t *f;
-		void *fct_arg;
-
-		/* wait command */
-		do {
-			n = _read(m2w, &c, 1);
-		} while (n < 0 && errno == EINTR);
-
-		if (n <= 0)
-			rte_panic("cannot read on configuration pipe\n");
-
-		/* Set the state to 'RUNNING'. Use release order
-		 * since 'state' variable is used as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, RUNNING,
-					__ATOMIC_RELEASE);
-
-		/* send ack */
-		n = 0;
-		while (n == 0 || (n < 0 && errno == EINTR))
-			n = _write(w2m, &c, 1);
-		if (n < 0)
-			rte_panic("cannot write on configuration pipe\n");
-
-		/* Load 'f' with acquire order to ensure that
-		 * the memory operations from the main thread
-		 * are accessed only after update to 'f' is visible.
-		 * Wait till the update to 'f' is visible to the worker.
-		 */
-		while ((f = __atomic_load_n(&lcore_config[lcore_id].f,
-			__ATOMIC_ACQUIRE)) == NULL)
-			rte_pause();
-
-		/* call the function and store the return value */
-		fct_arg = lcore_config[lcore_id].arg;
-		ret = f(fct_arg);
-		lcore_config[lcore_id].ret = ret;
-		lcore_config[lcore_id].f = NULL;
-		lcore_config[lcore_id].arg = NULL;
-
-		/* Store the state with release order to ensure that
-		 * the memory operations from the worker thread
-		 * are completed before the state is updated.
-		 * Use 'state' as the guard variable.
-		 */
-		__atomic_store_n(&lcore_config[lcore_id].state, WAIT,
-					__ATOMIC_RELEASE);
-	}
+void
+eal_thread_ack_command(void)
+{
+	unsigned int lcore_id = rte_lcore_id();
+	char c = 0;
+	int w2m;
+	int n;
+
+	w2m = lcore_config[lcore_id].pipe_worker2main[1];
+	do {
+		n = _write(w2m, &c, 1);
+	} while (n == 0 || (n < 0 && errno == EINTR));
+	if (n < 0)
+		rte_panic("cannot write on configuration pipe\n");
 }
 
 /* function to create threads */
-- 
2.23.0

Re: [PATCH v3 2/2] eal: factorize lcore main loop

[David Marchand]

On Tue, Apr 5, 2022 at 6:37 PM David Marchand <david.marchand@redhat.com> wrote:
>
> All OS implementations provide the same main loop.
> Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
> between main and threads and factorize the rest as common code.
> Thread id are now logged as string in a common format across OS.
>
> Note: libabigail flags this change as breaking ABI in clang builds:
>
> 1 function with some indirect sub-type change:
>
>   [C] 'function int rte_eal_remote_launch(int (void*)*, void*, unsigned
>       int)' at eal_common_launch.c:35:1 has some indirect sub-type
>       changes:
>     parameter 1 of type 'int (void*)*' changed:
>       in pointed to type 'function type int (void*)' at rte_launch.h:31:1:
>         entity changed from 'function type int (void*)' to 'typedef
>           lcore_function_t' at rte_launch.h:31:1
>         type size hasn't changed
>
> This is being investigated on libabigail side.
> For now, we don't have much choice but to waive reports on this symbol.
>
> Signed-off-by: David Marchand <david.marchand@redhat.com>
> Acked-by: Morten Brørup <mb@smartsharesystems.com>
> Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>

Added a note in the commitlog about Windows EAL threads affinity (from
a parallel discussion with Tyler), and applied.
Thanks.


-- 
David Marchand