[PATCH v3 1/2] eal: get/set thread priority per thread identifier

[Tyler Retzlaff <roretzla@linux.microsoft.com>]

Add functions for setting and getting the priority of a thread.
Priorities on multiple platforms are similarly determined by a priority
value and a priority class/policy.

Currently in DPDK most threads operate at the OS-default priority level
but there are cases when increasing the priority is useful. For
example, high performance applications may require elevated priority
levels.

For these reasons, EAL will expose two priority levels which are named
suggestively "normal" and "realtime_critical" and are computed as
follows:

  On Linux, the following mapping is created:
    RTE_THREAD_PRIORITY_NORMAL corresponds to
      * policy SCHED_OTHER
      * priority value:   (sched_get_priority_min(SCHED_OTHER) +
			   sched_get_priority_max(SCHED_OTHER))/2;
    RTE_THREAD_PRIORITY_REALTIME_CRITICAL corresponds to
      * policy SCHED_RR
      * priority value: sched_get_priority_max(SCHED_RR);

  On Windows, the following mapping is created:
    RTE_THREAD_PRIORITY_NORMAL corresponds to
      * class NORMAL_PRIORITY_CLASS
      * priority THREAD_PRIORITY_NORMAL
    RTE_THREAD_PRIORITY_REALTIME_CRITICAL corresponds to
      * class REALTIME_PRIORITY_CLASS (when running with privileges)
      * class HIGH_PRIORITY_CLASS (when running without privileges)
      * priority THREAD_PRIORITY_TIME_CRITICAL

Note that on Linux the resulting priority value will be 0, in
accordance to the documentation that mention the value should be 0 for
SCHED_OTHER policy.

Signed-off-by: Narcisa Vasile <navasile@linux.microsoft.com>
Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
 lib/eal/include/rte_thread.h |  50 +++++++++++++++++
 lib/eal/unix/rte_thread.c    | 101 +++++++++++++++++++++++++++++++++
 lib/eal/version.map          |   2 +
 lib/eal/windows/rte_thread.c | 130 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 283 insertions(+)

diff --git a/lib/eal/include/rte_thread.h b/lib/eal/include/rte_thread.h
index 7888f7a..9e261bf 100644
--- a/lib/eal/include/rte_thread.h
+++ b/lib/eal/include/rte_thread.h
@@ -31,6 +31,16 @@
 } rte_thread_t;
 
 /**
+ * Thread priority values.
+ */
+enum rte_thread_priority {
+	RTE_THREAD_PRIORITY_NORMAL            = 0,
+	/**< normal thread priority, the default */
+	RTE_THREAD_PRIORITY_REALTIME_CRITICAL = 1,
+	/**< highest thread priority allowed */
+};
+
+/**
  * TLS key type, an opaque pointer.
  */
 typedef struct eal_tls_key *rte_thread_key;
@@ -115,6 +125,46 @@ int rte_thread_get_affinity_by_id(rte_thread_t thread_id,
 #endif /* RTE_HAS_CPUSET */
 
 /**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Get the priority of a thread.
+ *
+ * @param thread_id
+ *   Id of the thread for which to get priority.
+ *
+ * @param priority
+ *   Location to store the retrieved priority.
+ *
+ * @return
+ *   On success, return 0.
+ *   On failure, return a positive errno-style error number.
+ */
+__rte_experimental
+int rte_thread_get_priority(rte_thread_t thread_id,
+		enum rte_thread_priority *priority);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Set the priority of a thread.
+ *
+ * @param thread_id
+ *   Id of the thread for which to set priority.
+ *
+ * @param priority
+ *   Priority value to be set.
+ *
+ * @return
+ *   On success, return 0.
+ *   On failure, return a positive errno-style error number.
+ */
+__rte_experimental
+int rte_thread_set_priority(rte_thread_t thread_id,
+		enum rte_thread_priority priority);
+
+/**
  * Create a TLS data key visible to all threads in the process.
  * the created key is later used to get/set a value.
  * and optional destructor can be set to be called when a thread exits.
diff --git a/lib/eal/unix/rte_thread.c b/lib/eal/unix/rte_thread.c
index 9e5fa47..2b19f4a 100644
--- a/lib/eal/unix/rte_thread.c
+++ b/lib/eal/unix/rte_thread.c
@@ -16,6 +16,64 @@ struct eal_tls_key {
 	pthread_key_t thread_index;
 };
 
+static int
+thread_map_priority_to_os_value(enum rte_thread_priority eal_pri,
+		int *os_pri, int *pol)
+{
+	/* Clear the output parameters */
+	*os_pri = sched_get_priority_min(SCHED_OTHER) - 1;
+	*pol = -1;
+
+	switch (eal_pri) {
+	case RTE_THREAD_PRIORITY_NORMAL:
+		*pol = SCHED_OTHER;
+
+		/*
+		 * Choose the middle of the range to represent
+		 * the priority 'normal'.
+		 * On Linux, this should be 0, since both
+		 * sched_get_priority_min/_max return 0 for SCHED_OTHER.
+		 */
+		*os_pri = (sched_get_priority_min(SCHED_OTHER) +
+			sched_get_priority_max(SCHED_OTHER))/2;
+		break;
+	case RTE_THREAD_PRIORITY_REALTIME_CRITICAL:
+		*pol = SCHED_RR;
+		*os_pri = sched_get_priority_max(SCHED_RR);
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "The requested priority value is invalid.\n");
+		return EINVAL;
+	}
+	return 0;
+}
+
+static int
+thread_map_os_priority_to_eal_priority(int policy, int os_pri,
+		enum rte_thread_priority *eal_pri)
+{
+	switch (policy) {
+	case SCHED_OTHER:
+		if (os_pri == (sched_get_priority_min(SCHED_OTHER) +
+				sched_get_priority_max(SCHED_OTHER))/2) {
+			*eal_pri = RTE_THREAD_PRIORITY_NORMAL;
+			return 0;
+		}
+		break;
+	case SCHED_RR:
+		if (os_pri == sched_get_priority_max(SCHED_RR)) {
+			*eal_pri = RTE_THREAD_PRIORITY_REALTIME_CRITICAL;
+			return 0;
+		}
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "The OS priority value does not map to an EAL-defined priority.\n");
+		return EINVAL;
+	}
+
+	return 0;
+}
+
 rte_thread_t
 rte_thread_self(void)
 {
@@ -29,6 +87,49 @@ struct eal_tls_key {
 }
 
 int
+rte_thread_get_priority(rte_thread_t thread_id,
+		enum rte_thread_priority *priority)
+{
+	int ret;
+	int policy;
+	struct sched_param param;
+
+	ret = pthread_getschedparam((pthread_t)thread_id.opaque_id, &policy,
+			&param);
+	if (ret != 0) {
+		RTE_LOG(DEBUG, EAL, "pthread_getschedparam failed\n");
+		goto cleanup;
+	}
+
+	return thread_map_os_priority_to_eal_priority(policy,
+			param.sched_priority, priority);
+
+cleanup:
+	return ret;
+}
+
+int
+rte_thread_set_priority(rte_thread_t thread_id,
+		enum rte_thread_priority priority)
+{
+	int ret;
+	int policy;
+	struct sched_param param;
+
+/* Realtime priority can cause crashes on non-Windows platforms. */
+	if (priority == RTE_THREAD_PRIORITY_REALTIME_CRITICAL)
+		return ENOTSUP;
+
+	ret = thread_map_priority_to_os_value(priority, &param.sched_priority,
+		&policy);
+	if (ret != 0)
+		return ret;
+
+	return pthread_setschedparam((pthread_t)thread_id.opaque_id,
+		policy, &param);
+}
+
+int
 rte_thread_key_create(rte_thread_key *key, void (*destructor)(void *))
 {
 	int err;
diff --git a/lib/eal/version.map b/lib/eal/version.map
index d49e30b..ab27a4b 100644
--- a/lib/eal/version.map
+++ b/lib/eal/version.map
@@ -423,8 +423,10 @@ EXPERIMENTAL {
 
 	# added in 22.07
 	rte_thread_get_affinity_by_id;
+	rte_thread_get_priority;
 	rte_thread_self;
 	rte_thread_set_affinity_by_id;
+	rte_thread_set_priority;
 };
 
 INTERNAL {
diff --git a/lib/eal/windows/rte_thread.c b/lib/eal/windows/rte_thread.c
index a616703..495225e 100644
--- a/lib/eal/windows/rte_thread.c
+++ b/lib/eal/windows/rte_thread.c
@@ -61,6 +61,58 @@ struct eal_tls_key {
 	return thread_translate_win32_error(error);
 }
 
+static int
+thread_map_priority_to_os_value(enum rte_thread_priority eal_pri,
+		int *os_pri, DWORD *pri_class)
+{
+	/* Clear the output parameters */
+	*os_pri = -1;
+	*pri_class = -1;
+
+	switch (eal_pri) {
+	case RTE_THREAD_PRIORITY_NORMAL:
+		*pri_class = NORMAL_PRIORITY_CLASS;
+		*os_pri = THREAD_PRIORITY_NORMAL;
+		break;
+	case RTE_THREAD_PRIORITY_REALTIME_CRITICAL:
+		*pri_class = REALTIME_PRIORITY_CLASS;
+		*os_pri = THREAD_PRIORITY_TIME_CRITICAL;
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "The requested priority value is invalid.\n");
+		return EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+thread_map_os_priority_to_eal_value(int os_pri, DWORD pri_class,
+		enum rte_thread_priority *eal_pri)
+{
+	switch (pri_class) {
+	case NORMAL_PRIORITY_CLASS:
+		if (os_pri == THREAD_PRIORITY_NORMAL) {
+			*eal_pri = RTE_THREAD_PRIORITY_NORMAL;
+			return 0;
+		}
+		break;
+	case HIGH_PRIORITY_CLASS:
+		RTE_LOG(WARNING, EAL, "The OS priority class is high not real-time.\n");
+		/* FALLTHROUGH */
+	case REALTIME_PRIORITY_CLASS:
+		if (os_pri == THREAD_PRIORITY_TIME_CRITICAL) {
+			*eal_pri = RTE_THREAD_PRIORITY_REALTIME_CRITICAL;
+			return 0;
+		}
+		break;
+	default:
+		RTE_LOG(DEBUG, EAL, "The OS priority value does not map to an EAL-defined priority.\n");
+		return EINVAL;
+	}
+	return 0;
+}
+
 rte_thread_t
 rte_thread_self(void)
 {
@@ -72,6 +124,84 @@ struct eal_tls_key {
 }
 
 int
+rte_thread_get_priority(rte_thread_t thread_id,
+		enum rte_thread_priority *priority)
+{
+	HANDLE thread_handle = NULL;
+	DWORD pri_class;
+	int os_pri;
+	int ret;
+
+	pri_class = GetPriorityClass(GetCurrentProcess());
+	if (pri_class == 0) {
+		ret = thread_log_last_error("GetPriorityClass()");
+		goto cleanup;
+	}
+
+	thread_handle = OpenThread(THREAD_SET_INFORMATION |
+			THREAD_QUERY_INFORMATION, FALSE, thread_id.opaque_id);
+	if (thread_handle == NULL) {
+		ret = thread_log_last_error("OpenThread()");
+		goto cleanup;
+	}
+
+	os_pri = GetThreadPriority(thread_handle);
+	if (os_pri == THREAD_PRIORITY_ERROR_RETURN) {
+		ret = thread_log_last_error("GetThreadPriority()");
+		goto cleanup;
+	}
+
+	ret = thread_map_os_priority_to_eal_value(os_pri, pri_class, priority);
+	if (ret != 0)
+		goto cleanup;
+
+cleanup:
+	if (thread_handle != NULL)
+		CloseHandle(thread_handle);
+
+	return ret;
+}
+
+int
+rte_thread_set_priority(rte_thread_t thread_id,
+			enum rte_thread_priority priority)
+{
+	HANDLE thread_handle;
+	DWORD priority_class;
+	int os_priority;
+	int ret = 0;
+
+	thread_handle = OpenThread(THREAD_SET_INFORMATION |
+		THREAD_QUERY_INFORMATION, FALSE,
+		thread_id.opaque_id);
+	if (thread_handle == NULL) {
+		ret = thread_log_last_error("OpenThread()");
+		goto cleanup;
+	}
+
+	ret = thread_map_priority_to_os_value(priority, &os_priority,
+		&priority_class);
+	if (ret != 0)
+		goto cleanup;
+
+	if (!SetPriorityClass(GetCurrentProcess(), priority_class)) {
+		ret = thread_log_last_error("SetPriorityClass()");
+		goto cleanup;
+	}
+
+	if (!SetThreadPriority(thread_handle, os_priority)) {
+		ret = thread_log_last_error("SetThreadPriority()");
+		goto cleanup;
+	}
+
+cleanup:
+	if (thread_handle != NULL)
+		CloseHandle(thread_handle);
+
+	return ret;
+}
+
+int
 rte_thread_key_create(rte_thread_key *key,
 		__rte_unused void (*destructor)(void *))
 {
-- 
1.8.3.1