[v2,1/2] power: introduce PM QoS API on CPU wide

diff --git a/doc/guides/prog_guide/power_man.rst b/doc/guides/prog_guide/power_man.rst
index f6674efe2d..3ff46f06c1 100644
--- a/doc/guides/prog_guide/power_man.rst
+++ b/doc/guides/prog_guide/power_man.rst
@@ -249,6 +249,28 @@  Get Num Pkgs
 Get Num Dies
   Get the number of die's on a given package.
 
+
+PM QoS
+------
+
+The deeper the idle state, the lower the power consumption, but the longer
+the resume time. Some service are delay sensitive and very except the low
+resume time, like interrupt packet receiving mode.
+
+And the "/sys/devices/system/cpu/cpuX/power/pm_qos_resume_latency_us" sysfs
+interface is used to set and get the resume latency limit on the cpuX for
+userspace. Each cpuidle governor in Linux select which idle state to enter
+based on this CPU resume latency in their idle task.
+
+The per-CPU PM QoS API can be used to set and get the CPU resume latency.
+
+The ``rte_power_qos_set_cpu_resume_latency()`` function can effect the work
+CPU's idle state selection and just allow to enter the shallowest idle state
+if set to zero (strict resume latency) for this CPU.
+
+The ``rte_power_qos_get_cpu_resume_latency()`` function can obtain the resume
+latency on specified CPU.
+
 References
 ----------
 
diff --git a/doc/guides/rel_notes/release_24_07.rst b/doc/guides/rel_notes/release_24_07.rst
index e68a53d757..7c0d36e389 100644
--- a/doc/guides/rel_notes/release_24_07.rst
+++ b/doc/guides/rel_notes/release_24_07.rst
@@ -89,6 +89,10 @@  New Features
 
   * Added SSE/NEON vector datapath.
 
+* **Introduce PM QoS interface.**
+
+  * Introduce PM QoS interface to low the delay after sleep.
+
 
 Removed Items
 -------------
diff --git a/lib/power/meson.build b/lib/power/meson.build
index b8426589b2..8222e178b0 100644
--- a/lib/power/meson.build
+++ b/lib/power/meson.build
@@ -23,12 +23,14 @@  sources = files(
         'rte_power.c',
         'rte_power_uncore.c',
         'rte_power_pmd_mgmt.c',
+        'rte_power_qos.c',
 )
 headers = files(
         'rte_power.h',
         'rte_power_guest_channel.h',
         'rte_power_pmd_mgmt.h',
         'rte_power_uncore.h',
+        'rte_power_qos.h',
 )
 if cc.has_argument('-Wno-cast-qual')
     cflags += '-Wno-cast-qual'
diff --git a/lib/power/rte_power_qos.c b/lib/power/rte_power_qos.c
new file mode 100644
index 0000000000..706f8432ee
--- /dev/null
+++ b/lib/power/rte_power_qos.c
@@ -0,0 +1,116 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2024 HiSilicon Limited
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <rte_log.h>
+
+#include "power_common.h"
+#include "rte_power_qos.h"
+
+#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	((int)(UINT32_MAX >> 1))
+#define PM_QOS_SYSFILE_RESUME_LATENCY_US	\
+	"/sys/devices/system/cpu/cpu%u/power/pm_qos_resume_latency_us"
+
+int
+rte_power_qos_set_cpu_resume_latency(uint16_t lcore_id, int latency)
+{
+	char buf[BUFSIZ] = {0};
+	FILE *f;
+	int ret;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		POWER_LOG(ERR, "Lcore id %u can not exceeds %u",
+			  lcore_id, RTE_MAX_LCORE - 1U);
+		return -EINVAL;
+	}
+
+	if (latency < 0) {
+		POWER_LOG(ERR, "latency should be greater than and equal to 0");
+		return -EINVAL;
+	}
+
+	ret = open_core_sysfs_file(&f, "w", PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+	if (ret != 0) {
+		POWER_LOG(ERR, "Failed to open "PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+		return ret;
+	}
+
+	/*
+	 * Based on the sysfs interface pm_qos_resume_latency_us under
+	 * @PM_QOS_SYSFILE_RESUME_LATENCY_US directory in kernel, their meanning
+	 * is as follows for different input string.
+	 * 1> the resume latency is 0 if the input is "n/a".
+	 * 2> the resume latency is no constraint if the input is "0".
+	 * 3> the resume latency is the actual value to be set.
+	 */
+	if (latency == 0)
+		sprintf(buf, "%s", "n/a");
+	else if (latency == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		sprintf(buf, "%u", 0);
+	else
+		sprintf(buf, "%u", latency);
+
+	ret = write_core_sysfs_s(f, buf);
+	if (ret != 0) {
+		POWER_LOG(ERR, "Failed to write "PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+		goto out;
+	}
+
+out:
+	if (f != NULL)
+		fclose(f);
+
+	return ret;
+}
+
+int
+rte_power_qos_get_cpu_resume_latency(uint16_t lcore_id)
+{
+	char buf[BUFSIZ];
+	int latency = -1;
+	FILE *f;
+	int ret;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		POWER_LOG(ERR, "Lcore id %u can not exceeds %u",
+				lcore_id, RTE_MAX_LCORE - 1U);
+		return -EINVAL;
+	}
+
+	ret = open_core_sysfs_file(&f, "r", PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+	if (ret != 0) {
+		POWER_LOG(ERR, "Failed to open "PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+		return ret;
+	}
+
+	ret = read_core_sysfs_s(f, buf, sizeof(buf));
+	if (ret != 0) {
+		POWER_LOG(ERR, "Failed to read "PM_QOS_SYSFILE_RESUME_LATENCY_US, lcore_id);
+		goto out;
+	}
+
+	/*
+	 * Based on the sysfs interface pm_qos_resume_latency_us under
+	 * @PM_QOS_SYSFILE_RESUME_LATENCY_US directory in kernel, their meanning
+	 * is as follows for different output string.
+	 * 1> the resume latency is 0 if the output is "n/a".
+	 * 2> the resume latency is no constraint if the output is "0".
+	 * 3> the resume latency is the actual value in used for other string.
+	 */
+	if (strcmp(buf, "n/a") == 0)
+		latency = 0;
+	else {
+		latency = strtoul(buf, NULL, 10);
+		latency = latency == 0 ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : latency;
+	}
+
+out:
+	if (f != NULL)
+		fclose(f);
+
+	return latency != -1 ? latency : ret;
+}
diff --git a/lib/power/rte_power_qos.h b/lib/power/rte_power_qos.h
new file mode 100644
index 0000000000..1ba9568d1b
--- /dev/null
+++ b/lib/power/rte_power_qos.h
@@ -0,0 +1,70 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2024 HiSilicon Limited
+ */
+
+#ifndef RTE_POWER_QOS_H
+#define RTE_POWER_QOS_H
+
+#include <rte_compat.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * @file rte_power_qos.h
+ *
+ * PM QoS API.
+ *
+ * The CPU-wide resume latency limit has a positive impact on this CPU's idle
+ * state selection in each cpuidle governor.
+ * Please see the PM QoS on CPU wide in the following link:
+ * https://www.kernel.org/doc/html/latest/admin-guide/abi-testing.html?highlight=pm_qos_resume_latency_us#abi-sys-devices-power-pm-qos-resume-latency-us
+ *
+ * The deeper the idle state, the lower the power consumption, but the
+ * longer the resume time. Some service are delay sensitive and very except the
+ * low resume time, like interrupt packet receiving mode.
+ *
+ * In these case, per-CPU PM QoS API can be used to control this CPU's idle
+ * state selection and limit just enter the shallowest idle state to low the
+ * delay after sleep by setting strict resume latency (zero value).
+ */
+
+#define PM_QOS_STRICT_LATENCY_VALUE             0
+#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT    ((int)(UINT32_MAX >> 1))
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * @param lcore_id
+ *   target logical core id
+ *
+ * @param latency
+ *   The latency should be greater than and equal to zero in microseconds unit.
+ *
+ * @return
+ *   0 on success. Otherwise negative value is returned.
+ */
+__rte_experimental
+int rte_power_qos_set_cpu_resume_latency(uint16_t lcore_id, int latency);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Get the current resume latency of this logical core.
+ * The default value in kernel is @see PM_QOS_RESUME_LATENCY_NO_CONSTRAINT if don't set it.
+ *
+ * @return
+ *   Negative value on failure.
+ *   >= 0 means the actual resume latency limit on this core.
+ */
+__rte_experimental
+int rte_power_qos_get_cpu_resume_latency(uint16_t lcore_id);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* RTE_POWER_QOS_H */
diff --git a/lib/power/version.map b/lib/power/version.map
index ad92a65f91..81b8ff11b7 100644
--- a/lib/power/version.map
+++ b/lib/power/version.map
@@ -51,4 +51,6 @@  EXPERIMENTAL {
 	rte_power_set_uncore_env;
 	rte_power_uncore_freqs;
 	rte_power_unset_uncore_env;
+	rte_power_qos_set_cpu_resume_latency;
+	rte_power_qos_get_cpu_resume_latency;
 };