[dpdk-dev] [PATCH v2 1/2] power: add support for cppc cpufreq

[Richael Zhuang <richael.zhuang@arm.com>]

Currently in DPDK only acpi_cpufreq and pstate_cpufreq drivers are
supported, which are both not available on arm64 platforms. Add
support for cppc_cpufreq driver which works on most arm64 platforms.

Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
---
 app/test/test_power.c          |   3 +-
 app/test/test_power_cpufreq.c  |   3 +-
 lib/power/meson.build          |   1 +
 lib/power/power_cppc_cpufreq.c | 632 +++++++++++++++++++++++++++++++++
 lib/power/power_cppc_cpufreq.h | 229 ++++++++++++
 lib/power/rte_power.c          |  26 ++
 lib/power/rte_power.h          |   2 +-
 7 files changed, 893 insertions(+), 3 deletions(-)
 create mode 100644 lib/power/power_cppc_cpufreq.c
 create mode 100644 lib/power/power_cppc_cpufreq.h

diff --git a/app/test/test_power.c b/app/test/test_power.c
index da1d67c0a..b7b556134 100644
--- a/app/test/test_power.c
+++ b/app/test/test_power.c
@@ -133,7 +133,8 @@ test_power(void)
 	/* Perform tests for valid environments.*/
 	const enum power_management_env envs[] = {PM_ENV_ACPI_CPUFREQ,
 			PM_ENV_KVM_VM,
-			PM_ENV_PSTATE_CPUFREQ};
+			PM_ENV_PSTATE_CPUFREQ,
+			PM_ENV_CPPC_CPUFREQ};
 
 	unsigned int i;
 	for (i = 0; i < RTE_DIM(envs); ++i) {
diff --git a/app/test/test_power_cpufreq.c b/app/test/test_power_cpufreq.c
index f753d24ac..87d07191d 100644
--- a/app/test/test_power_cpufreq.c
+++ b/app/test/test_power_cpufreq.c
@@ -470,7 +470,8 @@ test_power_cpufreq(void)
 
 	/* Test environment configuration */
 	env = rte_power_get_env();
-	if ((env != PM_ENV_ACPI_CPUFREQ) && (env != PM_ENV_PSTATE_CPUFREQ)) {
+	if ((env != PM_ENV_ACPI_CPUFREQ) && (env != PM_ENV_PSTATE_CPUFREQ) &&
+			(env != PM_ENV_CPPC_CPUFREQ)) {
 		printf("Unexpectedly got an environment other than ACPI/PSTATE\n");
 		goto fail_all;
 	}
diff --git a/lib/power/meson.build b/lib/power/meson.build
index 74c5f3a29..4a5b07292 100644
--- a/lib/power/meson.build
+++ b/lib/power/meson.build
@@ -21,6 +21,7 @@ sources = files(
         'rte_power.c',
         'rte_power_empty_poll.c',
         'rte_power_pmd_mgmt.c',
+	'power_cppc_cpufreq.c',
 )
 headers = files(
         'rte_power.h',
diff --git a/lib/power/power_cppc_cpufreq.c b/lib/power/power_cppc_cpufreq.c
new file mode 100644
index 000000000..c4a71a3d3
--- /dev/null
+++ b/lib/power/power_cppc_cpufreq.c
@@ -0,0 +1,632 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Arm Limited
+ */
+
+#include <rte_memcpy.h>
+#include <rte_memory.h>
+
+#include "power_cppc_cpufreq.h"
+#include "power_common.h"
+
+/* macros used for rounding frequency to nearest 100000 */
+#define FREQ_ROUNDING_DELTA 50000
+#define ROUND_FREQ_TO_N_100000 100000
+
+/* the unit of highest_perf and nominal_perf differs on different arm platforms.
+ * For highest_perf, it maybe 300 or 3000000, both means 3.0GHz.
+ */
+#define UNIT_DIFF 10000
+
+#define POWER_CONVERT_TO_DECIMAL 10
+
+#define POWER_GOVERNOR_USERSPACE "userspace"
+#define POWER_SYSFILE_SETSPEED   \
+		"/sys/devices/system/cpu/cpu%u/cpufreq/scaling_setspeed"
+#define POWER_SYSFILE_SCALING_MAX_FREQ \
+		"/sys/devices/system/cpu/cpu%u/cpufreq/scaling_max_freq"
+#define POWER_SYSFILE_SCALING_MIN_FREQ  \
+		"/sys/devices/system/cpu/cpu%u/cpufreq/scaling_min_freq"
+#define POWER_SYSFILE_HIGHEST_PERF \
+		"/sys/devices/system/cpu/cpu%u/acpi_cppc/highest_perf"
+#define POWER_SYSFILE_NOMINAL_PERF \
+		"/sys/devices/system/cpu/cpu%u/acpi_cppc/nominal_perf"
+#define POWER_SYSFILE_SYS_MAX \
+		"/sys/devices/system/cpu/cpu%u/cpufreq/cpuinfo_max_freq"
+
+#define POWER_CPPC_DRIVER "cppc-cpufreq"
+#define BUS_FREQ     100000
+
+enum power_state {
+	POWER_IDLE = 0,
+	POWER_ONGOING,
+	POWER_USED,
+	POWER_UNKNOWN
+};
+
+/**
+ * Power info per lcore.
+ */
+struct cppc_power_info {
+	unsigned int lcore_id;                   /**< Logical core id */
+	uint32_t state;                      /**< Power in use state */
+	FILE *f;                             /**< FD of scaling_setspeed */
+	char governor_ori[32];               /**< Original governor name */
+	uint32_t curr_idx;                   /**< Freq index in freqs array */
+	uint32_t highest_perf;		     /**< system wide max freq */
+	uint32_t nominal_perf;		     /**< system wide nominal freq */
+	uint16_t turbo_available;            /**< Turbo Boost available */
+	uint16_t turbo_enable;               /**< Turbo Boost enable/disable */
+	uint32_t nb_freqs;                   /**< number of available freqs */
+	uint32_t freqs[RTE_MAX_LCORE_FREQS]; /**< Frequency array */
+} __rte_cache_aligned;
+
+static struct cppc_power_info lcore_power_info[RTE_MAX_LCORE];
+
+/**
+ * It is to set specific freq for specific logical core, according to the index
+ * of supported frequencies.
+ */
+static int
+set_freq_internal(struct cppc_power_info *pi, uint32_t idx)
+{
+	if (idx >= RTE_MAX_LCORE_FREQS || idx >= pi->nb_freqs) {
+		RTE_LOG(ERR, POWER, "Invalid frequency index %u, which "
+				"should be less than %u\n", idx, pi->nb_freqs);
+		return -1;
+	}
+
+	/* Check if it is the same as current */
+	if (idx == pi->curr_idx)
+		return 0;
+
+	POWER_DEBUG_TRACE("Frequency[%u] %u to be set for lcore %u\n",
+			idx, pi->freqs[idx], pi->lcore_id);
+	if (fseek(pi->f, 0, SEEK_SET) < 0) {
+		RTE_LOG(ERR, POWER, "Fail to set file position indicator to 0 "
+				"for setting frequency for lcore %u\n", pi->lcore_id);
+		return -1;
+	}
+	if (fprintf(pi->f, "%u", pi->freqs[idx]) < 0) {
+		RTE_LOG(ERR, POWER, "Fail to write new frequency for "
+				"lcore %u\n", pi->lcore_id);
+		return -1;
+	}
+	fflush(pi->f);
+	pi->curr_idx = idx;
+
+	return 1;
+}
+
+/**
+ * It is to check the current scaling governor by reading sys file, and then
+ * set it into 'userspace' if it is not by writing the sys file. The original
+ * governor will be saved for rolling back.
+ */
+static int
+power_set_governor_userspace(struct cppc_power_info *pi)
+{
+	return power_set_governor(pi->lcore_id, POWER_GOVERNOR_USERSPACE,
+			pi->governor_ori, sizeof(pi->governor_ori));
+}
+
+static int
+power_check_turbo(struct cppc_power_info *pi)
+{
+	FILE *f_nom, *f_max, *f_cmax;
+	int ret = -1;
+	uint32_t nominal_perf = 0, highest_perf = 0, cpuinfo_max_freq = 0;
+
+	open_core_sysfs_file(POWER_SYSFILE_HIGHEST_PERF, pi->lcore_id, "r",
+			&f_max);
+	FOPEN_OR_ERR_GOTO(f_max, err);
+
+	open_core_sysfs_file(POWER_SYSFILE_NOMINAL_PERF, pi->lcore_id, "r",
+			&f_nom);
+	FOPEN_OR_ERR_GOTO(f_nom, err);
+
+	open_core_sysfs_file(POWER_SYSFILE_SYS_MAX, pi->lcore_id, "r",
+			&f_cmax);
+	FOPEN_OR_ERR_GOTO(f_cmax, err);
+
+	ret = read_core_sysfs_u32(f_max, &highest_perf);
+	FOPS_OR_ERR_GOTO(ret, err);
+
+	ret = read_core_sysfs_u32(f_nom, &nominal_perf);
+	FOPS_OR_ERR_GOTO(ret, err);
+
+	ret = read_core_sysfs_u32(f_cmax, &cpuinfo_max_freq);
+	FOPS_OR_ERR_GOTO(ret, err);
+
+	pi->highest_perf = highest_perf;
+	pi->nominal_perf = nominal_perf;
+
+	if ((highest_perf > nominal_perf) && ((cpuinfo_max_freq == highest_perf) ||
+				cpuinfo_max_freq == highest_perf * UNIT_DIFF)) {
+		pi->turbo_available = 1;
+		pi->turbo_enable = 1;
+		ret = 0;
+		POWER_DEBUG_TRACE("Lcore %u can do Turbo Boost! highest perf %u, "
+				"nominal perf %u\n",
+				pi->lcore_id, highest_perf, nominal_perf);
+	} else {
+		pi->turbo_available = 0;
+		pi->turbo_enable = 0;
+		POWER_DEBUG_TRACE("Lcore %u Turbo not available! highest perf %u, "
+				"nominal perf %u\n",
+				pi->lcore_id, highest_perf, nominal_perf);
+	}
+
+err:
+	if (f_max != NULL)
+		fclose(f_max);
+	if (f_nom != NULL)
+		fclose(f_nom);
+	if (f_cmax != NULL)
+		fclose(f_cmax);
+
+	return ret;
+}
+
+/**
+ * It is to get the available frequencies of the specific lcore by reading the
+ * sys file.
+ */
+static int
+power_get_available_freqs(struct cppc_power_info *pi)
+{
+	FILE *f_min, *f_max;
+	int ret = -1;
+	uint32_t scaling_min_freq = 0, scaling_max_freq = 0, nominal_perf = 0;
+	uint32_t i, num_freqs = 0;
+
+	open_core_sysfs_file(POWER_SYSFILE_SCALING_MAX_FREQ, pi->lcore_id, "r",
+			&f_max);
+	FOPEN_OR_ERR_GOTO(f_max, out);
+
+	open_core_sysfs_file(POWER_SYSFILE_SCALING_MIN_FREQ, pi->lcore_id, "r",
+			&f_min);
+	FOPEN_OR_ERR_GOTO(f_min, out);
+
+	ret = read_core_sysfs_u32(f_max, &scaling_max_freq);
+	FOPS_OR_ERR_GOTO(ret, out);
+
+	ret = read_core_sysfs_u32(f_min, &scaling_min_freq);
+	FOPS_OR_ERR_GOTO(ret, out);
+
+	power_check_turbo(pi);
+
+	if (scaling_max_freq < scaling_min_freq)
+		goto out;
+
+	/* If turbo is available then there is one extra freq bucket
+	 * to store the sys max freq which value is scaling_max_freq
+	 */
+	nominal_perf = (pi->nominal_perf < UNIT_DIFF) ?
+			pi->nominal_perf * UNIT_DIFF : pi->nominal_perf;
+	num_freqs = (nominal_perf - scaling_min_freq) / BUS_FREQ + 1 +
+		pi->turbo_available;
+
+	/* Generate the freq bucket array. */
+	for (i = 0, pi->nb_freqs = 0; i < num_freqs; i++) {
+		if ((i == 0) && pi->turbo_available)
+			pi->freqs[pi->nb_freqs++] = scaling_max_freq;
+		else
+			pi->freqs[pi->nb_freqs++] =
+			nominal_perf - (i - pi->turbo_available) * BUS_FREQ;
+	}
+
+	ret = 0;
+
+	POWER_DEBUG_TRACE("%d frequency(s) of lcore %u are available\n",
+			num_freqs, pi->lcore_id);
+
+out:
+	if (f_min != NULL)
+		fclose(f_min);
+	if (f_max != NULL)
+		fclose(f_max);
+
+	return ret;
+}
+
+/**
+ * It is to fopen the sys file for the future setting the lcore frequency.
+ */
+static int
+power_init_for_setting_freq(struct cppc_power_info *pi)
+{
+	FILE *f;
+	char buf[BUFSIZ];
+	uint32_t i, freq;
+	int ret;
+
+	open_core_sysfs_file(POWER_SYSFILE_SETSPEED, pi->lcore_id, "rw+",
+			&f);
+	FOPEN_OR_ERR_GOTO(f, err);
+
+	ret = read_core_sysfs_s(f, buf, sizeof(buf));
+	FOPS_OR_ERR_GOTO(ret, err);
+
+	freq = strtoul(buf, NULL, POWER_CONVERT_TO_DECIMAL);
+
+	/* convert the frequency to nearest 100000 value
+	 * Ex: if freq=1396789 then freq_conv=1400000
+	 * Ex: if freq=800030 then freq_conv=800000
+	 */
+	unsigned int freq_conv = 0;
+	freq_conv = (freq + FREQ_ROUNDING_DELTA)
+				/ ROUND_FREQ_TO_N_100000;
+	freq_conv = freq_conv * ROUND_FREQ_TO_N_100000;
+
+	for (i = 0; i < pi->nb_freqs; i++) {
+		if (freq_conv == pi->freqs[i]) {
+			pi->curr_idx = i;
+			pi->f = f;
+			return 0;
+		}
+	}
+
+err:
+	if (f != NULL)
+		fclose(f);
+
+	return -1;
+}
+
+int
+power_cppc_cpufreq_check_supported(void)
+{
+	return cpufreq_check_scaling_driver(POWER_CPPC_DRIVER);
+}
+
+int
+power_cppc_cpufreq_init(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+	uint32_t exp_state;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Lcore id %u can not exceeds %u\n",
+				lcore_id, RTE_MAX_LCORE - 1U);
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+	exp_state = POWER_IDLE;
+	/* The power in use state works as a guard variable between
+	 * the CPU frequency control initialization and exit process.
+	 * The ACQUIRE memory ordering here pairs with the RELEASE
+	 * ordering below as lock to make sure the frequency operations
+	 * in the critical section are done under the correct state.
+	 */
+	if (!__atomic_compare_exchange_n(&(pi->state), &exp_state,
+					POWER_ONGOING, 0,
+					__ATOMIC_ACQUIRE, __ATOMIC_RELAXED)) {
+		RTE_LOG(INFO, POWER, "Power management of lcore %u is "
+				"in use\n", lcore_id);
+		return -1;
+	}
+
+	pi->lcore_id = lcore_id;
+	/* Check and set the governor */
+	if (power_set_governor_userspace(pi) < 0) {
+		RTE_LOG(ERR, POWER, "Cannot set governor of lcore %u to "
+				"userspace\n", lcore_id);
+		goto fail;
+	}
+
+	/* Get the available frequencies */
+	if (power_get_available_freqs(pi) < 0) {
+		RTE_LOG(ERR, POWER, "Cannot get available frequencies of "
+				"lcore %u\n", lcore_id);
+		goto fail;
+	}
+
+	/* Init for setting lcore frequency */
+	if (power_init_for_setting_freq(pi) < 0) {
+		RTE_LOG(ERR, POWER, "Cannot init for setting frequency for "
+				"lcore %u\n", lcore_id);
+		goto fail;
+	}
+
+	/* Set freq to max by default */
+	if (power_cppc_cpufreq_freq_max(lcore_id) < 0) {
+		RTE_LOG(ERR, POWER, "Cannot set frequency of lcore %u "
+				"to max\n", lcore_id);
+		goto fail;
+	}
+
+	RTE_LOG(INFO, POWER, "Initialized successfully for lcore %u "
+			"power management\n", lcore_id);
+
+	__atomic_store_n(&(pi->state), POWER_USED, __ATOMIC_RELEASE);
+
+	return 0;
+
+fail:
+	__atomic_store_n(&(pi->state), POWER_UNKNOWN, __ATOMIC_RELEASE);
+	return -1;
+}
+
+/**
+ * It is to check the governor and then set the original governor back if
+ * needed by writing the sys file.
+ */
+static int
+power_set_governor_original(struct cppc_power_info *pi)
+{
+	return power_set_governor(pi->lcore_id, pi->governor_ori, NULL, 0);
+}
+
+int
+power_cppc_cpufreq_exit(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+	uint32_t exp_state;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Lcore id %u can not exceeds %u\n",
+				lcore_id, RTE_MAX_LCORE - 1U);
+		return -1;
+	}
+	pi = &lcore_power_info[lcore_id];
+	exp_state = POWER_USED;
+	/* The power in use state works as a guard variable between
+	 * the CPU frequency control initialization and exit process.
+	 * The ACQUIRE memory ordering here pairs with the RELEASE
+	 * ordering below as lock to make sure the frequency operations
+	 * in the critical section are done under the correct state.
+	 */
+	if (!__atomic_compare_exchange_n(&(pi->state), &exp_state,
+					POWER_ONGOING, 0,
+					__ATOMIC_ACQUIRE, __ATOMIC_RELAXED)) {
+		RTE_LOG(INFO, POWER, "Power management of lcore %u is "
+				"not used\n", lcore_id);
+		return -1;
+	}
+
+	/* Close FD of setting freq */
+	fclose(pi->f);
+	pi->f = NULL;
+
+	/* Set the governor back to the original */
+	if (power_set_governor_original(pi) < 0) {
+		RTE_LOG(ERR, POWER, "Cannot set the governor of %u back "
+				"to the original\n", lcore_id);
+		goto fail;
+	}
+
+	RTE_LOG(INFO, POWER, "Power management of lcore %u has exited from "
+			"'userspace' mode and been set back to the "
+			"original\n", lcore_id);
+	__atomic_store_n(&(pi->state), POWER_IDLE, __ATOMIC_RELEASE);
+
+	return 0;
+
+fail:
+	__atomic_store_n(&(pi->state), POWER_UNKNOWN, __ATOMIC_RELEASE);
+
+	return -1;
+}
+
+uint32_t
+power_cppc_cpufreq_freqs(unsigned int lcore_id, uint32_t *freqs, uint32_t num)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return 0;
+	}
+
+	if (freqs == NULL) {
+		RTE_LOG(ERR, POWER, "NULL buffer supplied\n");
+		return 0;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+	if (num < pi->nb_freqs) {
+		RTE_LOG(ERR, POWER, "Buffer size is not enough\n");
+		return 0;
+	}
+	rte_memcpy(freqs, pi->freqs, pi->nb_freqs * sizeof(uint32_t));
+
+	return pi->nb_freqs;
+}
+
+uint32_t
+power_cppc_cpufreq_get_freq(unsigned int lcore_id)
+{
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return RTE_POWER_INVALID_FREQ_INDEX;
+	}
+
+	return lcore_power_info[lcore_id].curr_idx;
+}
+
+int
+power_cppc_cpufreq_set_freq(unsigned int lcore_id, uint32_t index)
+{
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	return set_freq_internal(&(lcore_power_info[lcore_id]), index);
+}
+
+int
+power_cppc_cpufreq_freq_down(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+	if (pi->curr_idx + 1 == pi->nb_freqs)
+		return 0;
+
+	/* Frequencies in the array are from high to low. */
+	return set_freq_internal(pi, pi->curr_idx + 1);
+}
+
+int
+power_cppc_cpufreq_freq_up(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+	if (pi->curr_idx == 0 || (pi->curr_idx == 1 &&
+		pi->turbo_available && !pi->turbo_enable))
+		return 0;
+
+	/* Frequencies in the array are from high to low. */
+	return set_freq_internal(pi, pi->curr_idx - 1);
+}
+
+int
+power_cppc_cpufreq_freq_max(unsigned int lcore_id)
+{
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	/* Frequencies in the array are from high to low. */
+	if (lcore_power_info[lcore_id].turbo_available) {
+		if (lcore_power_info[lcore_id].turbo_enable)
+			/* Set to Turbo */
+			return set_freq_internal(
+				&lcore_power_info[lcore_id], 0);
+		else
+			/* Set to max non-turbo */
+			return set_freq_internal(
+				&lcore_power_info[lcore_id], 1);
+	} else
+		return set_freq_internal(&lcore_power_info[lcore_id], 0);
+}
+
+int
+power_cppc_cpufreq_freq_min(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+
+	/* Frequencies in the array are from high to low. */
+	return set_freq_internal(pi, pi->nb_freqs - 1);
+}
+
+int
+power_cppc_turbo_status(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+
+	return pi->turbo_enable;
+}
+
+int
+power_cppc_enable_turbo(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+
+	if (pi->turbo_available)
+		pi->turbo_enable = 1;
+	else {
+		pi->turbo_enable = 0;
+		RTE_LOG(ERR, POWER,
+			"Failed to enable turbo on lcore %u\n",
+			lcore_id);
+		return -1;
+	}
+
+	/* TODO: must set to max once enbling Turbo? Considering add condition:
+	 * if ((pi->turbo_available) && (pi->curr_idx <= 1))
+	 */
+	/* Max may have changed, so call to max function */
+	if (power_cppc_cpufreq_freq_max(lcore_id) < 0) {
+		RTE_LOG(ERR, POWER,
+			"Failed to set frequency of lcore %u to max\n",
+			lcore_id);
+		return -1;
+	}
+
+	return 0;
+}
+
+int
+power_cppc_disable_turbo(unsigned int lcore_id)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+
+	pi->turbo_enable = 0;
+
+	if ((pi->turbo_available) && (pi->curr_idx <= 1)) {
+		/* Try to set freq to max by default coming out of turbo */
+		if (power_cppc_cpufreq_freq_max(lcore_id) < 0) {
+			RTE_LOG(ERR, POWER,
+				"Failed to set frequency of lcore %u to max\n",
+				lcore_id);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+int
+power_cppc_get_capabilities(unsigned int lcore_id,
+		struct rte_power_core_capabilities *caps)
+{
+	struct cppc_power_info *pi;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+	if (caps == NULL) {
+		RTE_LOG(ERR, POWER, "Invalid argument\n");
+		return -1;
+	}
+
+	pi = &lcore_power_info[lcore_id];
+	caps->capabilities = 0;
+	caps->turbo = !!(pi->turbo_available);
+
+	return 0;
+}
diff --git a/lib/power/power_cppc_cpufreq.h b/lib/power/power_cppc_cpufreq.h
new file mode 100644
index 000000000..427ce4f83
--- /dev/null
+++ b/lib/power/power_cppc_cpufreq.h
@@ -0,0 +1,229 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Arm Limited
+ */
+
+#ifndef _POWER_CPPC_CPUFREQ_H
+#define _POWER_CPPC_CPUFREQ_H
+
+/**
+ * @file
+ * RTE Power Management via userspace CPPC cpufreq
+ */
+
+#include <rte_common.h>
+#include <rte_byteorder.h>
+#include <rte_log.h>
+#include <rte_string_fns.h>
+#include "rte_power.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Check if CPPC power management is supported.
+ *
+ * @return
+ *   - 1 if supported
+ *   - 0 if unsupported
+ *   - -1 if error, with rte_errno indicating reason for error.
+ */
+int power_cppc_cpufreq_check_supported(void);
+
+/**
+ * Initialize power management for a specific lcore. It will check and set the
+ * governor to userspace for the lcore, get the available frequencies, and
+ * prepare to set new lcore frequency.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 on success.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_init(unsigned int lcore_id);
+
+/**
+ * Exit power management on a specific lcore. It will set the governor to which
+ * is before initialized.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 on success.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_exit(unsigned int lcore_id);
+
+/**
+ * Get the available frequencies of a specific lcore. The return value will be
+ * the minimal one of the total number of available frequencies and the number
+ * of buffer. The index of available frequencies used in other interfaces
+ * should be in the range of 0 to this return value.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ * @param freqs
+ *  The buffer array to save the frequencies.
+ * @param num
+ *  The number of frequencies to get.
+ *
+ * @return
+ *  The number of available frequencies.
+ */
+uint32_t power_cppc_cpufreq_freqs(unsigned int lcore_id, uint32_t *freqs,
+		uint32_t num);
+
+/**
+ * Return the current index of available frequencies of a specific lcore. It
+ * will return 'RTE_POWER_INVALID_FREQ_INDEX = (~0)' if error.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  The current index of available frequencies.
+ */
+uint32_t power_cppc_cpufreq_get_freq(unsigned int lcore_id);
+
+/**
+ * Set the new frequency for a specific lcore by indicating the index of
+ * available frequencies.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ * @param index
+ *  The index of available frequencies.
+ *
+ * @return
+ *  - 1 on success with frequency changed.
+ *  - 0 on success without frequency changed.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_set_freq(unsigned int lcore_id, uint32_t index);
+
+/**
+ * Scale up the frequency of a specific lcore according to the available
+ * frequencies.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success with frequency changed.
+ *  - 0 on success without frequency changed.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_freq_up(unsigned int lcore_id);
+
+/**
+ * Scale down the frequency of a specific lcore according to the available
+ * frequencies.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success with frequency changed.
+ *  - 0 on success without frequency changed.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_freq_down(unsigned int lcore_id);
+
+/**
+ * Scale up the frequency of a specific lcore to the highest according to the
+ * available frequencies.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success with frequency changed.
+ *  - 0 on success without frequency changed.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_freq_max(unsigned int lcore_id);
+
+/**
+ * Scale down the frequency of a specific lcore to the lowest according to the
+ * available frequencies.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success with frequency changed.
+ *  - 0 on success without frequency changed.
+ *  - Negative on error.
+ */
+int power_cppc_cpufreq_freq_min(unsigned int lcore_id);
+
+/**
+ * Get the turbo status of a specific lcore.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 Turbo Boost is enabled on this lcore.
+ *  - 0 Turbo Boost is disabled on this lcore.
+ *  - Negative on error.
+ */
+int power_cppc_turbo_status(unsigned int lcore_id);
+
+/**
+ * Enable Turbo Boost on a specific lcore.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 Turbo Boost is enabled successfully on this lcore.
+ *  - Negative on error.
+ */
+int power_cppc_enable_turbo(unsigned int lcore_id);
+
+/**
+ * Disable Turbo Boost on a specific lcore.
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 Turbo Boost disabled successfully on this lcore.
+ *  - Negative on error.
+ */
+int power_cppc_disable_turbo(unsigned int lcore_id);
+
+/**
+ * Returns power capabilities for a specific lcore.
+ *
+ * @param lcore_id
+ *  lcore id.
+ * @param caps
+ *  pointer to rte_power_core_capabilities object.
+ *
+ * @return
+ *  - 0 on success.
+ *  - Negative on error.
+ */
+int power_cppc_get_capabilities(unsigned int lcore_id,
+		struct rte_power_core_capabilities *caps);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/lib/power/rte_power.c b/lib/power/rte_power.c
index 98eaba915..3d51ff8be 100644
--- a/lib/power/rte_power.c
+++ b/lib/power/rte_power.c
@@ -10,6 +10,7 @@
 #include "power_kvm_vm.h"
 #include "power_pstate_cpufreq.h"
 #include "power_common.h"
+#include "power_cppc_cpufreq.h"
 
 enum power_management_env global_default_env = PM_ENV_NOT_SET;
 
@@ -54,6 +55,8 @@ rte_power_check_env_supported(enum power_management_env env)
 		return power_pstate_cpufreq_check_supported();
 	case PM_ENV_KVM_VM:
 		return power_kvm_vm_check_supported();
+	case PM_ENV_CPPC_CPUFREQ:
+		return power_cppc_cpufreq_check_supported();
 	default:
 		rte_errno = EINVAL;
 		return -1;
@@ -110,6 +113,18 @@ rte_power_set_env(enum power_management_env env)
 		rte_power_freq_disable_turbo = power_pstate_disable_turbo;
 		rte_power_get_capabilities = power_pstate_get_capabilities;
 
+	} else if (env == PM_ENV_CPPC_CPUFREQ) {
+		rte_power_freqs = power_cppc_cpufreq_freqs;
+		rte_power_get_freq = power_cppc_cpufreq_get_freq;
+		rte_power_set_freq = power_cppc_cpufreq_set_freq;
+		rte_power_freq_up = power_cppc_cpufreq_freq_up;
+		rte_power_freq_down = power_cppc_cpufreq_freq_down;
+		rte_power_freq_min = power_cppc_cpufreq_freq_min;
+		rte_power_freq_max = power_cppc_cpufreq_freq_max;
+		rte_power_turbo_status = power_cppc_turbo_status;
+		rte_power_freq_enable_turbo = power_cppc_enable_turbo;
+		rte_power_freq_disable_turbo = power_cppc_disable_turbo;
+		rte_power_get_capabilities = power_cppc_get_capabilities;
 	} else {
 		RTE_LOG(ERR, POWER, "Invalid Power Management Environment(%d) set\n",
 				env);
@@ -153,6 +168,8 @@ rte_power_init(unsigned int lcore_id)
 		return power_kvm_vm_init(lcore_id);
 	case PM_ENV_PSTATE_CPUFREQ:
 		return power_pstate_cpufreq_init(lcore_id);
+	case PM_ENV_CPPC_CPUFREQ:
+		return power_cppc_cpufreq_init(lcore_id);
 	default:
 		RTE_LOG(INFO, POWER, "Env isn't set yet!\n");
 	}
@@ -172,6 +189,13 @@ rte_power_init(unsigned int lcore_id)
 		goto out;
 	}
 
+	RTE_LOG(INFO, POWER, "Attempting to initialise CPPC power management...\n");
+	ret = power_cppc_cpufreq_init(lcore_id);
+	if (ret == 0) {
+		rte_power_set_env(PM_ENV_CPPC_CPUFREQ);
+		goto out;
+	}
+
 	RTE_LOG(INFO, POWER, "Attempting to initialise VM power management...\n");
 	ret = power_kvm_vm_init(lcore_id);
 	if (ret == 0) {
@@ -194,6 +218,8 @@ rte_power_exit(unsigned int lcore_id)
 		return power_kvm_vm_exit(lcore_id);
 	case PM_ENV_PSTATE_CPUFREQ:
 		return power_pstate_cpufreq_exit(lcore_id);
+	case PM_ENV_CPPC_CPUFREQ:
+		return power_cppc_cpufreq_exit(lcore_id);
 	default:
 		RTE_LOG(ERR, POWER, "Environment has not been set, unable to exit gracefully\n");
 
diff --git a/lib/power/rte_power.h b/lib/power/rte_power.h
index c8086bf6b..c5759afa3 100644
--- a/lib/power/rte_power.h
+++ b/lib/power/rte_power.h
@@ -22,7 +22,7 @@ extern "C" {
 
 /* Power Management Environment State */
 enum power_management_env {PM_ENV_NOT_SET, PM_ENV_ACPI_CPUFREQ, PM_ENV_KVM_VM,
-		PM_ENV_PSTATE_CPUFREQ};
+		PM_ENV_PSTATE_CPUFREQ, PM_ENV_CPPC_CPUFREQ};
 
 /**
  * @warning
-- 
2.20.1