[dpdk-dev] [PATCH v1 1/4] lib/librte_power: add per-core turbo capability

[David Hunt <david.hunt@intel.com>]

Adds a new set of APIs to allow per-core turbo
enable-disable.

Signed-off-by: David Hunt <david.hunt@intel.com>
---
 lib/librte_power/channel_commands.h       |   2 +
 lib/librte_power/rte_power.c              |   9 ++
 lib/librte_power/rte_power.h              |  41 +++++++++
 lib/librte_power/rte_power_acpi_cpufreq.c | 143 ++++++++++++++++++++++++++++++
 lib/librte_power/rte_power_acpi_cpufreq.h |  40 +++++++++
 lib/librte_power/rte_power_kvm_vm.c       |  19 ++++
 lib/librte_power/rte_power_kvm_vm.h       |  35 +++++++-
 7 files changed, 288 insertions(+), 1 deletion(-)

diff --git a/lib/librte_power/channel_commands.h b/lib/librte_power/channel_commands.h
index 383897b..484085b 100644
--- a/lib/librte_power/channel_commands.h
+++ b/lib/librte_power/channel_commands.h
@@ -52,6 +52,8 @@ extern "C" {
 #define CPU_POWER_SCALE_DOWN    2
 #define CPU_POWER_SCALE_MAX     3
 #define CPU_POWER_SCALE_MIN     4
+#define CPU_POWER_ENABLE_TURBO  5
+#define CPU_POWER_DISABLE_TURBO 6
 
 struct channel_packet {
 	uint64_t resource_id; /**< core_num, device */
diff --git a/lib/librte_power/rte_power.c b/lib/librte_power/rte_power.c
index 998ed1c..b327a86 100644
--- a/lib/librte_power/rte_power.c
+++ b/lib/librte_power/rte_power.c
@@ -50,6 +50,9 @@ rte_power_freq_change_t rte_power_freq_up = NULL;
 rte_power_freq_change_t rte_power_freq_down = NULL;
 rte_power_freq_change_t rte_power_freq_max = NULL;
 rte_power_freq_change_t rte_power_freq_min = NULL;
+rte_power_freq_change_t rte_power_turbo_status;
+rte_power_freq_change_t rte_power_freq_enable_turbo;
+rte_power_freq_change_t rte_power_freq_disable_turbo;
 
 int
 rte_power_set_env(enum power_management_env env)
@@ -65,6 +68,9 @@ rte_power_set_env(enum power_management_env env)
 		rte_power_freq_down = rte_power_acpi_cpufreq_freq_down;
 		rte_power_freq_min = rte_power_acpi_cpufreq_freq_min;
 		rte_power_freq_max = rte_power_acpi_cpufreq_freq_max;
+		rte_power_turbo_status = rte_power_acpi_turbo_status;
+		rte_power_freq_enable_turbo = rte_power_acpi_enable_turbo;
+		rte_power_freq_disable_turbo = rte_power_acpi_disable_turbo;
 	} else if (env == PM_ENV_KVM_VM) {
 		rte_power_freqs = rte_power_kvm_vm_freqs;
 		rte_power_get_freq = rte_power_kvm_vm_get_freq;
@@ -73,6 +79,9 @@ rte_power_set_env(enum power_management_env env)
 		rte_power_freq_down = rte_power_kvm_vm_freq_down;
 		rte_power_freq_min = rte_power_kvm_vm_freq_min;
 		rte_power_freq_max = rte_power_kvm_vm_freq_max;
+		rte_power_turbo_status = rte_power_kvm_vm_turbo_status;
+		rte_power_freq_enable_turbo = rte_power_kvm_vm_enable_turbo;
+		rte_power_freq_disable_turbo = rte_power_kvm_vm_disable_turbo;
 	} else {
 		RTE_LOG(ERR, POWER, "Invalid Power Management Environment(%d) set\n",
 				env);
diff --git a/lib/librte_power/rte_power.h b/lib/librte_power/rte_power.h
index 67e0ec0..b17b7a5 100644
--- a/lib/librte_power/rte_power.h
+++ b/lib/librte_power/rte_power.h
@@ -236,6 +236,47 @@ extern rte_power_freq_change_t rte_power_freq_max;
  */
 extern rte_power_freq_change_t rte_power_freq_min;
 
+/**
+ * Query the Turbo Boost status of a specific lcore.
+ * Review each environments specific documentation for usage..
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 Turbo Boost is enabled for this lcore.
+ *  - 0 Turbo Boost is disabled for this lcore.
+ *  - Negative on error.
+ */
+extern rte_power_freq_change_t rte_power_turbo_status;
+
+/**
+ * Enable Turbo Boost for this lcore.
+ * Review each environments specific documentation for usage..
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 on success.
+ *  - Negative on error.
+ */
+extern rte_power_freq_change_t rte_power_freq_enable_turbo;
+
+/**
+ * Disable Turbo Boost for this lcore.
+ * Review each environments specific documentation for usage..
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 0 on success.
+ *  - Negative on error.
+ */
+extern rte_power_freq_change_t rte_power_freq_disable_turbo;
+
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/librte_power/rte_power_acpi_cpufreq.c b/lib/librte_power/rte_power_acpi_cpufreq.c
index a56c9b5..6695f59 100644
--- a/lib/librte_power/rte_power_acpi_cpufreq.c
+++ b/lib/librte_power/rte_power_acpi_cpufreq.c
@@ -87,6 +87,14 @@
 #define POWER_SYSFILE_SETSPEED   \
 		"/sys/devices/system/cpu/cpu%u/cpufreq/scaling_setspeed"
 
+/*
+ * MSR related
+ */
+#define PLATFORM_INFO     0x0CE
+#define TURBO_RATIO_LIMIT 0x1AD
+#define IA32_PERF_CTL     0x199
+#define CORE_TURBO_DISABLE_BIT ((uint64_t)1<<32)
+
 enum power_state {
 	POWER_IDLE = 0,
 	POWER_ONGOING,
@@ -543,3 +551,138 @@ rte_power_acpi_cpufreq_freq_min(unsigned lcore_id)
 	/* Frequencies in the array are from high to low. */
 	return set_freq_internal(pi, pi->nb_freqs - 1);
 }
+
+
+static int
+rdmsr(int lcore, int msr, uint64_t *val)
+{
+	char filename[32];
+	int fd;
+	int retval;
+
+	sprintf(filename, "/dev/cpu/%d/msr", lcore);
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	retval = pread(fd, val, sizeof(uint64_t), msr);
+	if (retval < 0) {
+		close(fd);
+		return retval;
+	}
+	close(fd);
+	return 0;
+}
+
+static int
+wrmsr(int lcore, int msr, uint64_t val)
+{
+	char filename[32];
+	int fd;
+	int retval;
+
+	sprintf(filename, "/dev/cpu/%d/msr", lcore);
+	fd = open(filename, O_WRONLY);
+	if (fd < 0)
+		return fd;
+
+	retval = pwrite(fd, (void *)&val, sizeof(uint64_t), msr);
+	if (retval < 0) {
+		close(fd);
+		return retval;
+	}
+	close(fd);
+	return 0;
+}
+
+int
+rte_power_acpi_turbo_status(unsigned int lcore_id)
+{
+	uint64_t val;
+	int retval;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+#if defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_64)
+	retval = rdmsr(lcore_id, IA32_PERF_CTL, &val);
+	if (retval)
+		return retval;
+	else
+		return(!(val & CORE_TURBO_DISABLE_BIT));
+#else
+	return 0
+#endif
+}
+
+
+int
+rte_power_acpi_enable_turbo(unsigned int lcore_id)
+{
+	uint64_t val;
+	int retval;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+#if defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_64)
+	/*
+	 * The low byte of 1ADh MSR contains max recomended ratio when a small
+	 * number of cores are active. Use this ratio when turbo is enabled.
+	 */
+	retval = rdmsr(lcore_id, TURBO_RATIO_LIMIT, &val);
+	if (retval)
+		return retval;
+
+	val = (val & 0x00ff) << 8;       /* Move to second lowest byte     */
+	val &= ~CORE_TURBO_DISABLE_BIT;  /* Switch bit off to enable turbo */
+
+	retval = wrmsr(lcore_id, IA32_PERF_CTL, val);
+	if (retval)
+		return retval;
+	else
+		return 0;
+#else
+	return 0;
+#endif
+}
+
+int
+rte_power_acpi_disable_turbo(unsigned int lcore_id)
+{
+	uint64_t val;
+	int retval;
+
+	if (lcore_id >= RTE_MAX_LCORE) {
+		RTE_LOG(ERR, POWER, "Invalid lcore ID\n");
+		return -1;
+	}
+
+#if defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_64)
+	/*
+	 * 0CEh MSR contains max non-turbo ratio in bits 8-15. Use this
+	 * for the freq when turbo is disabled for that core.
+	 */
+	retval = rdmsr(lcore_id, PLATFORM_INFO, &val);
+	if (retval)
+		return retval;
+
+	val = val & 0xff00;             /* Only need second lowest byte   */
+	val |= CORE_TURBO_DISABLE_BIT;  /* Switch bit on to disable turbo */
+
+	retval = wrmsr(lcore_id, IA32_PERF_CTL, val);
+	if (retval)
+		return retval;
+
+	/* Try to set freq to max by default coming out of turbo */
+	if (rte_power_acpi_cpufreq_freq_max(lcore_id) < 0) {
+		RTE_LOG(ERR, POWER, "Failed to set frequency of lcore %u to max\n",
+				lcore_id);
+	}
+#endif
+	return 0;
+}
diff --git a/lib/librte_power/rte_power_acpi_cpufreq.h b/lib/librte_power/rte_power_acpi_cpufreq.h
index 68578e9..eee0ca0 100644
--- a/lib/librte_power/rte_power_acpi_cpufreq.h
+++ b/lib/librte_power/rte_power_acpi_cpufreq.h
@@ -185,6 +185,46 @@ int rte_power_acpi_cpufreq_freq_max(unsigned lcore_id);
  */
 int rte_power_acpi_cpufreq_freq_min(unsigned 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 rte_power_acpi_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 rte_power_acpi_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 rte_power_acpi_disable_turbo(unsigned int lcore_id);
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/lib/librte_power/rte_power_kvm_vm.c b/lib/librte_power/rte_power_kvm_vm.c
index a1badf3..9906062 100644
--- a/lib/librte_power/rte_power_kvm_vm.c
+++ b/lib/librte_power/rte_power_kvm_vm.c
@@ -134,3 +134,22 @@ rte_power_kvm_vm_freq_min(unsigned lcore_id)
 {
 	return send_msg(lcore_id, CPU_POWER_SCALE_MIN);
 }
+
+int
+rte_power_kvm_vm_turbo_status(__attribute__((unused)) unsigned int lcore_id)
+{
+	RTE_LOG(ERR, POWER, "rte_power_turbo_status is not implemented for Virtual Machine Power Management\n");
+	return -ENOTSUP;
+}
+
+int
+rte_power_kvm_vm_enable_turbo(unsigned int lcore_id)
+{
+	return send_msg(lcore_id, CPU_POWER_ENABLE_TURBO);
+}
+
+int
+rte_power_kvm_vm_disable_turbo(unsigned int lcore_id)
+{
+	return send_msg(lcore_id, CPU_POWER_DISABLE_TURBO);
+}
diff --git a/lib/librte_power/rte_power_kvm_vm.h b/lib/librte_power/rte_power_kvm_vm.h
index dcbc878..9af41d6 100644
--- a/lib/librte_power/rte_power_kvm_vm.h
+++ b/lib/librte_power/rte_power_kvm_vm.h
@@ -172,8 +172,41 @@ int rte_power_kvm_vm_freq_max(unsigned lcore_id);
  */
 int rte_power_kvm_vm_freq_min(unsigned lcore_id);
 
+/**
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  -ENOTSUP
+ */
+int rte_power_kvm_vm_turbo_status(unsigned int lcore_id);
+
+/**
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success.
+ *  - Negative on error.
+ */
+int rte_power_kvm_vm_enable_turbo(unsigned int lcore_id);
+
+/**
+ * It should be protected outside of this function for threadsafe.
+ *
+ * @param lcore_id
+ *  lcore id.
+ *
+ * @return
+ *  - 1 on success.
+ *  - Negative on error.
+ */
+int rte_power_kvm_vm_disable_turbo(unsigned int lcore_id);
 #ifdef __cplusplus
 }
 #endif
-
 #endif
-- 
2.7.4