intel_idle: Add cmdline option to adjust C-states table

Add a new module parameter that allows adjusting the C-states table used by
the driver.

Currently, the C-states table is hardcoded in the driver based on the CPU
model. The goal is to have good enough defaults for most users.

However, C-state characteristics, such as exit latency and residency, can
vary between different variants of the same CPU model and BIOS settings.
Moreover, different platform usage models and user preferences may benefit
from different C-state target_residency values.

Provide a way for users to adjust the C-states table via a module parameter
"table". The general format is:
"state1:latency1:target_residency1,state2:latency2:target_residency2,..."

In other words, represent each C-state by its name, exit latency (in
microseconds), and target residency (in microseconds), separated by colons.
Separate multiple C-states by commas.

For example, suppose a CPU has 3 C-states with the following
characteristics:
  C1:  exit_latency=1, target_residency=2
  C1E: exit_latency=10, target_residency=10
  C6:  exit_latency=100, target_residency=500

Users can specify a custom C-states table as follows:

1. intel_idle.table="C1:2:2,C1E:5:20,C6:150:600"
   Result: C1:  exit_latency=2, target_residency=2
           C1E: exit_latency=5, target_residency=20
           C6:  exit_latency=150, target_residency=600
2. intel_idle.table="C6::400"
   Result: C1:  exit_latency=1, target_residency=2 (unchanged)
           C1E: exit_latency=10, target_residency=10 (unchanged)
           C6:  exit_latency=100, target_residency=400
                (only target_residency changed)

Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/20251216080402.156988-3-dedekind1@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f64463e00df7e7a51da89bf3bc227950fbab7ae5..ab6b86ff9905f667ed994a61913969a9c6414678 100644 (file)
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -73,6 +73,10 @@ static unsigned int disabled_states_mask __read_mostly;
 static bool force_irq_on __read_mostly;
 static bool ibrs_off __read_mostly;
 
+/* The maximum allowed length for the 'table' module parameter  */
+#define MAX_CMDLINE_TABLE_LEN 256
+static char cmdline_table_str[MAX_CMDLINE_TABLE_LEN] __read_mostly;
+
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
 static unsigned long auto_demotion_disable_flags;
@@ -104,6 +108,9 @@ static struct device *sysfs_root __initdata;
 static const struct idle_cpu *icpu __initdata;
 static struct cpuidle_state *cpuidle_state_table __initdata;
 
+/* C-states data from the 'intel_idle.table' cmdline parameter */
+static struct cpuidle_state cmdline_states[CPUIDLE_STATE_MAX] __initdata;
+
 static unsigned int mwait_substates __initdata;
 
 /*
@@ -2393,6 +2400,149 @@ static void __init intel_idle_sysfs_uninit(void)
        put_device(sysfs_root);
 }
 
+ /**
+  * get_cmdline_field - Get the current field from a cmdline string.
+  * @args: The cmdline string to get the current field from.
+  * @field: Pointer to the current field upon return.
+  * @sep: The fields separator character.
+  *
+  * Examples:
+  *   Input: args="C1:1:1,C1E:2:10", sep=':'
+  *   Output: field="C1", return "1:1,C1E:2:10"
+  *   Input: args="C1:1:1,C1E:2:10", sep=','
+  *   Output: field="C1:1:1", return "C1E:2:10"
+  *   Ipnut: args="::", sep=':'
+  *   Output: field="", return ":"
+  *
+  * Return: The continuation of the cmdline string after the field or NULL.
+  */
+static char *get_cmdline_field(char *args, char **field, char sep)
+{
+       unsigned int i;
+
+       for (i = 0; args[i] && !isspace(args[i]); i++) {
+               if (args[i] == sep)
+                       break;
+       }
+
+       *field = args;
+
+       if (args[i] != sep)
+               return NULL;
+
+       args[i] = '\0';
+       return args + i + 1;
+}
+
+/**
+ * cmdline_table_adjust - Adjust the C-states table with data from cmdline.
+ * @drv: cpuidle driver (assumed to point to intel_idle_driver).
+ *
+ * Adjust the C-states table with data from the 'intel_idle.table' module
+ * parameter (if specified).
+ */
+static void __init cmdline_table_adjust(struct cpuidle_driver *drv)
+{
+       char *args = cmdline_table_str;
+       struct cpuidle_state *state;
+       int i;
+
+       if (args[0] == '\0')
+               /* The 'intel_idle.table' module parameter was not specified */
+               return;
+
+       /* Create a copy of the C-states table */
+       for (i = 0; i < drv->state_count; i++)
+               cmdline_states[i] = drv->states[i];
+
+       /*
+        * Adjust the C-states table copy with data from the 'intel_idle.table'
+        * module parameter.
+        */
+       while (args) {
+               char *fields, *name, *val;
+
+               /*
+                * Get the next C-state definition, which is expected to be
+                * '<name>:<latency_us>:<target_residency_us>'. Treat "empty"
+                * fields as unchanged. For example,
+                * '<name>::<target_residency_us>' leaves the latency unchanged.
+                */
+               args = get_cmdline_field(args, &fields, ',');
+
+               /* name */
+               fields = get_cmdline_field(fields, &name, ':');
+               if (!fields)
+                       goto error;
+
+               if (!strcmp(name, "POLL")) {
+                       pr_err("Cannot adjust POLL\n");
+                       continue;
+               }
+
+               /* Find the C-state by its name */
+               state = NULL;
+               for (i = 0; i < drv->state_count; i++) {
+                       if (!strcmp(name, drv->states[i].name)) {
+                               state = &cmdline_states[i];
+                               break;
+                       }
+               }
+
+               if (!state) {
+                       pr_err("C-state '%s' was not found\n", name);
+                       continue;
+               }
+
+               /* Latency */
+               fields = get_cmdline_field(fields, &val, ':');
+               if (!fields)
+                       goto error;
+
+               if (*val) {
+                       if (kstrtouint(val, 0, &state->exit_latency))
+                               goto error;
+               }
+
+               /* Target residency */
+               fields = get_cmdline_field(fields, &val, ':');
+
+               if (*val) {
+                       if (kstrtouint(val, 0, &state->target_residency))
+                               goto error;
+               }
+
+               /*
+                * Allow for 3 more fields, but ignore them. Helps to make
+                * possible future extensions of the cmdline format backward
+                * compatible.
+                */
+               for (i = 0; fields && i < 3; i++) {
+                       fields = get_cmdline_field(fields, &val, ':');
+                       if (!fields)
+                               break;
+               }
+
+               if (fields) {
+                       pr_err("Too many fields for C-state '%s'\n", state->name);
+                       goto error;
+               }
+
+               pr_info("C-state from cmdline: name=%s, latency=%u, residency=%u\n",
+                       state->name, state->exit_latency, state->target_residency);
+       }
+
+       /* Copy the adjusted C-states table back */
+       for (i = 1; i < drv->state_count; i++)
+               drv->states[i] = cmdline_states[i];
+
+       pr_info("Adjusted C-states with data from 'intel_idle.table'\n");
+       return;
+
+error:
+       pr_info("Failed to adjust C-states with data from 'intel_idle.table'\n");
+}
+
 static int __init intel_idle_init(void)
 {
        const struct x86_cpu_id *id;
@@ -2456,6 +2606,7 @@ static int __init intel_idle_init(void)
                return -ENOMEM;
 
        intel_idle_cpuidle_driver_init(&intel_idle_driver);
+       cmdline_table_adjust(&intel_idle_driver);
 
        retval = intel_idle_sysfs_init();
        if (retval)
@@ -2519,3 +2670,21 @@ module_param(force_irq_on, bool, 0444);
  */
 module_param(ibrs_off, bool, 0444);
 MODULE_PARM_DESC(ibrs_off, "Disable IBRS when idle");
+
+/*
+ * Define the C-states table from a user input string. Expected format is
+ * 'name:latency:residency', where:
+ * - name: The C-state name.
+ * - latency: The C-state exit latency in us.
+ * - residency: The C-state target residency in us.
+ *
+ * Multiple C-states can be defined by separating them with commas:
+ * 'name1:latency1:residency1,name2:latency2:residency2'
+ *
+ * Example: intel_idle.table=C1:1:1,C1E:5:10,C6:100:600
+ *
+ * To leave latency or residency unchanged, use an empty field, for example:
+ * 'C1:1:1,C1E::10' - leaves C1E latency unchanged.
+ */
+module_param_string(table, cmdline_table_str, MAX_CMDLINE_TABLE_LEN, 0444);
+MODULE_PARM_DESC(table, "Build the C-states table from a user input string");