PowerOp core patch

[David Singleton <dsingleton@mvista.com>]

Here is the core patch for the PowerOp concept.  It adds the powerop  
struct
for opertaing point support to linux/pm.h and adds support to transition 
to supported operating points by
setting their name into /sys/power/state.

The supported operating points are shown in a readonly sysfs file,
/sys/power/supported_states.


Signed-Off-by: David Singleton <dsingleton@mvista.com>

 Documentation/power/powerop.txt |  168 +++++++++++++++++++++++++++++++++++
 include/linux/pm.h              |   26 +++++
 kernel/power/main.c             |  190 
+++++++++++++++++++++++++++++++---------
 kernel/power/power.h            |    2
 4 files changed, 342 insertions(+), 44 deletions(-)

Index: linux-2.6.17/kernel/power/main.c
===================================================================
--- linux-2.6.17.orig/kernel/power/main.c
+++ linux-2.6.17/kernel/power/main.c
@@ -49,7 +49,7 @@ void pm_set_ops(struct pm_ops * ops)
  *     the platform can enter the requested state.
  */

-static int suspend_prepare(suspend_state_t state)
+static int suspend_prepare(struct powerop * state)
 {
        int error = 0;
        unsigned int free_pages;
@@ -82,7 +82,7 @@ static int suspend_prepare(suspend_state
        }

        if (pm_ops->prepare) {
-               if ((error = pm_ops->prepare(state)))
+               if ((error = pm_ops->prepare(state->type)))
                        goto Thaw;
        }

@@ -94,7 +94,7 @@ static int suspend_prepare(suspend_state
        return 0;
  Finish:
        if (pm_ops->finish)
-               pm_ops->finish(state);
+               pm_ops->finish(state->type);
  Thaw:
        thaw_processes();
  Enable_cpu:
@@ -104,7 +104,7 @@ static int suspend_prepare(suspend_state
 }


-int suspend_enter(suspend_state_t state)
+int suspend_enter(struct powerop * state)
 {
        int error = 0;
        unsigned long flags;
@@ -115,7 +115,7 @@ int suspend_enter(suspend_state_t state)
                printk(KERN_ERR "Some devices failed to power down\n");
                goto Done;
        }
-       error = pm_ops->enter(state);
+       error = pm_ops->enter(state->type);
        device_power_up();
  Done:
        local_irq_restore(flags);
@@ -131,36 +131,95 @@ int suspend_enter(suspend_state_t state)
  *     console that we've allocated. This is not called for 
suspend-to-disk.
  */

-static void suspend_finish(suspend_state_t state)
+static void suspend_finish(struct powerop * state)
 {
        device_resume();
        resume_console();
        thaw_processes();
        enable_nonboot_cpus();
        if (pm_ops && pm_ops->finish)
-               pm_ops->finish(state);
+               pm_ops->finish(state->type);
        pm_restore_console();
 }


+struct powerop *current_state;
+struct powerop pm_states = {
+       .name = "default",
+       .type = PM_SUSPEND_ON,
+};
+EXPORT_SYMBOL(pm_states);

-
-static const char * const pm_states[PM_SUSPEND_MAX] = {
-       [PM_SUSPEND_STANDBY]    = "standby",
-       [PM_SUSPEND_MEM]        = "mem",
+static struct powerop standby = {
+       .name = "standby",
+       .description = "Power-On Suspend ACPI State: S1",
+       .type = PM_SUSPEND_STANDBY,
+};
+static struct powerop mem = {
+       .name = "mem   ",
+       .description = "Suspend-to-RAM ACPI State: S3",
+       .type = PM_SUSPEND_MEM,
+};
 #ifdef CONFIG_SOFTWARE_SUSPEND
-       [PM_SUSPEND_DISK]       = "disk",
-#endif
+static struct powerop disk = {
+       .name = "disk  ",
+       .description = "Suspend-to-disk ACPI State: S4",
+       .type = PM_SUSPEND_DISK,
 };
+#endif

-static inline int valid_state(suspend_state_t state)
+/*
+ *
+ */
+static int pm_change_state(struct powerop *state)
+{
+       int error = -EINVAL;
+       int len = strlen(state->name);
+       struct powerop *this, *next;
+       struct list_head *head = &pm_states.list;
+
+       /*
+        * list_find new operating point.
+        * compare to current operating point.
+        * if different change to new operating point.
+        */
+       list_for_each_entry_safe(this, next, head, list) {
+               if (strncmp(state->name, this->name, len) == 0) {
+                       if ((strcmp(current_state->name, this->name)) == 
0) {
+                               return 0;
+                       }
+
+                       if (this->prepare_transition(current_state, 
this)) {
+                               break;
+                       }
+
+                       if (this->transition(current_state, this)) {
+                               break;
+                       }
+
+                       /*
+                        * now lets wait for the transition latency
+                        */
+                       udelay(this->latency);
+
+                       error = this->finish_transition(current_state, 
this);
+
+                       if (error == 0)
+                               current_state = this;
+                       break;
+               }
+       }
+       return error;
+}
+
+static inline int valid_state(struct powerop * state)
 {
        /* Suspend-to-disk does not really need low-level support.
         * It can work with reboot if needed. */
-       if (state == PM_SUSPEND_DISK)
+       if (state->type == PM_SUSPEND_DISK)
                return 1;

-       if (pm_ops && pm_ops->valid && !pm_ops->valid(state))
+       if (pm_ops && pm_ops->valid && !pm_ops->valid(state->type))
                return 0;
        return 1;
 }
@@ -168,7 +227,7 @@ static inline int valid_state(suspend_st

 /**
  *     enter_state - Do common work of entering low-power state.
- *     @state:         pm_state structure for state we're entering.
+ *     @state:         powerop structure for state we're entering.
  *
  *     Make sure we're the only ones trying to enter a sleep state. Fail
  *     if someone has beat us to it, since we don't want anything weird to
@@ -177,7 +236,7 @@ static inline int valid_state(suspend_st
  *     we've woken up).
  */

-static int enter_state(suspend_state_t state)
+static int enter_state(struct powerop *state)
 {
        int error;

@@ -186,16 +245,21 @@ static int enter_state(suspend_state_t s
        if (down_trylock(&pm_sem))
                return -EBUSY;

-       if (state == PM_SUSPEND_DISK) {
+       if (state->type == PM_SUSPEND_DISK) {
                error = pm_suspend_disk();
                goto Unlock;
        }

-       pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+       if (state->type == PM_FREQ_CHANGE) {
+               error = pm_change_state(state);
+               goto Unlock;
+       }
+
+       pr_debug("PM: Preparing system for %s sleep\n", state->name);
        if ((error = suspend_prepare(state)))
                goto Unlock;

-       pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+       pr_debug("PM: Entering %s sleep\n", state->name);
        error = suspend_enter(state);

        pr_debug("PM: Finishing wakeup.\n");
@@ -211,7 +275,15 @@ static int enter_state(suspend_state_t s
  */
 int software_suspend(void)
 {
-       return enter_state(PM_SUSPEND_DISK);
+       struct powerop *this, *next;
+       struct list_head *head = &pm_states.list;
+       int error = 0;
+
+       list_for_each_entry_safe(this, next, head, list) {
+               if (this->type == PM_SUSPEND_DISK)
+                       error= enter_state(this);
+       }
+       return error;
 }


@@ -223,16 +295,48 @@ int software_suspend(void)
  *     structure, and enter (above).
  */

-int pm_suspend(suspend_state_t state)
+int pm_suspend(struct powerop * state)
 {
-       if (state > PM_SUSPEND_ON && state <= PM_SUSPEND_MAX)
+       if (state->type > PM_SUSPEND_ON && state->type <= PM_SUSPEND_MAX)
                return enter_state(state);
        return -EINVAL;
 }

+decl_subsys(power,NULL,NULL);

+/**
+ *     supported_states - control system power state.
+ *
+ *     show() returns what states are supported, which are no longer
+ *     hard-coded to just 'standby' (Power-On Suspend), 'mem' 
(Suspend-to-RAM),
+ *     and *'disk' (Suspend-to-Disk), but show all the power states.
+ *
+ *     store() unwritable
+ */

-decl_subsys(power,NULL,NULL);
+static ssize_t supported_states_show(struct subsystem * subsys, char * 
buf)
+{
+       struct powerop *this, *next;
+       struct list_head *head = &pm_states.list;
+       const char *header =  "< Name >    <Frequency>  <Voltage>  
<Transition Latency>  < Description >\n";
+       char * s = buf;
+
+       s += sprintf(s, "%s", header);
+       list_for_each_entry_safe(this, next, head, list) {
+               s += sprintf(s,"%s %dKHz %dmV %dus %s\n", this->name,
+                  this->frequency, this->voltage, this->latency,
+                  this->description);
+       }
+
+       return (s - buf);
+}
+
+static ssize_t supported_states_store(struct subsystem * subsys, const 
char *buf, size_t n)
+{
+       return -EINVAL;
+}
+
+power_attr(supported_states);


 /**
@@ -248,36 +352,28 @@ decl_subsys(power,NULL,NULL);

 static ssize_t state_show(struct subsystem * subsys, char * buf)
 {
-       int i;
        char * s = buf;

-       for (i = 0; i < PM_SUSPEND_MAX; i++) {
-               if (pm_states[i] && valid_state(i))
-                       s += sprintf(s,"%s ", pm_states[i]);
-       }
-       s += sprintf(s,"\n");
+       s += sprintf(s,"%s\n", current_state->name);
        return (s - buf);
 }

 static ssize_t state_store(struct subsystem * subsys, const char * buf, 
size_t n)
 {
-       suspend_state_t state = PM_SUSPEND_STANDBY;
-       const char * const *s;
+       struct powerop *this, *next;
+       struct list_head *head = &pm_states.list;
        char *p;
-       int error;
+       int error = -EINVAL;
        int len;

        p = memchr(buf, '\n', n);
        len = p ? p - buf : n;
-
-       for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
-               if (*s && !strncmp(buf, *s, len))
+       list_for_each_entry_safe(this, next, head, list) {
+               if (!strncmp(buf, this->name, len)) {
+                       error = enter_state(this);
                        break;
+               }
        }
-       if (state < PM_SUSPEND_MAX && *s)
-               error = enter_state(state);
-       else
-               error = -EINVAL;
        return error ? error : n;
 }

@@ -285,6 +381,7 @@ power_attr(state);

 static struct attribute * g[] = {
        &state_attr.attr,
+       &supported_states_attr.attr,
        NULL,
 };

@@ -295,9 +392,20 @@ static struct attribute_group attr_group

 static int __init pm_init(void)
 {
+
        int error = subsystem_register(&power_subsys);
        if (!error)
                error = 
sysfs_create_group(&power_subsys.kset.kobj,&attr_group);
+
+       INIT_LIST_HEAD(&pm_states.list);
+
+#ifdef CONFIG_SOFTWARE_SUSPEND
+       list_add(&disk.list, &pm_states.list);
+#endif
+       list_add(&mem.list, &pm_states.list);
+       list_add(&standby.list, &pm_states.list);
+       current_state = &pm_states;
+
        return error;
 }

Index: linux-2.6.17/include/linux/pm.h
===================================================================
--- linux-2.6.17.orig/include/linux/pm.h
+++ linux-2.6.17/include/linux/pm.h
@@ -108,7 +108,29 @@ typedef int __bitwise suspend_state_t;
 #define PM_SUSPEND_STANDBY     ((__force suspend_state_t) 1)
 #define PM_SUSPEND_MEM         ((__force suspend_state_t) 3)
 #define PM_SUSPEND_DISK                ((__force suspend_state_t) 4)
-#define PM_SUSPEND_MAX         ((__force suspend_state_t) 5)
+#define PM_FREQ_CHANGE         ((__force suspend_state_t) 5)
+#define PM_VOLT_CHANGE         ((__force suspend_state_t) 6)
+#define PM_SUSPEND_MAX         ((__force suspend_state_t) 7)
+
+#define PM_NAME_SIZE            16
+#define PM_DESCRIPTION_SIZE     48
+
+struct powerop {
+       struct list_head list;
+       suspend_state_t type;
+       char name[PM_NAME_SIZE];
+       char description[PM_DESCRIPTION_SIZE];
+       unsigned int frequency;         /* in KHz */
+       unsigned int voltage;           /* mV */
+       unsigned int latency;           /* transition latency in us */
+       int     (*prepare_transition)(struct powerop *cur, struct 
powerop *new);
+       int     (*transition)(struct powerop *cur, struct powerop *new);
+       int     (*finish_transition)(struct powerop *cur, struct powerop 
*new);
+
+       void *md_data;                  /* arch dependent data (dpm_opt) */
+};
+extern struct powerop pm_states;
+extern struct powerop *current_state;

 typedef int __bitwise suspend_disk_method_t;

@@ -128,7 +150,7 @@ struct pm_ops {

 extern void pm_set_ops(struct pm_ops *);
 extern struct pm_ops *pm_ops;
-extern int pm_suspend(suspend_state_t state);
+extern int pm_suspend(struct powerop *state);


 /*
Index: linux-2.6.17/kernel/power/power.h
===================================================================
--- linux-2.6.17.orig/kernel/power/power.h
+++ linux-2.6.17/kernel/power/power.h
@@ -113,4 +113,4 @@ extern int swsusp_resume(void);
 extern int swsusp_read(void);
 extern int swsusp_write(void);
 extern void swsusp_close(void);
-extern int suspend_enter(suspend_state_t state);
+extern int suspend_enter(struct powerop * state);
Index: linux-2.6.17/Documentation/power/powerop.txt
===================================================================
--- /dev/null
+++ linux-2.6.17/Documentation/power/powerop.txt
@@ -0,0 +1,168 @@
+
+The PowerOp Power Management infrastructure.
+
+David Singleton <dsingleton@mvista.com>
+
+25 July 2006
+
+Copyright (c) 2006 MontaVista Software Inc.
+
+0. Introduction
+
+The goal of PowerOp power management is to provide a framework that 
unifies
+and simplifies the various power management infrastructures in Linux.  The
+three infrastructures Power Op is concerned with are:
+
+       1) basic suspend/resume power management (CONFIG_PM)
+
+       2) basic processor frequency management (CONFIG_CPUFREQ)
+
+       3) SourceForge's Dynamic Power Management (CONFIG_DPM)
+
+All three power management infrastructures are concerned with controlling
+power states of the system, and interestingly enough they all perform the
+same basic operational steps to control changes in power state.
+
+PowerOp uses the existing power management sysfs infrastructure and 
extends it
+to perform cpufreq and dynamic power management operations. The 
traditional
+suspend to memory or disk (or swap) infrastructure has the correct 
operational
+structure that supports all types of power state change.
+
+The CPUFREQ table based frequency control makes controlling cpu frequency
+simple and straight forward.  The user doesn't get to set the cpu to
+any speed, but only to supported speeds that have been provided by
+the hardware vendor and validated.
+
+Dynamic Power Management treats all types of power states as operating 
points,
+wether it's a suspend operating point, a particular frequency, or a 
specific
+voltage.
+
+By combining the best of all of these power management infrastructures
+PowerOp uses the operational structure of tradition CONFIG_PM power
+management and converts all power states, frequency, voltage, idle or
+suspend to the CPUFREQ concept of only supported and validated operating
+points.
+
+PowerOp then becomes a simplified power management infrastructure in that
+only operating points that are supported and validated are available
+to the user.  Control of all operating points are done by the operating
+point name.  The user cannot supply invalid, or malicious,
+parameters that would hang or crash the system.
+
+1) PowerOp interface.
+
+To simplify power management all operations take place through two sysfs
+files, /sys/power/state and /sys/power/supported_states.  The 'state' file
+shows the current operating point of the system.  The readonly
+'supported_states' file shows the operating points the system supports.
+
+Supported operating points are displayed in tuple format of:
+
+<name, frequency, voltage, transition latency, description>
+
+The supported_states file contains rows of tuples with each
+tuple describing a supported operating point of the system.
+The supported_states file looks like a merge between the old
+/sys/power/state file and a cpufreq table.
+
+The system can transition to any of the supported states by simply
+storing the operating point name in the /sys/power/state file.
+
+To allow user space notification of events, like low battery, lid of
+the notebook being closed, etc.  PowerOp notifies the user through
+the hotplug interface.
+
+
+2) PowerOP Operating Points.
+
+An operating point is represented by the powerop struct which contains:
+
+struct powerop {
+        struct list_head list;
+        suspend_state_t type;
+        char name[PM_NAME_SIZE];
+        char description[PM_DESCRIPTION_SIZE];
+        unsigned int frequency;         /* in KHz */
+        unsigned int voltage;           /* mV */
+        unsigned int latency;           /* transition latency in us */
+        int     (*prepare_transition)(struct powerop *cur, struct 
powerop *new);
+        int     (*transition)(struct powerop *cur, struct powerop *new);
+        int     (*finish_transition)(struct powerop *cur, struct 
powerop *new);
+
+        void *md_data;                  /* arch dependent data  */
+};
+
+Each operating point has its own functions for preparing to transition,
+transitioning and finishing transition.  Cpu frequency operating points
+will probably share their op vectors, idle and suspend operating points 
my have
+different op vectors.
+
+
+3) Traditional Operation of Power Management Code.
+
+All three power management infrastructures have the same operational 
model.
+All three follow the PM model of preparing to suspend,  suspending,
+and finish the state change.  It was easiest to follow the model
+enforced by the traditional power management and use the three step 
process of:
+
+       1) get ready to change state
+       2) change state
+       3) finish changes
+
+Cpufreq infrastructure makes three calls to change the frequency of the
+processor:
+
+       1) cpufreq_notify_transition(&freq, CPUFREQ_PRECHANGE);
+
+       2) acpi_processor_set_performance (data, j, next_state);
+
+       3) cpufreq_notify_transition(&freq, CPUFREQ_POSTCHANGE);
+
+DPM uses these three calls to change frequency and/or voltage:
+
+       1) dpm_driver_scale(SCALE_PRECHANGE, new);
+
+       2) clk_set_rate(prcm_set, new->md_opt.prcm_clock);
+
+       3) dpm_driver_scale(SCALE_POStCHANGE, new);
+
+PM uses these three calls to suspend:
+
+       1) suspend_prepare(state);
+
+       2) suspend_enter(state->type);
+
+       3) suspend_finish(state);
+
+
+4) PowerOP Operation.
+
+PowerOP uses the following three calls to transition to a new operating
+point.
+
+       prepare_to_transition(cur_state, new_state);
+
+       transition(cur_state, new_state);
+
+       finish_transistion(cur_state, new_state);
+
+The parameters are pointers to operating point structures, struct powerop.
+
+Power OP is a simplified version of all three of these infrastructures in
+that it only deals with operating points, and more specifically with
+supported operating points.  Power Op presents a set of supported 
operating
+points to the user.  This is similar to the cpufreq table concept in that
+only supported and validated frequencies are avaliable.
+
+The definition of the operating point is done in a manner similar to 
cpufreqs
+in that the supported operating frequency, voltage and transition latency,
+are predefined (by the hardware vendor) and validated.
+
+The user maninuplates the operting points of the system by the
+name of the operating points.  This simplifies both the code and the
+control of the system's operating points in the PowerOp daemon.
+
+All supported operating points are defined at compile time and
+the user sets the system to different operating points by
+the operating point name.
+