ACPI: Processor native C-states using MWAIT

Intel processors starting with the Core Duo support
support processor native C-state using the MWAIT instruction.
Refer: Intel Architecture Software Developer's Manual
http://www.intel.com/design/Pentium4/manuals/253668.htm

Platform firmware exports the support for Native C-state to OS using
ACPI _PDC and _CST methods.
Refer: Intel Processor Vendor-Specific ACPI: Interface Specification
http://www.intel.com/technology/iapc/acpi/downloads/302223.htm

With Processor Native C-state, we use 'MWAIT' instruction on the processor
to enter different C-states (C1, C2, C3).  We won't use the special IO
ports to enter C-state and no SMM mode etc required to enter C-state.
Overall this will mean better C-state support.

One major advantage of using MWAIT for all C-states is, with this and
"treat interrupt as break event" feature of MWAIT, we can now get accurate
timing for the time spent in C1, C2, ..  states.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Len Brown <len.brown@intel.com>

1 files changed, 63 insertions, 38 deletions

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 0a395fca843..429a39dbd75 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -219,6 +219,23 @@ static void acpi_safe_halt(void)
 
 static atomic_t c3_cpu_count;
 
+/* Common C-state entry for C2, C3, .. */
+static void acpi_cstate_enter(struct acpi_processor_cx *cstate)
+{
+        if (cstate->space_id == ACPI_CSTATE_FFH) {
+                /* Call into architectural FFH based C-state */
+                acpi_processor_ffh_cstate_enter(cstate);
+        } else {
+                int unused;
+                /* IO port based C-state */
+                inb(cstate->address);
+                /* Dummy wait op - must do something useless after P_LVL2 read
+                   because chipsets cannot guarantee that STPCLK# signal
+                   gets asserted in time to freeze execution properly. */
+                unused = inl(acpi_fadt.xpm_tmr_blk.address);
+        }
+}
+
 static void acpi_processor_idle(void)
 {
         struct acpi_processor *pr = NULL;
@@ -361,11 +378,7 @@ static void acpi_processor_idle(void)
                 /* Get start time (ticks) */
                 t1 = inl(acpi_fadt.xpm_tmr_blk.address);
                 /* Invoke C2 */
-                inb(cx->address);
-                /* Dummy wait op - must do something useless after P_LVL2 read
-                   because chipsets cannot guarantee that STPCLK# signal
-                   gets asserted in time to freeze execution properly. */
-                t2 = inl(acpi_fadt.xpm_tmr_blk.address);
+                acpi_cstate_enter(cx);
                 /* Get end time (ticks) */
                 t2 = inl(acpi_fadt.xpm_tmr_blk.address);
 
@@ -401,9 +414,7 @@ static void acpi_processor_idle(void)
                 /* Get start time (ticks) */
                 t1 = inl(acpi_fadt.xpm_tmr_blk.address);
                 /* Invoke C3 */
-                inb(cx->address);
-                /* Dummy wait op (see above) */
-                t2 = inl(acpi_fadt.xpm_tmr_blk.address);
+                acpi_cstate_enter(cx);
                 /* Get end time (ticks) */
                 t2 = inl(acpi_fadt.xpm_tmr_blk.address);
                 if (pr->flags.bm_check) {
@@ -628,20 +639,16 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
         return 0;
 }
 
-static int acpi_processor_get_power_info_default_c1(struct acpi_processor *pr)
+static int acpi_processor_get_power_info_default(struct acpi_processor *pr)
 {
-
-        /* Zero initialize all the C-states info. */
-        memset(pr->power.states, 0, sizeof(pr->power.states));
-
-        /* set the first C-State to C1 */
-        pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
-
-        /* the C0 state only exists as a filler in our array,
-         * and all processors need to support C1 */
+        if (!pr->power.states[ACPI_STATE_C1].valid) {
+                /* set the first C-State to C1 */
+                /* all processors need to support C1 */
+                pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
+                pr->power.states[ACPI_STATE_C1].valid = 1;
+        }
+        /* the C0 state only exists as a filler in our array */
         pr->power.states[ACPI_STATE_C0].valid = 1;
-        pr->power.states[ACPI_STATE_C1].valid = 1;
-
         return 0;
 }
 
@@ -658,12 +665,7 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
         if (nocst)
                 return -ENODEV;
 
-        current_count = 1;
-
-        /* Zero initialize C2 onwards and prepare for fresh CST lookup */
-        for (i = 2; i < ACPI_PROCESSOR_MAX_POWER; i++)
-                memset(&(pr->power.states[i]), 0, 
-                                sizeof(struct acpi_processor_cx));
+        current_count = 0;
 
         status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer);
         if (ACPI_FAILURE(status)) {
@@ -718,22 +720,39 @@ static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
                     (reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE))
                         continue;
 
-                cx.address = (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) ?
-                    0 : reg->address;
-
                 /* There should be an easy way to extract an integer... */
                 obj = (union acpi_object *)&(element->package.elements[1]);
                 if (obj->type != ACPI_TYPE_INTEGER)
                         continue;
 
                 cx.type = obj->integer.value;
-
-                if ((cx.type != ACPI_STATE_C1) &&
-                    (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO))
-                        continue;
-
-                if ((cx.type < ACPI_STATE_C2) || (cx.type > ACPI_STATE_C3))
-                        continue;
+                /*
+                 * Some buggy BIOSes won't list C1 in _CST -
+                 * Let acpi_processor_get_power_info_default() handle them later
+                 */
+                if (i == 1 && cx.type != ACPI_STATE_C1)
+                        current_count++;
+
+                cx.address = reg->address;
+                cx.index = current_count + 1;
+
+                cx.space_id = ACPI_CSTATE_SYSTEMIO;
+                if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
+                        if (acpi_processor_ffh_cstate_probe
+                                        (pr->id, &cx, reg) == 0) {
+                                cx.space_id = ACPI_CSTATE_FFH;
+                        } else if (cx.type != ACPI_STATE_C1) {
+                                /*
+                                 * C1 is a special case where FIXED_HARDWARE
+                                 * can be handled in non-MWAIT way as well.
+                                 * In that case, save this _CST entry info.
+                                 * That is, we retain space_id of SYSTEM_IO for
+                                 * halt based C1.
+                                 * Otherwise, ignore this info and continue.
+                                 */
+                                continue;
+                        }
+                }
 
                 obj = (union acpi_object *)&(element->package.elements[2]);
                 if (obj->type != ACPI_TYPE_INTEGER)
@@ -938,12 +957,18 @@ static int acpi_processor_get_power_info(struct acpi_processor *pr)
         /* NOTE: the idle thread may not be running while calling
          * this function */
 
-        /* Adding C1 state */
-        acpi_processor_get_power_info_default_c1(pr);
+        /* Zero initialize all the C-states info. */
+        memset(pr->power.states, 0, sizeof(pr->power.states));
+
         result = acpi_processor_get_power_info_cst(pr);
         if (result == -ENODEV)
                 acpi_processor_get_power_info_fadt(pr);
 
+        if (result)
+                return result;
+
+        acpi_processor_get_power_info_default(pr);
+
         pr->power.count = acpi_processor_power_verify(pr);
 
         /*