[PATCH 08/12] ARM: OMAP2+: powerdomain: cache the powerdomain's previous power state

[Paul Walmsley]

Cache the powerdomain previous power state registers.  The objective
here is to avoid unneeded reads from the previous power state
registers.  Reads from these registers can be extremely slow, even by
I/O device standards.  I no longer recall the exact measurements, but
my recollection was that they cost several microseconds.

The cache is invalidated as part of the powerdomain pre-transition
code, which runs shortly before WFI/WFE.

Signed-off-by: Paul Walmsley <paul at pwsan.com>
Cc: Kevin Hilman <khilman at deeprootsystems.com>
---
 arch/arm/mach-omap2/powerdomain.c |    9 +++++++++
 arch/arm/mach-omap2/powerdomain.h |   14 ++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c
index 425c868..f5e2727 100644
--- a/arch/arm/mach-omap2/powerdomain.c
+++ b/arch/arm/mach-omap2/powerdomain.c
@@ -499,6 +499,9 @@ static int _pwrdm_read_prev_fpwrst(struct powerdomain *pwrdm)
 	if (!_pwrdm_pwrst_can_change(pwrdm))
 		return PWRDM_FUNC_PWRST_ON;
 
+	if (pwrdm->_flags & _PWRDM_PREV_FPWRST_IS_VALID)
+		return pwrdm->prev_fpwrst;
+
 	pwrst = arch_pwrdm->pwrdm_read_prev_pwrst(pwrdm);
 	if (pwrst < 0)
 		return pwrst;
@@ -512,6 +515,10 @@ static int _pwrdm_read_prev_fpwrst(struct powerdomain *pwrdm)
 	}
 
 	ret = _pwrdm_pwrst_to_fpwrst(pwrdm, pwrst, logic_pwrst, &fpwrst);
+	if (!ret) {
+		pwrdm->prev_fpwrst = fpwrst;
+		pwrdm->_flags |= _PWRDM_PREV_FPWRST_IS_VALID;
+	}
 
 	return (ret) ? ret : fpwrst;
 }
@@ -1017,6 +1024,8 @@ int pwrdm_clear_all_prev_pwrst(struct powerdomain *pwrdm)
 	pr_debug("powerdomain: %s: clearing previous power state reg\n",
 		 pwrdm->name);
 
+	pwrdm->_flags &= ~_PWRDM_PREV_FPWRST_IS_VALID;
+
 	if (arch_pwrdm && arch_pwrdm->pwrdm_clear_all_prev_pwrst)
 		ret = arch_pwrdm->pwrdm_clear_all_prev_pwrst(pwrdm);
 
diff --git a/arch/arm/mach-omap2/powerdomain.h b/arch/arm/mach-omap2/powerdomain.h
index 1fb21f5..f4a189a 100644
--- a/arch/arm/mach-omap2/powerdomain.h
+++ b/arch/arm/mach-omap2/powerdomain.h
@@ -90,8 +90,17 @@ enum pwrdm_func_state {
  *    powerdomain's next-functional-power-state -- struct
  *    powerdomain.next_fpwrst -- is valid.  If this bit is not set,
  *    the code needs to load the current value from the hardware.
+ *
+ * _PWRDM_PREV_FPWRST_IS_VALID: the locally-cached copy of the
+ *    powerdomain's previous-functional-power-state -- struct
+ *    powerdomain.prev_fpwrst -- is valid.  If this bit is not set,
+ *    the code needs to load the current value from the hardware.  The
+ *    previous-functional-power-state cache for the CORE and MPU needs
+ *    to be invalidated right before WFI, unless they were not programmed
+ *    to change power states.
  */
 #define _PWRDM_NEXT_FPWRST_IS_VALID	BIT(0)
+#define _PWRDM_PREV_FPWRST_IS_VALID	BIT(1)
 
 /*
  * Number of memory banks that are power-controllable.	On OMAP4430, the
@@ -138,6 +147,7 @@ struct powerdomain;
  * @fpwrst: current func power state (set in pwrdm_state_switch() or post_trans)
  * @fpwrst_counter: estimated number of times the pwrdm entered the power states
  * @next_fpwrst: cache of the powerdomain's next-power-state
+ * @prev_fpwrst: cache of the powerdomain's previous-power-state bitfield
  * @timer: sched_clock() timestamp of last pwrdm_state_switch()
  * @fpwrst_timer: estimated nanoseconds of residency in the various power states
  * @_lock: spinlock used to serialize powerdomain and some clockdomain ops
@@ -146,6 +156,9 @@ struct powerdomain;
  *
  * @prcm_partition possible values are defined in mach-omap2/prcm44xx.h.
  *
+ * @prev_fpwrst is updated during pwrdm_pre_transition(), but presumably
+ * should also be updated upon clock/IP block idle transitions.
+ *
  * Possible values for @_flags are documented above in the
  * "Powerdomain internal flags (struct powerdomain._flags)" comments.
  */
@@ -165,6 +178,7 @@ struct powerdomain {
 	const u8 prcm_partition;
 	u8 fpwrst;
 	u8 next_fpwrst;
+	u8 prev_fpwrst;
 	u8 _flags;
 	struct clockdomain *pwrdm_clkdms[PWRDM_MAX_CLKDMS];
 	struct list_head node;