ARM: tegra: Ensure entire dcache is flushed on entering LP0/1

Tegra support several low-power (LPx) states, which are:
- LP0: CPU + Core voltage off and DRAM in self-refresh
- LP1: CPU voltage off and DRAM in self-refresh
- LP2: CPU voltage off

When entering any of the above states the tegra_disable_clean_inv_dcache()
function is called to flush the dcache. The function
tegra_disable_clean_inv_dcache() will either flush the entire data cache or
up to the Level of Unification Inner Shareable (LoUIS) depending on the
value in r0. When tegra_disable_clean_inv_dcache() is called by
tegra20_sleep_core_finish() or tegra30_sleep_core_finish(), to enter LP0
and LP1 power state, the r0 register contains a physical memory address
which will not be equal to TEGRA_FLUSH_CACHE_ALL (1) and so the data cache
will be only flushed to the LoUIS. However, when
tegra_disable_clean_inv_dcache() called by tegra_sleep_cpu_finish() to
enter to LP2 power state, r0 is set to TEGRA_FLUSH_CACHE_ALL to flush the
entire dcache.

Please note that tegra20_sleep_core_finish(), tegra30_sleep_core_finish()
and tegra_sleep_cpu_finish() are called by the boot CPU once all other CPUs
have been disabled and so it seems appropriate to flush the entire cache at
this stage.

Therefore, ensure that r0 is set to TEGRA_FLUSH_CACHE_ALL when calling
tegra_disable_clean_inv_dcache() from tegra20_sleep_core_finish() and
tegra30_sleep_core_finish().

Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Joseph Lo <josephl@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>

arch/arm/mach-tegra/sleep-tegra20.S

@@ -231,8 +231,11 @@ ENDPROC(tegra20_cpu_is_resettable_soon)
  * tegra20_tear_down_core in IRAM
  */
 ENTRY(tegra20_sleep_core_finish)
+	mov     r4, r0
 	/* Flush, disable the L1 data cache and exit SMP */
+	mov     r0, #TEGRA_FLUSH_CACHE_ALL
 	bl	tegra_disable_clean_inv_dcache
+	mov     r0, r4
 
 	mov32	r3, tegra_shut_off_mmu
 	add	r3, r3, r0

arch/arm/mach-tegra/sleep-tegra30.S

@@ -242,8 +242,11 @@ ENDPROC(tegra30_cpu_shutdown)
  * tegra30_tear_down_core in IRAM
  */
 ENTRY(tegra30_sleep_core_finish)
+	mov	r4, r0
 	/* Flush, disable the L1 data cache and exit SMP */
+	mov	r0, #TEGRA_FLUSH_CACHE_ALL
 	bl	tegra_disable_clean_inv_dcache
+	mov	r0, r4
 
 	/*
 	 * Preload all the address literals that are needed for the