ARM: tegra: Use WFE for power-gating on Tegra30

Turned out that WFI doesn't work reliably on Tegra30 as a trigger for
the power-gating, it causes CPU hang under some circumstances like having
memory controller running of PLLP. The TRM doc states that WFI should be
used for the Big-Little "Cluster Switch", while WFE for the power-gating.
Hence let's use the WFE for CPU0 power-gating, like it is done for the
power-gating of a secondary cores. This fixes CPU hang after entering LP2
with memory running off PLLP.
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Peter Geis <pgwipeout@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>

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

@@ -682,10 +682,12 @@ tegra30_enter_sleep:
 	dsb
 	ldr	r0, [r6, r2] /* memory barrier */
 
+	cmp	r10, #TEGRA30
 halted:
 	isb
 	dsb
-	wfi	/* CPU should be power gated here */
+	wfine	/* CPU should be power gated here */
+	wfeeq
 
 	/* !!!FIXME!!! Implement halt failure handler */
 	b	halted

drivers/soc/tegra/flowctrl.c

@@ -91,8 +91,23 @@ void flowctrl_cpu_suspend_enter(unsigned int cpuid)
 		reg &= ~TEGRA30_FLOW_CTRL_CSR_WFE_BITMAP;
 		/* clear wfi bitmap */
 		reg &= ~TEGRA30_FLOW_CTRL_CSR_WFI_BITMAP;
-		/* pwr gating on wfi */
-		reg |= TEGRA30_FLOW_CTRL_CSR_WFI_CPU0 << cpuid;
+
+		if (tegra_get_chip_id() == TEGRA30) {
+			/*
+			 * The wfi doesn't work well on Tegra30 because
+			 * CPU hangs under some odd circumstances after
+			 * power-gating (like memory running off PLLP),
+			 * hence use wfe that is working perfectly fine.
+			 * Note that Tegra30 TRM doc clearly stands that
+			 * wfi should be used for the "Cluster Switching",
+			 * while wfe for the power-gating, just like it
+			 * is done on Tegra20.
+			 */
+			reg |= TEGRA20_FLOW_CTRL_CSR_WFE_CPU0 << cpuid;
+		} else {
+			/* pwr gating on wfi */
+			reg |= TEGRA30_FLOW_CTRL_CSR_WFI_CPU0 << cpuid;
+		}
 		break;
 	}
 	reg |= FLOW_CTRL_CSR_INTR_FLAG;			/* clear intr flag */