OMAP3: PM: Clear the SCTLR C bit in asm code to prevent data cache allocation

On the newer ARM processors like CortexA8, CortexA9, the caches can be
speculatively loaded while they are getting flushed.

Clear the SCTLR C bit to prevent further data cache allocation as
part of cache clean routine

Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Kevin Hilman <khilman@ti.com>

arch/arm/mach-omap2/sleep34xx.S

@@ -246,6 +246,27 @@ clean_caches:
 	 *  - it executes in a cached space so is faster than refetch per-block
 	 *  - should be faster and will change with kernel
 	 *  - 'might' have to copy address, load and jump to it
+	 * Flush all data from the L1 data cache before disabling
+	 * SCTLR.C bit.
+	 */
+	ldr	r1, kernel_flush
+	mov	lr, pc
+	bx	r1
+
+	/*
+	 * Clear the SCTLR.C bit to prevent further data cache
+	 * allocation. Clearing SCTLR.C would make all the data accesses
+	 * strongly ordered and would not hit the cache.
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	bic	r0, r0, #(1 << 2)	@ Disable the C bit
+	mcr	p15, 0, r0, c1, c0, 0
+	isb
+
+	/*
+	 * Invalidate L1 data cache. Even though only invalidate is
+	 * necessary exported flush API is used here. Doing clean
+	 * on already clean cache would be almost NOP.
 	 */
 	ldr	r1, kernel_flush
 	blx	r1
@@ -295,6 +316,12 @@ omap3_do_wfi:
 	nop
 	bl wait_sdrc_ok
 
+	mrc	p15, 0, r0, c1, c0, 0
+	tst	r0, #(1 << 2)		@ Check C bit enabled?
+	orreq	r0, r0, #(1 << 2)	@ Enable the C bit if cleared
+	mcreq	p15, 0, r0, c1, c0, 0
+	isb
+
 /*
  * ===================================
  * == Exit point from non-OFF modes ==