OMAP3: PM: Update clean_l2 to use v7_flush_dcache_all

Analysis in TI kernel with ETM showed that using cache mapped flush
in kernel instead of SO mapped flush cost drops by 65% (3.39mS down
to 1.17mS) for clean_l2 which is used during sleep sequences.
Overall:
	- speed up
	- unfortunately there isn't a good alternative flush method today
	- code reduction and less maintenance and potential bug in
	  unmaintained code

This also fixes the bug with the clean_l2 function usage.
Reported-by: NTony Lindgren <tony@atomide.com>

Cc: Kevin Hilman <khilman@deeprootsystems.com>
Cc: Tony Lindgren <tony@atomide.com>
Acked-by: NSantosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: NJean Pihet <j-pihet@ti.com>

[nm@ti.com: ported rkw's proposal to 2.6.37-rc2]
Signed-off-by: NNishanth Menon <nm@ti.com>
Signed-off-by: NRichard Woodruff <r-woodruff2@ti.com>
Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>

arch/arm/mach-omap2/sleep34xx.S

@@ -520,72 +520,18 @@ clean_caches:
 	cmp	r9, #1 /* Check whether L2 inval is required or not*/
 	bne	skip_l2_inval
 clean_l2:
-	/* read clidr */
-	mrc     p15, 1, r0, c0, c0, 1
-	/* extract loc from clidr */
-	ands    r3, r0, #0x7000000
-	/* left align loc bit field */
-	mov     r3, r3, lsr #23
-	/* if loc is 0, then no need to clean */
-	beq     finished
-	/* start clean at cache level 0 */
-	mov     r10, #0
-loop1:
-	/* work out 3x current cache level */
-	add     r2, r10, r10, lsr #1
-	/* extract cache type bits from clidr*/
-	mov     r1, r0, lsr r2
-	/* mask of the bits for current cache only */
-	and     r1, r1, #7
-	/* see what cache we have at this level */
-	cmp     r1, #2
-	/* skip if no cache, or just i-cache */
-	blt     skip
-	/* select current cache level in cssr */
-	mcr     p15, 2, r10, c0, c0, 0
-	/* isb to sych the new cssr&csidr */
-	isb
-	/* read the new csidr */
-	mrc     p15, 1, r1, c0, c0, 0
-	/* extract the length of the cache lines */
-	and     r2, r1, #7
-	/* add 4 (line length offset) */
-	add     r2, r2, #4
-	ldr     r4, assoc_mask
-	/* find maximum number on the way size */
-	ands    r4, r4, r1, lsr #3
-	/* find bit position of way size increment */
-	clz     r5, r4
-	ldr     r7, numset_mask
-	/* extract max number of the index size*/
-	ands    r7, r7, r1, lsr #13
-loop2:
-	mov     r9, r4
-	/* create working copy of max way size*/
-loop3:
-	/* factor way and cache number into r11 */
-	orr     r11, r10, r9, lsl r5
-	/* factor index number into r11 */
-	orr     r11, r11, r7, lsl r2
-	/*clean & invalidate by set/way */
-	mcr     p15, 0, r11, c7, c10, 2
-	/* decrement the way*/
-	subs    r9, r9, #1
-	bge     loop3
-	/*decrement the index */
-	subs    r7, r7, #1
-	bge     loop2
-skip:
-	add     r10, r10, #2
-	/* increment cache number */
-	cmp     r3, r10
-	bgt     loop1
-finished:
-	/*swith back to cache level 0 */
-	mov     r10, #0
-	/* select current cache level in cssr */
-	mcr     p15, 2, r10, c0, c0, 0
-	isb
+	/*
+	 * Jump out to kernel flush routine
+	 *  - reuse that code is better
+	 *  - 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
+	 *  - lr is used since we are running in SRAM currently.
+	 */
+	ldr r1, kernel_flush
+	mov lr, pc
+	bx  r1
+
 skip_l2_inval:
 	/* Data memory barrier and Data sync barrier */
 	mov     r1, #0
@@ -668,5 +614,7 @@ cache_pred_disable_mask:
 	.word	0xFFFFE7FB
 control_stat:
 	.word	CONTROL_STAT
+kernel_flush:
+	.word v7_flush_dcache_all
 ENTRY(omap34xx_cpu_suspend_sz)
 	.word	. - omap34xx_cpu_suspend