OMAP3: PM: Fixes for low power code

index 5403bc4..8894c08 100644
@@ -145,8 +145,8 @@ ENTRY(save_secure_ram_context)
 	mov	r1, #0			@ set task id for ROM code in r1
 	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
-	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
-	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
 	nop
 	nop

@@ -316,9 +316,8 @@ omap3_do_wfi:
 	str	r5, [r4]		@ write back to SDRC_POWER register
 
 	/* Data memory barrier and Data sync barrier */
-	mov	r1, #0
-	mcr	p15, 0, r1, c7, c10, 4
-	mcr	p15, 0, r1, c7, c10, 5
+	dsb
+	dmb
 
 /*
  * ===================================

@@ -433,8 +432,8 @@ skipl2dis:
 	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
 	adr	r3, l2_inv_api_params	@ r3 points to dummy parameters
-	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
-	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
 	/* Write to Aux control register to set some bits */
 	mov	r0, #42			@ set service ID for PPA

@@ -444,8 +443,8 @@ skipl2dis:
 	mov	r6, #0xff
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4, #0xBC]		@ r3 points to parameters
-	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
-	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
 
 #ifdef CONFIG_OMAP3_L2_AUX_SECURE_SAVE_RESTORE

@@ -459,8 +458,8 @@ skipl2dis:
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4, #0xBC]
 	adds	r3, r3, #8		@ r3 points to parameters
-	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
-	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
 	smc	#1			@ call SMI monitor (smi #1)
 #endif
 	b	logic_l1_restore

index 8894c08..e58ec7d 100644
@@ -619,12 +619,17 @@ usettbr0:
 	ldr	r2, cache_pred_disable_mask
 	and	r4, r2
 	mcr	p15, 0, r4, c1, c0, 0
+	dsb
+	isb
+	ldr     r0, =restoremmu_on
+	bx      r0
 
 /*
  * ==============================
  * == Exit point from OFF mode ==
  * ==============================
  */
+restoremmu_on:
 	ldmfd	sp!, {r0-r12, pc}	@ restore regs and return
 
 

index e58ec7d..7f13336 100644
@@ -190,12 +190,12 @@ ENTRY(omap34xx_cpu_suspend)
 	stmfd	sp!, {r0-r12, lr}	@ save registers on stack
 
 	/*
-	 * r0 contains restore pointer in sdram
+	 * r0 contains CPU context save/restore pointer in sdram
 	 * r1 contains information about saving context:
 	 *   0 - No context lost
 	 *   1 - Only L1 and logic lost
-	 *   2 - Only L2 lost
-	 *   3 - Both L1 and L2 lost
+	 *   2 - Only L2 lost (Even L1 is retained we clean it along with L2)
+	 *   3 - Both L1 and L2 lost and logic lost
 	 */
 
 	/* Directly jump to WFI is the context save is not required */

@@ -280,15 +280,6 @@ l1_logic_lost:
 
 clean_caches:
 	/*
-	 * Clean Data or unified cache to POU
-	 * How to invalidate only L1 cache???? - #FIX_ME#
-	 * mcr	p15, 0, r11, c7, c11, 1
-	 */
-	cmp	r1, #0x1 		@ Check whether L2 inval is required
-	beq	omap3_do_wfi
-
-clean_l2:
-	/*
 	 * jump out to kernel flush routine
 	 *  - reuse that code is better
 	 *  - it executes in a cached space so is faster than refetch per-block

index 7f13336..d29476e 100644
@@ -216,66 +216,29 @@ save_context_wfi:
 	beq	clean_caches
 
 l1_logic_lost:
-	/* Store sp and spsr to SDRAM */
-	mov	r4, sp
-	mrs	r5, spsr
-	mov	r6, lr
+	mov	r4, sp			@ Store sp
+	mrs	r5, spsr		@ Store spsr
+	mov	r6, lr			@ Store lr
 	stmia	r8!, {r4-r6}
-	/* Save all ARM registers */
-	/* Coprocessor access control register */
-	mrc	p15, 0, r6, c1, c0, 2
-	stmia	r8!, {r6}
-	/* TTBR0, TTBR1 and Translation table base control */
-	mrc	p15, 0, r4, c2, c0, 0
-	mrc	p15, 0, r5, c2, c0, 1
-	mrc	p15, 0, r6, c2, c0, 2
-	stmia	r8!, {r4-r6}
-	/*
-	 * Domain access control register, data fault status register,
-	 * and instruction fault status register
-	 */
-	mrc	p15, 0, r4, c3, c0, 0
-	mrc	p15, 0, r5, c5, c0, 0
-	mrc	p15, 0, r6, c5, c0, 1
-	stmia	r8!, {r4-r6}
-	/*
-	 * Data aux fault status register, instruction aux fault status,
-	 * data fault address register and instruction fault address register
-	 */
-	mrc	p15, 0, r4, c5, c1, 0
-	mrc	p15, 0, r5, c5, c1, 1
-	mrc	p15, 0, r6, c6, c0, 0
-	mrc	p15, 0, r7, c6, c0, 2
-	stmia	r8!, {r4-r7}
-	/*
-	 * user r/w thread and process ID, user r/o thread and process ID,
-	 * priv only thread and process ID, cache size selection
-	 */
-	mrc	p15, 0, r4, c13, c0, 2
-	mrc	p15, 0, r5, c13, c0, 3
-	mrc	p15, 0, r6, c13, c0, 4
-	mrc	p15, 2, r7, c0, c0, 0
+
+	mrc	p15, 0, r4, c1, c0, 2	@ Coprocessor access control register
+	mrc	p15, 0, r5, c2, c0, 0	@ TTBR0
+	mrc	p15, 0, r6, c2, c0, 1	@ TTBR1
+	mrc	p15, 0, r7, c2, c0, 2	@ TTBCR
 	stmia	r8!, {r4-r7}
-	/* Data TLB lockdown, instruction TLB lockdown registers */
-	mrc	p15, 0, r5, c10, c0, 0
-	mrc	p15, 0, r6, c10, c0, 1
-	stmia	r8!, {r5-r6}
-	/* Secure or non secure vector base address, FCSE PID, Context PID*/
-	mrc	p15, 0, r4, c12, c0, 0
-	mrc	p15, 0, r5, c13, c0, 0
-	mrc	p15, 0, r6, c13, c0, 1
-	stmia	r8!, {r4-r6}
-	/* Primary remap, normal remap registers */
-	mrc	p15, 0, r4, c10, c2, 0
-	mrc	p15, 0, r5, c10, c2, 1
-	stmia	r8!,{r4-r5}
 
-	/* Store current cpsr*/
-	mrs	r2, cpsr
-	stmia	r8!, {r2}
+	mrc	p15, 0, r4, c3, c0, 0	@ Domain access Control Register
+	mrc	p15, 0, r5, c10, c2, 0	@ PRRR
+	mrc	p15, 0, r6, c10, c2, 1	@ NMRR
+	stmia	r8!,{r4-r6}
+
+	mrc	p15, 0, r4, c13, c0, 1	@ Context ID
+	mrc	p15, 0, r5, c13, c0, 2	@ User r/w thread and process ID
+	mrc	p15, 0, r6, c12, c0, 0	@ Secure or NS vector base address
+	mrs	r7, cpsr		@ Store current cpsr
+	stmia	r8!, {r4-r7}
 
-	mrc	p15, 0, r4, c1, c0, 0
-	/* save control register */
+	mrc	p15, 0, r4, c1, c0, 0	@ save control register
 	stmia	r8!, {r4}
 
 clean_caches:

@@ -491,68 +454,29 @@ skipl2reen:
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4,#0xBC]
 	adds	r3, r3, #16
+
 	ldmia	r3!, {r4-r6}
-	mov	sp, r4
-	msr	spsr_cxsf, r5
-	mov	lr, r6
-
-	ldmia	r3!, {r4-r9}
-	/* Coprocessor access Control Register */
-	mcr p15, 0, r4, c1, c0, 2
-
-	/* TTBR0 */
-	MCR p15, 0, r5, c2, c0, 0
-	/* TTBR1 */
-	MCR p15, 0, r6, c2, c0, 1
-	/* Translation table base control register */
-	MCR p15, 0, r7, c2, c0, 2
-	/* Domain access Control Register */
-	MCR p15, 0, r8, c3, c0, 0
-	/* Data fault status Register */
-	MCR p15, 0, r9, c5, c0, 0
-
-	ldmia	r3!,{r4-r8}
-	/* Instruction fault status Register */
-	MCR p15, 0, r4, c5, c0, 1
-	/* Data Auxiliary Fault Status Register */
-	MCR p15, 0, r5, c5, c1, 0
-	/* Instruction Auxiliary Fault Status Register*/
-	MCR p15, 0, r6, c5, c1, 1
-	/* Data Fault Address Register */
-	MCR p15, 0, r7, c6, c0, 0
-	/* Instruction Fault Address Register*/
-	MCR p15, 0, r8, c6, c0, 2
-	ldmia	r3!,{r4-r7}
+	mov	sp, r4			@ Restore sp
+	msr	spsr_cxsf, r5		@ Restore spsr
+	mov	lr, r6			@ Restore lr
 
-	/* User r/w thread and process ID */
-	MCR p15, 0, r4, c13, c0, 2
-	/* User ro thread and process ID */
-	MCR p15, 0, r5, c13, c0, 3
-	/* Privileged only thread and process ID */
-	MCR p15, 0, r6, c13, c0, 4
-	/* Cache size selection */
-	MCR p15, 2, r7, c0, c0, 0
-	ldmia	r3!,{r4-r8}
-	/* Data TLB lockdown registers */
-	MCR p15, 0, r4, c10, c0, 0
-	/* Instruction TLB lockdown registers */
-	MCR p15, 0, r5, c10, c0, 1
-	/* Secure or Nonsecure Vector Base Address */
-	MCR p15, 0, r6, c12, c0, 0
-	/* FCSE PID */
-	MCR p15, 0, r7, c13, c0, 0
-	/* Context PID */
-	MCR p15, 0, r8, c13, c0, 1
-
-	ldmia	r3!,{r4-r5}
-	/* Primary memory remap register */
-	MCR p15, 0, r4, c10, c2, 0
-	/* Normal memory remap register */
-	MCR p15, 0, r5, c10, c2, 1
-
-	/* Restore cpsr */
-	ldmia	r3!,{r4}		@ load CPSR from SDRAM
-	msr	cpsr, r4		@ store cpsr
+	ldmia	r3!, {r4-r7}
+	mcr	p15, 0, r4, c1, c0, 2	@ Coprocessor access Control Register
+	mcr	p15, 0, r5, c2, c0, 0	@ TTBR0
+	mcr	p15, 0, r6, c2, c0, 1	@ TTBR1
+	mcr	p15, 0, r7, c2, c0, 2	@ TTBCR
+
+	ldmia	r3!,{r4-r6}
+	mcr	p15, 0, r4, c3, c0, 0	@ Domain access Control Register
+	mcr	p15, 0, r5, c10, c2, 0	@ PRRR
+	mcr	p15, 0, r6, c10, c2, 1	@ NMRR
+
+
+	ldmia	r3!,{r4-r7}
+	mcr	p15, 0, r4, c13, c0, 1	@ Context ID
+	mcr	p15, 0, r5, c13, c0, 2	@ User r/w thread and process ID
+	mrc	p15, 0, r6, c12, c0, 0	@ Secure or NS vector base address
+	msr	cpsr, r7		@ store cpsr
 
 	/* Enabling MMU here */
 	mrc	p15, 0, r7, c2, c0, 2 	@ Read TTBRControl

index d29476e..63f1066 100644
@@ -248,6 +248,27 @@ 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

@@ -297,6 +318,12 @@ 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 ==