OMAP3: rework of the ASM sleep code execution paths

- Reworked and simplified the execution paths for better
  readability and to avoid duplication of code,
- Added comments on the entry and exit points and the interaction
  with the ROM code for OFF mode restore,
- Reworked the existing comments for better readability.

Tested on N900 and Beagleboard with full RET and OFF modes,
using cpuidle and suspend.

Signed-off-by: Jean Pihet <j-pihet@ti.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Kevin Hilman <khilman@deeprootsystems.com>

1 files changed, 187 insertions, 131 deletions

diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index 5b978b8..06e4732 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -71,6 +71,13 @@
  * API functions
  */
 
+/*
+ * The "get_*restore_pointer" functions are used to provide a
+ * physical restore address where the ROM code jumps while waking
+ * up from MPU OFF/OSWR state.
+ * The restore pointer is stored into the scratchpad.
+ */
+
 	.text
 /* Function call to get the restore pointer for resume from OFF */
 ENTRY(get_restore_pointer)
@@ -102,7 +109,7 @@ ENTRY(get_es3_restore_pointer_sz)
 /*
  * L2 cache needs to be toggled for stable OFF mode functionality on 3630.
  * This function sets up a flag that will allow for this toggling to take
- * place on 3630. Hopefully some version in the future maynot need this
+ * place on 3630. Hopefully some version in the future may not need this.
  */
 ENTRY(enable_omap3630_toggle_l2_on_restore)
         stmfd   sp!, {lr}     @ save registers on stack
@@ -144,34 +151,162 @@ ENTRY(save_secure_ram_context_sz)
 	.word	. - save_secure_ram_context
 
 /*
+ * ======================
+ * == Idle entry point ==
+ * ======================
+ */
+
+/*
  * Forces OMAP into idle state
  *
- * omap34xx_suspend() - This bit of code just executes the WFI
- * for normal idles.
+ * omap34xx_cpu_suspend() - This bit of code saves the CPU context if needed
+ * and executes the WFI instruction. Calling WFI effectively changes the
+ * power domains states to the desired target power states.
+ *
  *
- * Note: This code get's copied to internal SRAM at boot. When the OMAP
- *	 wakes up it continues execution at the point it went to sleep.
+ * Notes:
+ * - this code gets copied to internal SRAM at boot. The execution pointer
+ *   in SRAM is _omap_sram_idle.
+ * - when the OMAP wakes up it continues at different execution points
+ *   depending on the low power mode (non-OFF vs OFF modes),
+ *   cf. 'Resume path for xxx mode' comments.
  */
 ENTRY(omap34xx_cpu_suspend)
 	stmfd	sp!, {r0-r12, lr}		@ save registers on stack
 
-	/* r0 contains restore pointer in sdram */
-	/* r1 contains information about saving context */
-	ldr     r4, sdrc_power          @ read the SDRC_POWER register
-	ldr     r5, [r4]                @ read the contents of SDRC_POWER
-	orr     r5, r5, #0x40           @ enable self refresh on idle req
-	str     r5, [r4]                @ write back to SDRC_POWER register
+	/*
+	 * r0 contains 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
+	 */
 
+	/* Directly jump to WFI is the context save is not required */
 	cmp	r1, #0x0
-	/* If context save is required, do that and execute wfi */
-	bne	save_context_wfi
+	beq	omap3_do_wfi
+
+	/* Otherwise fall through to the save context code */
+save_context_wfi:
+	mov	r8, r0			@ Store SDRAM address in r8
+	mrc	p15, 0, r5, c1, c0, 1	@ Read Auxiliary Control Register
+	mov	r4, #0x1		@ Number of parameters for restore call
+	stmia	r8!, {r4-r5}		@ Push parameters for restore call
+	mrc	p15, 1, r5, c9, c0, 2	@ Read L2 AUX ctrl register
+	stmia	r8!, {r4-r5}		@ Push parameters for restore call
+
+        /* Check what that target sleep state is from r1 */
+	cmp	r1, #0x2		@ Only L2 lost, no need to save context
+	beq	clean_caches
+
+l1_logic_lost:
+	/* Store sp and spsr to SDRAM */
+	mov	r4, sp
+	mrs	r5, spsr
+	mov	r6, 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
+	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, c1, c0, 0
+	/* save control register */
+	stmia	r8!, {r4}
+
+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
+	 *  - should be faster and will change with kernel
+	 *  - 'might' have to copy address, load and jump to it
+	 */
+	ldr r1, kernel_flush
+	mov lr, pc
+	bx  r1
+
+omap3_do_wfi:
+	ldr	r4, sdrc_power		@ read the SDRC_POWER register
+	ldr	r5, [r4]		@ read the contents of SDRC_POWER
+	orr	r5, r5, #0x40		@ enable self refresh on idle req
+	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
 
+/*
+ * ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
 	wfi				@ wait for interrupt
 
+/*
+ * ===================================
+ * == Resume path for non-OFF modes ==
+ * ===================================
+ */
 	nop
 	nop
 	nop
@@ -184,7 +319,29 @@ ENTRY(omap34xx_cpu_suspend)
 	nop
 	bl wait_sdrc_ok
 
-	ldmfd	sp!, {r0-r12, pc}		@ restore regs and return
+/*
+ * ===================================
+ * == Exit point from non-OFF modes ==
+ * ===================================
+ */
+	ldmfd	sp!, {r0-r12, pc}	@ restore regs and return
+
+
+/*
+ * ==============================
+ * == Resume path for OFF mode ==
+ * ==============================
+ */
+
+/*
+ * The restore_* functions are called by the ROM code
+ *  when back from WFI in OFF mode.
+ * Cf. the get_*restore_pointer functions.
+ *
+ *  restore_es3: applies to 34xx >= ES3.0
+ *  restore_3630: applies to 36xx
+ *  restore: common code for 3xxx
+ */
 restore_es3:
 	ldr	r5, pm_prepwstst_core_p
 	ldr	r4, [r5]
@@ -214,12 +371,17 @@ restore_3630:
 	ldr	r1, control_mem_rta
 	mov	r2, #OMAP36XX_RTA_DISABLE
 	str	r2, [r1]
-	/* Fall thru for the remaining logic */
+
+	/* Fall through to common code for the remaining logic */
+
 restore:
-        /* Check what was the reason for mpu reset and store the reason in r9*/
-        /* 1 - Only L1 and logic lost */
-        /* 2 - Only L2 lost - In this case, we wont be here */
-        /* 3 - Both L1 and L2 lost */
+        /*
+	 * Check what was the reason for mpu reset and store the reason in r9:
+	 *  0 - No context lost
+         *  1 - Only L1 and logic lost
+         *  2 - Only L2 lost - In this case, we wont be here
+         *  3 - Both L1 and L2 lost
+	 */
 	ldr     r1, pm_pwstctrl_mpu
 	ldr	r2, [r1]
 	and     r2, r2, #0x3
@@ -422,119 +584,12 @@ usettbr0:
 	and	r4, r2
 	mcr	p15, 0, r4, c1, c0, 0
 
+/*
+ * ==============================
+ * == Exit point from OFF mode ==
+ * ==============================
+ */
 	ldmfd	sp!, {r0-r12, pc}		@ restore regs and return
-save_context_wfi:
-	mov	r8, r0 /* Store SDRAM address in r8 */
-	mrc	p15, 0, r5, c1, c0, 1	@ Read Auxiliary Control Register
-	mov	r4, #0x1		@ Number of parameters for restore call
-	stmia	r8!, {r4-r5}		@ Push parameters for restore call
-	mrc	p15, 1, r5, c9, c0, 2	@ Read L2 AUX ctrl register
-	stmia	r8!, {r4-r5}		@ Push parameters for restore call
-        /* Check what that target sleep state is:stored in r1*/
-        /* 1 - Only L1 and logic lost */
-        /* 2 - Only L2 lost */
-        /* 3 - Both L1 and L2 lost */
-	cmp	r1, #0x2 /* Only L2 lost */
-	beq	clean_l2
-	cmp	r1, #0x1 /* L2 retained */
-	/* r9 stores whether to clean L2 or not*/
-	moveq	r9, #0x0 /* Dont Clean L2 */
-	movne	r9, #0x1 /* Clean L2 */
-l1_logic_lost:
-	/* Store sp and spsr to SDRAM */
-	mov	r4, sp
-	mrs	r5, spsr
-	mov	r6, 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,
-	datat 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
-	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, c1, c0, 0
-	/* save control register */
-	stmia	r8!, {r4}
-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	r9, #1 /* Check whether L2 inval is required or not*/
-	bne	skip_l2_inval
-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
-	 *  - 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
-	mcr     p15, 0, r1, c7, c10, 4
-	mcr     p15, 0, r1, c7, c10, 5
-
-	wfi                             @ wait for interrupt
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	bl wait_sdrc_ok
-	/* restore regs and return */
-	ldmfd   sp!, {r0-r12, pc}
 
 
 /*
@@ -687,5 +742,6 @@ kick_counter:
 	.word	0
 wait_dll_lock_counter:
 	.word	0
+
 ENTRY(omap34xx_cpu_suspend_sz)
 	.word	. - omap34xx_cpu_suspend