1 files changed, 466 insertions, 370 deletions

diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index 2fb205a7f285..98d8232808b8 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -1,6 +1,4 @@
 /*
- * linux/arch/arm/mach-omap2/sleep.S
- *
  * (C) Copyright 2007
  * Texas Instruments
  * Karthik Dasu <karthik-dp@ti.com>
@@ -26,28 +24,35 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <plat/sram.h>
 #include <mach/io.h>
 
-#include "cm.h"
-#include "prm.h"
+#include "cm2xxx_3xxx.h"
+#include "prm2xxx_3xxx.h"
 #include "sdrc.h"
 #include "control.h"
 
-#define SDRC_SCRATCHPAD_SEM_V   0xfa00291c
-
-#define PM_PREPWSTST_CORE_V     OMAP34XX_PRM_REGADDR(CORE_MOD, \
-                                OMAP3430_PM_PREPWSTST)
-#define PM_PREPWSTST_CORE_P     0x48306AE8
-#define PM_PREPWSTST_MPU_V      OMAP34XX_PRM_REGADDR(MPU_MOD, \
-                                OMAP3430_PM_PREPWSTST)
+/*
+ * Registers access definitions
+ */
+#define SDRC_SCRATCHPAD_SEM_OFFS        0xc
+#define SDRC_SCRATCHPAD_SEM_V   OMAP343X_SCRATCHPAD_REGADDR\
+                                        (SDRC_SCRATCHPAD_SEM_OFFS)
+#define PM_PREPWSTST_CORE_P     OMAP3430_PRM_BASE + CORE_MOD +\
+                                        OMAP3430_PM_PREPWSTST
 #define PM_PWSTCTRL_MPU_P       OMAP3430_PRM_BASE + MPU_MOD + OMAP2_PM_PWSTCTRL
 #define CM_IDLEST1_CORE_V       OMAP34XX_CM_REGADDR(CORE_MOD, CM_IDLEST1)
-#define SRAM_BASE_P             0x40200000
-#define CONTROL_STAT            0x480022F0
-#define SCRATCHPAD_MEM_OFFS     0x310 /* Move this as correct place is
-                                       * available */
-#define SCRATCHPAD_BASE_P       (OMAP343X_CTRL_BASE + OMAP343X_CONTROL_MEM_WKUP\
-                                                + SCRATCHPAD_MEM_OFFS)
+#define CM_IDLEST_CKGEN_V       OMAP34XX_CM_REGADDR(PLL_MOD, CM_IDLEST)
+#define SRAM_BASE_P             OMAP3_SRAM_PA
+#define CONTROL_STAT            OMAP343X_CTRL_BASE + OMAP343X_CONTROL_STATUS
+#define CONTROL_MEM_RTA_CTRL    (OMAP343X_CTRL_BASE +\
+                                        OMAP36XX_CONTROL_MEM_RTA_CTRL)
+
+/* Move this as correct place is available */
+#define SCRATCHPAD_MEM_OFFS     0x310
+#define SCRATCHPAD_BASE_P       (OMAP343X_CTRL_BASE +\
+                                        OMAP343X_CONTROL_MEM_WKUP +\
+                                        SCRATCHPAD_MEM_OFFS)
 #define SDRC_POWER_V            OMAP34XX_SDRC_REGADDR(SDRC_POWER)
 #define SDRC_SYSCONFIG_P        (OMAP343X_SDRC_BASE + SDRC_SYSCONFIG)
 #define SDRC_MR_0_P             (OMAP343X_SDRC_BASE + SDRC_MR_0)
@@ -59,48 +64,38 @@
 #define SDRC_DLLA_STATUS_V      OMAP34XX_SDRC_REGADDR(SDRC_DLLA_STATUS)
 #define SDRC_DLLA_CTRL_V        OMAP34XX_SDRC_REGADDR(SDRC_DLLA_CTRL)
 
-        .text
-/* Function to acquire the semaphore in scratchpad */
-ENTRY(lock_scratchpad_sem)
-        stmfd   sp!, {lr}       @ save registers on stack
-wait_sem:
-        mov     r0,#1
-        ldr     r1, sdrc_scratchpad_sem
-wait_loop:
-        ldr     r2, [r1]        @ load the lock value
-        cmp     r2, r0          @ is the lock free ?
-        beq     wait_loop       @ not free...
-        swp     r2, r0, [r1]    @ semaphore free so lock it and proceed
-        cmp     r2, r0          @ did we succeed ?
-        beq     wait_sem        @ no - try again
-        ldmfd   sp!, {pc}       @ restore regs and return
-sdrc_scratchpad_sem:
-        .word SDRC_SCRATCHPAD_SEM_V
-ENTRY(lock_scratchpad_sem_sz)
-        .word   . - lock_scratchpad_sem
-
-        .text
-/* Function to release the scratchpad semaphore */
-ENTRY(unlock_scratchpad_sem)
-        stmfd   sp!, {lr}       @ save registers on stack
-        ldr     r3, sdrc_scratchpad_sem
-        mov     r2,#0
-        str     r2,[r3]
-        ldmfd   sp!, {pc}       @ restore regs and return
-ENTRY(unlock_scratchpad_sem_sz)
-        .word   . - unlock_scratchpad_sem
+
+/*
+ * 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)
-        stmfd   sp!, {lr}     @ save registers on stack
+        stmfd   sp!, {lr}       @ save registers on stack
         adr     r0, restore
-        ldmfd   sp!, {pc}     @ restore regs and return
+        ldmfd   sp!, {pc}       @ restore regs and return
 ENTRY(get_restore_pointer_sz)
-        .word   . - get_restore_pointer
+        .word   . - get_restore_pointer
 
         .text
-/* Function call to get the restore pointer for for ES3 to resume from OFF */
+/* Function call to get the restore pointer for 3630 resume from OFF */
+ENTRY(get_omap3630_restore_pointer)
+        stmfd   sp!, {lr}       @ save registers on stack
+        adr     r0, restore_3630
+        ldmfd   sp!, {pc}       @ restore regs and return
+ENTRY(get_omap3630_restore_pointer_sz)
+        .word   . - get_omap3630_restore_pointer
+
+        .text
+/* Function call to get the restore pointer for ES3 to resume from OFF */
 ENTRY(get_es3_restore_pointer)
         stmfd   sp!, {lr}       @ save registers on stack
         adr     r0, restore_es3
@@ -108,54 +103,23 @@ ENTRY(get_es3_restore_pointer)
 ENTRY(get_es3_restore_pointer_sz)
         .word   . - get_es3_restore_pointer
 
-ENTRY(es3_sdrc_fix)
-        ldr     r4, sdrc_syscfg         @ get config addr
-        ldr     r5, [r4]                @ get value
-        tst     r5, #0x100              @ is part access blocked
-        it      eq
-        biceq   r5, r5, #0x100          @ clear bit if set
-        str     r5, [r4]                @ write back change
-        ldr     r4, sdrc_mr_0           @ get config addr
-        ldr     r5, [r4]                @ get value
-        str     r5, [r4]                @ write back change
-        ldr     r4, sdrc_emr2_0         @ get config addr
-        ldr     r5, [r4]                @ get value
-        str     r5, [r4]                @ write back change
-        ldr     r4, sdrc_manual_0       @ get config addr
-        mov     r5, #0x2                @ autorefresh command
-        str     r5, [r4]                @ kick off refreshes
-        ldr     r4, sdrc_mr_1           @ get config addr
-        ldr     r5, [r4]                @ get value
-        str     r5, [r4]                @ write back change
-        ldr     r4, sdrc_emr2_1         @ get config addr
-        ldr     r5, [r4]                @ get value
-        str     r5, [r4]                @ write back change
-        ldr     r4, sdrc_manual_1       @ get config addr
-        mov     r5, #0x2                @ autorefresh command
-        str     r5, [r4]                @ kick off refreshes
-        bx      lr
-sdrc_syscfg:
-        .word   SDRC_SYSCONFIG_P
-sdrc_mr_0:
-        .word   SDRC_MR_0_P
-sdrc_emr2_0:
-        .word   SDRC_EMR2_0_P
-sdrc_manual_0:
-        .word   SDRC_MANUAL_0_P
-sdrc_mr_1:
-        .word   SDRC_MR_1_P
-sdrc_emr2_1:
-        .word   SDRC_EMR2_1_P
-sdrc_manual_1:
-        .word   SDRC_MANUAL_1_P
-ENTRY(es3_sdrc_fix_sz)
-        .word   . - es3_sdrc_fix
+        .text
+/*
+ * 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 may not need this.
+ */
+ENTRY(enable_omap3630_toggle_l2_on_restore)
+        stmfd   sp!, {lr}       @ save registers on stack
+        /* Setup so that we will disable and enable l2 */
+        mov     r1, #0x1
+        str     r1, l2dis_3630
+        ldmfd   sp!, {pc}       @ restore regs and return
 
+        .text
 /* Function to call rom code to save secure ram context */
 ENTRY(save_secure_ram_context)
         stmfd   sp!, {r1-r12, lr}       @ save registers on stack
-save_secure_ram_debug:
-        /* b save_secure_ram_debug */   @ enable to debug save code
         adr     r3, api_params          @ r3 points to parameters
         str     r0, [r3,#0x4]           @ r0 has sdram address
         ldr     r12, high_mask
@@ -185,35 +149,162 @@ 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 and after wake-up
+ *   from OFF mode. 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
-loop:
-        /*b     loop*/  @Enable to debug by stepping through code
-        /* 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
+        stmfd   sp!, {r0-r12, lr}       @ save registers on stack
 
+        /*
+         * 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
@@ -226,9 +317,30 @@ loop:
         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:
-        /*b restore_es3*/               @ Enable to debug restore code
         ldr     r5, pm_prepwstst_core_p
         ldr     r4, [r5]
         and     r4, r4, #0x3
@@ -245,82 +357,117 @@ copy_to_sram:
         bne     copy_to_sram
         ldr     r1, sram_base
         blx     r1
+        b       restore
+
+restore_3630:
+        ldr     r1, pm_prepwstst_core_p
+        ldr     r2, [r1]
+        and     r2, r2, #0x3
+        cmp     r2, #0x0        @ Check if previous power state of CORE is OFF
+        bne     restore
+        /* Disable RTA before giving control */
+        ldr     r1, control_mem_rta
+        mov     r2, #OMAP36XX_RTA_DISABLE
+        str     r2, [r1]
+
+        /* Fall through to common code for the remaining logic */
+
 restore:
-        /* b restore*/  @ Enable to debug restore code
-        /* 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 */
-        ldr     r1, pm_pwstctrl_mpu
+        /*
+         * 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
-        cmp     r2, #0x0        @ Check if target power state was OFF or RET
-        moveq   r9, #0x3        @ MPU OFF => L1 and L2 lost
+        and     r2, r2, #0x3
+        cmp     r2, #0x0        @ Check if target power state was OFF or RET
+        moveq   r9, #0x3        @ MPU OFF => L1 and L2 lost
         movne   r9, #0x1        @ Only L1 and L2 lost => avoid L2 invalidation
         bne     logic_l1_restore
+
+        ldr     r0, l2dis_3630
+        cmp     r0, #0x1        @ should we disable L2 on 3630?
+        bne     skipl2dis
+        mrc     p15, 0, r0, c1, c0, 1
+        bic     r0, r0, #2      @ disable L2 cache
+        mcr     p15, 0, r0, c1, c0, 1
+skipl2dis:
         ldr     r0, control_stat
         ldr     r1, [r0]
         and     r1, #0x700
         cmp     r1, #0x300
         beq     l2_inv_gp
-        mov     r0, #40         @ set service ID for PPA
-        mov     r12, r0         @ copy secure Service ID in r12
-        mov     r1, #0          @ set task id for ROM code in r1
-        mov     r2, #4          @ set some flags in r2, r6
+        mov     r0, #40                 @ set service ID for PPA
+        mov     r12, r0                 @ copy secure Service ID in r12
+        mov     r1, #0                  @ set task id for ROM code in r1
+        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
         .word   0xE1600071              @ call SMI monitor (smi #1)
         /* Write to Aux control register to set some bits */
-        mov     r0, #42         @ set service ID for PPA
-        mov     r12, r0         @ copy secure Service ID in r12
-        mov     r1, #0          @ set task id for ROM code in r1
-        mov     r2, #4          @ set some flags in r2, r6
+        mov     r0, #42                 @ set service ID for PPA
+        mov     r12, r0                 @ copy secure Service ID in r12
+        mov     r1, #0                  @ set task id for ROM code in r1
+        mov     r2, #4                  @ set some flags in r2, r6
         mov     r6, #0xff
         ldr     r4, scratchpad_base
-        ldr     r3, [r4, #0xBC] @ r3 points to parameters
+        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
         .word   0xE1600071              @ call SMI monitor (smi #1)
 
 #ifdef CONFIG_OMAP3_L2_AUX_SECURE_SAVE_RESTORE
         /* Restore L2 aux control register */
-        @ set service ID for PPA
+                                        @ set service ID for PPA
         mov     r0, #CONFIG_OMAP3_L2_AUX_SECURE_SERVICE_SET_ID
-        mov     r12, r0         @ copy service ID in r12
-        mov     r1, #0          @ set task ID for ROM code in r1
-        mov     r2, #4          @ set some flags in r2, r6
+        mov     r12, r0                 @ copy service ID in r12
+        mov     r1, #0                  @ set task ID for ROM code in r1
+        mov     r2, #4                  @ set some flags in r2, r6
         mov     r6, #0xff
         ldr     r4, scratchpad_base
         ldr     r3, [r4, #0xBC]
-        adds    r3, r3, #8      @ r3 points to parameters
+        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
         .word   0xE1600071              @ call SMI monitor (smi #1)
 #endif
         b       logic_l1_restore
+
 l2_inv_api_params:
-        .word   0x1, 0x00
+        .word   0x1, 0x00
 l2_inv_gp:
         /* Execute smi to invalidate L2 cache */
-        mov r12, #0x1                         @ set up to invalide L2
-smi:    .word 0xE1600070                @ Call SMI monitor (smieq)
+        mov r12, #0x1                   @ set up to invalidate L2
+        .word 0xE1600070                @ Call SMI monitor (smieq)
         /* Write to Aux control register to set some bits */
         ldr     r4, scratchpad_base
         ldr     r3, [r4,#0xBC]
         ldr     r0, [r3,#4]
         mov     r12, #0x3
-        .word 0xE1600070        @ Call SMI monitor (smieq)
+        .word   0xE1600070              @ Call SMI monitor (smieq)
         ldr     r4, scratchpad_base
         ldr     r3, [r4,#0xBC]
         ldr     r0, [r3,#12]
         mov     r12, #0x2
-        .word 0xE1600070        @ Call SMI monitor (smieq)
+        .word   0xE1600070              @ Call SMI monitor (smieq)
 logic_l1_restore:
+        ldr     r1, l2dis_3630
+        cmp     r1, #0x1                @ Test if L2 re-enable needed on 3630
+        bne     skipl2reen
+        mrc     p15, 0, r1, c1, c0, 1
+        orr     r1, r1, #2              @ re-enable L2 cache
+        mcr     p15, 0, r1, c1, c0, 1
+skipl2reen:
         mov     r1, #0
-        /* Invalidate all instruction caches to PoU
-         * and flush branch target cache */
+        /*
+         * Invalidate all instruction caches to PoU
+         * and flush branch target cache
+         */
         mcr     p15, 0, r1, c7, c5, 0
 
         ldr     r4, scratchpad_base
@@ -341,33 +488,33 @@ logic_l1_restore:
         MCR p15, 0, r6, c2, c0, 1
         /* Translation table base control register */
         MCR p15, 0, r7, c2, c0, 2
-        /*domain access Control Register */
+        /* Domain access Control Register */
         MCR p15, 0, r8, c3, c0, 0
-        /* data fault status Register */
+        /* Data fault status Register */
         MCR p15, 0, r9, c5, c0, 0
 
-        ldmia  r3!,{r4-r8}
-        /* instruction fault status Register */
+        ldmia   r3!,{r4-r8}
+        /* Instruction fault status Register */
         MCR p15, 0, r4, c5, c0, 1
-        /*Data Auxiliary Fault Status Register */
+        /* Data Auxiliary Fault Status Register */
         MCR p15, 0, r5, c5, c1, 0
-        /*Instruction Auxiliary Fault Status Register*/
+        /* Instruction Auxiliary Fault Status Register*/
         MCR p15, 0, r6, c5, c1, 1
-        /*Data Fault Address Register */
+        /* Data Fault Address Register */
         MCR p15, 0, r7, c6, c0, 0
-        /*Instruction Fault Address Register*/
+        /* Instruction Fault Address Register*/
         MCR p15, 0, r8, c6, c0, 2
-        ldmia  r3!,{r4-r7}
+        ldmia   r3!,{r4-r7}
 
-        /* user r/w thread and process ID */
+        /* User r/w thread and process ID */
         MCR p15, 0, r4, c13, c0, 2
-        /* user ro thread and process ID */
+        /* User ro thread and process ID */
         MCR p15, 0, r5, c13, c0, 3
-        /*Privileged only thread and process ID */
+        /* Privileged only thread and process ID */
         MCR p15, 0, r6, c13, c0, 4
-        /* cache size selection */
+        /* Cache size selection */
         MCR p15, 2, r7, c0, c0, 0
-        ldmia  r3!,{r4-r8}
+        ldmia   r3!,{r4-r8}
         /* Data TLB lockdown registers */
         MCR p15, 0, r4, c10, c0, 0
         /* Instruction TLB lockdown registers */
@@ -379,26 +526,27 @@ logic_l1_restore:
         /* Context PID */
         MCR p15, 0, r8, c13, c0, 1
 
-        ldmia  r3!,{r4-r5}
-        /* primary memory remap register */
+        ldmia   r3!,{r4-r5}
+        /* Primary memory remap register */
         MCR p15, 0, r4, c10, c2, 0
-        /*normal memory remap register */
+        /* 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}                @ load CPSR from SDRAM
+        msr     cpsr, r4                @ store cpsr
 
         /* Enabling MMU here */
-        mrc     p15, 0, r7, c2, c0, 2 /* Read TTBRControl */
-        /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1*/
+        mrc     p15, 0, r7, c2, c0, 2   @ Read TTBRControl
+        /* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */
         and     r7, #0x7
         cmp     r7, #0x0
         beq     usettbr0
 ttbr_error:
-        /* More work needs to be done to support N[0:2] value other than 0
-        * So looping here so that the error can be detected
-        */
+        /*
+         * More work needs to be done to support N[0:2] value other than 0
+         * So looping here so that the error can be detected
+         */
         b       ttbr_error
 usettbr0:
         mrc     p15, 0, r2, c2, c0, 0
@@ -406,21 +554,25 @@ usettbr0:
         and     r2, r5
         mov     r4, pc
         ldr     r5, table_index_mask
-        and     r4, r5 /* r4 = 31 to 20 bits of pc */
+        and     r4, r5                  @ r4 = 31 to 20 bits of pc
         /* Extract the value to be written to table entry */
         ldr     r1, table_entry
-        add     r1, r1, r4 /* r1 has value to be written to table entry*/
+        /* r1 has the value to be written to table entry*/
+        add     r1, r1, r4
         /* Getting the address of table entry to modify */
         lsr     r4, #18
-        add     r2, r4 /* r2 has the location which needs to be modified */
+        /* r2 has the location which needs to be modified */
+        add     r2, r4
         /* Storing previous entry of location being modified */
         ldr     r5, scratchpad_base
         ldr     r4, [r2]
         str     r4, [r5, #0xC0]
         /* Modify the table entry */
         str     r1, [r2]
-        /* Storing address of entry being modified
-         * - will be restored after enabling MMU */
+        /*
+         * Storing address of entry being modified
+         * - will be restored after enabling MMU
+         */
         ldr     r5, scratchpad_base
         str     r2, [r5, #0xC4]
 
@@ -429,8 +581,11 @@ usettbr0:
         mcr     p15, 0, r0, c7, c5, 6   @ Invalidate branch predictor array
         mcr     p15, 0, r0, c8, c5, 0   @ Invalidate instruction TLB
         mcr     p15, 0, r0, c8, c6, 0   @ Invalidate data TLB
-        /* Restore control register  but dont enable caches here*/
-        /* Caches will be enabled after restoring MMU table entry */
+        /*
+         * Restore control register. This enables the MMU.
+         * The caches and prediction are not enabled here, they
+         * will be enabled after restoring the MMU table entry.
+         */
         ldmia   r3!, {r4}
         /* Store previous value of control register in scratchpad */
         str     r4, [r5, #0xC8]
@@ -438,212 +593,144 @@ usettbr0:
         and     r4, r2
         mcr     p15, 0, r4, c1, c0, 0
 
-        ldmfd   sp!, {r0-r12, pc}               @ restore regs and return
-save_context_wfi:
-        /*b     save_context_wfi*/      @ enable to debug save code
-        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}
+/*
+ * ==============================
+ * == Exit point from OFF mode ==
+ * ==============================
+ */
+        ldmfd   sp!, {r0-r12, pc}       @ restore regs and return
 
-        /* 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:
-        /* 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
-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
+/*
+ * Internal functions
+ */
 
-        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}
+/* This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0 */
+        .text
+ENTRY(es3_sdrc_fix)
+        ldr     r4, sdrc_syscfg         @ get config addr
+        ldr     r5, [r4]                @ get value
+        tst     r5, #0x100              @ is part access blocked
+        it      eq
+        biceq   r5, r5, #0x100          @ clear bit if set
+        str     r5, [r4]                @ write back change
+        ldr     r4, sdrc_mr_0           @ get config addr
+        ldr     r5, [r4]                @ get value
+        str     r5, [r4]                @ write back change
+        ldr     r4, sdrc_emr2_0         @ get config addr
+        ldr     r5, [r4]                @ get value
+        str     r5, [r4]                @ write back change
+        ldr     r4, sdrc_manual_0       @ get config addr
+        mov     r5, #0x2                @ autorefresh command
+        str     r5, [r4]                @ kick off refreshes
+        ldr     r4, sdrc_mr_1           @ get config addr
+        ldr     r5, [r4]                @ get value
+        str     r5, [r4]                @ write back change
+        ldr     r4, sdrc_emr2_1         @ get config addr
+        ldr     r5, [r4]                @ get value
+        str     r5, [r4]                @ write back change
+        ldr     r4, sdrc_manual_1       @ get config addr
+        mov     r5, #0x2                @ autorefresh command
+        str     r5, [r4]                @ kick off refreshes
+        bx      lr
+
+sdrc_syscfg:
+        .word   SDRC_SYSCONFIG_P
+sdrc_mr_0:
+        .word   SDRC_MR_0_P
+sdrc_emr2_0:
+        .word   SDRC_EMR2_0_P
+sdrc_manual_0:
+        .word   SDRC_MANUAL_0_P
+sdrc_mr_1:
+        .word   SDRC_MR_1_P
+sdrc_emr2_1:
+        .word   SDRC_EMR2_1_P
+sdrc_manual_1:
+        .word   SDRC_MANUAL_1_P
+ENTRY(es3_sdrc_fix_sz)
+        .word   . - es3_sdrc_fix
+
+/*
+ * This function implements the erratum ID i581 WA:
+ *  SDRC state restore before accessing the SDRAM
+ *
+ * Only used at return from non-OFF mode. For OFF
+ * mode the ROM code configures the SDRC and
+ * the DPLL before calling the restore code directly
+ * from DDR.
+ */
 
 /* Make sure SDRC accesses are ok */
 wait_sdrc_ok:
-        ldr     r4, cm_idlest1_core
-        ldr     r5, [r4]
-        and     r5, r5, #0x2
-        cmp     r5, #0
-        bne     wait_sdrc_ok
-        ldr     r4, sdrc_power
-        ldr     r5, [r4]
-        bic     r5, r5, #0x40
-        str     r5, [r4]
+
+/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */
+        ldr     r4, cm_idlest_ckgen
+wait_dpll3_lock:
+        ldr     r5, [r4]
+        tst     r5, #1
+        beq     wait_dpll3_lock
+
+        ldr     r4, cm_idlest1_core
+wait_sdrc_ready:
+        ldr     r5, [r4]
+        tst     r5, #0x2
+        bne     wait_sdrc_ready
+        /* allow DLL powerdown upon hw idle req */
+        ldr     r4, sdrc_power
+        ldr     r5, [r4]
+        bic     r5, r5, #0x40
+        str     r5, [r4]
+
+is_dll_in_lock_mode:
+        /* Is dll in lock mode? */
+        ldr     r4, sdrc_dlla_ctrl
+        ldr     r5, [r4]
+        tst     r5, #0x4
+        bxne    lr                      @ Return if locked
+        /* wait till dll locks */
+wait_dll_lock_timed:
+        ldr     r4, wait_dll_lock_counter
+        add     r4, r4, #1
+        str     r4, wait_dll_lock_counter
+        ldr     r4, sdrc_dlla_status
+        /* Wait 20uS for lock */
+        mov     r6, #8
 wait_dll_lock:
-        /* Is dll in lock mode? */
-        ldr     r4, sdrc_dlla_ctrl
-        ldr     r5, [r4]
-        tst     r5, #0x4
-        bxne    lr
-        /* wait till dll locks */
-        ldr     r4, sdrc_dlla_status
-        ldr     r5, [r4]
-        and     r5, r5, #0x4
-        cmp     r5, #0x4
-        bne     wait_dll_lock
-        bx      lr
+        subs    r6, r6, #0x1
+        beq     kick_dll
+        ldr     r5, [r4]
+        and     r5, r5, #0x4
+        cmp     r5, #0x4
+        bne     wait_dll_lock
+        bx      lr                      @ Return when locked
+
+        /* disable/reenable DLL if not locked */
+kick_dll:
+        ldr     r4, sdrc_dlla_ctrl
+        ldr     r5, [r4]
+        mov     r6, r5
+        bic     r6, #(1<<3)             @ disable dll
+        str     r6, [r4]
+        dsb
+        orr     r6, r6, #(1<<3)         @ enable dll
+        str     r6, [r4]
+        dsb
+        ldr     r4, kick_counter
+        add     r4, r4, #1
+        str     r4, kick_counter
+        b       wait_dll_lock_timed
 
 cm_idlest1_core:
         .word   CM_IDLEST1_CORE_V
+cm_idlest_ckgen:
+        .word   CM_IDLEST_CKGEN_V
 sdrc_dlla_status:
         .word   SDRC_DLLA_STATUS_V
 sdrc_dlla_ctrl:
         .word   SDRC_DLLA_CTRL_V
-pm_prepwstst_core:
-        .word   PM_PREPWSTST_CORE_V
 pm_prepwstst_core_p:
         .word   PM_PREPWSTST_CORE_P
-pm_prepwstst_mpu:
-        .word   PM_PREPWSTST_MPU_V
 pm_pwstctrl_mpu:
         .word   PM_PWSTCTRL_MPU_P
 scratchpad_base:
@@ -651,13 +738,7 @@ scratchpad_base:
 sram_base:
         .word   SRAM_BASE_P + 0x8000
 sdrc_power:
-        .word SDRC_POWER_V
-clk_stabilize_delay:
-        .word 0x000001FF
-assoc_mask:
-        .word   0x3ff
-numset_mask:
-        .word   0x7fff
+        .word   SDRC_POWER_V
 ttbrbit_mask:
         .word   0xFFFFC000
 table_index_mask:
@@ -668,5 +749,20 @@ cache_pred_disable_mask:
         .word   0xFFFFE7FB
 control_stat:
         .word   CONTROL_STAT
+control_mem_rta:
+        .word   CONTROL_MEM_RTA_CTRL
+kernel_flush:
+        .word   v7_flush_dcache_all
+l2dis_3630:
+        .word   0
+        /*
+         * When exporting to userspace while the counters are in SRAM,
+         * these 2 words need to be at the end to facilitate retrival!
+         */
+kick_counter:
+        .word   0
+wait_dll_lock_counter:
+        .word   0
+
 ENTRY(omap34xx_cpu_suspend_sz)
         .word   . - omap34xx_cpu_suspend