ARM: OMAP2+: Introduce low-level suspend code for AM33XX

In preparation for suspend-resume support for AM33XX, add
the assembly file with the code which is copied to internal
memory (OCMC RAM) during bootup and runs from there.

As part of the low power entry (DeepSleep0 mode in AM33XX TRM),
the code running from OCMC RAM does the following
1. Calls routine to store the EMIF configuration
2. Calls routine to place external memory in self-refresh
3. Disables EMIF clock
4. Executes WFI after writing to MPU_CLKCTRL register.

If no interrupts have come, WFI execution on MPU gets registered
as an interrupt with the WKUP-M3. WKUP-M3 takes care of disabling
some clocks which MPU should not (L3, L4, OCMC RAM etc) and takes
care of clockdomain and powerdomain transitions as part of the
DeepSleep0 mode entry.

In case a late interrupt comes in, WFI ends up as a NOP and MPU
continues execution from internal memory. The 'abort path' code
undoes whatever was done as part of the low power entry and indicates
a suspend failure by passing a non-zero value to the cpu_resume routine.

The 'resume path' code is similar to the 'abort path' with the key
difference of MMU being enabled in the 'abort path' but being
disabled in the 'resume path' due to MPU getting powered off.

Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
Acked-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>

arch/arm/mach-omap2/sleep33xx.S

@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Low level suspend code for AM33XX SoCs
+ *
+ * Copyright (C) 2012-2018 Texas Instruments Incorporated - http://www.ti.com/
+ *	Dave Gerlach, Vaibhav Bedia
+ */
+
+#include <linux/linkage.h>
+#include <linux/ti-emif-sram.h>
+#include <asm/assembler.h>
+#include <asm/memory.h>
+
+#include "iomap.h"
+#include "cm33xx.h"
+
+#define AM33XX_CM_CLKCTRL_MODULESTATE_DISABLED			0x00030000
+#define AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE			0x0003
+#define AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE			0x0002
+
+	.arm
+	.align 3
+
+ENTRY(am33xx_do_wfi)
+	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
+
+	/*
+	 * Flush all data from the L1 and L2 data cache before disabling
+	 * SCTLR.C bit.
+	 */
+	ldr	r1, kernel_flush
+	blx	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 and L2 data cache.
+	 */
+	ldr	r1, kernel_flush
+	blx	r1
+
+	adr	r9, am33xx_emif_sram_table
+
+	ldr	r3, [r9, #EMIF_PM_ENTER_SR_OFFSET]
+	blx	r3
+
+	ldr	r3, [r9, #EMIF_PM_SAVE_CONTEXT_OFFSET]
+	blx	r3
+
+	/* Disable EMIF */
+	ldr     r1, virt_emif_clkctrl
+	ldr     r2, [r1]
+	bic     r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str     r2, [r1]
+
+	ldr	r1, virt_emif_clkctrl
+wait_emif_disable:
+	ldr	r2, [r1]
+	mov	r3, #AM33XX_CM_CLKCTRL_MODULESTATE_DISABLED
+	cmp	r2, r3
+	bne	wait_emif_disable
+
+	/*
+	 * For the MPU WFI to be registered as an interrupt
+	 * to WKUP_M3, MPU_CLKCTRL.MODULEMODE needs to be set
+	 * to DISABLED
+	 */
+	ldr	r1, virt_mpu_clkctrl
+	ldr	r2, [r1]
+	bic	r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str	r2, [r1]
+
+	/*
+	 * Execute an ISB instruction to ensure that all of the
+	 * CP15 register changes have been committed.
+	 */
+	isb
+
+	/*
+	 * Execute a barrier instruction to ensure that all cache,
+	 * TLB and branch predictor maintenance operations issued
+	 * have completed.
+	 */
+	dsb
+	dmb
+
+	/*
+	 * Execute a WFI instruction and wait until the
+	 * STANDBYWFI output is asserted to indicate that the
+	 * CPU is in idle and low power state. CPU can specualatively
+	 * prefetch the instructions so add NOPs after WFI. Thirteen
+	 * NOPs as per Cortex-A8 pipeline.
+	 */
+	wfi
+
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* We come here in case of an abort due to a late interrupt */
+
+	/* Set MPU_CLKCTRL.MODULEMODE back to ENABLE */
+	ldr	r1, virt_mpu_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+
+	/* Re-enable EMIF */
+	ldr	r1, virt_emif_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+wait_emif_enable:
+	ldr	r3, [r1]
+	cmp	r2, r3
+	bne	wait_emif_enable
+
+
+	ldr	r1, [r9, #EMIF_PM_ABORT_SR_OFFSET]
+	blx	r1
+
+	/*
+	 * Set SCTLR.C bit to allow data cache allocation
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	orr	r0, r0, #(1 << 2)	@ Enable the C bit
+	mcr	p15, 0, r0, c1, c0, 0
+	isb
+
+	/* Let the suspend code know about the abort */
+	mov	r0, #1
+	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
+ENDPROC(am33xx_do_wfi)
+
+	.align
+ENTRY(am33xx_resume_offset)
+	.word . - am33xx_do_wfi
+
+ENTRY(am33xx_resume_from_deep_sleep)
+	/* Re-enable EMIF */
+	ldr	r0, phys_emif_clkctrl
+	mov	r1, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r1, [r0]
+wait_emif_enable1:
+	ldr	r2, [r0]
+	cmp	r1, r2
+	bne	wait_emif_enable1
+
+	adr	r9, am33xx_emif_sram_table
+
+	ldr	r1, [r9, #EMIF_PM_RESTORE_CONTEXT_OFFSET]
+	blx	r1
+
+	ldr	r1, [r9, #EMIF_PM_EXIT_SR_OFFSET]
+	blx	r1
+
+resume_to_ddr:
+	/* We are back. Branch to the common CPU resume routine */
+	mov	r0, #0
+	ldr	pc, resume_addr
+ENDPROC(am33xx_resume_from_deep_sleep)
+
+/*
+ * Local variables
+ */
+	.align
+resume_addr:
+	.word	cpu_resume - PAGE_OFFSET + 0x80000000
+kernel_flush:
+	.word   v7_flush_dcache_all
+virt_mpu_clkctrl:
+	.word	AM33XX_CM_MPU_MPU_CLKCTRL
+virt_emif_clkctrl:
+	.word	AM33XX_CM_PER_EMIF_CLKCTRL
+phys_emif_clkctrl:
+	.word	(AM33XX_CM_BASE + AM33XX_CM_PER_MOD + \
+		AM33XX_CM_PER_EMIF_CLKCTRL_OFFSET)
+
+.align 3
+/* DDR related defines */
+am33xx_emif_sram_table:
+	.space EMIF_PM_FUNCTIONS_SIZE
+
+ENTRY(am33xx_pm_sram)
+	.word am33xx_do_wfi
+	.word am33xx_do_wfi_sz
+	.word am33xx_resume_offset
+	.word am33xx_emif_sram_table
+	.word am33xx_pm_ro_sram_data
+
+.align 3
+ENTRY(am33xx_pm_ro_sram_data)
+	.space AMX3_PM_RO_SRAM_DATA_SIZE
+
+ENTRY(am33xx_do_wfi_sz)
+	.word	. - am33xx_do_wfi