Merge tag 'omap-for-v4.17/am-pm-signed' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into next/soc

Pull "Add am335x and am437x PM code for v4.17" from Tony Lindgren:

This series of changes from Dave Gerlach adds the PM related
code to allow low-power suspend states. The code consists of
the SoC specific assembly code and a related PM driver.

* tag 'omap-for-v4.17/am-pm-signed' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
  soc: ti: Add pm33xx driver for basic suspend support
  ARM: OMAP2+: pm33xx-core: Add platform code needed for PM
  ARM: OMAP2+: Introduce low-level suspend code for AM43XX
  ARM: OMAP2+: Introduce low-level suspend code for AM33XX

9 files changed, 850 insertions, 0 deletions

diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 00b1f17f8d44..9f27b486a536 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -72,6 +72,7 @@ config SOC_AM43XX
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
 	select OMAP_INTERCONNECT
+	select ARM_CPU_SUSPEND if PM
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index c15bbcad5f67..4603c30fef73 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -88,6 +88,8 @@ omap-4-5-pm-common			+= pm44xx.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-4-5-pm-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(omap-4-5-pm-common)
 obj-$(CONFIG_SOC_DRA7XX)		+= $(omap-4-5-pm-common)
+obj-$(CONFIG_SOC_AM33XX)		+= pm33xx-core.o sleep33xx.o
+obj-$(CONFIG_SOC_AM43XX)		+= pm33xx-core.o sleep43xx.o
 obj-$(CONFIG_PM_DEBUG)			+= pm-debug.o
 
 obj-$(CONFIG_POWER_AVS_OMAP)		+= sr_device.o
@@ -95,6 +97,8 @@ obj-$(CONFIG_POWER_AVS_OMAP_CLASS3)    += smartreflex-class3.o
 
 AFLAGS_sleep24xx.o			:=-Wa,-march=armv6
 AFLAGS_sleep34xx.o			:=-Wa,-march=armv7-a$(plus_sec)
+AFLAGS_sleep33xx.o			:=-Wa,-march=armv7-a$(plus_sec)
+AFLAGS_sleep43xx.o			:=-Wa,-march=armv7-a$(plus_sec)
 
 endif
 
@@ -232,3 +236,15 @@ obj-y					+= $(omap-hsmmc-m) $(omap-hsmmc-y)
 obj-y					+= omap_phy_internal.o
 
 obj-$(CONFIG_MACH_OMAP2_TUSB6010)	+= usb-tusb6010.o
+
+arch/arm/mach-omap2/pm-asm-offsets.s: arch/arm/mach-omap2/pm-asm-offsets.c
+	$(call if_changed_dep,cc_s_c)
+
+include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORCE
+	$(call filechk,offsets,__TI_PM_ASM_OFFSETS_H__)
+
+# For rule to generate ti-emif-asm-offsets.h dependency
+include drivers/memory/Makefile.asm-offsets
+
+arch/arm/mach-omap2/sleep33xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
+arch/arm/mach-omap2/sleep43xx.o: include/generated/ti-pm-asm-offsets.h include/generated/ti-emif-asm-offsets.h
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index bc202835371b..fbe0b78bf489 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -77,6 +77,13 @@ static inline int omap4_pm_init_early(void)
 }
 #endif
 
+#if defined(CONFIG_PM) && (defined(CONFIG_SOC_AM33XX) || \
+	defined(CONFIG_SOC_AM43XX))
+void amx3_common_pm_init(void);
+#else
+static inline void amx3_common_pm_init(void) { }
+#endif
+
 extern void omap2_init_common_infrastructure(void);
 
 extern void omap_init_time(void);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index cb5d7314cf99..cf546dfe3b32 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -622,6 +622,7 @@ void __init am33xx_init_early(void)
 void __init am33xx_init_late(void)
 {
 	omap_common_late_init();
+	amx3_common_pm_init();
 }
 #endif
 
@@ -646,6 +647,7 @@ void __init am43xx_init_late(void)
 {
 	omap_common_late_init();
 	omap2_clk_enable_autoidle_all();
+	amx3_common_pm_init();
 }
 #endif
 
diff --git a/arch/arm/mach-omap2/pm-asm-offsets.c b/arch/arm/mach-omap2/pm-asm-offsets.c
new file mode 100644
index 000000000000..6d4392da7c11
--- /dev/null
+++ b/arch/arm/mach-omap2/pm-asm-offsets.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TI AM33XX and AM43XX PM Assembly Offsets
+ *
+ * Copyright (C) 2017-2018 Texas Instruments Inc.
+ */
+
+#include <linux/kbuild.h>
+#include <linux/platform_data/pm33xx.h>
+
+int main(void)
+{
+	DEFINE(AMX3_PM_WFI_FLAGS_OFFSET,
+	       offsetof(struct am33xx_pm_sram_data, wfi_flags));
+	DEFINE(AMX3_PM_L2_AUX_CTRL_VAL_OFFSET,
+	       offsetof(struct am33xx_pm_sram_data, l2_aux_ctrl_val));
+	DEFINE(AMX3_PM_L2_PREFETCH_CTRL_VAL_OFFSET,
+	       offsetof(struct am33xx_pm_sram_data, l2_prefetch_ctrl_val));
+	DEFINE(AMX3_PM_SRAM_DATA_SIZE, sizeof(struct am33xx_pm_sram_data));
+
+	BLANK();
+
+	DEFINE(AMX3_PM_RO_SRAM_DATA_VIRT_OFFSET,
+	       offsetof(struct am33xx_pm_ro_sram_data, amx3_pm_sram_data_virt));
+	DEFINE(AMX3_PM_RO_SRAM_DATA_PHYS_OFFSET,
+	       offsetof(struct am33xx_pm_ro_sram_data, amx3_pm_sram_data_phys));
+	DEFINE(AMX3_PM_RO_SRAM_DATA_SIZE,
+	       sizeof(struct am33xx_pm_ro_sram_data));
+
+	return 0;
+}
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 8e30772cfe32..c73776b82348 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -81,6 +81,9 @@ extern unsigned int omap3_do_wfi_sz;
 /* ... and its pointer from SRAM after copy */
 extern void (*omap3_do_wfi_sram)(void);
 
+extern struct am33xx_pm_sram_addr am33xx_pm_sram;
+extern struct am33xx_pm_sram_addr am43xx_pm_sram;
+
 extern void omap3_save_scratchpad_contents(void);
 
 #define PM_RTA_ERRATUM_i608		(1 << 0)
diff --git a/arch/arm/mach-omap2/pm33xx-core.c b/arch/arm/mach-omap2/pm33xx-core.c
new file mode 100644
index 000000000000..93c0b5ba9f09
--- /dev/null
+++ b/arch/arm/mach-omap2/pm33xx-core.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AM33XX Arch Power Management Routines
+ *
+ * Copyright (C) 2016-2018 Texas Instruments Incorporated - http://www.ti.com/
+ *	Dave Gerlach
+ */
+
+#include <asm/smp_scu.h>
+#include <asm/suspend.h>
+#include <linux/errno.h>
+#include <linux/platform_data/pm33xx.h>
+
+#include "cm33xx.h"
+#include "common.h"
+#include "control.h"
+#include "clockdomain.h"
+#include "iomap.h"
+#include "omap_hwmod.h"
+#include "pm.h"
+#include "powerdomain.h"
+#include "prm33xx.h"
+#include "soc.h"
+#include "sram.h"
+
+static struct powerdomain *cefuse_pwrdm, *gfx_pwrdm, *per_pwrdm, *mpu_pwrdm;
+static struct clockdomain *gfx_l4ls_clkdm;
+static void __iomem *scu_base;
+
+static int __init am43xx_map_scu(void)
+{
+	scu_base = ioremap(scu_a9_get_base(), SZ_256);
+
+	if (!scu_base)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int amx3_common_init(void)
+{
+	gfx_pwrdm = pwrdm_lookup("gfx_pwrdm");
+	per_pwrdm = pwrdm_lookup("per_pwrdm");
+	mpu_pwrdm = pwrdm_lookup("mpu_pwrdm");
+
+	if ((!gfx_pwrdm) || (!per_pwrdm) || (!mpu_pwrdm))
+		return -ENODEV;
+
+	(void)clkdm_for_each(omap_pm_clkdms_setup, NULL);
+
+	/* CEFUSE domain can be turned off post bootup */
+	cefuse_pwrdm = pwrdm_lookup("cefuse_pwrdm");
+	if (cefuse_pwrdm)
+		omap_set_pwrdm_state(cefuse_pwrdm, PWRDM_POWER_OFF);
+	else
+		pr_err("PM: Failed to get cefuse_pwrdm\n");
+
+	return 0;
+}
+
+static int am33xx_suspend_init(void)
+{
+	int ret;
+
+	gfx_l4ls_clkdm = clkdm_lookup("gfx_l4ls_gfx_clkdm");
+
+	if (!gfx_l4ls_clkdm) {
+		pr_err("PM: Cannot lookup gfx_l4ls_clkdm clockdomains\n");
+		return -ENODEV;
+	}
+
+	ret = amx3_common_init();
+
+	return ret;
+}
+
+static int am43xx_suspend_init(void)
+{
+	int ret = 0;
+
+	ret = am43xx_map_scu();
+	if (ret) {
+		pr_err("PM: Could not ioremap SCU\n");
+		return ret;
+	}
+
+	ret = amx3_common_init();
+
+	return ret;
+}
+
+static void amx3_pre_suspend_common(void)
+{
+	omap_set_pwrdm_state(gfx_pwrdm, PWRDM_POWER_OFF);
+}
+
+static void amx3_post_suspend_common(void)
+{
+	int status;
+	/*
+	 * Because gfx_pwrdm is the only one under MPU control,
+	 * comment on transition status
+	 */
+	status = pwrdm_read_pwrst(gfx_pwrdm);
+	if (status != PWRDM_POWER_OFF)
+		pr_err("PM: GFX domain did not transition: %x\n", status);
+}
+
+static int am33xx_suspend(unsigned int state, int (*fn)(unsigned long))
+{
+	int ret = 0;
+
+	amx3_pre_suspend_common();
+	ret = cpu_suspend(0, fn);
+	amx3_post_suspend_common();
+
+	/*
+	 * BUG: GFX_L4LS clock domain needs to be woken up to
+	 * ensure thet L4LS clock domain does not get stuck in
+	 * transition. If that happens L3 module does not get
+	 * disabled, thereby leading to PER power domain
+	 * transition failing
+	 */
+
+	clkdm_wakeup(gfx_l4ls_clkdm);
+	clkdm_sleep(gfx_l4ls_clkdm);
+
+	return ret;
+}
+
+static int am43xx_suspend(unsigned int state, int (*fn)(unsigned long))
+{
+	int ret = 0;
+
+	amx3_pre_suspend_common();
+	scu_power_mode(scu_base, SCU_PM_POWEROFF);
+	ret = cpu_suspend(0, fn);
+	scu_power_mode(scu_base, SCU_PM_NORMAL);
+	amx3_post_suspend_common();
+
+	return ret;
+}
+
+static struct am33xx_pm_sram_addr *amx3_get_sram_addrs(void)
+{
+	if (soc_is_am33xx())
+		return &am33xx_pm_sram;
+	else if (soc_is_am437x())
+		return &am43xx_pm_sram;
+	else
+		return NULL;
+}
+
+static struct am33xx_pm_platform_data am33xx_ops = {
+	.init = am33xx_suspend_init,
+	.soc_suspend = am33xx_suspend,
+	.get_sram_addrs = amx3_get_sram_addrs,
+};
+
+static struct am33xx_pm_platform_data am43xx_ops = {
+	.init = am43xx_suspend_init,
+	.soc_suspend = am43xx_suspend,
+	.get_sram_addrs = amx3_get_sram_addrs,
+};
+
+static struct am33xx_pm_platform_data *am33xx_pm_get_pdata(void)
+{
+	if (soc_is_am33xx())
+		return &am33xx_ops;
+	else if (soc_is_am437x())
+		return &am43xx_ops;
+	else
+		return NULL;
+}
+
+void __init amx3_common_pm_init(void)
+{
+	struct am33xx_pm_platform_data *pdata;
+	struct platform_device_info devinfo;
+
+	pdata = am33xx_pm_get_pdata();
+
+	memset(&devinfo, 0, sizeof(devinfo));
+	devinfo.name = "pm33xx";
+	devinfo.data = pdata;
+	devinfo.size_data = sizeof(*pdata);
+	devinfo.id = -1;
+	platform_device_register_full(&devinfo);
+}
diff --git a/arch/arm/mach-omap2/sleep33xx.S b/arch/arm/mach-omap2/sleep33xx.S
new file mode 100644
index 000000000000..218d79930b04
--- /dev/null
+++ b/arch/arm/mach-omap2/sleep33xx.S
@@ -0,0 +1,214 @@
+/* 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 <generated/ti-emif-asm-offsets.h>
+#include <generated/ti-pm-asm-offsets.h>
+#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
diff --git a/arch/arm/mach-omap2/sleep43xx.S b/arch/arm/mach-omap2/sleep43xx.S
new file mode 100644
index 000000000000..59770a69396b
--- /dev/null
+++ b/arch/arm/mach-omap2/sleep43xx.S
@@ -0,0 +1,387 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Low level suspend code for AM43XX SoCs
+ *
+ * Copyright (C) 2013-2018 Texas Instruments Incorporated - http://www.ti.com/
+ *	Dave Gerlach, Vaibhav Bedia
+ */
+
+#include <generated/ti-emif-asm-offsets.h>
+#include <generated/ti-pm-asm-offsets.h>
+#include <linux/linkage.h>
+#include <linux/ti-emif-sram.h>
+
+#include <asm/assembler.h>
+#include <asm/hardware/cache-l2x0.h>
+#include <asm/memory.h>
+
+#include "cm33xx.h"
+#include "common.h"
+#include "iomap.h"
+#include "omap-secure.h"
+#include "omap44xx.h"
+#include "prm33xx.h"
+#include "prcm43xx.h"
+
+#define AM33XX_CM_CLKCTRL_MODULESTATE_DISABLED		0x00030000
+#define AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE		0x0003
+#define AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE		0x0002
+
+#define AM43XX_EMIF_POWEROFF_ENABLE			0x1
+#define AM43XX_EMIF_POWEROFF_DISABLE			0x0
+
+#define AM43XX_CM_CLKSTCTRL_CLKTRCTRL_SW_SLEEP		0x1
+#define AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO		0x3
+
+#define AM43XX_CM_BASE					0x44DF0000
+
+#define AM43XX_CM_REGADDR(inst, reg)                           \
+       AM33XX_L4_WK_IO_ADDRESS(AM43XX_CM_BASE + (inst) + (reg))
+
+#define AM43XX_CM_MPU_CLKSTCTRL AM43XX_CM_REGADDR(AM43XX_CM_MPU_INST, \
+					AM43XX_CM_MPU_MPU_CDOFFS)
+#define AM43XX_CM_MPU_MPU_CLKCTRL AM43XX_CM_REGADDR(AM43XX_CM_MPU_INST, \
+					AM43XX_CM_MPU_MPU_CLKCTRL_OFFSET)
+#define AM43XX_CM_PER_EMIF_CLKCTRL  AM43XX_CM_REGADDR(AM43XX_CM_PER_INST, \
+					AM43XX_CM_PER_EMIF_CLKCTRL_OFFSET)
+#define AM43XX_PRM_EMIF_CTRL_OFFSET			0x0030
+
+	.arm
+	.align 3
+
+ENTRY(am43xx_do_wfi)
+	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
+
+	/* Retrieve l2 cache virt address BEFORE we shut off EMIF */
+	ldr	r1, get_l2cache_base
+	blx	r1
+	mov	r8, r0
+
+	/*
+	 * 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
+	dsb
+
+	/*
+	 * Invalidate L1 and L2 data cache.
+	 */
+	ldr	r1, kernel_flush
+	blx	r1
+
+#ifdef CONFIG_CACHE_L2X0
+	/*
+	 * Clean and invalidate the L2 cache.
+	 */
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x03
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+	mov	r0, r8
+	adr	r4, am43xx_pm_ro_sram_data
+	ldr	r3, [r4, #AMX3_PM_RO_SRAM_DATA_VIRT_OFFSET]
+
+	mov	r2, r0
+	ldr	r0, [r2, #L2X0_AUX_CTRL]
+	str	r0, [r3, #AMX3_PM_L2_AUX_CTRL_VAL_OFFSET]
+	ldr	r0, [r2, #L310_PREFETCH_CTRL]
+	str	r0, [r3, #AMX3_PM_L2_PREFETCH_CTRL_VAL_OFFSET]
+
+	ldr	r0, l2_val
+	str	r0, [r2, #L2X0_CLEAN_INV_WAY]
+wait:
+	ldr	r0, [r2, #L2X0_CLEAN_INV_WAY]
+	ldr	r1, l2_val
+	ands	r0, r0, r1
+	bne	wait
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x00
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+l2x_sync:
+	mov	r0, r8
+	mov	r2, r0
+	mov	r0, #0x0
+	str	r0, [r2, #L2X0_CACHE_SYNC]
+sync:
+	ldr	r0, [r2, #L2X0_CACHE_SYNC]
+	ands	r0, r0, #0x1
+	bne	sync
+#endif
+
+	adr     r9, am43xx_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, am43xx_virt_emif_clkctrl
+	ldr	r2, [r1]
+	bic	r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str	r2, [r1]
+
+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, am43xx_virt_mpu_clkctrl
+	ldr	r2, [r1]
+	bic	r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str	r2, [r1]
+
+	/*
+	 * Put MPU CLKDM to SW_SLEEP
+	 */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_SW_SLEEP
+	str	r2, [r1]
+
+	/*
+	 * 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. Sixteen
+	 * NOPs as per Cortex-A9 pipeline.
+	 */
+	wfi
+
+	nop
+	nop
+	nop
+	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 */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO
+	str	r2, [r1]
+
+	/* Set MPU_CLKCTRL.MODULEMODE back to ENABLE */
+	ldr	r1, am43xx_virt_mpu_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+
+	/* Re-enable EMIF */
+	ldr	r1, am43xx_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
+
+	/*
+	 * 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
+
+	ldr     r1, [r9, #EMIF_PM_ABORT_SR_OFFSET]
+	blx     r1
+
+	/* Let the suspend code know about the abort */
+	mov	r0, #1
+	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
+ENDPROC(am43xx_do_wfi)
+
+	.align
+ENTRY(am43xx_resume_offset)
+	.word . - am43xx_do_wfi
+
+ENTRY(am43xx_resume_from_deep_sleep)
+	/* Set MPU CLKSTCTRL to HW AUTO so that CPUidle works properly */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO
+	str	r2, [r1]
+
+	/* For AM43xx, use EMIF power down until context is restored */
+	ldr	r2, am43xx_phys_emif_poweroff
+	mov	r1, #AM43XX_EMIF_POWEROFF_ENABLE
+	str	r1, [r2, #0x0]
+
+	/* Re-enable EMIF */
+	ldr	r1, am43xx_phys_emif_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+wait_emif_enable1:
+	ldr	r3, [r1]
+	cmp	r2, r3
+	bne	wait_emif_enable1
+
+	adr     r9, am43xx_emif_sram_table
+
+	ldr     r1, [r9, #EMIF_PM_RESTORE_CONTEXT_OFFSET]
+	blx     r1
+
+	ldr     r1, [r9, #EMIF_PM_EXIT_SR_OFFSET]
+	blx     r1
+
+	ldr     r2, am43xx_phys_emif_poweroff
+	mov     r1, #AM43XX_EMIF_POWEROFF_DISABLE
+	str     r1, [r2, #0x0]
+
+#ifdef CONFIG_CACHE_L2X0
+	ldr	r2, l2_cache_base
+	ldr	r0, [r2, #L2X0_CTRL]
+	and	r0, #0x0f
+	cmp	r0, #1
+	beq	skip_l2en			@ Skip if already enabled
+
+	adr	r4, am43xx_pm_ro_sram_data
+	ldr	r3, [r4, #AMX3_PM_RO_SRAM_DATA_PHYS_OFFSET]
+	ldr     r0, [r3, #AMX3_PM_L2_PREFETCH_CTRL_VAL_OFFSET]
+
+	ldr	r12, l2_smc1
+	dsb
+	smc	#0
+	dsb
+set_aux_ctrl:
+	ldr     r0, [r3, #AMX3_PM_L2_AUX_CTRL_VAL_OFFSET]
+	ldr	r12, l2_smc2
+	dsb
+	smc	#0
+	dsb
+
+	/* L2 invalidate on resume */
+	ldr	r0, l2_val
+	ldr	r2, l2_cache_base
+	str	r0, [r2, #L2X0_INV_WAY]
+wait2:
+	ldr	r0, [r2, #L2X0_INV_WAY]
+	ldr	r1, l2_val
+	ands	r0, r0, r1
+	bne	wait2
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x00
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+l2x_sync2:
+	ldr	r2, l2_cache_base
+	mov	r0, #0x0
+	str	r0, [r2, #L2X0_CACHE_SYNC]
+sync2:
+	ldr	r0, [r2, #L2X0_CACHE_SYNC]
+	ands	r0, r0, #0x1
+	bne	sync2
+
+	mov	r0, #0x1
+	ldr	r12, l2_smc3
+	dsb
+	smc	#0
+	dsb
+#endif
+skip_l2en:
+	/* We are back. Branch to the common CPU resume routine */
+	mov	r0, #0
+	ldr	pc, resume_addr
+ENDPROC(am43xx_resume_from_deep_sleep)
+
+/*
+ * Local variables
+ */
+	.align
+resume_addr:
+	.word	cpu_resume - PAGE_OFFSET + 0x80000000
+get_l2cache_base:
+	.word	omap4_get_l2cache_base
+kernel_flush:
+	.word   v7_flush_dcache_all
+ddr_start:
+	.word	PAGE_OFFSET
+
+am43xx_phys_emif_poweroff:
+	.word   (AM43XX_CM_BASE + AM43XX_PRM_DEVICE_INST + \
+		 AM43XX_PRM_EMIF_CTRL_OFFSET)
+am43xx_virt_mpu_clkstctrl:
+	.word	(AM43XX_CM_MPU_CLKSTCTRL)
+am43xx_virt_mpu_clkctrl:
+	.word	(AM43XX_CM_MPU_MPU_CLKCTRL)
+am43xx_virt_emif_clkctrl:
+	.word	(AM43XX_CM_PER_EMIF_CLKCTRL)
+am43xx_phys_emif_clkctrl:
+	.word	(AM43XX_CM_BASE + AM43XX_CM_PER_INST + \
+		 AM43XX_CM_PER_EMIF_CLKCTRL_OFFSET)
+
+/* L2 cache related defines for AM437x */
+l2_cache_base:
+	.word	OMAP44XX_L2CACHE_BASE
+l2_smc1:
+	.word	OMAP4_MON_L2X0_PREFETCH_INDEX
+l2_smc2:
+	.word	OMAP4_MON_L2X0_AUXCTRL_INDEX
+l2_smc3:
+	.word	OMAP4_MON_L2X0_CTRL_INDEX
+l2_val:
+	.word	0xffff
+
+.align 3
+/* DDR related defines */
+ENTRY(am43xx_emif_sram_table)
+	.space EMIF_PM_FUNCTIONS_SIZE
+
+ENTRY(am43xx_pm_sram)
+	.word am43xx_do_wfi
+	.word am43xx_do_wfi_sz
+	.word am43xx_resume_offset
+	.word am43xx_emif_sram_table
+	.word am43xx_pm_ro_sram_data
+
+.align 3
+
+ENTRY(am43xx_pm_ro_sram_data)
+	.space AMX3_PM_RO_SRAM_DATA_SIZE
+
+ENTRY(am43xx_do_wfi_sz)
+	.word	. - am43xx_do_wfi