diff --git a/lib/psci/psci_common.c b/lib/psci/psci_common.c
index 026690d..1be37c0 100644
--- a/lib/psci/psci_common.c
+++ b/lib/psci/psci_common.c
@@ -79,7 +79,8 @@
 #endif
 ;
 
-DEFINE_BAKERY_LOCK(psci_locks[PSCI_NUM_NON_CPU_PWR_DOMAINS]);
+/* Lock for PSCI state coordination */
+DEFINE_PSCI_LOCK(psci_locks[PSCI_NUM_NON_CPU_PWR_DOMAINS]);
 
 cpu_pd_node_t psci_cpu_pd_nodes[PLATFORM_CORE_COUNT];
 
@@ -992,3 +993,33 @@
 }
 
 #endif
+
+/*******************************************************************************
+ * Initiate power down sequence, by calling power down operations registered for
+ * this CPU.
+ ******************************************************************************/
+void psci_do_pwrdown_sequence(unsigned int power_level)
+{
+#if HW_ASSISTED_COHERENCY
+	/*
+	 * With hardware-assisted coherency, the CPU drivers only initiate the
+	 * power down sequence, without performing cache-maintenance operations
+	 * in software. Data caches and MMU remain enabled both before and after
+	 * this call.
+	 */
+	prepare_cpu_pwr_dwn(power_level);
+#else
+	/*
+	 * Without hardware-assisted coherency, the CPU drivers disable data
+	 * caches and MMU, then perform cache-maintenance operations in
+	 * software.
+	 *
+	 * We ought to call prepare_cpu_pwr_dwn() to initiate power down
+	 * sequence. We currently have data caches and MMU enabled, but the
+	 * function will return with data caches and MMU disabled. We must
+	 * ensure that the stack memory is flushed out to memory before we start
+	 * popping from it again.
+	 */
+	psci_do_pwrdown_cache_maintenance(power_level);
+#endif
+}
diff --git a/lib/psci/psci_off.c b/lib/psci/psci_off.c
index 94cf2ed..4ba7865 100644
--- a/lib/psci/psci_off.c
+++ b/lib/psci/psci_off.c
@@ -119,10 +119,9 @@
 #endif
 
 	/*
-	 * Arch. management. Perform the necessary steps to flush all
-	 * cpu caches.
+	 * Arch. management. Initiate power down sequence.
 	 */
-	psci_do_pwrdown_cache_maintenance(psci_find_max_off_lvl(&state_info));
+	psci_do_pwrdown_sequence(psci_find_max_off_lvl(&state_info));
 
 #if ENABLE_RUNTIME_INSTRUMENTATION
 	PMF_CAPTURE_TIMESTAMP(rt_instr_svc,
diff --git a/lib/psci/psci_on.c b/lib/psci/psci_on.c
index f4bb797..675ed66 100644
--- a/lib/psci/psci_on.c
+++ b/lib/psci/psci_on.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013-2016, ARM Limited and Contributors. All rights reserved.
+ * Copyright (c) 2013-2017, ARM Limited and Contributors. All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -165,10 +165,12 @@
 	 */
 	psci_plat_pm_ops->pwr_domain_on_finish(state_info);
 
+#if !HW_ASSISTED_COHERENCY
 	/*
 	 * Arch. management: Enable data cache and manage stack memory
 	 */
 	psci_do_pwrup_cache_maintenance();
+#endif
 
 	/*
 	 * All the platform specific actions for turning this cpu
diff --git a/lib/psci/psci_private.h b/lib/psci/psci_private.h
index 7f0204a..a27e215 100644
--- a/lib/psci/psci_private.h
+++ b/lib/psci/psci_private.h
@@ -39,6 +39,7 @@
 #include <spinlock.h>
 
 #if HW_ASSISTED_COHERENCY
+
 /*
  * On systems with hardware-assisted coherency, make PSCI cache operations NOP,
  * as PSCI participants are cache-coherent, and there's no need for explicit
@@ -49,7 +50,21 @@
 #define psci_inv_cpu_data(member)
 
 #define psci_dsbish()
+
+/*
+ * On systems where participant CPUs are cache-coherent, we can use spinlocks
+ * instead of bakery locks.
+ */
+#define DEFINE_PSCI_LOCK(_name)		spinlock_t _name
+#define DECLARE_PSCI_LOCK(_name)	extern DEFINE_PSCI_LOCK(_name)
+
+#define psci_lock_get(non_cpu_pd_node)				\
+	spin_lock(&psci_locks[(non_cpu_pd_node)->lock_index])
+#define psci_lock_release(non_cpu_pd_node)			\
+	spin_unlock(&psci_locks[(non_cpu_pd_node)->lock_index])
+
 #else
+
 /*
  * If not all PSCI participants are cache-coherent, perform cache maintenance
  * and issue barriers wherever required to coordinate state.
@@ -59,19 +74,24 @@
 #define psci_inv_cpu_data(member)		inv_cpu_data(member)
 
 #define psci_dsbish()				dsbish()
-#endif
 
 /*
- * The following helper macros abstract the interface to the Bakery
- * Lock API.
+ * Use bakery locks for state coordination as not all PSCI participants are
+ * cache coherent.
  */
-#define psci_lock_init(non_cpu_pd_node, idx)			\
-	((non_cpu_pd_node)[(idx)].lock_index = (idx))
+#define DEFINE_PSCI_LOCK(_name)		DEFINE_BAKERY_LOCK(_name)
+#define DECLARE_PSCI_LOCK(_name)	DECLARE_BAKERY_LOCK(_name)
+
 #define psci_lock_get(non_cpu_pd_node)				\
 	bakery_lock_get(&psci_locks[(non_cpu_pd_node)->lock_index])
 #define psci_lock_release(non_cpu_pd_node)			\
 	bakery_lock_release(&psci_locks[(non_cpu_pd_node)->lock_index])
 
+#endif
+
+#define psci_lock_init(non_cpu_pd_node, idx)			\
+	((non_cpu_pd_node)[(idx)].lock_index = (idx))
+
 /*
  * The PSCI capability which are provided by the generic code but does not
  * depend on the platform or spd capabilities.
@@ -189,8 +209,8 @@
 extern cpu_pd_node_t psci_cpu_pd_nodes[PLATFORM_CORE_COUNT];
 extern unsigned int psci_caps;
 
-/* One bakery lock is required for each non-cpu power domain */
-DECLARE_BAKERY_LOCK(psci_locks[PSCI_NUM_NON_CPU_PWR_DOMAINS]);
+/* One lock is required per non-CPU power domain node */
+DECLARE_PSCI_LOCK(psci_locks[PSCI_NUM_NON_CPU_PWR_DOMAINS]);
 
 /*******************************************************************************
  * SPD's power management hooks registered with PSCI
@@ -227,6 +247,14 @@
 void psci_print_power_domain_map(void);
 unsigned int psci_is_last_on_cpu(void);
 int psci_spd_migrate_info(u_register_t *mpidr);
+void psci_do_pwrdown_sequence(unsigned int power_level);
+
+/*
+ * CPU power down is directly called only when HW_ASSISTED_COHERENCY is
+ * available. Otherwise, this needs post-call stack maintenance, which is
+ * handled in assembly.
+ */
+void prepare_cpu_pwr_dwn(unsigned int power_level);
 
 /* Private exported functions from psci_on.c */
 int psci_cpu_on_start(u_register_t target_cpu,
diff --git a/lib/psci/psci_suspend.c b/lib/psci/psci_suspend.c
index 23e5ada..08c8fd6 100644
--- a/lib/psci/psci_suspend.c
+++ b/lib/psci/psci_suspend.c
@@ -121,13 +121,11 @@
 #endif
 
 	/*
-	 * Arch. management. Perform the necessary steps to flush all
-	 * cpu caches. Currently we assume that the power level correspond
-	 * the cache level.
+	 * Arch. management. Initiate power down sequence.
 	 * TODO : Introduce a mechanism to query the cache level to flush
 	 * and the cpu-ops power down to perform from the platform.
 	 */
-	psci_do_pwrdown_cache_maintenance(max_off_lvl);
+	psci_do_pwrdown_sequence(max_off_lvl);
 
 #if ENABLE_RUNTIME_INSTRUMENTATION
 	PMF_CAPTURE_TIMESTAMP(rt_instr_svc,
@@ -304,12 +302,10 @@
 	 */
 	psci_plat_pm_ops->pwr_domain_suspend_finish(state_info);
 
-	/*
-	 * Arch. management: Enable the data cache, manage stack memory and
-	 * restore the stashed EL3 architectural context from the 'cpu_context'
-	 * structure for this cpu.
-	 */
+#if !HW_ASSISTED_COHERENCY
+	/* Arch. management: Enable the data cache, stack memory maintenance. */
 	psci_do_pwrup_cache_maintenance();
+#endif
 
 	/* Re-init the cntfrq_el0 register */
 	counter_freq = plat_get_syscnt_freq2();