Re-design bakery lock memory allocation and algorithm

This patch unifies the bakery lock api's across coherent and normal
memory implementation of locks by using same data type `bakery_lock_t`
and similar arguments to functions.

A separate section `bakery_lock` has been created and used to allocate
memory for bakery locks using `DEFINE_BAKERY_LOCK`. When locks are
allocated in normal memory, each lock for a core has to spread
across multiple cache lines. By using the total size allocated in a
separate cache line for a single core at compile time, the memory for
other core locks is allocated at link time by multiplying the single
core locks size with (PLATFORM_CORE_COUNT - 1). The normal memory lock
algorithm now uses lock address instead of the `id` in the per_cpu_data.
For locks allocated in coherent memory, it moves locks from
tzfw_coherent_memory to bakery_lock section.

The bakery locks are allocated as part of bss or in coherent memory
depending on usage of coherent memory. Both these regions are
initialised to zero as part of run_time_init before locks are used.
Hence, bakery_lock_init() is made an empty function as the lock memory
is already initialised to zero.

The above design lead to the removal of psci bakery locks from
non_cpu_power_pd_node to psci_locks.

NOTE: THE BAKERY LOCK API WHEN USE_COHERENT_MEM IS NOT SET HAS CHANGED.
THIS IS A BREAKING CHANGE FOR ALL PLATFORM PORTS THAT ALLOCATE BAKERY
LOCKS IN NORMAL MEMORY.

Change-Id: Ic3751c0066b8032dcbf9d88f1d4dc73d15f61d8b
diff --git a/services/std_svc/psci/psci_private.h b/services/std_svc/psci/psci_private.h
index 9b55d9f..8c028a7 100644
--- a/services/std_svc/psci/psci_private.h
+++ b/services/std_svc/psci/psci_private.h
@@ -42,23 +42,12 @@
  * The following helper macros abstract the interface to the Bakery
  * Lock API.
  */
-#if USE_COHERENT_MEM
-#define psci_lock_init(non_cpu_pd_node, idx)	\
-	bakery_lock_init(&(non_cpu_pd_node)[(idx)].lock)
-#define psci_lock_get(non_cpu_pd_node)		\
-	bakery_lock_get(&((non_cpu_pd_node)->lock))
-#define psci_lock_release(non_cpu_pd_node)	\
-	bakery_lock_release(&((non_cpu_pd_node)->lock))
-#else
 #define psci_lock_init(non_cpu_pd_node, idx)			\
 	((non_cpu_pd_node)[(idx)].lock_index = (idx))
 #define psci_lock_get(non_cpu_pd_node)				\
-	bakery_lock_get((non_cpu_pd_node)->lock_index, 		\
-			CPU_DATA_PSCI_LOCK_OFFSET)
+	bakery_lock_get(&psci_locks[(non_cpu_pd_node)->lock_index])
 #define psci_lock_release(non_cpu_pd_node)			\
-	bakery_lock_release((non_cpu_pd_node)->lock_index,	\
-			     CPU_DATA_PSCI_LOCK_OFFSET)
-#endif
+	bakery_lock_release(&psci_locks[(non_cpu_pd_node)->lock_index])
 
 /*
  * The PSCI capability which are provided by the generic code but does not
@@ -140,12 +129,9 @@
 	plat_local_state_t local_state;
 
 	unsigned char level;
-#if USE_COHERENT_MEM
-	bakery_lock_t lock;
-#else
-	/* For indexing the bakery_info array in per CPU data */
+
+	/* For indexing the psci_lock array*/
 	unsigned char lock_index;
-#endif
 } non_cpu_pd_node_t;
 
 typedef struct cpu_pwr_domain_node {
@@ -174,6 +160,9 @@
 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]);
+
 /*******************************************************************************
  * SPD's power management hooks registered with PSCI
  ******************************************************************************/