15 files changed, 694 insertions, 349 deletions

diff --git a/arch/arm/cpu/armv8/fsl-layerscape/Makefile b/arch/arm/cpu/armv8/fsl-layerscape/Makefile
index 5f86ef9..8c1317f 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/Makefile
+++ b/arch/arm/cpu/armv8/fsl-layerscape/Makefile
@@ -10,6 +10,7 @@ obj-y += soc.o
 obj-$(CONFIG_MP) += mp.o
 obj-$(CONFIG_OF_LIBFDT) += fdt.o
 obj-$(CONFIG_SPL) += spl.o
+obj-$(CONFIG_FSL_LS_PPA) += ppa.o
 
 ifneq ($(CONFIG_FSL_LSCH3),)
 obj-y += fsl_lsch3_speed.o
@@ -28,3 +29,11 @@ endif
 ifneq ($(CONFIG_LS1043A),)
 obj-$(CONFIG_SYS_HAS_SERDES) += ls1043a_serdes.o
 endif
+
+ifneq ($(CONFIG_LS1012A),)
+obj-$(CONFIG_SYS_HAS_SERDES) += ls1012a_serdes.o
+endif
+
+ifneq ($(CONFIG_LS1046A),)
+obj-$(CONFIG_SYS_HAS_SERDES) += ls1046a_serdes.o
+endif
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/cpu.c b/arch/arm/cpu/armv8/fsl-layerscape/cpu.c
index d939900..e12b773 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/cpu.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/cpu.c
@@ -23,16 +23,13 @@
 #ifdef CONFIG_FSL_ESDHC
 #include <fsl_esdhc.h>
 #endif
+#ifdef CONFIG_ARMV8_SEC_FIRMWARE_SUPPORT
+#include <asm/armv8/sec_firmware.h>
+#endif
 
 DECLARE_GLOBAL_DATA_PTR;
 
-static struct mm_region layerscape_mem_map[] = {
-	{
-		/* List terminator */
-		0,
-	}
-};
-struct mm_region *mem_map = layerscape_mem_map;
+struct mm_region *mem_map = early_map;
 
 void cpu_name(char *name)
 {
@@ -56,358 +53,106 @@ void cpu_name(char *name)
 }
 
 #ifndef CONFIG_SYS_DCACHE_OFF
-static void set_pgtable_section(u64 *page_table, u64 index, u64 section,
-			u64 memory_type, u64 attribute)
-{
-       u64 value;
-
-       value = section | PTE_TYPE_BLOCK | PTE_BLOCK_AF;
-       value |= PMD_ATTRINDX(memory_type);
-       value |= attribute;
-       page_table[index] = value;
-}
-
-static void set_pgtable_table(u64 *page_table, u64 index, u64 *table_addr)
-{
-       u64 value;
-
-       value = (u64)table_addr | PTE_TYPE_TABLE;
-       page_table[index] = value;
-}
-
-/*
- * Set the block entries according to the information of the table.
- */
-static int set_block_entry(const struct sys_mmu_table *list,
-			   struct table_info *table)
-{
-	u64 block_size = 0, block_shift = 0;
-	u64 block_addr, index;
-	int j;
-
-	if (table->entry_size == BLOCK_SIZE_L1) {
-		block_size = BLOCK_SIZE_L1;
-		block_shift = SECTION_SHIFT_L1;
-	} else if (table->entry_size == BLOCK_SIZE_L2) {
-		block_size = BLOCK_SIZE_L2;
-		block_shift = SECTION_SHIFT_L2;
-	} else {
-		return -EINVAL;
-	}
-
-	block_addr = list->phys_addr;
-	index = (list->virt_addr - table->table_base) >> block_shift;
-
-	for (j = 0; j < (list->size >> block_shift); j++) {
-		set_pgtable_section(table->ptr,
-				    index,
-				    block_addr,
-				    list->memory_type,
-				    list->attribute);
-		block_addr += block_size;
-		index++;
-	}
-
-	return 0;
-}
-
-/*
- * Find the corresponding table entry for the list.
- */
-static int find_table(const struct sys_mmu_table *list,
-		      struct table_info *table, u64 *level0_table)
-{
-	u64 index = 0, level = 0;
-	u64 *level_table = level0_table;
-	u64 temp_base = 0, block_size = 0, block_shift = 0;
-
-	while (level < 3) {
-		if (level == 0) {
-			block_size = BLOCK_SIZE_L0;
-			block_shift = SECTION_SHIFT_L0;
-		} else if (level == 1) {
-			block_size = BLOCK_SIZE_L1;
-			block_shift = SECTION_SHIFT_L1;
-		} else if (level == 2) {
-			block_size = BLOCK_SIZE_L2;
-			block_shift = SECTION_SHIFT_L2;
-		}
-
-		index = 0;
-		while (list->virt_addr >= temp_base) {
-			index++;
-			temp_base += block_size;
-		}
-
-		temp_base -= block_size;
-
-		if ((level_table[index - 1] & PTE_TYPE_MASK) ==
-		    PTE_TYPE_TABLE) {
-			level_table = (u64 *)(level_table[index - 1] &
-				      ~PTE_TYPE_MASK);
-			level++;
-			continue;
-		} else {
-			if (level == 0)
-				return -EINVAL;
-
-			if ((list->phys_addr + list->size) >
-			    (temp_base + block_size * NUM_OF_ENTRY))
-				return -EINVAL;
-
-			/*
-			 * Check the address and size of the list member is
-			 * aligned with the block size.
-			 */
-			if (((list->phys_addr & (block_size - 1)) != 0) ||
-			    ((list->size & (block_size - 1)) != 0))
-				return -EINVAL;
-
-			table->ptr = level_table;
-			table->table_base = temp_base -
-					    ((index - 1) << block_shift);
-			table->entry_size = block_size;
-
-			return 0;
-		}
-	}
-	return -EINVAL;
-}
-
 /*
  * To start MMU before DDR is available, we create MMU table in SRAM.
  * The base address of SRAM is CONFIG_SYS_FSL_OCRAM_BASE. We use three
  * levels of translation tables here to cover 40-bit address space.
  * We use 4KB granule size, with 40 bits physical address, T0SZ=24
- * Level 0 IA[39], table address @0
- * Level 1 IA[38:30], table address @0x1000, 0x2000
- * Level 2 IA[29:21], table address @0x3000, 0x4000
- * Address above 0x5000 is free for other purpose.
+ * Address above EARLY_PGTABLE_SIZE (0x5000) is free for other purpose.
+ * Note, the debug print in cache_v8.c is not usable for debugging
+ * these early MMU tables because UART is not yet available.
  */
 static inline void early_mmu_setup(void)
 {
-	unsigned int el, i;
-	u64 *level0_table = (u64 *)CONFIG_SYS_FSL_OCRAM_BASE;
-	u64 *level1_table0 = (u64 *)(CONFIG_SYS_FSL_OCRAM_BASE + 0x1000);
-	u64 *level1_table1 = (u64 *)(CONFIG_SYS_FSL_OCRAM_BASE + 0x2000);
-	u64 *level2_table0 = (u64 *)(CONFIG_SYS_FSL_OCRAM_BASE + 0x3000);
-	u64 *level2_table1 = (u64 *)(CONFIG_SYS_FSL_OCRAM_BASE + 0x4000);
-
-	struct table_info table = {level0_table, 0, BLOCK_SIZE_L0};
+	unsigned int el = current_el();
 
-	/* Invalidate all table entries */
-	memset(level0_table, 0, 0x5000);
+	/* global data is already setup, no allocation yet */
+	gd->arch.tlb_addr = CONFIG_SYS_FSL_OCRAM_BASE;
+	gd->arch.tlb_fillptr = gd->arch.tlb_addr;
+	gd->arch.tlb_size = EARLY_PGTABLE_SIZE;
 
-	/* Fill in the table entries */
-	set_pgtable_table(level0_table, 0, level1_table0);
-	set_pgtable_table(level0_table, 1, level1_table1);
-	set_pgtable_table(level1_table0, 0, level2_table0);
+	/* Create early page tables */
+	setup_pgtables();
 
-#ifdef CONFIG_FSL_LSCH3
-	set_pgtable_table(level1_table0,
-			  CONFIG_SYS_FLASH_BASE >> SECTION_SHIFT_L1,
-			  level2_table1);
-#elif defined(CONFIG_FSL_LSCH2)
-	set_pgtable_table(level1_table0, 1, level2_table1);
-#endif
-	/* Find the table and fill in the block entries */
-	for (i = 0; i < ARRAY_SIZE(early_mmu_table); i++) {
-		if (find_table(&early_mmu_table[i],
-			       &table, level0_table) == 0) {
-			/*
-			 * If find_table() returns error, it cannot be dealt
-			 * with here. Breakpoint can be added for debugging.
-			 */
-			set_block_entry(&early_mmu_table[i], &table);
-			/*
-			 * If set_block_entry() returns error, it cannot be
-			 * dealt with here too.
-			 */
-		}
-	}
-
-	el = current_el();
-
-	set_ttbr_tcr_mair(el, (u64)level0_table, LAYERSCAPE_TCR,
+	/* point TTBR to the new table */
+	set_ttbr_tcr_mair(el, gd->arch.tlb_addr,
+			  get_tcr(el, NULL, NULL) &
+			  ~(TCR_ORGN_MASK | TCR_IRGN_MASK),
 			  MEMORY_ATTRIBUTES);
-	set_sctlr(get_sctlr() | CR_M);
-}
 
-#ifdef CONFIG_SYS_MEM_RESERVE_SECURE
-/*
- * Called from final mmu setup. The phys_addr is new, non-existing
- * address. A new sub table is created @level2_table_secure to cover
- * size of CONFIG_SYS_MEM_RESERVE_SECURE memory.
- */
-static inline int final_secure_ddr(u64 *level0_table,
-				   u64 *level2_table_secure,
-				   phys_addr_t phys_addr)
-{
-	int ret = -EINVAL;
-	struct table_info table = {};
-	struct sys_mmu_table ddr_entry = {
-		0, 0, BLOCK_SIZE_L1, MT_NORMAL,
-		PTE_BLOCK_OUTER_SHARE | PTE_BLOCK_NS
-	};
-	u64 index;
-
-	/* Need to create a new table */
-	ddr_entry.virt_addr = phys_addr & ~(BLOCK_SIZE_L1 - 1);
-	ddr_entry.phys_addr = phys_addr & ~(BLOCK_SIZE_L1 - 1);
-	ret = find_table(&ddr_entry, &table, level0_table);
-	if (ret)
-		return ret;
-	index = (ddr_entry.virt_addr - table.table_base) >> SECTION_SHIFT_L1;
-	set_pgtable_table(table.ptr, index, level2_table_secure);
-	table.ptr = level2_table_secure;
-	table.table_base = ddr_entry.virt_addr;
-	table.entry_size = BLOCK_SIZE_L2;
-	ret = set_block_entry(&ddr_entry, &table);
-	if (ret) {
-		printf("MMU error: could not fill non-secure ddr block entries\n");
-		return ret;
-	}
-	ddr_entry.virt_addr = phys_addr;
-	ddr_entry.phys_addr = phys_addr;
-	ddr_entry.size = CONFIG_SYS_MEM_RESERVE_SECURE;
-	ddr_entry.attribute = PTE_BLOCK_OUTER_SHARE;
-	ret = find_table(&ddr_entry, &table, level0_table);
-	if (ret) {
-		printf("MMU error: could not find secure ddr table\n");
-		return ret;
-	}
-	ret = set_block_entry(&ddr_entry, &table);
-	if (ret)
-		printf("MMU error: could not set secure ddr block entry\n");
-
-	return ret;
+	set_sctlr(get_sctlr() | CR_M);
 }
-#endif
 
 /*
  * The final tables look similar to early tables, but different in detail.
  * These tables are in DRAM. Sub tables are added to enable cache for
  * QBMan and OCRAM.
  *
- * Put the MMU table in secure memory if gd->secure_ram is valid.
- * OCRAM will be not used for this purpose so gd->secure_ram can't be 0.
- *
- * Level 1 table 0 contains 512 entries for each 1GB from 0 to 512GB.
- * Level 1 table 1 contains 512 entries for each 1GB from 512GB to 1TB.
- * Level 2 table 0 contains 512 entries for each 2MB from 0 to 1GB.
- *
- * For LSCH3:
- * Level 2 table 1 contains 512 entries for each 2MB from 32GB to 33GB.
- * For LSCH2:
- * Level 2 table 1 contains 512 entries for each 2MB from 1GB to 2GB.
- * Level 2 table 2 contains 512 entries for each 2MB from 20GB to 21GB.
+ * Put the MMU table in secure memory if gd->arch.secure_ram is valid.
+ * OCRAM will be not used for this purpose so gd->arch.secure_ram can't be 0.
  */
 static inline void final_mmu_setup(void)
 {
+	u64 tlb_addr_save = gd->arch.tlb_addr;
 	unsigned int el = current_el();
-	unsigned int i;
-	u64 *level0_table = (u64 *)gd->arch.tlb_addr;
-	u64 *level1_table0;
-	u64 *level1_table1;
-	u64 *level2_table0;
-	u64 *level2_table1;
-#ifdef CONFIG_FSL_LSCH2
-	u64 *level2_table2;
-#endif
-	struct table_info table = {NULL, 0, BLOCK_SIZE_L0};
-
 #ifdef CONFIG_SYS_MEM_RESERVE_SECURE
-	u64 *level2_table_secure;
-
-	if (el == 3) {
-		/*
-		 * Only use gd->secure_ram if the address is recalculated
-		 * Align to 4KB for MMU table
-		 */
-		if (gd->secure_ram & MEM_RESERVE_SECURE_MAINTAINED)
-			level0_table = (u64 *)(gd->secure_ram & ~0xfff);
-		else
-			printf("MMU warning: gd->secure_ram is not maintained, disabled.\n");
-	}
+	int index;
 #endif
-	level1_table0 = level0_table + 512;
-	level1_table1 = level1_table0 + 512;
-	level2_table0 = level1_table1 + 512;
-	level2_table1 = level2_table0 + 512;
-#ifdef CONFIG_FSL_LSCH2
-	level2_table2 = level2_table1 + 512;
-#endif
-	table.ptr = level0_table;
 
-	/* Invalidate all table entries */
-	memset(level0_table, 0, PGTABLE_SIZE);
+	mem_map = final_map;
 
-	/* Fill in the table entries */
-	set_pgtable_table(level0_table, 0, level1_table0);
-	set_pgtable_table(level0_table, 1, level1_table1);
-	set_pgtable_table(level1_table0, 0, level2_table0);
-#ifdef CONFIG_FSL_LSCH3
-	set_pgtable_table(level1_table0,
-			  CONFIG_SYS_FSL_QBMAN_BASE >> SECTION_SHIFT_L1,
-			  level2_table1);
-#elif defined(CONFIG_FSL_LSCH2)
-	set_pgtable_table(level1_table0, 1, level2_table1);
-	set_pgtable_table(level1_table0,
-			  CONFIG_SYS_FSL_QBMAN_BASE >> SECTION_SHIFT_L1,
-			  level2_table2);
-#endif
-
-	/* Find the table and fill in the block entries */
-	for (i = 0; i < ARRAY_SIZE(final_mmu_table); i++) {
-		if (find_table(&final_mmu_table[i],
-			       &table, level0_table) == 0) {
-			if (set_block_entry(&final_mmu_table[i],
-					    &table) != 0) {
-				printf("MMU error: could not set block entry for %p\n",
-				       &final_mmu_table[i]);
-			}
-
-		} else {
-			printf("MMU error: could not find the table for %p\n",
-			       &final_mmu_table[i]);
-		}
-	}
-	/* Set the secure memory to secure in MMU */
 #ifdef CONFIG_SYS_MEM_RESERVE_SECURE
-	if (el == 3 && gd->secure_ram & MEM_RESERVE_SECURE_MAINTAINED) {
-#ifdef CONFIG_FSL_LSCH3
-		level2_table_secure = level2_table1 + 512;
-#elif defined(CONFIG_FSL_LSCH2)
-		level2_table_secure = level2_table2 + 512;
-#endif
-		if (!final_secure_ddr(level0_table,
-				      level2_table_secure,
-				      gd->secure_ram & ~0x3)) {
-			gd->secure_ram |= MEM_RESERVE_SECURE_SECURED;
-			debug("Now MMU table is in secured memory at 0x%llx\n",
-			      gd->secure_ram & ~0x3);
+	if (gd->arch.secure_ram & MEM_RESERVE_SECURE_MAINTAINED) {
+		if (el == 3) {
+			/*
+			 * Only use gd->arch.secure_ram if the address is
+			 * recalculated. Align to 4KB for MMU table.
+			 */
+			/* put page tables in secure ram */
+			index = ARRAY_SIZE(final_map) - 2;
+			gd->arch.tlb_addr = gd->arch.secure_ram & ~0xfff;
+			final_map[index].virt = gd->arch.secure_ram & ~0x3;
+			final_map[index].phys = final_map[index].virt;
+			final_map[index].size = CONFIG_SYS_MEM_RESERVE_SECURE;
+			final_map[index].attrs = PTE_BLOCK_OUTER_SHARE;
+			gd->arch.secure_ram |= MEM_RESERVE_SECURE_SECURED;
+			tlb_addr_save = gd->arch.tlb_addr;
 		} else {
-			printf("MMU warning: Failed to secure DDR\n");
+			/* Use allocated (board_f.c) memory for TLB */
+			tlb_addr_save = gd->arch.tlb_allocated;
+			gd->arch.tlb_addr = tlb_addr_save;
 		}
 	}
 #endif
 
+	/* Reset the fill ptr */
+	gd->arch.tlb_fillptr = tlb_addr_save;
+
+	/* Create normal system page tables */
+	setup_pgtables();
+
+	/* Create emergency page tables */
+	gd->arch.tlb_addr = gd->arch.tlb_fillptr;
+	gd->arch.tlb_emerg = gd->arch.tlb_addr;
+	setup_pgtables();
+	gd->arch.tlb_addr = tlb_addr_save;
+
 	/* flush new MMU table */
-	flush_dcache_range((ulong)level0_table,
-			   (ulong)level0_table + gd->arch.tlb_size);
+	flush_dcache_range(gd->arch.tlb_addr,
+			   gd->arch.tlb_addr + gd->arch.tlb_size);
 
-#ifdef CONFIG_SYS_DPAA_FMAN
-	flush_dcache_all();
-#endif
 	/* point TTBR to the new table */
-	set_ttbr_tcr_mair(el, (u64)level0_table, LAYERSCAPE_TCR_FINAL,
+	set_ttbr_tcr_mair(el, gd->arch.tlb_addr, get_tcr(el, NULL, NULL),
 			  MEMORY_ATTRIBUTES);
 	/*
-	 * MMU is already enabled, just need to invalidate TLB to load the
+	 * EL3 MMU is already enabled, just need to invalidate TLB to load the
 	 * new table. The new table is compatible with the current table, if
 	 * MMU somehow walks through the new table before invalidation TLB,
 	 * it still works. So we don't need to turn off MMU here.
+	 * When EL2 MMU table is created by calling this function, MMU needs
+	 * to be enabled.
 	 */
+	set_sctlr(get_sctlr() | CR_M);
 }
 
 u64 get_page_table_size(void)
@@ -425,15 +170,21 @@ int arch_cpu_init(void)
 	return 0;
 }
 
+void mmu_setup(void)
+{
+	final_mmu_setup();
+}
+
 /*
- * This function is called from lib/board.c.
- * It recreates MMU table in main memory. MMU and d-cache are enabled earlier.
- * There is no need to disable d-cache for this operation.
+ * This function is called from common/board_r.c.
+ * It recreates MMU table in main memory.
  */
 void enable_caches(void)
 {
-	final_mmu_setup();
+	mmu_setup();
 	__asm_invalidate_tlb_all();
+	icache_enable();
+	dcache_enable();
 }
 #endif
 
@@ -531,6 +282,13 @@ u32 fsl_qoriq_core_to_type(unsigned int core)
 	return -1;      /* cannot identify the cluster */
 }
 
+uint get_svr(void)
+{
+	struct ccsr_gur __iomem *gur = (void *)(CONFIG_SYS_FSL_GUTS_ADDR);
+
+	return gur_in32(&gur->svr);
+}
+
 #ifdef CONFIG_DISPLAY_CPUINFO
 int print_cpuinfo(void)
 {
@@ -554,7 +312,8 @@ int print_cpuinfo(void)
 		printf("CPU%d(%s):%-4s MHz  ", core,
 		       type == TY_ITYP_VER_A7 ? "A7 " :
 		       (type == TY_ITYP_VER_A53 ? "A53" :
-			(type == TY_ITYP_VER_A57 ? "A57" : "   ")),
+		       (type == TY_ITYP_VER_A57 ? "A57" :
+		       (type == TY_ITYP_VER_A72 ? "A72" : "   "))),
 		       strmhz(buf, sysinfo.freq_processor[core]));
 	}
 	printf("\n       Bus:      %-4s MHz  ",
@@ -612,6 +371,7 @@ int arch_early_init_r(void)
 {
 #ifdef CONFIG_MP
 	int rv = 1;
+	u32 psci_ver = 0xffffffff;
 #endif
 
 #ifdef CONFIG_SYS_FSL_ERRATUM_A009635
@@ -619,9 +379,15 @@ int arch_early_init_r(void)
 #endif
 
 #ifdef CONFIG_MP
-	rv = fsl_layerscape_wake_seconday_cores();
-	if (rv)
-		printf("Did not wake secondary cores\n");
+#if defined(CONFIG_ARMV8_SEC_FIRMWARE_SUPPORT) && defined(CONFIG_ARMV8_PSCI)
+	/* Check the psci version to determine if the psci is supported */
+	psci_ver = sec_firmware_support_psci_version();
+#endif
+	if (psci_ver == 0xffffffff) {
+		rv = fsl_layerscape_wake_seconday_cores();
+		if (rv)
+			printf("Did not wake secondary cores\n");
+	}
 #endif
 
 #ifdef CONFIG_SYS_HAS_SERDES
@@ -639,6 +405,9 @@ int timer_init(void)
 #ifdef CONFIG_FSL_LSCH3
 	u32 __iomem *cltbenr = (u32 *)CONFIG_SYS_FSL_PMU_CLTBENR;
 #endif
+#ifdef CONFIG_LS2080A
+	u32 __iomem *pctbenr = (u32 *)FSL_PMU_PCTBENR_OFFSET;
+#endif
 #ifdef COUNTER_FREQUENCY_REAL
 	unsigned long cntfrq = COUNTER_FREQUENCY_REAL;
 
@@ -653,6 +422,15 @@ int timer_init(void)
 	out_le32(cltbenr, 0xf);
 #endif
 
+#ifdef CONFIG_LS2080A
+	/*
+	 * In certain Layerscape SoCs, the clock for each core's
+	 * has an enable bit in the PMU Physical Core Time Base Enable
+	 * Register (PCTBENR), which allows the watchdog to operate.
+	 */
+	setbits_le32(pctbenr, 0xff);
+#endif
+
 	/* Enable clock for timer
 	 * This is a global setting.
 	 */
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/README.lsch2 b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.lsch2
index a6ef830..a6ef830 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/README.lsch2
+++ b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.lsch2
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/README.lsch3 b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.lsch3
index f9323c1..7867c37 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/README.lsch3
+++ b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.lsch3
@@ -121,6 +121,35 @@ mcboottimeout:	MC boot timeout in milliseconds. If this variable is not defined
 mcmemsize:	MC DRAM block size. If this variable is not defined, the value
 		CONFIG_SYS_LS_MC_DRAM_BLOCK_MIN_SIZE will be assumed.
 
+mcinitcmd:	This environment variable is defined to initiate MC and DPL deployment
+		from the location where it is stored(NOR, NAND, SD, SATA, USB)during
+		u-boot booting.If this variable is not defined then MC_BOOT_ENV_VAR
+		will be null and MC will not be booted and DPL will not be applied
+		during U-boot booting.However the MC, DPC and DPL can be applied from
+		console independently.
+		The variable needs to be set from the console once and then on
+		rebooting the parameters set in the variable will automatically be
+		executed. The commmand is demostrated taking an example of mc boot
+		using NOR Flash i.e. MC, DPL, and DPC is stored in the NOR flash:
+
+		cp.b 0xa0000000 0x580300000 $filesize
+		cp.b 0x80000000 0x580800000 $filesize
+		cp.b 0x90000000 0x580700000 $filesize
+
+		setenv mcinitcmd 'fsl_mc start mc 0x580300000 0x580800000'
+
+		If only linux is to be booted then the mcinitcmd environment should be set as
+
+		setenv mcinitcmd 'fsl_mc start mc 0x580300000 0x580800000;fsl_mc apply DPL 0x580700000'
+
+		Here the addresses 0xa0000000, 0x80000000, 0x80000000 are of DDR to where
+		MC binary, DPC binary and DPL binary are stored and 0x580300000, 0x580800000
+		and 0x580700000 are addresses in NOR where these are copied. It is to be
+		noted that these addresses in 'fsl_mc start mc 0x580300000 0x580800000;fsl_mc apply DPL 0x580700000'
+		can be replaced with the addresses of DDR to
+		which these will be copied in case of these binaries being stored in other
+		devices like SATA, USB, NAND, SD etc.
+
 Booting from NAND
 -------------------
 Booting from NAND requires two images, RCW and u-boot-with-spl.bin.
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/doc/README.soc b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.soc
new file mode 100644
index 0000000..f7b949a
--- /dev/null
+++ b/arch/arm/cpu/armv8/fsl-layerscape/doc/README.soc
@@ -0,0 +1,171 @@
+SoC overview
+
+	1. LS1043A
+	2. LS2080A
+	3. LS1012A
+	4. LS1046A
+
+LS1043A
+---------
+The LS1043A integrated multicore processor combines four ARM Cortex-A53
+processor cores with datapath acceleration optimized for L2/3 packet
+processing, single pass security offload and robust traffic management
+and quality of service.
+
+The LS1043A SoC includes the following function and features:
+ - Four 64-bit ARM Cortex-A53 CPUs
+ - 1 MB unified L2 Cache
+ - One 32-bit DDR3L/DDR4 SDRAM memory controllers with ECC and interleaving
+   support
+ - Data Path Acceleration Architecture (DPAA) incorporating acceleration the
+   the following functions:
+   - Packet parsing, classification, and distribution (FMan)
+   - Queue management for scheduling, packet sequencing, and congestion
+     management (QMan)
+   - Hardware buffer management for buffer allocation and de-allocation (BMan)
+   - Cryptography acceleration (SEC)
+ - Ethernet interfaces by FMan
+   - Up to 1 x XFI supporting 10G interface
+   - Up to 1 x QSGMII
+   - Up to 4 x SGMII supporting 1000Mbps
+   - Up to 2 x SGMII supporting 2500Mbps
+   - Up to 2 x RGMII supporting 1000Mbps
+ - High-speed peripheral interfaces
+   - Three PCIe 2.0 controllers, one supporting x4 operation
+   - One serial ATA (SATA 3.0) controllers
+ - Additional peripheral interfaces
+   - Three high-speed USB 3.0 controllers with integrated PHY
+   - Enhanced secure digital host controller (eSDXC/eMMC)
+   - Quad Serial Peripheral Interface (QSPI) Controller
+   - Serial peripheral interface (SPI) controller
+   - Four I2C controllers
+   - Two DUARTs
+   - Integrated flash controller supporting NAND and NOR flash
+ - QorIQ platform's trust architecture 2.1
+
+LS2080A
+--------
+The LS2080A integrated multicore processor combines eight ARM Cortex-A57
+processor cores with high-performance data path acceleration logic and network
+and peripheral bus interfaces required for networking, telecom/datacom,
+wireless infrastructure, and mil/aerospace applications.
+
+The LS2080A SoC includes the following function and features:
+
+ - Eight 64-bit ARM Cortex-A57 CPUs
+ - 1 MB platform cache with ECC
+ - Two 64-bit DDR4 SDRAM memory controllers with ECC and interleaving support
+ - One secondary 32-bit DDR4 SDRAM memory controller, intended for use by
+  the AIOP
+ - Data path acceleration architecture (DPAA2) incorporating acceleration for
+ the following functions:
+   - Packet parsing, classification, and distribution (WRIOP)
+   - Queue and Hardware buffer management for scheduling, packet sequencing, and
+     congestion management, buffer allocation and de-allocation (QBMan)
+   - Cryptography acceleration (SEC) at up to 10 Gbps
+   - RegEx pattern matching acceleration (PME) at up to 10 Gbps
+   - Decompression/compression acceleration (DCE) at up to 20 Gbps
+   - Accelerated I/O processing (AIOP) at up to 20 Gbps
+   - QDMA engine
+ - 16 SerDes lanes at up to 10.3125 GHz
+ - Ethernet interfaces
+   - Up to eight 10 Gbps Ethernet MACs
+   - Up to eight 1 / 2.5 Gbps Ethernet MACs
+ - High-speed peripheral interfaces
+   - Four PCIe 3.0 controllers, one supporting SR-IOV
+ - Additional peripheral interfaces
+   - Two serial ATA (SATA 3.0) controllers
+   - Two high-speed USB 3.0 controllers with integrated PHY
+   - Enhanced secure digital host controller (eSDXC/eMMC)
+   - Serial peripheral interface (SPI) controller
+   - Quad Serial Peripheral Interface (QSPI) Controller
+   - Four I2C controllers
+   - Two DUARTs
+   - Integrated flash controller (IFC 2.0) supporting NAND and NOR flash
+ - Support for hardware virtualization and partitioning enforcement
+ - QorIQ platform's trust architecture 3.0
+ - Service processor (SP) provides pre-boot initialization and secure-boot
+  capabilities
+
+LS1012A
+--------
+The LS1012A features an advanced 64-bit ARM v8 Cortex-
+A53 processor, with 32 KB of parity protected L1-I cache,
+32 KB of ECC protected L1-D cache, as well as 256 KB of
+ECC protected L2 cache.
+
+The LS1012A SoC includes the following function and features:
+ - One 64-bit ARM v8 Cortex-A53 core with the following capabilities:
+ - ARM v8 cryptography extensions
+ - One 16-bit DDR3L SDRAM memory controller, Up to 1.0 GT/s, Supports
+    16-/8-bit operation (no ECC support)
+ - ARM core-link CCI-400 cache coherent interconnect
+ - Packet Forwarding Engine (PFE)
+ - Cryptography acceleration (SEC)
+ - Ethernet interfaces supported by PFE:
+ - One Configurable x3 SerDes:
+    Two Serdes PLLs supported for usage by any SerDes data lane
+    Support for up to 6 GBaud operation
+ - High-speed peripheral interfaces:
+     - One PCI Express Gen2 controller, supporting x1 operation
+     - One serial ATA (SATA Gen 3.0) controller
+     - One USB 3.0/2.0 controller with integrated PHY
+     - One USB 2.0 controller with ULPI interface. .
+ - Additional peripheral interfaces:
+    - One quad serial peripheral interface (QuadSPI) controller
+    - One serial peripheral interface (SPI) controller
+    - Two enhanced secure digital host controllers
+    - Two I2C controllers
+    - One 16550 compliant DUART (two UART interfaces)
+    - Two general purpose IOs (GPIO)
+    - Two FlexTimers
+    - Five synchronous audio interfaces (SAI)
+    - Pre-boot loader (PBL) provides pre-boot initialization and RCW loading
+    - Single-source clocking solution enabling generation of core, platform,
+    DDR, SerDes, and USB clocks from a single external crystal and internal
+    crystaloscillator
+    - Thermal monitor unit (TMU) with +/- 3C accuracy
+    - Two WatchDog timers
+    - ARM generic timer
+ - QorIQ platform's trust architecture 2.1
+
+LS1046A
+--------
+The LS1046A integrated multicore processor combines four ARM Cortex-A72
+processor cores with datapath acceleration optimized for L2/3 packet
+processing, single pass security offload and robust traffic management
+and quality of service.
+
+The LS1046A SoC includes the following function and features:
+ - Four 64-bit ARM Cortex-A72 CPUs
+ - 2 MB unified L2 Cache
+ - One 64-bit DDR4 SDRAM memory controllers with ECC and interleaving
+   support
+ - Data Path Acceleration Architecture (DPAA) incorporating acceleration the
+   the following functions:
+   - Packet parsing, classification, and distribution (FMan)
+   - Queue management for scheduling, packet sequencing, and congestion
+     management (QMan)
+   - Hardware buffer management for buffer allocation and de-allocation (BMan)
+   - Cryptography acceleration (SEC)
+ - Two Configurable x4 SerDes
+   - Two PLLs per four-lane SerDes
+   - Support for 10G operation
+ - Ethernet interfaces by FMan
+   - Up to 2 x XFI supporting 10G interface (MAC 9, 10)
+   - Up to 1 x QSGMII (MAC 5, 6, 10, 1)
+   - Up to 4 x SGMII supporting 1000Mbps (MAC 5, 6, 9, 10)
+   - Up to 3 x SGMII supporting 2500Mbps (MAC 5, 9, 10)
+   - Up to 2 x RGMII supporting 1000Mbps (MAC 3, 4)
+ - High-speed peripheral interfaces
+   - Three PCIe 3.0 controllers, one supporting x4 operation
+   - One serial ATA (SATA 3.0) controllers
+ - Additional peripheral interfaces
+   - Three high-speed USB 3.0 controllers with integrated PHY
+   - Enhanced secure digital host controller (eSDXC/eMMC)
+   - Quad Serial Peripheral Interface (QSPI) Controller
+   - Serial peripheral interface (SPI) controller
+   - Four I2C controllers
+   - Two DUARTs
+   - Integrated flash controller (IFC) supporting NAND and NOR flash
+ - QorIQ platform's trust architecture 2.1
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/fdt.c b/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
index 1e875c4..40d6a76 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/fdt.c
@@ -20,6 +20,11 @@
 #ifdef CONFIG_MP
 #include <asm/arch/mp.h>
 #endif
+#include <fsl_sec.h>
+#include <asm/arch-fsl-layerscape/soc.h>
+#ifdef CONFIG_ARMV8_SEC_FIRMWARE_SUPPORT
+#include <asm/armv8/sec_firmware.h>
+#endif
 
 int fdt_fixup_phy_connection(void *blob, int offset, phy_interface_t phyc)
 {
@@ -36,7 +41,37 @@ void ft_fixup_cpu(void *blob)
 	int addr_cells;
 	u64 val, core_id;
 	size_t *boot_code_size = &(__secondary_boot_code_size);
+#if defined(CONFIG_ARMV8_SEC_FIRMWARE_SUPPORT) && defined(CONFIG_ARMV8_PSCI)
+	int node;
+	u32 psci_ver;
+
+	/* Check the psci version to determine if the psci is supported */
+	psci_ver = sec_firmware_support_psci_version();
+	if (psci_ver == 0xffffffff) {
+		/* remove psci DT node */
+		node = fdt_path_offset(blob, "/psci");
+		if (node >= 0)
+			goto remove_psci_node;
+
+		node = fdt_node_offset_by_compatible(blob, -1, "arm,psci");
+		if (node >= 0)
+			goto remove_psci_node;
+
+		node = fdt_node_offset_by_compatible(blob, -1, "arm,psci-0.2");
+		if (node >= 0)
+			goto remove_psci_node;
 
+		node = fdt_node_offset_by_compatible(blob, -1, "arm,psci-1.0");
+		if (node >= 0)
+			goto remove_psci_node;
+
+remove_psci_node:
+		if (node >= 0)
+			fdt_del_node(blob, node);
+	} else {
+		return;
+	}
+#endif
 	off = fdt_path_offset(blob, "/cpus");
 	if (off < 0) {
 		puts("couldn't find /cpus node\n");
@@ -75,6 +110,23 @@ void ft_fixup_cpu(void *blob)
 
 void ft_cpu_setup(void *blob, bd_t *bd)
 {
+#ifdef CONFIG_FSL_LSCH2
+	struct ccsr_gur __iomem *gur = (void *)(CONFIG_SYS_FSL_GUTS_ADDR);
+	unsigned int svr = in_be32(&gur->svr);
+
+	/* delete crypto node if not on an E-processor */
+	if (!IS_E_PROCESSOR(svr))
+		fdt_fixup_crypto_node(blob, 0);
+#if CONFIG_SYS_FSL_SEC_COMPAT >= 4
+	else {
+		ccsr_sec_t __iomem *sec;
+
+		sec = (void __iomem *)CONFIG_SYS_FSL_SEC_ADDR;
+		fdt_fixup_crypto_node(blob, sec_in32(&sec->secvid_ms));
+	}
+#endif
+#endif
+
 #ifdef CONFIG_MP
 	ft_fixup_cpu(blob);
 #endif
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_serdes.c b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_serdes.c
index fe3444a..f73092a 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_serdes.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_serdes.c
@@ -13,6 +13,9 @@
 #ifdef CONFIG_SYS_FSL_SRDS_1
 static u8 serdes1_prtcl_map[SERDES_PRCTL_COUNT];
 #endif
+#ifdef CONFIG_SYS_FSL_SRDS_2
+static u8 serdes2_prtcl_map[SERDES_PRCTL_COUNT];
+#endif
 
 int is_serdes_configured(enum srds_prtcl device)
 {
@@ -21,6 +24,9 @@ int is_serdes_configured(enum srds_prtcl device)
 #ifdef CONFIG_SYS_FSL_SRDS_1
 	ret |= serdes1_prtcl_map[device];
 #endif
+#ifdef CONFIG_SYS_FSL_SRDS_2
+	ret |= serdes2_prtcl_map[device];
+#endif
 
 	return !!ret;
 }
@@ -38,6 +44,12 @@ int serdes_get_first_lane(u32 sd, enum srds_prtcl device)
 		cfg >>= FSL_CHASSIS2_RCWSR4_SRDS1_PRTCL_SHIFT;
 		break;
 #endif
+#ifdef CONFIG_SYS_FSL_SRDS_2
+	case FSL_SRDS_2:
+		cfg &= FSL_CHASSIS2_RCWSR4_SRDS2_PRTCL_MASK;
+		cfg >>= FSL_CHASSIS2_RCWSR4_SRDS2_PRTCL_SHIFT;
+		break;
+#endif
 	default:
 		printf("invalid SerDes%d\n", sd);
 		break;
@@ -114,4 +126,11 @@ void fsl_serdes_init(void)
 		    FSL_CHASSIS2_RCWSR4_SRDS1_PRTCL_SHIFT,
 		    serdes1_prtcl_map);
 #endif
+#ifdef CONFIG_SYS_FSL_SRDS_2
+	serdes_init(FSL_SRDS_2,
+		    CONFIG_SYS_FSL_SERDES_ADDR,
+		    FSL_CHASSIS2_RCWSR4_SRDS2_PRTCL_MASK,
+		    FSL_CHASSIS2_RCWSR4_SRDS2_PRTCL_SHIFT,
+		    serdes2_prtcl_map);
+#endif
 }
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_speed.c b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_speed.c
index 453a93d..8922197 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_speed.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch2_speed.c
@@ -11,6 +11,7 @@
 #include <asm/arch/clock.h>
 #include <asm/arch/soc.h>
 #include <fsl_ifc.h>
+#include "cpu.h"
 
 DECLARE_GLOBAL_DATA_PTR;
 
@@ -25,7 +26,10 @@ void get_sys_info(struct sys_info *sys_info)
 	struct fsl_ifc ifc_regs = {(void *)CONFIG_SYS_IFC_ADDR, (void *)NULL};
 	u32 ccr;
 #endif
-#if defined(CONFIG_FSL_ESDHC) || defined(CONFIG_SYS_DPAA_FMAN)
+#if (defined(CONFIG_FSL_ESDHC) &&\
+	defined(CONFIG_FSL_ESDHC_USE_PERIPHERAL_CLK)) ||\
+	defined(CONFIG_SYS_DPAA_FMAN)
+
 	u32 rcw_tmp;
 #endif
 	struct ccsr_clk *clk = (void *)(CONFIG_SYS_FSL_CLK_ADDR);
@@ -44,7 +48,7 @@ void get_sys_info(struct sys_info *sys_info)
 		[5] = 2,	/* CC2 PPL / 2 */
 	};
 
-	uint i;
+	uint i, cluster;
 	uint freq_c_pll[CONFIG_SYS_FSL_NUM_CC_PLLS];
 	uint ratio[CONFIG_SYS_FSL_NUM_CC_PLLS];
 	unsigned long sysclk = CONFIG_SYS_CLK_FREQ;
@@ -56,12 +60,18 @@ void get_sys_info(struct sys_info *sys_info)
 	sys_info->freq_ddrbus = sysclk;
 #endif
 
+#ifdef CONFIG_LS1012A
+	sys_info->freq_ddrbus *= (gur_in32(&gur->rcwsr[0]) >>
+			FSL_CHASSIS2_RCWSR0_SYS_PLL_RAT_SHIFT) &
+			FSL_CHASSIS2_RCWSR0_SYS_PLL_RAT_MASK;
+#else
 	sys_info->freq_systembus *= (gur_in32(&gur->rcwsr[0]) >>
 			FSL_CHASSIS2_RCWSR0_SYS_PLL_RAT_SHIFT) &
 			FSL_CHASSIS2_RCWSR0_SYS_PLL_RAT_MASK;
 	sys_info->freq_ddrbus *= (gur_in32(&gur->rcwsr[0]) >>
 			FSL_CHASSIS2_RCWSR0_MEM_PLL_RAT_SHIFT) &
 			FSL_CHASSIS2_RCWSR0_MEM_PLL_RAT_MASK;
+#endif
 
 	for (i = 0; i < CONFIG_SYS_FSL_NUM_CC_PLLS; i++) {
 		ratio[i] = (in_be32(&clk->pllcgsr[i].pllcngsr) >> 1) & 0xff;
@@ -71,8 +81,9 @@ void get_sys_info(struct sys_info *sys_info)
 			freq_c_pll[i] = sys_info->freq_systembus * ratio[i];
 	}
 
-	for (cpu = 0; cpu < CONFIG_MAX_CPUS; cpu++) {
-		u32 c_pll_sel = (in_be32(&clk->clkcsr[cpu].clkcncsr) >> 27)
+	for_each_cpu(i, cpu, cpu_numcores(), cpu_mask()) {
+		cluster = fsl_qoriq_core_to_cluster(cpu);
+		u32 c_pll_sel = (in_be32(&clk->clkcsr[cluster].clkcncsr) >> 27)
 				& 0xf;
 		u32 cplx_pll = core_cplx_pll[c_pll_sel];
 
@@ -80,6 +91,11 @@ void get_sys_info(struct sys_info *sys_info)
 			freq_c_pll[cplx_pll] / core_cplx_pll_div[c_pll_sel];
 	}
 
+#ifdef CONFIG_LS1012A
+	sys_info->freq_systembus = sys_info->freq_ddrbus / 2;
+	sys_info->freq_ddrbus *= 2;
+#endif
+
 #define HWA_CGA_M1_CLK_SEL	0xe0000000
 #define HWA_CGA_M1_CLK_SHIFT	29
 #ifdef CONFIG_SYS_DPAA_FMAN
@@ -91,6 +107,12 @@ void get_sys_info(struct sys_info *sys_info)
 	case 3:
 		sys_info->freq_fman[0] = freq_c_pll[0] / 3;
 		break;
+	case 4:
+		sys_info->freq_fman[0] = freq_c_pll[0] / 4;
+		break;
+	case 5:
+		sys_info->freq_fman[0] = sys_info->freq_systembus;
+		break;
 	case 6:
 		sys_info->freq_fman[0] = freq_c_pll[1] / 2;
 		break;
@@ -108,8 +130,23 @@ void get_sys_info(struct sys_info *sys_info)
 #ifdef CONFIG_FSL_ESDHC
 #ifdef CONFIG_FSL_ESDHC_USE_PERIPHERAL_CLK
 	rcw_tmp = in_be32(&gur->rcwsr[15]);
-	rcw_tmp = (rcw_tmp & HWA_CGA_M2_CLK_SEL) >> HWA_CGA_M2_CLK_SHIFT;
-	sys_info->freq_sdhc = freq_c_pll[1] / rcw_tmp;
+	switch ((rcw_tmp & HWA_CGA_M2_CLK_SEL) >> HWA_CGA_M2_CLK_SHIFT) {
+	case 1:
+		sys_info->freq_sdhc = freq_c_pll[1];
+		break;
+	case 2:
+		sys_info->freq_sdhc = freq_c_pll[1] / 2;
+		break;
+	case 3:
+		sys_info->freq_sdhc = freq_c_pll[1] / 3;
+		break;
+	case 6:
+		sys_info->freq_sdhc = freq_c_pll[0] / 2;
+		break;
+	default:
+		printf("Error: Unknown ESDHC clock select!\n");
+		break;
+	}
 #else
 	sys_info->freq_sdhc = sys_info->freq_systembus;
 #endif
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch3_speed.c b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch3_speed.c
index d580a43..a9b12a4 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch3_speed.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/fsl_lsch3_speed.c
@@ -180,7 +180,7 @@ ulong get_ddr_freq(ulong ctrl_num)
 
 	/*
 	 * DDR controller 0 & 1 are on memory complex 0
-	 * DDR controler 2 is on memory complext 1
+	 * DDR controller 2 is on memory complext 1
 	 */
 #ifdef CONFIG_SYS_FSL_HAS_DP_DDR
 	if (ctrl_num >= 2)
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
index 04831ca..5af6b73 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
+++ b/arch/arm/cpu/armv8/fsl-layerscape/lowlevel.S
@@ -94,11 +94,13 @@ ENTRY(lowlevel_init)
 	bl	ccn504_set_qos
 #endif
 
+#ifdef SMMU_BASE
 	/* Set the SMMU page size in the sACR register */
 	ldr	x1, =SMMU_BASE
 	ldr	w0, [x1, #0x10]
 	orr	w0, w0, #1 << 16  /* set sACR.pagesize to indicate 64K page */
 	str	w0, [x1, #0x10]
+#endif
 
 	/* Initialize GIC Secure Bank Status */
 #if defined(CONFIG_GICV2) || defined(CONFIG_GICV3)
@@ -181,6 +183,7 @@ ENTRY(lowlevel_init)
 	ret
 ENDPROC(lowlevel_init)
 
+#ifdef CONFIG_FSL_LSCH3
 hnf_pstate_poll:
 	/* x0 has the desired status, return 0 for success, 1 for timeout
 	 * clobber x1, x2, x3, x4, x6, x7
@@ -258,6 +261,7 @@ ENTRY(__asm_flush_l3_cache)
 	mov	lr, x29
 	ret
 ENDPROC(__asm_flush_l3_cache)
+#endif
 
 #ifdef CONFIG_MP
 	/* Keep literals not used by the secondary boot code outside it */
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/ls1012a_serdes.c b/arch/arm/cpu/armv8/fsl-layerscape/ls1012a_serdes.c
new file mode 100644
index 0000000..ff0903c
--- /dev/null
+++ b/arch/arm/cpu/armv8/fsl-layerscape/ls1012a_serdes.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/arch/fsl_serdes.h>
+#include <asm/arch/immap_lsch2.h>
+
+struct serdes_config {
+	u32 protocol;
+	u8 lanes[SRDS_MAX_LANES];
+};
+
+static struct serdes_config serdes1_cfg_tbl[] = {
+	{0x2208, {SGMII_2500_FM1_DTSEC1, SGMII_2500_FM1_DTSEC2, NONE, SATA1} },
+	{0x0008, {NONE, NONE, NONE, SATA1} },
+	{0x3508, {SGMII_FM1_DTSEC1, PCIE1, NONE, SATA1} },
+	{0x3305, {SGMII_FM1_DTSEC1, SGMII_FM1_DTSEC2, NONE, PCIE1} },
+	{0x2205, {SGMII_2500_FM1_DTSEC1, SGMII_2500_FM1_DTSEC2, NONE, PCIE1} },
+	{0x2305, {SGMII_2500_FM1_DTSEC1, SGMII_FM1_DTSEC2, NONE, PCIE1} },
+	{0x9508, {TX_CLK, PCIE1, NONE, SATA1} },
+	{0x3905, {SGMII_FM1_DTSEC1, TX_CLK, NONE, PCIE1} },
+	{0x9305, {TX_CLK, SGMII_FM1_DTSEC2, NONE, PCIE1} },
+	{}
+};
+
+static struct serdes_config *serdes_cfg_tbl[] = {
+	serdes1_cfg_tbl,
+};
+
+enum srds_prtcl serdes_get_prtcl(int serdes, int cfg, int lane)
+{
+	struct serdes_config *ptr;
+
+	if (serdes >= ARRAY_SIZE(serdes_cfg_tbl))
+		return 0;
+
+	ptr = serdes_cfg_tbl[serdes];
+	while (ptr->protocol) {
+		if (ptr->protocol == cfg)
+			return ptr->lanes[lane];
+		ptr++;
+	}
+
+	return 0;
+}
+
+int is_serdes_prtcl_valid(int serdes, u32 prtcl)
+{
+	int i;
+	struct serdes_config *ptr;
+
+	if (serdes >= ARRAY_SIZE(serdes_cfg_tbl))
+		return 0;
+
+	ptr = serdes_cfg_tbl[serdes];
+	while (ptr->protocol) {
+		if (ptr->protocol == prtcl)
+			break;
+		ptr++;
+	}
+
+	if (!ptr->protocol)
+		return 0;
+
+	for (i = 0; i < SRDS_MAX_LANES; i++) {
+		if (ptr->lanes[i] != NONE)
+			return 1;
+	}
+
+	return 0;
+}
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/ls1046a_serdes.c b/arch/arm/cpu/armv8/fsl-layerscape/ls1046a_serdes.c
new file mode 100644
index 0000000..1da6b71
--- /dev/null
+++ b/arch/arm/cpu/armv8/fsl-layerscape/ls1046a_serdes.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright 2016 Freescale Semiconductor, Inc.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/arch/fsl_serdes.h>
+#include <asm/arch/immap_lsch2.h>
+
+struct serdes_config {
+	u32 protocol;
+	u8 lanes[SRDS_MAX_LANES];
+};
+
+static struct serdes_config serdes1_cfg_tbl[] = {
+	/* SerDes 1 */
+	{0x3333, {SGMII_FM1_DTSEC9, SGMII_FM1_DTSEC10, SGMII_FM1_DTSEC5,
+		  SGMII_FM1_DTSEC6} },
+	{0x1133, {XFI_FM1_MAC9, XFI_FM1_MAC10, SGMII_FM1_DTSEC5,
+		  SGMII_FM1_DTSEC6} },
+	{0x1333, {XFI_FM1_MAC9, SGMII_FM1_DTSEC10, SGMII_FM1_DTSEC5,
+		  SGMII_FM1_DTSEC6} },
+	{0x2333, {SGMII_2500_FM1_DTSEC9, SGMII_FM1_DTSEC10, SGMII_FM1_DTSEC5,
+		  SGMII_FM1_DTSEC6} },
+	{0x2233, {SGMII_2500_FM1_DTSEC9, SGMII_2500_FM1_DTSEC10,
+		  SGMII_FM1_DTSEC5, SGMII_FM1_DTSEC6} },
+	{0x1040, {XFI_FM1_MAC9, NONE, QSGMII_FM1_A, NONE} },
+	{0x2040, {SGMII_2500_FM1_DTSEC9, NONE, QSGMII_FM1_A, NONE} },
+	{0x1163, {XFI_FM1_MAC9, XFI_FM1_MAC10, PCIE1, SGMII_FM1_DTSEC6} },
+	{0x2263, {SGMII_2500_FM1_DTSEC9, SGMII_2500_FM1_DTSEC10, PCIE1,
+		  SGMII_FM1_DTSEC6} },
+	{0x3363, {SGMII_FM1_DTSEC5, SGMII_FM1_DTSEC6, PCIE1,
+		  SGMII_FM1_DTSEC6} },
+	{0x2223, {SGMII_2500_FM1_DTSEC9, SGMII_2500_FM1_DTSEC10,
+		  SGMII_2500_FM1_DTSEC5, SGMII_FM1_DTSEC6} },
+	{}
+};
+
+static struct serdes_config serdes2_cfg_tbl[] = {
+	/* SerDes 2 */
+	{0x8888, {PCIE1, PCIE1, PCIE1, PCIE1} },
+	{0x5559, {PCIE1, PCIE2, PCIE3, SATA1} },
+	{0x5577, {PCIE1, PCIE2, PCIE3, PCIE3} },
+	{0x5506, {PCIE1, PCIE2, NONE, PCIE3} },
+	{0x0506, {NONE, PCIE2, NONE, PCIE3} },
+	{0x0559, {NONE, PCIE2, PCIE3, SATA1} },
+	{0x5A59, {PCIE1, SGMII_FM1_DTSEC2, PCIE3, SATA1} },
+	{0x5A06, {PCIE1, SGMII_FM1_DTSEC2, NONE, PCIE3} },
+	{}
+};
+
+static struct serdes_config *serdes_cfg_tbl[] = {
+	serdes1_cfg_tbl,
+	serdes2_cfg_tbl,
+};
+
+enum srds_prtcl serdes_get_prtcl(int serdes, int cfg, int lane)
+{
+	struct serdes_config *ptr;
+
+	if (serdes >= ARRAY_SIZE(serdes_cfg_tbl))
+		return 0;
+
+	ptr = serdes_cfg_tbl[serdes];
+	while (ptr->protocol) {
+		if (ptr->protocol == cfg)
+			return ptr->lanes[lane];
+		ptr++;
+	}
+
+	return 0;
+}
+
+int is_serdes_prtcl_valid(int serdes, u32 prtcl)
+{
+	int i;
+	struct serdes_config *ptr;
+
+	if (serdes >= ARRAY_SIZE(serdes_cfg_tbl))
+		return 0;
+
+	ptr = serdes_cfg_tbl[serdes];
+	while (ptr->protocol) {
+		if (ptr->protocol == prtcl)
+			break;
+		ptr++;
+	}
+
+	if (!ptr->protocol)
+		return 0;
+
+	for (i = 0; i < SRDS_MAX_LANES; i++) {
+		if (ptr->lanes[i] != NONE)
+			return 1;
+	}
+
+	return 0;
+}
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/ppa.c b/arch/arm/cpu/armv8/fsl-layerscape/ppa.c
new file mode 100644
index 0000000..f54ac3f
--- /dev/null
+++ b/arch/arm/cpu/armv8/fsl-layerscape/ppa.c
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2016 NXP Semiconductor, Inc.
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+#include <common.h>
+#include <config.h>
+#include <errno.h>
+#include <asm/system.h>
+#include <asm/types.h>
+#include <asm/arch/soc.h>
+#ifdef CONFIG_FSL_LSCH3
+#include <asm/arch/immap_lsch3.h>
+#elif defined(CONFIG_FSL_LSCH2)
+#include <asm/arch/immap_lsch2.h>
+#endif
+#ifdef CONFIG_ARMV8_SEC_FIRMWARE_SUPPORT
+#include <asm/armv8/sec_firmware.h>
+#endif
+
+int ppa_init(void)
+{
+	const void *ppa_fit_addr;
+	u32 *boot_loc_ptr_l, *boot_loc_ptr_h;
+	int ret;
+
+#ifdef CONFIG_SYS_LS_PPA_FW_IN_XIP
+	ppa_fit_addr = (void *)CONFIG_SYS_LS_PPA_FW_ADDR;
+#else
+#error "No CONFIG_SYS_LS_PPA_FW_IN_xxx defined"
+#endif
+
+#ifdef CONFIG_FSL_LSCH3
+	struct ccsr_gur __iomem *gur = (void *)(CONFIG_SYS_FSL_GUTS_ADDR);
+	boot_loc_ptr_l = &gur->bootlocptrl;
+	boot_loc_ptr_h = &gur->bootlocptrh;
+#elif defined(CONFIG_FSL_LSCH2)
+	struct ccsr_scfg __iomem *scfg = (void *)(CONFIG_SYS_FSL_SCFG_ADDR);
+	boot_loc_ptr_l = &scfg->scratchrw[1];
+	boot_loc_ptr_h = &scfg->scratchrw[0];
+#endif
+
+	debug("fsl-ppa: boot_loc_ptr_l = 0x%p, boot_loc_ptr_h =0x%p\n",
+	      boot_loc_ptr_l, boot_loc_ptr_h);
+	ret = sec_firmware_init(ppa_fit_addr, boot_loc_ptr_l, boot_loc_ptr_h);
+
+	return ret;
+}
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/soc.c b/arch/arm/cpu/armv8/fsl-layerscape/soc.c
index 0cb0100..f62b78d 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/soc.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/soc.c
@@ -12,6 +12,10 @@
 #include <asm/io.h>
 #include <asm/global_data.h>
 #include <asm/arch-fsl-layerscape/config.h>
+#ifdef CONFIG_SYS_FSL_DDR
+#include <fsl_ddr_sdram.h>
+#include <fsl_ddr.h>
+#endif
 #ifdef CONFIG_CHAIN_OF_TRUST
 #include <fsl_validate.h>
 #endif
@@ -24,7 +28,7 @@ bool soc_has_dp_ddr(void)
 	u32 svr = gur_in32(&gur->svr);
 
 	/* LS2085A has DP_DDR */
-	if (SVR_SOC_VER(svr) == SVR_LS2085)
+	if (SVR_SOC_VER(svr) == SVR_LS2085A)
 		return true;
 
 	return false;
@@ -36,7 +40,7 @@ bool soc_has_aiop(void)
 	u32 svr = gur_in32(&gur->svr);
 
 	/* LS2085A has AIOP */
-	if (SVR_SOC_VER(svr) == SVR_LS2085)
+	if (SVR_SOC_VER(svr) == SVR_LS2085A)
 		return true;
 
 	return false;
@@ -120,15 +124,6 @@ void erratum_a009635(void)
 }
 #endif	/* CONFIG_SYS_FSL_ERRATUM_A009635 */
 
-static void erratum_a008751(void)
-{
-#ifdef CONFIG_SYS_FSL_ERRATUM_A008751
-	u32 __iomem *scfg = (u32 __iomem *)SCFG_BASE;
-
-	writel(0x27672b2a, scfg + SCFG_USB3PRM1CR / 4);
-#endif
-}
-
 static void erratum_rcw_src(void)
 {
 #if defined(CONFIG_SPL)
@@ -185,7 +180,6 @@ void bypass_smmu(void)
 }
 void fsl_lsch3_early_init_f(void)
 {
-	erratum_a008751();
 	erratum_rcw_src();
 	init_early_memctl_regs();	/* tighten IFC timing */
 	erratum_a009203();
@@ -222,7 +216,7 @@ int sata_init(void)
 }
 #endif
 
-#elif defined(CONFIG_LS1043A)
+#elif defined(CONFIG_FSL_LSCH2)
 #ifdef CONFIG_SCSI_AHCI_PLAT
 int sata_init(void)
 {
@@ -271,6 +265,39 @@ static void erratum_a009660(void)
 #endif
 }
 
+static void erratum_a008850_early(void)
+{
+#ifdef CONFIG_SYS_FSL_ERRATUM_A008850
+	/* part 1 of 2 */
+	struct ccsr_cci400 __iomem *cci = (void *)CONFIG_SYS_CCI400_ADDR;
+	struct ccsr_ddr __iomem *ddr = (void *)CONFIG_SYS_FSL_DDR_ADDR;
+
+	/* disables propagation of barrier transactions to DDRC from CCI400 */
+	out_le32(&cci->ctrl_ord, CCI400_CTRLORD_TERM_BARRIER);
+
+	/* disable the re-ordering in DDRC */
+	ddr_out32(&ddr->eor, DDR_EOR_RD_REOD_DIS | DDR_EOR_WD_REOD_DIS);
+#endif
+}
+
+void erratum_a008850_post(void)
+{
+#ifdef CONFIG_SYS_FSL_ERRATUM_A008850
+	/* part 2 of 2 */
+	struct ccsr_cci400 __iomem *cci = (void *)CONFIG_SYS_CCI400_ADDR;
+	struct ccsr_ddr __iomem *ddr = (void *)CONFIG_SYS_FSL_DDR_ADDR;
+	u32 tmp;
+
+	/* enable propagation of barrier transactions to DDRC from CCI400 */
+	out_le32(&cci->ctrl_ord, CCI400_CTRLORD_EN_BARRIER);
+
+	/* enable the re-ordering in DDRC */
+	tmp = ddr_in32(&ddr->eor);
+	tmp &= ~(DDR_EOR_RD_REOD_DIS | DDR_EOR_WD_REOD_DIS);
+	ddr_out32(&ddr->eor, tmp);
+#endif
+}
+
 void fsl_lsch2_early_init_f(void)
 {
 	struct ccsr_cci400 *cci = (struct ccsr_cci400 *)CONFIG_SYS_CCI400_ADDR;
@@ -295,6 +322,7 @@ void fsl_lsch2_early_init_f(void)
 		 CCI400_DVM_MESSAGE_REQ_EN | CCI400_SNOOP_REQ_EN);
 
 	/* Erratum */
+	erratum_a008850_early(); /* part 1 of 2 */
 	erratum_a009929();
 	erratum_a009660();
 }
diff --git a/arch/arm/cpu/armv8/fsl-layerscape/spl.c b/arch/arm/cpu/armv8/fsl-layerscape/spl.c
index c1229c8..19e34fa 100644
--- a/arch/arm/cpu/armv8/fsl-layerscape/spl.c
+++ b/arch/arm/cpu/armv8/fsl-layerscape/spl.c
@@ -24,12 +24,12 @@ u32 spl_boot_device(void)
 	return 0;
 }
 
-u32 spl_boot_mode(void)
+u32 spl_boot_mode(const u32 boot_device)
 {
 	switch (spl_boot_device()) {
 	case BOOT_DEVICE_MMC1:
 #ifdef CONFIG_SPL_FAT_SUPPORT
-		return MMCSD_MODE_FAT;
+		return MMCSD_MODE_FS;
 #else
 		return MMCSD_MODE_RAW;
 #endif
@@ -49,9 +49,6 @@ void board_init_f(ulong dummy)
 #ifdef CONFIG_LS2080A
 	arch_cpu_init();
 #endif
-#ifdef CONFIG_FSL_IFC
-	init_early_memctl_regs();
-#endif
 	board_early_init_f();
 	timer_init();
 #ifdef CONFIG_LS2080A